{"meta":{"query_hash":"30a66daf5ed9","filters":{"topic":"AI in cancer detection"},"cohort_total":1463,"direct_labels_cover":4,"predictions_cover":1463,"exported":1463,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/30a66daf5ed9","api":"https://metacan.xera.ac/api/v1/cohort?topic=AI+in+cancer+detection"},"results":[{"id":"W111626876","doi":"10.1007/978-3-642-23957-1_30","title":"Segmentation of Breast Ultrasound Images Using Neural Networks","year":2011,"lang":"en","type":"book-chapter","venue":"IFIP International Federation for Information Processing/IFIP","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Scale-invariant feature transform; Segmentation; Computer science; Artificial neural network; Pattern recognition (psychology); Computer vision; Image segmentation; Set (abstract data type); Generalization; Image (mathematics); Mathematics","score_opus":0.025369205415768297,"score_gpt":0.26492428231870707,"score_spread":0.23955507690293878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W111626876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000056502107,0.00010322813,0.9256375,0.00018654989,0.002305915,0.0007372899,0.00019681164,0.00020259705,0.07057361],"genre_scores_gemma":[0.7898054,0.00022454934,0.1480441,0.0020296045,0.0028186,0.00047006,0.0054395455,0.00025182028,0.050916325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706787,0.000022467462,0.0013727328,0.0004179226,0.00085111096,0.00026789392],"domain_scores_gemma":[0.9951249,0.00011215668,0.002142026,0.00034263844,0.0021896684,0.0000886209],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042401673,0.00044355122,0.00035084644,0.000611916,0.0004728718,0.001173737,0.0007877812,0.00037910757,0.00014519916],"category_scores_gemma":[0.000064005144,0.00048133126,0.00021609143,0.00012727553,0.00011409846,0.0077817044,0.00012547214,0.00031556195,0.000026048121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005729031,0.00013123007,0.00012859848,0.00102201,0.0005217986,0.0000026891958,0.0038410842,0.075137705,0.00226154,0.32059518,0.007702526,0.58808273],"study_design_scores_gemma":[0.001580165,0.00023820702,0.00021316335,0.0005765692,0.00012819585,0.00042499238,0.00009613181,0.93386453,0.008039362,0.03283178,0.020764539,0.0012423744],"about_ca_topic_score_codex":0.00003397711,"about_ca_topic_score_gemma":0.000010302132,"teacher_disagreement_score":0.8587268,"about_ca_system_score_codex":0.0005007334,"about_ca_system_score_gemma":0.00028123133,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W1147193425","doi":"10.1109/tmi.2015.2470529","title":"Triaging Diagnostically Relevant Regions from Pathology Whole Slides of Breast Cancer: A Texture Based Approach","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Kela; Sunnybrook Research Institute","keywords":"Breast cancer; Digital pathology; Texture (cosmology); Pathology; Computer science; Medicine; Artificial intelligence; Cancer; Computer vision; Image (mathematics); Internal medicine","score_opus":0.01958976026000064,"score_gpt":0.26796877451544715,"score_spread":0.2483790142554465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1147193425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001487909,0.00034116046,0.97751796,0.018487426,0.0014297187,0.00019695275,0.000075625794,0.00027170405,0.00019156394],"genre_scores_gemma":[0.96423715,0.00009719578,0.033673346,0.0016004083,0.0001962759,0.00013506754,0.0000042988695,0.000027948347,0.000028275801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972826,0.00027879814,0.00046802376,0.0006417565,0.0009383921,0.00039043315],"domain_scores_gemma":[0.9977894,0.0007371032,0.00014923998,0.0006604594,0.00020704567,0.00045675185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062253774,0.00022640725,0.0003588382,0.00024878173,0.00015449528,0.00006303681,0.0007718975,0.00015245787,0.00006054502],"category_scores_gemma":[0.00014042448,0.00020497717,0.00014350232,0.00064168044,0.00030286238,0.00039083313,0.0000101142,0.00074358634,0.00001879628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018714242,0.00089739444,0.0004468234,0.00006141075,0.00009556673,0.00026240794,0.0019784758,0.024848966,0.0029907923,0.0003567633,0.00401305,0.9638612],"study_design_scores_gemma":[0.0025367055,0.00009083892,0.0006699357,0.00041493654,0.00009797386,0.00026867865,0.00024882547,0.9858978,0.005768609,0.001953695,0.0016608424,0.00039116136],"about_ca_topic_score_codex":0.0005879963,"about_ca_topic_score_gemma":0.0000736322,"teacher_disagreement_score":0.96347004,"about_ca_system_score_codex":0.00022656108,"about_ca_system_score_gemma":0.00066494563,"threshold_uncertainty_score":0.83587265},"labels":[],"label_agreement":null},{"id":"W1480764567","doi":"10.1007/978-3-540-68825-9_14","title":"Comparison of Pleomorphic and Structural Features Used for Breast Cancer Malignancy Classification","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Malignancy; Grading (engineering); Support vector machine; Breast cancer; Computer science; Artificial intelligence; Cancer; Pattern recognition (psychology); Medicine; Pathology; Biology; Internal medicine","score_opus":0.03646471651196816,"score_gpt":0.3026271346907655,"score_spread":0.2661624181787974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480764567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020043312,0.0018841248,0.9924786,0.00096629176,0.0017251377,0.00068053894,0.00007226518,0.00009495307,0.00009372547],"genre_scores_gemma":[0.8821803,0.00017079509,0.11690669,0.00019063267,0.00039572833,0.000036120553,0.000006263557,0.000032209,0.00008128008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968986,0.000027931763,0.00057762454,0.0012877063,0.00076136534,0.00044680142],"domain_scores_gemma":[0.99760866,0.0003603053,0.0006419115,0.00087255053,0.00040138507,0.00011516167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029307493,0.0004416753,0.00064991286,0.0005634491,0.00029977484,0.00018449966,0.0015540593,0.00034708867,0.000009210188],"category_scores_gemma":[0.000026967735,0.00040702,0.000107980835,0.0004422325,0.00087167515,0.0005225936,0.0004279456,0.00050038676,0.0000011042509],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003312215,0.000018515813,0.0024603775,0.00017789469,0.000026810443,0.0000052867695,0.002118577,0.0125497,0.0020806307,0.005655124,0.00011678543,0.9747572],"study_design_scores_gemma":[0.000820389,0.0003801389,0.04658899,0.00079592515,0.000032534652,0.0003286602,0.0000010524947,0.90433586,0.011344759,0.033818725,0.0005169572,0.0010360274],"about_ca_topic_score_codex":0.00006917841,"about_ca_topic_score_gemma":0.00026325043,"teacher_disagreement_score":0.97372115,"about_ca_system_score_codex":0.00034357284,"about_ca_system_score_gemma":0.00050818647,"threshold_uncertainty_score":0.9998382},"labels":[],"label_agreement":null},{"id":"W1511438171","doi":"10.1007/978-3-540-39903-2_40","title":"Projection-Based Needle Segmentation in 3D Ultrasound Images","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials","funders":"","keywords":"Computer science; Computer vision; Segmentation; Artificial intelligence; Projection (relational algebra); Image segmentation; Computer graphics (images); Algorithm","score_opus":0.013045012408162084,"score_gpt":0.24715458103886487,"score_spread":0.23410956863070279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511438171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011245805,0.0002377043,0.9927083,0.0004463278,0.0027663046,0.00067415636,0.000004161096,0.00017937763,0.0028712004],"genre_scores_gemma":[0.07667403,0.000052395597,0.91902876,0.00316998,0.00045792607,0.0000807351,0.000010173187,0.00006794498,0.00045804886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615866,0.00007460611,0.00056205684,0.0015897086,0.0009980213,0.00061695755],"domain_scores_gemma":[0.99776274,0.00055508316,0.00032786053,0.0010381959,0.00021141458,0.00010472112],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009355891,0.0005050776,0.00040576997,0.0014636142,0.00023052939,0.0005789252,0.0016315194,0.00031999458,0.000032639426],"category_scores_gemma":[0.00010770275,0.0005157428,0.00009715797,0.0013794457,0.00046100272,0.0009337144,0.00022841475,0.0008409628,0.000032183438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018165229,0.000089721245,0.0010686052,0.000111664034,0.000012952573,0.00007369948,0.0011747541,0.20345835,0.0034223425,0.0012650864,0.00013326704,0.7891714],"study_design_scores_gemma":[0.0015619487,0.0007160963,0.0013235972,0.0009245639,0.000019955563,0.00022423669,0.0000017415019,0.8246763,0.080001876,0.08635543,0.0019246594,0.0022696133],"about_ca_topic_score_codex":0.00012046608,"about_ca_topic_score_gemma":0.0002678721,"teacher_disagreement_score":0.7869018,"about_ca_system_score_codex":0.0013620942,"about_ca_system_score_gemma":0.00077836256,"threshold_uncertainty_score":0.9997294},"labels":[],"label_agreement":null},{"id":"W1512585278","doi":"10.1002/sam.11261","title":"Prediction using hierarchical data: Applications for automated detection of cervical cancer","year":2015,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Papanicolaou stain; Cervical cancer; Artificial intelligence; Data mining; Pattern recognition (psychology); Machine learning; Cancer; Medicine","score_opus":0.18075572576648957,"score_gpt":0.4095357243360112,"score_spread":0.22877999856952164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512585278","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039459006,0.00013102213,0.98864555,0.0005501893,0.0002650826,0.00015713759,0.0062488336,0.000050446157,0.0000058195824],"genre_scores_gemma":[0.4717241,0.000078206096,0.5271198,0.000054176755,0.00030739678,0.000010394334,0.00069756375,0.0000063296234,0.0000020011119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724835,0.00012429859,0.0005323223,0.00092400715,0.00086297543,0.0003080495],"domain_scores_gemma":[0.9954346,0.00044125193,0.00035277792,0.0031196414,0.00036547953,0.00028627086],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0058922996,0.000118291115,0.0002530214,0.0003065503,0.00082511466,0.00070520805,0.005997716,0.000044482615,0.0000059606004],"category_scores_gemma":[0.0010973244,0.00008165226,0.000021325319,0.0024475364,0.00069192145,0.0041032555,0.0039522615,0.00024836764,7.257976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022301062,0.00030445773,0.013808686,0.00008094403,0.001243338,0.0000079551055,0.0011659289,0.008027632,0.007350794,0.0054215775,0.010481947,0.95188373],"study_design_scores_gemma":[0.0001985856,0.00006657782,0.009380024,0.000011329474,0.0005668012,0.00006531797,0.00015163915,0.98687536,0.00006286104,0.0010912698,0.0014379731,0.00009224749],"about_ca_topic_score_codex":0.00051298976,"about_ca_topic_score_gemma":0.00039303928,"teacher_disagreement_score":0.97884774,"about_ca_system_score_codex":0.000100849385,"about_ca_system_score_gemma":0.0007429511,"threshold_uncertainty_score":0.9993803},"labels":[],"label_agreement":null},{"id":"W1518212064","doi":"10.1007/11559573_117","title":"Suppression of Stripe Artifacts in Mammograms Using Weighted Median Filtering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Median filter; Artificial intelligence; Computer vision; Algorithm; Image processing; Image (mathematics)","score_opus":0.023598017720119806,"score_gpt":0.2576725451081746,"score_spread":0.23407452738805481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518212064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047355,0.0002608295,0.99148285,0.0002587629,0.002261642,0.00036547656,0.000003977366,0.00010157263,0.0005293667],"genre_scores_gemma":[0.4870765,0.000046285557,0.51220965,0.00018092977,0.0004062071,0.0000051258726,0.0000027838907,0.00003283386,0.00003969141],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960461,0.00004951651,0.00077576947,0.0013320021,0.0011062473,0.0006903532],"domain_scores_gemma":[0.9976672,0.00028620794,0.0004703302,0.001246321,0.00016774559,0.00016218059],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072607887,0.00047527492,0.0005846945,0.0014203562,0.00012027598,0.00022380607,0.0024487718,0.0004046926,0.00003580883],"category_scores_gemma":[0.000052292886,0.00045919462,0.00011209755,0.0010701254,0.0004663355,0.00091138005,0.0011796246,0.0008603421,0.000008531116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001039014,0.000024831263,0.00020579001,0.000050075345,0.0000054881657,0.00005250117,0.0006511657,0.059004735,0.0039054381,0.00046263973,0.0000031324885,0.9356238],"study_design_scores_gemma":[0.00034513918,0.00014446682,0.00029901028,0.0012866692,0.0000059797026,0.000063362335,3.4368216e-7,0.93108267,0.03823976,0.027321102,0.0006220862,0.0005894108],"about_ca_topic_score_codex":0.00011887874,"about_ca_topic_score_gemma":0.0003111711,"teacher_disagreement_score":0.9350344,"about_ca_system_score_codex":0.0007164397,"about_ca_system_score_gemma":0.0004988168,"threshold_uncertainty_score":0.99978596},"labels":[],"label_agreement":null},{"id":"W1519980098","doi":"10.1109/icassp.2015.7178095","title":"Blind stain decomposition for histo-pathology images using circular nature of chroma components","year":2015,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stain; Hue; Artificial intelligence; Segmentation; Histogram; Computer science; Pattern recognition (psychology); Computer vision; Thresholding; Pathology; Staining; Image (mathematics); Medicine","score_opus":0.04651017758345501,"score_gpt":0.3307822388623806,"score_spread":0.2842720612789256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519980098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2749192,0.00022888475,0.72355235,0.0002096393,0.0006176754,0.0001940586,0.000003958364,0.00006049035,0.00021376793],"genre_scores_gemma":[0.779739,0.0000016695545,0.22001734,0.00012705012,0.00006383671,0.000009188677,0.0000054576076,0.000007779211,0.000028653627],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990747,0.00006650422,0.00019766089,0.00028692017,0.0002012497,0.00017294734],"domain_scores_gemma":[0.99916434,0.0000440189,0.00013671718,0.00033162948,0.00025962395,0.00006366988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000328526,0.00009589346,0.00015821299,0.00013530445,0.0000626418,0.000029331019,0.00035038037,0.00014018793,0.0000034920504],"category_scores_gemma":[0.00002836938,0.0000960606,0.000056672026,0.00019045747,0.000053240907,0.0003528,0.00010917729,0.00011492322,0.0000028126271],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018277744,0.00021246038,0.00079692027,0.00013058884,0.0000563032,0.000035871573,0.0007663492,0.002610877,0.97190726,0.0090279095,0.0032308383,0.011041852],"study_design_scores_gemma":[0.003943041,0.0007629204,0.0035769262,0.00005498862,0.0000442454,0.00036752698,0.00008720637,0.49162006,0.47034156,0.024694227,0.0040183594,0.00048893114],"about_ca_topic_score_codex":0.000047562582,"about_ca_topic_score_gemma":0.0000047482404,"teacher_disagreement_score":0.5048198,"about_ca_system_score_codex":0.00029436048,"about_ca_system_score_gemma":0.0000922983,"threshold_uncertainty_score":0.39172375},"labels":[],"label_agreement":null},{"id":"W1528741131","doi":"10.1007/978-3-319-18305-3_1","title":"What Is Machine Learning?","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":752,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Context (archaeology); Machine learning; Artificial intelligence; Radiation therapy; Reinforcement learning; Medicine","score_opus":0.03534761703590294,"score_gpt":0.2577465307629128,"score_spread":0.22239891372700987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528741131","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2100252e-7,0.0042298324,0.11495691,0.0014693057,0.0026073575,0.000110859575,0.0000013962072,0.00044733516,0.8761768],"genre_scores_gemma":[0.00009880597,0.0012074509,0.0041989526,0.00087817863,0.00026951256,0.0000039014576,0.0000041635785,0.00003310157,0.9933059],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866825,0.000011579926,0.00017977484,0.00050871505,0.00046820164,0.0001634914],"domain_scores_gemma":[0.9989171,0.000026671103,0.00014299936,0.00066172617,0.00014676212,0.000104732455],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019350812,0.00023310354,0.0002098835,0.000121984514,0.00006201114,0.00032536057,0.00072438974,0.00024329146,0.0014041436],"category_scores_gemma":[0.000005015878,0.00021226562,0.00009228251,0.00003519722,0.000034702338,0.0007554663,0.00040642155,0.00049614295,0.002080343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060532366,0.000005687649,0.0000044327435,0.000022412029,0.000061929815,0.000024032692,0.00046196626,0.00004834344,0.000004977748,0.33264542,0.12160106,0.5451137],"study_design_scores_gemma":[0.000086098924,0.00010339451,4.8877655e-7,0.000047773665,0.000006788601,0.000023053453,0.000002742422,0.009267951,0.00006923156,0.060856726,0.9292904,0.00024531898],"about_ca_topic_score_codex":0.0000369144,"about_ca_topic_score_gemma":0.000029689523,"teacher_disagreement_score":0.80768937,"about_ca_system_score_codex":0.00019457273,"about_ca_system_score_gemma":0.000101059035,"threshold_uncertainty_score":0.9995087},"labels":[],"label_agreement":null},{"id":"W1543519699","doi":"10.1002/0470094168.ch15","title":"The Roadmap for Recognizing Regions of Interest in Medical Images","year":2005,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Data science; Cartography; Geography","score_opus":0.06834866045234671,"score_gpt":0.315082539177281,"score_spread":0.2467338787249343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543519699","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015563049,0.0007938145,0.63193154,0.005475052,0.00088776293,0.00027456175,0.0000025320967,0.00013144086,0.36050174],"genre_scores_gemma":[0.0015096611,0.0014400899,0.07369251,0.0004590038,0.0010306637,0.00015823278,0.0000021918102,0.00016765084,0.92154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992224,0.000037805294,0.0002133181,0.00023939255,0.00013129348,0.0001558117],"domain_scores_gemma":[0.99912316,0.00025004288,0.00014643432,0.00041725804,0.000025910616,0.000037186568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036545823,0.00009810245,0.00014552413,0.00013842435,0.00002910828,0.00003137159,0.00090418506,0.00017036332,0.0002467006],"category_scores_gemma":[0.00014218727,0.000066177716,0.000059503156,0.00016374802,0.00007864146,0.000055037537,0.00015976303,0.00016712619,0.000014607882],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002200217,0.000009835414,0.000004874415,0.000016016274,0.000010500244,8.764866e-7,0.000028270611,4.100453e-7,0.000004311362,0.008962753,0.5802756,0.41068435],"study_design_scores_gemma":[0.00020810777,0.00004198765,0.000020579158,0.00032295592,0.000003047899,0.000008084791,0.000021657705,0.0027172929,0.00036335105,0.0022166164,0.9939637,0.00011259464],"about_ca_topic_score_codex":0.0002285516,"about_ca_topic_score_gemma":0.014238801,"teacher_disagreement_score":0.56103826,"about_ca_system_score_codex":0.00005168793,"about_ca_system_score_gemma":0.00010684382,"threshold_uncertainty_score":0.7945585},"labels":[],"label_agreement":null},{"id":"W1561324538","doi":"10.1155/2004/238769","title":"Quantitative Histopathological Analysis of Cervical Intra‐Epithelial Neoplasia Sections: Methodological Issues","year":2003,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Cancer Institute","keywords":"Pathology; Medicine","score_opus":0.0847497381561954,"score_gpt":0.34715363434456986,"score_spread":0.26240389618837445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561324538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1938145,0.0004220525,0.8018959,0.0007220848,0.00045478457,0.00013203101,0.00000908423,0.00014129162,0.0024082798],"genre_scores_gemma":[0.8256478,0.00007676413,0.1736919,0.000255737,0.000052868065,0.000024420433,0.000008966311,0.000012513138,0.00022908406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99455804,0.0026312636,0.0008039756,0.001028794,0.0004364155,0.0005415045],"domain_scores_gemma":[0.9971292,0.0012805734,0.0002621533,0.000876113,0.00025861675,0.0001933369],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019079216,0.00029931197,0.0010605523,0.00069686334,0.00015195365,0.00004191018,0.0007144603,0.00045786542,0.00039596626],"category_scores_gemma":[0.0019115992,0.00025365062,0.0005512195,0.0028984987,0.0006226708,0.00019692442,0.0002026562,0.0005417361,0.000084038984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110196095,0.00048887165,0.0050101546,0.000022984,0.00058066234,0.000996125,0.00070412905,0.0020512922,0.03566059,0.9517989,0.00019987476,0.002376182],"study_design_scores_gemma":[0.0022109628,0.007990784,0.05199932,0.00003091045,0.005049681,0.0015870115,0.00081283465,0.59119356,0.13303278,0.1839488,0.01979536,0.0023479916],"about_ca_topic_score_codex":0.0000382712,"about_ca_topic_score_gemma":0.000031727042,"teacher_disagreement_score":0.76785016,"about_ca_system_score_codex":0.0001423477,"about_ca_system_score_gemma":0.000084708896,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W1573405790","doi":"10.1007/978-3-540-74260-9","title":"Image analysis and recognition : 4th International Conference, ICIAR 2007 Montreal, Canada, August 22-24, 2007 : proceedings","year":2007,"lang":"en","type":"book","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Political science; Media studies; History; Computer science; Sociology","score_opus":0.01656934670163446,"score_gpt":0.2359065417551571,"score_spread":0.21933719505352264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573405790","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007574932,0.000107464075,0.17037033,0.00026647377,0.0016061274,0.00028479678,0.00010385445,0.00019328078,0.8269919],"genre_scores_gemma":[0.0009931988,0.0006174991,0.030946115,0.0011248764,0.0013024636,0.000043665408,0.00031086997,0.000054785894,0.9646065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687034,0.00001596133,0.0005869222,0.0010425046,0.0010249884,0.00045925734],"domain_scores_gemma":[0.9976786,0.00008320216,0.0005087252,0.00033992835,0.0011334869,0.00025609383],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045047697,0.00045119377,0.00051471597,0.0010332826,0.00014762781,0.00048701678,0.0009012864,0.0003786745,0.0027335335],"category_scores_gemma":[0.00003687492,0.00046791963,0.00014333634,0.0006241096,0.00011879484,0.00082793576,0.00031551864,0.0005650246,0.00005135172],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023434433,0.000022219896,0.00016622918,0.000043549095,0.0006338295,0.000040157065,0.0000727294,0.0000020542827,0.0000166283,0.0013093153,0.9414139,0.056255948],"study_design_scores_gemma":[0.0016074829,0.00033216056,0.009336681,0.00045927387,0.0018565938,0.00018913606,0.00025979689,0.10659245,0.0007938661,0.032899052,0.8422257,0.0034478593],"about_ca_topic_score_codex":0.38239542,"about_ca_topic_score_gemma":0.65271217,"teacher_disagreement_score":0.27031675,"about_ca_system_score_codex":0.0014950591,"about_ca_system_score_gemma":0.0014878956,"threshold_uncertainty_score":0.99977726},"labels":[],"label_agreement":null},{"id":"W1576189204","doi":"10.5772/17984","title":"On Redefining Telemedicine Paradigm: An Innovative Integrated Model for Efficient Implementation of Healthcare Delivery in Developing Countries","year":2011,"lang":"en","type":"book-chapter","venue":"InTech eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Telemedicine; Healthcare delivery; Health care; Business; Process management; Knowledge management; Computer science; Economic growth; Economics","score_opus":0.06943664021658154,"score_gpt":0.3229026053134446,"score_spread":0.2534659650968631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576189204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032223202,0.00007278277,0.98766136,0.0003363808,0.00040890585,0.0012020133,0.00008326902,0.0001426729,0.0068702754],"genre_scores_gemma":[0.9619081,0.000051538424,0.034624904,0.0011820907,0.00006578919,0.00029060998,0.000077905555,0.00007928229,0.0017198039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99782676,0.000028635734,0.00087409694,0.00061069604,0.00036068595,0.00029915888],"domain_scores_gemma":[0.99796027,0.00013313096,0.0006647932,0.0004583789,0.0007348426,0.000048565005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053809833,0.0003423827,0.00046567962,0.0007771244,0.000089089546,0.000029080593,0.0005200411,0.00025939746,0.000006838748],"category_scores_gemma":[0.000020068745,0.00033493267,0.000053040276,0.000110022615,0.00011846738,0.00009682067,0.00012503669,0.0004114478,0.0000022766344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016772456,0.000008362566,0.000008085399,0.0001490349,0.000041746964,0.0000048215065,0.008146481,0.00012972111,0.00023710984,0.88798064,0.0000399311,0.10308636],"study_design_scores_gemma":[0.004004679,0.006122842,0.000070150054,0.008707652,0.000065145505,0.00003854731,0.00097080384,0.14736389,0.20369647,0.60585696,0.020839037,0.0022638133],"about_ca_topic_score_codex":0.0006347492,"about_ca_topic_score_gemma":0.0014401532,"teacher_disagreement_score":0.95868576,"about_ca_system_score_codex":0.00089614704,"about_ca_system_score_gemma":0.0011120037,"threshold_uncertainty_score":0.9999103},"labels":[],"label_agreement":null},{"id":"W1581431793","doi":"10.1007/978-3-642-02611-9","title":"Image analysis and recognition : 6th International Conference, ICIAR 2009, Halifax, Canada, July 6-8, 2009 : proceedings","year":2009,"lang":"en","type":"book","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Pattern recognition (psychology)","score_opus":0.014228874210387966,"score_gpt":0.2251877527574318,"score_spread":0.21095887854704384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581431793","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003483732,0.00012069934,0.12795955,0.0013193705,0.0005333696,0.0002962516,0.0001908477,0.00021887089,0.8693262],"genre_scores_gemma":[0.00263509,0.00070995133,0.05638425,0.0026451556,0.0010310402,0.000055968336,0.00047334412,0.00005134049,0.9360139],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973478,0.000018961533,0.0004903645,0.0009421528,0.00086170674,0.00033903462],"domain_scores_gemma":[0.9980977,0.000041394458,0.00044528293,0.0003034199,0.00092987524,0.00018231386],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026060926,0.000399503,0.00047815763,0.0007634359,0.00013553923,0.0005583241,0.0008677695,0.00028016334,0.0004265053],"category_scores_gemma":[0.000032497053,0.00041081037,0.00013268126,0.00058741035,0.000068412104,0.0008024221,0.00018644145,0.00047011956,0.000049637412],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013890475,0.000023543547,0.000035932226,0.00003425577,0.00054591824,0.000025573103,0.000109574794,0.000003778518,0.000042781972,0.002050174,0.8805193,0.116595335],"study_design_scores_gemma":[0.00097381684,0.00036730166,0.0031811034,0.00039469925,0.0013455107,0.00014249727,0.000060824837,0.09088086,0.0011335775,0.07829538,0.82063836,0.0025860458],"about_ca_topic_score_codex":0.07441974,"about_ca_topic_score_gemma":0.29718885,"teacher_disagreement_score":0.22276911,"about_ca_system_score_codex":0.00090922083,"about_ca_system_score_gemma":0.0015705602,"threshold_uncertainty_score":0.99983436},"labels":[],"label_agreement":null},{"id":"W1597221361","doi":"10.1007/978-3-642-13681-8_68","title":"A New Preprocessing Filter for Digital Mammograms","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Carleton University","funders":"","keywords":"Adaptive histogram equalization; Computer science; Preprocessor; Artificial intelligence; Computer vision; Filter (signal processing); Histogram equalization; Segmentation; Adaptive filter; Median filter; Noise (video); Pattern recognition (psychology); Histogram; Image segmentation; Edge-preserving smoothing; Bilateral filter; Image processing; Image (mathematics); Algorithm","score_opus":0.01623168453621582,"score_gpt":0.24816024041653767,"score_spread":0.23192855588032185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597221361","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021336142,0.00021303813,0.9919435,0.00071414263,0.0038189644,0.00061662996,0.000007867439,0.00031401715,0.0023505092],"genre_scores_gemma":[0.027213601,0.0000076011966,0.9683344,0.0008237132,0.0017263012,0.000029004603,0.0000063138646,0.00006327492,0.0017957888],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959711,0.0000073564875,0.00048375814,0.0019567555,0.0008473638,0.0007336915],"domain_scores_gemma":[0.99717337,0.00039643294,0.00033712896,0.0015746328,0.00027148804,0.00024695185],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004724027,0.0005373915,0.00044506753,0.00058908365,0.0003178311,0.0020950958,0.003482842,0.0004915775,0.00002271537],"category_scores_gemma":[0.00012214872,0.0005075508,0.00019375239,0.00051885255,0.00043852543,0.0015933127,0.0011410263,0.0009710684,0.000035247882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007877588,0.000008669712,0.000015941569,0.000041079707,0.000006534938,0.000009259195,0.00035578362,0.0015323813,0.00023450711,0.0015998906,0.000043465898,0.9961446],"study_design_scores_gemma":[0.00058344833,0.00040528382,0.000037821104,0.00059503806,0.000013896064,0.00019299294,1.2626363e-7,0.29068512,0.011001818,0.65858376,0.036592603,0.0013081032],"about_ca_topic_score_codex":0.000016807122,"about_ca_topic_score_gemma":0.000081737264,"teacher_disagreement_score":0.9948365,"about_ca_system_score_codex":0.00029689693,"about_ca_system_score_gemma":0.0010345423,"threshold_uncertainty_score":0.9997376},"labels":[],"label_agreement":null},{"id":"W1601572767","doi":"10.5220/0002997600880093","title":"BREAST MASS DETECTION USING BILATERAL FILTER AND MEAN SHIFT BASED CLUSTERING","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Cluster analysis; Mammography; Image segmentation; Mean-shift; Filter (signal processing); Pixel; Segmentation; Computer vision; Feature extraction; Artificial neural network; Feature vector; Breast cancer; Cancer","score_opus":0.016179289830896667,"score_gpt":0.2316211926397184,"score_spread":0.21544190280882172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601572767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34531745,0.000001288158,0.6534056,0.00015610206,0.0007253756,0.000054791017,5.4399226e-7,0.0001377561,0.00020110213],"genre_scores_gemma":[0.90559393,1.9776925e-7,0.094103396,0.00013214708,0.0001284306,0.0000039523807,1.78069e-7,0.0000086970185,0.000029075974],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923754,0.00002475295,0.000119684926,0.0003018193,0.00013425674,0.00018193276],"domain_scores_gemma":[0.9995337,0.000023390341,0.0000432346,0.00030245841,0.000028727523,0.00006844736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016842053,0.00010113052,0.000074265685,0.000104023195,0.00013592467,0.00021759579,0.00018621261,0.0000694825,0.000045463745],"category_scores_gemma":[0.0000027741225,0.00009192646,0.000026522448,0.00016211161,0.00003056788,0.0005918758,0.0001017992,0.00016872311,0.000007598518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003559454,0.000019609275,0.0043684645,0.000038411257,0.000013963412,0.000009749437,0.0004759145,0.0019449936,0.75283617,0.0002604564,0.000010690662,0.23998597],"study_design_scores_gemma":[0.00020646519,0.000028949857,0.007645812,0.000007597234,0.0000032286218,0.00014776469,0.00000397471,0.9291534,0.06213817,0.00042786964,0.00010024153,0.00013655968],"about_ca_topic_score_codex":0.0002746744,"about_ca_topic_score_gemma":0.00089166197,"teacher_disagreement_score":0.92720836,"about_ca_system_score_codex":0.00004293849,"about_ca_system_score_gemma":0.000021143496,"threshold_uncertainty_score":0.3748652},"labels":[],"label_agreement":null},{"id":"W1623194643","doi":"10.1016/j.bbe.2015.07.002","title":"Classification of abnormalities in mammograms by new asymmetric fractal features","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fractal; Pattern recognition (psychology); Mammography; Medicine; Artificial intelligence; Radiology; Support vector machine; Malignancy; Wavelet; Lesion; Biopsy; Breast cancer; Computer science; Mathematics; Cancer; Pathology","score_opus":0.020445324190910066,"score_gpt":0.26278246254212984,"score_spread":0.24233713835121978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1623194643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35848153,0.00719622,0.5964675,0.014110513,0.004098652,0.0005706071,0.0000067946066,0.00009919206,0.018968986],"genre_scores_gemma":[0.98942107,0.00007601377,0.009899538,0.00014551499,0.00035969756,0.0000015874926,0.000001972934,0.0000060084462,0.000088576955],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851245,0.000021517551,0.00053638447,0.00012231297,0.000659288,0.0001480303],"domain_scores_gemma":[0.99880964,0.00006987188,0.0006142669,0.00019007834,0.0001503265,0.0001658322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080465036,0.00009670546,0.00025911847,0.00069194887,0.000014024272,0.000024718769,0.00046554458,0.00008396031,0.0000033852766],"category_scores_gemma":[0.000047694775,0.000073597614,0.000039514827,0.0014827244,0.00007018784,0.00026583346,0.00004624506,0.00024047369,0.000002583407],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004521801,0.00025321366,0.0020859612,0.000056806064,0.000069929105,0.000022564709,0.0032373723,0.00008274503,0.048757676,0.0048841583,0.16188242,0.778215],"study_design_scores_gemma":[0.031066248,0.011395489,0.2858835,0.0008992827,0.00022963139,0.0016741852,0.012685926,0.009306155,0.25703672,0.06728096,0.32089728,0.0016446214],"about_ca_topic_score_codex":0.00010814181,"about_ca_topic_score_gemma":0.000008279569,"teacher_disagreement_score":0.7765704,"about_ca_system_score_codex":0.0001797361,"about_ca_system_score_gemma":0.00020925376,"threshold_uncertainty_score":0.30012235},"labels":[],"label_agreement":null},{"id":"W1696053030","doi":"10.1007/s00428-015-1834-4","title":"Does standardised structured reporting contribute to quality in diagnostic pathology? The importance of evidence-based datasets","year":2015,"lang":"en","type":"review","venue":"Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin","topic":"AI in cancer detection","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Partnership Against Cancer","funders":"","keywords":"Benchmarking; eHealth; Medicine; CLARITY; Population health; Population; Comparability; Interoperability; Data quality; Health care; Data science; Pathology; Computer science; Environmental health; Business; World Wide Web","score_opus":0.18225910412897958,"score_gpt":0.47194136592103675,"score_spread":0.28968226179205714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1696053030","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018416065,0.9440543,0.043463647,0.0019477136,0.002164652,0.0041360217,0.0019486698,0.00033274275,0.000110625595],"genre_scores_gemma":[0.02711487,0.9519827,0.016604094,0.0017098734,0.0005864861,0.00089776044,0.00097339676,0.00011046699,0.000020392932],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98312896,0.0055796336,0.0058949073,0.0026065556,0.0014147137,0.0013752239],"domain_scores_gemma":[0.9667994,0.01970336,0.007667767,0.004959303,0.00042394054,0.00044623518],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018152842,0.0012565162,0.0048819343,0.00061129563,0.0002866339,0.000118749216,0.004922211,0.0007938799,0.000015760455],"category_scores_gemma":[0.07178707,0.00059228996,0.00078589487,0.0021143602,0.001403712,0.0004728968,0.002076865,0.0024978733,0.000020587224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025737632,0.00020685952,0.002180436,0.004617071,0.00038549106,0.0013985522,0.000666814,0.0006846974,0.0001776019,0.0015953023,0.0028963978,0.9849334],"study_design_scores_gemma":[0.0049450747,0.0034986453,0.01636391,0.03906371,0.0030264417,0.00017000009,0.000573339,0.0016369197,0.0013529652,0.0517203,0.87282753,0.0048211943],"about_ca_topic_score_codex":0.00021241547,"about_ca_topic_score_gemma":0.0003223972,"teacher_disagreement_score":0.9801122,"about_ca_system_score_codex":0.00050274306,"about_ca_system_score_gemma":0.0031657515,"threshold_uncertainty_score":0.9998034},"labels":[],"label_agreement":null},{"id":"W1707563711","doi":"10.2196/ijmr.3495","title":"A Virtual Microscope for Academic Medical Education: The Pate Project","year":2015,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Virtual microscopy; Telepathology; Set (abstract data type); Medical education; Scope (computer science); Sample (material); Psychology; Computer science; Mathematics education; Medicine; Pathology; Health care; Telemedicine; Political science; Chemistry","score_opus":0.16696862886905478,"score_gpt":0.5383615392905717,"score_spread":0.37139291042151695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1707563711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077113435,0.0020050493,0.61809695,0.29095036,0.00930992,0.0009767794,0.000002966875,0.000035353198,0.0015091923],"genre_scores_gemma":[0.9872799,0.0006588818,0.0030365682,0.0032983352,0.0047935983,0.00015806456,7.8268846e-7,0.000024982253,0.0007488777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918969,0.0010266207,0.00057364645,0.00024018557,0.0058625196,0.00040008192],"domain_scores_gemma":[0.9925766,0.0035624618,0.0002815376,0.00031068386,0.0025595264,0.00070921873],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01845112,0.00010354675,0.00021054744,0.00035877642,0.00015204564,0.00016007245,0.0034341037,0.0002398493,0.000107305284],"category_scores_gemma":[0.033976067,0.000060860268,0.00010960216,0.00068680046,0.00037291733,0.00070987386,0.00061659835,0.0034264172,0.00003667741],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005231535,0.00020811688,0.000063471794,0.000014210378,0.000066993874,0.000060221795,0.0038390474,0.0000026320324,0.00021515794,0.0037731032,0.38161036,0.6096235],"study_design_scores_gemma":[0.0025748748,0.0039050397,0.00017799281,0.0014741567,0.000013654308,0.0033226113,0.00475214,0.028732339,0.0068801926,0.015377834,0.93258256,0.00020659657],"about_ca_topic_score_codex":0.0001174075,"about_ca_topic_score_gemma":0.00002303554,"teacher_disagreement_score":0.9101665,"about_ca_system_score_codex":0.000609144,"about_ca_system_score_gemma":0.017686505,"threshold_uncertainty_score":0.9988727},"labels":[],"label_agreement":null},{"id":"W1711370505","doi":"","title":"Classification of breast masses via transformation of features using kernel principal component analysis","year":2007,"lang":"en","type":"article","venue":"International Conference on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pattern recognition (psychology); Kernel principal component analysis; Artificial intelligence; Feature extraction; Principal component analysis; Kernel (algebra); Linear discriminant analysis; Computer science; Feature (linguistics); Transformation (genetics); Feature vector; Kernel Fisher discriminant analysis; Receiver operating characteristic; Mathematics; Kernel method; Support vector machine; Machine learning","score_opus":0.029326346865451602,"score_gpt":0.2929556657441522,"score_spread":0.2636293188787006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1711370505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14624292,0.000006994473,0.8525739,0.0002816017,0.00038400936,0.00006019843,0.000013429639,0.000044240343,0.000392725],"genre_scores_gemma":[0.98456043,0.0000072513994,0.015329075,0.0000097473385,0.000058774105,0.0000028627176,0.000022252447,0.0000047794188,0.000004834634],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985497,0.000013384225,0.00043693808,0.00018845047,0.0006762078,0.00013529483],"domain_scores_gemma":[0.9992647,0.00006756249,0.00019156079,0.0001780518,0.00022518479,0.00007292799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035951048,0.00010506506,0.00017092944,0.00067268685,0.000019510517,0.000024134553,0.00045680744,0.00008311716,0.000030659943],"category_scores_gemma":[0.000024060646,0.00010150845,0.00009280694,0.00065434363,0.000054675034,0.00024203461,0.000042068743,0.00013058922,0.0000013469345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000902999,0.00024021874,0.0013345097,0.00009417487,0.00055400014,0.000004872034,0.00074187486,0.025726225,0.7528406,0.16650811,0.0000055821106,0.051859543],"study_design_scores_gemma":[0.00018310593,0.000044838922,0.08623104,0.0000588313,0.000026053,0.000016586777,0.000030178446,0.8941827,0.018897662,0.00015290617,0.00008444997,0.000091689486],"about_ca_topic_score_codex":0.00008189799,"about_ca_topic_score_gemma":0.000009371701,"teacher_disagreement_score":0.8684564,"about_ca_system_score_codex":0.000159281,"about_ca_system_score_gemma":0.00004634241,"threshold_uncertainty_score":0.41393945},"labels":[],"label_agreement":null},{"id":"W1739199097","doi":"10.1007/978-3-642-02611-9_79","title":"Region, Lesion and Border-Based Multiresolution Analysis of Mammogram Lesions","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Thresholding; Wavelet; Computer science; Wavelet transform; Computer vision; Contextual image classification; Entropy (arrow of time); Principal component analysis; Image texture; Co-occurrence matrix; Segmentation; Image segmentation; Image (mathematics); Physics","score_opus":0.02490377545372607,"score_gpt":0.27942231627082936,"score_spread":0.2545185408171033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1739199097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004943187,0.0006248724,0.9966818,0.0008833965,0.0004805852,0.0003127783,0.000004124674,0.00014439822,0.00037373474],"genre_scores_gemma":[0.60586005,0.00016921967,0.3928799,0.0007440949,0.00014318066,0.000008328274,0.000010078261,0.000024779345,0.0001603402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661595,0.00004744662,0.00058044784,0.0014203412,0.0008950171,0.00044078418],"domain_scores_gemma":[0.99728984,0.0003803627,0.0004903171,0.0013599758,0.00033387664,0.00014565022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006167262,0.00041783066,0.0006469528,0.0025615278,0.0002655327,0.000200586,0.0014963112,0.0003674964,0.0000055729015],"category_scores_gemma":[0.00007560702,0.00040015279,0.0002120918,0.0023991866,0.0006960592,0.00040837063,0.00046661714,0.00050715567,0.000002119072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008780164,0.000027582182,0.0001969571,0.000020318876,0.000029320545,0.000016260017,0.00014863163,0.08092122,0.00012416617,0.0018092451,0.000008694868,0.9166888],"study_design_scores_gemma":[0.00025976758,0.00029862422,0.0042972486,0.00026828222,0.000113519774,0.000015641226,1.2348117e-7,0.9777788,0.0011634585,0.014511637,0.00084467867,0.0004482107],"about_ca_topic_score_codex":0.000109105335,"about_ca_topic_score_gemma":0.00030612026,"teacher_disagreement_score":0.91624063,"about_ca_system_score_codex":0.0003356908,"about_ca_system_score_gemma":0.00038900579,"threshold_uncertainty_score":0.999845},"labels":[],"label_agreement":null},{"id":"W1776789407","doi":"10.1089/tmj.2014.9976","title":"ATA Clinical Guidelines for Telepathology","year":2014,"lang":"en","type":"article","venue":"Telemedicine Journal and e-Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"","keywords":"Telepathology; Library science; Gerontology; Medicine; Health care; Telemedicine; Computer science; Political science; Law","score_opus":0.22832020441943296,"score_gpt":0.48492628023976575,"score_spread":0.2566060758203328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1776789407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003038159,0.0016966561,0.8113,0.18162589,0.0020334946,0.00014575274,9.497663e-7,0.0000545196,0.000104582476],"genre_scores_gemma":[0.15345123,0.012445412,0.67099607,0.14513716,0.01727814,0.000024953073,0.0000052777727,0.000037527014,0.0006242045],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981233,0.00015984892,0.0008938548,0.0002660102,0.00020999652,0.0003469987],"domain_scores_gemma":[0.9985086,0.00017325273,0.00045524613,0.00024731908,0.00027578394,0.0003398269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070606265,0.000107760476,0.00037107652,0.00010229169,0.00031348894,0.00003820007,0.00034365716,0.00005575169,0.000008748147],"category_scores_gemma":[0.0005073679,0.00007587171,0.000061274994,0.00013034261,0.00006864196,0.00015573243,0.000086779946,0.00032356274,0.000004885258],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081528315,0.000012664266,0.00167844,0.00002536687,0.000006603137,0.0000012752043,0.00010144956,0.000002746604,0.00000788628,0.0011190344,0.21396731,0.7830691],"study_design_scores_gemma":[0.0028760587,0.0062310477,0.032104474,0.00019984378,0.000011086091,0.0022096587,0.00010601854,0.045541745,0.000018785004,0.02125717,0.88923883,0.00020526184],"about_ca_topic_score_codex":0.000043966855,"about_ca_topic_score_gemma":0.00003369282,"teacher_disagreement_score":0.7828638,"about_ca_system_score_codex":0.000055998567,"about_ca_system_score_gemma":0.00024819624,"threshold_uncertainty_score":0.30939585},"labels":[],"label_agreement":null},{"id":"W1851207850","doi":"10.1007/978-3-642-13498-2_43","title":"Computer-Aided Detection and Classification of Masses in Digitized Mammograms Using Artificial Neural Network","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Preprocessor; Artificial intelligence; CAD; Pattern recognition (psychology); Artificial neural network; Computer-aided diagnosis; Gray level; Noise (video); Computer vision; Image (mathematics)","score_opus":0.03281826650673853,"score_gpt":0.260889094934732,"score_spread":0.22807082842799348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1851207850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024415905,0.00013788488,0.9710226,0.00014657782,0.0035135192,0.00049723947,0.0000022425295,0.00014014798,0.00012385196],"genre_scores_gemma":[0.70267344,0.000017459975,0.29645815,0.00011228134,0.0006973387,0.000007802325,0.000001946276,0.000026465234,0.0000051572733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963715,0.00007450727,0.0008318214,0.0013983682,0.0007346261,0.000589183],"domain_scores_gemma":[0.9976554,0.0004376069,0.00062200736,0.00093790353,0.00022649828,0.00012058436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009195552,0.00046243053,0.0005999278,0.0008633621,0.00023282353,0.0004981669,0.0012569021,0.0004986651,0.0000041601966],"category_scores_gemma":[0.00005042238,0.00047728553,0.00010141634,0.0010831151,0.00083505217,0.0008248375,0.00072960556,0.0010854164,0.0000022867523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024959303,0.000023856433,0.0002867819,0.00004649262,0.0000065820063,0.000015337033,0.00020302569,0.07439079,0.011235814,0.002774913,4.7486395e-7,0.91099095],"study_design_scores_gemma":[0.00022999685,0.00019211271,0.0021417271,0.00024383898,0.00000844034,0.000080675505,2.0774111e-7,0.89447266,0.005127006,0.097004846,0.0000778849,0.000420622],"about_ca_topic_score_codex":0.00008621232,"about_ca_topic_score_gemma":0.0009203485,"teacher_disagreement_score":0.9105704,"about_ca_system_score_codex":0.0003367624,"about_ca_system_score_gemma":0.00027748145,"threshold_uncertainty_score":0.9997679},"labels":[],"label_agreement":null},{"id":"W1875130055","doi":"10.4137/bii.s2222","title":"Avoiding Pitfalls in the Statistical Analysis of Heterogeneous Tumors","year":2009,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University Health Network","funders":"National Cancer Institute","keywords":"Context (archaeology); Computer science; Feature (linguistics); Focus (optics); Sample (material); Data science; Biology","score_opus":0.016836428194098293,"score_gpt":0.2720042407984965,"score_spread":0.2551678126043982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1875130055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14169294,0.000059868078,0.8565897,0.00025866262,0.00014342475,0.00012480596,0.000005163578,0.000045102148,0.0010803638],"genre_scores_gemma":[0.9835453,0.000019972369,0.015532681,0.00085517316,0.00002739174,0.000004686636,0.000010249969,0.0000019136946,0.0000026228481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809456,0.00013470107,0.0007253651,0.00011263402,0.0007126206,0.00022011931],"domain_scores_gemma":[0.9988458,0.00041710938,0.00018693341,0.0004166981,0.00004590627,0.00008753919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068182405,0.000110553505,0.00025932485,0.0005783273,0.000098067445,0.0000743689,0.00085435994,0.000080830265,0.000011435321],"category_scores_gemma":[0.00015177809,0.00007164548,0.00007678864,0.0022393102,0.00012458095,0.0003049736,0.00007408918,0.00027868312,0.000011808681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055188855,0.0011036004,0.0003588081,0.00017856254,0.00070947845,0.00029280514,0.12190196,0.0075454377,0.0009737615,0.49464193,0.0025923054,0.36964616],"study_design_scores_gemma":[0.00037577492,0.00047829348,0.009451386,0.000053935055,0.000097452525,0.000049745566,0.00052256166,0.9687493,0.0011831555,0.014734963,0.004051861,0.0002515797],"about_ca_topic_score_codex":0.000018632138,"about_ca_topic_score_gemma":0.000014351381,"teacher_disagreement_score":0.9612039,"about_ca_system_score_codex":0.00007655789,"about_ca_system_score_gemma":0.00006409312,"threshold_uncertainty_score":0.2921618},"labels":[],"label_agreement":null},{"id":"W1892614893","doi":"10.11606/t.18.2013.tde-01072013-101058","title":"Esquema CADx para classificação de nódulos em imagens mamográficas digitais baseado na segmentação pelo modelo EICAMM","year":2013,"lang":"pt","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Orthopaedic Innovation Centre","funders":"","keywords":"Physics; Computer science","score_opus":0.03984800727748176,"score_gpt":0.29738103331692345,"score_spread":0.25753302603944167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1892614893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117967725,0.0005154936,0.8638944,0.00086266577,0.0038999158,0.0027105028,0.00017625344,0.0012088591,0.008764159],"genre_scores_gemma":[0.91593516,0.0003573291,0.025487553,0.0011689332,0.0005514647,0.0011124464,0.00072288385,0.00034388498,0.054320373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9897412,0.0004142949,0.0019594948,0.003379675,0.002164227,0.0023411294],"domain_scores_gemma":[0.9929622,0.00041827263,0.0012767244,0.0030597455,0.0011292724,0.0011538287],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0008080701,0.001828693,0.0013829591,0.00087965553,0.0009764555,0.0027325791,0.0032060312,0.0015350176,0.002344266],"category_scores_gemma":[0.00014073202,0.0018965882,0.0009003319,0.00170249,0.0002312312,0.0028467479,0.0005743154,0.0018688692,0.0040140883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008264562,0.0022347036,0.0022384636,0.0028369671,0.0017681932,0.0006900025,0.03392334,0.006023203,0.0538396,0.006590749,0.06963837,0.81938994],"study_design_scores_gemma":[0.0012966114,0.00063670054,0.0051098904,0.0005354081,0.00034123956,0.00019915258,0.007037311,0.94210064,0.037311725,0.0010833996,0.0014392409,0.0029086685],"about_ca_topic_score_codex":0.0017032842,"about_ca_topic_score_gemma":0.0005420676,"teacher_disagreement_score":0.9360775,"about_ca_system_score_codex":0.0024374363,"about_ca_system_score_gemma":0.0015877816,"threshold_uncertainty_score":0.9997612},"labels":[],"label_agreement":null},{"id":"W1906581343","doi":"10.1016/j.ultrasmedbio.2015.05.022","title":"A Computerized System to Assess Axillary Lymph Node Malignancy from Sonographic Images","year":2015,"lang":"en","type":"article","venue":"Ultrasound in Medicine & Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Pixel; Receiver operating characteristic; Feature vector; Lymph node; Computer science; Hilum (anatomy); Pattern recognition (psychology); Artificial intelligence; Radiology; Medicine; Pathology","score_opus":0.042083284456521985,"score_gpt":0.2989161760902593,"score_spread":0.2568328916337373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906581343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25903255,0.0013875485,0.7301592,0.002262003,0.004651542,0.00033739593,0.000015957849,0.00040385028,0.0017499266],"genre_scores_gemma":[0.9465983,0.00011071416,0.05079263,0.0016748488,0.00067428086,0.00007777921,0.00003387596,0.000018945351,0.000018609933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99747634,0.00042416662,0.0005593759,0.00077932735,0.00026699528,0.0004937936],"domain_scores_gemma":[0.9978958,0.00069894013,0.00017506172,0.00080055767,0.00016004834,0.00026964294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009069826,0.0002758737,0.00059665734,0.00042501136,0.0000693158,0.000050198163,0.0011268832,0.00017695242,0.000014276306],"category_scores_gemma":[0.0003358958,0.0002261182,0.000054382297,0.0010059403,0.00019774213,0.00023499016,0.00022090324,0.00021871417,0.000067805704],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046651575,0.00035792493,0.4797903,0.00028517612,0.00033219464,0.00048670275,0.011298508,0.0010022236,0.27454513,0.02168705,0.03097645,0.17877182],"study_design_scores_gemma":[0.03383323,0.007742654,0.63206136,0.0054322532,0.00024942646,0.0028831144,0.006979289,0.05191855,0.014554946,0.055142622,0.18347472,0.005727831],"about_ca_topic_score_codex":0.001975963,"about_ca_topic_score_gemma":0.000059865048,"teacher_disagreement_score":0.68756574,"about_ca_system_score_codex":0.00031966172,"about_ca_system_score_gemma":0.00014499763,"threshold_uncertainty_score":0.92208326},"labels":[],"label_agreement":null},{"id":"W1908634864","doi":"10.1007/978-3-642-40763-5_78","title":"Manifold Learning of Brain MRIs by Deep Learning","year":2013,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Nonlinear dimensionality reduction; Manifold alignment; Deep learning; Deep belief network; Manifold (fluid mechanics); Segmentation; Pattern recognition (psychology); Machine learning; Population; Similarity (geometry); Computer vision; Image (mathematics); Dimensionality reduction","score_opus":0.006201457851369817,"score_gpt":0.22405991227068445,"score_spread":0.21785845441931462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1908634864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049819034,0.00021180003,0.9474768,0.0014165452,0.0006239636,0.00019314705,1.3694314e-7,0.00018394497,0.000074622425],"genre_scores_gemma":[0.81332076,0.000010061536,0.1860501,0.00050301844,0.000082530554,0.000014105562,4.860349e-7,0.000010363626,0.000008586605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974061,0.00015515376,0.00035541746,0.00082567194,0.00067401375,0.00058359565],"domain_scores_gemma":[0.9983576,0.0005726852,0.00021677486,0.000546454,0.00019015408,0.000116324554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008759295,0.00021020943,0.00024212022,0.0003655388,0.00027150882,0.00035563356,0.0018508745,0.000102162354,0.000032956836],"category_scores_gemma":[0.0003097733,0.00020017294,0.000058863203,0.002291211,0.00024368326,0.0012546272,0.0007144341,0.00061961665,0.000046681776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016041122,0.000023869685,0.0049172104,0.000015273714,0.000003473541,0.000003075514,0.0014523829,0.14886665,0.023111995,0.00020813556,0.000057462876,0.82133883],"study_design_scores_gemma":[0.00018729619,0.0002477826,0.0034937095,0.000041599298,0.0000011897048,0.000022565931,0.0000026497735,0.941963,0.04940085,0.004048855,0.00035565512,0.000234853],"about_ca_topic_score_codex":0.00032096132,"about_ca_topic_score_gemma":0.00002445993,"teacher_disagreement_score":0.821104,"about_ca_system_score_codex":0.00018396381,"about_ca_system_score_gemma":0.00009812455,"threshold_uncertainty_score":0.81628156},"labels":[],"label_agreement":null},{"id":"W1916400104","doi":"10.1111/j.1399-0012.2011.01506.x","title":"Superiority of virtual microscopy versus light microscopy in transplantation pathology","year":2011,"lang":"en","type":"article","venue":"Clinical Transplantation","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Metabolomics Innovation Centre; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Virtual microscopy; Reproducibility; Medicine; Microscopy; Transplantation; Telepathology; Biopsy; Digital pathology; Pathology; Nuclear medicine; Surgery; Telemedicine","score_opus":0.07000004930259092,"score_gpt":0.358823330259666,"score_spread":0.2888232809570751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916400104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70592564,0.00004655077,0.29083857,0.000065211425,0.002113154,0.00020129059,0.000022118167,0.000071294686,0.00071613706],"genre_scores_gemma":[0.96437514,0.0013705849,0.034040533,0.000077651785,0.00006802813,0.000022130005,0.000022555416,0.000012999771,0.00001036497],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99776,0.00033703903,0.00091679627,0.00053463597,0.00019280553,0.00025869842],"domain_scores_gemma":[0.9989228,0.0003717072,0.0001921582,0.00035898667,0.00007642474,0.0000778988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007120897,0.00016851409,0.00033223492,0.0001658809,0.000056868757,0.000018228422,0.0004684537,0.00027390788,0.000026302727],"category_scores_gemma":[0.000030462319,0.00017765135,0.00012878749,0.00038842848,0.00016194522,0.0005439114,0.000015783024,0.00030674794,0.000032294276],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019365452,0.0023116856,0.2646003,0.0009962628,0.00017382501,0.0008029518,0.062649496,0.00015082795,0.5533428,0.019944705,0.00008641355,0.07557527],"study_design_scores_gemma":[0.007675647,0.0025664603,0.3935817,0.00016252082,0.000095900454,0.00008009511,0.00014292254,0.00096262514,0.5927281,0.0014381609,0.00012825117,0.00043766334],"about_ca_topic_score_codex":0.00011717933,"about_ca_topic_score_gemma":0.00041889196,"teacher_disagreement_score":0.2584495,"about_ca_system_score_codex":0.000047600992,"about_ca_system_score_gemma":0.00009847903,"threshold_uncertainty_score":0.72444123},"labels":[],"label_agreement":null},{"id":"W1923884056","doi":"10.1111/jmi.12237","title":"Automated image analysis of nuclear atypia in high‐power field histopathological image","year":2015,"lang":"en","type":"article","venue":"Journal of Microscopy","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Haematoxylin; Pattern recognition (psychology); Eosin; Digital image; Histogram; Digital pathology; Image processing; Feature (linguistics); Computer vision; Atypia; Image (mathematics); Pathology; Medicine","score_opus":0.011656964345398807,"score_gpt":0.291077122236882,"score_spread":0.27942015789148317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1923884056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9373486,0.00013493889,0.060566537,0.0007993584,0.00067778095,0.000044966193,0.0000023099446,0.000057501602,0.00036798057],"genre_scores_gemma":[0.86222047,0.000018824663,0.13745336,0.00024873624,0.000030529674,4.6447752e-7,2.6646865e-7,0.0000068069135,0.000020568546],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986682,0.00012289216,0.0005652411,0.00017299269,0.00029750413,0.0001731923],"domain_scores_gemma":[0.99870074,0.00007224826,0.0005148332,0.00030761788,0.00030632303,0.00009822535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077594916,0.00010404393,0.00040322493,0.0005167794,0.000024441593,0.000059754624,0.00063821475,0.00010012619,0.00007210478],"category_scores_gemma":[0.0001723059,0.00008795954,0.00016385337,0.0010066525,0.00006703538,0.00050821545,0.00012904711,0.0002780453,0.000016425553],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003546087,0.00035946094,0.00755405,0.000017548093,0.00023425114,0.0004976657,0.0024858024,0.00060593756,0.9470268,0.00033966498,0.03909288,0.0014313412],"study_design_scores_gemma":[0.008050016,0.00758233,0.41209844,0.00033722824,0.0010498062,0.0008898281,0.0007051092,0.13586615,0.4145478,0.0036878467,0.013895262,0.001290202],"about_ca_topic_score_codex":0.00005412186,"about_ca_topic_score_gemma":0.000009898861,"teacher_disagreement_score":0.532479,"about_ca_system_score_codex":0.0002527527,"about_ca_system_score_gemma":0.00010066435,"threshold_uncertainty_score":0.3586886},"labels":[],"label_agreement":null},{"id":"W1931887591","doi":"10.1109/wescan.1997.627128","title":"Mammographic image registration using the starbyte transformation","year":2002,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Transformation (genetics); Computer vision; Artificial intelligence; Image registration; Computer science; Matching (statistics); Image matching; Image (mathematics); Mathematics","score_opus":0.034954696146742736,"score_gpt":0.24306523630416865,"score_spread":0.20811054015742592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1931887591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012506475,0.000047590027,0.9705953,0.0027411643,0.00021197682,0.00013460999,3.250593e-7,0.00016382193,0.013598717],"genre_scores_gemma":[0.9662002,0.000037201255,0.03327642,0.0002469873,0.000053430427,0.000007147135,3.5290083e-7,0.0000040313453,0.00017424181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935687,0.000039717987,0.00014242824,0.00013606856,0.00020530277,0.00011963939],"domain_scores_gemma":[0.9995359,0.000018695984,0.000056787158,0.00032380124,0.000043510994,0.000021263873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001919352,0.000061383325,0.00004077438,0.00006073161,0.00018762927,0.00017906645,0.0002848575,0.00002846178,0.000060351922],"category_scores_gemma":[0.000004572627,0.00004364793,0.00003804374,0.00043864577,0.00003633129,0.0012085399,0.000015414393,0.000079018675,0.000022345052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021281026,0.00015546133,0.00035072144,0.00009221474,0.000073226984,0.000011712093,0.015303828,0.0044517256,0.08987534,0.2788725,0.011588871,0.59920317],"study_design_scores_gemma":[0.00012696657,0.000037432488,0.00029034313,0.0000054015563,0.0000048067272,0.000028660561,0.0000696011,0.9830768,0.009736395,0.002896748,0.0036319285,0.00009492673],"about_ca_topic_score_codex":0.00007424335,"about_ca_topic_score_gemma":0.000054782744,"teacher_disagreement_score":0.97862506,"about_ca_system_score_codex":0.000044710454,"about_ca_system_score_gemma":0.000008161875,"threshold_uncertainty_score":0.17799109},"labels":[],"label_agreement":null},{"id":"W1934355748","doi":"10.1109/isbi.2015.7163846","title":"Segmentation of overlapping cervical cells: A variational method with star-shape prior","year":2015,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Segmentation; Star (game theory); Constraint (computer-aided design); Artificial intelligence; Computer science; Computer vision; Prior probability; Noise (video); Image segmentation; Pattern recognition (psychology); Image (mathematics); Mathematics; Geometry; Mathematical analysis","score_opus":0.030908230365046814,"score_gpt":0.2877206245455071,"score_spread":0.2568123941804603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1934355748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076026437,0.000008661796,0.9896921,0.00038249337,0.00019982317,0.00013385195,0.0000012360734,0.00008044022,0.0018987344],"genre_scores_gemma":[0.19987692,6.7036e-7,0.79980433,0.00016389076,0.000044181532,0.000012345564,0.0000011461051,0.000004638841,0.000091856826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989843,0.000077482684,0.00016922435,0.00022564924,0.0004388187,0.0001045516],"domain_scores_gemma":[0.99933743,0.00008892357,0.000114938826,0.00020305646,0.00018869595,0.000066946064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032484828,0.00007234804,0.00009682404,0.00006442754,0.000032503212,0.000041964908,0.00022570736,0.00003517525,0.00005473306],"category_scores_gemma":[0.000012316621,0.00005941607,0.000020137442,0.00033211242,0.000014411991,0.00048049403,0.00008108671,0.000060081562,0.000013551562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005939295,0.0006343622,0.0033345171,0.0002579403,0.00038264878,0.000017612905,0.016204648,0.04699709,0.21230179,0.26606628,0.0040908903,0.4491183],"study_design_scores_gemma":[0.0008555581,0.00033475383,0.0039193477,0.000014433312,0.000011078775,0.000011093121,0.000192237,0.93678963,0.052749086,0.0044851573,0.0004937609,0.0001438594],"about_ca_topic_score_codex":0.00010670761,"about_ca_topic_score_gemma":0.000021076392,"teacher_disagreement_score":0.88979256,"about_ca_system_score_codex":0.00013655366,"about_ca_system_score_gemma":0.00020845828,"threshold_uncertainty_score":0.2422917},"labels":[],"label_agreement":null},{"id":"W1951829736","doi":"10.1111/j.1365-2559.2011.03896.x","title":"Development and evaluation of a robust algorithm for computer-assisted detection of sentinel lymph node micrometastases","year":2011,"lang":"en","type":"article","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Micrometastasis; Sentinel lymph node; Lymph; Lymph node; Medicine; Pathology; Radiology; Nuclear medicine; Breast cancer; Cancer; Internal medicine","score_opus":0.07808902492461786,"score_gpt":0.26590087173267896,"score_spread":0.1878118468080611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951829736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32049403,0.00016113314,0.6787674,0.0000055121322,0.00036631088,0.00013547846,0.0000030775534,0.000025507488,0.000041541058],"genre_scores_gemma":[0.38919163,0.0000034058398,0.6107035,0.000016606042,0.000018415858,0.00005158372,0.0000027801684,0.0000057068723,0.000006376903],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989595,0.00011736824,0.00033105107,0.00029211398,0.00017081923,0.00012915357],"domain_scores_gemma":[0.99906296,0.00003841537,0.0002986804,0.00022901787,0.00034366973,0.00002729089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007696549,0.000095732794,0.00019748109,0.00020788689,0.0000654402,0.000004880647,0.00016189263,0.00006661662,0.0000037207562],"category_scores_gemma":[0.000019745627,0.000102099846,0.000038120288,0.0001827177,0.000085018946,0.000108219814,0.0000894262,0.000033388555,0.0000010299659],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001743632,0.00010709359,0.00047947248,0.000056765708,0.000008407762,0.0000019816155,0.0014541312,0.00005088865,0.07280171,0.000088773406,0.0000083287305,0.924925],"study_design_scores_gemma":[0.0018788581,0.00017209288,0.39809328,0.00003915254,0.00010252211,0.00030753337,0.000058663187,0.37233976,0.22598973,0.0003512487,0.00043264436,0.00023453201],"about_ca_topic_score_codex":0.00002919475,"about_ca_topic_score_gemma":0.0000084868625,"teacher_disagreement_score":0.9246905,"about_ca_system_score_codex":0.00014440663,"about_ca_system_score_gemma":0.000114515584,"threshold_uncertainty_score":0.41635108},"labels":[],"label_agreement":null},{"id":"W1966034269","doi":"10.1118/1.2241387","title":"MO‐A‐330A‐01: Recent Advances in Digital Mammography","year":2006,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Mammography; Digital mammography; Medicine; Breast cancer; Medical physics; Radiology; Cancer detection; Cancer; Internal medicine","score_opus":0.006933601709324488,"score_gpt":0.2365370155472141,"score_spread":0.2296034138378896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966034269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0092307115,0.0023085037,0.9729743,0.0014264717,0.0009603437,0.00013014479,0.0000031746206,0.00024400112,0.012722333],"genre_scores_gemma":[0.9971205,0.00074927596,0.0009345786,0.00040089374,0.0007030371,0.000024447687,0.000005441284,0.00001157839,0.00005025047],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985168,0.0000152450175,0.00020415454,0.0003084585,0.0006946118,0.0002607334],"domain_scores_gemma":[0.9995117,0.00006710936,0.00005556892,0.00024017956,0.00003435949,0.0000910863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012480706,0.000108201406,0.0001294826,0.000051196555,0.000041093368,0.00007343792,0.00050866214,0.00006377423,0.00001503655],"category_scores_gemma":[0.000037443548,0.00009906583,0.000053485113,0.0008403208,0.00009975633,0.0008773352,0.00013072825,0.00022381515,0.000043714965],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037715654,0.000112456524,0.0029965634,0.00000876543,0.0000020889327,0.000012356003,0.0000309849,0.00012907229,0.000008459591,0.005919157,0.0012216045,0.9895547],"study_design_scores_gemma":[0.0009479455,0.00015783672,0.006886268,0.00009963427,0.0000037975092,0.000013058716,0.000011403185,0.013730696,0.003333775,0.59492755,0.37942344,0.00046456206],"about_ca_topic_score_codex":0.000016397173,"about_ca_topic_score_gemma":0.000033551973,"teacher_disagreement_score":0.98909014,"about_ca_system_score_codex":0.000072991985,"about_ca_system_score_gemma":0.00005888925,"threshold_uncertainty_score":0.40397874},"labels":[],"label_agreement":null},{"id":"W1966619881","doi":"10.4103/2153-3539.112689","title":"The history of pathology informatics: A global perspective","year":2013,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"National Institute of Environmental Health Sciences","keywords":"Informatics; Digital pathology; Health informatics; Computer science; Data science; Health Administration Informatics; Telepathology; Information technology; Medicine; Pathology; Health care; Political science; Telemedicine; Artificial intelligence","score_opus":0.012638374115956473,"score_gpt":0.249703627727103,"score_spread":0.23706525361114653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966619881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16482271,0.001682674,0.79693246,0.0019518887,0.008378618,0.00039519032,0.000005768367,0.000064534404,0.025766153],"genre_scores_gemma":[0.7234272,0.0008931938,0.2719454,0.0028730326,0.00037421094,0.000031674477,8.1065457e-7,0.000018713528,0.00043582663],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976563,0.00012490193,0.0014798742,0.000051280163,0.0003926113,0.00029504954],"domain_scores_gemma":[0.99580145,0.00020952307,0.002275821,0.00048386134,0.0011381757,0.000091141796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010892187,0.00014995324,0.0003396972,0.00016033657,0.00009330466,0.00004993296,0.001169184,0.00016350762,0.000016374926],"category_scores_gemma":[0.00034297045,0.00010159074,0.00015723825,0.00023126656,0.00040238252,0.0016725801,0.00024865186,0.00043641412,0.000069265894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017698415,0.00035782764,0.0039010248,0.0003605438,0.000541321,0.00045088382,0.32949197,0.0030297644,0.0008732223,0.2022645,0.17294273,0.28560922],"study_design_scores_gemma":[0.008731615,0.011263327,0.0372771,0.00042218197,0.00038273266,0.10569675,0.14623198,0.2289245,0.001415582,0.29613316,0.1615142,0.0020068868],"about_ca_topic_score_codex":0.000011397511,"about_ca_topic_score_gemma":0.000006335786,"teacher_disagreement_score":0.5586044,"about_ca_system_score_codex":0.001377642,"about_ca_system_score_gemma":0.0005990049,"threshold_uncertainty_score":0.41427502},"labels":[],"label_agreement":null},{"id":"W1966803846","doi":"10.5585/exacta.v4i2.765","title":"Classification of mammographic features using RBF-SA","year":2008,"lang":"en","type":"article","venue":"Exacta","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.04748681195169131,"score_gpt":0.2696742353071807,"score_spread":0.2221874233554894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966803846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7665135,0.0002854325,0.22984207,0.0002851275,0.00057876,0.00010302584,0.0000011016712,0.0001313558,0.0022595897],"genre_scores_gemma":[0.98229533,0.000036166526,0.017448988,0.00003968891,0.00007139422,0.0000031985332,6.1030585e-7,0.0000054935826,0.00009911336],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99932593,0.000034249028,0.0001260057,0.0001970333,0.00020271767,0.00011404692],"domain_scores_gemma":[0.99935913,0.000028862918,0.00010736778,0.0004153264,0.000058220623,0.000031068983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000091832066,0.00006412397,0.00008099494,0.00012774578,0.00009492656,0.000016274927,0.00033966036,0.000052103944,0.000007848765],"category_scores_gemma":[0.000015045531,0.000063317435,0.000043941636,0.00049384544,0.00006115298,0.00028637896,0.000054552394,0.000087401044,0.000005692788],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006342997,0.00028481352,0.09337252,0.00010999747,0.00011020979,0.0000397914,0.00495547,0.0009101131,0.72056246,0.037084024,0.013714642,0.12879252],"study_design_scores_gemma":[0.00032488,0.00011206795,0.89509827,0.000038388214,0.000009919275,0.00020072612,0.000036354766,0.041938525,0.05546003,0.0020187548,0.0044962647,0.0002658387],"about_ca_topic_score_codex":0.00007567662,"about_ca_topic_score_gemma":0.000010600328,"teacher_disagreement_score":0.80172575,"about_ca_system_score_codex":0.0000430768,"about_ca_system_score_gemma":0.00005207587,"threshold_uncertainty_score":0.258201},"labels":[],"label_agreement":null},{"id":"W1966871760","doi":"10.3791/50341","title":"Detection of Architectural Distortion in Prior Mammograms <em>via</em> Analysis of Oriented Patterns","year":2013,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Distortion (music); Mammography; False positive paradox; Artificial intelligence; Pattern recognition (psychology); Breast cancer; Linear discriminant analysis; Receiver operating characteristic; Fractal dimension; Computer science; Medicine; Cancer; Mathematics; Fractal; Internal medicine","score_opus":0.015538371501576805,"score_gpt":0.3355714869614179,"score_spread":0.3200331154598411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966871760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6527521,0.0002072151,0.34629285,0.000017121934,0.00050075457,0.00020061278,0.0000021682479,0.000018612529,0.000008582982],"genre_scores_gemma":[0.99444586,0.000033614106,0.0053491453,0.000027369224,0.00007280124,0.000029013008,0.0000030664673,0.000018237875,0.000020883877],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99657214,0.00029905708,0.0014396629,0.0003246996,0.0010468143,0.00031761278],"domain_scores_gemma":[0.9971791,0.00007430513,0.0017478248,0.00039393708,0.0004589089,0.00014592602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005548397,0.00023965062,0.00071179756,0.0013636636,0.000064331696,0.000068841095,0.00057167304,0.00012030207,0.0000757062],"category_scores_gemma":[0.00006507405,0.0002128499,0.0004248126,0.0018367259,0.000055368993,0.00079741527,0.00014248717,0.00023425603,0.0000040259633],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003451149,0.00057215506,0.0072939578,0.000041639123,0.00067603233,0.000008961223,0.0057284245,0.0008022436,0.86408097,0.000023712613,0.000011700351,0.12041512],"study_design_scores_gemma":[0.0027850964,0.0011958808,0.19206326,0.00015585848,0.00024279175,0.00004161916,0.00040454278,0.04306032,0.7594974,0.00014396792,0.000108860026,0.0003004052],"about_ca_topic_score_codex":0.00031109306,"about_ca_topic_score_gemma":0.00018203311,"teacher_disagreement_score":0.3416938,"about_ca_system_score_codex":0.00047854154,"about_ca_system_score_gemma":0.000056199257,"threshold_uncertainty_score":0.8679767},"labels":[],"label_agreement":null},{"id":"W1969234383","doi":"10.1118/1.3476182","title":"Sci-Fri AM: Imaging - 03: Automated Registration of X-Ray Mammograms and Magnetic Resonance Breast Images","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Mammography; Magnetic resonance imaging; Projection (relational algebra); Artificial intelligence; Image registration; Breast cancer; Computer vision; Computer science; Breast MRI; Medical imaging; Breast imaging; Medicine; Pattern recognition (psychology); Radiology; Cancer; Image (mathematics)","score_opus":0.005547131477671038,"score_gpt":0.2382415018634314,"score_spread":0.23269437038576035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969234383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22488424,0.0011140635,0.75668275,0.009369022,0.0026030936,0.00048519287,0.00002156398,0.0016464088,0.0031936388],"genre_scores_gemma":[0.9924892,0.000028523957,0.007002499,0.00014729511,0.0002540367,0.000010002449,0.00000244693,0.000010369243,0.000055579145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854815,0.00003724494,0.0002342147,0.00033037033,0.0006406803,0.00020934136],"domain_scores_gemma":[0.9991313,0.00007703216,0.00011800532,0.000436575,0.00010416599,0.00013288665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003688591,0.000116158786,0.0001464089,0.000031646934,0.00008318232,0.00007914596,0.00044611408,0.00006732213,0.00001831258],"category_scores_gemma":[0.00008765783,0.00010834868,0.0000323582,0.0003651363,0.00042013783,0.00039773044,0.00014606916,0.00030420005,0.00001027449],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063179255,0.00006117299,0.0024665098,0.000037785067,0.00000291736,0.000012353748,0.00015566754,0.00000545674,0.005845364,0.0011453467,0.0023950166,0.9878661],"study_design_scores_gemma":[0.0016651045,0.00028179868,0.20957258,0.00033399233,0.00003425938,0.00034726885,0.000034613535,0.721903,0.035254538,0.02380774,0.0060549965,0.000710108],"about_ca_topic_score_codex":0.000116507035,"about_ca_topic_score_gemma":0.000022872822,"teacher_disagreement_score":0.987156,"about_ca_system_score_codex":0.000019512061,"about_ca_system_score_gemma":0.00011010732,"threshold_uncertainty_score":0.44183308},"labels":[],"label_agreement":null},{"id":"W1969328520","doi":"10.1109/biocas.2011.6107815","title":"DWT and RT-based approach for feature extraction and classification of mammograms with SVM","year":2011,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Support vector machine; Discrete wavelet transform; Pattern recognition (psychology); Artificial intelligence; Feature extraction; Kernel (algebra); Computer science; Feature (linguistics); Wavelet transform; Wavelet; Mathematics; Computer vision","score_opus":0.045025026224063076,"score_gpt":0.2471488323880045,"score_spread":0.20212380616394143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969328520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012326829,0.000038929127,0.98517954,0.00011844185,0.000043495387,0.00025088177,0.0000010916508,0.000059306672,0.0019814705],"genre_scores_gemma":[0.59665626,0.0000027970816,0.40319717,0.000020972788,0.000010227292,0.000031210726,0.0000019402116,0.000003398535,0.00007604982],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995256,0.000013597073,0.00007107439,0.00022779274,0.000085568136,0.00007633405],"domain_scores_gemma":[0.9996121,0.000024557243,0.000081491125,0.00018706756,0.00006372605,0.000031050455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011584235,0.000062333565,0.00006933825,0.00005004713,0.000046684934,0.000028471779,0.00008311444,0.00005645587,0.0000013491174],"category_scores_gemma":[0.000003965467,0.00004741672,0.00001155417,0.00012883292,0.000049018283,0.00026863188,0.000013052169,0.000049486145,1.7239924e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058474374,0.00037613016,0.029160734,0.00042099037,0.00006589673,9.310449e-7,0.0016706854,0.000121407524,0.030928386,0.051560357,0.0012839191,0.88382584],"study_design_scores_gemma":[0.0013007949,0.0010874639,0.22512785,0.000021767268,0.00003461255,0.000037588645,0.00022731403,0.7021701,0.06702145,0.0013860604,0.0013094919,0.00027553397],"about_ca_topic_score_codex":0.0000434355,"about_ca_topic_score_gemma":0.000027185557,"teacher_disagreement_score":0.8835503,"about_ca_system_score_codex":0.000016061103,"about_ca_system_score_gemma":0.000019297862,"threshold_uncertainty_score":0.19335978},"labels":[],"label_agreement":null},{"id":"W1974195684","doi":"10.4103/2153-3539.83746","title":"Review of the current state of whole slide imaging in pathology","year":2011,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":432,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Toronto General Hospital","funders":"University Health Network","keywords":"Digital pathology; Telepathology; Medical diagnosis; Digitization; Computer science; Quality assurance; Medical physics; Rendering (computer graphics); Data science; Pathology; Medicine; Health care; Artificial intelligence; Telemedicine; Telecommunications","score_opus":0.02392586273398132,"score_gpt":0.27799936320672985,"score_spread":0.2540735004727485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974195684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3774588,0.032063734,0.5819951,0.0011200131,0.0050143898,0.00048458218,0.000014096156,0.000021172582,0.0018280649],"genre_scores_gemma":[0.86922926,0.025569016,0.10270452,0.0023889232,0.000071989845,0.000008378995,5.6649867e-7,0.000015712127,0.0000116480505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998037,0.00016641649,0.0013939922,0.000046436195,0.00020235826,0.00015378681],"domain_scores_gemma":[0.99717134,0.000055005756,0.0020760102,0.00036583428,0.00030186443,0.000029920775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599538,0.00008559296,0.0003299385,0.00019461288,0.00001999749,0.0000045176985,0.000804299,0.000024509452,0.0000032357234],"category_scores_gemma":[0.00018843272,0.000057861536,0.00011258942,0.0003249793,0.00013038768,0.0005243784,0.00022298087,0.00038407784,0.000003370308],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016777634,0.00011446235,0.010165675,0.002397976,0.000013345715,0.000079432866,0.01655285,0.00015289731,0.0007092456,0.00040488262,0.0012107602,0.96818167],"study_design_scores_gemma":[0.0082806125,0.004082757,0.5982992,0.0646714,0.00047309892,0.036800653,0.0018472676,0.037807215,0.0742739,0.12532811,0.046293817,0.001841962],"about_ca_topic_score_codex":0.0000012679116,"about_ca_topic_score_gemma":0.0000028582958,"teacher_disagreement_score":0.9663397,"about_ca_system_score_codex":0.000054021646,"about_ca_system_score_gemma":0.00017249156,"threshold_uncertainty_score":0.2359525},"labels":[],"label_agreement":null},{"id":"W1977212742","doi":"10.5858/arpa.2014-0082-ra","title":"Cancer Biomarkers: The Role of Structured Data Reporting","year":2014,"lang":"en","type":"review","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre; Grand River Hospital","funders":"","keywords":"Standardization; Terminology; Medicine; Cancer; Computer science; Medical physics; Interoperability; Checklist; Data science; World Wide Web; Internal medicine; Psychology","score_opus":0.05011504533423014,"score_gpt":0.36529000670870415,"score_spread":0.315174961374474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977212742","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027624264,0.98766524,0.009927141,0.00018678246,0.0011317619,0.00039276935,0.00014621057,0.00004864763,0.0004738205],"genre_scores_gemma":[0.00042135452,0.9930479,0.0057977354,0.000087705674,0.0004972853,0.000048935497,0.000058257363,0.000030766612,0.000010086054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99569243,0.00093150255,0.0019694862,0.00079865096,0.0003350283,0.00027292722],"domain_scores_gemma":[0.98958176,0.0010966565,0.0057044737,0.0034279046,0.00011899563,0.000070221424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019216021,0.0003312531,0.0018553092,0.00029225543,0.00008290822,0.0000064477763,0.0033494402,0.00018089746,0.000016659586],"category_scores_gemma":[0.0014700887,0.00019634728,0.00012582002,0.0007482766,0.0012547445,0.00012994006,0.0010640192,0.00047734327,0.0000012914645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042755833,0.000007668151,0.000063359046,0.002230927,0.00017865787,0.00002829793,0.00051977305,0.0000010618504,0.00048285275,0.00068073254,0.00028406823,0.9955183],"study_design_scores_gemma":[0.00020163323,0.0001688379,0.00017846108,0.0071581295,0.0005587485,0.00014851359,0.00008361382,0.00042681332,0.00018754054,0.001968348,0.9887031,0.00021630204],"about_ca_topic_score_codex":0.00007515469,"about_ca_topic_score_gemma":0.00005692529,"teacher_disagreement_score":0.995302,"about_ca_system_score_codex":0.000029727502,"about_ca_system_score_gemma":0.0008376855,"threshold_uncertainty_score":0.80068094},"labels":[],"label_agreement":null},{"id":"W1978566161","doi":"10.1016/j.compmedimag.2011.05.002","title":"Increasing specimen coverage using digital whole-mount breast pathology: Implementation, clinical feasibility and application in research","year":2011,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Ontario Institute for Cancer Research","keywords":"Computer science; Sampling (signal processing); Visualization; Digital pathology; Image processing; Software; Mount; Computer vision; Artificial intelligence; Pathology; Biomedical engineering; Medical physics; Medicine; Image (mathematics)","score_opus":0.12077809785623259,"score_gpt":0.42455350166978256,"score_spread":0.30377540381354995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978566161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54643947,0.00015243194,0.45245814,0.0005000618,0.00016416404,0.00019611901,0.0000052256046,0.000055834007,0.000028542147],"genre_scores_gemma":[0.9843873,0.00020649703,0.014908978,0.0003233924,0.00014258281,0.0000117591,0.000008435548,0.00001050754,5.5937164e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99731594,0.0005640925,0.00054660783,0.0007133968,0.00049501756,0.00036493858],"domain_scores_gemma":[0.998641,0.00040825745,0.0001177772,0.0004046563,0.00015339162,0.00027489194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004377005,0.00014468473,0.00026190988,0.00026190034,0.00022345444,0.00023552723,0.00037922795,0.0001122565,0.000003630892],"category_scores_gemma":[0.00014416399,0.00014281766,0.000039165236,0.0005795688,0.000697734,0.00067146315,0.0006790035,0.0005862249,0.0000016537939],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064752654,0.00013411627,0.5268527,0.000030097266,0.000010561945,0.000070220354,0.0007331742,4.9113925e-7,0.0002910742,0.00320894,0.000035981273,0.46856788],"study_design_scores_gemma":[0.0022092557,0.0000837571,0.7563022,0.00009758522,0.00000730686,0.001117378,0.00012692895,0.21247505,0.000023354996,0.026725313,0.0005941246,0.00023775508],"about_ca_topic_score_codex":0.0004528223,"about_ca_topic_score_gemma":0.000040570787,"teacher_disagreement_score":0.46833012,"about_ca_system_score_codex":0.00011637621,"about_ca_system_score_gemma":0.00015927394,"threshold_uncertainty_score":0.5823935},"labels":[],"label_agreement":null},{"id":"W1979799189","doi":"10.1117/12.535372","title":"Removing radiopaque artifacts from mammograms using area morphology","year":2004,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Mammography; Mathematical morphology; Computer vision; Image segmentation; Pattern recognition (psychology); Identification (biology); Representation (politics); Image processing; Image (mathematics); Medicine; Breast cancer; Biology","score_opus":0.017589263718338296,"score_gpt":0.23115088014268573,"score_spread":0.21356161642434743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979799189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826832,0.00013694432,0.012703698,0.002632386,0.0006667517,0.00041350067,0.000017801913,0.0001995063,0.0005462506],"genre_scores_gemma":[0.5195662,0.000048561953,0.47965345,0.0001869289,0.00041307436,0.000055832377,0.0000033196616,0.000046658904,0.000026017931],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99738985,1.873498e-8,0.00071530574,0.00062959414,0.00075087085,0.00051433017],"domain_scores_gemma":[0.9979695,0.0001256339,0.0005057143,0.0001247926,0.0011177951,0.00015655812],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052634656,0.00035042685,0.00043771812,0.00013798966,0.00013221371,0.0002241704,0.0017743725,0.00025343912,0.0000074098803],"category_scores_gemma":[0.00038526955,0.0003196112,0.00054992206,0.00054612407,0.00022852788,0.0011810681,0.00037232463,0.0004179963,0.000002475506],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042170508,0.00008166387,0.00022096695,0.00010843163,0.00025131527,5.147307e-7,0.00030356366,0.0022682147,0.7418302,0.25355792,0.00031797186,0.0010170194],"study_design_scores_gemma":[0.0021787419,0.0005091212,0.0013292978,0.00071060937,0.00017681035,0.00015524091,0.0007489767,0.21399486,0.7456934,0.03202535,0.0016535993,0.0008240007],"about_ca_topic_score_codex":0.000116964526,"about_ca_topic_score_gemma":6.285e-7,"teacher_disagreement_score":0.46694976,"about_ca_system_score_codex":0.00058180635,"about_ca_system_score_gemma":0.000082706065,"threshold_uncertainty_score":0.9999256},"labels":[],"label_agreement":null},{"id":"W1979811710","doi":"10.1117/12.709873","title":"Implementing a large-scale multicentric study for evaluation of lossy JPEG and JPEG2000 medical image compression: challenges and rewards","year":2007,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hôpital Saint-Luc; Canada Health Infoway; Fraser Health; Sunnybrook Health Science Centre","funders":"","keywords":"Lossy compression; JPEG; JPEG 2000; Computer science; Quantization (signal processing); Image compression; Lossless JPEG; Compression artifact; Compression ratio; Data compression; Discrete cosine transform; Computer vision; Lossless compression; File size; Artificial intelligence; Computer engineering; Image processing; Image (mathematics)","score_opus":0.019587723365209028,"score_gpt":0.2923845994864881,"score_spread":0.27279687612127906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979811710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931264,0.00081733096,0.0030679898,0.0012396367,0.00019487548,0.0011664642,0.00001404715,0.00005578063,0.000317455],"genre_scores_gemma":[0.85049355,0.0003074834,0.14869794,0.000034167228,0.0002661774,0.00015913283,0.000001646936,0.00002907967,0.000010809038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690086,8.232611e-8,0.0007356498,0.0004823056,0.0014453243,0.00043580335],"domain_scores_gemma":[0.99666864,0.0003125099,0.0004562966,0.000074156625,0.0023491227,0.00013930118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053923447,0.00022775783,0.00035958237,0.00013593206,0.00014424449,0.000097067394,0.0007381762,0.0001490427,0.0000052023743],"category_scores_gemma":[0.0008641533,0.00019557032,0.00020474763,0.00024931502,0.00017426013,0.00066295196,0.00046223996,0.000212646,1.2367428e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006578653,0.0016946068,0.0047197794,0.0042383466,0.0017110371,5.460108e-7,0.018497255,0.00008855026,0.39164415,0.44610527,0.0011964639,0.1294461],"study_design_scores_gemma":[0.009494515,0.0014904046,0.022828106,0.0007525955,0.00048443646,0.000045047167,0.011545595,0.8450648,0.10167168,0.0037593802,0.0022470541,0.0006163714],"about_ca_topic_score_codex":0.0000092862665,"about_ca_topic_score_gemma":0.0000025988713,"teacher_disagreement_score":0.84497625,"about_ca_system_score_codex":0.00013903622,"about_ca_system_score_gemma":0.00005691448,"threshold_uncertainty_score":0.79751265},"labels":[],"label_agreement":null},{"id":"W1980245463","doi":"10.1186/1471-2342-13-43","title":"Automatic detection of anomalies in screening mammograms","year":2013,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Cancer Centre; Saskatchewan Hospital; Janeway Children's Health and Rehabilitation Centre; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Artificial intelligence; Mammography; Pattern recognition (psychology); Wavelet; Classifier (UML); Abnormality; Medical diagnosis; Population; Breast cancer; Medicine; Radiology; Cancer","score_opus":0.012051177395817186,"score_gpt":0.24991893857150435,"score_spread":0.23786776117568717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980245463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20354986,0.00015259883,0.79520476,0.00031597505,0.00027159377,0.00011289804,6.035763e-8,0.00014715065,0.00024507812],"genre_scores_gemma":[0.9199603,0.00000492767,0.079790324,0.00013159396,0.000054775028,0.000039542112,2.270528e-7,0.000006791877,0.000011490638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862266,0.00010109175,0.00032152008,0.00022866974,0.0004960768,0.00023000866],"domain_scores_gemma":[0.9992538,0.00023066724,0.000100818026,0.00026938424,0.000046111658,0.00009923572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004931452,0.00008588087,0.00014213477,0.00017728613,0.000040050985,0.00006466589,0.00042966317,0.000044433797,0.000108033826],"category_scores_gemma":[0.00032827604,0.00008065085,0.000041761537,0.00047274417,0.00008804801,0.00063746766,0.00016667678,0.00016092713,0.0000290269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.1623364e-7,0.000014845548,0.024584262,0.000052502975,0.0000027758447,0.0000038339294,0.00015766533,0.000029390345,0.0014058937,0.00010032222,0.000033234774,0.97361445],"study_design_scores_gemma":[0.0002466139,0.000014222607,0.077774204,0.00016591582,0.0000021369076,0.00003335461,0.0000820559,0.91636354,0.004242238,0.00092677824,0.00006170416,0.00008722997],"about_ca_topic_score_codex":0.0007042449,"about_ca_topic_score_gemma":0.00020289992,"teacher_disagreement_score":0.97352725,"about_ca_system_score_codex":0.000052722546,"about_ca_system_score_gemma":0.00007778755,"threshold_uncertainty_score":0.3288846},"labels":[],"label_agreement":null},{"id":"W1980625890","doi":"10.3791/51325","title":"Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands","year":2014,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Sunnybrook Health Science Centre; University of Toronto","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Sunnybrook Research Institute","keywords":"Histology; Volume (thermodynamics); H&E stain; 3D reconstruction; Image registration; Computer science; High resolution; Anatomy; Biomedical engineering; Pathology; Biology; Artificial intelligence; Medicine; Staining; Image (mathematics); Geology","score_opus":0.01789053461565562,"score_gpt":0.3604686455290449,"score_spread":0.3425781109133893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980625890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71252143,0.00016598884,0.28650647,0.000121232195,0.00046893986,0.00016359655,3.268964e-7,0.000015552967,0.000036449626],"genre_scores_gemma":[0.9749202,0.000009935711,0.02482053,0.000097155746,0.000079021105,0.000014914248,2.7187474e-7,0.0000074346444,0.000050530143],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986813,0.00017301187,0.0004979001,0.00020627365,0.00032544485,0.00011604954],"domain_scores_gemma":[0.99889857,0.00003460405,0.0005093047,0.000217343,0.00023359871,0.000106561885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049585506,0.00010180225,0.00026502134,0.00023328396,0.00006487297,0.000022527021,0.00030902147,0.00005479179,0.000008966018],"category_scores_gemma":[0.000041685384,0.00009561257,0.00004314198,0.00018411386,0.000018459446,0.00040839674,0.00013512107,0.00009352973,0.0000048300553],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005431915,0.001144541,0.006121982,0.000024396693,0.00019428523,0.0000075957173,0.0038799965,0.00021861568,0.815393,0.0018628767,0.0006211747,0.1699884],"study_design_scores_gemma":[0.007458884,0.007726321,0.014092427,0.000067894995,0.000053157324,0.0009437783,0.00029161116,0.06449181,0.8998247,0.0014712164,0.0031245751,0.00045364915],"about_ca_topic_score_codex":0.000011510112,"about_ca_topic_score_gemma":9.471311e-7,"teacher_disagreement_score":0.26239878,"about_ca_system_score_codex":0.000111355424,"about_ca_system_score_gemma":0.000040053517,"threshold_uncertainty_score":0.38989675},"labels":[],"label_agreement":null},{"id":"W1980637629","doi":"10.1007/s10278-007-9069-9","title":"Feature Extraction from a Signature Based on the Turning Angle Function for the Classification of Breast Tumors","year":2007,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Research Services, University of Calgary","keywords":"Receiver operating characteristic; Fractal dimension; Mammography; Artificial intelligence; Function (biology); Breast cancer; Convexity; Pattern recognition (psychology); Medicine; Mathematics; Computer science; Fractal; Cancer; Statistics; Mathematical analysis; Biology","score_opus":0.015135584662762911,"score_gpt":0.2539445665402357,"score_spread":0.23880898187747282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980637629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02556124,0.00019994455,0.96413773,0.008708064,0.0008056154,0.00013893054,0.000008649149,0.000021637648,0.0004181918],"genre_scores_gemma":[0.9971048,0.0000013680301,0.002170146,0.0002477799,0.0004396888,0.0000025809156,0.0000020067373,0.000009662855,0.000021954216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990682,0.00002629531,0.000252628,0.00013175086,0.00038690053,0.00013419583],"domain_scores_gemma":[0.9977501,0.0009827024,0.00068791915,0.00022923734,0.0003150341,0.000035021036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006898895,0.00009657313,0.000101827914,0.00012225415,0.00015153912,0.0002887734,0.0003609447,0.00003937713,0.0000025582651],"category_scores_gemma":[0.000140596,0.00005573573,0.00013991272,0.0003102241,0.000038890423,0.001327756,0.000020521526,0.00038119257,9.0879973e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006999108,0.00014432693,0.0046797376,0.000018817835,0.00008358987,0.00001063297,0.0006030538,0.0055214325,0.10723098,0.0009705084,0.0052125654,0.87482446],"study_design_scores_gemma":[0.0012411468,0.00048518137,0.31215554,0.00047809412,0.000112064416,0.00038810624,0.0017007856,0.63974214,0.026266115,0.0065380028,0.010588834,0.0003039954],"about_ca_topic_score_codex":0.0000034850154,"about_ca_topic_score_gemma":0.0000022261622,"teacher_disagreement_score":0.97154355,"about_ca_system_score_codex":0.00013571307,"about_ca_system_score_gemma":0.00006635694,"threshold_uncertainty_score":0.27846482},"labels":[],"label_agreement":null},{"id":"W1981453096","doi":"10.1117/12.877587","title":"Detection of architectural distortion in prior mammograms using measures of angular distribution","year":2011,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Receiver operating characteristic; Pattern recognition (psychology); Coherence (philosophical gambling strategy); Gabor filter; Computer science; Feature extraction; Histogram; Orientation (vector space); Computer vision; Mathematics; Statistics; Geometry","score_opus":0.02241881657133121,"score_gpt":0.2272350514207983,"score_spread":0.2048162348494671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981453096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98057956,0.00008382986,0.01836289,0.000117636155,0.00027468707,0.00040512448,0.000018875257,0.000052185078,0.00010519967],"genre_scores_gemma":[0.9166978,0.000018695342,0.08312261,0.0000056229437,0.00008549544,0.000042760246,0.0000023919238,0.000019393678,0.000005210812],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979777,5.014242e-8,0.00075854326,0.00032922113,0.00066456234,0.00026992508],"domain_scores_gemma":[0.99796975,0.000052570555,0.0006343602,0.0000785033,0.0012042285,0.000060619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067158724,0.00021158262,0.0003417725,0.00014582142,0.000047912188,0.000031781477,0.000837705,0.0001537145,0.0000017214477],"category_scores_gemma":[0.00032073547,0.00019070099,0.00041161958,0.00060256565,0.00026217737,0.0006595112,0.00015931111,0.00023094942,1.3700367e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014812492,0.0001366427,0.001527835,0.00044189705,0.00014906071,6.2716026e-8,0.0006957101,0.00032885026,0.9022499,0.08622865,0.000011724906,0.0080815805],"study_design_scores_gemma":[0.00067355897,0.00044275343,0.012391149,0.0003282673,0.00006948128,0.000019211117,0.00044875368,0.08145748,0.90147066,0.002410664,0.00006130376,0.000226741],"about_ca_topic_score_codex":0.00014653352,"about_ca_topic_score_gemma":0.0000023922028,"teacher_disagreement_score":0.08381798,"about_ca_system_score_codex":0.0003184999,"about_ca_system_score_gemma":0.000034801164,"threshold_uncertainty_score":0.7776561},"labels":[],"label_agreement":null},{"id":"W1982310921","doi":"10.1117/12.2007103","title":"Toward quantitative digital histopathology for prostate cancer: comparison of inter-slide interpolation methods for tumour measurement","year":2013,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"","keywords":"Prostatectomy; Interpolation (computer graphics); Computer science; Prostate cancer; Digital pathology; Artificial intelligence; Pathology; Medicine; Cancer","score_opus":0.0398540447318733,"score_gpt":0.3108905008880842,"score_spread":0.27103645615621086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982310921","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6965315,0.00023671343,0.29732051,0.0031096903,0.00066973263,0.0017862297,0.000058555175,0.000086660126,0.00020040342],"genre_scores_gemma":[0.43247336,0.000019466832,0.566226,0.000035171404,0.000116059295,0.0010572895,0.000003910226,0.0000328562,0.000035864367],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764067,6.815045e-8,0.0009907755,0.00049484894,0.00049219606,0.00038143602],"domain_scores_gemma":[0.993842,0.00033411875,0.0008939884,0.000073923766,0.004764646,0.00009133603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010616201,0.00029997158,0.0005638913,0.00014992109,0.00007760635,0.00017263422,0.0011950204,0.00014755242,0.0000033560113],"category_scores_gemma":[0.0011714023,0.00026253084,0.0006026857,0.0002808943,0.0001977093,0.0012853884,0.00022985412,0.00021090929,5.484607e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018089422,0.00013868211,0.00037595376,0.00092819816,0.00028726822,9.488735e-9,0.0018894738,0.00015928569,0.71311057,0.2674224,0.0024635529,0.013043712],"study_design_scores_gemma":[0.0013710257,0.0016727244,0.0005583995,0.00048760747,0.00012656538,0.0000065550007,0.0022682555,0.6027054,0.37411687,0.013725252,0.0025553466,0.0004059556],"about_ca_topic_score_codex":0.000029750578,"about_ca_topic_score_gemma":5.201808e-7,"teacher_disagreement_score":0.60254616,"about_ca_system_score_codex":0.00047508004,"about_ca_system_score_gemma":0.00007502099,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W1982388674","doi":"10.1007/s10278-013-9654-z","title":"An Efficient Fractal Method for Detection and Diagnosis of Breast Masses in Mammograms","year":2014,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Mammography; Radiology; Fractal; Biopsy; Artificial intelligence; Feature (linguistics); Computer-aided diagnosis; Pattern recognition (psychology); Computer science; Breast cancer; Mathematics; Cancer; Internal medicine","score_opus":0.008114782716642161,"score_gpt":0.27940798638152764,"score_spread":0.27129320366488546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982388674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30023867,0.000049123584,0.69923586,0.00018628695,0.0001848258,0.000048856717,0.000001818458,0.00000919731,0.000045372526],"genre_scores_gemma":[0.94316906,0.0000039744323,0.056708917,0.000022272203,0.00008390189,0.000004111177,1.3571454e-7,0.000006886858,7.441061e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919987,0.00003883092,0.00031114827,0.00013618954,0.00018404219,0.0001299157],"domain_scores_gemma":[0.9991242,0.00024059541,0.00031031657,0.00011690562,0.00014386704,0.00006407018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005460002,0.000076187374,0.0001602134,0.00022314809,0.00003168393,0.0002479413,0.0001982967,0.000020236675,5.3724256e-7],"category_scores_gemma":[0.000092721486,0.00006838883,0.000062877385,0.00020226695,0.000026865444,0.0014283301,0.00004348169,0.000098252975,1.6104069e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025357029,0.00008222683,0.028777057,0.000020451433,0.0000072659927,0.0000023382363,0.00019379258,0.001674652,0.0034438171,0.00005727981,0.0000044851217,0.9657113],"study_design_scores_gemma":[0.0009820363,0.0005902672,0.04995126,0.00014945205,0.000018704513,0.00092317566,0.00017622039,0.9063445,0.036523096,0.003679519,0.00047708803,0.00018470206],"about_ca_topic_score_codex":0.000013418048,"about_ca_topic_score_gemma":0.0000046625228,"teacher_disagreement_score":0.9655266,"about_ca_system_score_codex":0.000059734542,"about_ca_system_score_gemma":0.000020834532,"threshold_uncertainty_score":0.27888155},"labels":[],"label_agreement":null},{"id":"W1984374046","doi":"10.1117/12.530966","title":"Detection of architectural distortion in mammograms using phase portraits","year":2004,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Distortion (music); Computer vision; False positive paradox; Orientation (vector space); Pattern recognition (psychology); Mathematics","score_opus":0.013582830239303354,"score_gpt":0.24659045183094716,"score_spread":0.23300762159164382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984374046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9840899,0.000067788205,0.014262822,0.00052785105,0.00036817833,0.00043903262,0.00001046338,0.000082021244,0.00015194477],"genre_scores_gemma":[0.87284964,0.000015515632,0.12686896,0.00002131221,0.00015793586,0.0000522379,0.0000015771961,0.000024983381,0.000007803852],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978651,1.8870638e-8,0.00074417,0.00039346493,0.00066599686,0.00033128494],"domain_scores_gemma":[0.99845004,0.000051471237,0.000513971,0.00007024509,0.00083208334,0.00008217651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005247735,0.00024171654,0.00033081774,0.00020304197,0.000060362105,0.00007164374,0.0008924497,0.00015192646,0.0000014441121],"category_scores_gemma":[0.00022352983,0.00022146109,0.00042454887,0.0006949495,0.0001715494,0.00085372635,0.00015301206,0.0002991015,2.9378128e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093308496,0.0001790541,0.00017221725,0.00027936237,0.000106436484,1.3879767e-7,0.00042473286,0.0028804631,0.8866062,0.10285303,0.000009020743,0.0063959905],"study_design_scores_gemma":[0.0027183983,0.0008105407,0.0023314976,0.00047094063,0.00006940617,0.00007019687,0.0004033532,0.12030743,0.8657135,0.006580874,0.00014405184,0.00037984076],"about_ca_topic_score_codex":0.00006932457,"about_ca_topic_score_gemma":0.000001922608,"teacher_disagreement_score":0.11742697,"about_ca_system_score_codex":0.00048955454,"about_ca_system_score_gemma":0.000052726424,"threshold_uncertainty_score":0.90309215},"labels":[],"label_agreement":null},{"id":"W1986750896","doi":"10.1109/tbme.2015.2405791","title":"A Complete Color Normalization Approach to Histopathology Images Using Color Cues Computed From Saturation-Weighted Statistics","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Normalization (sociology); Artificial intelligence; Pattern recognition (psychology); Color space; Computer science; Computer vision; Pixel; Color normalization; Mathematics; Color image; Image processing; Image (mathematics)","score_opus":0.029358548008753413,"score_gpt":0.24393884325709692,"score_spread":0.2145802952483435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986750896","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053356905,0.000027057436,0.99086285,0.00024084086,0.0025150406,0.0002985351,0.00022089962,0.00047661294,0.000022497374],"genre_scores_gemma":[0.370114,0.0000042334123,0.62944394,0.00017605055,0.00012855872,0.000046165394,0.000050459104,0.00002303268,0.000013577394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983046,0.00007243735,0.00037728625,0.00046204927,0.0004705926,0.00031300628],"domain_scores_gemma":[0.99891263,0.00015436723,0.00007858335,0.00032729967,0.00018258378,0.00034453164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018583231,0.00022405232,0.00026669042,0.00039227953,0.00014406357,0.00009545865,0.00038929473,0.00015704785,0.000007413539],"category_scores_gemma":[0.000024321449,0.00023364743,0.000044902088,0.0009384908,0.000073520336,0.00031201326,0.00000980394,0.00026682392,0.000028538774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008734709,0.0003855738,0.000004768776,0.00004767816,0.00007175662,0.0000325548,0.0017516243,0.88847005,0.08856825,0.001169261,0.0016836317,0.017727472],"study_design_scores_gemma":[0.0005378002,0.00021768111,0.00011698147,0.000026832537,0.00002357577,0.000037332775,0.000017913033,0.9897391,0.0055294777,0.00007689338,0.0034243818,0.00025203667],"about_ca_topic_score_codex":0.00018958384,"about_ca_topic_score_gemma":0.000011062555,"teacher_disagreement_score":0.3647783,"about_ca_system_score_codex":0.0005410532,"about_ca_system_score_gemma":0.0001352713,"threshold_uncertainty_score":0.95278656},"labels":[],"label_agreement":null},{"id":"W1989913905","doi":"10.1186/1472-6963-7-s1-a11","title":"Maximizing the explanation of cost and LOS variation while minimizing the effects of coding","year":2007,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Health Information","funders":"","keywords":"Health administration; Health informatics; Nursing research; Variation (astronomy); Medicine; Coding (social sciences); Quality of Life Research; Public health; Health economics; Health services research; Statistics; Nursing; Mathematics","score_opus":0.05610144594925385,"score_gpt":0.3845641516394859,"score_spread":0.328462705690232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989913905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35459402,0.0019102377,0.63904804,0.0012013724,0.0005558687,0.0020927007,0.0000031399,0.000050593328,0.0005440296],"genre_scores_gemma":[0.9942752,0.0002133627,0.0051980647,0.00018243458,0.000081911836,0.00003196575,0.0000012655565,0.0000066148286,0.00000916922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978146,0.00054144114,0.00033900962,0.0002205793,0.00073441485,0.0003499582],"domain_scores_gemma":[0.9960894,0.0028988519,0.00024573025,0.00041434122,0.0002861713,0.00006548928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069052707,0.00006629728,0.00012383833,0.00021536714,0.0004352022,0.000066791414,0.0005914748,0.000048095928,0.0000018531118],"category_scores_gemma":[0.000067775276,0.000044172488,0.000020456037,0.0009690787,0.000065344466,0.0002938389,0.00024782098,0.0002292964,0.000001394736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043333918,0.00022969887,0.033121295,0.02304703,0.00008245185,0.0000048991883,0.16140112,0.00091380795,0.035375297,0.04702503,0.0002467902,0.6981192],"study_design_scores_gemma":[0.0011414859,0.0006783564,0.60958475,0.0013950749,0.00000843229,0.0000164302,0.0062024333,0.328937,0.048484504,0.002098382,0.0012727794,0.00018035063],"about_ca_topic_score_codex":0.001053822,"about_ca_topic_score_gemma":0.00083595497,"teacher_disagreement_score":0.69793886,"about_ca_system_score_codex":0.00016176986,"about_ca_system_score_gemma":0.0001647985,"threshold_uncertainty_score":0.33472675},"labels":[],"label_agreement":null},{"id":"W1991834834","doi":"10.1117/12.713660","title":"Fractal analysis for assessing tumour grade in microscopic images of breast tissue","year":2007,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Grading (engineering); Breast cancer; Fractal dimension; Fractal analysis; Fractal; Medicine; Radiology; Computer science; Pathology; Oncology; Cancer; Internal medicine; Mathematics; Biology","score_opus":0.010803285210498871,"score_gpt":0.2641881510745353,"score_spread":0.2533848658640364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991834834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97058827,0.00008316833,0.027055746,0.001193437,0.00024077814,0.00044025204,0.000032874974,0.000061628445,0.00030383293],"genre_scores_gemma":[0.73078877,0.000015937252,0.2688793,0.00002941526,0.00017725895,0.000050262042,0.0000030186534,0.000024311445,0.000031742187],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976615,1.9479248e-8,0.00083505677,0.00045429857,0.00061985705,0.0004292823],"domain_scores_gemma":[0.997675,0.00025136065,0.0005677776,0.0000755732,0.0013392107,0.000091051676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011855066,0.00025899112,0.000487476,0.0003460164,0.00006744821,0.0001580504,0.0012784814,0.00016931548,0.0000030837782],"category_scores_gemma":[0.00027982524,0.00023923046,0.0005722811,0.0011355022,0.00016594927,0.0011296712,0.00020104171,0.0002627243,2.9694218e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038304315,0.00012642692,0.0035367112,0.00039331036,0.0004020997,1.2454544e-7,0.00024333253,0.0002921894,0.90874124,0.08478167,0.00022824352,0.0012163693],"study_design_scores_gemma":[0.001029867,0.00023556767,0.043584343,0.00028630317,0.00022875836,0.00002030592,0.00075315475,0.057318464,0.89397705,0.001924781,0.00028546987,0.00035593062],"about_ca_topic_score_codex":0.00003701863,"about_ca_topic_score_gemma":0.0000012502833,"teacher_disagreement_score":0.24182355,"about_ca_system_score_codex":0.00026617505,"about_ca_system_score_gemma":0.000044907116,"threshold_uncertainty_score":0.97555345},"labels":[],"label_agreement":null},{"id":"W1992014265","doi":"10.1109/imac4s.2013.6526445","title":"Improvement of masses detection in digital mammograms employing non-linear filtering","year":2013,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Digital mammography; Visualization; Computer vision; Artificial intelligence; Contrast (vision); Filter (signal processing); Digital filter; Linear filter; Contrast enhancement; Mammography; Pattern recognition (psychology)","score_opus":0.01203446061992772,"score_gpt":0.23173213120642142,"score_spread":0.2196976705864937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992014265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4760729,0.0000030389892,0.52295756,0.000030151698,0.00018551509,0.0001366222,2.009023e-7,0.0000628832,0.00055110955],"genre_scores_gemma":[0.9825023,0.0000028901268,0.017267913,0.000028619126,0.00003474068,0.000054039127,3.0926884e-7,0.000007131109,0.00010207059],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918574,0.000004159099,0.00023701333,0.00022724636,0.0001638811,0.00018194059],"domain_scores_gemma":[0.9995444,0.00002588219,0.00007245926,0.00026613218,0.000056606495,0.000034536715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008031654,0.00008522984,0.000097830016,0.00011902557,0.00002834654,0.00012322029,0.00025817964,0.000036691687,0.000021701871],"category_scores_gemma":[0.000013061835,0.00007947256,0.000035747376,0.00032023157,0.000016125021,0.0012150935,0.00018284029,0.000075032964,0.000033300366],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002826329,0.000034506615,0.0028922935,0.000028754981,0.0000067940923,0.0000010523073,0.00015352364,0.00047124297,0.16084033,0.000041178417,0.000015742913,0.83551174],"study_design_scores_gemma":[0.00030004524,0.00034163365,0.008342167,0.000035368,0.0000011838439,0.0000054996713,0.00010626896,0.23914151,0.7501596,0.0011957405,0.00019222274,0.00017873273],"about_ca_topic_score_codex":0.00080054894,"about_ca_topic_score_gemma":0.000100452635,"teacher_disagreement_score":0.835333,"about_ca_system_score_codex":0.00009106429,"about_ca_system_score_gemma":0.00001522289,"threshold_uncertainty_score":0.32407966},"labels":[],"label_agreement":null},{"id":"W1992083555","doi":"10.1117/12.480828","title":"Mammographic thickness compensation for image analysis and display enhancement","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Imaging phantom; SIGNAL (programming language); Attenuator (electronics); Computer vision; Projection (relational algebra); Artificial intelligence; Mammography; Image processing; Image (mathematics); Optics; Algorithm; Attenuation; Physics; Breast cancer","score_opus":0.008985723575121141,"score_gpt":0.2313149523795374,"score_spread":0.22232922880441625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992083555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314179,0.000070056565,0.06539823,0.0016349937,0.00023957012,0.000583912,0.000016639724,0.00006869684,0.0005700096],"genre_scores_gemma":[0.53240955,0.00009641323,0.46691713,0.00007432028,0.000110831716,0.00028418572,0.000004695618,0.00002619392,0.00007668283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99806494,2.5413206e-8,0.0005442826,0.0004880812,0.00057657814,0.00032611965],"domain_scores_gemma":[0.99777544,0.00018326713,0.0003865696,0.000081091355,0.0014781283,0.000095500975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008981971,0.00025241976,0.00036623128,0.00020776919,0.00013412171,0.00021733616,0.0007965892,0.0001327254,0.0000050338467],"category_scores_gemma":[0.00031753143,0.00021998977,0.0005579398,0.000851002,0.00017812276,0.00083884253,0.00012709424,0.00018088434,4.2300513e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030065044,0.00007119875,0.0005570258,0.000281813,0.0007035724,2.4728122e-8,0.00017777339,0.00006560356,0.31285203,0.684365,0.00034247234,0.00055346783],"study_design_scores_gemma":[0.0023210186,0.0008814208,0.0059142075,0.0002655712,0.001087613,0.00002975723,0.00085610733,0.34759328,0.6190804,0.01715347,0.003933549,0.0008835982],"about_ca_topic_score_codex":0.000007760123,"about_ca_topic_score_gemma":5.5021167e-7,"teacher_disagreement_score":0.6672115,"about_ca_system_score_codex":0.00013560412,"about_ca_system_score_gemma":0.000027439288,"threshold_uncertainty_score":0.8970923},"labels":[],"label_agreement":null},{"id":"W1993233243","doi":"10.1109/memea.2012.6226626","title":"Detection of architectural distortion in prior mammograms using measures of angular dispersion","year":2012,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Gabor filter; Receiver operating characteristic; Mathematics; Pattern recognition (psychology); Distortion (music); Computer vision; Feature extraction; Optics; Computer science; Physics; Statistics; Bandwidth (computing)","score_opus":0.03298540243345616,"score_gpt":0.2566321633651544,"score_spread":0.22364676093169822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993233243","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5444458,0.00013055008,0.45505187,0.000010896627,0.00023257836,0.00007288352,1.8471101e-7,0.000021940967,0.00003329909],"genre_scores_gemma":[0.986329,0.0000036854483,0.013605216,0.0000051329926,0.000041522395,0.0000032787557,2.742864e-7,0.000005022007,0.0000068560903],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991284,0.00006753818,0.00023471795,0.00013847814,0.00026258428,0.00016829195],"domain_scores_gemma":[0.9995241,0.00002170626,0.00013533563,0.00023397054,0.000046854995,0.000038025555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031002978,0.00007403587,0.000119785625,0.0001767204,0.000030910825,0.000007939861,0.00016308007,0.00004845042,0.0000037038674],"category_scores_gemma":[0.000025931104,0.000065283,0.00005648348,0.0004340315,0.00005813773,0.00042554786,0.00006568961,0.00007263734,8.162916e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003081553,0.0000630724,0.025393605,0.000035428235,0.0000066103075,2.1102645e-7,0.0009316196,0.0009258391,0.4091001,0.00020610678,5.661693e-7,0.56330603],"study_design_scores_gemma":[0.000272262,0.00013145698,0.13032825,0.000045883513,0.000008875444,0.000019627998,0.00010195743,0.041073468,0.8276129,0.00022332955,0.000055676282,0.00012635057],"about_ca_topic_score_codex":0.0011210303,"about_ca_topic_score_gemma":0.00032711783,"teacher_disagreement_score":0.56317973,"about_ca_system_score_codex":0.00016087323,"about_ca_system_score_gemma":0.000016154338,"threshold_uncertainty_score":0.26621637},"labels":[],"label_agreement":null},{"id":"W1995166554","doi":"10.4103/2153-3539.129455","title":"Guidelines from the Canadian Association of Pathologists for establishing a telepathology service for anatomic pathology using whole-slide imaging","year":2014,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre hospitalier universitaire de Québec; Canadian Partnership Against Cancer; Royal Alexandra Hospital; Cégep de Rimouski; Island Health; Montreal Children's Hospital; St. John’s Health Sciences Centre; Western University; Dalhousie University; Ottawa Hospital; University Health Network; Ministry of Health; Interior Health; Horizon Health Network; Royal Columbian Hospital; Diagnostic Services Manitoba; Canada Health Infoway; Alberta Health Services; Saint John Regional Hospital; Canadian Electricity Association","funders":"","keywords":"Telepathology; Hematopathology; Medical physics; Medicine; Medical laboratory; Digital pathology; Modalities; Pathology; Virtual microscopy; Service (business); Standardization; Medical education; Computer science; Health care; Telemedicine; Business; Political science","score_opus":0.03363023587749861,"score_gpt":0.30024929013930707,"score_spread":0.26661905426180843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995166554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23996456,0.000106285464,0.75126123,0.006309337,0.0018927933,0.00030076245,0.00009283325,0.000022471166,0.000049700837],"genre_scores_gemma":[0.37518635,0.000028861106,0.6156392,0.008377476,0.0006855711,0.000024924375,0.00001858748,0.0000270345,0.000011988179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969535,0.00031220858,0.0017480257,0.00016994477,0.00029565155,0.00052069797],"domain_scores_gemma":[0.99199283,0.0016681274,0.0031975724,0.00049795303,0.0025294921,0.000114028546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062577464,0.00021203057,0.0005709288,0.00038377004,0.0003562803,0.00015308255,0.0012568727,0.0003241978,0.0000015754171],"category_scores_gemma":[0.004749704,0.00016942757,0.00019998114,0.00035935148,0.00009209259,0.0011368289,0.00015399639,0.00041599397,0.00000224045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000585957,0.0002877185,0.21302958,0.0010758203,0.0007447577,0.0005180126,0.09461417,0.101004295,0.060289606,0.01993696,0.050239827,0.45767328],"study_design_scores_gemma":[0.002871592,0.00051684957,0.007152937,0.00017660648,0.0002570607,0.0029507354,0.0016630567,0.9261552,0.0018656707,0.034371838,0.021565948,0.00045248025],"about_ca_topic_score_codex":0.0011099905,"about_ca_topic_score_gemma":0.013336357,"teacher_disagreement_score":0.8251509,"about_ca_system_score_codex":0.0006346753,"about_ca_system_score_gemma":0.0007313391,"threshold_uncertainty_score":0.7442},"labels":[],"label_agreement":null},{"id":"W1995235228","doi":"10.3233/acp-2011-0020","title":"Abstracts of the 1st Congress of the International Academy of Digital Pathology August 3–5, 2011 Quebec city, Canada","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Digital pathology; Medicine; Political science; Pathology; Computer science","score_opus":0.233198057721166,"score_gpt":0.46403503074326663,"score_spread":0.23083697302210063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995235228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869677,0.0009098429,0.0005349472,0.00060474855,0.0030406693,0.00032726958,0.00011357768,0.000011283605,0.007489952],"genre_scores_gemma":[0.99893296,0.0002685258,0.00012180153,0.00017436118,0.000064555235,0.0000088171055,7.0232244e-7,0.000014659945,0.0004136328],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99734116,0.00015494147,0.0009859554,0.00030857456,0.0009801892,0.000229205],"domain_scores_gemma":[0.9968953,0.00021177017,0.0018285306,0.00057658606,0.00039630022,0.00009150892],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007364701,0.00019109862,0.00044690946,0.00021636265,0.000102454185,0.00019167218,0.008855535,0.00011275211,0.0014153845],"category_scores_gemma":[0.00020429122,0.00013068006,0.00017191764,0.0004940114,0.00040014487,0.002046836,0.002711467,0.0004329143,0.0000012495375],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012769885,0.0003120929,0.85840094,0.000099161465,0.0003414816,0.000014900823,0.00064440083,0.00041899845,0.050525744,0.0013010451,0.07058014,0.017233428],"study_design_scores_gemma":[0.00020140443,0.0000057212355,0.7577517,0.00015801736,0.000019324576,0.00002488399,0.00002870988,0.00006458556,0.23721565,0.0028418908,0.0015694266,0.00011867293],"about_ca_topic_score_codex":0.26257455,"about_ca_topic_score_gemma":0.09179666,"teacher_disagreement_score":0.18668991,"about_ca_system_score_codex":0.00018837255,"about_ca_system_score_gemma":0.00079382316,"threshold_uncertainty_score":0.9994975},"labels":[],"label_agreement":null},{"id":"W1996792125","doi":"10.1109/iembs.2010.5627180","title":"Application of fractal analysis to mammography","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal dimension; Mammography; Fractal; Dimension (graph theory); Receiver operating characteristic; Artificial intelligence; Box counting; Pattern recognition (psychology); Compact space; Mathematics; Computer science; Fractal analysis; Medicine; Statistics; Combinatorics; Mathematical analysis; Breast cancer; Cancer","score_opus":0.003534030842952614,"score_gpt":0.2372903824470869,"score_spread":0.23375635160413427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996792125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101367205,0.0000014583096,0.8953957,0.00030399972,0.000103565675,0.000059528425,4.3783163e-7,0.00006554627,0.002702533],"genre_scores_gemma":[0.8745988,2.909112e-7,0.12523177,0.00009859896,0.00002246037,0.000014555463,4.0051094e-7,0.0000014269876,0.00003167324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995345,0.0000053939175,0.00009341874,0.00016838644,0.0001335783,0.000064752865],"domain_scores_gemma":[0.9993899,0.000017983024,0.000041212985,0.0004502755,0.000058855305,0.000041764368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010005728,0.000035469413,0.00006377498,0.00027186616,0.000020712476,0.000018147328,0.00033230265,0.00002809843,0.000027687167],"category_scores_gemma":[0.0000055876903,0.00003260362,0.00006421708,0.0019221627,0.000011773772,0.00013022091,0.000058240774,0.000054067492,0.000024966126],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061650435,0.000066804285,0.06465013,0.00000483686,0.00019692082,2.6956738e-7,0.000306389,0.00075517024,0.20284067,0.057180025,0.0005578521,0.6734348],"study_design_scores_gemma":[0.00013945374,0.00011879074,0.42001626,9.692855e-7,0.00009560588,0.00000250883,0.000018811286,0.3119392,0.24151167,0.005336002,0.020562258,0.0002584603],"about_ca_topic_score_codex":0.00020034563,"about_ca_topic_score_gemma":0.00033393022,"teacher_disagreement_score":0.7732316,"about_ca_system_score_codex":0.000005558121,"about_ca_system_score_gemma":0.000007851134,"threshold_uncertainty_score":0.1329537},"labels":[],"label_agreement":null},{"id":"W1996941612","doi":"10.1007/s10278-007-9035-6","title":"Radon-Domain Detection of the Nipple and the Pectoral Muscle in Mammograms","year":2007,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundação de Apoio ao Ensino, Pesquisa e Assistência do Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; University of Calgary","keywords":"Pectoral muscle; Mammography; Medicine; Edge detection; Point location; Domain (mathematical analysis); Computer science; Anatomy; Image processing; Radiology; Computer vision; Image (mathematics); Point (geometry); Mathematics; Breast cancer; Geometry","score_opus":0.005384542515084909,"score_gpt":0.21742409009803004,"score_spread":0.21203954758294513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996941612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74448526,0.000334671,0.25295892,0.0011386609,0.0005410469,0.000077911296,3.6916163e-7,0.000008030751,0.00045509933],"genre_scores_gemma":[0.99884087,0.000006063083,0.0009901368,0.00006271912,0.0000870086,4.8901126e-7,1.8836204e-8,0.000004681628,0.000008003816],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999149,0.00003736861,0.0003255783,0.00008383991,0.00026540636,0.00013876741],"domain_scores_gemma":[0.99928856,0.0001310923,0.00031391854,0.00015923636,0.00006936929,0.000037821024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000883548,0.00006410296,0.000114406255,0.000103988794,0.000059369006,0.00018248685,0.00034934963,0.000015086077,5.9304335e-7],"category_scores_gemma":[0.000088141904,0.000037126105,0.00008426879,0.00038549033,0.00013883912,0.0010451261,0.00012265144,0.00020666752,3.049123e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012925336,0.000058721736,0.064369306,0.000015961434,0.000018582286,0.000027752974,0.0024771984,0.00012488272,0.01273984,0.00076983735,0.000044319586,0.9192243],"study_design_scores_gemma":[0.0106263915,0.00044256705,0.73605347,0.00048419728,0.00004914664,0.0047784713,0.00374315,0.03769842,0.080529444,0.11555444,0.009407573,0.0006327436],"about_ca_topic_score_codex":0.000031231888,"about_ca_topic_score_gemma":0.00004253929,"teacher_disagreement_score":0.9185916,"about_ca_system_score_codex":0.00008765584,"about_ca_system_score_gemma":0.000033375763,"threshold_uncertainty_score":0.17597249},"labels":[],"label_agreement":null},{"id":"W1997005084","doi":"10.5858/arpa.2012-0412-oa","title":"Analysis of Addenda in Anatomic Pathology as a Quality Monitoring Initiative","year":2014,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Subspecialty; Context (archaeology); Medicine; Audit; Pathology; General surgery; Biology; Management","score_opus":0.02375253171823658,"score_gpt":0.3307198170584482,"score_spread":0.3069672853402116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997005084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371931,0.00044144774,0.060124177,0.00038811774,0.00043679966,0.000104991035,0.000016516251,0.00004294844,0.0012518909],"genre_scores_gemma":[0.9942518,0.00012733771,0.005302713,0.00019472276,0.000085207794,0.000019870477,0.000005018677,0.000008500534,0.000004825398],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968934,0.0013669911,0.0007393866,0.00049843726,0.00024352208,0.000258247],"domain_scores_gemma":[0.9971196,0.0013559216,0.00056068413,0.0007505394,0.00013538588,0.0000778872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001404444,0.0001671865,0.0008188708,0.0012457863,0.000037813785,0.0000025423312,0.0006230858,0.00010251825,0.000016535349],"category_scores_gemma":[0.0009252706,0.00015461535,0.0000800498,0.0019608529,0.0008370035,0.00016195672,0.00019071484,0.00028154888,0.0000026257983],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021077509,0.00021818842,0.56651217,0.00013254724,0.0004794035,0.00032701323,0.039118238,0.0006391947,0.3119466,0.027248394,0.000023848406,0.053143647],"study_design_scores_gemma":[0.0013348424,0.0008657995,0.953597,0.00011241151,0.00017587803,0.0000151023705,0.00094994466,0.0035613498,0.031114941,0.007981876,0.000099409954,0.00019141489],"about_ca_topic_score_codex":0.000113124624,"about_ca_topic_score_gemma":0.000118326745,"teacher_disagreement_score":0.3870849,"about_ca_system_score_codex":0.00004074622,"about_ca_system_score_gemma":0.00015268671,"threshold_uncertainty_score":0.6305031},"labels":[],"label_agreement":null},{"id":"W1997181982","doi":"10.1118/1.2961448","title":"SU‐GG‐I‐50: Breast Tissue Classification in Digital Breast Tomosynthesis Images Using Texture Features","year":2008,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Digital mammography; Mammography; Breast tissue; Artificial intelligence; Breast imaging; Breast density; Nuclear medicine; Medicine; Digital Breast Tomosynthesis; Pattern recognition (psychology); Computer science; Cancer; Internal medicine","score_opus":0.018974372563070135,"score_gpt":0.25993931504742745,"score_spread":0.24096494248435732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997181982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06646507,0.00016849807,0.92697537,0.0036416086,0.0006047041,0.0002066911,0.000043848064,0.00029314458,0.0016010847],"genre_scores_gemma":[0.9976647,0.000021378066,0.0012825555,0.00018748021,0.000696052,0.000010258415,0.000008038202,0.000018546141,0.00011099911],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981455,0.0000394691,0.00023031529,0.00044704985,0.00082468975,0.00031293847],"domain_scores_gemma":[0.99907243,0.0001221904,0.00009954585,0.00045691925,0.000080743404,0.00016815441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013932111,0.00018122199,0.00020785592,0.00006402972,0.0001434265,0.00013303393,0.0006632551,0.00016274577,0.000027552614],"category_scores_gemma":[0.00006882317,0.00016595387,0.0000589466,0.0005835871,0.00021332683,0.000962467,0.0001715328,0.00038417644,0.00004473242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015431333,0.00022649864,0.0038368865,0.000027455666,0.00001551528,0.00007953883,0.00059093325,0.0000622765,0.0026117603,0.000766862,0.002929781,0.98883706],"study_design_scores_gemma":[0.0030849476,0.0003139254,0.70184577,0.0011048812,0.00006943464,0.0119055705,0.00023985955,0.14579202,0.08495325,0.035502028,0.012029446,0.003158865],"about_ca_topic_score_codex":0.00012144002,"about_ca_topic_score_gemma":0.000008862315,"teacher_disagreement_score":0.9856782,"about_ca_system_score_codex":0.0002096925,"about_ca_system_score_gemma":0.00021285402,"threshold_uncertainty_score":0.6767402},"labels":[],"label_agreement":null},{"id":"W1997241015","doi":"10.1097/pai.0000000000000069","title":"Standardization of Negative Controls in Diagnostic Immunohistochemistry","year":2014,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lions Gate Hospital; University of Toronto; University Health Network","funders":"National Cancer Institute","keywords":"Standardization; Medicine; Terminology; Clinical Practice; Immunohistochemistry; Pathology; Computer science; Family medicine","score_opus":0.0034230488180172322,"score_gpt":0.22999722257343375,"score_spread":0.22657417375541652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997241015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29269394,0.00051766477,0.6982601,0.00013237128,0.00021180129,0.00032478393,0.0000064248834,0.00009770003,0.007755172],"genre_scores_gemma":[0.98642975,0.000023892086,0.012909235,0.00022746294,0.000033403918,0.00027183065,0.000024753565,0.000032828837,0.00004685852],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975856,0.000099134304,0.0007770165,0.00073307176,0.00035998275,0.00044521596],"domain_scores_gemma":[0.9973793,0.0005385906,0.00051606534,0.0013176851,0.00017387928,0.0000744766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048131528,0.00032636494,0.00054704334,0.0001228539,0.00008046155,0.00003058217,0.001065259,0.00029513508,0.000040185554],"category_scores_gemma":[0.00081665843,0.00039548098,0.00012410866,0.0005457452,0.00033390833,0.00011041441,0.0002761994,0.00041065115,0.000015975416],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007003565,0.00006833185,0.000022381295,0.00004798682,0.000033721437,0.000017764927,0.00015399861,0.0018159647,0.98932624,0.004684752,0.00008332358,0.0036754708],"study_design_scores_gemma":[0.0018254431,0.000094700365,0.0002554238,0.000043514687,0.000021372169,0.000059906757,0.00003357105,0.00090648583,0.9901226,0.006079468,0.00020236701,0.00035513664],"about_ca_topic_score_codex":0.00006415596,"about_ca_topic_score_gemma":1.4904509e-7,"teacher_disagreement_score":0.6937358,"about_ca_system_score_codex":0.0005214557,"about_ca_system_score_gemma":0.0001658438,"threshold_uncertainty_score":0.99984974},"labels":[],"label_agreement":null},{"id":"W2000003470","doi":"10.1117/12.767669","title":"Detection of architectural distortion in mammograms acquired prior to the detection of breast cancer using texture and fractal analysis","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research","keywords":"Mammography; Fractal dimension; Distortion (music); Receiver operating characteristic; Artificial intelligence; Fractal; Computer science; Fractal analysis; Breast cancer; Pattern recognition (psychology); Texture (cosmology); Computer vision; Mathematics; Cancer; Medicine; Image (mathematics); Telecommunications","score_opus":0.01005948340341973,"score_gpt":0.22945030121139579,"score_spread":0.21939081780797606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000003470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98521084,0.0001207359,0.013238707,0.00071700587,0.00020188831,0.0004338328,0.00002356302,0.00003635372,0.000017048746],"genre_scores_gemma":[0.9803034,0.000049682185,0.019372022,0.000022182201,0.00015069336,0.00007443837,8.393562e-7,0.000018567394,0.000008165224],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998167,7.8600166e-8,0.00061100244,0.00036157388,0.0006146379,0.00024571025],"domain_scores_gemma":[0.9983431,0.0000774447,0.0005056801,0.00007851425,0.00092591404,0.00006935032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004301524,0.00021092333,0.0003641444,0.0002711132,0.00010280225,0.000044142504,0.00064932567,0.00013631125,0.000001608531],"category_scores_gemma":[0.00014319031,0.00016346616,0.00039532554,0.0013530432,0.00019751774,0.0005560216,0.00017776278,0.0002046035,8.409821e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017573185,0.00006456139,0.003510735,0.00020810118,0.00042284038,6.4713035e-8,0.0011049843,0.0040863925,0.9732735,0.0023090097,0.000006876877,0.014837182],"study_design_scores_gemma":[0.000752504,0.00036179356,0.14371257,0.00023748547,0.00029876508,0.00008413546,0.0005720422,0.44441208,0.4089278,0.00025583088,0.000073988565,0.00031099134],"about_ca_topic_score_codex":0.0002746486,"about_ca_topic_score_gemma":0.000018168936,"teacher_disagreement_score":0.5643457,"about_ca_system_score_codex":0.00029492448,"about_ca_system_score_gemma":0.00003191401,"threshold_uncertainty_score":0.66659564},"labels":[],"label_agreement":null},{"id":"W2000218629","doi":"10.1007/s10044-006-0023-0","title":"A new approach for breast skin-line estimation in mammograms","year":2006,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Line (geometry); Thresholding; Pixel; Artificial intelligence; Boundary (topology); Standard deviation; Computer science; Ground truth; Pattern recognition (psychology); Euclidean distance; Enhanced Data Rates for GSM Evolution; Mathematics; Computer vision; Image (mathematics); Statistics; Geometry; Mathematical analysis","score_opus":0.011499080979121171,"score_gpt":0.25949574408666826,"score_spread":0.2479966631075471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000218629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000939812,0.000036721587,0.9980251,0.0004390515,0.000006794536,0.00027553586,0.000012569804,0.000044828997,0.00021956311],"genre_scores_gemma":[0.8434645,0.000005339221,0.15576082,0.00005047687,0.00007865959,0.00041263577,0.00007266324,0.000004410675,0.00015047287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926907,0.000011679199,0.00018670424,0.00032726297,0.00009164571,0.000113652415],"domain_scores_gemma":[0.99953187,0.000026517266,0.000077435776,0.00029515228,0.00003160962,0.000037425845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011692825,0.00007389422,0.00012281128,0.00020693183,0.000075067335,0.000108170425,0.0001849799,0.00003244232,0.0000071469285],"category_scores_gemma":[9.601315e-7,0.00007293262,0.000069268965,0.0011859282,0.00001173237,0.000119979835,0.000034903143,0.00004005561,0.000004666676],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.572065e-7,0.000051804538,0.007946063,0.000008815132,0.000031718562,4.5198835e-8,0.000026214795,0.014486176,0.00005661791,0.0017968079,0.000075638214,0.9755191],"study_design_scores_gemma":[0.00018626348,0.000005926938,0.064022176,0.000001755983,0.00008660383,0.000003447768,0.0000073317037,0.9303793,0.00020805853,0.0044724797,0.00053175876,0.00009491246],"about_ca_topic_score_codex":0.0016290658,"about_ca_topic_score_gemma":0.00069302006,"teacher_disagreement_score":0.97542423,"about_ca_system_score_codex":0.000034570592,"about_ca_system_score_gemma":0.000013117675,"threshold_uncertainty_score":0.29741058},"labels":[],"label_agreement":null},{"id":"W2003243867","doi":"10.1117/1.2920413","title":"Polygonal approximation of contours based on the turning angle function","year":2008,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Function (biology); Computer science; Pattern recognition (psychology); Measure (data warehouse); Receiver operating characteristic; Computer vision; Mathematics; Data mining","score_opus":0.009554413727215078,"score_gpt":0.21140006204664089,"score_spread":0.2018456483194258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003243867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07828453,0.00048048253,0.91663116,0.0032097818,0.00038053657,0.000071244736,1.6044812e-7,0.00002140376,0.00092070835],"genre_scores_gemma":[0.9974242,0.00001388757,0.0019339166,0.00042375497,0.00017498608,0.0000019812712,2.0403279e-7,0.0000072052508,0.000019874611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880964,0.00010200117,0.0003045883,0.000107316526,0.00044540904,0.00023105444],"domain_scores_gemma":[0.9988651,0.00016846521,0.00055378163,0.00018759043,0.00019569769,0.00002931889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007861849,0.000085330816,0.00012813605,0.0001814473,0.00015389548,0.000031802734,0.00033804023,0.000020560467,0.000013349563],"category_scores_gemma":[0.00006646858,0.000061664774,0.000104561324,0.00031573224,0.000044701545,0.00050592964,0.000019308865,0.0003780762,0.000001876552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016241637,0.0008103096,0.018598866,0.00010739424,0.00043049752,0.00010188235,0.004587995,0.15605748,0.20937093,0.08677332,0.01420417,0.507333],"study_design_scores_gemma":[0.001177289,0.00091612403,0.0064413296,0.00012323172,0.000032434316,0.0006231249,0.000095883384,0.9365927,0.045031294,0.006165545,0.002622567,0.00017848065],"about_ca_topic_score_codex":0.000008858271,"about_ca_topic_score_gemma":0.0000014031885,"teacher_disagreement_score":0.9191397,"about_ca_system_score_codex":0.00030345994,"about_ca_system_score_gemma":0.00039131587,"threshold_uncertainty_score":0.25146165},"labels":[],"label_agreement":null},{"id":"W2005297934","doi":"10.1117/12.535310","title":"Nonlinear enhancement of mammograms using area morphology","year":2004,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Morphology (biology); Nonlinear system; Computer science; Physics; Geology","score_opus":0.01702482220815432,"score_gpt":0.24332759057614362,"score_spread":0.2263027683679893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005297934","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818126,0.000098577235,0.015244143,0.0013798021,0.00045691646,0.00042327517,0.000014842334,0.00008149865,0.00048837054],"genre_scores_gemma":[0.38122055,0.000060272698,0.6182576,0.000097315744,0.00023080825,0.00006404321,0.0000022984293,0.000033380737,0.000033746295],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99764717,1.2273239e-8,0.0007488153,0.00045499697,0.00075060903,0.00039838726],"domain_scores_gemma":[0.99763346,0.00006829867,0.00055885,0.00010119709,0.0015383126,0.000099900724],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005312753,0.00027962922,0.00040881848,0.0001311427,0.0000737791,0.000078618075,0.0015121563,0.00018348018,0.0000068447753],"category_scores_gemma":[0.00020549004,0.00024896956,0.00051152596,0.00053003593,0.00025285356,0.000684453,0.00033788785,0.00027315837,0.0000010875382],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041232248,0.00016452803,0.00011283726,0.00025037045,0.00023078025,1.3244828e-7,0.00022347613,0.0008925,0.7672741,0.23011838,0.00019843651,0.0004932473],"study_design_scores_gemma":[0.0011181483,0.0006032258,0.00012793315,0.00032723608,0.000080928294,0.000040727507,0.00033652582,0.09887449,0.8931021,0.004279831,0.0008009078,0.00030791562],"about_ca_topic_score_codex":0.000034650897,"about_ca_topic_score_gemma":2.107164e-7,"teacher_disagreement_score":0.60301346,"about_ca_system_score_codex":0.00035598374,"about_ca_system_score_gemma":0.0000751855,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W2006849327","doi":"10.1088/0031-9155/59/14/3697","title":"Computer-aided detection (CAD) of breast masses in mammography: combined detection and ensemble classification","year":2014,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); University of Toronto","funders":"","keywords":"CAD; Mammography; Computer science; Sensitivity (control systems); Benchmark (surveying); Artificial intelligence; Computer-aided diagnosis; Pattern recognition (psychology); Algorithm; Medicine; Breast cancer","score_opus":0.0914172295712387,"score_gpt":0.32050674109416155,"score_spread":0.22908951152292284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006849327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45194286,0.000044867564,0.5471262,0.00042742435,0.00025271357,0.00009411799,5.216972e-7,0.000024203455,0.00008715102],"genre_scores_gemma":[0.9977855,0.00012412877,0.0017802201,0.00008633459,0.00020167719,0.000014508072,0.0000024341455,0.000004332623,8.31627e-7],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990882,0.00015459183,0.0002495078,0.00030661596,0.0000647814,0.0001362788],"domain_scores_gemma":[0.9994186,0.00018443193,0.00013691078,0.00017856208,0.000050910752,0.000030545347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039352145,0.00010504186,0.00024074041,0.00021960179,0.00003756456,0.000007761034,0.00011062713,0.000087079745,5.981514e-7],"category_scores_gemma":[0.000021306561,0.00008846791,0.000015808773,0.00050590275,0.00017121578,0.00013992366,0.000057705638,0.00014594395,3.464646e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046607547,0.000041730334,0.016107935,0.000048231326,0.0000078731855,2.988215e-7,0.00025333356,0.000029322178,0.19843026,0.0058915354,0.000006369964,0.7791365],"study_design_scores_gemma":[0.00253842,0.002097667,0.46049055,0.00014055963,0.000015844118,0.0000451667,0.000117447664,0.40494213,0.026886925,0.10221552,0.00026373813,0.00024602102],"about_ca_topic_score_codex":0.00041196868,"about_ca_topic_score_gemma":0.00031566332,"teacher_disagreement_score":0.7788905,"about_ca_system_score_codex":0.000027791575,"about_ca_system_score_gemma":0.0000086007,"threshold_uncertainty_score":0.36076167},"labels":[],"label_agreement":null},{"id":"W2007078234","doi":"10.1016/j.compbiomed.2012.09.008","title":"Colorization of CT images to improve tissue contrast for tumor segmentation","year":2012,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Calgary","keywords":"Segmentation; Artificial intelligence; Thresholding; Computer science; False positive paradox; Grayscale; Pixel; Pattern recognition (psychology); Contrast (vision); Computer vision; Image segmentation; Image (mathematics)","score_opus":0.01263160323887479,"score_gpt":0.3230265880365096,"score_spread":0.3103949847976348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007078234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07645915,0.00034735465,0.91977906,0.0010371794,0.0019402904,0.00037004726,0.0000028868044,0.000020293484,0.000043742126],"genre_scores_gemma":[0.9411663,0.000027280339,0.057851266,0.0006461233,0.00024528324,0.000043631127,0.000006686878,0.000002869515,0.0000105623385],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945664,0.000037560563,0.00017037934,0.00015691074,0.000035739264,0.00014274483],"domain_scores_gemma":[0.99955326,0.00017993775,0.000076802586,0.000098582575,0.000040688865,0.000050754737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031624406,0.0000637913,0.00015126141,0.00010685398,0.000030355477,0.0000028406064,0.00011484915,0.0000230399,0.0000017795788],"category_scores_gemma":[0.00005357078,0.000052951367,0.0000072900957,0.00014135274,0.00007991292,0.00011968219,0.00004935586,0.00003674922,6.266847e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098145014,0.00006385185,0.022551008,0.00011941272,0.00002456211,0.0000014079442,0.0025540525,0.000040989486,0.40700966,0.025768172,0.0023047337,0.539464],"study_design_scores_gemma":[0.00973567,0.008863086,0.13663244,0.0004582016,0.000060630857,0.00012357855,0.0005492834,0.028821256,0.78287953,0.016733667,0.014481207,0.00066143787],"about_ca_topic_score_codex":0.00003058548,"about_ca_topic_score_gemma":0.00000475642,"teacher_disagreement_score":0.8647072,"about_ca_system_score_codex":0.00003472601,"about_ca_system_score_gemma":0.000011763646,"threshold_uncertainty_score":0.21592942},"labels":[],"label_agreement":null},{"id":"W2008038138","doi":"10.1088/1742-6596/489/1/012088","title":"Semi-automated contour recognition using DICOMautomaton","year":2014,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Agency; Conquer Cancer Foundation","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision","score_opus":0.03692877275879976,"score_gpt":0.26641474735278076,"score_spread":0.229485974593981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008038138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15440731,0.000023173803,0.843699,0.00025186833,0.0008415362,0.00005323105,0.0000016869803,0.0002024373,0.000519785],"genre_scores_gemma":[0.9763532,0.000025383255,0.023104796,0.00009361536,0.00039551195,0.0000014486666,8.69524e-7,0.000011166416,0.0000139587855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987351,0.00013539026,0.00040466213,0.00016040288,0.0003668366,0.00019763762],"domain_scores_gemma":[0.99822646,0.000067914945,0.0006837111,0.00024492235,0.0006901972,0.000086781816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033939985,0.00014851082,0.00028167522,0.000085281084,0.00012232122,0.00025790185,0.0004677618,0.00006524903,0.000010617519],"category_scores_gemma":[0.00006095581,0.0001366574,0.00009507598,0.00028172767,0.0000713593,0.002321023,0.000081280654,0.00022003833,0.000012671082],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000830504,0.00013117607,0.00047899142,0.00009487974,0.00012622813,0.000021859127,0.0018185491,0.0020093825,0.119971454,0.029224304,0.00071501813,0.8453251],"study_design_scores_gemma":[0.0006431993,0.00055459567,0.0009716673,0.00030575707,0.00003806668,0.00036258594,0.0001432443,0.47107533,0.43849045,0.08618659,0.00089979894,0.00032871627],"about_ca_topic_score_codex":0.000015509202,"about_ca_topic_score_gemma":0.0000047155872,"teacher_disagreement_score":0.8449964,"about_ca_system_score_codex":0.0000950871,"about_ca_system_score_gemma":0.0002072782,"threshold_uncertainty_score":0.55727273},"labels":[],"label_agreement":null},{"id":"W2008797112","doi":"10.4103/2153-3539.108540","title":"Digital pathology: Attitudes and practices in the Canadian pathology community","year":2013,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Sinai Hospital; University of Calgary; St. Michael's Hospital; Calgary Laboratory Services; University of Toronto","funders":"","keywords":"Digital pathology; Telepathology; Informatics; Surgical pathology; Medicine; Pathology; Popularity; Medical education; Anatomical pathology; Psychology; Telemedicine; Health care","score_opus":0.034092203511299934,"score_gpt":0.30062403732516535,"score_spread":0.2665318338138654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008797112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9819036,0.00015716297,0.009587118,0.004155941,0.00047117582,0.00017352506,0.0000035716885,0.000014131114,0.003533769],"genre_scores_gemma":[0.9848793,0.00009581899,0.01267583,0.0022737123,0.00005266084,0.000008406373,0.000001033124,0.000004315664,0.000008928808],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998303,0.0004688109,0.0006781126,0.00006029669,0.0001991132,0.00029065376],"domain_scores_gemma":[0.9975503,0.00053975807,0.0011566532,0.000420878,0.00022626341,0.000106127554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023641132,0.0001244881,0.00023831608,0.00035457505,0.00028894356,0.00036826427,0.0010611417,0.00018603659,0.0000057720404],"category_scores_gemma":[0.0007297155,0.00008596353,0.00004239143,0.00025171635,0.0002687826,0.0028753786,0.00018115017,0.0012316568,0.000030349433],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003766891,0.0004992965,0.43502784,0.00028674863,0.00011194349,0.0049282596,0.19284582,0.00045918053,0.00044332483,0.008899112,0.007624862,0.34883595],"study_design_scores_gemma":[0.0013525382,0.0018983932,0.8598904,0.00009553314,0.000033224245,0.094106205,0.012616814,0.0046861223,0.000072516574,0.018747177,0.0060777194,0.00042336684],"about_ca_topic_score_codex":0.001031707,"about_ca_topic_score_gemma":0.015031549,"teacher_disagreement_score":0.42486253,"about_ca_system_score_codex":0.0001248275,"about_ca_system_score_gemma":0.00026584792,"threshold_uncertainty_score":0.8387957},"labels":[],"label_agreement":null},{"id":"W2010188354","doi":"10.1117/12.403591","title":"<title>Parallel implementation of an algorithm to detect calcifications in mammograms</title>","year":2000,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Thresholding; Histogram; Algorithm; Segmentation; Pixel; Boundary (topology); Speedup; Parallel algorithm; Image segmentation; Region growing; Artificial intelligence; Computer vision; Image (mathematics); Parallel computing; Mathematics; Image texture","score_opus":0.01161065788448812,"score_gpt":0.25910755096868215,"score_spread":0.24749689308419404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010188354","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9845527,0.0000622252,0.0048443577,0.0009621047,0.000226119,0.00044094966,0.000028625167,0.000086304746,0.008796621],"genre_scores_gemma":[0.19879222,0.00010714471,0.7998854,0.0000961175,0.0002973484,0.0001906481,0.000007957754,0.00004200976,0.0005811488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879456,2.6342656e-8,0.0003755543,0.00025248138,0.0003792196,0.00019816241],"domain_scores_gemma":[0.99928194,0.000030253408,0.00012862375,0.00006722533,0.0004240539,0.00006791299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028403525,0.00013166826,0.00016523499,0.0001057399,0.000033669985,0.000054052507,0.00069529744,0.000083567415,0.000103111706],"category_scores_gemma":[0.000039943985,0.00012448862,0.00016306827,0.00041643815,0.00005441229,0.0003592131,0.000066644294,0.00011797402,0.000014872159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003539242,0.00013133948,0.00008322274,0.0001827533,0.0001779328,1.7542978e-7,0.0006024609,0.00049747335,0.21695103,0.5311425,0.008853455,0.24134228],"study_design_scores_gemma":[0.0031156559,0.0017759532,0.010277042,0.0005360179,0.00018426644,0.000058159225,0.0011706747,0.48767033,0.29436168,0.01725771,0.1820458,0.0015466992],"about_ca_topic_score_codex":0.000014941193,"about_ca_topic_score_gemma":0.0000010659245,"teacher_disagreement_score":0.795041,"about_ca_system_score_codex":0.0001393052,"about_ca_system_score_gemma":0.000031167947,"threshold_uncertainty_score":0.50764984},"labels":[],"label_agreement":null},{"id":"W2011992172","doi":"10.3233/acp-2011-0022","title":"Abstracts of the 1st Congress of the International Academy of Digital Pathology, August 3–5, 2011, Quebec City, Canada.","year":2011,"lang":"en","type":"other","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Digital pathology; Library science; Pathology; Medicine; Computer science","score_opus":0.02697039843656265,"score_gpt":0.2154859542733184,"score_spread":0.18851555583675575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011992172","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011694686,0.0007780637,0.0007659979,0.005916469,0.020426515,0.0024000045,0.0012565427,0.00012054471,0.9566412],"genre_scores_gemma":[0.73307955,0.000025197973,0.00005858796,0.00014620979,0.00018339696,0.00011754704,0.0000020762761,0.00005486529,0.26633254],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9986795,0.000039622715,0.0003427883,0.00024480806,0.0005046343,0.00018860328],"domain_scores_gemma":[0.99857813,0.000048835464,0.0007952535,0.00047233223,0.00006498627,0.000040460403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018974011,0.00014240276,0.00022129357,0.00008082703,0.000019274241,0.000019598152,0.0025773062,0.00020092832,0.00013247397],"category_scores_gemma":[0.00006985347,0.000092272756,0.00009294244,0.00012787168,0.0003182128,0.00011786954,0.0007013536,0.00025832624,0.0000014792522],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008790004,0.00005458613,0.0054292725,0.00007322651,0.00015638824,0.000001782497,0.0000726811,0.000012792253,0.000029380393,0.001721407,0.9608747,0.031565014],"study_design_scores_gemma":[0.00033899047,0.0000064117203,0.6161965,0.00012781718,0.000033526594,0.000023554612,0.000012120701,0.0000183567,0.013736735,0.00066322216,0.36860743,0.00023533838],"about_ca_topic_score_codex":0.24319509,"about_ca_topic_score_gemma":0.49012452,"teacher_disagreement_score":0.7213849,"about_ca_system_score_codex":0.00015314766,"about_ca_system_score_gemma":0.00039367177,"threshold_uncertainty_score":0.7618445},"labels":[],"label_agreement":null},{"id":"W2012684637","doi":"10.5121/ijaia.2010.1301","title":"An Efficient Automatic Mass Classification Method In Digitized Mammograms Using Artificial Neural Network","year":2010,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence & Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Artificial neural network; Kurtosis; Pattern recognition (psychology); Computer science; Standard deviation; Skewness; Entropy (arrow of time); Computer-aided diagnosis; Sensitivity (control systems); Mathematics; Statistics; Engineering","score_opus":0.057743165654555506,"score_gpt":0.3816841791298209,"score_spread":0.3239410134752654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012684637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100558236,0.000021739623,0.8955182,0.00094441493,0.0023443312,0.0004210132,0.000005064957,0.00009650106,0.00009052785],"genre_scores_gemma":[0.6838106,0.000005592432,0.31495464,0.000085800944,0.0010456587,0.0000758701,0.000004349367,0.000015487569,0.0000020131993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967099,0.00017434111,0.0014571403,0.0004406752,0.0008626705,0.00035531094],"domain_scores_gemma":[0.9970766,0.0002972754,0.00094141456,0.00057062344,0.00092880696,0.00018532501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015156309,0.00021342597,0.00027492436,0.0005254552,0.00018443113,0.0006022454,0.0020845425,0.00014964191,0.000054703876],"category_scores_gemma":[0.00011975142,0.00021769168,0.00016837248,0.0010579482,0.00013692597,0.0008253383,0.00009506691,0.0006941731,0.000032491094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035508805,0.000286063,0.00017574856,0.000002882649,0.000024943562,0.0000083277855,0.00021960548,0.24439995,0.07164633,0.16615218,0.000005781194,0.5170427],"study_design_scores_gemma":[0.00004813148,0.000067988425,0.0005206152,0.00002271756,0.000014566389,0.00012253023,0.00016393673,0.86065626,0.012100999,0.12566629,0.00043478588,0.00018116944],"about_ca_topic_score_codex":0.00006546221,"about_ca_topic_score_gemma":0.0001592711,"teacher_disagreement_score":0.6162563,"about_ca_system_score_codex":0.00029414755,"about_ca_system_score_gemma":0.00026500216,"threshold_uncertainty_score":0.8877209},"labels":[],"label_agreement":null},{"id":"W2013733580","doi":"10.2478/jaiscr-2014-0019","title":"A Novel Approach for Automatic Detection and Classification of Suspicious Lesions in Breast Ultrasound Images","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Soft Computing Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; AdaBoost; Support vector machine; Breast ultrasound; Segmentation; Feature selection; Artificial neural network; Feature (linguistics); Fuzzy logic; Feature vector; Breast cancer; Mammography; Cancer; Medicine","score_opus":0.1198881459729667,"score_gpt":0.37272856945499994,"score_spread":0.2528404234820332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013733580","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35929683,0.0000803943,0.6400889,0.00023812632,0.00006905679,0.00020364854,5.669502e-7,0.0000085802785,0.000013888885],"genre_scores_gemma":[0.9469645,0.000042293,0.05286794,0.000007474117,0.00009918997,0.000008082438,1.9186857e-7,0.0000062971185,0.000004009037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984088,0.00012558253,0.000617075,0.00021723917,0.00038146452,0.00024983374],"domain_scores_gemma":[0.99744743,0.0012480582,0.0002724934,0.00015233876,0.00079875207,0.00008091939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024940968,0.00008470153,0.00019887433,0.000510905,0.00021184192,0.00022832555,0.0003100451,0.00007359987,0.0000017773498],"category_scores_gemma":[0.0004884934,0.00007459487,0.000043481323,0.00060273963,0.00020408131,0.00045403893,0.000094430485,0.00035712717,0.0000011236741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022777334,0.0001440782,0.000672564,0.00008763319,0.000010512732,5.9229524e-7,0.0013541095,0.0013269268,0.20197345,0.0009825171,0.000019352248,0.7934055],"study_design_scores_gemma":[0.000078575664,0.00037581843,0.029745083,0.000107320324,0.0000044149992,0.00025040895,0.0017367104,0.9314087,0.02455421,0.011648028,0.0000032194323,0.000087505185],"about_ca_topic_score_codex":0.00017296891,"about_ca_topic_score_gemma":0.000019280867,"teacher_disagreement_score":0.9300818,"about_ca_system_score_codex":0.00008632689,"about_ca_system_score_gemma":0.00010124327,"threshold_uncertainty_score":0.30418906},"labels":[],"label_agreement":null},{"id":"W2015162053","doi":"10.3138/jvme.34.4.416","title":"Virtual Microscopy in a Veterinary Curriculum","year":2007,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Virtual microscopy; The Internet; Computer science; Multimedia; Curriculum; Telepathology; Microscope; World Wide Web; Medicine; Pathology; Psychology","score_opus":0.030940725176474126,"score_gpt":0.3780206014362514,"score_spread":0.34707987625977726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015162053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86266005,0.00038887386,0.12986507,0.0013880597,0.005387405,0.00006721784,1.2193004e-7,0.000018906601,0.00022431476],"genre_scores_gemma":[0.9809943,0.00010892165,0.01745417,0.0006686334,0.00072476955,0.0000040830896,5.1520476e-7,0.000008751801,0.000035854642],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980764,0.00012479346,0.0006748163,0.00018494177,0.0006857004,0.00025338272],"domain_scores_gemma":[0.9988581,0.0001140059,0.0003446537,0.00023149692,0.00015887209,0.0002928762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019630848,0.000116823416,0.00019101438,0.00040951205,0.000047376674,0.00004301212,0.00073275476,0.00013108013,0.0000707979],"category_scores_gemma":[0.0004341663,0.00010680354,0.00007813847,0.00053086487,0.000062030216,0.0007453364,0.00013015539,0.00047927722,0.000014621688],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028813587,0.0015321585,0.0030300003,0.000054880235,0.000020975036,0.00083791773,0.002091774,0.000017463735,0.02640307,0.000945334,0.0048908684,0.95988744],"study_design_scores_gemma":[0.008159548,0.04881852,0.3327209,0.004686111,0.000055959445,0.088953905,0.0047973706,0.015929341,0.01028927,0.0062024826,0.47740713,0.0019794635],"about_ca_topic_score_codex":0.000034628338,"about_ca_topic_score_gemma":0.000004751551,"teacher_disagreement_score":0.957908,"about_ca_system_score_codex":0.00039009235,"about_ca_system_score_gemma":0.0011793597,"threshold_uncertainty_score":0.4355322},"labels":[],"label_agreement":null},{"id":"W2015547418","doi":"10.1109/iembs.2010.5626299","title":"Learning cellular texture features in microscopic cancer cell images for automated cell-detection","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Texture (cosmology); Artificial intelligence; Pixel; Computer science; Image texture; Abstraction; Pattern recognition (psychology); Computer vision; Partition (number theory); Image (mathematics); Contrast (vision); Texture compression; Image processing; Mathematics","score_opus":0.0037785725660564942,"score_gpt":0.24288643272681887,"score_spread":0.23910786016076238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015547418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47331685,0.0008743907,0.5129161,0.00057320844,0.0047096903,0.0009893206,0.000006235842,0.0024545686,0.0041596503],"genre_scores_gemma":[0.9727701,0.00003670765,0.022572486,0.00010454437,0.00017924522,0.00014121665,0.00000237219,0.000023340906,0.0041700094],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99875623,0.00004479406,0.00019473967,0.0004981359,0.00015834105,0.00034776606],"domain_scores_gemma":[0.99933034,0.0000737732,0.00011495396,0.0003259209,0.000094788884,0.00006023325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020708553,0.00018083437,0.00015274365,0.000113855385,0.00019067776,0.0001885029,0.000440969,0.00021438293,0.000053789943],"category_scores_gemma":[0.000019312049,0.00016866879,0.00006318724,0.0003448371,0.000030986346,0.0004890818,0.00009423953,0.0005241114,0.000015167783],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008163491,0.000026085527,0.0003221901,0.000048878905,0.0000026338307,0.0000015414355,0.00030613452,0.001037122,0.97800624,0.000020667312,0.001676569,0.018543757],"study_design_scores_gemma":[0.0004835284,0.00011007579,0.0022687821,0.000011078306,0.0000048110746,0.000003108973,0.000059021495,0.099536374,0.8919034,0.000084935484,0.0053375894,0.00019730872],"about_ca_topic_score_codex":0.0014421378,"about_ca_topic_score_gemma":0.0022663372,"teacher_disagreement_score":0.49945322,"about_ca_system_score_codex":0.00014740437,"about_ca_system_score_gemma":0.00007667079,"threshold_uncertainty_score":0.6878114},"labels":[],"label_agreement":null},{"id":"W2015657065","doi":"10.1016/j.humpath.2009.04.012","title":"Primary frozen section diagnosis by robotic microscopy and virtual slide telepathology: the University Health Network experience","year":2009,"lang":"en","type":"article","venue":"Human Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Telepathology; Frozen section procedure; Medicine; Medical diagnosis; Medical laboratory; Nuclear medicine; Surgery; Pathology; Health care; Telemedicine","score_opus":0.011837190844234758,"score_gpt":0.25064556274711736,"score_spread":0.2388083719028826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015657065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7103873,0.0010937987,0.28353357,0.0032022363,0.0009803714,0.00029485725,0.0000028473444,0.00023919817,0.00026584158],"genre_scores_gemma":[0.98765856,0.00042362095,0.0061124214,0.005331496,0.0002273727,0.000012866688,0.000005660136,0.000008929791,0.00021906961],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99834853,0.00041853279,0.00018443739,0.0005462769,0.00011136836,0.00039083304],"domain_scores_gemma":[0.99917763,0.00009366952,0.00015687401,0.0004645749,0.000028828495,0.00007840146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036555703,0.00015093136,0.00022275005,0.00006235197,0.0008569998,0.000050009676,0.0005155829,0.00012423401,0.000009508449],"category_scores_gemma":[0.000011641415,0.00013942512,0.000037508675,0.00027880326,0.00027134508,0.00028607473,0.00019346342,0.00028539673,0.000008255914],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002199804,0.00072853087,0.09014323,0.00006809682,0.00006730926,0.00083320023,0.054334417,0.0047818716,0.115317866,0.03960249,0.31491184,0.3789912],"study_design_scores_gemma":[0.0022127228,0.0068822056,0.91114825,0.000095177355,0.000044598048,0.0017969809,0.0009862455,0.0024210345,0.004031702,0.009566689,0.059587438,0.0012269401],"about_ca_topic_score_codex":0.00004452577,"about_ca_topic_score_gemma":0.000051427625,"teacher_disagreement_score":0.82100505,"about_ca_system_score_codex":0.00023108876,"about_ca_system_score_gemma":0.000049936818,"threshold_uncertainty_score":0.6591436},"labels":[],"label_agreement":null},{"id":"W2016296285","doi":"10.1016/j.media.2015.03.001","title":"Skin lesion tracking using structured graphical models","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vancouver Coastal Health Research Institute; University of British Columbia; Simon Fraser University; Vancouver Coastal Health","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Dermatology Foundation","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Computer vision; Matching (statistics); Set (abstract data type); Mathematics","score_opus":0.06139986517366262,"score_gpt":0.3265433110588494,"score_spread":0.26514344588518673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016296285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065882824,0.00012411966,0.9326181,0.0007542121,0.00021205861,0.000045618268,8.618326e-7,0.00013401276,0.00022821379],"genre_scores_gemma":[0.92551273,0.000012886295,0.07394324,0.00032405512,0.00017403792,0.0000032097619,0.0000035688374,0.000009097823,0.000017172848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725807,0.00018030497,0.0003323865,0.00049447163,0.0014391006,0.00029566803],"domain_scores_gemma":[0.99861246,0.00006176299,0.00010719152,0.0005666855,0.00020577286,0.00044611946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008726734,0.00014496877,0.00031505869,0.00045938473,0.00011068693,0.00017728854,0.00078613084,0.00016441163,0.000078084064],"category_scores_gemma":[0.00023161963,0.00012356385,0.00025009186,0.0028718037,0.00012040579,0.00090064993,0.0002443977,0.00030822234,0.000009467884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007934545,0.00036923002,0.0052207042,0.000056995497,0.0026536696,0.0009792583,0.00543889,0.10934304,0.0077797445,0.0074137026,0.003469661,0.8571958],"study_design_scores_gemma":[0.0002453937,0.000021783253,0.0004708254,0.000009217161,0.00022491149,0.000021258184,0.000039288287,0.9858566,0.0016845677,0.011179962,0.000098885015,0.00014733362],"about_ca_topic_score_codex":0.00036198986,"about_ca_topic_score_gemma":0.00015061762,"teacher_disagreement_score":0.87651354,"about_ca_system_score_codex":0.00013854104,"about_ca_system_score_gemma":0.00016445074,"threshold_uncertainty_score":0.5038788},"labels":[],"label_agreement":null},{"id":"W2017052470","doi":"10.1159/000326277","title":"Dedicating Speci.c Sessions of Cytopathology Courses to Medical Students","year":2004,"lang":"en","type":"article","venue":"Acta Cytologica","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Cytopathology; Medical education; Medical physics; Pathology; Cytology","score_opus":0.019973248229505875,"score_gpt":0.33057006172511794,"score_spread":0.3105968134956121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017052470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7470934,0.00004701998,0.23810686,0.012129773,0.0006562045,0.00018802704,0.000002207273,0.00020090984,0.0015756132],"genre_scores_gemma":[0.9556784,0.000033114204,0.042528067,0.0016106091,0.00009356023,0.000026616204,6.878677e-7,0.0000057728635,0.00002319273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981125,0.00008483083,0.00030499187,0.0003987303,0.00081057753,0.00028834539],"domain_scores_gemma":[0.9988367,0.00016705539,0.00014837425,0.00052925776,0.00007728819,0.00024132062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005010564,0.00011727715,0.00023323594,0.00010499183,0.00012542433,0.00003287458,0.0021299622,0.00014959965,0.00011391713],"category_scores_gemma":[0.000866522,0.00009409741,0.00004960437,0.00043358887,0.0001212377,0.00014816999,0.0009175861,0.00021431527,0.00005899864],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024630368,0.0045680976,0.28969163,0.00016413048,0.00028815592,0.0025340936,0.0125196995,0.0014810014,0.22899425,0.1345487,0.020703232,0.3042607],"study_design_scores_gemma":[0.0051605967,0.0049409796,0.76314086,0.0008319389,0.00008109777,0.002562925,0.0009984111,0.0010156353,0.13492121,0.041084647,0.043529063,0.0017326317],"about_ca_topic_score_codex":0.000030076873,"about_ca_topic_score_gemma":0.000024622637,"teacher_disagreement_score":0.47344923,"about_ca_system_score_codex":0.00010076489,"about_ca_system_score_gemma":0.00022057339,"threshold_uncertainty_score":0.3958035},"labels":[],"label_agreement":null},{"id":"W2017074421","doi":"10.1007/bf02345742","title":"Boundary modelling and shape analysis methods for classification of mammographic masses","year":2000,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":195,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Boundary (topology); Segmentation; Pattern recognition (psychology); Mammography; Computer-aided diagnosis; Receiver operating characteristic; Artificial intelligence; Shape analysis (program analysis); Computer science; Feature (linguistics); Mathematics; Medicine; Machine learning; Breast cancer","score_opus":0.03869811745693699,"score_gpt":0.31843429355149194,"score_spread":0.2797361760945549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017074421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1831548,0.00074747996,0.81552726,0.00016005085,0.000107792184,0.00009799735,8.726055e-7,0.00015802722,0.000045723766],"genre_scores_gemma":[0.5981328,0.000098576864,0.4016552,0.000039236213,0.000056017525,0.00000777367,0.0000030649405,0.000004597037,0.0000027377966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857056,0.000089563306,0.00041280364,0.00045078722,0.00020133326,0.00027494828],"domain_scores_gemma":[0.9986329,0.0008613156,0.00008552726,0.00022814766,0.000052645897,0.00013946141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012968,0.00014612208,0.00033998664,0.0001909892,0.000102641025,0.000050589722,0.00042373894,0.0001847888,0.0000615964],"category_scores_gemma":[0.00018761193,0.000120667704,0.00014694846,0.0010037923,0.00009681929,0.00008549005,0.00010400083,0.00021289776,0.0000011500473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009337838,0.00002898343,0.0022958475,0.000045421264,0.000121582016,9.656023e-7,0.000075496115,0.117309034,0.0013025308,0.0018485306,0.0000041175263,0.87695813],"study_design_scores_gemma":[0.00012479407,0.00008566238,0.013342882,0.000037745624,0.000033391054,0.000006139234,0.0000040489695,0.98426455,0.00015393709,0.0005747268,0.0012384233,0.00013367743],"about_ca_topic_score_codex":0.000012009376,"about_ca_topic_score_gemma":3.7962164e-7,"teacher_disagreement_score":0.8768245,"about_ca_system_score_codex":0.000027935754,"about_ca_system_score_gemma":0.000026750082,"threshold_uncertainty_score":0.4920686},"labels":[],"label_agreement":null},{"id":"W2017110558","doi":"10.1038/nm0309-238a","title":"Stromal signature identifies basal breast cancers","year":2009,"lang":"en","type":"article","venue":"Nature Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Clinical Research Institute","funders":"","keywords":"Stromal cell; Breast cancer; Basal (medicine); Medicine; Oncology; Signature (topology); Pathology; Internal medicine; Biology; Cancer","score_opus":0.0048430623236616266,"score_gpt":0.2576718448439651,"score_spread":0.2528287825203035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017110558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0998626,0.03900458,0.49272949,0.28085113,0.038111426,0.0014190194,0.00004363216,0.0030671267,0.044910993],"genre_scores_gemma":[0.98992765,0.00004788493,0.0020310362,0.0056775953,0.0017120284,0.000004791081,0.0000054662924,0.000008710429,0.00058484706],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99829656,0.00004293628,0.00020110278,0.00045703095,0.0006865345,0.00031582863],"domain_scores_gemma":[0.99903286,0.00005611606,0.00010316852,0.0005259513,0.00015301871,0.00012891348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026983538,0.00019067839,0.00022223,0.00016921226,0.00012118607,0.000046084657,0.0007891506,0.00032840835,0.00009091075],"category_scores_gemma":[0.000052112307,0.0001470968,0.000049724014,0.00070621824,0.000087517175,0.00043066638,0.000056223285,0.0010869276,0.00001467781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018369342,0.000080504295,0.0005940996,0.000064805456,0.000105751045,0.00030011692,0.002410176,0.00049826095,0.08970139,0.033491507,0.50611264,0.36645707],"study_design_scores_gemma":[0.0124317,0.0063611143,0.5040473,0.0022065437,0.00026810364,0.0026217366,0.0009410151,0.04912935,0.11812455,0.1284831,0.17171939,0.0036661557],"about_ca_topic_score_codex":0.00006258765,"about_ca_topic_score_gemma":0.00004871446,"teacher_disagreement_score":0.890065,"about_ca_system_score_codex":0.0002760515,"about_ca_system_score_gemma":0.000118064185,"threshold_uncertainty_score":0.5998433},"labels":[],"label_agreement":null},{"id":"W2017258397","doi":"10.1002/sim.2895","title":"Tests of association under misclassification: Application to histological sampling in oncology","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute","keywords":"Feature (linguistics); Medicine; Oligodendroglioma; Outcome (game theory); Association (psychology); Sampling (signal processing); Radiology; Pathology; Computer science; Psychology; Glioma; Mathematics; Astrocytoma","score_opus":0.0552569513599816,"score_gpt":0.3907814980580758,"score_spread":0.33552454669809423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017258397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044099577,0.0000486043,0.98953944,0.0035340644,0.00036916987,0.00020756244,0.0000028563222,0.000024263461,0.0018640785],"genre_scores_gemma":[0.7727816,0.000016160882,0.22665147,0.00039864928,0.000079182515,0.000021449088,0.0000067969904,0.0000038663125,0.000040829054],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987086,0.00006270175,0.0004899198,0.00024879907,0.00030598347,0.00018401728],"domain_scores_gemma":[0.99806994,0.0012693309,0.00024348915,0.00022373973,0.00014187073,0.000051633855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018243998,0.00006861143,0.00019747719,0.00026003603,0.000021967888,0.0000034734824,0.00024967457,0.00010522752,0.000010827517],"category_scores_gemma":[0.0010749236,0.00006657263,0.000006744054,0.0007377552,0.00004727037,0.000045997425,0.00003319079,0.0001813794,0.000007803386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000560545,0.00018704013,0.04256163,0.00004383081,0.000009491265,0.000013361512,0.0028541044,0.0022823017,0.017755073,0.31175005,0.0028216983,0.6196653],"study_design_scores_gemma":[0.0008420759,0.0004733129,0.90078086,0.000061685285,0.000007400507,0.0000058994433,0.0002901273,0.011688714,0.0004885236,0.07659684,0.00862544,0.00013912785],"about_ca_topic_score_codex":0.00019252348,"about_ca_topic_score_gemma":0.0020101364,"teacher_disagreement_score":0.8582192,"about_ca_system_score_codex":0.0016342979,"about_ca_system_score_gemma":0.00007663128,"threshold_uncertainty_score":0.42736322},"labels":[],"label_agreement":null},{"id":"W2017346422","doi":"10.4103/2153-3539.77170","title":"Re: Barriers and facilitators to adoption of soft copy interpretation from the user perspective: Lessons learned from filmless radiology for slideless pathology. J Pathol Inform, 2011;2:1, Patterson et al.","year":2011,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto General Hospital","funders":"","keywords":"Digital pathology; Computer science; Telepathology; Focus (optics); Digitization; Digital imaging; Medicine; Digital image; Pathology; Medical physics; Multimedia; Data science; Health care; Artificial intelligence; Image processing; Computer vision","score_opus":0.0395341361821138,"score_gpt":0.3077343010306085,"score_spread":0.2682001648484947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017346422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4112642,0.00011316788,0.5837242,0.003712365,0.0007315098,0.0002457588,0.00015502547,0.000019272919,0.00003447434],"genre_scores_gemma":[0.8732252,0.00025143998,0.12002891,0.006367787,0.000052474483,0.00003707053,0.000015339418,0.000015487143,0.0000062603317],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99771047,0.00034663748,0.0011677968,0.00021150942,0.00027224395,0.00029135784],"domain_scores_gemma":[0.99654686,0.0007625247,0.0014130109,0.00047836092,0.00065008324,0.00014914482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017422026,0.0002377843,0.0005252917,0.0002649227,0.00014861909,0.000054325,0.0007711362,0.00024609343,0.000023320668],"category_scores_gemma":[0.00072500156,0.00018231716,0.00015726541,0.00016594816,0.00022915697,0.0013236412,0.00021183142,0.00052639487,0.000009520941],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019269818,0.00012198915,0.033129316,0.00010565136,0.0005127762,0.00012328791,0.8079637,0.0026590736,0.0056474307,0.008119237,0.023587842,0.11610268],"study_design_scores_gemma":[0.014796601,0.01489747,0.26829013,0.0010586648,0.0009433753,0.0028172554,0.4512405,0.11503925,0.017139416,0.09329606,0.017623525,0.0028577545],"about_ca_topic_score_codex":0.0000729789,"about_ca_topic_score_gemma":0.000087993314,"teacher_disagreement_score":0.4636953,"about_ca_system_score_codex":0.00015800996,"about_ca_system_score_gemma":0.00019351396,"threshold_uncertainty_score":0.74346787},"labels":[],"label_agreement":null},{"id":"W2017730583","doi":"10.1117/12.594696","title":"<title>Pseudonymisation of radiology data for research purposes</title>","year":2005,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Confidentiality; Identification (biology); Relation (database); Information retrieval; Data science; Data security; Database; Data mining; Encryption; Computer security","score_opus":0.040962063506184615,"score_gpt":0.2974900715403371,"score_spread":0.25652800803415243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017730583","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94480854,0.0006844472,0.008316888,0.009675059,0.0011843344,0.0011958032,0.00013019991,0.00019556162,0.03380915],"genre_scores_gemma":[0.3359078,0.00034489785,0.65972424,0.00012447481,0.0018791826,0.00020233996,0.000027181932,0.00007343029,0.0017164814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852234,3.5430876e-8,0.0003765295,0.00033312463,0.00050856906,0.00025941027],"domain_scores_gemma":[0.9982842,0.00015830768,0.00019300329,0.00012638918,0.0011822388,0.00005586895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010045513,0.00013026499,0.00020298487,0.000112849215,0.000056907516,0.000056087265,0.001552338,0.0001404895,0.0000309258],"category_scores_gemma":[0.00046636793,0.00011611108,0.00018029203,0.00029333011,0.00018239222,0.0004887119,0.000301685,0.00018842157,0.000010894923],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025234984,0.00004582091,0.000021827786,0.00018395732,0.00011748792,2.0475369e-8,0.000082416955,0.000042512926,0.13249741,0.78270566,0.07818057,0.0060970727],"study_design_scores_gemma":[0.0011073955,0.0005538927,0.0003934405,0.00024513662,0.000084857136,0.000037530117,0.00015181593,0.46366867,0.107911356,0.011682799,0.41372803,0.00043506268],"about_ca_topic_score_codex":0.0000020659802,"about_ca_topic_score_gemma":1.6338994e-7,"teacher_disagreement_score":0.77102286,"about_ca_system_score_codex":0.0001646262,"about_ca_system_score_gemma":0.000057841793,"threshold_uncertainty_score":0.47348723},"labels":[],"label_agreement":null},{"id":"W2017977174","doi":"10.1109/hicss.2014.355","title":"Telepathology Implementation Challenges and Benefits: A Scoping Review","year":2014,"lang":"en","type":"review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Telepathology; Computer science; Management science; Quality (philosophy); Process management; Telemedicine; Health care; Engineering; Political science","score_opus":0.13509954995238813,"score_gpt":0.4189257957199202,"score_spread":0.2838262457675321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017977174","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0088964e-8,0.9772806,0.019962318,0.00036042795,0.0002879416,0.0011812355,0.0000011275998,0.00014592643,0.0007804136],"genre_scores_gemma":[5.6269396e-8,0.99245715,0.0067084986,0.0003185228,0.000118706856,0.00035867267,0.0000053582003,0.000017408556,0.000015633866],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998199,0.0002501787,0.00054353545,0.0006386455,0.00015385203,0.00021478884],"domain_scores_gemma":[0.9987827,0.0001594267,0.0003805116,0.00057727465,0.000044935958,0.000055128745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006794163,0.00025817033,0.0011648447,0.00013037074,0.000059117574,0.00004643781,0.00046204164,0.0001345386,0.000027877926],"category_scores_gemma":[0.00002534526,0.00020785425,0.00012349742,0.00017271622,0.000021854794,0.00021975838,0.00032222917,0.00015069908,0.00004734359],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.992088e-8,0.0000013604613,2.5201047e-8,0.11978364,0.000007932259,6.8291456e-7,0.0000133890335,1.5660765e-8,2.9440421e-9,0.004354747,0.000071138624,0.87576705],"study_design_scores_gemma":[0.000049006172,0.0000767013,7.5053504e-7,0.3102935,0.0001136317,0.00018736285,0.0000023301152,0.0000071840273,4.112062e-7,0.0002001511,0.68882626,0.00024274306],"about_ca_topic_score_codex":0.000006081431,"about_ca_topic_score_gemma":0.00009563886,"teacher_disagreement_score":0.8755243,"about_ca_system_score_codex":0.00007356901,"about_ca_system_score_gemma":0.00013834893,"threshold_uncertainty_score":0.84760505},"labels":[],"label_agreement":null},{"id":"W2019763242","doi":"10.1109/iembs.2010.5626017","title":"Fractal analysis of contours of breast masses in mammograms via the power spectra of their signatures","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal; Fractal dimension; Receiver operating characteristic; Mammography; Fractal analysis; Dimension (graph theory); Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer science; Medicine; Breast cancer; Statistics; Mathematical analysis; Cancer; Pure mathematics; Internal medicine","score_opus":0.0047835522954923935,"score_gpt":0.22551965865164847,"score_spread":0.22073610635615606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019763242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87616295,0.000055970784,0.12028221,0.00040339472,0.00022996766,0.00011164926,0.000009940775,0.000023791034,0.002720144],"genre_scores_gemma":[0.995836,0.0000037073187,0.0040905075,0.00003199284,0.0000140286165,0.0000027950496,6.4170445e-7,0.0000037329191,0.000016566946],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991356,0.000044412696,0.00027267644,0.00017709903,0.00024637658,0.00012384406],"domain_scores_gemma":[0.99890757,0.00019160061,0.00021983896,0.00054438267,0.00011350256,0.000023099536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031682354,0.00008702899,0.00024896458,0.00024309683,0.000015637286,0.000015206452,0.0006578832,0.00007406737,0.00018687893],"category_scores_gemma":[0.000014062207,0.000053154476,0.00015093222,0.0012915945,0.00013674857,0.00016948108,0.00008561407,0.00019719913,4.805492e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010470116,0.0005093344,0.11776633,0.000032051154,0.0011692233,0.0000042938423,0.003940643,0.0021581454,0.7516304,0.024057651,0.00020896536,0.09841821],"study_design_scores_gemma":[0.00024748535,0.00015234362,0.6762384,0.000012260009,0.00008652807,0.000007979032,0.0003731911,0.04699533,0.27332994,0.0023199168,0.00009250872,0.00014410664],"about_ca_topic_score_codex":0.0011308506,"about_ca_topic_score_gemma":0.0033192714,"teacher_disagreement_score":0.5584721,"about_ca_system_score_codex":0.000013319035,"about_ca_system_score_gemma":0.000036183537,"threshold_uncertainty_score":0.21675766},"labels":[],"label_agreement":null},{"id":"W2019768588","doi":"10.1053/j.semdp.2010.05.002","title":"Frequently asked questions concerning the use of whole-slide imaging telepathology for neuropathology frozen sections","year":2010,"lang":"en","type":"review","venue":"Seminars in Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Telepathology; Digital pathology; Neuropathology; Medical diagnosis; Computer science; Section (typography); The Internet; Medical physics; Pathology; Medicine; Telemedicine; World Wide Web; Artificial intelligence; Disease; Health care; Political science","score_opus":0.06576257754016035,"score_gpt":0.3285536021191969,"score_spread":0.2627910245790365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019768588","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034675968,0.77492946,0.21529475,0.0005187511,0.0061765118,0.0021696235,0.00028000853,0.00021840647,0.000065756976],"genre_scores_gemma":[0.00028071075,0.9527079,0.043326057,0.00041284368,0.00039463327,0.002564363,0.000089190085,0.000118926415,0.000105414096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938471,0.0018846799,0.0016820589,0.0014340904,0.00023943861,0.0009126759],"domain_scores_gemma":[0.9737205,0.02247062,0.0014330937,0.0019968906,0.00026855475,0.000110328656],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015510037,0.0006910023,0.0019135352,0.00086627697,0.00033508465,0.000102857615,0.0020976576,0.0008715317,0.000008092821],"category_scores_gemma":[0.016530696,0.00059052673,0.0005321609,0.0010771588,0.0010105268,0.0004017245,0.000798153,0.0021301585,0.000033781744],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005037852,0.00010003559,0.0005703518,0.0007402732,0.000023842644,0.0008758012,0.00054879946,0.00025252593,0.00009271391,0.002125267,0.0010457955,0.99361956],"study_design_scores_gemma":[0.00036614388,0.00027999035,0.0002589274,0.003980679,0.00036424806,0.0064659757,0.000025257194,0.0014642666,0.000029546813,0.0025645876,0.9836228,0.00057755865],"about_ca_topic_score_codex":0.00007323927,"about_ca_topic_score_gemma":0.00017427324,"teacher_disagreement_score":0.993042,"about_ca_system_score_codex":0.00028450976,"about_ca_system_score_gemma":0.0006087209,"threshold_uncertainty_score":0.9996546},"labels":[],"label_agreement":null},{"id":"W2022549960","doi":"10.1088/0031-9155/51/20/002","title":"Design and characterization of a digital image acquisition system for whole-specimen breast histopathology","year":2006,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Optical transfer function; Image resolution; Computer vision; Digital imaging; Artificial intelligence; Optics; Digital image; Image processing; Physics; Image (mathematics)","score_opus":0.058951528669202655,"score_gpt":0.29141443844447995,"score_spread":0.23246290977527728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022549960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109632954,0.000061527404,0.8892181,0.00068568124,0.00014001835,0.00016030703,0.000010821878,0.000019988785,0.000070641654],"genre_scores_gemma":[0.9960645,0.000011659163,0.0035572858,0.00003837554,0.00025520084,0.000022749364,0.000039631374,0.0000034921802,0.0000071230643],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99948895,0.000039553073,0.00016022736,0.00018899456,0.00002949935,0.00009280057],"domain_scores_gemma":[0.99966717,0.00007546815,0.00010388091,0.00009089078,0.000049953436,0.000012627186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001586542,0.000064359214,0.00016658926,0.000056155797,0.000025442232,0.000007906851,0.000069511065,0.000044467986,3.0244007e-7],"category_scores_gemma":[0.000003534281,0.00005284719,0.000008528848,0.000101329744,0.00013527086,0.00017293548,0.00003517618,0.00003423743,3.2813583e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004720524,0.00002606283,0.001146082,0.000079206206,0.0000030032138,0.0000016290497,0.00023346109,0.0000067393175,0.9296477,0.022073675,0.000045353125,0.046689898],"study_design_scores_gemma":[0.014342047,0.007983693,0.19386066,0.0009833709,0.00014296887,0.0013686989,0.0005165228,0.29058516,0.11113102,0.37405342,0.0036302307,0.0014022307],"about_ca_topic_score_codex":0.000015434242,"about_ca_topic_score_gemma":6.3405656e-7,"teacher_disagreement_score":0.8864315,"about_ca_system_score_codex":0.000032912216,"about_ca_system_score_gemma":0.0000100965835,"threshold_uncertainty_score":0.21550459},"labels":[],"label_agreement":null},{"id":"W2025845047","doi":"10.4018/jcini.2009070103","title":"Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing","year":2009,"lang":"en","type":"article","venue":"International Journal of Cognitive Informatics and Natural Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Radial basis function; Computer science; Pattern recognition (psychology); Simulated annealing; Artificial intelligence; Classifier (UML); Artificial neural network; Mammography; Receiver operating characteristic; Breast cancer; Algorithm; Machine learning; Cancer; Medicine","score_opus":0.026392648618994267,"score_gpt":0.3112548033929178,"score_spread":0.2848621547739235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025845047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6383831,0.00025598743,0.3606148,0.0001878088,0.00040777496,0.000057752182,0.000006929289,0.000005836666,0.00007998785],"genre_scores_gemma":[0.99207246,0.00027768535,0.0074869334,0.00009281246,0.00006245122,2.79323e-7,0.00000225961,0.000002187882,0.0000029311873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988428,0.00002784488,0.00064387405,0.00007034737,0.00031951396,0.0000956263],"domain_scores_gemma":[0.998165,0.00023670479,0.0005451981,0.000048322927,0.0009574443,0.000047300848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002936648,0.00009001146,0.00014201853,0.00041424084,0.00003909585,0.00011977911,0.0002341488,0.000049522194,0.0000037404172],"category_scores_gemma":[0.00014070654,0.00007933737,0.000042490672,0.00028808223,0.00007067595,0.0012905662,0.00004578379,0.00022520332,4.767922e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021645034,0.000057867914,0.005730131,0.000014805536,0.0000777927,0.000010450832,0.0021258302,0.005148395,0.0014094139,0.0015441985,0.000004446264,0.9836602],"study_design_scores_gemma":[0.00040144878,0.00023008496,0.063456416,0.0005407336,0.000021133457,0.000768083,0.0016040864,0.9255302,0.00442648,0.0028552187,0.000024641515,0.00014150742],"about_ca_topic_score_codex":0.000021778571,"about_ca_topic_score_gemma":0.0000058566357,"teacher_disagreement_score":0.9835187,"about_ca_system_score_codex":0.00007071596,"about_ca_system_score_gemma":0.00005710603,"threshold_uncertainty_score":0.3235284},"labels":[],"label_agreement":null},{"id":"W2026487926","doi":"10.1371/journal.pone.0091015","title":"Automated Breast Image Classification Using Features from Its Discrete Cosine Transform","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Discrete cosine transform; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Computer science; Naive Bayes classifier; k-nearest neighbors algorithm; Contextual image classification; Cross-validation; Mathematics; Support vector machine; Image (mathematics)","score_opus":0.03891820655005278,"score_gpt":0.251993381613427,"score_spread":0.2130751750633742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026487926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2930101,0.00008892979,0.698541,0.004073305,0.00019949322,0.00038429373,0.00005403203,0.0018107741,0.0018380937],"genre_scores_gemma":[0.9387927,0.000010791123,0.06077266,0.000103475286,0.00019625234,0.000015983844,0.000018155524,0.000017116095,0.000072840376],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988385,0.00006266802,0.00017660673,0.00035439842,0.00036493014,0.00020291819],"domain_scores_gemma":[0.9992352,0.00005052059,0.00009663326,0.0004248682,0.00011935143,0.000073398754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012605375,0.00012828383,0.00016259024,0.00007145197,0.00013506296,0.00016546693,0.00040025663,0.00007948261,0.000020848156],"category_scores_gemma":[0.0000219557,0.00012422472,0.000036034,0.00029384185,0.000034528195,0.00072634313,0.000046090314,0.00014001082,0.00005932676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024206352,0.00019096899,0.00012263373,0.00004435093,0.00007322208,0.0000011977857,0.00033322684,0.00003864477,0.98672754,0.00081636105,0.00020401529,0.011423653],"study_design_scores_gemma":[0.00027331556,0.000041190782,0.019035662,0.0001283741,0.000036524478,0.0000062366125,0.0000062242525,0.7937128,0.18598829,0.0005782196,0.00003923276,0.00015390945],"about_ca_topic_score_codex":0.00011263043,"about_ca_topic_score_gemma":0.000028385015,"teacher_disagreement_score":0.8007392,"about_ca_system_score_codex":0.00013762873,"about_ca_system_score_gemma":0.000031605683,"threshold_uncertainty_score":0.5065737},"labels":[],"label_agreement":null},{"id":"W2026506545","doi":"10.1007/s10278-006-0860-9","title":"Fractal Analysis of Contours of Breast Masses in Mammograms","year":2006,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Mammography; Fractal; Radiology; Computer vision; Medicine; Computer science; Artificial intelligence; Breast cancer; Mathematics; Internal medicine; Mathematical analysis","score_opus":0.005110840688967574,"score_gpt":0.23224844266854006,"score_spread":0.22713760197957247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026506545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8033702,0.0002831141,0.19340938,0.0003706316,0.00018243806,0.0000319678,0.000010311107,0.000010435647,0.0023315526],"genre_scores_gemma":[0.9967542,0.0000037939167,0.0031654204,0.000010708146,0.000048907117,2.6393397e-7,7.40794e-7,0.0000045483685,0.000011363039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987975,0.000018053744,0.0005894039,0.00010248884,0.00035775636,0.00013479304],"domain_scores_gemma":[0.9987934,0.000081360224,0.00070713175,0.0001537373,0.0002290657,0.00003525327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021302266,0.00007822261,0.00031160557,0.00068714214,0.000011386496,0.00012887521,0.0003554816,0.000018231709,0.0000047265985],"category_scores_gemma":[0.000024491577,0.00007094016,0.00021603146,0.001179755,0.00005688622,0.001933635,0.00006177356,0.0001135603,3.8006976e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029247689,0.00020211466,0.8468488,0.000016669112,0.00020495453,0.00006630056,0.00018118042,0.0053103464,0.0039127017,0.0002713535,0.00011224846,0.14284408],"study_design_scores_gemma":[0.001006985,0.00015136552,0.9190213,0.00019719667,0.00024590554,0.0005184018,0.0003198856,0.064480394,0.009395696,0.0041485713,0.0002597497,0.00025456067],"about_ca_topic_score_codex":0.00012349652,"about_ca_topic_score_gemma":0.000027562493,"teacher_disagreement_score":0.19338408,"about_ca_system_score_codex":0.00008027457,"about_ca_system_score_gemma":0.00005920472,"threshold_uncertainty_score":0.28928557},"labels":[],"label_agreement":null},{"id":"W2026781634","doi":"10.2200/s00453ed1v01y201210bme046","title":"Fractal Analysis of Breast Masses in Mammograms","year":2012,"lang":"en","type":"article","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fondation pour la Recherche Médicale; Natural Sciences and Engineering Research Council of Canada; University of Liverpool","keywords":"Fractal; Fractal analysis; Fractal dimension; Grayscale; Image processing; Artificial intelligence; Scale (ratio); Computer science; Computer vision; Computer graphics (images); Mathematics; Image (mathematics); Cartography; Geography; Mathematical analysis","score_opus":0.00616104816703966,"score_gpt":0.22113440799634693,"score_spread":0.21497335982930726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026781634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18864423,0.00033017684,0.8091833,0.0005574974,0.00069750805,0.00010216251,0.000012518798,0.00023188554,0.00024073229],"genre_scores_gemma":[0.9917056,0.000010637393,0.008098054,0.000041705465,0.00010632054,0.00002295155,0.0000017786197,0.000010976689,0.0000019897925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869114,0.000035462243,0.00025550567,0.00022482098,0.00042628474,0.0003667813],"domain_scores_gemma":[0.9989701,0.00047113854,0.000061205676,0.000333777,0.000016131711,0.000147638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034334604,0.00014522196,0.00029241914,0.000993051,0.000019592717,0.000023269336,0.0004074373,0.00012331354,0.00007424735],"category_scores_gemma":[0.00022833502,0.0001255087,0.000133278,0.002345546,0.00003835728,0.00018403662,0.00007005997,0.00018608353,0.0000061765786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060782055,0.000873572,0.016231604,0.00019887491,0.0016728766,0.000027706757,0.0012242458,0.058592506,0.061615843,0.0041111712,0.00024430838,0.8551465],"study_design_scores_gemma":[0.0002678292,0.00012119029,0.3705447,0.0002009965,0.0002611773,0.00004128819,0.000028011415,0.55832934,0.06412152,0.00007421182,0.005351424,0.0006583228],"about_ca_topic_score_codex":0.000060364637,"about_ca_topic_score_gemma":0.000006994129,"teacher_disagreement_score":0.8544882,"about_ca_system_score_codex":0.00011712665,"about_ca_system_score_gemma":0.000019633266,"threshold_uncertainty_score":0.5118096},"labels":[],"label_agreement":null},{"id":"W2027328448","doi":"10.1007/bf02344714","title":"Segmentation of the fibro-glandular disc in mammogrms using Gaussian mixture modelling","year":2004,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Alberta Heritage Foundation for Medical Research; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Segmentation; Pattern recognition (psychology); Artificial intelligence; Mixture model; Ranking (information retrieval); Gaussian; Computer science; Mathematics; Anatomy; Biology; Physics","score_opus":0.017862576346699934,"score_gpt":0.23859262563843114,"score_spread":0.2207300492917312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027328448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44341314,0.00008545883,0.5558848,0.00017429133,0.00028363933,0.00007475791,3.0437891e-7,0.00007345649,0.000010185567],"genre_scores_gemma":[0.9244464,0.000007945784,0.07534424,0.000071171264,0.00011753525,0.0000022785932,9.028216e-7,0.000008892841,6.567888e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857783,0.000054332064,0.0003710257,0.00031553002,0.00037659906,0.00030467994],"domain_scores_gemma":[0.9994604,0.00010443837,0.000093399416,0.00023221706,0.000020816686,0.00008875799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004650072,0.00014680307,0.000203806,0.00006924401,0.00007281952,0.00002756738,0.0006126084,0.00017976384,0.0000054056313],"category_scores_gemma":[0.00011453894,0.000094641895,0.00007968609,0.00057761115,0.00005788922,0.00009355722,0.0003121067,0.0004158227,0.000001863329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024070828,0.000019770807,0.005622409,0.000023515517,0.0000056275303,0.000007639498,0.00021682271,0.9844882,0.0032205044,0.0012584286,6.2096e-7,0.0051340545],"study_design_scores_gemma":[0.00032176758,0.00004088338,0.010234289,0.00031844934,0.000002330158,0.000028162747,0.00001471865,0.9861681,0.002099291,0.00062335294,0.00002047977,0.00012817967],"about_ca_topic_score_codex":0.00013277319,"about_ca_topic_score_gemma":0.000003257739,"teacher_disagreement_score":0.48103327,"about_ca_system_score_codex":0.00016627726,"about_ca_system_score_gemma":0.00005598014,"threshold_uncertainty_score":0.38593844},"labels":[],"label_agreement":null},{"id":"W2029219200","doi":"10.3138/jvme.34.4.437","title":"Introduction and Evaluation of Virtual Microscopy in Teaching Veterinary Cytopathology","year":2007,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Virtual microscopy; Cytopathology; Curriculum; Medical education; Preference; Test (biology); Virtual Laboratory; Virtual reality; Medical physics; Psychology; Medicine; Pathology; Multimedia; Computer science; Artificial intelligence; Biology; Mathematics; Pedagogy","score_opus":0.048701162130316104,"score_gpt":0.4126389433040752,"score_spread":0.3639377811737591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029219200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9330572,0.00064210204,0.060888108,0.0018766494,0.0033769307,0.00008952662,1.2440476e-7,0.000007454593,0.000061903054],"genre_scores_gemma":[0.98488384,0.00011439125,0.013938626,0.0001176746,0.0009289738,0.0000035614917,8.117561e-7,0.0000056404433,0.0000064583214],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978836,0.00043404466,0.000639703,0.00018088544,0.00072180864,0.00013994338],"domain_scores_gemma":[0.9988716,0.00012201751,0.00045123728,0.00017728728,0.00026496546,0.00011289502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008276581,0.00008542718,0.00018148648,0.00035129304,0.00004396883,0.00001709209,0.0002650403,0.00011334153,0.000030619874],"category_scores_gemma":[0.0010929243,0.000082383915,0.0000347756,0.00021398226,0.000082577615,0.00062419847,0.000083543935,0.00040667,0.0000010698908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002197435,0.00031966364,0.00090696884,0.00003205627,0.000007813148,0.000025251962,0.0017952446,0.000042434258,0.10323298,0.0004765999,0.00052498037,0.89241624],"study_design_scores_gemma":[0.008948392,0.04084901,0.7237152,0.0019432023,0.00019401866,0.069147736,0.0048059146,0.058323894,0.027840089,0.011071894,0.052066263,0.0010944221],"about_ca_topic_score_codex":0.000018029463,"about_ca_topic_score_gemma":0.0000035522485,"teacher_disagreement_score":0.89132184,"about_ca_system_score_codex":0.0003058638,"about_ca_system_score_gemma":0.0007617733,"threshold_uncertainty_score":0.33595186},"labels":[],"label_agreement":null},{"id":"W2030677791","doi":"10.1016/j.ejmp.2013.05.001","title":"Method for data analysis in different institutions: Example of image guidance of prostate cancer patients","year":2013,"lang":"en","type":"article","venue":"Physica Medica","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Normality; Pooling; Set (abstract data type); Data set; Computer science; Data mining; Independence (probability theory); Position (finance); Statistical analysis; Statistics; Prostate cancer; Mathematics; Medical physics; Pattern recognition (psychology); Medicine; Cancer; Artificial intelligence","score_opus":0.05161727742852141,"score_gpt":0.3493948349227943,"score_spread":0.29777755749427287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030677791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06792938,0.00008831403,0.93040407,0.0005745271,0.00016871137,0.0005873931,0.00011015765,0.000023448269,0.000113982846],"genre_scores_gemma":[0.8707218,0.00004010833,0.12872446,0.000042279415,0.0000443023,0.00036350737,0.000041975138,0.0000055473847,0.000016019661],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986761,0.00006742122,0.0003591107,0.00039904696,0.0003285909,0.00016969227],"domain_scores_gemma":[0.998385,0.00017098131,0.00028436232,0.0009103895,0.00019999543,0.000049250528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023181831,0.000098694174,0.00031718108,0.00015028077,0.000031015083,0.000014126983,0.0009496253,0.000024749932,0.000015801015],"category_scores_gemma":[0.00009862935,0.00007936793,0.00006239962,0.0008915585,0.000089829315,0.00056396,0.00033741136,0.0000663449,0.0000015692657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069419235,0.0021369443,0.050471846,0.00081830274,0.0011889465,6.5094656e-7,0.0064979084,0.0013599887,0.035064872,0.008028822,0.014879325,0.879483],"study_design_scores_gemma":[0.001444964,0.00022106242,0.19465306,0.00016445098,0.00022631203,1.0090968e-7,0.00003268871,0.75174195,0.041006267,0.0060253213,0.0042115254,0.00027228528],"about_ca_topic_score_codex":0.0056153825,"about_ca_topic_score_gemma":0.00024942955,"teacher_disagreement_score":0.8792107,"about_ca_system_score_codex":0.00007015112,"about_ca_system_score_gemma":0.00011418509,"threshold_uncertainty_score":0.8488816},"labels":[],"label_agreement":null},{"id":"W2032882281","doi":"10.1118/1.1997502","title":"SU‐FF‐I‐22: An Inward Mammilla Detection Algorithm for Analysis of Skin‐Line Retraction","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pixel; Gray level; Position (finance); Line (geometry); Mathematics; Physics; Anatomy; Geometry; Medicine; Optics","score_opus":0.019239940433745866,"score_gpt":0.30010942915370714,"score_spread":0.28086948871996126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032882281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017844228,0.00002772914,0.9806966,0.00036733504,0.00068118935,0.00014500812,0.000009276144,0.00013070443,0.000097928685],"genre_scores_gemma":[0.95895463,0.000031815704,0.039015148,0.00025484886,0.0016273075,0.00003524094,0.000022180528,0.000014839239,0.000043988362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981536,0.00006112662,0.000352546,0.00040220123,0.00080363493,0.000226848],"domain_scores_gemma":[0.9988153,0.00013284896,0.00020209474,0.00048075645,0.0002073088,0.00016170654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056269846,0.00013280132,0.00028675553,0.0001679487,0.00010197581,0.00003790503,0.00041927389,0.00018752847,0.00003374567],"category_scores_gemma":[0.00008119119,0.00013020869,0.00019772074,0.0014568076,0.00007230602,0.00056394225,0.00006622587,0.0002493718,0.0000078716785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000900104,0.00011112144,0.00003633983,0.000008595305,0.00012521782,5.583775e-7,0.00013000975,0.0012761896,0.00039059305,0.00013792662,0.0001030077,0.9976714],"study_design_scores_gemma":[0.00033405548,0.00027215312,0.0008282519,0.000008561826,0.00016368538,0.0000029946593,0.000010781528,0.9199009,0.07287352,0.001758683,0.0037049982,0.00014144747],"about_ca_topic_score_codex":0.00009831039,"about_ca_topic_score_gemma":0.00014460411,"teacher_disagreement_score":0.99753,"about_ca_system_score_codex":0.00018203612,"about_ca_system_score_gemma":0.00008083667,"threshold_uncertainty_score":0.53097564},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2033392784","doi":"10.1016/j.ijrobp.2012.07.2284","title":"A Novel Semi-automated Multimodality Segmentation Tool for Radiation Therapy Treatment Planning in Sarcoma Patients","year":2012,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Contouring; Segmentation; Ground truth; Concordance; Radiation treatment planning; Radiation therapy; Artificial intelligence; Radiology; Nuclear medicine; Thresholding; Computer science; Internal medicine","score_opus":0.036195680780238486,"score_gpt":0.358155759826528,"score_spread":0.3219600790462895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033392784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55668277,0.00020392677,0.43897626,0.00039459454,0.0031824051,0.00041284345,0.00003829348,0.00008111208,0.000027807355],"genre_scores_gemma":[0.97484046,0.00018098044,0.023121484,0.00040399752,0.0012434222,0.00008214925,0.000107368374,0.00001638714,0.0000037229797],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99816644,0.00022678472,0.0007851,0.00024477666,0.0002763985,0.00030047202],"domain_scores_gemma":[0.9975207,0.0005079484,0.0012368186,0.00015915779,0.0004947197,0.0000806511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070141186,0.00020759754,0.00031516163,0.00024787497,0.000088967296,0.000059245314,0.00047675913,0.00019610516,0.0000053189933],"category_scores_gemma":[0.0001466033,0.00019184238,0.00015769561,0.00023869507,0.000045192093,0.0014370836,0.00004434805,0.00018243947,0.000005927788],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002518373,0.0010067021,0.4829096,0.0000031746483,0.0001970978,0.0000012379045,0.0019696353,0.0075101373,0.005462986,0.0018016493,0.00014078924,0.49874514],"study_design_scores_gemma":[0.025701672,0.0029092808,0.5947421,0.0000504447,0.00004412115,0.000057020512,0.00007656449,0.33179635,0.024565263,0.0038413731,0.01570586,0.000509924],"about_ca_topic_score_codex":0.000045767076,"about_ca_topic_score_gemma":0.0000031336808,"teacher_disagreement_score":0.49823523,"about_ca_system_score_codex":0.0026410385,"about_ca_system_score_gemma":0.00027142194,"threshold_uncertainty_score":0.7823105},"labels":[],"label_agreement":null},{"id":"W2034415322","doi":"10.1118/1.2829871","title":"A needle guidance system for biopsy and therapy using two-dimensional ultrasound","year":2008,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"","keywords":"Imaging phantom; Biopsy; Ultrasound; Breast biopsy; Needle biopsy; Mammography; Computer science; Radiology; Medicine; Breast cancer; Biomedical engineering; Medical physics; Cancer","score_opus":0.036994888100088906,"score_gpt":0.28110629761924577,"score_spread":0.24411140951915686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034415322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26926184,0.00038125706,0.72929657,0.0001437586,0.0005943946,0.00013483141,0.0000022663698,0.00010482716,0.000080257414],"genre_scores_gemma":[0.9794224,0.000014835286,0.01955309,0.00032905958,0.00063135626,0.000019235873,0.0000010655439,0.000010934603,0.000018053408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890757,0.000028555023,0.0001497469,0.00027294713,0.00044946952,0.00019172138],"domain_scores_gemma":[0.9993103,0.00020615452,0.00006490357,0.00023089688,0.000070054855,0.0001176852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020093146,0.00010089702,0.0001415534,0.000018475988,0.00022073816,0.000025278707,0.00025386433,0.00005259648,0.0000023672694],"category_scores_gemma":[0.000037520134,0.00008681786,0.000043373035,0.00020765373,0.00013554156,0.00019300624,0.00005908489,0.000098222234,0.0000040630953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003305913,0.001012571,0.008783144,0.000648934,0.00040589622,0.00027718942,0.006688057,0.0056969333,0.19243535,0.03866706,0.01151956,0.7335347],"study_design_scores_gemma":[0.0053668316,0.00046786078,0.0023116795,0.00040334705,0.000019261708,0.0025336882,0.000046342557,0.8689486,0.101487935,0.014858292,0.0026791415,0.00087703107],"about_ca_topic_score_codex":0.00004660177,"about_ca_topic_score_gemma":5.077405e-7,"teacher_disagreement_score":0.8632516,"about_ca_system_score_codex":0.00007051337,"about_ca_system_score_gemma":0.00014723839,"threshold_uncertainty_score":0.35403296},"labels":[],"label_agreement":null},{"id":"W2035526062","doi":"10.1007/s10278-009-9238-0","title":"Effect of Pixel Resolution on Texture Features of Breast Masses in Mammograms","year":2009,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale; University of Calgary","keywords":"Pixel; Artificial intelligence; Texture (cosmology); Pattern recognition (psychology); Receiver operating characteristic; Feature (linguistics); Nuclear medicine; Computer science; Mathematics; Medicine; Statistics; Image (mathematics)","score_opus":0.003942811802363157,"score_gpt":0.24945344573326106,"score_spread":0.2455106339308979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035526062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8784867,0.0014900684,0.107133426,0.0031906138,0.0008862962,0.00024063369,0.00001018968,0.0000507324,0.008511349],"genre_scores_gemma":[0.99870163,0.000009539774,0.0011541308,0.000037711816,0.00007823349,3.0202673e-7,3.0291915e-7,0.0000046586215,0.0000134849715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99895823,0.000050269962,0.00035878326,0.00011596648,0.00037169814,0.00014506896],"domain_scores_gemma":[0.99911404,0.00011590857,0.00044213305,0.00017065313,0.000114479,0.000042792555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035939328,0.000103243096,0.0002300299,0.0002989571,0.000017891967,0.00011116617,0.0003485177,0.00003105133,8.0998683e-7],"category_scores_gemma":[0.00007923335,0.0000802635,0.00011939145,0.00039148223,0.0000367394,0.001338472,0.000029249444,0.00023766689,6.2328496e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021653947,0.000105406245,0.008740608,0.000037979422,0.0000125134975,0.00003306835,0.00016295683,0.00070269656,0.013175449,0.00021290984,0.0003484391,0.9762514],"study_design_scores_gemma":[0.0060208393,0.01124357,0.6905027,0.00436733,0.00008455142,0.006895141,0.00018854794,0.016505543,0.24746858,0.014619835,0.0012459292,0.0008574526],"about_ca_topic_score_codex":0.000004817722,"about_ca_topic_score_gemma":9.845584e-7,"teacher_disagreement_score":0.975394,"about_ca_system_score_codex":0.00010014689,"about_ca_system_score_gemma":0.000039013416,"threshold_uncertainty_score":0.32730505},"labels":[],"label_agreement":null},{"id":"W2036929809","doi":"10.1016/j.bspc.2014.09.001","title":"Detection of the nipple in mammograms with Gabor filters and the Radon transform","year":2014,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Computer science; Gabor filter; Mammography; Computer vision; Radon transform; Distortion (music); Position (finance); Pattern recognition (psychology); Breast cancer; Medicine; Image (mathematics); Cancer; Telecommunications","score_opus":0.003150911215943249,"score_gpt":0.1825787168293061,"score_spread":0.17942780561336286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036929809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054318253,0.00043752824,0.9407718,0.0041439366,0.000055545275,0.00020088498,6.6043077e-7,0.000024822844,0.000046524074],"genre_scores_gemma":[0.9994016,0.000008931077,0.00023716512,0.00026408516,0.000048259728,0.000029038096,8.831718e-8,0.0000035117123,0.00000726648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992257,0.00008964574,0.00014549964,0.00016864948,0.00023902422,0.00013150455],"domain_scores_gemma":[0.99964577,0.00011841116,0.00007399832,0.00009275584,0.000024606845,0.000044460856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005160272,0.00007435735,0.00012912953,0.000035428744,0.00013117965,0.00006272107,0.00018185817,0.000049057624,9.722309e-7],"category_scores_gemma":[0.000015544661,0.000034408866,0.00002030878,0.00029005445,0.00046021203,0.00011533474,0.000018752573,0.00012990879,1.1338989e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018460602,0.0000141972605,0.00028845388,0.00003886797,0.0000058875125,2.612987e-7,0.00034240444,0.000008303917,0.0029835112,0.00009681151,0.0000026309035,0.9960341],"study_design_scores_gemma":[0.010976922,0.00075186853,0.008163937,0.00029636302,0.00004788892,0.000073677074,0.00015108092,0.9649004,0.006292337,0.004222052,0.003912772,0.0002107402],"about_ca_topic_score_codex":0.000103225735,"about_ca_topic_score_gemma":0.00005814446,"teacher_disagreement_score":0.9958233,"about_ca_system_score_codex":0.000014677764,"about_ca_system_score_gemma":0.000035548674,"threshold_uncertainty_score":0.16956703},"labels":[],"label_agreement":null},{"id":"W2041176167","doi":"10.1109/tmi.2014.2365436","title":"Analysis of Structural Similarity in Mammograms for Detection of Bilateral Asymmetry","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pattern recognition (psychology); Artificial intelligence; Mammography; Mathematics; Linear discriminant analysis; Receiver operating characteristic; Computer science; Correlation; Grayscale; Similarity (geometry); Wavelet; Statistics; Breast cancer; Pixel; Image (mathematics); Medicine","score_opus":0.009288029834090262,"score_gpt":0.2742700130887849,"score_spread":0.26498198325469463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041176167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12513116,0.0000122439205,0.87374693,0.00027699172,0.0006470807,0.000109381726,0.000005701901,0.00004792996,0.000022573464],"genre_scores_gemma":[0.9934162,0.000004410671,0.006410012,0.00011000551,0.000026544509,0.000020356723,9.580286e-7,0.0000071887494,0.000004319431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985238,0.00009922762,0.00041893614,0.00030050788,0.0004571127,0.00020041432],"domain_scores_gemma":[0.99908745,0.00029388088,0.00012684119,0.0003165355,0.00008947329,0.000085791056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006047856,0.00010852105,0.00029426962,0.00073703734,0.0000636642,0.000019324872,0.00033664884,0.00008281528,0.00001965554],"category_scores_gemma":[0.00004482526,0.00010358882,0.0002100682,0.0015700872,0.00010498501,0.00026326985,0.0000031716393,0.00025508646,4.6866526e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004361629,0.00006680557,0.0021769558,0.000049771155,0.00013247202,9.920849e-7,0.00022769436,0.016213128,0.006676718,0.00006757151,0.00000193312,0.97434235],"study_design_scores_gemma":[0.0004296405,0.00007098966,0.0061570103,0.000028604458,0.00010064106,0.0000036476874,0.000017587954,0.89954334,0.09306655,0.00046602523,0.000026177984,0.000089756206],"about_ca_topic_score_codex":0.00034516613,"about_ca_topic_score_gemma":0.00045680138,"teacher_disagreement_score":0.9742526,"about_ca_system_score_codex":0.00008518175,"about_ca_system_score_gemma":0.000037838996,"threshold_uncertainty_score":0.42242295},"labels":[],"label_agreement":null},{"id":"W2041284290","doi":"10.4103/2153-3539.143329","title":"American Telemedicine Association clinical guidelines for telepathology","year":2014,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"","keywords":"Telepathology; Virtual microscopy; Computer science; Second opinion; The Internet; Medical physics; Digital pathology; Multimedia; Telemedicine; Pathology; Medicine; Artificial intelligence; World Wide Web","score_opus":0.05496575470795071,"score_gpt":0.3955475637044483,"score_spread":0.3405818089964976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041284290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08731253,0.00002358628,0.903878,0.005684292,0.0026941458,0.00009779501,0.0000016016185,0.00003177329,0.000276309],"genre_scores_gemma":[0.11246854,0.00019669514,0.8762968,0.009137802,0.0018034487,0.000007730259,0.0000014586034,0.000010332813,0.00007717124],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972628,0.00018710099,0.0019283564,0.00007859529,0.00029729021,0.00024587315],"domain_scores_gemma":[0.993991,0.0008843306,0.0031355205,0.00027473908,0.0016245466,0.00008986439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064811152,0.00010843078,0.0004861548,0.00021112528,0.00007047598,0.00002937518,0.0005796117,0.00014671622,0.0000022184886],"category_scores_gemma":[0.006735252,0.00008514355,0.00016597628,0.00022674401,0.00009918691,0.00045084168,0.00008098127,0.00034277822,0.000012414184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059780024,0.00007784401,0.037243567,0.00004486014,0.00009018651,0.000023463364,0.0015988473,0.0005611677,0.0001994421,0.0029108992,0.082588285,0.87460166],"study_design_scores_gemma":[0.0072987787,0.016479522,0.051385034,0.0001194756,0.00026762785,0.006084478,0.0012533199,0.32287458,0.0010101355,0.020449288,0.57207197,0.00070576934],"about_ca_topic_score_codex":9.31151e-7,"about_ca_topic_score_gemma":0.0000033233403,"teacher_disagreement_score":0.8738959,"about_ca_system_score_codex":0.00012955126,"about_ca_system_score_gemma":0.00012108393,"threshold_uncertainty_score":0.8063212},"labels":[],"label_agreement":null},{"id":"W2042363537","doi":"10.1016/j.humpath.2007.04.006","title":"Spatial resolution requirements for acquisition of the virtual screening slide for digital whole-specimen breast histopathology","year":2007,"lang":"en","type":"article","venue":"Human Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Histopathology; Malignancy; Medicine; Breast cancer; Gold standard (test); Specialty; Breast imaging; Receiver operating characteristic; Sampling (signal processing); Radiology; Image resolution; Digital pathology; Medical physics; Pathology; Mammography; Artificial intelligence; Computer science; Cancer; Internal medicine; Computer vision","score_opus":0.03292699772400237,"score_gpt":0.2848834500725904,"score_spread":0.25195645234858804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042363537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11882915,0.000025206731,0.8789193,0.0003485388,0.0009254304,0.0005325756,0.00006550511,0.000069908536,0.00028437562],"genre_scores_gemma":[0.98740876,4.4151108e-7,0.011623025,0.0001781833,0.00040723314,0.00006977371,0.000033090935,0.000017866903,0.00026164335],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984381,0.000068807974,0.0004565905,0.00045345098,0.00019183152,0.00039120877],"domain_scores_gemma":[0.9987573,0.00012795557,0.0003713783,0.0005174499,0.00018432333,0.000041589665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085360795,0.00014279562,0.00020946488,0.0001493777,0.00033958917,0.000034976274,0.0005731491,0.0001543504,0.0000053298854],"category_scores_gemma":[0.000057937326,0.00013148849,0.00014249403,0.00014053822,0.00020534503,0.00037072852,0.0002421687,0.00010762877,0.0000036253016],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010527446,0.0003300051,0.0059142914,0.00009284409,0.000043265536,0.00003824036,0.0032607557,0.00041061846,0.52153474,0.11567197,0.0032703013,0.34838024],"study_design_scores_gemma":[0.014037285,0.009949955,0.72072667,0.0003182869,0.00018555402,0.0026009562,0.0006455264,0.024091372,0.09915711,0.09023716,0.036236107,0.0018139924],"about_ca_topic_score_codex":0.00001226707,"about_ca_topic_score_gemma":0.00006667204,"teacher_disagreement_score":0.86857957,"about_ca_system_score_codex":0.00019682669,"about_ca_system_score_gemma":0.000034495086,"threshold_uncertainty_score":0.5361945},"labels":[],"label_agreement":null},{"id":"W2042563007","doi":"10.1117/12.2079935","title":"Color model comparative analysis for breast cancer diagnosis using H and E stained images","year":2015,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Color space; Artificial intelligence; RGB color model; Feature extraction; Pattern recognition (psychology); Benchmark (surveying); Grayscale; Histopathology; Feature (linguistics); Computer vision; Image (mathematics); Pathology; Medicine","score_opus":0.032847617755678515,"score_gpt":0.2817156189121414,"score_spread":0.2488680011564629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042563007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97367895,0.0001426713,0.022399666,0.0025801715,0.0001585249,0.00058021955,0.00021466179,0.0000798408,0.00016529615],"genre_scores_gemma":[0.65306914,0.00006426399,0.34599882,0.00007555068,0.0001862267,0.00053403864,0.0000023482041,0.000022037268,0.000047559635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813867,2.042802e-8,0.00048656904,0.00046977232,0.00056829944,0.0003366996],"domain_scores_gemma":[0.9963673,0.00015229126,0.0003912817,0.000063259264,0.0028652935,0.0001605922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000585315,0.00026754793,0.00047588776,0.00016888777,0.00010570178,0.00020732787,0.0008785299,0.00012455137,0.0000022410402],"category_scores_gemma":[0.00016642378,0.00023062158,0.0004425321,0.00068162085,0.00019329325,0.0010767941,0.00025653272,0.00016070534,1.4239536e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000452138,0.00029302086,0.0074777347,0.00078423024,0.004495458,1.1355044e-7,0.0026340687,0.085090525,0.2602037,0.63016295,0.0070988247,0.0013072437],"study_design_scores_gemma":[0.00084559544,0.00016436266,0.0010130405,0.00008364252,0.00038969496,0.000006501308,0.00071549276,0.95250106,0.04167274,0.0021611506,0.0001908838,0.00025583708],"about_ca_topic_score_codex":0.000043491495,"about_ca_topic_score_gemma":9.3452275e-7,"teacher_disagreement_score":0.86741054,"about_ca_system_score_codex":0.0003904456,"about_ca_system_score_gemma":0.0000875911,"threshold_uncertainty_score":0.94044745},"labels":[],"label_agreement":null},{"id":"W2043070197","doi":"10.1371/journal.pone.0026007","title":"A TMA De-Arraying Method for High Throughput Biomarker Discovery in Tissue Research","year":2011,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Public Health Agency; Queen's University Belfast; Department for Employment and Learning, Northern Ireland","keywords":"Segmentation; Computer science; Core (optical fiber); Artificial intelligence; Pattern recognition (psychology); Thresholding; Single-core; Image (mathematics)","score_opus":0.31175309446777244,"score_gpt":0.3861568754857151,"score_spread":0.07440378101794265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043070197","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06296219,0.00012210969,0.93397665,0.0007546207,0.00013006372,0.00048333083,0.0000031299173,0.00008959294,0.001478288],"genre_scores_gemma":[0.42977166,0.000020529364,0.5694201,0.00007233129,0.00007348298,0.00022457277,6.190961e-7,0.00001410266,0.00040260493],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99827474,0.00025017565,0.00019007115,0.00044447155,0.00039263806,0.00044792148],"domain_scores_gemma":[0.9988567,0.00038874004,0.000049464048,0.00053372624,0.00011701751,0.00005432341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001824922,0.000093269504,0.00016856019,0.00022287038,0.00011751498,0.000103112914,0.00062869594,0.000085720945,0.000025169622],"category_scores_gemma":[0.00020710129,0.00009349434,0.000026159558,0.00066663267,0.000045442684,0.00078721636,0.00026063772,0.00019924113,0.000037772294],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045334635,0.0028872783,0.0057836124,0.0006634024,0.000322428,0.000066996334,0.014432919,0.000022000031,0.68522847,0.05846723,0.0024110463,0.22926126],"study_design_scores_gemma":[0.00064264575,0.00042528755,0.009014915,0.00021986011,0.000016014721,0.0000055097653,0.00008957111,0.030296264,0.8704703,0.08804297,0.0005199903,0.00025669328],"about_ca_topic_score_codex":0.0012010311,"about_ca_topic_score_gemma":0.0001726828,"teacher_disagreement_score":0.3668095,"about_ca_system_score_codex":0.00026508834,"about_ca_system_score_gemma":0.00010872692,"threshold_uncertainty_score":0.38125885},"labels":[],"label_agreement":null},{"id":"W2044979877","doi":"10.3138/jvme.34.2.177","title":"Teaching Histology to First-Year Veterinary Science Students Using Virtual Microscopy and Traditional Microscopy: A Comparison of Student Responses","year":2007,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Virtual microscopy; Flexibility (engineering); Interactivity; CLARITY; Computer science; Multimedia; Medical education; Medicine; Pathology; Biology; Mathematics","score_opus":0.11461739796550134,"score_gpt":0.47552913324435286,"score_spread":0.3609117352788515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044979877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90340185,0.0002433113,0.09230296,0.0008050377,0.003091337,0.00012379038,0.0000011781514,0.0000112765865,0.000019267052],"genre_scores_gemma":[0.93226594,0.000016158865,0.067123465,0.00028066197,0.0002879676,0.0000024687545,3.6874724e-7,0.000008696905,0.000014256829],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970024,0.00018917296,0.00081694406,0.00030021073,0.0014172905,0.00027397068],"domain_scores_gemma":[0.9982277,0.00032211113,0.000541105,0.0002352773,0.00026262394,0.00041116192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034920417,0.0001427055,0.00031298966,0.00083381723,0.00030052182,0.00008145212,0.001117285,0.000095333926,0.000016393826],"category_scores_gemma":[0.00052629074,0.00014000115,0.000056277473,0.00046656348,0.00037724292,0.00064199814,0.00036337943,0.00043339722,0.0000016187868],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023437638,0.0038840654,0.048677064,0.00014189439,0.000073730684,0.00014359677,0.021994682,0.0000822624,0.8474933,0.0014629608,0.0008977695,0.07280489],"study_design_scores_gemma":[0.0040076054,0.05919946,0.8565899,0.0029052391,0.000117648604,0.018462507,0.008731684,0.0040772115,0.026729979,0.00068718224,0.017470375,0.0010212247],"about_ca_topic_score_codex":0.00003291422,"about_ca_topic_score_gemma":0.0000033645238,"teacher_disagreement_score":0.82076335,"about_ca_system_score_codex":0.00068521703,"about_ca_system_score_gemma":0.0017815562,"threshold_uncertainty_score":0.5709081},"labels":[],"label_agreement":null},{"id":"W2045598464","doi":"10.1177/153303460500400103","title":"Quantitative Target Sizes for Breast Tumor Detection Prior to Metastasis: A Prerequisite to Rational Design of 4D Scanners for Breast Screening","year":2005,"lang":"en","type":"article","venue":"Technology in Cancer Research & Treatment","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Breast cancer; Medicine; Breast tumor; Computer science; Medical physics; Internal medicine; Cancer","score_opus":0.10621306605477678,"score_gpt":0.41829997841625693,"score_spread":0.3120869123614802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045598464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054275464,0.00044529265,0.9234426,0.016349679,0.00010031018,0.0047873645,0.0004119618,0.00018098515,0.000006320491],"genre_scores_gemma":[0.5605783,0.000018218829,0.4294836,0.00005131949,0.000059309383,0.009744667,0.0000024333146,0.00002216233,0.00004000541],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99723953,0.00016410432,0.00044345003,0.0008630091,0.00050032715,0.00078960846],"domain_scores_gemma":[0.99788153,0.0005443066,0.00014109476,0.0005339826,0.0007569284,0.00014216699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011816957,0.00024878883,0.0003958245,0.0016691099,0.0003548985,0.00008023269,0.00070887944,0.00012460777,0.000018098832],"category_scores_gemma":[0.00017994268,0.00023605126,0.00009578588,0.0021257137,0.00019047316,0.0004043532,0.0002026678,0.00018929837,0.000007952042],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032156156,0.00036131404,0.00033244953,0.00005230809,0.00028709698,0.0000048762113,0.0010733973,0.087350294,0.05250578,0.005575402,0.00023108831,0.84901035],"study_design_scores_gemma":[0.005207776,0.0136614125,0.0025522686,0.00037765756,0.000063987165,0.00012806324,0.0010627608,0.20817778,0.75427735,0.011173973,0.0026818835,0.0006351187],"about_ca_topic_score_codex":0.00065858976,"about_ca_topic_score_gemma":0.0021716943,"teacher_disagreement_score":0.84837526,"about_ca_system_score_codex":0.0025192983,"about_ca_system_score_gemma":0.0006583874,"threshold_uncertainty_score":0.96258914},"labels":[],"label_agreement":null},{"id":"W2047595924","doi":"10.1155/2013/578320","title":"Biomedical Signal and Image Processing for Clinical Decision Support Systems","year":2013,"lang":"en","type":"editorial","venue":"Computational and Mathematical Methods in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data science; Variety (cybernetics); Image processing; Decision support system; Signal processing; Artificial intelligence; Health care; Computational complexity theory; Computational model; Machine learning; Risk analysis (engineering); Data mining; Image (mathematics); Medicine; Algorithm; Digital signal processing","score_opus":0.07886041873988194,"score_gpt":0.495713254256492,"score_spread":0.41685283551661007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047595924","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012153815,0.0010426341,0.86052716,0.00057412556,0.13702276,0.0006304724,0.000008048682,0.00006599037,0.000116632335],"genre_scores_gemma":[0.000025748637,0.00016153467,0.8776199,0.00009614349,0.1217722,0.00018285285,0.000034654306,0.00002573498,0.00008122147],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959055,0.00043637987,0.0014804484,0.0008558878,0.0010052992,0.00031647272],"domain_scores_gemma":[0.9734826,0.025078766,0.00041385356,0.00023480921,0.00049523776,0.00029473653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073320204,0.00032694824,0.0011350358,0.00030862383,0.00011968187,0.00017023056,0.00046161076,0.00064438116,0.000031691798],"category_scores_gemma":[0.006254282,0.00023635213,0.00006402207,0.00028413162,0.00068367546,0.000271341,0.00031850272,0.00072252715,0.000007156077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032722906,0.000084410865,0.0000021673332,0.0015647924,0.000027018601,0.000009317016,0.00021815354,0.00001272349,0.000013143205,0.0046776207,0.5165571,0.47680083],"study_design_scores_gemma":[0.0013187861,0.0005968863,0.00002710217,0.0012896127,0.000047873848,0.000042703563,0.000047991325,0.54216164,0.000001425116,0.35557905,0.09865697,0.00022999254],"about_ca_topic_score_codex":0.000007114772,"about_ca_topic_score_gemma":2.3930707e-7,"teacher_disagreement_score":0.5421489,"about_ca_system_score_codex":0.00007861016,"about_ca_system_score_gemma":0.00033125718,"threshold_uncertainty_score":0.96381605},"labels":[],"label_agreement":null},{"id":"W2047934791","doi":"10.1007/s11548-010-0408-9","title":"Correction to “Detection of architectural distortion in prior mammograms using Gabor filters, phase portraits, fractal dimension, and texture analysis [1]”","year":2010,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal dimension; Gabor filter; Computer science; Dimension (graph theory); Artificial intelligence; Computer vision; Texture (cosmology); Distortion (music); Fractal; Pattern recognition (psychology); Image (mathematics); Mathematics; Telecommunications","score_opus":0.010199669807528443,"score_gpt":0.2731174456021993,"score_spread":0.26291777579467085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047934791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5847722,0.000058337882,0.4105313,0.0002372844,0.0043497793,0.000038912975,0.0000019048912,0.000008774394,0.0000014669208],"genre_scores_gemma":[0.98920846,0.000019978126,0.010286449,0.000121541656,0.00034838074,0.0000014417337,0.000004514629,0.000005399414,0.000003853345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985751,0.00015290962,0.00063712074,0.00024136667,0.00025656458,0.0001369409],"domain_scores_gemma":[0.9984691,0.00044016086,0.0005646365,0.00012231988,0.00030634823,0.00009744337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005822859,0.00013030511,0.00037777406,0.0012565082,0.000058613346,0.0000570199,0.0001984934,0.000111602865,0.000003966768],"category_scores_gemma":[0.000100238016,0.00011667855,0.00015661621,0.0005085911,0.000084833206,0.00036864434,0.000070858514,0.0004140352,1.3585867e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047605956,0.00015129455,0.06768111,0.000008130296,0.00051107246,0.00010373443,0.00055013,0.0032337941,0.049739204,0.000023481996,0.00013903914,0.87738293],"study_design_scores_gemma":[0.0007072886,0.0002744929,0.801265,0.00007469258,0.00008701525,0.005094196,0.000017832152,0.18799281,0.003952482,0.00010544843,0.0002566085,0.00017211313],"about_ca_topic_score_codex":0.00007525025,"about_ca_topic_score_gemma":0.00018738493,"teacher_disagreement_score":0.87721086,"about_ca_system_score_codex":0.00006617362,"about_ca_system_score_gemma":0.00007443043,"threshold_uncertainty_score":0.47580132},"labels":[],"label_agreement":null},{"id":"W2048351707","doi":"10.5539/gjhs.v7n6p46","title":"Diagnosis of Malignancy in Thyroid Tumors by Multi-Layer Perceptron Neural Networks With Different Batch Learning Algorithms","year":2015,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Shiraz University; Shiraz University of Medical Sciences","keywords":"Broyden–Fletcher–Goldfarb–Shanno algorithm; Artificial neural network; Conjugate gradient method; Algorithm; Receiver operating characteristic; Perceptron; Computer science; Backpropagation; Multilayer perceptron; Artificial intelligence; Mathematics; Machine learning","score_opus":0.03220490927487328,"score_gpt":0.3117327149596835,"score_spread":0.2795278056848102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048351707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74729896,0.0018632596,0.24898794,0.0009834672,0.00068447023,0.00014355723,0.0000013047336,0.00001867712,0.000018345747],"genre_scores_gemma":[0.98602206,0.00020095696,0.0135322185,0.00017339626,0.000055833734,0.0000054832926,1.9437408e-7,0.000005609066,0.0000042727193],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968705,0.00018147961,0.00075456704,0.00036171597,0.0011920101,0.0006397192],"domain_scores_gemma":[0.9980123,0.000040053787,0.00090197235,0.00024253287,0.00038708883,0.00041605884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001891933,0.00017503029,0.00040314303,0.0001623754,0.0001697883,0.00010582933,0.0012358244,0.000042973996,0.0000021034002],"category_scores_gemma":[0.000065675704,0.00012889758,0.000052989606,0.0014973573,0.0002603721,0.0010471825,0.00020436339,0.00042250147,8.423692e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007096598,0.00025317437,0.6715932,0.000029404195,0.000006792624,0.000039446495,0.0008867959,0.12329115,0.00011419031,0.000061591156,0.0006631018,0.20299019],"study_design_scores_gemma":[0.001525735,0.0027726192,0.48062938,0.00034386283,0.0000044611215,0.0005617295,0.0005081152,0.5129113,0.00037942448,0.00008615304,0.000052014693,0.00022520272],"about_ca_topic_score_codex":0.0004947738,"about_ca_topic_score_gemma":0.00007240099,"teacher_disagreement_score":0.38962016,"about_ca_system_score_codex":0.0010593265,"about_ca_system_score_gemma":0.0007601409,"threshold_uncertainty_score":0.52562904},"labels":[],"label_agreement":null},{"id":"W2058959360","doi":"10.1038/nrc2466","title":"Can genes for mammographic density inform cancer aetiology?","year":2008,"lang":"en","type":"review","venue":"Nature reviews. Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation","funders":"National Cancer Institute","keywords":"Breast cancer; Gene; MAMMOGRAPHIC DENSITY; Genetic predisposition; Cancer; Biology; Bioinformatics; Stromal cell; Genetics; Medicine; Cancer research; Mammography","score_opus":0.0557732485331422,"score_gpt":0.38038801889944035,"score_spread":0.32461477036629816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058959360","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.7185554e-7,0.9830807,0.0047062407,0.00044871224,0.006875971,0.004264866,0.00022528078,0.00025946545,0.00013831556],"genre_scores_gemma":[0.0000012022545,0.98323554,0.0046809134,0.001457415,0.0021588989,0.007836268,0.00007272535,0.000097904536,0.00045910725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953645,0.00028249243,0.0013752052,0.0015301988,0.0005359379,0.0009117054],"domain_scores_gemma":[0.9956468,0.0002910214,0.0016156088,0.0017115339,0.00048606863,0.00024897268],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005864625,0.0011079186,0.0036758585,0.0005412571,0.00041108928,0.000113525886,0.0023472314,0.0020679268,0.00004883608],"category_scores_gemma":[0.00015471787,0.0008416119,0.001909846,0.0021306213,0.00017980374,0.0003646596,0.00038064527,0.0021671383,0.00003488177],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034120721,0.00001091423,0.000016475646,0.013014011,0.00018187489,0.000004677338,0.0000347378,0.0000020983794,2.4979585e-7,0.0005098867,0.029369269,0.9568524],"study_design_scores_gemma":[0.0001814164,0.000052050993,0.000011698801,0.011393041,0.00047970994,0.0001519535,6.6964066e-7,0.00003286596,0.000006518752,0.00019813317,0.9865948,0.0008971463],"about_ca_topic_score_codex":0.00035063134,"about_ca_topic_score_gemma":0.0024553514,"teacher_disagreement_score":0.9572255,"about_ca_system_score_codex":0.0014361556,"about_ca_system_score_gemma":0.0019740118,"threshold_uncertainty_score":0.9994035},"labels":[],"label_agreement":null},{"id":"W2059242372","doi":"10.1016/j.humpath.2007.10.001","title":"Relationship between tumor grade and computed architectural complexity in breast cancer specimens","year":2008,"lang":"en","type":"article","venue":"Human Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Cancer; Medicine; Oncology; Internal medicine","score_opus":0.13730880661903144,"score_gpt":0.31945282944948206,"score_spread":0.1821440228304506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059242372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98141617,0.00006866587,0.016602308,0.0012690168,0.00018306165,0.00014183551,0.000015362686,0.00013653436,0.00016705332],"genre_scores_gemma":[0.99351364,0.0000019257175,0.006031214,0.0001957272,0.00019460282,0.000018601675,0.000005587741,0.000009410155,0.00002929162],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871075,0.00020775334,0.00024737712,0.00042514195,0.0001263294,0.00028267608],"domain_scores_gemma":[0.9993422,0.00014966357,0.0000991297,0.00031017532,0.000028271714,0.000070548114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015471087,0.00013512708,0.00022253786,0.00020975167,0.0002797283,0.000020927908,0.00031085857,0.00006219568,0.000015830212],"category_scores_gemma":[0.000009328807,0.00013988565,0.000029383758,0.00029878542,0.0003784572,0.0001495458,0.00019905098,0.00033844318,0.000012150248],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045023958,0.000020237549,0.988677,0.000009255289,0.0000032398702,0.00015387389,0.0012766427,0.00007383954,0.0003658685,0.008491844,0.00013494209,0.0007887507],"study_design_scores_gemma":[0.000457729,0.000049306018,0.97972333,0.000010150469,0.000003069573,0.0015384036,0.0000057326884,0.001049417,0.00008134398,0.016893739,0.00004146507,0.00014629724],"about_ca_topic_score_codex":0.00021676283,"about_ca_topic_score_gemma":0.00041669855,"teacher_disagreement_score":0.012097477,"about_ca_system_score_codex":0.00012236327,"about_ca_system_score_gemma":0.000036759775,"threshold_uncertainty_score":0.5704372},"labels":[],"label_agreement":null},{"id":"W2059483270","doi":"10.1007/s11517-006-0088-3","title":"Gabor filters and phase portraits for the detection of architectural distortion in mammograms","year":2006,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer vision; Computer science; Distortion (music); Mammography; Orientation (vector space); Mathematics; Medicine; Geometry","score_opus":0.010927639814719468,"score_gpt":0.24537964296831338,"score_spread":0.2344520031535939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059483270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41782194,0.00023622424,0.5813742,0.00014921486,0.00023157492,0.000119219505,7.2777675e-7,0.00006294451,0.0000039413776],"genre_scores_gemma":[0.9928562,0.0000064220385,0.006900702,0.000038048514,0.00017259117,0.000017454404,0.0000021060353,0.0000050363487,0.0000014248684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989781,0.000029662675,0.00031355783,0.00025689183,0.0001821735,0.0002396457],"domain_scores_gemma":[0.9992032,0.0005217471,0.00007779852,0.00011963371,0.000022016808,0.000055573015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052793394,0.00011040159,0.00015797377,0.00006473501,0.000061929735,0.000021834334,0.00025199185,0.000097300144,0.0000025255772],"category_scores_gemma":[0.00025018657,0.000073239185,0.000053638225,0.00027132191,0.000077844146,0.000044268825,0.000097786404,0.0002099546,3.2402056e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024114917,0.000053141248,0.0014362074,0.00003547072,0.0000075532907,0.0000042520624,0.00007907206,0.020549772,0.007884469,0.0004811223,0.0000044026124,0.9694404],"study_design_scores_gemma":[0.0005778412,0.00025198955,0.08431719,0.00004948072,0.0000030718252,0.00003687481,0.000005491383,0.9124239,0.0016475035,0.00018034237,0.00039976166,0.000106511194],"about_ca_topic_score_codex":0.00009894826,"about_ca_topic_score_gemma":0.000018894178,"teacher_disagreement_score":0.9693339,"about_ca_system_score_codex":0.000047449357,"about_ca_system_score_gemma":0.0000128926795,"threshold_uncertainty_score":0.29866073},"labels":[],"label_agreement":null},{"id":"W2060226124","doi":"10.1007/s11548-012-0681-x","title":"Measures of angular spread and entropy for the detection of architectural distortion in prior mammograms","year":2012,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Receiver operating characteristic; Artificial intelligence; Pattern recognition (psychology); Computer science; Breast cancer; Entropy (arrow of time); False positive paradox; Mammography; Feature selection; Mathematics; Medicine; Machine learning; Cancer; Physics","score_opus":0.02483441937952409,"score_gpt":0.2583454058111386,"score_spread":0.2335109864316145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060226124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46280232,0.0016004466,0.53376025,0.00033981694,0.001445422,0.000046784713,9.720248e-7,0.000003100309,9.027972e-7],"genre_scores_gemma":[0.9942313,0.00015781717,0.0052261692,0.000045364373,0.0003305129,0.0000038314543,6.427636e-7,0.0000032075784,0.0000011590132],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99902886,0.00014834812,0.00044580805,0.00008705454,0.00018127178,0.000108630375],"domain_scores_gemma":[0.99822336,0.0009953456,0.00046344998,0.000081241655,0.00020192369,0.00003464507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009176178,0.000072275674,0.00022413858,0.00026448845,0.000031964893,0.00001607474,0.00019917198,0.000057643185,6.128679e-7],"category_scores_gemma":[0.00007857877,0.000051117473,0.00010618748,0.000088955,0.00015064952,0.00023658735,0.000043893804,0.00011914765,3.5346815e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003145046,0.00005614213,0.089332655,0.000017543805,0.00020226128,0.000003864814,0.0005101167,0.0002765465,0.004929828,0.0003941593,0.000028302116,0.90393406],"study_design_scores_gemma":[0.0006083266,0.00020243776,0.9761973,0.000082542225,0.00002818737,0.0018968894,0.000026022208,0.0124659045,0.0069092624,0.0007255078,0.0007719963,0.000085630774],"about_ca_topic_score_codex":0.000022832199,"about_ca_topic_score_gemma":0.000013827857,"teacher_disagreement_score":0.90384847,"about_ca_system_score_codex":0.00004698551,"about_ca_system_score_gemma":0.00003205358,"threshold_uncertainty_score":0.208451},"labels":[],"label_agreement":null},{"id":"W2062072025","doi":"10.1016/j.micron.2014.07.005","title":"Digital differentiation of non-small cell carcinomas of the lung by the fractal dimension of their epithelial architecture","year":2014,"lang":"en","type":"article","venue":"Micron","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; Alberta Cancer Foundation; University of Calgary","funders":"Alberta Cancer Foundation","keywords":"Adenocarcinoma; Receiver operating characteristic; Pathology; Cytokeratin; Fractal dimension; Lung cancer; Lung; Medicine; Stage (stratigraphy); Histology; Carcinoma; Fractal; Cancer; Biology; Internal medicine; Immunohistochemistry; Mathematics","score_opus":0.0038841579597617467,"score_gpt":0.17558389796742063,"score_spread":0.1716997400076589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062072025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8454113,0.00009170186,0.15360649,0.00016989924,0.00026282563,0.00015837232,0.00002178834,0.000009499913,0.0002681445],"genre_scores_gemma":[0.9994621,0.0000025639724,0.00037517515,0.000024475425,0.0000415804,0.0000030119334,0.0000029221674,0.000007973204,0.00008015423],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924284,0.000074141884,0.00021794841,0.00017375535,0.00017344172,0.00011789611],"domain_scores_gemma":[0.9989989,0.00011163036,0.00030460424,0.0005099946,0.000058615584,0.000016261767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001297066,0.00010369702,0.00014011796,0.000032845805,0.00005635965,0.00002002565,0.0005870015,0.00005587051,0.000001995322],"category_scores_gemma":[0.00001060438,0.000056910834,0.000103281105,0.00014123382,0.00008469478,0.000084993815,0.00023465925,0.00013004587,8.8068197e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015248206,0.00004443318,0.003891072,0.00004434761,0.000009094833,2.6790207e-8,0.0015294536,0.00019209053,0.9639173,0.000027267675,0.00023349714,0.030096143],"study_design_scores_gemma":[0.00023633616,0.00010175382,0.027847039,0.00003034287,0.000009804445,0.0000020609125,0.00002709077,0.012103332,0.95905215,0.0001953593,0.00033224467,0.00006248933],"about_ca_topic_score_codex":0.00007708484,"about_ca_topic_score_gemma":0.000012463399,"teacher_disagreement_score":0.15405086,"about_ca_system_score_codex":0.000029163035,"about_ca_system_score_gemma":0.000025041261,"threshold_uncertainty_score":0.23207565},"labels":[],"label_agreement":null},{"id":"W2062630716","doi":"10.1504/ijcbdd.2008.021422","title":"An ensemble machine learning approach to predict survival in breast cancer","year":2008,"lang":"en","type":"article","venue":"International Journal of Computational Biology and Drug Design","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Machine learning; Ensemble learning; Computer science; Artificial intelligence; Sensitivity (control systems); Feature (linguistics); Perspective (graphical); Ensemble forecasting; Engineering","score_opus":0.0236461057749262,"score_gpt":0.2889562404185216,"score_spread":0.2653101346435954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062630716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10244424,0.00018976851,0.8946811,0.0017802608,0.0006888657,0.00006331789,0.000007584028,0.00001950113,0.00012534266],"genre_scores_gemma":[0.93029135,0.0001017119,0.06900293,0.00031089157,0.000258401,0.000005876697,0.0000054507295,0.000005336621,0.000018069866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987211,0.0003136854,0.00033599886,0.00020704725,0.00029535798,0.0001268083],"domain_scores_gemma":[0.99897623,0.00026090594,0.00019585279,0.000058155834,0.0004133675,0.00009547539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006531088,0.0001017464,0.00016376922,0.00034657243,0.00008193365,0.000038162634,0.0005232415,0.000050215414,0.0000072881867],"category_scores_gemma":[0.00002967026,0.00009078154,0.000036034005,0.00017866369,0.000060230952,0.00043132016,0.00006554,0.00024100718,0.0000025670606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031029427,0.000157211,0.06701278,0.0000023638672,0.0000776402,0.000037457085,0.0010332612,0.9030866,0.0006915645,0.0053286077,0.00025955474,0.022002688],"study_design_scores_gemma":[0.0015846987,0.00031888203,0.17913012,0.000041831052,0.000006940355,0.0026923378,0.000041403164,0.79353064,0.0004157242,0.021380357,0.0006127224,0.00024434974],"about_ca_topic_score_codex":0.00007394672,"about_ca_topic_score_gemma":0.0000055883097,"teacher_disagreement_score":0.8278471,"about_ca_system_score_codex":0.00010438588,"about_ca_system_score_gemma":0.00020265098,"threshold_uncertainty_score":0.3701964},"labels":[],"label_agreement":null},{"id":"W2063223696","doi":"10.1186/1756-0500-5-35","title":"Performance of a simple chromatin-rich segmentation algorithm in quantifying basal cell carcinoma from histology images","year":2012,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Calgary Laboratory Services","funders":"University of Calgary","keywords":"Basal cell carcinoma; Segmentation; Histology; Algorithm; Computer science; Artificial intelligence; Chromatin; Pattern recognition (psychology); Basal cell; Pathology; Biology; Medicine; Genetics; DNA","score_opus":0.1553866638217305,"score_gpt":0.3851778046942798,"score_spread":0.22979114087254932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063223696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8862982,0.00059377693,0.112397015,0.000056897177,0.00024189963,0.00021635763,0.0000067983224,0.00002462982,0.00016446874],"genre_scores_gemma":[0.8625492,0.000025797295,0.13720825,0.0000095979585,0.0001235604,0.00005223454,0.0000057065076,0.000010156206,0.000015511592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99783206,0.00043601068,0.00029582952,0.0003115075,0.00058062526,0.00054398214],"domain_scores_gemma":[0.99808174,0.001149328,0.000107247346,0.00042663858,0.0001560103,0.00007905334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013464851,0.00010581324,0.00017652313,0.00036084332,0.00012781814,0.000043487777,0.000534303,0.000074612384,0.000039668375],"category_scores_gemma":[0.00018225603,0.00010626596,0.000031473184,0.00072498847,0.00011532559,0.0007082718,0.00031270116,0.00026763414,0.000049382204],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002363939,0.00010322985,0.84153664,0.000121595775,0.0000032828648,0.0000023058756,0.0018760535,0.00011785379,0.10887349,0.000030802836,0.000211884,0.04709925],"study_design_scores_gemma":[0.00030978819,0.00013654595,0.45969877,0.000013738337,0.000001459124,0.0000017497085,0.00012661962,0.12496025,0.41449675,0.00013549253,0.000030412462,0.00008842316],"about_ca_topic_score_codex":0.0029959606,"about_ca_topic_score_gemma":0.00018049913,"teacher_disagreement_score":0.38183784,"about_ca_system_score_codex":0.00024507497,"about_ca_system_score_gemma":0.00017085398,"threshold_uncertainty_score":0.45290163},"labels":[],"label_agreement":null},{"id":"W2063548382","doi":"10.1309/ajcpvbzz4ikjhy3u","title":"An Improved Processing Method for Breast Whole-Mount Serial Sections for Three-Dimensional Histopathology Imaging","year":2009,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Fixation (population genetics); Histopathology; Pathology; Medicine; Biomedical engineering","score_opus":0.02764733658943384,"score_gpt":0.4022674204029074,"score_spread":0.37462008381347356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063548382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060142566,0.00007667561,0.92850393,0.008233248,0.0026610277,0.000284424,0.000021476215,0.00006594111,0.000010706565],"genre_scores_gemma":[0.45371047,0.000001941692,0.54212797,0.00263035,0.0014864516,0.000018154322,0.0000020290145,0.000016531043,0.0000061232304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966773,0.0005429043,0.0015044947,0.0006137172,0.00019601655,0.00046556193],"domain_scores_gemma":[0.9953248,0.0009397543,0.0019302146,0.00043184485,0.0011239173,0.0002494617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040227305,0.00021814146,0.0008990465,0.00022306525,0.00026094881,0.000070257985,0.0007671788,0.00013010752,0.0000027989274],"category_scores_gemma":[0.0006515895,0.0001945812,0.00042340264,0.00031146462,0.00038120942,0.0006590885,0.000056201647,0.000534338,0.000001290558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008701116,0.00023207586,0.00041955634,0.0000056286453,0.000012929564,0.000036711797,0.00010996959,0.00086987927,0.01833451,0.0003630142,0.00017050549,0.9785751],"study_design_scores_gemma":[0.0067011667,0.027484301,0.11355792,0.000072303854,0.00024023298,0.020257317,0.00017060028,0.7738834,0.00054443383,0.049590476,0.006697927,0.0007999278],"about_ca_topic_score_codex":0.000013143979,"about_ca_topic_score_gemma":0.000029620323,"teacher_disagreement_score":0.97777516,"about_ca_system_score_codex":0.0001590812,"about_ca_system_score_gemma":0.0005780677,"threshold_uncertainty_score":0.7934791},"labels":[],"label_agreement":null},{"id":"W2065789139","doi":"10.1117/12.503210","title":"<title>Segmentation of the breast region in mammograms using active contours</title>","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Active contour model; Computer science; Segmentation; Breast tissue; Breast cancer; Artificial intelligence; Right breast; Mammography; Pattern recognition (psychology); Image segmentation; Computer vision; Medicine; Internal medicine; Cancer","score_opus":0.013550986099385,"score_gpt":0.2317970674408512,"score_spread":0.21824608134146622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065789139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98611724,0.00006736142,0.0013849429,0.00058905844,0.00048331163,0.00031095222,0.000007923204,0.00003671238,0.011002509],"genre_scores_gemma":[0.9272442,0.000054186043,0.07204859,0.000057003876,0.00018856468,0.00004416245,0.0000011922399,0.00003188125,0.00033022472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989667,4.2285173e-8,0.0002848857,0.00019905064,0.00038129874,0.00016801819],"domain_scores_gemma":[0.9991358,0.000040447958,0.00024404543,0.000054693803,0.0004913121,0.000033696793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024304191,0.00012622631,0.00015609834,0.000063629675,0.0000373868,0.000040684794,0.00054140744,0.00009401188,0.000012692208],"category_scores_gemma":[0.00011374831,0.00010057005,0.00020887076,0.00034786505,0.00010161266,0.000337002,0.00008065618,0.00014875435,0.0000018945058],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000223624,0.00006308919,0.00031566407,0.00012960943,0.0001067206,7.212567e-8,0.00023011604,0.00014682769,0.28641477,0.70699024,0.00196639,0.0036141744],"study_design_scores_gemma":[0.0028818592,0.00046439123,0.0060213325,0.0014263836,0.00023151013,0.000230518,0.0014585592,0.21003237,0.7339076,0.019223468,0.023049863,0.00107214],"about_ca_topic_score_codex":0.00000603278,"about_ca_topic_score_gemma":2.8238603e-7,"teacher_disagreement_score":0.68776673,"about_ca_system_score_codex":0.00022341328,"about_ca_system_score_gemma":0.000038369228,"threshold_uncertainty_score":0.41011274},"labels":[],"label_agreement":null},{"id":"W2067136649","doi":"10.1109/memb.2005.1384102","title":"Characterization of architectural distortion in mammograms","year":2005,"lang":"en","type":"article","venue":"IEEE Engineering in Medicine and Biology Magazine","topic":"AI in cancer detection","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Characterization (materials science); Distortion (music); Mammography; Medical imaging; Computer science; Biomedical engineering; Artificial intelligence; Medical physics; Engineering; Medicine; Materials science; Breast cancer; Nanotechnology; Electronic engineering; Internal medicine; Cancer","score_opus":0.017245158297575527,"score_gpt":0.25394253676901063,"score_spread":0.2366973784714351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067136649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.778982,0.00010446949,0.21975093,0.00077733,0.00026900374,0.00006067119,3.7700244e-7,0.00003073339,0.000024514953],"genre_scores_gemma":[0.99724865,0.00007875404,0.002411602,0.000057600177,0.00017141999,0.000009344301,0.0000055343708,0.0000035759547,0.000013544893],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99945,0.000017786275,0.0002171062,0.00015282515,0.00004101688,0.000121212484],"domain_scores_gemma":[0.9997812,0.000033590943,0.000044960878,0.00010571054,0.000012694263,0.000021863203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018334585,0.000073940515,0.00014949332,0.0002489649,0.000006022652,0.0000022155898,0.00010180524,0.000053175547,0.0000027741737],"category_scores_gemma":[0.000027675424,0.00006131391,0.000009097492,0.00029803472,0.000040800023,0.00009107517,0.00001927831,0.00011405004,0.0000011757267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014868432,0.00002181342,0.016798254,0.000044829412,0.0000045844376,0.0000027982733,0.000656381,0.0028905303,0.7423919,0.00041194187,0.000012018233,0.2367501],"study_design_scores_gemma":[0.0019262334,0.0007308115,0.7031159,0.00026254245,0.000005791099,0.000067073626,0.0000061022424,0.2679856,0.020259425,0.00020835642,0.0051733125,0.00025883203],"about_ca_topic_score_codex":0.000024104793,"about_ca_topic_score_gemma":0.000060013113,"teacher_disagreement_score":0.72213244,"about_ca_system_score_codex":0.000038703776,"about_ca_system_score_gemma":0.0000058073115,"threshold_uncertainty_score":0.25003088},"labels":[],"label_agreement":null},{"id":"W2068848953","doi":"10.1007/s10916-011-9788-9","title":"An Expert Support System for Breast Cancer Diagnosis using Color Wavelet Features","year":2011,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Saskatchewan Health Research Foundation; Government of Canada","keywords":"Artificial intelligence; Support vector machine; Breast cancer; Pattern recognition (psychology); Computer science; Classifier (UML); Naive Bayes classifier; Wavelet; Artificial neural network; Computer-aided diagnosis; Cancer; Medicine","score_opus":0.052460414810077474,"score_gpt":0.32570621915030196,"score_spread":0.2732458043402245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068848953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079534695,0.0028808743,0.8869604,0.0034631165,0.026013676,0.0007662691,0.00006294366,0.00015930072,0.00015873332],"genre_scores_gemma":[0.99105823,0.00012638452,0.0056815394,0.00023517187,0.0027343368,0.00012547878,3.0545482e-7,0.000020674326,0.000017871293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971959,0.00018017394,0.00070117984,0.0002331947,0.0013778072,0.00031172627],"domain_scores_gemma":[0.9980356,0.00012335974,0.00065956987,0.00029138042,0.0003932237,0.00049684395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018699197,0.00015295172,0.00042546936,0.00013766864,0.00012694424,0.00012577078,0.0012275546,0.00023518717,0.000076314536],"category_scores_gemma":[0.000058609465,0.000109556306,0.00014607619,0.00020110064,0.00005034485,0.0006118935,0.00006669378,0.00026204652,0.000002269843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015370212,0.001963524,0.018165234,0.0044970443,0.0019289758,0.0027705529,0.025917882,0.00083908107,0.005732922,0.019655567,0.26989844,0.6470938],"study_design_scores_gemma":[0.013278738,0.007856537,0.031772662,0.015508553,0.00050879293,0.08668379,0.009481371,0.7185326,0.029453091,0.0003118819,0.08395589,0.00265607],"about_ca_topic_score_codex":0.0012353447,"about_ca_topic_score_gemma":0.000032473177,"teacher_disagreement_score":0.9115235,"about_ca_system_score_codex":0.000552783,"about_ca_system_score_gemma":0.0005465303,"threshold_uncertainty_score":0.44675764},"labels":[],"label_agreement":null},{"id":"W2070210288","doi":"10.1016/j.cmpb.2004.04.003","title":"A Java application for tissue section image analysis","year":2005,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Java; Computer science; Section (typography); Computer graphics (images); Image (mathematics); Artificial intelligence; Programming language; Operating system","score_opus":0.03408717445000564,"score_gpt":0.39247996345919417,"score_spread":0.35839278900918853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070210288","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001756277,0.00046996013,0.99450594,0.0019635372,0.00046539796,0.0006347437,7.968162e-7,0.00015686192,0.000046462763],"genre_scores_gemma":[0.031050896,0.000046725716,0.96747196,0.00023824761,0.0009036718,0.00023602741,0.000015657904,0.000008299029,0.000028528088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986767,0.00013482397,0.0003153167,0.0005172238,0.00013116037,0.00022478247],"domain_scores_gemma":[0.99919283,0.00014466178,0.0001152064,0.00037964896,0.000086980006,0.00008064405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014971829,0.00013597374,0.00027193158,0.00046264383,0.00007741369,0.000084720945,0.00027449275,0.00008959497,0.000002414763],"category_scores_gemma":[0.00001159665,0.00011932773,0.000055216573,0.0018822876,0.0000804276,0.00026131803,0.000110322224,0.000105743326,0.0000014117786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007990201,0.000044916953,0.00026160388,0.000027534768,0.000043554966,4.751616e-7,0.00038966074,0.000038659615,0.003674445,0.0004290702,0.00009027752,0.99499184],"study_design_scores_gemma":[0.0006393165,0.0004900669,0.0027955882,0.000018268653,0.00005869133,0.000016157117,0.000011302844,0.7925543,0.003065859,0.0023354741,0.19784674,0.00016821304],"about_ca_topic_score_codex":0.00007214648,"about_ca_topic_score_gemma":0.000043730444,"teacher_disagreement_score":0.9948236,"about_ca_system_score_codex":0.00008091137,"about_ca_system_score_gemma":0.00001560768,"threshold_uncertainty_score":0.48660436},"labels":[],"label_agreement":null},{"id":"W2071096105","doi":"10.1006/rtim.2001.0285","title":"Multiresolution-Based Segmentation of Calcifications for the Early Detection of Breast Cancer","year":2002,"lang":"en","type":"article","venue":"Real-Time Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of South Florida; BC Cancer Agency; University of Florida","keywords":"Segmentation; Artificial intelligence; Mammography; Pixel; Computer science; Computer vision; Wavelet; Pattern recognition (psychology); Multiresolution analysis; Contrast (vision); Digital mammography; Fuzzy logic; CAD; Breast cancer; Wavelet transform; Discrete wavelet transform; Cancer; Medicine; Engineering","score_opus":0.017606832025224835,"score_gpt":0.26649911075052574,"score_spread":0.2488922787253009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071096105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017179321,0.00017129353,0.9805286,0.0012069345,0.00022254336,0.00042200478,0.000032082375,0.000090870744,0.00014635989],"genre_scores_gemma":[0.9891786,0.00004127358,0.01046875,0.000023180686,0.00005775912,0.00015365501,0.0000013581371,0.000010698068,0.00006475341],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916196,0.00004121426,0.00025224622,0.00020215486,0.00019562608,0.00014677552],"domain_scores_gemma":[0.9988692,0.0002524178,0.00025433442,0.00035031166,0.0002472035,0.000026527243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018441322,0.000082227154,0.00009889422,0.00010628455,0.00016947386,0.000030506748,0.00026490033,0.00002334914,0.000028771903],"category_scores_gemma":[0.000018840026,0.00007163077,0.00007356978,0.00039148517,0.000074558084,0.00030634544,0.000023029696,0.00005033743,0.000006204463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016236685,0.000050173647,0.0014469295,0.000039308314,0.000023540737,1.1942495e-7,0.00059979275,0.0059037907,0.6537061,0.00009987226,0.00017309091,0.33794108],"study_design_scores_gemma":[0.0002923433,0.000018936551,0.023644717,0.000029440012,0.00002208907,0.0000030681874,0.00002462793,0.83614737,0.13964956,0.000045751476,0.00005533143,0.00006674665],"about_ca_topic_score_codex":0.001951916,"about_ca_topic_score_gemma":0.00002673867,"teacher_disagreement_score":0.9719992,"about_ca_system_score_codex":0.00015145027,"about_ca_system_score_gemma":0.000036382193,"threshold_uncertainty_score":0.29507262},"labels":[],"label_agreement":null},{"id":"W2071470910","doi":"10.1109/spices.2015.7091536","title":"Novel hybrid hardware architecture for nuclei detection in skin histopathological images","year":2015,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Architecture; Computer science; Computer hardware; Artificial intelligence; Embedded system","score_opus":0.029593960644338054,"score_gpt":0.25682884956471935,"score_spread":0.2272348889203813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071470910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019368723,0.000039935778,0.9770575,0.00087807694,0.00073645485,0.00028199688,0.000004819429,0.00027864365,0.0013538582],"genre_scores_gemma":[0.81312025,0.0000015357992,0.18595886,0.00033396788,0.00014401841,0.00009175267,0.0000012843158,0.000011104774,0.00033722894],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889964,0.000037313497,0.00018212973,0.00044097012,0.00019228656,0.00024768952],"domain_scores_gemma":[0.9993662,0.000059410253,0.000058936494,0.0003379243,0.00009032922,0.000087184475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036857335,0.00012549973,0.00013840967,0.00014286741,0.000057289784,0.00007444616,0.00042504747,0.000064320746,0.0000055034707],"category_scores_gemma":[0.00013238478,0.00010796786,0.00006149697,0.00023517381,0.000039099086,0.00028612383,0.00014063178,0.00016953574,0.000018483792],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014083396,0.00018882808,0.0003140904,0.000032445816,0.000006850195,0.00003157087,0.0008751704,0.0035098994,0.05012943,0.0018956137,0.0058609755,0.9370143],"study_design_scores_gemma":[0.0051318416,0.0020145974,0.018691557,0.000050004655,0.000016001773,0.0012249113,0.0001939089,0.19866602,0.58771986,0.047231033,0.13778856,0.0012717318],"about_ca_topic_score_codex":0.00008518997,"about_ca_topic_score_gemma":0.00019505125,"teacher_disagreement_score":0.93574256,"about_ca_system_score_codex":0.0003026007,"about_ca_system_score_gemma":0.0000510485,"threshold_uncertainty_score":0.44028017},"labels":[],"label_agreement":null},{"id":"W2078113043","doi":"10.1117/12.2041310","title":"CI Slide: calibration slide for quantitative microscopy imaging in absorbance","year":2014,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Scanner; Calibration; Computer science; Computer vision; Artificial intelligence; Orientation (vector space); Software; Optics; Mathematics; Physics","score_opus":0.0117561437107534,"score_gpt":0.2536701782675176,"score_spread":0.2419140345567642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078113043","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9404233,0.00010144691,0.053414095,0.0041125775,0.0005032782,0.0006913841,0.000022712757,0.00012000622,0.00061120774],"genre_scores_gemma":[0.39305913,0.000042447235,0.6058321,0.00025697012,0.00032408192,0.00034732342,0.0000049400137,0.000053024036,0.000079953556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977803,3.427734e-8,0.00071344286,0.00054818403,0.0005312618,0.00042677956],"domain_scores_gemma":[0.9977981,0.00033301496,0.0004618598,0.00008714316,0.0012349084,0.00008499174],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010200855,0.0002855591,0.0003618842,0.00015774323,0.00009943476,0.00021920756,0.0013192875,0.00013073959,0.0000023959137],"category_scores_gemma":[0.0008177686,0.00026630893,0.00039084634,0.00047458085,0.00015166335,0.0014135075,0.00018727133,0.00025600631,0.0000011957579],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059627328,0.000049189613,0.0005820493,0.0002661161,0.000057101184,2.8401088e-8,0.0003276464,0.00041118046,0.42591405,0.569679,0.0017408489,0.00091312657],"study_design_scores_gemma":[0.0011838125,0.00030076888,0.00090853113,0.00034291277,0.000034794582,0.000008122343,0.0004760639,0.6776174,0.30338868,0.012241396,0.003130031,0.00036749546],"about_ca_topic_score_codex":0.0000180042,"about_ca_topic_score_gemma":8.186425e-7,"teacher_disagreement_score":0.6772062,"about_ca_system_score_codex":0.00028348496,"about_ca_system_score_gemma":0.00004545837,"threshold_uncertainty_score":0.9999789},"labels":[],"label_agreement":null},{"id":"W2078176535","doi":"10.1007/bf02344632","title":"Identification of the breast boundary in mammograms using active contour models","year":2004,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prairie Bible Institute; University of Calgary","funders":"","keywords":"Preprocessor; Artificial intelligence; Pixel; Boundary (topology); Mammography; Active contour model; Computer science; CAD; Pattern recognition (psychology); Computer vision; Chain code; Segmentation; Breast cancer; Image segmentation; Edge detection; Mathematics; Image processing; Image (mathematics); Medicine; Cancer","score_opus":0.01874016144980575,"score_gpt":0.24542672044084474,"score_spread":0.22668655899103898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078176535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42970476,0.000058998663,0.56943595,0.00024302387,0.00037834837,0.000089978406,9.112369e-7,0.0000689997,0.000019053336],"genre_scores_gemma":[0.99405646,0.000005002298,0.0057544746,0.000070803224,0.00010123181,0.000003682521,6.528364e-7,0.0000066655316,0.0000010410209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984823,0.000062380415,0.00044253017,0.0003328364,0.0003871306,0.0002928125],"domain_scores_gemma":[0.9993182,0.00012234427,0.00014208167,0.00028065717,0.00005139427,0.00008536443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006217968,0.00013378501,0.00020617376,0.00006948609,0.000082888415,0.000037293754,0.00079675013,0.00016571388,0.0000042675106],"category_scores_gemma":[0.00019124393,0.000094810144,0.00008251955,0.00060934003,0.0001143076,0.00016201944,0.0003922829,0.00040731995,0.0000022147021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010443563,0.00010256172,0.001560343,0.00003085381,0.00001836954,0.000011491723,0.00047561707,0.8982698,0.015217705,0.009578173,0.0000014797054,0.074723214],"study_design_scores_gemma":[0.00030016416,0.000027029308,0.033623613,0.00018446831,0.0000022918796,0.00009417923,0.000017499373,0.96090746,0.0024842506,0.002221639,0.000014185476,0.00012320923],"about_ca_topic_score_codex":0.0001378509,"about_ca_topic_score_gemma":0.0000056982926,"teacher_disagreement_score":0.5643517,"about_ca_system_score_codex":0.00025792758,"about_ca_system_score_gemma":0.0001099004,"threshold_uncertainty_score":0.38662454},"labels":[],"label_agreement":null},{"id":"W2078710233","doi":"10.1148/radiology.215.2.r00ma15554","title":"Potential Contribution of Computer-aided Detection to the Sensitivity of Screening Mammography","year":2000,"lang":"en","type":"article","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":555,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Mammography; Recall rate; CAD; Radiology; Recall; Breast cancer; Cancer detection; Biopsy; Screening mammography; Medical physics; Cancer; Internal medicine; Artificial intelligence","score_opus":0.0061880135713373785,"score_gpt":0.2157110581818913,"score_spread":0.2095230446105539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078710233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37503305,0.00002925884,0.62415373,0.0002897555,0.00032201855,0.00011507432,0.0000024669107,0.000035604935,0.00001907336],"genre_scores_gemma":[0.9882405,0.000011556321,0.011437121,0.00012269971,0.00017193316,0.0000062378735,0.0000014330299,0.0000036787437,0.000004851769],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988255,0.0004134981,0.00022791927,0.00022967295,0.00012765577,0.00017573724],"domain_scores_gemma":[0.9992691,0.00013950448,0.000117211246,0.00033288746,0.00010630061,0.000034993045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006636499,0.000079871774,0.00019217709,0.00011384229,0.00008627517,0.000009375915,0.00022172858,0.00007868225,0.0000095635805],"category_scores_gemma":[0.00002188634,0.00006671364,0.000090914495,0.00046937214,0.000086945525,0.00010942513,0.00005705462,0.000103522456,0.0000060353655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014199574,0.000027724342,0.00089131616,0.0000067189044,0.000057438534,0.0000060920693,0.00021128969,0.041871022,0.08878101,0.00084339565,0.0001640042,0.866998],"study_design_scores_gemma":[0.00081173866,0.0011089664,0.19152457,0.000027593536,0.000031088042,0.0006003119,0.000012281803,0.6446851,0.1573064,0.00091991154,0.0027550808,0.00021695856],"about_ca_topic_score_codex":0.00020553131,"about_ca_topic_score_gemma":0.00007609645,"teacher_disagreement_score":0.86678106,"about_ca_system_score_codex":0.000028950295,"about_ca_system_score_gemma":0.000015364483,"threshold_uncertainty_score":0.27205035},"labels":[],"label_agreement":null},{"id":"W2079273483","doi":"10.1111/j.1939-165x.2002.tb00277.x","title":"Atlas of Canine and Feline Cytology","year":2002,"lang":"en","type":"article","venue":"Veterinary Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Citation; Medicine; Library science; Cytology; Veterinary medicine; Pathology; Computer science","score_opus":0.12060300880681235,"score_gpt":0.3577109234789234,"score_spread":0.23710791467211106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079273483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95235676,0.00048468483,0.043203536,0.001722742,0.0012199939,0.000087424865,0.0000033121787,0.000087735185,0.00083380594],"genre_scores_gemma":[0.97697175,0.00042233025,0.021780523,0.00051107246,0.00015179346,0.000008076927,6.6141723e-7,0.0000073927436,0.00014642741],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99841374,0.0003254275,0.0005405098,0.00043811504,0.000078988094,0.00020323262],"domain_scores_gemma":[0.9987927,0.00041955605,0.00017428093,0.00048386585,0.000049959723,0.00007964849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041365362,0.00010469038,0.00033494935,0.000073022806,0.00004004644,0.000006909896,0.00036378554,0.00018671268,0.000065600645],"category_scores_gemma":[0.0001938003,0.00009863763,0.00006286899,0.00015938265,0.00033832848,0.00011224214,0.00040171045,0.00022143249,0.000047453497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024378141,0.00074477476,0.026588393,0.00010686645,0.00007273365,0.0029122666,0.0008430325,0.000062002684,0.032165855,0.00639735,0.005224726,0.9246382],"study_design_scores_gemma":[0.010040173,0.079965614,0.45460144,0.0001243921,0.00011469588,0.033663396,0.00006647074,0.2314011,0.002767226,0.021151148,0.16415691,0.0019474347],"about_ca_topic_score_codex":0.000012317481,"about_ca_topic_score_gemma":0.0000057223738,"teacher_disagreement_score":0.9226908,"about_ca_system_score_codex":0.0000135853925,"about_ca_system_score_gemma":0.000008533533,"threshold_uncertainty_score":0.4022326},"labels":[],"label_agreement":null},{"id":"W2080216777","doi":"10.1117/12.843840","title":"Detection of architectural distortion in prior mammograms using fractal analysis and angular spread of power","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Fractal dimension; Spectral density; Fourier transform; Fourier analysis; Artificial intelligence; Fractal analysis; Distortion (music); Fractal; Mathematics; Pattern recognition (psychology); Computer science; Computer vision; Statistics; Telecommunications; Mathematical analysis","score_opus":0.006805911204208375,"score_gpt":0.22473683764503202,"score_spread":0.21793092644082365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080216777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930717,0.000044207864,0.0060431813,0.00019197488,0.0002354296,0.00029516604,0.000010778413,0.000035464713,0.00007213156],"genre_scores_gemma":[0.8816363,0.000009848954,0.1182343,0.000007390868,0.00006778017,0.00002221119,0.0000010636456,0.0000159672,0.0000051219445],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982312,3.2607886e-8,0.00063907966,0.0003442007,0.00055508397,0.00023040928],"domain_scores_gemma":[0.9983851,0.00008732007,0.0005490125,0.0000784838,0.0008333705,0.00006675195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055771216,0.00019684115,0.00038190972,0.00030629043,0.000043632754,0.00005432593,0.0006339848,0.00016412942,0.0000027226954],"category_scores_gemma":[0.00028778764,0.00017639517,0.00043393465,0.0008965653,0.00022688208,0.0006216807,0.0001761476,0.00032499837,6.8926454e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006225639,0.00007312869,0.004886505,0.00020304746,0.00031419046,5.0369653e-8,0.00040089185,0.00030266578,0.96740276,0.02209167,0.00000282261,0.0042600296],"study_design_scores_gemma":[0.0006627333,0.00034946398,0.048732568,0.00013897294,0.00022208877,0.000021846994,0.00031552845,0.20893498,0.7391709,0.0011521137,0.00004758152,0.00025119702],"about_ca_topic_score_codex":0.00010457845,"about_ca_topic_score_gemma":0.0000060993198,"teacher_disagreement_score":0.22823182,"about_ca_system_score_codex":0.000114474286,"about_ca_system_score_gemma":0.000023927409,"threshold_uncertainty_score":0.7193186},"labels":[],"label_agreement":null},{"id":"W2080572871","doi":"10.1109/icip.2010.5652047","title":"Mean shift based algorithm for mammographic breast mass detection","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mean-shift; Mammography; Pixel; Artificial intelligence; Computer science; Pattern recognition (psychology); Image segmentation; Feature extraction; Feature (linguistics); Computer vision; Segmentation; Algorithm; Breast cancer; Cancer","score_opus":0.006929554286713935,"score_gpt":0.22014083789489866,"score_spread":0.21321128360818473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080572871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001622206,0.000006511141,0.9942606,0.0006814037,0.0021252343,0.00027499362,0.0000063873513,0.0005117187,0.00051092665],"genre_scores_gemma":[0.5560033,6.936025e-7,0.44339594,0.00019809649,0.00022212861,0.00009072591,0.0000012396283,0.000012302112,0.00007562691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893343,0.000023149445,0.0001544577,0.00040739766,0.00021854774,0.00026302898],"domain_scores_gemma":[0.99914515,0.00007582786,0.0000657415,0.0005197593,0.0000980049,0.000095514704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032926645,0.00012719532,0.00009683597,0.00019385158,0.00017615155,0.00014880126,0.00047318364,0.00011156725,0.000043715525],"category_scores_gemma":[0.0000063327784,0.00011959454,0.0001072307,0.00047297892,0.000040845218,0.00041704124,0.000038917256,0.00019424547,0.000023133429],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005219825,0.00001715153,0.00008288287,0.0000059072368,0.0000069814605,6.73836e-7,0.000023836417,0.00000908546,0.010393807,0.0019495073,0.0000627704,0.9874422],"study_design_scores_gemma":[0.00053881225,0.00014178418,0.0026654329,0.000004030166,0.000008214588,0.00003099025,0.0000064525475,0.9005313,0.081110604,0.008499551,0.0062251063,0.00023774213],"about_ca_topic_score_codex":0.00010649512,"about_ca_topic_score_gemma":0.0008470836,"teacher_disagreement_score":0.98720443,"about_ca_system_score_codex":0.00003517707,"about_ca_system_score_gemma":0.00004818479,"threshold_uncertainty_score":0.48769236},"labels":[],"label_agreement":null},{"id":"W2080864511","doi":"10.1016/j.carj.2010.12.001","title":"Promoting High-quality Breast Imaging","year":2011,"lang":"en","type":"editorial","venue":"Canadian Association of Radiologists Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Medicine; Breast imaging; Medical physics; Quality (philosophy); Mammography; Radiology; Breast cancer; Internal medicine; Cancer","score_opus":0.011121380789180343,"score_gpt":0.25268086993349537,"score_spread":0.24155948914431502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080864511","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025749995,0.00030343691,0.017570157,0.0019515184,0.97785914,0.00018955769,0.00032485032,0.00009997602,0.0014438813],"genre_scores_gemma":[0.0664486,0.000350654,0.007448064,0.00020659356,0.9240499,0.000018114413,0.00009368539,0.000073467134,0.0013109238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960648,0.00073975715,0.0009662362,0.0004905006,0.0009815341,0.0007572173],"domain_scores_gemma":[0.9935438,0.00064272806,0.0032962793,0.0004951471,0.0014936914,0.00052835874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004890887,0.00030880215,0.0006315115,0.00055812614,0.000379572,0.00031260037,0.0016488236,0.0008394097,0.000053783446],"category_scores_gemma":[0.0033733787,0.0003248593,0.00023751816,0.00037502853,0.000075239754,0.0006388734,0.00008931456,0.0018731504,0.00002330492],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000490024,0.000009496805,0.0029098648,0.00002920921,0.0001121745,0.00003599358,0.00042046662,0.0000071389604,0.000016534297,0.000373646,0.9763368,0.01974377],"study_design_scores_gemma":[0.001363145,0.00016810365,0.028932221,0.00036157836,0.0001022418,0.00048084123,0.00004036888,0.0005533604,0.000105518426,0.010277632,0.9564751,0.0011398809],"about_ca_topic_score_codex":0.036519874,"about_ca_topic_score_gemma":0.026459252,"teacher_disagreement_score":0.0661911,"about_ca_system_score_codex":0.009451331,"about_ca_system_score_gemma":0.005019326,"threshold_uncertainty_score":0.99992037},"labels":[],"label_agreement":null},{"id":"W2083125248","doi":"10.1109/jbhi.2013.2277837","title":"Toward Automatic Mitotic Cell Detection and Segmentation in Multispectral Histopathological Images","year":2013,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Multispectral image; Computer science; Pattern recognition (psychology); Segmentation; Discriminative model; Linear discriminant analysis; Feature extraction; Computer vision; Image segmentation; Mitosis; Biology","score_opus":0.025795794804661702,"score_gpt":0.2816623811225924,"score_spread":0.2558665863179307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083125248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49096715,0.00028909082,0.50495374,0.0029406736,0.0006314696,0.00017358025,5.671051e-7,0.000021934573,0.000021820892],"genre_scores_gemma":[0.9002466,0.0005314918,0.098523006,0.0006007999,0.00008593693,0.0000049705163,2.0438083e-7,0.0000025717418,0.00000441556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849343,0.000055322314,0.00089209166,0.00006390507,0.0002962019,0.00019904497],"domain_scores_gemma":[0.999076,0.000060368122,0.0005172157,0.000066871406,0.000055451987,0.00022409046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007474718,0.000086218504,0.0002094367,0.00024587903,0.00007173878,0.00008068774,0.00013076552,0.000074175194,0.0000061738447],"category_scores_gemma":[0.000024886624,0.000064007465,0.000023980389,0.00018757,0.00009017118,0.0008230269,0.000033421034,0.00027553746,0.000005169998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007020381,0.00009348214,0.0006861166,0.0007110202,0.000004892995,0.00001295799,0.007243205,0.000023752365,0.0022211894,0.000018739769,0.0007797676,0.98819786],"study_design_scores_gemma":[0.004058212,0.004796734,0.18003461,0.00043512761,0.000017329685,0.0026642745,0.002214323,0.79435945,0.0058742426,0.0043999664,0.0007494596,0.00039629987],"about_ca_topic_score_codex":0.0000495802,"about_ca_topic_score_gemma":0.000004917242,"teacher_disagreement_score":0.98780155,"about_ca_system_score_codex":0.00019893814,"about_ca_system_score_gemma":0.00009801949,"threshold_uncertainty_score":0.26101488},"labels":[],"label_agreement":null},{"id":"W2083660024","doi":"10.2200/s00325ed1v01y201012bme039","title":"Modeling and Analysis of Shape with Applications in Computer-Aided Diagnosis of Breast Cancer","year":2011,"lang":"en","type":"article","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Research Services, University of Calgary; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Fondation pour la Recherche Médicale; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research; Universidade Federal de Uberlândia; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Artificial intelligence; Mammography; Segmentation; Observer (physics); Computer vision; Pattern recognition (psychology); Artifact (error); Shape analysis (program analysis); Noise (video); Active contour model; Breast cancer; Image segmentation; Image (mathematics); Cancer; Medicine","score_opus":0.011352059008089721,"score_gpt":0.21531299733282078,"score_spread":0.20396093832473106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083660024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22120203,0.00011355233,0.77844435,0.000069487534,0.000027011858,0.00008404356,0.000013583563,0.00003974446,0.0000061767873],"genre_scores_gemma":[0.96846163,0.000069915746,0.03128639,0.000015580115,0.000019225274,0.0001376778,8.5574493e-7,0.000008604819,1.2442024e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908924,0.000017381311,0.00024144186,0.00027254687,0.00023004027,0.00014936659],"domain_scores_gemma":[0.9993593,0.00021654849,0.0000625179,0.0002513576,0.000038546787,0.00007169336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012481882,0.00011935015,0.00029759228,0.00067743973,0.000018787005,0.000008331722,0.00027437895,0.00006801145,0.000020883546],"category_scores_gemma":[0.000019429153,0.00009477598,0.000051221992,0.0014818135,0.00005249046,0.00007387804,0.000055539538,0.00009696078,1.3109894e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044958724,0.00026050938,0.011882955,0.00021250243,0.00083083764,0.0000037094505,0.0012769214,0.68755144,0.0026148646,0.0012004138,0.000003297564,0.29411757],"study_design_scores_gemma":[0.000074778334,0.000044286786,0.03462435,0.000117101124,0.00008679119,0.000001703483,0.0000047351396,0.95876205,0.0061497246,0.000031151787,0.000005156303,0.000098150835],"about_ca_topic_score_codex":0.00040397042,"about_ca_topic_score_gemma":0.000047890953,"teacher_disagreement_score":0.7472596,"about_ca_system_score_codex":0.00004913768,"about_ca_system_score_gemma":0.000026280864,"threshold_uncertainty_score":0.38648525},"labels":[],"label_agreement":null},{"id":"W2085422756","doi":"10.1158/0008-5472.sabcs12-s4-6","title":"Abstract S4-6: An international Ki67 reproducibility study","year":2012,"lang":"en","type":"article","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ontario Institute for Cancer Research","funders":"","keywords":"Concordance; Intraclass correlation; Reproducibility; Medicine; Breast cancer; Concordance correlation coefficient; Cancer; Nuclear medicine; Pathology; Medical physics; Statistics; Mathematics; Internal medicine","score_opus":0.25524922145127793,"score_gpt":0.5060120228200258,"score_spread":0.25076280136874785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085422756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99080855,0.00021877862,0.0018616895,0.0010430455,0.0025441865,0.00048640018,0.000005199332,0.00015219649,0.0028799393],"genre_scores_gemma":[0.99730486,0.00003548588,0.0006845828,0.000050538187,0.0013997264,0.00024784057,0.000001438867,0.000012735781,0.00026276993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99678415,0.00027828253,0.00021534115,0.0010431806,0.0011269336,0.00055208185],"domain_scores_gemma":[0.99662524,0.0001051118,0.000050072245,0.002544039,0.00045554858,0.00021995463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007643544,0.00009673024,0.000104518236,0.00019088354,0.00022362596,0.00021113212,0.0015985472,0.00004972742,0.00036845604],"category_scores_gemma":[0.00038038017,0.00009130186,0.000031991087,0.0006377952,0.000091368434,0.0020902862,0.00054178224,0.0005088413,0.00015850962],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014876612,0.0021967676,0.49102485,0.000039725874,0.00010237613,0.00001710251,0.012491942,0.00018366084,0.024740685,0.0028456508,0.0059581785,0.4602503],"study_design_scores_gemma":[0.00042532635,0.00027961936,0.95086855,0.00001624091,0.0000026901996,0.0000060354955,0.0005280088,0.00061264733,0.022688312,0.001034195,0.023318065,0.00022029558],"about_ca_topic_score_codex":0.001164167,"about_ca_topic_score_gemma":0.0001666023,"teacher_disagreement_score":0.46003,"about_ca_system_score_codex":0.00071162876,"about_ca_system_score_gemma":0.00022079691,"threshold_uncertainty_score":0.40343353},"labels":[],"label_agreement":null},{"id":"W2085579853","doi":"10.1038/modpathol.2009.190","title":"Informatics for practicing anatomical pathologists: marking a new era in pathology practice","year":2010,"lang":"en","type":"review","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto; London Health Sciences Centre","funders":"","keywords":"Telepathology; Digital pathology; Informatics; Virtual microscopy; Computer science; Health informatics; Pathology; Data science; Medicine; Medical physics; Telemedicine; Health care; Engineering","score_opus":0.05521905502469059,"score_gpt":0.36946407163475903,"score_spread":0.31424501661006843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085579853","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011156231,0.44160903,0.5546328,0.0003958597,0.0014570077,0.0011159357,0.000013207428,0.00018924453,0.00057579164],"genre_scores_gemma":[0.000030004561,0.68237615,0.31571996,0.00076857465,0.00037686503,0.0005181116,0.00003230135,0.00008004111,0.0000980242],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946155,0.0009596879,0.0018604221,0.0011786036,0.00033161032,0.0010542],"domain_scores_gemma":[0.9929809,0.0028265836,0.0020419855,0.0017660835,0.00019797786,0.00018646373],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0029246416,0.00074225524,0.0021640083,0.0008680708,0.00017070872,0.00022426546,0.001878275,0.002006497,0.000006767799],"category_scores_gemma":[0.0032927871,0.00070634624,0.00041990817,0.0007050159,0.0001750169,0.001300511,0.0009218981,0.0031578618,0.0000702036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002118492,0.000067201385,0.0000030769315,0.0014184848,0.000020988584,0.0006709258,0.0014152493,0.000027297794,0.0000067691767,0.0021555456,0.00029087442,0.9939024],"study_design_scores_gemma":[0.00063127594,0.00028014876,0.000004519387,0.001016532,0.00022408532,0.011645353,0.000047673067,0.016886707,0.0000038050507,0.007028745,0.9615009,0.000730243],"about_ca_topic_score_codex":0.00002574643,"about_ca_topic_score_gemma":0.00010589016,"teacher_disagreement_score":0.99317217,"about_ca_system_score_codex":0.000617863,"about_ca_system_score_gemma":0.0014823494,"threshold_uncertainty_score":0.9995388},"labels":[],"label_agreement":null},{"id":"W2086944268","doi":"10.1109/embc.2013.6611041","title":"Measures of radial correlation and trend for classification of breast masses in mammograms","year":2013,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Linear discriminant analysis; Receiver operating characteristic; Radial basis function; Support vector machine; Correlation; Feature extraction; Computer science; Artificial neural network; Cross-validation; Logistic regression; Mammography; Feature selection; Mathematics; Machine learning; Breast cancer; Medicine","score_opus":0.03435364014891569,"score_gpt":0.2469157134681874,"score_spread":0.21256207331927168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086944268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14355236,0.00003913287,0.8549404,0.0003493154,0.00014285257,0.0002632336,0.0000021523883,0.000022072232,0.0006884608],"genre_scores_gemma":[0.98154515,0.0000072865364,0.018349921,0.0000058472224,0.000014928685,0.000035176938,0.0000014675685,0.0000024370192,0.00003776361],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995283,0.000020575655,0.00017023915,0.00012129061,0.000097388045,0.000062206534],"domain_scores_gemma":[0.9996287,0.00007005771,0.0000970915,0.00012460284,0.00006264058,0.000016913187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012690465,0.000040491173,0.000076932745,0.00009463284,0.000012833019,0.000017835868,0.000095352596,0.000037767742,0.000007977581],"category_scores_gemma":[0.0000140556995,0.0000362886,0.000016923941,0.0001782999,0.000032191605,0.00033472735,0.00001598945,0.000023696955,6.6333445e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020842968,0.000043583008,0.037008934,0.000035375746,0.000007063278,2.7045157e-8,0.0003748276,0.00015258243,0.026499333,0.012243809,0.00030866626,0.923305],"study_design_scores_gemma":[0.00045268284,0.000111347945,0.6614904,0.000016609378,0.000003888262,0.0000048558622,0.00007834694,0.32768798,0.005769506,0.0041525434,0.00016634622,0.00006551767],"about_ca_topic_score_codex":0.00030414175,"about_ca_topic_score_gemma":0.0002590558,"teacher_disagreement_score":0.9232394,"about_ca_system_score_codex":0.000023330063,"about_ca_system_score_gemma":0.00001727711,"threshold_uncertainty_score":0.1479806},"labels":[],"label_agreement":null},{"id":"W2087222240","doi":"10.1016/j.micron.2008.12.004","title":"Quantifying the architectural complexity of microscopic images of histology specimens","year":2008,"lang":"en","type":"article","venue":"Micron","topic":"AI in cancer detection","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Calgary","funders":"Alberta Cancer Foundation; Alberta Health Services","keywords":"Fractal dimension; Segmentation; Fractal; Fractal analysis; Pixel; Histology; Prostate; H&E stain; Pattern recognition (psychology); Mathematics; Pathology; Computer science; Artificial intelligence; Staining; Medicine; Cancer","score_opus":0.08797517386802385,"score_gpt":0.288525546263181,"score_spread":0.20055037239515716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087222240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91400933,0.00069053366,0.08365108,0.00070675684,0.00040338605,0.000102038284,0.00000433813,0.00003310094,0.00039945342],"genre_scores_gemma":[0.9729079,0.000015173965,0.026917757,0.000053719603,0.000029230527,0.0000020376324,6.2392985e-7,0.000004417803,0.00006912233],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928355,0.00007406025,0.00021011084,0.00017902677,0.000102347985,0.00015089074],"domain_scores_gemma":[0.9993004,0.00006657401,0.00015950236,0.00041055688,0.0000474228,0.000015496287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010470918,0.000077525714,0.00016194773,0.00005825925,0.00010456043,0.0000056631447,0.0005331748,0.000029739307,0.000014217373],"category_scores_gemma":[0.000010738989,0.00005901652,0.000057419948,0.00016061771,0.0006074148,0.00006179931,0.00015696103,0.00011160071,0.000007663823],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012203469,0.000024158824,0.0033086156,0.00003125657,0.0000118243115,0.000003148354,0.0016511275,0.00003880466,0.9879131,0.0010287788,0.00078142766,0.0051955543],"study_design_scores_gemma":[0.0002178239,0.00010993289,0.08836425,0.000016700133,0.0000046507726,0.00015144834,0.00002114014,0.00045256142,0.9082474,0.0006590078,0.0016717069,0.000083387305],"about_ca_topic_score_codex":0.00040646567,"about_ca_topic_score_gemma":0.000105881845,"teacher_disagreement_score":0.085055634,"about_ca_system_score_codex":0.000054406504,"about_ca_system_score_gemma":0.000040349645,"threshold_uncertainty_score":0.24066237},"labels":[],"label_agreement":null},{"id":"W2087320040","doi":"10.5858/arpa.2013-0466-oa","title":"Telepathology for Intraoperative Consultations and Expert Opinions: The Experience of the Eastern Québec Telepathology Network","year":2014,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cégep de Rimouski; Cegep de Sept Iles; Institut Universitaire en Santé Mentale de Québec; Centre hospitalier universitaire de Québec; Hôpital du Saint-Sacrement","funders":"","keywords":"Telepathology; Second opinion; Turnaround time; Concordance; Medicine; Medical diagnosis; Terminology; Expert opinion; Medical physics; Telemedicine; Pathology; Computer science; Health care; Intensive care medicine","score_opus":0.012270900088302797,"score_gpt":0.2763506336896046,"score_spread":0.2640797336013018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087320040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4249993,0.003154855,0.54389614,0.02436023,0.001999542,0.00094126025,0.000034223354,0.000069372734,0.0005451167],"genre_scores_gemma":[0.97944117,0.00020415941,0.017159605,0.0024952884,0.00036062562,0.00027153353,0.0000030515555,0.000013617638,0.000050981438],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9979227,0.0008137882,0.00046677052,0.0004014327,0.0001308203,0.00026448548],"domain_scores_gemma":[0.99623203,0.0024426526,0.00035830846,0.0007285625,0.00018420465,0.00005422455],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005839412,0.00016895708,0.00038013162,0.00007973539,0.00028369593,0.000005563937,0.00080784014,0.000082299295,0.000005490378],"category_scores_gemma":[0.0010931633,0.00009820336,0.00004549133,0.00035773835,0.0038558312,0.000108474385,0.000267397,0.00020173907,9.3503695e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033050752,0.0002232103,0.082379855,0.00017098614,0.00015580357,0.000029701518,0.38547742,0.00064377126,0.1607469,0.2162219,0.0041118306,0.14950812],"study_design_scores_gemma":[0.015708027,0.014159094,0.42788276,0.0014965968,0.00036902406,0.0019736148,0.034392893,0.10739429,0.08158785,0.09983286,0.2131208,0.0020821786],"about_ca_topic_score_codex":0.00019720674,"about_ca_topic_score_gemma":0.00061391684,"teacher_disagreement_score":0.55444187,"about_ca_system_score_codex":0.000014171068,"about_ca_system_score_gemma":0.00023504421,"threshold_uncertainty_score":0.9988551},"labels":[],"label_agreement":null},{"id":"W2087550369","doi":"10.1007/s11548-012-0793-3","title":"Measures of divergence of oriented patterns for the detection of architectural distortion in prior mammograms","year":2012,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Divergence (linguistics); Computer science; Distortion (music); Computer vision; Artificial intelligence; Telecommunications","score_opus":0.029951698229891625,"score_gpt":0.2648277068847739,"score_spread":0.23487600865488228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087550369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47572264,0.0004357713,0.52155054,0.00011282126,0.0021286947,0.000043683318,0.0000026669397,0.0000024808205,7.137951e-7],"genre_scores_gemma":[0.9965918,0.000117307536,0.003022852,0.000024955729,0.00023343725,0.000004184704,0.0000010854255,0.0000032846751,0.0000011034269],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987115,0.00016617794,0.0006557522,0.00009145144,0.00025971903,0.000115348616],"domain_scores_gemma":[0.99760264,0.0010417299,0.0008185414,0.00010743952,0.00039762974,0.000032040552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096969306,0.00007777627,0.0002681415,0.0003116732,0.000028024731,0.0000067675483,0.0003146704,0.00005915642,0.0000014129366],"category_scores_gemma":[0.00009879828,0.00005568323,0.00016207967,0.00014512904,0.00010904299,0.00023522029,0.00006158866,0.00012486315,4.0110123e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035860267,0.00009839011,0.38869864,0.000029975492,0.00022574651,0.0000025258773,0.0006546777,0.00075886067,0.004343433,0.00017925576,0.000018412864,0.6046315],"study_design_scores_gemma":[0.00038242943,0.00017175538,0.98048455,0.0001034535,0.000020405094,0.0004792234,0.000023128778,0.007458513,0.010445658,0.00016727435,0.00020183837,0.00006176481],"about_ca_topic_score_codex":0.000038389735,"about_ca_topic_score_gemma":0.000021363448,"teacher_disagreement_score":0.60456973,"about_ca_system_score_codex":0.00005458219,"about_ca_system_score_gemma":0.0000448458,"threshold_uncertainty_score":0.22706963},"labels":[],"label_agreement":null},{"id":"W2087770224","doi":"10.1117/12.911299","title":"Creating a semantic lesion database for computer-aided MR mammography","year":2012,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Mammography; CAD; Computer-aided diagnosis; DICOM; Breast imaging; Computer science; Lesion; Medicine; Radiology; Database; Malignancy; Breast cancer; Medical physics; Pathology; Cancer; Engineering drawing; Internal medicine","score_opus":0.0185050879889889,"score_gpt":0.24830311895526605,"score_spread":0.22979803096627716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087770224","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95700306,0.00015673353,0.0392557,0.0012892431,0.00078991463,0.00081185397,0.00003762772,0.00020070963,0.00045514017],"genre_scores_gemma":[0.34609935,0.000052263422,0.6523671,0.00013101783,0.000990095,0.00024939358,0.000008399667,0.000051393272,0.00005097035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740535,2.5086262e-8,0.0007109211,0.0005060594,0.0007608039,0.00061683706],"domain_scores_gemma":[0.9975145,0.00030345994,0.0005066046,0.000120907214,0.001366997,0.00018755467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001136954,0.0003463749,0.00041074827,0.00018049392,0.00018543476,0.0002080687,0.0015525013,0.00017216681,0.0000035900787],"category_scores_gemma":[0.00034597612,0.00030427412,0.0007124942,0.00057315413,0.00015032016,0.0017912122,0.0004267965,0.00028505534,0.0000015767146],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006683462,0.00017663479,0.00091166765,0.0008687678,0.00031972327,4.7770417e-8,0.00045028003,0.00011379122,0.47723433,0.51428616,0.0036787246,0.0018930632],"study_design_scores_gemma":[0.0025208634,0.0009562605,0.0025439346,0.0010986833,0.00028620914,0.000064076004,0.00084115734,0.585874,0.3943466,0.0033470355,0.0071223895,0.0009987922],"about_ca_topic_score_codex":0.000014160109,"about_ca_topic_score_gemma":1.4284494e-7,"teacher_disagreement_score":0.61311144,"about_ca_system_score_codex":0.00019022507,"about_ca_system_score_gemma":0.000033776694,"threshold_uncertainty_score":0.99994093},"labels":[],"label_agreement":null},{"id":"W2087911641","doi":"10.3923/itj.2003.178.190","title":"Morphological Analysis of Mammograms Using Visualization Pipelines","year":2003,"lang":"en","type":"article","venue":"Information Technology Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Visualization; Computer graphics (images); Artificial intelligence","score_opus":0.017021428038834947,"score_gpt":0.2838618961317006,"score_spread":0.26684046809286566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087911641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11364967,0.00004564705,0.8855148,0.0001332415,0.0002610346,0.000046830082,0.0000010637881,0.00012161801,0.00022607294],"genre_scores_gemma":[0.897125,0.00003712566,0.10271728,0.000098849436,0.0000111711015,0.000002508986,0.0000023810992,0.0000021964208,0.0000034616867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998935,0.000047414953,0.00055361935,0.00007818094,0.0002340317,0.00015174776],"domain_scores_gemma":[0.99877304,0.00001923183,0.0005693774,0.00023158081,0.00037354956,0.000033219763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000472806,0.00007986696,0.00017474299,0.0019080221,0.00013761267,0.00008131748,0.00037584102,0.00017675552,0.00003842016],"category_scores_gemma":[0.0002009823,0.00007069554,0.000087519715,0.0037906282,0.00007490485,0.0014908324,0.00005010597,0.00018974382,0.000007809699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002759878,0.0001614947,0.055875976,0.000031664837,0.0010467954,0.000022484177,0.0013618009,0.14505212,0.0067598135,0.40844822,0.00057264994,0.38063937],"study_design_scores_gemma":[0.00057597115,0.00020588633,0.002419013,0.000020268206,0.00018637683,0.0015823713,0.000478136,0.9308833,0.03275845,0.02192657,0.008703892,0.00025976638],"about_ca_topic_score_codex":0.0000030071672,"about_ca_topic_score_gemma":0.0000011820815,"teacher_disagreement_score":0.78583115,"about_ca_system_score_codex":0.00009471051,"about_ca_system_score_gemma":0.000063575666,"threshold_uncertainty_score":0.28828803},"labels":[],"label_agreement":null},{"id":"W2088588656","doi":"10.1118/1.2965967","title":"Sci‐Fri AM: YIS‐05: A new guidance device for lateral‐approach stereotactic breast biopsy","year":2008,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Robarts Clinical Trials; Western University","funders":"","keywords":"Imaging phantom; Elevation angle; Computer science; Biomedical engineering; Flexibility (engineering); Biopsy; Medicine; Radiology; Mathematics","score_opus":0.03814760128356216,"score_gpt":0.27487267728094705,"score_spread":0.2367250759973849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088588656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018663978,0.00012029138,0.9758279,0.002662057,0.001012756,0.00031073464,0.000006509567,0.00027966703,0.0011161243],"genre_scores_gemma":[0.9529824,0.000022924889,0.041655514,0.0021829025,0.002236007,0.00008361292,0.00000825124,0.00003876601,0.0007896163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977329,0.00005142199,0.00030624116,0.00059464853,0.0008516669,0.0004631336],"domain_scores_gemma":[0.9985743,0.00013035574,0.00013985006,0.0006605823,0.00011982661,0.0003750775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026183456,0.00021717855,0.00026904995,0.000039981198,0.00023532455,0.000072453695,0.0010709773,0.00012817844,0.00001859416],"category_scores_gemma":[0.000073602445,0.0001956734,0.00011780376,0.0006142495,0.00015542527,0.0006184252,0.00023102232,0.0002940294,0.00007374113],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027493254,0.0012067516,0.00416189,0.0005964559,0.0002883033,0.0002241914,0.0042344364,0.00036888337,0.0015211958,0.008260385,0.12838528,0.8504773],"study_design_scores_gemma":[0.012133626,0.0013371933,0.03453861,0.000956302,0.00018436137,0.008485882,0.000057892878,0.74164414,0.018578334,0.057894588,0.12015717,0.0040319073],"about_ca_topic_score_codex":0.00009669928,"about_ca_topic_score_gemma":0.0000056587546,"teacher_disagreement_score":0.9343184,"about_ca_system_score_codex":0.0001460307,"about_ca_system_score_gemma":0.00048226482,"threshold_uncertainty_score":0.797933},"labels":[],"label_agreement":null},{"id":"W2088887361","doi":"10.1007/s10278-014-9683-2","title":"Digitized Whole Slides for Breast Pathology Interpretation: Current Practices and Perceptions","year":2014,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"National Institutes of Health; National Cancer Institute; University of Washington","keywords":"Concordance; Medicine; Likert scale; Licensure; Medical education; Perception; Medical diagnosis; Family medicine; Scale (ratio); Descriptive statistics; Medical physics; Psychology; Pathology; Cartography; Geography; Statistics","score_opus":0.013603935767550718,"score_gpt":0.3041665004290453,"score_spread":0.2905625646614946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088887361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07291614,0.00026461168,0.92234445,0.003289601,0.0006631488,0.000059341997,0.000007288023,0.00003059122,0.00042484934],"genre_scores_gemma":[0.9889334,0.000016895445,0.010673277,0.00008821833,0.00025739797,0.0000036137224,7.608659e-7,0.000006509922,0.00001992465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992989,0.000030822062,0.00027285996,0.00014009206,0.00013465971,0.00012270833],"domain_scores_gemma":[0.9987139,0.00025355042,0.00060263014,0.00011339542,0.0002498206,0.00006669023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027872671,0.00007808121,0.00013282904,0.0001223735,0.00008043423,0.0007877918,0.0002204143,0.000013549978,0.0000014575871],"category_scores_gemma":[0.00032478248,0.00006764306,0.00006974104,0.00008520115,0.000054280456,0.004289795,0.00007975039,0.00012402942,0.0000034210427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024487012,0.00003265024,0.0029175824,0.000021047072,0.000010467312,0.0000032927496,0.0007044712,0.00002533511,0.0010408431,0.00051006186,0.00037980182,0.99433],"study_design_scores_gemma":[0.0065780384,0.0016783891,0.07588871,0.0011991059,0.00023162966,0.034623288,0.0023439485,0.5345593,0.0015836719,0.23130745,0.10864983,0.0013566021],"about_ca_topic_score_codex":3.5879603e-7,"about_ca_topic_score_gemma":4.5125128e-7,"teacher_disagreement_score":0.9929734,"about_ca_system_score_codex":0.000044065917,"about_ca_system_score_gemma":0.00004025106,"threshold_uncertainty_score":0.7596695},"labels":[],"label_agreement":null},{"id":"W2089459993","doi":"10.1109/titb.2012.2199595","title":"Automated Segmentation of the Melanocytes in Skin Histopathological Images","year":2013,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Image segmentation; Artificial intelligence; Segmentation; Computer science; Computer vision; Pattern recognition (psychology)","score_opus":0.02082102809643108,"score_gpt":0.2961571124579657,"score_spread":0.2753360843615346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089459993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7325897,0.0004751234,0.24700308,0.01782393,0.0016100154,0.00033800266,0.000003055228,0.00004722869,0.000109836605],"genre_scores_gemma":[0.94138265,0.00037056798,0.056907143,0.0012623492,0.00006467389,0.0000031491493,2.5353916e-7,0.0000019792558,0.0000072494613],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99856114,0.0000578184,0.0008932951,0.00003262184,0.00033031547,0.00012478181],"domain_scores_gemma":[0.99895775,0.000053122272,0.0007266689,0.00008683173,0.00008119065,0.00009444111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008471492,0.000053044565,0.00016773069,0.00012849571,0.000048015,0.00002543105,0.00025734826,0.00005136189,0.000005881378],"category_scores_gemma":[0.000032613527,0.000029585004,0.000029398583,0.00025660882,0.0001150124,0.00042998456,0.000048146758,0.00018298144,0.000002202971],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020608146,0.00024163087,0.0063434197,0.000853863,0.000020909694,0.0000068357517,0.016601255,0.00020285537,0.0022363816,0.0004132242,0.03602948,0.93702954],"study_design_scores_gemma":[0.0034431317,0.0030326964,0.5558959,0.0009129002,0.000014355554,0.0012851767,0.0018353971,0.40974632,0.012506164,0.0060532275,0.00496701,0.0003077175],"about_ca_topic_score_codex":0.000043267424,"about_ca_topic_score_gemma":0.0000026215753,"teacher_disagreement_score":0.9367218,"about_ca_system_score_codex":0.000110578636,"about_ca_system_score_gemma":0.0001642123,"threshold_uncertainty_score":0.120644145},"labels":[],"label_agreement":null},{"id":"W2092794669","doi":"10.1118/1.2244681","title":"Sci‐Fri PM Imaging‐06: Registered Digital Stereotactic Mammography and 3D‐Ultrasound for Breast Biopsy Guidance","year":2006,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"","keywords":"Mammography; Medicine; Ultrasound; Breast imaging; Medical imaging; Biopsy; Radiology; Digital mammography; Modalities; Breast biopsy; Magnetic resonance imaging; Nuclear medicine; Medical physics; Breast cancer","score_opus":0.010166903930392795,"score_gpt":0.24107319016816658,"score_spread":0.2309062862377738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092794669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020271797,0.00038064655,0.9747852,0.0018095543,0.0006457177,0.00028054003,0.00006069489,0.00026393333,0.0015018946],"genre_scores_gemma":[0.99308705,0.000008376127,0.005380424,0.00032953185,0.00093930407,0.00003941139,0.0000137194065,0.00002448124,0.00017771078],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805456,0.000024816527,0.00029695482,0.00058248785,0.0006427858,0.00039836904],"domain_scores_gemma":[0.998746,0.00024069399,0.0001617038,0.0005584028,0.00011095133,0.00018224443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022354526,0.0002082124,0.00021191276,0.000058582704,0.00017194913,0.0004236951,0.00058723235,0.00007035219,0.000005792545],"category_scores_gemma":[0.00007575317,0.00019553902,0.000100395446,0.00045609233,0.00034690087,0.0009384734,0.00016431246,0.00018416398,0.000014115488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007728198,0.0004923772,0.054020766,0.00031262016,0.000094487026,0.00007029364,0.00031031144,0.0000193388,0.0009090525,0.008277643,0.024226628,0.9111892],"study_design_scores_gemma":[0.011725078,0.0008345448,0.25824186,0.001374515,0.00022685294,0.0057600825,0.00009453124,0.10203018,0.0063258563,0.49141306,0.11739652,0.0045769317],"about_ca_topic_score_codex":0.000044003784,"about_ca_topic_score_gemma":0.0000070929013,"teacher_disagreement_score":0.9728152,"about_ca_system_score_codex":0.00006839517,"about_ca_system_score_gemma":0.0000894121,"threshold_uncertainty_score":0.797385},"labels":[],"label_agreement":null},{"id":"W2093230932","doi":"10.1007/s11548-007-0072-x","title":"Reduction of false positives in the detection of architectural distortion in mammograms by using a geometrically constrained phase portrait model","year":2007,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"False positive paradox; Distortion (music); Reduction (mathematics); Computer science; Artificial intelligence; True positive rate; Computer vision; Pattern recognition (psychology); Mathematics; Bandwidth (computing); Geometry","score_opus":0.022300395737548454,"score_gpt":0.2925099227800277,"score_spread":0.27020952704247925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093230932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50396144,0.00018580236,0.49528292,0.00012442518,0.00040314585,0.00003390103,0.0000017184257,0.0000027205729,0.0000039352835],"genre_scores_gemma":[0.9923941,0.00003571525,0.007416769,0.0000466296,0.00009949019,9.176603e-7,0.0000025908528,0.0000032020898,5.695022e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983775,0.00021356218,0.00085201964,0.00014017567,0.0002889701,0.00012775656],"domain_scores_gemma":[0.99838495,0.00056542654,0.0007082065,0.0000800434,0.00022918443,0.000032166237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001699999,0.00009108992,0.00027646337,0.0010563342,0.000024121968,0.000018990624,0.0002574026,0.0000861437,5.5234005e-7],"category_scores_gemma":[0.00006449447,0.00007334343,0.000115267445,0.0004658141,0.00016311448,0.00028278684,0.000027941358,0.0002440985,2.054328e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008077504,0.00037495984,0.0076101185,0.000013426473,0.00012748191,0.00011874259,0.0010461757,0.010453002,0.057821665,0.00017332463,0.000014703856,0.92143863],"study_design_scores_gemma":[0.0042720144,0.001236643,0.33312157,0.00040494374,0.000051902258,0.024324128,0.00024903554,0.6133007,0.01911214,0.0034809853,0.000051199244,0.00039479433],"about_ca_topic_score_codex":0.0000386881,"about_ca_topic_score_gemma":0.000013108597,"teacher_disagreement_score":0.9210439,"about_ca_system_score_codex":0.00012409546,"about_ca_system_score_gemma":0.00008565274,"threshold_uncertainty_score":0.29908583},"labels":[],"label_agreement":null},{"id":"W2095060692","doi":"10.1109/dese.2013.26","title":"A Bayesian Approach for the Classification of Mammographic Masses","year":2013,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Local binary patterns; Pattern recognition (psychology); Computer science; Mammography; Histogram; Feature extraction; Breast cancer; Noise (video); Image texture; Preprocessor; Image processing; Image (mathematics); Cancer; Medicine","score_opus":0.027924213090486295,"score_gpt":0.2439432976152418,"score_spread":0.21601908452475552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095060692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007233196,0.000046366968,0.9930712,0.0013985017,0.00010581524,0.00044866727,3.1969276e-7,0.00006993166,0.0041358876],"genre_scores_gemma":[0.7947726,0.0000073403617,0.20462832,0.00006985113,0.000027285107,0.0002995158,4.586092e-7,0.0000032908345,0.00019129612],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950033,0.000017917158,0.000115922136,0.00015757182,0.00011322003,0.000095061136],"domain_scores_gemma":[0.999306,0.00011101644,0.00006689258,0.00040889505,0.000088636974,0.0000185176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015123062,0.000047667017,0.000052395044,0.000052746305,0.00006737251,0.000060211987,0.00045641614,0.00002964421,0.000015670112],"category_scores_gemma":[0.000011566279,0.00002950962,0.000046665205,0.00031550566,0.00004026739,0.00026616966,0.000036911406,0.000035427653,0.000003847764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000903273,0.00012766897,0.004724042,0.00010773874,0.0000728496,3.8786716e-8,0.0005046994,0.0005427085,0.017723827,0.3457482,0.015068155,0.61537105],"study_design_scores_gemma":[0.000099209334,0.000050673993,0.022196788,0.0000020572693,0.000004999973,0.0000017680112,0.000118943695,0.9644687,0.003273306,0.008158819,0.0015651393,0.000059591937],"about_ca_topic_score_codex":0.00008796696,"about_ca_topic_score_gemma":0.000007974516,"teacher_disagreement_score":0.963926,"about_ca_system_score_codex":0.000012797746,"about_ca_system_score_gemma":0.000019133522,"threshold_uncertainty_score":0.120336734},"labels":[],"label_agreement":null},{"id":"W2095193333","doi":"10.1117/12.479680","title":"Use of CAD output to guide the intelligent display of digital mammograms","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Adaptive histogram equalization; CAD; Mammography; Context (archaeology); Digital mammography; DICOM; Contrast (vision); Computer vision; Artificial intelligence; Software; Histogram; Histogram equalization; Image (mathematics); Medicine; Breast cancer; Engineering drawing","score_opus":0.020974864707799006,"score_gpt":0.2426828694926995,"score_spread":0.2217080047849005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095193333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987234,0.00006106366,0.008558958,0.0018292047,0.00041467414,0.0005935026,0.000039596256,0.000059175974,0.0012098128],"genre_scores_gemma":[0.82263786,0.00006006096,0.17649953,0.00011501372,0.00014703095,0.000111460125,0.000001927943,0.0000452702,0.0003818333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973879,3.3090434e-8,0.000905514,0.00041095467,0.0009313528,0.00036424966],"domain_scores_gemma":[0.9970652,0.00025970765,0.0005195757,0.00014451549,0.0018863957,0.00012464315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006804676,0.00028302794,0.00039125246,0.000117695345,0.00006571991,0.00019388415,0.0017427512,0.00013516977,0.0000035244675],"category_scores_gemma":[0.0011610913,0.00020680243,0.00059677806,0.0006533913,0.0002529022,0.0009844076,0.00035201624,0.00025177578,0.0000014987569],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055612352,0.00015761361,0.00095172075,0.00031486453,0.0003893384,7.693169e-8,0.00077819236,0.001082006,0.14758703,0.84191537,0.0035338046,0.0032343555],"study_design_scores_gemma":[0.0008668517,0.001219524,0.0015228969,0.00069136993,0.00018679231,0.000049715054,0.0018895642,0.065845385,0.87112325,0.0059774686,0.049884733,0.0007424205],"about_ca_topic_score_codex":0.000026513306,"about_ca_topic_score_gemma":3.6273178e-7,"teacher_disagreement_score":0.8359379,"about_ca_system_score_codex":0.00020246475,"about_ca_system_score_gemma":0.00005669524,"threshold_uncertainty_score":0.84331584},"labels":[],"label_agreement":null},{"id":"W2096662216","doi":"10.1136/jcp.2009.068122","title":"Atlas of gross pathology with histologic correlation","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Atlas (anatomy); Gross examination; Gross anatomy; Pathology; Medicine; Anatomy","score_opus":0.04779942102592565,"score_gpt":0.36425880118048337,"score_spread":0.3164593801545577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096662216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4674739,0.00022796432,0.52789617,0.0019482115,0.0016544972,0.000055979133,4.5182802e-7,0.000019727087,0.000723101],"genre_scores_gemma":[0.94994456,0.00010755905,0.04892402,0.00070801337,0.00026520484,6.7861686e-7,2.7157833e-7,0.000004448629,0.000045232395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973853,0.0005148983,0.0014094206,0.00024347643,0.0002548789,0.00019198238],"domain_scores_gemma":[0.996639,0.00060853746,0.0019238951,0.00035344463,0.00038223094,0.00009289675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002057915,0.0001116727,0.0006353303,0.00014790517,0.000041235846,0.000010011577,0.0005758501,0.00028075266,0.000010900546],"category_scores_gemma":[0.00069607765,0.00008006195,0.00018801952,0.0002508568,0.00025460852,0.00029968188,0.000051796822,0.0006414081,0.000010639293],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021626558,0.0014443175,0.13993776,0.00003013721,0.000095325275,0.0060828654,0.0010233073,0.0044865157,0.0052779797,0.0275421,0.0039357613,0.80798125],"study_design_scores_gemma":[0.003804796,0.024824144,0.89358735,0.00007303685,0.00008242723,0.013908204,0.000033447308,0.0042689075,0.0008570272,0.05413071,0.0041370955,0.0002928724],"about_ca_topic_score_codex":9.4613426e-7,"about_ca_topic_score_gemma":0.0000034587856,"teacher_disagreement_score":0.8076884,"about_ca_system_score_codex":0.00004526424,"about_ca_system_score_gemma":0.00016984824,"threshold_uncertainty_score":0.32648316},"labels":[],"label_agreement":null},{"id":"W2100069600","doi":"10.1109/pacrim.1997.620388","title":"Texture feature extraction for tumor detection in mammographic images","year":2002,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; False positive paradox; Pattern recognition (psychology); Feature extraction; Computer science; Image texture; Feature (linguistics); Segmentation; Image segmentation; Computer vision; Texture (cosmology); Mammography; Fuzzy set; Fuzzy logic; Image (mathematics)","score_opus":0.012204469270901089,"score_gpt":0.24116663879965564,"score_spread":0.22896216952875453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100069600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007321589,0.00030415592,0.9862061,0.002409346,0.00095323194,0.0004045916,0.0000015263485,0.00035608595,0.0020433874],"genre_scores_gemma":[0.97457194,0.000033828568,0.023327233,0.0002482259,0.00016050224,0.00012794949,5.229594e-7,0.000011222337,0.0015185946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990869,0.000030457697,0.00013128847,0.00037323937,0.00015382412,0.00022424763],"domain_scores_gemma":[0.9994749,0.00006246032,0.00006961645,0.0002951279,0.000057369616,0.000040562754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015521902,0.0001169944,0.00009730952,0.0002707291,0.00010093962,0.000111065456,0.0002496364,0.000093228125,0.000036979087],"category_scores_gemma":[0.000027512495,0.00010913443,0.00007176425,0.0007387727,0.000027409533,0.00080802385,0.00003099484,0.00021255318,0.000022491564],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031785916,0.00011504058,0.001036217,0.000052383042,0.000013563001,0.000014067614,0.00023487113,0.00022779482,0.03727405,0.0015286311,0.013847065,0.94562453],"study_design_scores_gemma":[0.0018833728,0.0006627255,0.03554757,0.000059369915,0.000018165641,0.0004065238,0.00018307025,0.61602235,0.270913,0.009028545,0.06442645,0.0008488951],"about_ca_topic_score_codex":0.000049773498,"about_ca_topic_score_gemma":0.00061869685,"teacher_disagreement_score":0.96725035,"about_ca_system_score_codex":0.000105777115,"about_ca_system_score_gemma":0.0000066673856,"threshold_uncertainty_score":0.44503728},"labels":[],"label_agreement":null},{"id":"W2100420476","doi":"10.1093/biostatistics/kxr010","title":"Classifying tissue samples from measurements on cells with within-class tissue sample heterogeneity","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute","keywords":"Latent class model; Computer science; Macro; Replicate; Class (philosophy); Heuristic; Object (grammar); Focus (optics); Sample (material); Cluster analysis; Statistics; Mixture model; Artificial intelligence; Pattern recognition (psychology); Mathematics; Machine learning","score_opus":0.13299273575744242,"score_gpt":0.2858008119355312,"score_spread":0.15280807617808878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100420476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022340858,0.00004372763,0.9748521,0.00005192388,0.0012609586,0.0002822722,0.00034514518,0.00022112562,0.00060191465],"genre_scores_gemma":[0.52146643,0.000006102833,0.47813988,0.000218862,0.00008708599,0.000015557825,0.000016557437,0.000024640896,0.00002487042],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99791265,0.00011703238,0.0003217842,0.00065482414,0.0006293426,0.00036436322],"domain_scores_gemma":[0.99835145,0.00025464655,0.0002543472,0.00081508514,0.00015590555,0.00016853838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020342092,0.00027790602,0.00023795445,0.00009144655,0.00026025026,0.00018512431,0.0006756952,0.000104541956,0.00006653022],"category_scores_gemma":[0.0000854205,0.00024785023,0.000022767257,0.0002613049,0.00012614999,0.00022523453,0.00014084102,0.00018341842,0.00015771243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00104196,0.0015607848,0.040820822,0.00036026156,0.0010638591,0.0004471067,0.021708146,0.0020013675,0.31295663,0.05703414,0.01839606,0.54260886],"study_design_scores_gemma":[0.00059804064,0.0010429858,0.009889972,0.000086023094,0.000044102486,0.000008078038,0.000048684342,0.003524546,0.9707023,0.0050348747,0.008464078,0.0005563052],"about_ca_topic_score_codex":0.0020630253,"about_ca_topic_score_gemma":0.0013494601,"teacher_disagreement_score":0.65774566,"about_ca_system_score_codex":0.00020926846,"about_ca_system_score_gemma":0.00013166186,"threshold_uncertainty_score":0.9999974},"labels":[],"label_agreement":null},{"id":"W2101771332","doi":"10.1109/titb.2008.2009441","title":"Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances","year":2009,"lang":"en","type":"review","venue":"IEEE Transactions on Information Technology in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":622,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Mammography; Medicine; Cancer; CAD; Computer-aided diagnosis; Cancer detection; Computer science; Medical physics; Radiology; Internal medicine","score_opus":0.010718065496861382,"score_gpt":0.2711614395953258,"score_spread":0.2604433740984644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101771332","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014496661,0.3902933,0.6074388,0.0007218083,0.0005791595,0.0006392722,0.000049500984,0.0002515761,0.000012106838],"genre_scores_gemma":[0.0014722323,0.9931626,0.0045329225,0.00008199698,0.000031668256,0.0006981301,0.0000059418353,0.000012695727,0.0000018497956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980123,0.000052929827,0.00096308254,0.00036365964,0.00033547124,0.0002725594],"domain_scores_gemma":[0.99838483,0.00009518165,0.0007462088,0.0005241259,0.00018610744,0.00006353113],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020383492,0.00038738656,0.00095564313,0.004504142,0.000111412766,0.000029660907,0.0004839973,0.00050538813,0.000011391639],"category_scores_gemma":[0.0000027198596,0.00030471635,0.000090135436,0.004949855,0.00033021552,0.001137881,0.0000064803617,0.0006502802,0.000004747214],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002044337,0.00005548286,0.000005964392,0.0014665428,0.000059689686,0.0000016391408,0.00005716858,0.00014494633,0.0000011303584,0.00003771016,0.000011378545,0.9981379],"study_design_scores_gemma":[0.0026503513,0.003529567,0.0001820239,0.025383117,0.0005490342,0.0011291633,0.00011598255,0.0036745935,0.0016530592,0.0007355966,0.9592558,0.0011417046],"about_ca_topic_score_codex":0.000049007274,"about_ca_topic_score_gemma":0.00008660581,"teacher_disagreement_score":0.9969962,"about_ca_system_score_codex":0.000329531,"about_ca_system_score_gemma":0.00013178986,"threshold_uncertainty_score":0.9999405},"labels":[],"label_agreement":null},{"id":"W2102427741","doi":"10.1109/tmi.2003.823062","title":"Automatic Identification of the Pectoral Muscle in Mammograms","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pectoral muscle; Pixel; Artificial intelligence; Hough transform; Computer vision; Computer science; Edge detection; Image processing; Mammography; Pattern recognition (psychology); Mathematics; Anatomy; Breast cancer; Image (mathematics); Medicine","score_opus":0.009787980422182364,"score_gpt":0.25933936459090123,"score_spread":0.24955138416871886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102427741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08968316,0.000019646814,0.9047437,0.0039775968,0.0012953598,0.00012693938,8.3502636e-7,0.00010770082,0.000045114495],"genre_scores_gemma":[0.9976102,0.000007844272,0.0020609007,0.0002506068,0.000021629352,0.000029274228,9.9942255e-8,0.0000071038044,0.00001233621],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861735,0.00006732493,0.00033167333,0.00022121475,0.00059581274,0.0001665964],"domain_scores_gemma":[0.99932927,0.000057030673,0.0000862597,0.00041685955,0.00003287988,0.000077727804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037734187,0.000080317615,0.00009621738,0.00013123862,0.000097585784,0.00003962636,0.0005830351,0.000042006028,0.000053265445],"category_scores_gemma":[0.000029622188,0.00006499196,0.00007620491,0.00074636197,0.00012403328,0.00031127947,0.000003879217,0.00030441268,0.0000160211],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022969448,0.0002167747,0.00012023388,0.00003121932,0.0000066790153,0.0000077059485,0.00094303215,0.010671655,0.005340059,0.00035920355,0.000016664504,0.9822845],"study_design_scores_gemma":[0.0012852452,0.000038559276,0.018384792,0.0003903335,0.000018187282,0.00006146481,0.00016272979,0.8438486,0.12923901,0.0062054317,0.00013029581,0.00023538426],"about_ca_topic_score_codex":0.0002359911,"about_ca_topic_score_gemma":0.00016313721,"teacher_disagreement_score":0.9820491,"about_ca_system_score_codex":0.00019642623,"about_ca_system_score_gemma":0.0001690458,"threshold_uncertainty_score":0.26502952},"labels":[],"label_agreement":null},{"id":"W2102810967","doi":"10.1109/itab.2009.5394391","title":"A new method for the detection of microcalcifications in mammograms","year":2009,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Mammography; Contrast (vision); Segmentation; Computer vision; Pattern recognition (psychology); Fuzzy logic; Image segmentation; Microcalcification; Selection (genetic algorithm); Sign (mathematics); Breast cancer; Mathematics; Cancer; Medicine","score_opus":0.02474489804357008,"score_gpt":0.32465649315583733,"score_spread":0.2999115951122673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102810967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013440792,0.000106225656,0.9961806,0.0028164524,0.00013236003,0.00024135485,1.8962476e-7,0.00005099641,0.0003374331],"genre_scores_gemma":[0.41974074,0.000009016721,0.5798187,0.00016370811,0.000030094761,0.000021383401,9.397983e-8,0.0000017116521,0.00021449459],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995504,0.000021738924,0.00013318997,0.00013864566,0.00006745368,0.00008858488],"domain_scores_gemma":[0.9994596,0.0001582445,0.000048305792,0.00028039303,0.000035874124,0.000017563514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025252183,0.00004095237,0.00005421369,0.00006153596,0.000042775217,0.000024858868,0.00031082198,0.000029449242,0.0000027391013],"category_scores_gemma":[0.000019765761,0.000029349469,0.000039980467,0.00047878627,0.0000064118585,0.000120140496,0.000015359361,0.0000465254,0.0000019412153],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048721286,0.0000090916565,0.000007595646,0.0000011132878,0.000001917926,2.2033689e-8,0.00013393746,0.00014432317,0.03393609,0.009978069,0.00012800547,0.955655],"study_design_scores_gemma":[0.00047859745,0.00030785808,0.012443348,0.000008860014,0.000009104921,0.000010674166,0.00009120598,0.3884853,0.51310056,0.06422305,0.020716531,0.00012486006],"about_ca_topic_score_codex":0.00030013788,"about_ca_topic_score_gemma":0.00031195526,"teacher_disagreement_score":0.9555301,"about_ca_system_score_codex":0.000038568214,"about_ca_system_score_gemma":0.000032721447,"threshold_uncertainty_score":0.11968366},"labels":[],"label_agreement":null},{"id":"W2103754897","doi":"10.1007/978-3-319-07176-3_12","title":"Computer-Aided System for Automatic Classification of Suspicious Lesions in Breast Ultrasound Images","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Breast ultrasound; Ultrasound; Computer vision; Pattern recognition (psychology); Breast cancer; Fuzzy logic; Image segmentation; Computer-aided diagnosis; Radiology; Mammography; Cancer; Medicine","score_opus":0.017157810705378793,"score_gpt":0.24966478001952436,"score_spread":0.23250696931414555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103754897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007287165,0.00012401056,0.99459654,0.00045960103,0.002445914,0.0010088442,0.000022548807,0.00027416483,0.00033967476],"genre_scores_gemma":[0.6728586,0.000012428355,0.32645753,0.00013595224,0.0003973912,0.00004863248,0.000007824816,0.000039137663,0.00004252496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957348,0.00009512693,0.0010777591,0.0015651614,0.00089420134,0.0006329107],"domain_scores_gemma":[0.99527174,0.0016687404,0.00083040976,0.0016410958,0.0004538338,0.00013420389],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014710043,0.00054372725,0.00084476,0.0012996789,0.00022172013,0.00032963374,0.0028905729,0.00039646367,0.0000038138119],"category_scores_gemma":[0.00008150794,0.0005283399,0.00018756055,0.0008378211,0.0006224368,0.00046361503,0.0005187995,0.0005482732,0.0000127219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014152654,0.000055514716,0.00023741211,0.00077286415,0.0000204027,0.000013914216,0.0006562762,0.036959022,0.0042382875,0.02446283,0.00006619128,0.9325031],"study_design_scores_gemma":[0.0005857265,0.00029479223,0.0044301595,0.0017099797,0.000017206004,0.0002896637,9.744732e-7,0.9693387,0.0037605583,0.018843412,0.000091474314,0.00063736486],"about_ca_topic_score_codex":0.0000614654,"about_ca_topic_score_gemma":0.00012836233,"teacher_disagreement_score":0.93237966,"about_ca_system_score_codex":0.001054583,"about_ca_system_score_gemma":0.0005570474,"threshold_uncertainty_score":0.9997168},"labels":[],"label_agreement":null},{"id":"W2105757513","doi":"10.1117/12.480132","title":"Statistical properties of 4000 raw and processed digital mammograms from a GE Senograph 2000D","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Histogram; Thresholding; Artificial intelligence; Computer science; Pixel; Computer vision; Image processing; Pattern recognition (psychology); Image (mathematics)","score_opus":0.010900651138842492,"score_gpt":0.2066685143770759,"score_spread":0.1957678632382334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105757513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99386716,0.00028048435,0.0035527688,0.0006291455,0.00019429998,0.0004857421,0.00004971793,0.00010231564,0.00083833764],"genre_scores_gemma":[0.8355897,0.00008332191,0.16400039,0.000041666048,0.00010518946,0.00009962132,0.0000032479447,0.00003473937,0.00004214152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976579,3.0959093e-8,0.0006872005,0.000505712,0.00077503745,0.00037413265],"domain_scores_gemma":[0.9979845,0.00014207452,0.0003845667,0.000085210624,0.0012654061,0.00013822709],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004038461,0.0003060055,0.0004233793,0.00011065001,0.00008040246,0.00031955627,0.0009414663,0.00016699957,0.0000059261383],"category_scores_gemma":[0.0005729188,0.0002502926,0.0002946315,0.000471107,0.00041482327,0.0013726216,0.00019550289,0.00026939088,8.227776e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012663216,0.00022128383,0.0015027659,0.0008666427,0.0005038535,1.9584536e-7,0.00071108394,0.00005233592,0.41761148,0.57406676,0.00072904024,0.0036079264],"study_design_scores_gemma":[0.003024343,0.0012508134,0.0031676264,0.0011046497,0.00025604654,0.00006583088,0.0027893584,0.092401706,0.86863494,0.02160693,0.0045767473,0.0011210255],"about_ca_topic_score_codex":0.000021521262,"about_ca_topic_score_gemma":2.2898607e-7,"teacher_disagreement_score":0.55245984,"about_ca_system_score_codex":0.00009426365,"about_ca_system_score_gemma":0.000063227155,"threshold_uncertainty_score":0.99999493},"labels":[],"label_agreement":null},{"id":"W2106258330","doi":"10.1007/s10278-007-9102-z","title":"Classification of Breast Masses Using Selected Shape, Edge-sharpness, and Texture Features with Linear and Kernel-based Classifiers","year":2008,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Medical Research Council; University of Liverpool; University of Calgary","keywords":"Artificial intelligence; Pattern recognition (psychology); Kernel (algebra); Texture (cosmology); Computer science; Computer vision; Mathematics; Image (mathematics); Combinatorics","score_opus":0.018435561038894464,"score_gpt":0.2439265988185529,"score_spread":0.22549103777965843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106258330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77442133,0.0006384289,0.2238091,0.00075222156,0.00011348747,0.00007422671,0.0000067835613,0.00003224794,0.00015217984],"genre_scores_gemma":[0.9838633,0.00002048454,0.015955823,0.000041708045,0.00009324687,5.07445e-7,0.0000010050697,0.000012536935,0.000011385672],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99908257,0.000022879392,0.0002681092,0.00018518785,0.00029443877,0.00014683309],"domain_scores_gemma":[0.99877226,0.000066094086,0.0004600858,0.00013174652,0.00047864023,0.000091176604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009324304,0.00013023062,0.00019626062,0.00019914942,0.00010961902,0.00020979175,0.00018701251,0.00003889279,0.0000010369541],"category_scores_gemma":[0.00004218628,0.00010290516,0.000033634507,0.00046351276,0.00018752736,0.0019496911,0.00004273942,0.00022234445,1.606972e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038529022,0.00020688657,0.7823498,0.00021222436,0.00015529268,0.00020696038,0.0010852745,0.0014849383,0.068237625,0.00013583845,0.00071353064,0.14482634],"study_design_scores_gemma":[0.00133449,0.00022816278,0.5990909,0.00039371406,0.000049205923,0.010922088,0.0001909188,0.38163087,0.0054125143,0.00018059861,0.0002607525,0.0003058092],"about_ca_topic_score_codex":0.000004450305,"about_ca_topic_score_gemma":0.0000012557011,"teacher_disagreement_score":0.38014594,"about_ca_system_score_codex":0.00006988194,"about_ca_system_score_gemma":0.00025275763,"threshold_uncertainty_score":0.41963506},"labels":[],"label_agreement":null},{"id":"W2106683649","doi":"10.1186/1746-1596-8-s1-s44","title":"Webconference mixed with virtual slides as a pedagogical tool to improve pathology practice in the French Midi-Pyrenees area","year":2013,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Université de Toulouse","keywords":"Telepathology; Digital pathology; Informatics; Medicine; Pathology; Population; Medical education; Telemedicine; Health care; Political science","score_opus":0.026333478175551643,"score_gpt":0.28783461098654367,"score_spread":0.261501132810992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106683649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82662046,0.0001340136,0.16079833,0.008969273,0.0007756438,0.0009320572,0.0000067491815,0.00010871256,0.001654766],"genre_scores_gemma":[0.97724324,0.00007104724,0.015431874,0.005405589,0.00012678743,0.0016022197,0.0000042972338,0.000016590515,0.0000983553],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99676794,0.00079243974,0.00042378344,0.00096693716,0.0003728391,0.0006760617],"domain_scores_gemma":[0.99001706,0.008342541,0.00020014527,0.001064679,0.0002512926,0.00012427327],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00077022606,0.00031577694,0.00036851928,0.00019972301,0.00014158487,0.00020510997,0.0013645598,0.0002325211,0.000091313916],"category_scores_gemma":[0.009824707,0.00021641831,0.000052218926,0.0006124122,0.0002273024,0.00068258983,0.0004007086,0.00053280074,0.000690981],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019263264,0.0019585814,0.023087569,0.000054369277,0.00009572918,0.013200626,0.060974922,0.0015047842,0.020962277,0.09313036,0.0104436865,0.77439445],"study_design_scores_gemma":[0.004313018,0.0238293,0.8701269,0.00024876214,0.0001613586,0.016771888,0.0100192195,0.005776261,0.008974374,0.038671877,0.018449068,0.0026579655],"about_ca_topic_score_codex":0.0005658542,"about_ca_topic_score_gemma":0.00047840312,"teacher_disagreement_score":0.84703934,"about_ca_system_score_codex":0.00008620029,"about_ca_system_score_gemma":0.00023944059,"threshold_uncertainty_score":0.99851596},"labels":[],"label_agreement":null},{"id":"W2106829632","doi":"10.1109/cccrv.2004.1301473","title":"Segmentation of the breast region in mammograms using snakes","year":2004,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Cancer Institute","keywords":"Breast tissue; Segmentation; Computer science; Artificial intelligence; Breast cancer; Mammography; Image segmentation; Right breast; Computer vision; Pattern recognition (psychology); Medicine; Cancer; Internal medicine","score_opus":0.021295586348274356,"score_gpt":0.24633233798707108,"score_spread":0.22503675163879672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106829632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36001402,0.000008827734,0.6387647,0.0006050792,0.00019394283,0.00008131439,9.924651e-8,0.000023825447,0.00030823215],"genre_scores_gemma":[0.9780853,0.0000020003552,0.021806631,0.00006726005,0.000014492447,0.0000022597676,7.25636e-8,0.000002077636,0.000019929903],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995872,0.000020168873,0.000099320314,0.00010431121,0.00011935538,0.00006964829],"domain_scores_gemma":[0.99971366,0.0000066667862,0.000055169254,0.00019449764,0.000020756095,0.000009278337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006594978,0.000035799974,0.000038143346,0.0000393702,0.000029100453,0.000018891446,0.00020381527,0.000019982355,0.0000016073582],"category_scores_gemma":[0.0000022326815,0.000025399006,0.000021121336,0.00040710834,0.00002300537,0.00025283315,0.00005253779,0.000037794205,0.0000010649982],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003486477,0.00025528294,0.0989107,0.0000715549,0.000022166709,0.000010438492,0.005827675,0.13428348,0.10296565,0.06055204,0.00010099326,0.59696513],"study_design_scores_gemma":[0.0024136375,0.00017765869,0.23774716,0.0003528494,0.000013675184,0.00079644914,0.00082256016,0.12252219,0.5815107,0.05305328,0.00013525761,0.00045457907],"about_ca_topic_score_codex":0.00082001404,"about_ca_topic_score_gemma":0.0002847143,"teacher_disagreement_score":0.61807126,"about_ca_system_score_codex":0.00014322497,"about_ca_system_score_gemma":0.000036534017,"threshold_uncertainty_score":0.12396214},"labels":[],"label_agreement":null},{"id":"W2110243528","doi":"10.1126/scitranslmed.3002564","title":"Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival","year":2011,"lang":"en","type":"article","venue":"Science Translational Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":793,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stromal cell; Breast cancer; Morphology (biology); Medicine; Oncology; Survival analysis; Cancer; Internal medicine; Biology; Cancer research; Pathology; Genetics","score_opus":0.024676629868706987,"score_gpt":0.2696336819160569,"score_spread":0.2449570520473499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110243528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59024996,0.00043476463,0.39918727,0.0033765244,0.0018777623,0.000689681,0.000110557055,0.0001943242,0.003879128],"genre_scores_gemma":[0.99783385,0.000005334833,0.0020023775,0.000072711104,0.000029152627,0.00001835474,0.0000039936426,0.000004400393,0.0000298316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976579,0.00009322824,0.00033964653,0.0004032369,0.0012523248,0.0002536656],"domain_scores_gemma":[0.99862504,0.00023891914,0.0002780797,0.00032359458,0.00043338092,0.00010096755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011721902,0.00012964936,0.00042689333,0.00067967357,0.0001302379,0.000012600327,0.00074536604,0.000038355956,0.00014216828],"category_scores_gemma":[0.00008449126,0.00008769973,0.000058259393,0.0051102494,0.00094533386,0.00051725795,0.000022993569,0.000108277694,9.831809e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069025153,0.0006572204,0.6710525,0.0018829459,0.0075063733,0.00008580521,0.042029396,0.044941194,0.053684086,0.17236923,0.00019059745,0.004910371],"study_design_scores_gemma":[0.00051572156,0.00018215108,0.980012,0.0005770918,0.0005614415,0.00001850996,0.00016920792,0.016613318,0.0006326369,0.0005919271,3.3783294e-7,0.00012568508],"about_ca_topic_score_codex":0.0008930506,"about_ca_topic_score_gemma":0.00084290735,"teacher_disagreement_score":0.40758386,"about_ca_system_score_codex":0.00011700992,"about_ca_system_score_gemma":0.0003507848,"threshold_uncertainty_score":0.35762912},"labels":[],"label_agreement":null},{"id":"W2110411550","doi":"10.1109/tip.2010.2048612","title":"Prostate Cancer Localization With Multispectral MRI Using Cost-Sensitive Support Vector Machines and Conditional Random Fields","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"AI in cancer detection","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"","keywords":"Multispectral image; Support vector machine; Prostate cancer; Conditional random field; Magnetic resonance imaging; Computer science; Artificial intelligence; Cancer; Image segmentation; Segmentation; Pattern recognition (psychology); Medicine; Radiology; Internal medicine","score_opus":0.009423474598115971,"score_gpt":0.2717700372076734,"score_spread":0.2623465626095574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110411550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02802287,0.000021411122,0.9703139,0.00047936084,0.0004924642,0.0004039016,0.000033888668,0.00017610169,0.00005606976],"genre_scores_gemma":[0.9518573,0.000020530952,0.047616456,0.000227107,0.000088148896,0.00009585996,0.0000037369107,0.000023283044,0.00006754645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988106,0.000037988644,0.00019680845,0.0004386295,0.00026523764,0.00025074428],"domain_scores_gemma":[0.9993126,0.000058313715,0.0001222832,0.00016112208,0.00025309034,0.000092609356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012476646,0.00019554437,0.0001659123,0.00014827804,0.00055802305,0.00030704754,0.000118955424,0.00008642806,0.000040527964],"category_scores_gemma":[0.000004277656,0.00017515,0.000035049456,0.00034368836,0.00019071932,0.0013304774,0.0000026308846,0.00041180587,0.0000028987895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013438453,0.00036962642,0.0006250939,0.00039950074,0.00016481931,0.000112652706,0.008343499,0.17728911,0.23120841,0.000120736615,0.00011218672,0.5799105],"study_design_scores_gemma":[0.0015561143,0.00010252701,0.00031367294,0.00007399332,0.000040569692,0.00020349101,0.00003994923,0.8224414,0.17474745,0.00016806342,0.000057932193,0.00025481687],"about_ca_topic_score_codex":0.0001769275,"about_ca_topic_score_gemma":0.0006202455,"teacher_disagreement_score":0.92383444,"about_ca_system_score_codex":0.00008427258,"about_ca_system_score_gemma":0.00025193897,"threshold_uncertainty_score":0.71424097},"labels":[],"label_agreement":null},{"id":"W2111545417","doi":"10.2478/v10006-008-0007-x","title":"Classification of Breast Cancer Malignancy Using Cytological Images of Fine Needle Aspiration Biopsies","year":2008,"lang":"en","type":"article","venue":"International Journal of Applied Mathematics and Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Uniwersytet Wrocławski","keywords":"Malignancy; Grading (engineering); Fine-needle aspiration; Medicine; Breast cancer; Biopsy; Radiology; Cancer; Support vector machine; Pathology; Internal medicine; Artificial intelligence; Computer science; Biology","score_opus":0.0395623605580739,"score_gpt":0.28502357803058437,"score_spread":0.24546121747251048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111545417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3956463,0.000038064743,0.6036741,0.00015155446,0.0003582653,0.000041588195,0.0000038361563,0.000005943264,0.000080339494],"genre_scores_gemma":[0.7046137,0.000043317734,0.29521656,0.00001997009,0.00010171997,0.0000012898971,1.2484202e-7,0.0000023784683,9.4239584e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850035,0.000006645681,0.00053705816,0.00016093906,0.0006946064,0.00010041678],"domain_scores_gemma":[0.99802446,0.000058921985,0.00086609815,0.00015112752,0.00085302035,0.00004633883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039634603,0.00008782539,0.00019869153,0.00028171897,0.000074656156,0.000059877162,0.00083814963,0.00003228899,0.0000046116666],"category_scores_gemma":[0.000011539311,0.00007043647,0.00004564513,0.00035966892,0.0003623292,0.00051956944,0.00020455067,0.00007680139,3.5102786e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006580757,0.00044084186,0.001615031,0.00009836889,0.000093320465,0.000017809687,0.003413583,0.0092536025,0.6966303,0.12088962,0.00009269755,0.16738904],"study_design_scores_gemma":[0.0005804463,0.00021845441,0.049400765,0.00025331875,0.00001807559,0.001372556,0.00007944796,0.811184,0.12434608,0.012345238,0.000018858249,0.00018279206],"about_ca_topic_score_codex":0.000008635856,"about_ca_topic_score_gemma":6.098073e-7,"teacher_disagreement_score":0.80193037,"about_ca_system_score_codex":0.00006850165,"about_ca_system_score_gemma":0.00019628141,"threshold_uncertainty_score":0.2872316},"labels":[],"label_agreement":null},{"id":"W2112241148","doi":"10.1109/iembs.2006.260441","title":"Spiculation-preserving Polygonal Modeling of Contours of Breast Tumors","year":2006,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Receiver operating characteristic; Mammography; Computer science; Artificial intelligence; Measure (data warehouse); Set (abstract data type); Pattern recognition (psychology); Computer vision; Medicine; Data mining; Breast cancer; Machine learning; Cancer","score_opus":0.00972263884541802,"score_gpt":0.21787442722607436,"score_spread":0.20815178838065634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112241148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23430218,0.00003186527,0.75944316,0.00016568822,0.00008382552,0.000045594956,0.0000014410361,0.00004281839,0.0058834273],"genre_scores_gemma":[0.97042435,4.3328458e-7,0.02940904,0.000013551964,0.000053705007,0.0000019017378,6.944927e-7,0.000003732628,0.00009260833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923825,0.000016216594,0.00025382498,0.00014727963,0.00023832891,0.00010609966],"domain_scores_gemma":[0.99945474,0.000026621263,0.00010649931,0.0002588629,0.0001336289,0.000019646319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012437075,0.0000577912,0.00010558065,0.000078049925,0.00002765155,0.000014492549,0.00032780188,0.000026150079,0.000030322444],"category_scores_gemma":[0.000005830666,0.000054737335,0.00004573182,0.00022004386,0.000019459852,0.00032568525,0.00010574645,0.000038709528,0.0000015039622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014371988,0.00006017657,0.012884901,0.00004251357,0.000014474166,0.0000013899612,0.00013400706,0.8763146,0.020691376,0.0831028,0.00023936697,0.006500016],"study_design_scores_gemma":[0.00012858174,0.000016467166,0.013922428,0.000024359562,0.0000020837365,0.000011553536,0.000017089127,0.96956336,0.009315499,0.006937244,0.0000038775465,0.000057479512],"about_ca_topic_score_codex":0.0031932122,"about_ca_topic_score_gemma":0.00012551936,"teacher_disagreement_score":0.73612213,"about_ca_system_score_codex":0.000031357646,"about_ca_system_score_gemma":0.000045134337,"threshold_uncertainty_score":0.4827203},"labels":[],"label_agreement":null},{"id":"W2112257301","doi":"10.5566/ias.v20.p169-174","title":"WAVELET-BASED MULTIFRACTAL FORMALISM TO ASSIST IN DIAGNOSIS IN DIGITIZED MAMMOGRAMS","year":2011,"lang":"en","type":"article","venue":"Image Analysis & Stereology","topic":"AI in cancer detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Occupational Cancer Research Centre","funders":"Institut Bergonié","keywords":"Multifractal system; Hurst exponent; Scaling; Wavelet; Wavelet transform; Exponent; Gravitational singularity; Mathematics; Statistical physics; Artificial intelligence; Fractal; Computer science; Mathematical analysis; Physics; Statistics; Geometry","score_opus":0.023616255894161872,"score_gpt":0.26280341246386557,"score_spread":0.23918715656970368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112257301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.576325,0.000023348402,0.4213161,0.0008243887,0.00015109009,0.00020896754,0.0000043099794,0.00010215094,0.0010446637],"genre_scores_gemma":[0.9353242,0.0000065646973,0.06333186,0.0009778526,0.000024513209,0.00027225105,0.000009663399,0.000012275365,0.00004084661],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99768835,0.00023404074,0.00058594294,0.00070303073,0.0002242516,0.00056438695],"domain_scores_gemma":[0.9985961,0.0001915319,0.00016784944,0.0008224673,0.000092733266,0.00012933541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045762205,0.00022402924,0.0005354119,0.0015571107,0.00004802394,0.00009393659,0.00087031536,0.00013485436,0.0001621877],"category_scores_gemma":[0.00009859882,0.00022603887,0.00023378427,0.003224739,0.00009235305,0.0006876765,0.00028748665,0.00023516694,0.000095035444],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013704177,0.0004652241,0.6488024,0.000015462383,0.00023400788,0.00051137916,0.0027126514,0.00016295593,0.00040327688,0.00036684854,0.00014911646,0.34603962],"study_design_scores_gemma":[0.0019448779,0.0002887688,0.8527875,0.000026134205,0.00016966395,0.000012230489,0.00010735519,0.13216276,0.009500646,0.0014562743,0.00091360015,0.00063017994],"about_ca_topic_score_codex":0.0042430954,"about_ca_topic_score_gemma":0.0193307,"teacher_disagreement_score":0.3589992,"about_ca_system_score_codex":0.00022148307,"about_ca_system_score_gemma":0.000051454736,"threshold_uncertainty_score":0.99856395},"labels":[],"label_agreement":null},{"id":"W2112417225","doi":"10.4103/2228-7477.161486","title":"Detection and classification of breast cancer in wavelet sub-bands of fractal segmented cancerous zones","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Signals & Sensors","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wavelet; Fractal; Fractal dimension; Pattern recognition (psychology); Artificial intelligence; Fractal analysis; Wavelet transform; Box counting; Mathematics; Computer science; Fractal transform; Fractal compression; Image processing; Image (mathematics); Algorithm; Computer vision; Mathematical analysis","score_opus":0.023966227367446295,"score_gpt":0.2871758487392604,"score_spread":0.2632096213718141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112417225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94175535,0.000626339,0.0546572,0.002310732,0.0005392415,0.000077482255,0.000005620099,0.000009306839,0.000018697752],"genre_scores_gemma":[0.9986684,0.0006080716,0.00045264207,0.000048338894,0.00020809069,0.0000022769436,1.8398143e-7,0.000007488092,0.0000045163524],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973672,0.0001909553,0.000765245,0.00016349975,0.0013471209,0.00016599876],"domain_scores_gemma":[0.9981746,0.00015289124,0.00084227644,0.00013443676,0.00045589983,0.00023986364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014907705,0.000110517314,0.0003483526,0.0002589101,0.00002234602,0.000017526221,0.00030871088,0.00015880546,0.000030579093],"category_scores_gemma":[0.00019705915,0.0000901684,0.00005955784,0.00049337704,0.00012412919,0.00034817422,0.000051798103,0.00034316874,6.262861e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070909923,0.00032055288,0.011768224,0.00014205469,0.00013630862,0.00007343322,0.0029245394,0.002653072,0.23215432,0.000078157944,0.0005261882,0.74851406],"study_design_scores_gemma":[0.0065601817,0.0018572137,0.40137047,0.0015696115,0.000100120014,0.0019994513,0.0012951418,0.30996433,0.2731882,0.0011877832,0.00043573388,0.0004717488],"about_ca_topic_score_codex":0.00058619934,"about_ca_topic_score_gemma":0.0003777217,"teacher_disagreement_score":0.7480423,"about_ca_system_score_codex":0.0002613708,"about_ca_system_score_gemma":0.0004251772,"threshold_uncertainty_score":0.36769608},"labels":[],"label_agreement":null},{"id":"W2115121886","doi":"10.1186/1746-1596-3-s1-s13","title":"Web conferencing systems: Skype and MSN in telepathology","year":2008,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cytodiagnostics (Canada)","funders":"","keywords":"Telepathology; The Internet; Computer science; Digital pathology; Multimedia; Transmission (telecommunications); Image file formats; Web application; World Wide Web; Telecommunications; Telemedicine; Artificial intelligence; Image (mathematics)","score_opus":0.019642488562338765,"score_gpt":0.23157722409915016,"score_spread":0.21193473553681139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115121886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94487315,0.0013779779,0.050817385,0.00029831886,0.0012094027,0.00021405125,0.0000035112535,0.00014524431,0.0010609839],"genre_scores_gemma":[0.99630964,0.00074407354,0.00246877,0.00027041073,0.00006286256,0.00009996045,0.0000014772604,0.0000099028275,0.000032888736],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984912,0.00025739358,0.00028422454,0.00049907184,0.00011164764,0.0003564592],"domain_scores_gemma":[0.998255,0.0011379372,0.00009167994,0.0003917682,0.000053088697,0.00007053414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032232376,0.00014461215,0.00028868488,0.00023785279,0.000094009105,0.000022547172,0.00032241287,0.00016838715,0.000004835495],"category_scores_gemma":[0.0008535991,0.00014819871,0.000021324779,0.00027984622,0.00018781179,0.00018755878,0.00020825239,0.00022816737,0.000055986133],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019291114,0.0001721594,0.88044757,0.00009571984,0.000016568049,0.017549524,0.0058571417,0.0007063502,0.0058861924,0.05343999,0.0011242701,0.03468523],"study_design_scores_gemma":[0.0018561243,0.00063721545,0.93561476,0.000110312234,0.0000128369675,0.018519558,0.00021684267,0.03504651,0.00081207947,0.0044982717,0.0020869863,0.0005885012],"about_ca_topic_score_codex":0.00009566038,"about_ca_topic_score_gemma":0.000098805605,"teacher_disagreement_score":0.0551672,"about_ca_system_score_codex":0.00008027209,"about_ca_system_score_gemma":0.00013009364,"threshold_uncertainty_score":0.60433686},"labels":[],"label_agreement":null},{"id":"W2115279400","doi":"10.1109/iciap.2003.1234061","title":"Computer aided detection of clustered microcalcifications in digitized mammograms using Gabor functions","year":2004,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Gabor filter; Computer vision; Gabor transform; Artificial neural network; Set (abstract data type); Feature extraction; Test set; Time–frequency analysis; Filter (signal processing)","score_opus":0.02410275617909282,"score_gpt":0.2545100079995015,"score_spread":0.2304072518204087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115279400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20739572,0.000018451221,0.79133254,0.00018019379,0.00046696907,0.00021061701,0.0000017139635,0.0001901679,0.00020360414],"genre_scores_gemma":[0.8770453,0.000004210694,0.12273668,0.00007975404,0.00005613147,0.000021300946,0.0000018879155,0.000009057,0.000045686753],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988229,0.000042812968,0.00039160534,0.00035331506,0.00017421888,0.00021513287],"domain_scores_gemma":[0.9991863,0.000045871137,0.00013253736,0.00046167825,0.00011987296,0.000053765223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014290297,0.00012001415,0.00016081461,0.0003003686,0.000103632716,0.00008079701,0.00030854216,0.000083257466,0.000006497653],"category_scores_gemma":[0.00001109528,0.00012286966,0.00007522922,0.0011608622,0.00005832439,0.00055157335,0.0001052719,0.00012661444,0.000018335579],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010195539,0.0006681068,0.0014907725,0.000077574136,0.0000751001,0.000008539155,0.0015278124,0.14099377,0.58993334,0.007567552,0.00006796586,0.25748754],"study_design_scores_gemma":[0.0050688544,0.0004939612,0.027114414,0.0001726514,0.00003191118,0.0001587811,0.00026880114,0.5721169,0.3814081,0.011177924,0.0012407561,0.0007469751],"about_ca_topic_score_codex":0.0006120524,"about_ca_topic_score_gemma":0.0005442755,"teacher_disagreement_score":0.6696496,"about_ca_system_score_codex":0.00032325226,"about_ca_system_score_gemma":0.00009602528,"threshold_uncertainty_score":0.50104797},"labels":[],"label_agreement":null},{"id":"W2117383078","doi":"10.5858/133.9.1362.b","title":"Coronal serial sequential sampling of breast specimen in the assessment of the extent of ductal carcinoma in situ.","year":2009,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Ductal carcinoma; In situ; Carcinoma in situ; Coronal plane; Sampling (signal processing); Carcinoma; Medicine; Pathology; Radiology; Breast cancer; Internal medicine; Chemistry; Cancer; Optics; Physics","score_opus":0.03455650883291844,"score_gpt":0.26503528224220785,"score_spread":0.2304787734092894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117383078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935467,0.000021865128,0.0043823677,0.0005497878,0.00046274427,0.00044308903,0.0000057200123,0.000005126066,0.00058259675],"genre_scores_gemma":[0.9989716,0.0000021981832,0.0008400225,0.000030789743,0.00009808203,0.000051934967,5.390837e-7,0.0000024967758,0.0000023695673],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988102,0.00012686808,0.00032086394,0.00016847903,0.00038878561,0.00018483648],"domain_scores_gemma":[0.9993653,0.000045854784,0.00019391747,0.00033659794,0.000040375806,0.00001795362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006543666,0.000071189104,0.00014284621,0.0000691622,0.000018874875,0.000015129963,0.00062620925,0.000032682954,0.00000271512],"category_scores_gemma":[0.000011562352,0.000049052625,0.000057868427,0.00035935882,0.00005767767,0.0001420365,0.000116522206,0.00011917798,8.4617916e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039693437,0.0014166638,0.25926405,0.00012519036,0.00007126566,0.000029767374,0.0061592604,0.01628872,0.23458152,0.024897145,0.00014666845,0.4566228],"study_design_scores_gemma":[0.00042332624,0.00003661287,0.9774915,0.0000100182815,0.0000039758916,0.0000307092,0.000045761633,0.0011967943,0.019851767,0.0008598049,0.0000052242967,0.000044532357],"about_ca_topic_score_codex":0.0001644969,"about_ca_topic_score_gemma":0.00015126841,"teacher_disagreement_score":0.71822745,"about_ca_system_score_codex":0.00016469008,"about_ca_system_score_gemma":0.00009443696,"threshold_uncertainty_score":0.2000308},"labels":[],"label_agreement":null},{"id":"W2117828866","doi":"10.1109/iembs.1997.757658","title":"A method for detection of malignant masses in digitized mammograms using a fuzzy segmentation algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"False positive paradox; Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Feature (linguistics); Image segmentation; Fuzzy logic; Mammography; Fuzzy set; Computer vision; Algorithm; Feature extraction; Breast cancer; Cancer; Medicine","score_opus":0.04269492528935226,"score_gpt":0.30772437456794877,"score_spread":0.2650294492785965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117828866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008372461,0.00004938229,0.9904944,0.0000670294,0.00025573006,0.0004230307,0.0000023456143,0.000108706634,0.00022693271],"genre_scores_gemma":[0.1502507,0.000013196226,0.8495124,0.000038667233,0.000032783795,0.000073448144,6.16687e-7,0.000008359425,0.00006982735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898475,0.00006920811,0.00029208956,0.00028528192,0.00018161547,0.00018707676],"domain_scores_gemma":[0.99944556,0.0001157062,0.00013778578,0.00019472312,0.00007602949,0.000030224846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031118892,0.00009699769,0.00015183422,0.0002056755,0.000048406968,0.00006449125,0.00016783779,0.000056257944,0.000011054776],"category_scores_gemma":[0.000016312379,0.00009346223,0.00006417315,0.0005957159,0.000014507636,0.00053028885,0.000045881967,0.00004811229,0.0000017479164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073871383,0.000036984147,0.00003831565,0.00002183272,0.000008666957,9.965684e-7,0.00021964323,0.00046882447,0.09839899,0.00023876483,0.000008761584,0.90055084],"study_design_scores_gemma":[0.0005100904,0.00011634048,0.0000661868,0.000017355733,0.0000059011886,0.000016002965,0.000069022935,0.6976316,0.29860604,0.0027438197,0.00013008338,0.00008757046],"about_ca_topic_score_codex":0.00031324348,"about_ca_topic_score_gemma":0.0000755512,"teacher_disagreement_score":0.9004633,"about_ca_system_score_codex":0.00017191218,"about_ca_system_score_gemma":0.000014462945,"threshold_uncertainty_score":0.38112792},"labels":[],"label_agreement":null},{"id":"W2117857464","doi":"10.1007/s10439-009-9790-2","title":"Detecting Mitoses in Time-Lapse Images of Embryonic Epithelia Using Intensity Analysis","year":2009,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; False positive paradox; Artificial intelligence; Algorithm; Mitosis; Computer vision; Biology; Cell biology","score_opus":0.02121057383834577,"score_gpt":0.2787145013939071,"score_spread":0.2575039275555613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117857464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58685374,0.0002315052,0.41240954,0.00030292926,0.00009883147,0.00003961903,0.0000018908586,0.000053793447,0.00000817457],"genre_scores_gemma":[0.9757549,0.000031509153,0.024105953,0.000053800366,0.000042817614,8.353985e-7,7.130281e-7,0.0000052618198,0.000004167808],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987395,0.00002571015,0.000385467,0.00024016929,0.00035050634,0.00025867458],"domain_scores_gemma":[0.9992469,0.00011092943,0.00014232253,0.00030631555,0.000107427906,0.000086135864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006037713,0.00011809949,0.00037225283,0.0007746859,0.000019516818,0.000017607741,0.00043987433,0.000084446845,0.0000057462994],"category_scores_gemma":[0.00027372703,0.000119056414,0.0001470355,0.002256816,0.000047360507,0.00023144008,0.00010820917,0.00015782131,0.0000014988726],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028460252,0.00016024138,0.0011433396,0.00010856114,0.0002847602,0.00003107376,0.00040560417,0.046014164,0.8585432,0.00006576826,0.00006364486,0.09315116],"study_design_scores_gemma":[0.000119282384,0.0001221517,0.016613374,0.00011916591,0.000027794491,0.00000720712,0.00000834651,0.6768869,0.30581972,0.00011973284,0.000031020907,0.00012529932],"about_ca_topic_score_codex":0.00010402189,"about_ca_topic_score_gemma":0.0000018730336,"teacher_disagreement_score":0.6308727,"about_ca_system_score_codex":0.0000323198,"about_ca_system_score_gemma":0.00003290563,"threshold_uncertainty_score":0.48549798},"labels":[],"label_agreement":null},{"id":"W2119460059","doi":"10.1089/tmj.2015.0083","title":"Impacts of a Large Decentralized Telepathology Network in Canada","year":2015,"lang":"en","type":"article","venue":"Telemedicine Journal and e-Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Telepathology; Telemedicine; Service (business); Medicine; Health care; Operations management; Business; Engineering; Marketing; Political science","score_opus":0.0277211068570841,"score_gpt":0.30787455436291317,"score_spread":0.28015344750582905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119460059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74621964,0.032041244,0.11592609,0.10020457,0.004764027,0.0004597547,0.000005565193,0.0000475279,0.0003315935],"genre_scores_gemma":[0.98601454,0.0024448053,0.005417283,0.0057546403,0.00035296942,0.0000013437091,6.5742114e-7,0.0000050252306,0.00000871074],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984342,0.00014618554,0.00048455465,0.00012846338,0.00030556362,0.00050102494],"domain_scores_gemma":[0.9989326,0.000032686323,0.00035097657,0.00013190787,0.000071511924,0.00048031562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002149223,0.000085583764,0.00032934253,0.00008899301,0.000068889116,0.000009630076,0.0002000534,0.000023635052,0.000014069817],"category_scores_gemma":[0.000048293376,0.000065419976,0.0000147196315,0.0003703315,0.0000199193,0.00012449211,0.000061226936,0.0002891743,5.91233e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009208582,0.00006407071,0.3936884,0.00011904712,0.000026386411,0.00017898962,0.0044137477,0.00034116287,0.000027922018,0.0007197659,0.37864104,0.22168735],"study_design_scores_gemma":[0.014295625,0.004675088,0.79479975,0.0011069675,0.000012995884,0.006232762,0.002499706,0.023806104,0.00009613195,0.0092529,0.1427473,0.00047464715],"about_ca_topic_score_codex":0.500574,"about_ca_topic_score_gemma":0.81908387,"teacher_disagreement_score":0.40111133,"about_ca_system_score_codex":0.000774327,"about_ca_system_score_gemma":0.0043834643,"threshold_uncertainty_score":0.77760774},"labels":[],"label_agreement":null},{"id":"W2120854520","doi":"10.1109/nafips.2004.1336330","title":"A fuzzy enhancement schema for density-typed mammograms","year":2004,"lang":"en","type":"article","venue":"IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04.","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mammography; Fuzzy logic; Artificial intelligence; Computer science; Breast cancer; Contrast enhancement; Contrast (vision); Pattern recognition (psychology); Breast tissue; Computer vision; Cancer; Radiology; Medicine","score_opus":0.012217601259420558,"score_gpt":0.24889712809366749,"score_spread":0.23667952683424692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120854520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18876682,0.000538628,0.79548085,0.0033956643,0.0033284994,0.0017130696,0.000034008568,0.00060820853,0.006134278],"genre_scores_gemma":[0.9234487,0.000011526617,0.07520132,0.00077462016,0.0002544627,0.00011926322,0.000008211286,0.000021954127,0.00015997372],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99731916,0.00005092273,0.00094463874,0.0003254739,0.00080410123,0.0005556981],"domain_scores_gemma":[0.9968163,0.0000826923,0.0010402448,0.0006694791,0.0012861157,0.00010516932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011103277,0.00030246732,0.0003152479,0.00022278861,0.000762075,0.00031909236,0.0013127903,0.00017033305,0.0000012883654],"category_scores_gemma":[0.00036411794,0.00025236048,0.00017583977,0.0010916784,0.00014717306,0.0033406748,0.00019479288,0.00026447792,0.000040727],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076026446,0.00083624216,0.0014246037,0.0056305523,0.00043247425,0.000004289735,0.09480719,0.11191468,0.020029621,0.014560603,0.02563194,0.72396755],"study_design_scores_gemma":[0.0053915433,0.0009740604,0.00082892156,0.003048704,0.00017261188,0.00013943996,0.0026398746,0.011170806,0.88599575,0.060378414,0.027575685,0.00168419],"about_ca_topic_score_codex":0.00011578813,"about_ca_topic_score_gemma":0.000028127719,"teacher_disagreement_score":0.86596614,"about_ca_system_score_codex":0.00037159084,"about_ca_system_score_gemma":0.00062643085,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W2121075186","doi":"10.1016/j.ajpath.2012.01.033","title":"Toward Routine Use of 3D Histopathology as a Research Tool","year":2012,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Wellcome Trust; National Institute for Health and Care Research; National Cancer Research Institute; Cancer Research Institute","keywords":"Computer science; Visualization; Computer vision; Artificial intelligence; 3D reconstruction; 3D modeling; Image registration; Image resolution; Computer graphics (images); Biomedical engineering; Image (mathematics); Medicine","score_opus":0.09757765091834479,"score_gpt":0.35997427317146186,"score_spread":0.26239662225311705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121075186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80509084,0.00030014905,0.19235171,0.000979028,0.00090948894,0.000063019135,0.0000012831484,0.000017006556,0.0002874785],"genre_scores_gemma":[0.9071911,0.00008583366,0.09202323,0.00034176788,0.0002743944,0.000004057127,1.5715565e-7,0.000011349496,0.00006808994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99720913,0.0010680866,0.0005767165,0.0001958461,0.00043561315,0.00051461946],"domain_scores_gemma":[0.9975975,0.0004794716,0.0007499986,0.00047426485,0.00055946107,0.00013928748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002555738,0.00011407849,0.00044464803,0.0005009243,0.00006042684,0.000018955243,0.0007244059,0.00006925597,0.000030550284],"category_scores_gemma":[0.0007142637,0.00010075087,0.00009932528,0.0007477886,0.0007743441,0.00064727664,0.00027236034,0.0005671706,0.00003574598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000506624,0.00058928615,0.07404977,0.000031806387,0.0000672608,0.00209212,0.017920673,0.00018081568,0.073136225,0.022662316,0.0027816677,0.80598146],"study_design_scores_gemma":[0.004925094,0.05238517,0.54290897,0.0002799115,0.00021811549,0.19767277,0.004490673,0.0023074143,0.043555677,0.012992395,0.13636325,0.0019005636],"about_ca_topic_score_codex":0.000071361384,"about_ca_topic_score_gemma":0.0000020867585,"teacher_disagreement_score":0.80408084,"about_ca_system_score_codex":0.0001990511,"about_ca_system_score_gemma":0.00022123921,"threshold_uncertainty_score":0.4108501},"labels":[],"label_agreement":null},{"id":"W2122925473","doi":"10.1109/tbme.2007.899310","title":"Polygonal Modeling of Contours of Breast Tumors With the Preservation of Spicules","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Sponge spicule; Mammography; Receiver operating characteristic; Artificial intelligence; Set (abstract data type); Breast tumor; Measure (data warehouse); Computer science; Pattern recognition (psychology); Computer vision; Medicine; Data mining; Breast cancer; Machine learning; Anatomy; Cancer","score_opus":0.008436105442129993,"score_gpt":0.20619771683845373,"score_spread":0.19776161139632373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122925473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11164192,0.0000189556,0.88778335,0.0002530433,0.00016115191,0.00007837174,0.000007644198,0.000038648835,0.00001692921],"genre_scores_gemma":[0.98827964,0.0000045206725,0.011663692,0.000007918529,0.00002656448,0.0000052770174,3.745834e-7,0.000007293585,0.0000047196745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990328,0.0000091674965,0.00027622856,0.00012577197,0.00041879108,0.00013727033],"domain_scores_gemma":[0.99945414,0.000107434615,0.00008510661,0.00021136303,0.000088995315,0.000052956475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002977992,0.00008378308,0.00013691805,0.00018321504,0.000028411396,0.000004748572,0.00027760695,0.000051620562,0.0000041606513],"category_scores_gemma":[0.000003863314,0.00006002174,0.00005325974,0.0005484491,0.00008457886,0.00017545624,0.0000022207773,0.00014294853,2.2760976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061890016,0.00009785772,0.000008845044,0.00007783995,0.000054533837,0.0000013407565,0.00036166975,0.9176552,0.05660359,0.00061242614,0.0000036500792,0.024461117],"study_design_scores_gemma":[0.0002617159,0.00017362689,0.00052139716,0.00012691195,0.000011695822,0.00002122623,0.000051155566,0.911391,0.08733896,0.000020107813,0.00001599116,0.00006620477],"about_ca_topic_score_codex":0.0001249119,"about_ca_topic_score_gemma":0.000015571934,"teacher_disagreement_score":0.8766377,"about_ca_system_score_codex":0.000037403126,"about_ca_system_score_gemma":0.000047102392,"threshold_uncertainty_score":0.24476156},"labels":[],"label_agreement":null},{"id":"W2125610074","doi":"10.2196/medinform.3251","title":"Clinical Data Miner: An Electronic Case Report Form System With Integrated Data Preprocessing and Machine-Learning Libraries Supporting Clinical Diagnostic Model Research","year":2014,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Workflow; Preprocessor; Data pre-processing; Machine learning; Software; Data mining; Interface (matter); Artificial intelligence; Software engineering; Database; Programming language; Operating system","score_opus":0.15390925479124679,"score_gpt":0.4471745632613304,"score_spread":0.29326530847008364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125610074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14030902,0.00008484556,0.8576835,0.00034585822,0.0001896029,0.00046012274,0.0000152694,0.00045846042,0.00045333765],"genre_scores_gemma":[0.9130184,0.0000828136,0.08577586,0.00022409792,0.00034658296,0.000041291045,0.00044150758,0.000031006002,0.000038409697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935644,0.0006816858,0.002515926,0.0008533746,0.0015586085,0.0008259969],"domain_scores_gemma":[0.99032426,0.0038696434,0.00096078916,0.0037655558,0.00033130948,0.0007484416],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.024641393,0.00025553783,0.000552386,0.00016562875,0.00052532705,0.00077238196,0.0032593764,0.00038039338,0.0000056306108],"category_scores_gemma":[0.013593842,0.0001869927,0.000032117005,0.00064326916,0.0006207379,0.005901824,0.004310307,0.002800495,0.000008272355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017546758,0.00035411766,0.032431953,0.0017149703,0.00016321277,0.00445957,0.005529919,0.0005530676,6.1160137e-7,0.0054023983,0.00455814,0.94465655],"study_design_scores_gemma":[0.0006218665,0.000637096,0.00008889884,0.00041283545,0.000025892821,0.014502189,0.0013414044,0.9780935,0.000003031509,0.00026313422,0.003774841,0.00023528175],"about_ca_topic_score_codex":0.00011859566,"about_ca_topic_score_gemma":0.00031974798,"teacher_disagreement_score":0.97754043,"about_ca_system_score_codex":0.00009420656,"about_ca_system_score_gemma":0.0021262032,"threshold_uncertainty_score":0.9995001},"labels":[],"label_agreement":null},{"id":"W2125804492","doi":"10.1109/iembs.2005.1617159","title":"Shape Analysis of Breast Masses in Mammograms via the Fractal Dimension","year":2005,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal dimension; Fractal; Box counting; Fractal analysis; Dimension (graph theory); Pattern recognition (psychology); Representation (politics); Receiver operating characteristic; Artificial intelligence; Breast cancer; Mammography; Feature (linguistics); Mathematics; Computer science; Medicine; Cancer; Statistics; Pure mathematics; Mathematical analysis","score_opus":0.008411757966983653,"score_gpt":0.23928440564511835,"score_spread":0.2308726476781347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125804492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6111134,0.000048695667,0.38443586,0.002779157,0.00010423719,0.00008554116,0.0000010140888,0.00007184711,0.0013602063],"genre_scores_gemma":[0.986123,0.0000069158873,0.013580264,0.00020282515,0.000028064409,0.000004866284,7.530952e-7,0.0000028237896,0.0000504587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992334,0.000039624276,0.00018040507,0.00019639051,0.00022333369,0.00012683484],"domain_scores_gemma":[0.9994147,0.000072013216,0.000070086644,0.00038036614,0.000039375995,0.000023471825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020783657,0.00006578026,0.00012145124,0.00019670496,0.00003509986,0.000033729673,0.00037909567,0.00003420943,0.00014706142],"category_scores_gemma":[0.000004447993,0.000043333224,0.00007738498,0.0016669163,0.000030319272,0.00031495732,0.00012770003,0.00007789106,0.000015561774],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009503143,0.00008223007,0.02028235,0.000002539872,0.000113451606,0.0000017726512,0.0003639502,0.007910577,0.0036290206,0.00082498905,0.00012990198,0.9666497],"study_design_scores_gemma":[0.00007210481,0.000021552663,0.13867548,0.0000031086984,0.000032106218,0.000007337335,0.000024086505,0.85750103,0.0030690837,0.00012512166,0.00040925437,0.000059713155],"about_ca_topic_score_codex":0.0004194367,"about_ca_topic_score_gemma":0.0011740989,"teacher_disagreement_score":0.96659,"about_ca_system_score_codex":0.000057492576,"about_ca_system_score_gemma":0.000014902297,"threshold_uncertainty_score":0.17670776},"labels":[],"label_agreement":null},{"id":"W2127570874","doi":"10.1109/pacrim.2007.4313303","title":"Pectoral Muscle Segmentation on Digital Mammograms by Nonlinear Diffusion Filtering","year":2007,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Calgary","keywords":"Pectoral muscle; Hough transform; Artificial intelligence; Segmentation; Computer science; Computer vision; Hausdorff distance; Pattern recognition (psychology); Mammography; Image processing; Image segmentation; Image (mathematics); Anatomy; Biology","score_opus":0.010933144128705689,"score_gpt":0.24890006209740478,"score_spread":0.2379669179686991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127570874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3072131,0.0000057492657,0.68902624,0.00012670943,0.0004370271,0.000089088855,0.0000025914032,0.00024964687,0.00284986],"genre_scores_gemma":[0.96735245,0.0000029796822,0.031675883,0.00023007301,0.00013487322,0.0000046569025,0.000012890666,0.000010691428,0.0005755319],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990302,0.000008076591,0.00015747487,0.00029026208,0.00028770385,0.00022633422],"domain_scores_gemma":[0.999554,0.00004182612,0.00005140346,0.00025306625,0.000025952875,0.000073761104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119256256,0.00010312651,0.000065582295,0.00006902943,0.00009361674,0.00023435523,0.00025241825,0.000042574826,0.000034348534],"category_scores_gemma":[0.00000771267,0.00009427067,0.00003875665,0.00024017003,0.000016882208,0.00065239856,0.00011105051,0.000086262415,0.00008631999],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019211351,0.000119316785,0.0011362486,0.0000064292503,0.0000052523255,0.000007846707,0.00022839315,0.000058408943,0.0814052,0.00029610557,0.001422239,0.91529536],"study_design_scores_gemma":[0.0021380815,0.0018829529,0.023931602,0.00007597843,0.000008693926,0.000039445094,0.0003970377,0.20375001,0.69539475,0.0007908966,0.070399426,0.0011911482],"about_ca_topic_score_codex":0.000051428822,"about_ca_topic_score_gemma":0.00001945074,"teacher_disagreement_score":0.9141042,"about_ca_system_score_codex":0.00013923021,"about_ca_system_score_gemma":0.00000772925,"threshold_uncertainty_score":0.38442466},"labels":[],"label_agreement":null},{"id":"W2127594721","doi":"10.1016/j.ejrad.2009.08.024","title":"Performance of computer-aided detection applied to full-field digital mammography in detection of breast cancers","year":2009,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Mount Sinai Hospital","funders":"","keywords":"Medicine; Mammography; Digital mammography; Medical physics; Breast cancer; Radiology; Internal medicine; Cancer","score_opus":0.005778351370046534,"score_gpt":0.19468813385984945,"score_spread":0.18890978248980292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127594721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6246371,0.000039626375,0.3742927,0.00008015495,0.0005146416,0.000067098976,7.620131e-7,0.000013900066,0.00035397118],"genre_scores_gemma":[0.9952872,0.000037507052,0.0043324423,0.0001049847,0.00022665568,7.319951e-7,1.5917907e-7,0.000008736749,0.0000016012465],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99854577,0.00016957925,0.00068433856,0.00020490719,0.00019085464,0.00020452906],"domain_scores_gemma":[0.99886316,0.00006687991,0.0006009247,0.00024052047,0.00014332787,0.000085164786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006336414,0.0001303604,0.0003223131,0.0006468674,0.000037547252,0.000020954427,0.0005346452,0.00004250978,0.0000019250547],"category_scores_gemma":[0.000020309644,0.00012568197,0.00010445768,0.0007453814,0.000053086806,0.00034616992,0.00005429345,0.00027110594,0.0000030679305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006525292,0.000036390324,0.0009874972,0.000014873706,0.000026763073,0.000019010533,0.00039277755,0.01613674,0.17564379,0.00003238912,0.000042075775,0.8060152],"study_design_scores_gemma":[0.00442139,0.034236003,0.6763881,0.00037763253,0.000043106545,0.010120671,0.00014416776,0.04487059,0.22747378,0.00031917865,0.0008739215,0.00073146564],"about_ca_topic_score_codex":0.000006507167,"about_ca_topic_score_gemma":0.0000099200415,"teacher_disagreement_score":0.8052837,"about_ca_system_score_codex":0.00013300065,"about_ca_system_score_gemma":0.000049399026,"threshold_uncertainty_score":0.5125162},"labels":[],"label_agreement":null},{"id":"W2128418623","doi":"10.1007/978-3-540-85988-8_55","title":"Simulation of Ground-Truth Validation Data Via Physically- and Statistically-Based Warps","year":2008,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ground truth; Upload; Landmark; Segmentation; Computation; Artificial intelligence; Data mining; Computer vision; Algorithm","score_opus":0.03501184614019765,"score_gpt":0.29030545211526004,"score_spread":0.2552936059750624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128418623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05696627,0.000023779667,0.94208753,0.00022821681,0.00045820605,0.00015356258,0.0000048240945,0.000074171774,0.0000034137413],"genre_scores_gemma":[0.6082106,0.0000021372891,0.39158395,0.00012930231,0.0000627172,0.000002079608,0.000004852731,0.000004246134,7.485927e-8],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978057,0.000085340296,0.000309264,0.0008538997,0.0006626229,0.000283141],"domain_scores_gemma":[0.9971171,0.001284143,0.00015848594,0.0011187745,0.00024091727,0.00008055765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058177114,0.0001539722,0.00019626024,0.00024465346,0.0001979559,0.00011262532,0.0014603781,0.000057972986,0.0000022751915],"category_scores_gemma":[0.00041470787,0.0001447464,0.0000173061,0.0017506405,0.00054076046,0.0012385007,0.0006347696,0.00016736577,0.0000029386492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071528366,0.000043939934,0.0007449205,0.000016388145,0.0000020558743,0.000004885026,0.00033402833,0.70117337,0.0017325465,0.00020868746,0.0000010534843,0.29573098],"study_design_scores_gemma":[0.0002612899,0.00013917995,0.008464587,0.000025848653,0.0000029622374,0.00001060884,1.2983129e-7,0.96705705,0.012982329,0.010895018,0.0000074865093,0.00015352193],"about_ca_topic_score_codex":0.00007755128,"about_ca_topic_score_gemma":0.000011582689,"teacher_disagreement_score":0.5512444,"about_ca_system_score_codex":0.000101786034,"about_ca_system_score_gemma":0.0002676614,"threshold_uncertainty_score":0.5902587},"labels":[],"label_agreement":null},{"id":"W2130780685","doi":"10.1186/1746-1596-9-s1-s5","title":"Online teaching of inflammatory skin pathology by a French-speaking International University Network","year":2014,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"Centre Hospitalier Universitaire de Bordeaux","keywords":"Medicine; Limiting; Computer science; Pathology; Multimedia; Engineering","score_opus":0.005794468054736518,"score_gpt":0.21652651414259155,"score_spread":0.21073204608785503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130780685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3592557,0.000080642945,0.63743186,0.0004225171,0.0014343767,0.000073971554,0.000013867818,0.00009622209,0.0011908638],"genre_scores_gemma":[0.967339,0.000050303326,0.03187776,0.0003426557,0.00031027055,0.0000034776504,0.000021208672,0.000009593969,0.000045781024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984557,0.0004616056,0.00025152403,0.0003998123,0.00015461729,0.00027671314],"domain_scores_gemma":[0.9978604,0.001344503,0.00025257948,0.00041011587,0.00007678294,0.000055644872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005876537,0.00012963485,0.00021635904,0.00012750774,0.00010220223,0.000013157033,0.0008384178,0.00014251181,0.00001251219],"category_scores_gemma":[0.001022882,0.0001465466,0.000058542355,0.00014664065,0.00013853781,0.0002143404,0.0004217484,0.00031236105,0.00001529576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034597622,0.0006593502,0.16603911,0.00005716693,0.0001085657,0.0011814764,0.0053615817,0.009065859,0.005393623,0.10798254,0.015295978,0.6888201],"study_design_scores_gemma":[0.0028761127,0.0009735556,0.6488446,0.0002432162,0.00007203266,0.00096545316,0.00018473167,0.09294113,0.0014983631,0.016892403,0.23348016,0.001028236],"about_ca_topic_score_codex":0.000063083455,"about_ca_topic_score_gemma":0.000076747725,"teacher_disagreement_score":0.68779194,"about_ca_system_score_codex":0.00009584836,"about_ca_system_score_gemma":0.000040890376,"threshold_uncertainty_score":0.5975997},"labels":[],"label_agreement":null},{"id":"W2131557603","doi":"10.5858/2003-127-721-covtah","title":"Comparison of Voice-Automated Transcription and Human Transcription in Generating Pathology Reports","year":2003,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Transcription (linguistics); Computer science; Software; Speech recognition; Headset; Vocabulary; Operating system; Telecommunications","score_opus":0.02322237174702594,"score_gpt":0.309816229726959,"score_spread":0.28659385797993303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131557603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9234479,0.0015175538,0.07376878,0.00015236529,0.00047701006,0.00020143723,0.0000035287228,0.00011164477,0.0003198],"genre_scores_gemma":[0.98241615,0.00006573683,0.01734672,0.00009262977,0.000033822304,0.000019835115,0.000007476285,0.000011539172,0.000006067474],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974743,0.0007348229,0.0009141558,0.00046537418,0.0001808881,0.00023043762],"domain_scores_gemma":[0.9988494,0.00013189584,0.00045817267,0.00041664837,0.000081708444,0.00006221141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000886088,0.00016943879,0.0005505294,0.00041369232,0.000077152,0.000004176428,0.00016765983,0.00012359125,0.000006259776],"category_scores_gemma":[0.00014070355,0.0001626236,0.000032874595,0.0004557848,0.00063503993,0.00019529079,0.000021925061,0.00024815576,3.081981e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000130151,0.000085258594,0.03271195,0.00007852622,0.000008618535,0.00016868881,0.007947731,0.00017694822,0.95291924,0.0030874175,0.000023938148,0.002778646],"study_design_scores_gemma":[0.0043317503,0.003881378,0.40627396,0.00057802047,0.000113108,0.0010318893,0.0018350536,0.033007562,0.5397252,0.0078075523,0.000824281,0.0005902889],"about_ca_topic_score_codex":0.000036928715,"about_ca_topic_score_gemma":0.0001435591,"teacher_disagreement_score":0.4131941,"about_ca_system_score_codex":0.000023661767,"about_ca_system_score_gemma":0.000075761316,"threshold_uncertainty_score":0.66315985},"labels":[],"label_agreement":null},{"id":"W2132120643","doi":"10.1007/s11517-007-0211-0","title":"Classification of breast masses via nonlinear transformation of features based on a kernel matrix","year":2007,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Kernel principal component analysis; Kernel (algebra); Feature (linguistics); Transformation (genetics); Feature extraction; Linear discriminant analysis; Computer science; Feature vector; Mathematics; Principal component analysis; Texture (cosmology); Receiver operating characteristic; Kernel method; Support vector machine; Image (mathematics); Statistics","score_opus":0.012358363625016872,"score_gpt":0.26469162987707456,"score_spread":0.2523332662520577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132120643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16677897,0.00003884389,0.8322324,0.00027586895,0.00024702164,0.00010218627,0.0000022789118,0.00014590098,0.00017651648],"genre_scores_gemma":[0.9465812,0.0000039067722,0.05320923,0.0000581522,0.00013055699,0.0000018286943,0.0000072016032,0.000006657538,0.0000012971601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841076,0.000042589483,0.00052122155,0.00026059092,0.0005069083,0.00025794227],"domain_scores_gemma":[0.99888587,0.00051826803,0.00016548803,0.00022727785,0.00008480373,0.00011829298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011130263,0.0001461377,0.00024318059,0.00015805791,0.000057340363,0.000010594055,0.0004717017,0.0002226945,0.000016915053],"category_scores_gemma":[0.00021419422,0.00011431823,0.000094343064,0.0004978118,0.00006436058,0.00007402173,0.00007642651,0.000309614,0.000003662328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023199216,0.0006577588,0.010833063,0.0005859794,0.00006168257,0.000021975182,0.0008058997,0.17198043,0.098879404,0.013260928,0.000044370066,0.70263654],"study_design_scores_gemma":[0.00025910337,0.00018790014,0.11620137,0.00014213819,0.000003067915,0.00002663533,0.000008614764,0.8770761,0.005814844,0.00003611971,0.00013570048,0.000108411376],"about_ca_topic_score_codex":0.000018372166,"about_ca_topic_score_gemma":0.0000011204211,"teacher_disagreement_score":0.7798022,"about_ca_system_score_codex":0.000069330155,"about_ca_system_score_gemma":0.000041599353,"threshold_uncertainty_score":0.46617624},"labels":[],"label_agreement":null},{"id":"W2134916573","doi":"10.1109/42.887618","title":"Gradient and texture analysis for the classification of mammographic masses","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":279,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Mahalanobis distance; Pixel; Artificial intelligence; Pattern recognition (psychology); Receiver operating characteristic; Texture (cosmology); Computer science; Contextual image classification; Database; Computer vision; Mathematics; Image (mathematics)","score_opus":0.015011280753163487,"score_gpt":0.2675426122484033,"score_spread":0.2525313314952398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134916573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069697346,0.0002156161,0.9863822,0.005903526,0.00023331272,0.00014805654,0.00000465814,0.00006221955,0.00008071189],"genre_scores_gemma":[0.9959994,0.00036544667,0.0031977962,0.00027452118,0.000029320117,0.00006771778,5.3592726e-7,0.000005464917,0.00005982426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900734,0.000045191206,0.00019659614,0.00025537575,0.0003559645,0.00013954284],"domain_scores_gemma":[0.99916375,0.0003378294,0.000050234987,0.00032102576,0.000048338967,0.000078825426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033006334,0.00008327237,0.00011989323,0.00020657314,0.00021027375,0.0000454797,0.00030400883,0.000042702108,0.00010805611],"category_scores_gemma":[0.000007944647,0.00006012299,0.00012875709,0.0009718856,0.0001647515,0.00017567321,0.0000010447621,0.00017655863,0.0000018144393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000123721775,0.00004712708,0.00028004192,0.0000120579,0.00013013519,7.153055e-7,0.00020932598,0.0022123673,0.0002452904,0.00022236432,0.00007234755,0.99655586],"study_design_scores_gemma":[0.00027992047,0.00003762457,0.008595789,0.000024158462,0.00024414752,0.000014489497,0.00008296714,0.9857851,0.0016327294,0.00053632644,0.0026699717,0.000096737735],"about_ca_topic_score_codex":0.000054649252,"about_ca_topic_score_gemma":0.00007849546,"teacher_disagreement_score":0.9964591,"about_ca_system_score_codex":0.000024937855,"about_ca_system_score_gemma":0.000033248736,"threshold_uncertainty_score":0.24517444},"labels":[],"label_agreement":null},{"id":"W2136593380","doi":"10.1109/sibgrapi.2008.10","title":"Can Bilateral Asymmetry Analysis of Breast MR Images Provide Additional  Information for Detection of Breast Diseases?","year":2008,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Health Sciences Centre; University Health Network","funders":"Terry Fox Foundation; Canadian Breast Cancer Research Alliance; Breast Cancer Alliance","keywords":"Breast cancer; Artificial intelligence; Linear discriminant analysis; Pattern recognition (psychology); Population; Computer science; Radiology; Mathematics; Medicine; Nuclear medicine; Cancer; Internal medicine","score_opus":0.006006141491981663,"score_gpt":0.21003491069620453,"score_spread":0.20402876920422286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136593380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07848302,0.000009219828,0.9156795,0.00028207773,0.00018316851,0.00031660424,0.0047362666,0.00012314339,0.00018701091],"genre_scores_gemma":[0.99219215,0.0000034247357,0.007289424,0.000060850554,0.00005188983,0.00007425461,0.00027925114,0.000004747304,0.00004401846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885,0.000029863279,0.00041400967,0.00019429174,0.00035409394,0.00015777901],"domain_scores_gemma":[0.99873835,0.000102977305,0.0003406218,0.0003018846,0.00044739267,0.00006876258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000924438,0.00011405988,0.0002192363,0.00067227846,0.000107704356,0.00003130409,0.00025377946,0.000053799373,0.00012236],"category_scores_gemma":[0.0000258768,0.000104878425,0.00021228839,0.0013983167,0.0000786718,0.0014889308,0.00006297621,0.00005206591,0.0000028160025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011460396,0.00093069987,0.06381046,0.0008145411,0.0038840473,0.0000055737723,0.002484729,0.025373558,0.038922396,0.0045774304,0.016891284,0.8411592],"study_design_scores_gemma":[0.00056189403,0.00018657076,0.6973163,0.000020063622,0.0002456266,0.00013314957,0.000055497505,0.27540818,0.025032898,0.00051988376,0.0002893544,0.00023061452],"about_ca_topic_score_codex":0.0005859946,"about_ca_topic_score_gemma":0.00011634396,"teacher_disagreement_score":0.9137091,"about_ca_system_score_codex":0.00012984978,"about_ca_system_score_gemma":0.00013488949,"threshold_uncertainty_score":0.4276818},"labels":[],"label_agreement":null},{"id":"W2136846495","doi":"10.1186/1746-1596-9-s1-s1","title":"The Eastern Québec Telepathology Network: a three-year experience of clinical diagnostic services","year":2014,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HEC Montréal; Cégep de Rimouski; Université Laval","funders":"","keywords":"Telepathology; Technician; Medicine; Concordance; Christian ministry; Telehealth; Second opinion; Telemedicine; Medical physics; Medical emergency; Pathology; Health care","score_opus":0.020581524946913156,"score_gpt":0.29898285430899235,"score_spread":0.2784013293620792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136846495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.685429,0.001070357,0.30573478,0.0016198767,0.0046493863,0.0003570985,0.0000031362154,0.00018470018,0.000951669],"genre_scores_gemma":[0.9928319,0.00038297646,0.0046538715,0.001000922,0.00085298595,0.00020854636,0.0000016516602,0.000020924675,0.000046256897],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99664134,0.00079637626,0.0008994657,0.0007275138,0.00028580354,0.0006495144],"domain_scores_gemma":[0.9752082,0.022604346,0.00052148773,0.0013631608,0.00016588063,0.00013689598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017032671,0.00023716902,0.00051489146,0.00005766875,0.00028264083,0.000056254772,0.0018252764,0.00023847946,0.000017195847],"category_scores_gemma":[0.006907745,0.0001806352,0.0001499998,0.00034325093,0.0006964129,0.00020842308,0.0007135803,0.00036416232,0.00026105653],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024266163,0.00008318452,0.8326689,0.000023633385,0.000017270479,0.00009661161,0.0010714154,0.0003752376,0.00001822978,0.007974666,0.00048305676,0.15716352],"study_design_scores_gemma":[0.0010926366,0.0013053428,0.8971478,0.00012032501,0.00004724534,0.00030654017,0.00016071032,0.049091626,0.00016186883,0.01392049,0.036181636,0.00046382044],"about_ca_topic_score_codex":0.0012077108,"about_ca_topic_score_gemma":0.008156927,"teacher_disagreement_score":0.30740288,"about_ca_system_score_codex":0.000034826287,"about_ca_system_score_gemma":0.00015943992,"threshold_uncertainty_score":0.8269715},"labels":[],"label_agreement":null},{"id":"W2139207838","doi":"10.1109/iembs.2005.1615343","title":"Fuzzy Entropy Based Detection of Suspicious Masses in Digital Mammogram Images","year":2005,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thresholding; Artificial intelligence; Mammography; Computer science; Digital mammography; Entropy (arrow of time); Computer vision; Segmentation; Fuzzy logic; Image segmentation; Digital image; Pattern recognition (psychology); Image (mathematics); Image processing; Breast cancer; Medicine","score_opus":0.006273150249316822,"score_gpt":0.2243470418575967,"score_spread":0.2180738916082799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139207838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16904153,0.000062525774,0.8244508,0.00066140335,0.00024411446,0.00015764382,0.0000018202051,0.0002407002,0.0051394897],"genre_scores_gemma":[0.97719663,0.0000065769586,0.022521965,0.000077111654,0.000062537554,0.00001358886,5.859287e-7,0.000006632975,0.000114373106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991137,0.000018026734,0.0002210205,0.00024579058,0.00021118195,0.00019032194],"domain_scores_gemma":[0.9994647,0.00006251398,0.000075311444,0.0003001935,0.000059746955,0.000037535327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000887247,0.00009478659,0.00011056812,0.00019384183,0.000026501286,0.00010454514,0.0002911271,0.000048453472,0.000017279488],"category_scores_gemma":[0.000031029114,0.00008996679,0.000050796312,0.00044646423,0.000035788427,0.0008494416,0.000063896536,0.00008396818,0.000026093865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000342156,0.00018586755,0.011530618,0.000024483148,0.000009087926,0.0000071914933,0.000084197156,0.0031138312,0.04385143,0.0018755858,0.00017953679,0.93910396],"study_design_scores_gemma":[0.0009283376,0.00038568903,0.012655114,0.000022018578,0.000004226181,0.000015577538,0.000057376914,0.088326745,0.89077413,0.0026227373,0.003931826,0.00027620772],"about_ca_topic_score_codex":0.00008759232,"about_ca_topic_score_gemma":0.0003034127,"teacher_disagreement_score":0.93882775,"about_ca_system_score_codex":0.00014018483,"about_ca_system_score_gemma":0.000039991795,"threshold_uncertainty_score":0.3668739},"labels":[],"label_agreement":null},{"id":"W2139858249","doi":"10.1309/w00t-2ca8-mh68-rvdv","title":"Telepathology for Routine Light Microscopic and Frozen Section Diagnosis","year":2002,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Blood Services; McMaster University","funders":"","keywords":"Telepathology; Frozen section procedure; Nuclear medicine; Medicine; Significant difference; Medical diagnosis; Pathology","score_opus":0.04183767315152204,"score_gpt":0.35291413576132125,"score_spread":0.3110764626097992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139858249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7164448,0.0004847314,0.27026963,0.009878918,0.0026648568,0.000115837734,0.0000022059046,0.00003101247,0.00010801269],"genre_scores_gemma":[0.9278275,0.0009992116,0.068381354,0.0016562616,0.0010535064,0.000017842722,1.979998e-7,0.000013061751,0.000051077313],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977505,0.00046912496,0.0010413281,0.00034847602,0.00012694432,0.00026360914],"domain_scores_gemma":[0.99700046,0.0012152072,0.0011391534,0.00028548716,0.00020734446,0.000152338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013533435,0.00013179821,0.00067171257,0.00015325658,0.0000861259,0.000031344345,0.0004158722,0.00013128234,0.000018077613],"category_scores_gemma":[0.0008966865,0.000113091155,0.00019278348,0.0002548608,0.00038559036,0.00023097233,0.00010425671,0.0004317433,0.000008096107],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112459085,0.00023176022,0.11413457,0.000010237343,0.00005453324,0.00014946131,0.00051984383,0.000014691501,0.0011035845,0.00029922367,0.003856577,0.8795131],"study_design_scores_gemma":[0.013951774,0.080651574,0.6373644,0.00021347245,0.00044261495,0.018521424,0.0004919908,0.012047494,0.007989942,0.02027972,0.20642316,0.0016224482],"about_ca_topic_score_codex":0.0000057605866,"about_ca_topic_score_gemma":0.0000071103277,"teacher_disagreement_score":0.8778906,"about_ca_system_score_codex":0.00003535254,"about_ca_system_score_gemma":0.0000340932,"threshold_uncertainty_score":0.46117234},"labels":[],"label_agreement":null},{"id":"W2140041904","doi":"10.1109/embc.2012.6346940","title":"Combining multiple feature representations and AdaBoost ensemble learning for reducing false-positive detections in Computer-aided Detection of masses on mammograms","year":2012,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"AdaBoost; Artificial intelligence; Computer science; Classifier (UML); Pattern recognition (psychology); Ensemble learning; Machine learning; Boosting (machine learning); Benchmark (surveying)","score_opus":0.020902205301062952,"score_gpt":0.27371498084954343,"score_spread":0.2528127755484805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140041904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28877413,0.0000652428,0.7099136,0.00013204588,0.00046520503,0.00035331346,0.0000013960604,0.00012983123,0.0001652177],"genre_scores_gemma":[0.91243345,0.000012310133,0.08722203,0.000032705433,0.000098971905,0.000094281546,0.000003454189,0.00001559184,0.00008720748],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987461,0.00014157179,0.0002544886,0.0003789571,0.00016773908,0.000311141],"domain_scores_gemma":[0.9985293,0.0008432162,0.00017592563,0.00025310233,0.000119471675,0.0000789846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038190067,0.0001485801,0.00019517561,0.00029506997,0.00030853227,0.00008356514,0.00013902734,0.00010525665,0.0000010577746],"category_scores_gemma":[0.0001644269,0.00015466825,0.000061065526,0.0005667062,0.000042484517,0.0006693331,0.00009805318,0.00027235248,0.0000015612025],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017997064,0.00032736518,0.03799611,0.00011266157,0.00008949156,0.0000020514362,0.007197888,0.043432068,0.22877045,0.002881721,0.00008712152,0.67892313],"study_design_scores_gemma":[0.0012061318,0.0007859642,0.06088969,0.00017552452,0.000020776803,0.000050083872,0.0007159152,0.46325725,0.47178307,0.0005538333,0.00025515855,0.0003065876],"about_ca_topic_score_codex":0.00053877884,"about_ca_topic_score_gemma":0.0004548228,"teacher_disagreement_score":0.6786165,"about_ca_system_score_codex":0.00012726642,"about_ca_system_score_gemma":0.000022341093,"threshold_uncertainty_score":0.63071877},"labels":[],"label_agreement":null},{"id":"W2140124228","doi":"10.1109/iembs.2009.5334886","title":"Gradient vector flow based active shape model for lung field segmentation in chest radiographs","year":2009,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Vector flow; Lung cancer; Active shape model; Segmentation; Radiography; Lung; Radiology; Computer science; Medicine; Image segmentation; Artificial intelligence; CAD; Computer vision; Pathology; Internal medicine; Engineering; Engineering drawing","score_opus":0.017318247705963657,"score_gpt":0.265767844236316,"score_spread":0.24844959653035234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140124228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018889138,0.000018852446,0.9781271,0.001833235,0.00021568035,0.0004511992,0.0000023402176,0.00011539328,0.0003470114],"genre_scores_gemma":[0.78174436,0.00000446137,0.2169472,0.001151269,0.000031002983,0.00008404185,0.0000032572411,0.0000042277507,0.000030153948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916464,0.000019352503,0.0001504923,0.0003163498,0.00014679745,0.00020236506],"domain_scores_gemma":[0.9995518,0.00009279545,0.000049303977,0.00021836512,0.00004041089,0.000047357527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119690565,0.000102484,0.00009850112,0.00018855289,0.0000613145,0.000053527252,0.00024488714,0.00005613784,0.000013552104],"category_scores_gemma":[0.000014817918,0.00010112189,0.00007047189,0.000404946,0.0000076114757,0.00043790563,0.000015231206,0.00007884443,0.0000011567492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021032212,0.00021029415,0.00048281933,0.00003532808,0.000019706691,0.000004013879,0.0020007326,0.2220612,0.0072752754,0.00390144,0.0025672766,0.7612316],"study_design_scores_gemma":[0.0005761792,0.00021251137,0.0027345957,0.000010993904,0.0000040186037,8.9512554e-7,0.000015118206,0.9638437,0.031013513,0.0014506549,0.000017882461,0.000119936674],"about_ca_topic_score_codex":0.000037273887,"about_ca_topic_score_gemma":0.00008949367,"teacher_disagreement_score":0.76285523,"about_ca_system_score_codex":0.00019822115,"about_ca_system_score_gemma":0.000054705455,"threshold_uncertainty_score":0.41236308},"labels":[],"label_agreement":null},{"id":"W2141076087","doi":"10.5858/arpa.2013-0289-ed","title":"Canadian Licensure for the Use of Digital Pathology for Routine Diagnoses: One More Step Toward a New Era of Pathology Practice Without Borders","year":2013,"lang":"en","type":"editorial","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Digital pathology; Telepathology; Licensure; License; Certification; Agency (philosophy); Health care; Medicine; Medical diagnosis; Virtual microscopy; Pathology; Medical education; Medical physics; Computer science; Telemedicine; Political science","score_opus":0.024263975594080656,"score_gpt":0.30068616935860076,"score_spread":0.2764221937645201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141076087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00444432,0.010263352,0.56511253,0.035957955,0.37123066,0.0066498723,0.0059550893,0.00026199562,0.00012424465],"genre_scores_gemma":[0.058066767,0.012217287,0.50322425,0.0062664193,0.41248345,0.003539379,0.0020177974,0.0011793997,0.0010052404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953798,0.00059164845,0.0014513648,0.001141866,0.00060730445,0.0008279889],"domain_scores_gemma":[0.9757574,0.018022623,0.0023166225,0.0017973459,0.0017539533,0.00035202721],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010684931,0.00062686915,0.0018046966,0.0005599767,0.00013311899,0.0000318383,0.0018336286,0.00094849814,0.000014496132],"category_scores_gemma":[0.016801402,0.0004981777,0.00023358854,0.00057814317,0.0021452266,0.0006304063,0.00032167684,0.0012281695,0.0000028478937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010633736,0.00027478635,0.0007120861,0.00091327867,0.00065106456,0.00025816515,0.014876529,0.00013779696,0.0017005833,0.0013039261,0.9322969,0.045811556],"study_design_scores_gemma":[0.005711178,0.006838335,0.0010702894,0.0008981474,0.0010223215,0.00013846713,0.0013770219,0.0012266268,0.0004999239,0.0010694753,0.9794556,0.0006926107],"about_ca_topic_score_codex":0.009130621,"about_ca_topic_score_gemma":0.008145121,"teacher_disagreement_score":0.061888263,"about_ca_system_score_codex":0.00014064371,"about_ca_system_score_gemma":0.0043248925,"threshold_uncertainty_score":0.999747},"labels":[],"label_agreement":null},{"id":"W2141386220","doi":"10.1117/12.811733","title":"Influence of nuclei segmentation on breast cancer malignancy classification","year":2009,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Malignancy; Pattern recognition (psychology); Breast cancer; Feature extraction; Support vector machine; Perceptron; Cancer; Artificial neural network; Machine learning; Medicine; Pathology; Internal medicine","score_opus":0.011867077775716202,"score_gpt":0.24381440329320664,"score_spread":0.23194732551749045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141386220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930672,0.000042416832,0.0005187183,0.0048639416,0.00018503194,0.00044294866,0.000033376786,0.00009762454,0.00074876414],"genre_scores_gemma":[0.9369408,0.00012526568,0.062355835,0.00020179819,0.00020065725,0.00010471617,0.00000218203,0.000022945003,0.00004581948],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978614,2.1488463e-8,0.0006413723,0.00042051554,0.00079601276,0.00028069553],"domain_scores_gemma":[0.9974122,0.00007361494,0.000614627,0.000093080474,0.0017251469,0.00008131456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039821333,0.00024268875,0.0002865617,0.0001286737,0.00007481879,0.00009087938,0.0012223485,0.00014478185,0.0000047579383],"category_scores_gemma":[0.00012708818,0.00021393408,0.0003160383,0.0005355368,0.00012365462,0.0011084761,0.00009147643,0.00022075874,0.0000013783899],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056134337,0.00009139849,0.00035292303,0.00014461929,0.00008456811,2.446996e-8,0.000194228,0.0014290817,0.60251266,0.39103785,0.0005651268,0.0035313647],"study_design_scores_gemma":[0.0015155461,0.0009890021,0.10498229,0.0011222413,0.00012518882,0.000027562206,0.00055473467,0.12995233,0.7524838,0.0071271914,0.0005116514,0.0006084923],"about_ca_topic_score_codex":0.000014792763,"about_ca_topic_score_gemma":1.2127282e-7,"teacher_disagreement_score":0.38391066,"about_ca_system_score_codex":0.00030742298,"about_ca_system_score_gemma":0.000048058264,"threshold_uncertainty_score":0.87239784},"labels":[],"label_agreement":null},{"id":"W2141817946","doi":"10.1155/2003/262918","title":"Risk Biomarker Assessment for Breast Cancer Progression: Replication Precision of Nuclear Morphometry","year":2003,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute; National Institutes of Health","keywords":"Feulgen stain; Pathology; Breast cancer; Histopathology; Stain; Nuclear DNA; Biology; Medicine; Cancer; Staining; Internal medicine","score_opus":0.0218421462256762,"score_gpt":0.32891936826515766,"score_spread":0.30707722203948146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141817946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07015672,0.00023639477,0.9270161,0.0008400753,0.00040268045,0.00041369736,0.00003146305,0.000076047545,0.00082681765],"genre_scores_gemma":[0.9183751,0.00007903786,0.081222296,0.00011467716,0.00004335992,0.00007290986,0.0000041723547,0.000017789213,0.000070674985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810153,0.00027219695,0.0003894143,0.00068982434,0.0002750169,0.0002720188],"domain_scores_gemma":[0.99819076,0.00017239331,0.0002861308,0.0010217743,0.00023477944,0.00009417026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001115924,0.00013857345,0.00025721692,0.00016713118,0.000118822936,0.000029548455,0.0003983063,0.00017442112,0.00012733137],"category_scores_gemma":[0.00017576221,0.00012013549,0.0001351941,0.0006028641,0.0001211787,0.000212987,0.00011140005,0.00016030087,0.000011259142],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016633191,0.00068961945,0.024233863,0.00012258772,0.00016139189,0.00004681207,0.00014622867,0.00022036565,0.09883353,0.120498165,0.0031781206,0.75170296],"study_design_scores_gemma":[0.0023584045,0.0010873234,0.17559545,0.00011098799,0.00029509637,0.00037879773,0.000062784464,0.71136445,0.04911272,0.027299603,0.031513665,0.0008207324],"about_ca_topic_score_codex":0.00001253824,"about_ca_topic_score_gemma":0.0000014886842,"teacher_disagreement_score":0.8482184,"about_ca_system_score_codex":0.00012906427,"about_ca_system_score_gemma":0.00009019279,"threshold_uncertainty_score":0.4898983},"labels":[],"label_agreement":null},{"id":"W2144045556","doi":"10.1148/radiographics.20.5.g00se311479","title":"Image Processing Algorithms for Digital Mammography: A Pictorial Essay","year":2000,"lang":"en","type":"review","venue":"Radiographics","topic":"AI in cancer detection","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute","keywords":"Visibility; Digital mammography; Medicine; Computer vision; Artificial intelligence; Histogram equalization; Mammography; Adaptive histogram equalization; Contrast (vision); Unsharp masking; Image processing; Histogram; Computer science; Enhanced Data Rates for GSM Evolution; Image (mathematics); Breast cancer; Optics","score_opus":0.034358444337614515,"score_gpt":0.31601471892358,"score_spread":0.2816562745859655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144045556","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.106842e-8,0.6715989,0.32430673,0.00001649394,0.0019898568,0.00096580404,0.00014450036,0.00041381642,0.0005638378],"genre_scores_gemma":[0.0000017941676,0.94518644,0.05151484,0.000021541491,0.0023889598,0.00058310706,0.00012010675,0.00011114451,0.000072044204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99662197,0.00008657558,0.000793454,0.0011993643,0.0005937281,0.00070491777],"domain_scores_gemma":[0.9978207,0.00026150132,0.00051776896,0.0010322432,0.00016356815,0.00020427053],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003799055,0.0007117147,0.0013997509,0.0013290829,0.0003426583,0.0015012384,0.0018786218,0.000589734,0.0000060301727],"category_scores_gemma":[0.000031950352,0.00065065274,0.001776262,0.0038603747,0.00020259043,0.0013460723,0.00014023943,0.00064113573,0.000012714011],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044035414,0.000038071994,9.349146e-7,0.0043148287,0.0001205613,0.000009252427,0.000053953325,5.0315566e-7,3.1711114e-8,0.00030414335,0.0008005835,0.99435276],"study_design_scores_gemma":[0.00028260465,0.00014196156,4.0132778e-7,0.0027851537,0.0002942479,0.00011028579,0.0000018596176,0.0017649884,3.0789215e-7,0.002154085,0.9917439,0.0007201709],"about_ca_topic_score_codex":0.000006878936,"about_ca_topic_score_gemma":0.0000021849535,"teacher_disagreement_score":0.99363256,"about_ca_system_score_codex":0.00018589289,"about_ca_system_score_gemma":0.0007419253,"threshold_uncertainty_score":0.99959445},"labels":[],"label_agreement":null},{"id":"W2144821277","doi":"10.1109/iembs.2005.1617227","title":"Effect of Adaptive-Neighborhood Contrast Enhancement on the Extraction of the Breast Skin-Line in Mammograms","year":2005,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hausdorff distance; Artificial intelligence; Computer science; Ground truth; Contrast (vision); Metric (unit); Pixel; Pattern recognition (psychology); Computer vision; Line (geometry); Noise (video); Mathematics; Image (mathematics)","score_opus":0.008659252030420849,"score_gpt":0.24981666687914444,"score_spread":0.2411574148487236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144821277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45044783,0.0000765482,0.5366317,0.0036355024,0.0006363412,0.0010113739,0.0000034391962,0.000049886457,0.007507356],"genre_scores_gemma":[0.9990727,0.00001055662,0.0005926019,0.00010219414,0.000068092726,0.000040020725,1.7291816e-7,0.0000050326316,0.00010863118],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881315,0.00022367117,0.00026656466,0.00020671998,0.00033740298,0.00015251286],"domain_scores_gemma":[0.99889815,0.00036881768,0.00018545652,0.00047725634,0.00005111721,0.000019217106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006871446,0.00011056155,0.00014490754,0.000052026986,0.000045418823,0.000015533979,0.00049135974,0.000042821335,0.000056890494],"category_scores_gemma":[0.000019898314,0.000056899597,0.00007724804,0.00039786252,0.00006273307,0.00017155579,0.00008158961,0.00015803112,0.000010298943],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002557684,0.00028764573,0.0010581093,0.000020030517,0.000032929172,4.758744e-7,0.00031026048,0.0022565895,0.025510084,0.015134446,0.0001549009,0.95497876],"study_design_scores_gemma":[0.0007468032,0.0011064153,0.012698959,0.0000977103,0.0000101689675,0.000017590852,0.000030648964,0.093452044,0.8912393,0.00025899522,0.00024288989,0.00009846212],"about_ca_topic_score_codex":0.00014681887,"about_ca_topic_score_gemma":0.00024700296,"teacher_disagreement_score":0.9548803,"about_ca_system_score_codex":0.00012404061,"about_ca_system_score_gemma":0.000028608752,"threshold_uncertainty_score":0.23202981},"labels":[],"label_agreement":null},{"id":"W2145375876","doi":"","title":"Mammography classification by an association rule-based classifier","year":2002,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; Preprocessor; Data mining; Classifier (UML); Artificial intelligence; Data pre-processing; Mammography; Architecture; Pattern recognition (psychology); Machine learning","score_opus":0.028830922098473547,"score_gpt":0.23366545046917223,"score_spread":0.20483452837069868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145375876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010608676,0.000058160836,0.9607667,0.005191993,0.0005973736,0.00015769989,0.00000380305,0.0006989662,0.021916647],"genre_scores_gemma":[0.9740763,0.000017053771,0.021248698,0.0013230329,0.00010108421,0.00005273437,0.000010204265,0.000013203686,0.0031577311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986239,0.000108147164,0.00019638291,0.00040464124,0.0004278207,0.00023909278],"domain_scores_gemma":[0.99903935,0.000066998575,0.0001596627,0.00052869256,0.00011105069,0.00009423981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028174848,0.000112035676,0.00008989077,0.00013847124,0.00014197257,0.00021548037,0.00044822937,0.0001362885,0.00022894835],"category_scores_gemma":[0.00002249205,0.000112208996,0.00006131972,0.00064777443,0.000018520637,0.0008753555,0.000023000233,0.00013394242,0.00021449171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000121834055,0.0006481736,0.046675406,0.00001798567,0.000054911765,0.0000019282854,0.00038437088,0.0001899258,0.034105673,0.015791928,0.38889763,0.5132199],"study_design_scores_gemma":[0.0004990842,0.0001526097,0.020340746,0.0000049389264,0.000009016159,0.0000012218117,0.000020558833,0.89087236,0.013263269,0.0013593818,0.07317121,0.00030561074],"about_ca_topic_score_codex":0.000030143632,"about_ca_topic_score_gemma":0.000018532524,"teacher_disagreement_score":0.9634676,"about_ca_system_score_codex":0.00032791702,"about_ca_system_score_gemma":0.000016055264,"threshold_uncertainty_score":0.457575},"labels":[],"label_agreement":null},{"id":"W2145677250","doi":"10.1109/iscas.2012.6271691","title":"Medical image classification using birth-and-death MCMC","year":2012,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Artificial intelligence; Mammography; Computer science; Pattern recognition (psychology); Gaussian; Metric (unit); Earth mover's distance; Breast cancer; Texture (cosmology); Contextual image classification; Image (mathematics); Computer vision; Cancer; Medicine","score_opus":0.05761997519683698,"score_gpt":0.31631331014976294,"score_spread":0.25869333495292596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145677250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044463266,0.000094613155,0.9479597,0.0010269965,0.0005086331,0.000051980296,1.6641279e-7,0.00017585108,0.0057187825],"genre_scores_gemma":[0.89924663,0.000020767822,0.10003893,0.00029768134,0.00022227663,0.000004322246,1.9782375e-7,0.000005236142,0.00016395641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999197,0.00003775811,0.00011498113,0.00016801302,0.0002926396,0.0001896137],"domain_scores_gemma":[0.99949384,0.00004126261,0.00003949245,0.00025050613,0.000030278881,0.00014461868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038401576,0.000061448474,0.000060237315,0.000052972333,0.000081700055,0.0000590891,0.00022674935,0.00006224803,0.00011530012],"category_scores_gemma":[0.00004129964,0.00005212844,0.00001756584,0.00015928726,0.000028785114,0.00081886054,0.00013057282,0.00009031964,0.00006284886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000101689675,0.00015536931,0.04733103,0.000050281706,0.000029887702,0.0000053428776,0.0014393006,0.000006553917,0.052407492,0.41316468,0.0025348382,0.48286504],"study_design_scores_gemma":[0.000389082,0.000051888434,0.08505899,0.00002384613,0.000009579247,0.00021062298,0.0000781242,0.8720568,0.01928151,0.0028353,0.019664718,0.0003395787],"about_ca_topic_score_codex":0.000052539646,"about_ca_topic_score_gemma":0.00000385811,"teacher_disagreement_score":0.8720502,"about_ca_system_score_codex":0.00007382139,"about_ca_system_score_gemma":0.000046779784,"threshold_uncertainty_score":0.2125736},"labels":[],"label_agreement":null},{"id":"W2148580193","doi":"10.1186/1746-1596-8-s1-s10","title":"Telepathology consultation in China using whole slide image and an internet based platform","year":2013,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Telepathology; The Internet; Pathology; Medicine; Computer science; China; Medical physics; World Wide Web; Telemedicine; Geography","score_opus":0.014679318562298411,"score_gpt":0.26752168111639435,"score_spread":0.2528423625540959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148580193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6750606,0.000048167218,0.32388982,0.0003334798,0.00026221355,0.00022513223,0.0000030759636,0.000067762805,0.00010975459],"genre_scores_gemma":[0.9430209,0.000008003027,0.056353636,0.000453561,0.000041954678,0.00009206153,0.000009467867,0.000011629578,0.000008823963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986935,0.000165604,0.00026518592,0.00047405472,0.0000891125,0.00031249836],"domain_scores_gemma":[0.9986955,0.00072433986,0.00011187689,0.00032518088,0.00006379489,0.00007932314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029436653,0.000146768,0.00020275825,0.00024263417,0.000050397524,0.00008304118,0.00028448127,0.00013880951,0.000026085272],"category_scores_gemma":[0.0009185514,0.00015071219,0.000018604369,0.00024069645,0.0001645149,0.00085419195,0.00013157389,0.000197893,0.000061224346],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082148996,0.000813482,0.24485466,0.00016060151,0.000025998821,0.0038720851,0.021082781,0.0036801884,0.20894632,0.011626064,0.00087066414,0.503985],"study_design_scores_gemma":[0.0012818765,0.00045520352,0.47635636,0.000041406416,0.000008609954,0.000532779,0.00010316555,0.5014221,0.007192696,0.012240831,0.0000679802,0.000296956],"about_ca_topic_score_codex":0.00047780457,"about_ca_topic_score_gemma":0.00014695099,"teacher_disagreement_score":0.50368804,"about_ca_system_score_codex":0.00009022502,"about_ca_system_score_gemma":0.000055565033,"threshold_uncertainty_score":0.6145865},"labels":[],"label_agreement":null},{"id":"W2149152304","doi":"10.1109/42.974917","title":"Detection of breast masses in mammograms by density slicing and texture flow-field analysis","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Artificial intelligence; Receiver operating characteristic; Mammography; Pattern recognition (psychology); Computer science; Pixel; False positive paradox; Digital mammography; Computer vision; Medicine; Breast cancer; Cancer","score_opus":0.004700363833605204,"score_gpt":0.23580450238668865,"score_spread":0.23110413855308345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149152304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09433789,0.00007153792,0.9036006,0.0014889248,0.0002884823,0.000069396825,0.0000020988489,0.00008660588,0.00005448471],"genre_scores_gemma":[0.9974078,0.00014182525,0.0020477604,0.00034068988,0.000027957034,0.0000105885565,4.7364296e-7,0.0000073972064,0.000015515974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857795,0.00008457652,0.00027951272,0.00036433656,0.00046677375,0.0002268428],"domain_scores_gemma":[0.99928737,0.00018469049,0.00006731877,0.00026929844,0.00005146396,0.00013988199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034881325,0.00012828753,0.00021914658,0.00041689616,0.000116586714,0.00005248802,0.00022191387,0.00009945754,0.000052094747],"category_scores_gemma":[0.000017881524,0.0001266864,0.00009073605,0.0015782325,0.00007054696,0.00037277816,0.0000047825088,0.0004417171,0.0000020081534],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002468067,0.000077595265,0.003744601,0.000013175599,0.00005810487,0.00002195474,0.0001959354,0.0014375071,0.0068456437,0.0000025016275,0.000021129743,0.9875572],"study_design_scores_gemma":[0.00048782534,0.000055422803,0.004934932,0.000080203616,0.00011192469,0.0002756261,0.00012630099,0.9474827,0.04601764,0.00010559053,0.00012460502,0.00019722492],"about_ca_topic_score_codex":0.001193632,"about_ca_topic_score_gemma":0.0015307805,"teacher_disagreement_score":0.98735994,"about_ca_system_score_codex":0.00008727367,"about_ca_system_score_gemma":0.000032717606,"threshold_uncertainty_score":0.5166122},"labels":[],"label_agreement":null},{"id":"W2149947933","doi":"10.1109/iembs.2004.1403474","title":"The application of Efron's bootstrap methods in validating feature classification using artificial neural networks for the analysis of mammographic masses","year":2005,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Overfitting; Computer science; Artificial neural network; Feature (linguistics); Artificial intelligence; Receiver operating characteristic; Generalization; Resampling; Pattern recognition (psychology); Machine learning; Mammography; Benchmark (surveying); Data mining; Mathematics","score_opus":0.08321408348523507,"score_gpt":0.3952794966294384,"score_spread":0.31206541314420333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149947933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015810132,0.00023857459,0.98206085,0.0013757483,0.00011143519,0.00034913796,0.0000011876482,0.000025831469,0.00002713045],"genre_scores_gemma":[0.7570486,0.00001603436,0.24277455,0.000029394923,0.000068525995,0.000051941744,0.0000020134837,0.000004478017,0.000004484817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988707,0.00018290688,0.0003757401,0.00024135162,0.0001707102,0.00015860357],"domain_scores_gemma":[0.99793315,0.0009942371,0.00040357048,0.0005288831,0.00012473595,0.000015449223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014358967,0.00008644629,0.00016259337,0.00020497988,0.0001790829,0.00006894032,0.00051495404,0.000074268566,0.000001099533],"category_scores_gemma":[0.00004506903,0.000055222386,0.000147228,0.002383384,0.000080517224,0.00021072477,0.000050984163,0.00012453902,4.1100485e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013389981,0.000014535196,0.0018934517,0.0000050400326,0.00008409213,9.502928e-9,0.00008286907,0.41228998,0.013178969,0.012500675,0.000009979724,0.55992705],"study_design_scores_gemma":[0.00004935349,0.0000148855615,0.018435083,0.0000028885524,0.00013500513,4.2922883e-7,0.00013421592,0.9722385,0.007933847,0.0007544766,0.00024635208,0.00005497055],"about_ca_topic_score_codex":0.00012607405,"about_ca_topic_score_gemma":0.00073571556,"teacher_disagreement_score":0.7412385,"about_ca_system_score_codex":0.000052647778,"about_ca_system_score_gemma":0.000022820152,"threshold_uncertainty_score":0.22519036},"labels":[],"label_agreement":null},{"id":"W2150196286","doi":"10.1093/bib/bbr008","title":"Caveats and pitfalls of ROC analysis in clinical microarray research (and how to avoid them)","year":2011,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Receiver operating characteristic; Ranking (information retrieval); Metric (unit); Gold standard (test); Confidence interval; Statistics; Performance metric; Computer science; Machine learning; Mathematics; Engineering","score_opus":0.1267116161059898,"score_gpt":0.3407471400724225,"score_spread":0.21403552396643272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150196286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84201306,0.00006915391,0.1544905,0.0012915854,0.000087404274,0.00034337663,0.000003474871,0.000029015155,0.001672405],"genre_scores_gemma":[0.86374396,0.00014771227,0.13571434,0.00031392885,0.000010665493,0.000010327924,4.1647738e-7,0.000004872081,0.000053762575],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99860096,0.00007983766,0.00052777416,0.00022015089,0.0002902686,0.00028102807],"domain_scores_gemma":[0.99894446,0.00027050095,0.00014712986,0.0004182032,0.00012292729,0.00009678256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023667975,0.000098937686,0.00028782472,0.00060558843,0.000048828348,0.000091191774,0.0004451882,0.00011310235,0.0000035811358],"category_scores_gemma":[0.0002737991,0.00009327553,0.000038728063,0.0016808735,0.00017701564,0.000466071,0.00044663937,0.00028953183,0.0000062404943],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018505711,0.00036388205,0.6453714,0.0006282496,0.0002475155,0.000019157816,0.10416987,0.00008867734,0.00068488007,0.010537037,0.0027032257,0.23500106],"study_design_scores_gemma":[0.001585763,0.00089033524,0.874513,0.00033232567,0.00004186556,0.000039616792,0.0013839598,0.099521525,0.009044178,0.009913795,0.0021242443,0.0006094176],"about_ca_topic_score_codex":0.0004794655,"about_ca_topic_score_gemma":0.00040675307,"teacher_disagreement_score":0.23439164,"about_ca_system_score_codex":0.000056918445,"about_ca_system_score_gemma":0.000055773093,"threshold_uncertainty_score":0.38036656},"labels":[],"label_agreement":null},{"id":"W2150761096","doi":"10.1016/s0221-0363(08)76059-1","title":"Compression des images medicales avec perte : le point sur le projet Canadien","year":2008,"lang":"fr","type":"article","venue":"Journal de Radiologie","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.07335944407648204,"score_gpt":0.26894642641801836,"score_spread":0.19558698234153632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150761096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4685556,0.04947881,0.40202072,0.0695861,0.0071971714,0.00033479082,0.00001618186,0.00033911187,0.002471493],"genre_scores_gemma":[0.94031453,0.016157752,0.03829285,0.0005862942,0.0015991093,0.000014173045,7.3172725e-7,0.000044585096,0.0029899962],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969091,0.00076339446,0.0005395523,0.00043061873,0.00041416002,0.00094319275],"domain_scores_gemma":[0.9980091,0.00038494196,0.0003351482,0.0004043314,0.00030577945,0.0005607027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001375378,0.00027769737,0.0004191464,0.00016073088,0.0012431041,0.00018243796,0.0010292651,0.00028387984,0.00007119717],"category_scores_gemma":[0.000707099,0.00023840678,0.00020639245,0.0003144321,0.0010356765,0.0017154713,0.00023573726,0.0011118029,0.000023731069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012232998,0.00042158132,0.038275667,0.00013935103,0.00023008735,0.011699763,0.009982914,0.005387815,0.0052206656,0.001070766,0.27206758,0.6553815],"study_design_scores_gemma":[0.0033595134,0.0020980907,0.387771,0.0014874398,0.00008187907,0.22482952,0.00078953773,0.1661475,0.012571301,0.024217246,0.17530335,0.0013435901],"about_ca_topic_score_codex":0.010601859,"about_ca_topic_score_gemma":0.0018883317,"teacher_disagreement_score":0.6540379,"about_ca_system_score_codex":0.0016703391,"about_ca_system_score_gemma":0.0035418954,"threshold_uncertainty_score":0.99598664},"labels":[],"label_agreement":null},{"id":"W2154095192","doi":"10.1109/memea.2011.5966645","title":"Rényi entropy of angular spread for detection of architectural distortion in prior mammograms","year":2011,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Receiver operating characteristic; Artificial intelligence; Pattern recognition (psychology); Linear discriminant analysis; Entropy (arrow of time); Feature extraction; False positive paradox; Mathematics; Computer science; Histogram; Statistics; Physics; Image (mathematics)","score_opus":0.029646542190552735,"score_gpt":0.2456003965503003,"score_spread":0.21595385435974757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154095192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4388417,0.000029241246,0.5604714,0.000018117287,0.00025674852,0.0002472461,0.0000014155743,0.00004392143,0.00009016606],"genre_scores_gemma":[0.9139286,0.0000035116184,0.08590863,0.000009959443,0.000030506162,0.000047738424,0.0000014259393,0.000007764701,0.000061811],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896896,0.00004325534,0.0003501604,0.0002655907,0.00018460718,0.00018739862],"domain_scores_gemma":[0.999244,0.000043958997,0.00020223344,0.00038486172,0.000088089335,0.000036901445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022311478,0.00010302598,0.00017260622,0.00019406767,0.000028452037,0.000008986905,0.0003054153,0.00006564063,0.000013831771],"category_scores_gemma":[0.000041447987,0.00009434608,0.00012265681,0.00034907123,0.00007855032,0.00022803275,0.00006433464,0.00007378616,0.0000024453886],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026687136,0.0001744343,0.0046077417,0.00013375665,0.000031616262,6.573148e-7,0.0031856385,0.000115580195,0.21756104,0.0043997704,0.000009200562,0.7695137],"study_design_scores_gemma":[0.0007937922,0.00073217833,0.045693364,0.00004095145,0.000016015736,0.0000138321575,0.00006736443,0.00726823,0.9358891,0.008913079,0.0003813201,0.00019072484],"about_ca_topic_score_codex":0.0013479331,"about_ca_topic_score_gemma":0.0017028047,"teacher_disagreement_score":0.769323,"about_ca_system_score_codex":0.00010426279,"about_ca_system_score_gemma":0.000026887941,"threshold_uncertainty_score":0.38473213},"labels":[],"label_agreement":null},{"id":"W2154273070","doi":"10.1016/j.compbiomed.2013.09.001","title":"Estimation of the breast skin-line in mammograms using multidirectional Gabor filters","year":2013,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Ground truth; Gabor filter; Thresholding; Computer science; Computer vision; Pattern recognition (psychology); Segmentation; Robustness (evolution); Hausdorff distance; Mammography; Feature extraction; Image (mathematics)","score_opus":0.01674175734021792,"score_gpt":0.2980715417651756,"score_spread":0.28132978442495765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154273070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57788765,0.00015423128,0.41860494,0.0018898915,0.0012426155,0.00017316353,6.8835584e-7,0.00001643586,0.000030409756],"genre_scores_gemma":[0.9710983,0.000023775827,0.028524704,0.00026066555,0.000075477226,0.00000874663,0.00000175236,0.0000023974444,0.0000041589738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993086,0.00009087697,0.00021900034,0.0001948861,0.00006223777,0.00012442902],"domain_scores_gemma":[0.99955595,0.00013488752,0.000088873014,0.0001635806,0.00003095303,0.000025785585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022751029,0.0000762268,0.00014666251,0.00013880318,0.00003793917,0.000004514199,0.0002097905,0.00006630721,0.0000059858826],"category_scores_gemma":[0.000026953667,0.00005128285,0.0000149996495,0.00036551515,0.00024594736,0.00011089545,0.00010981286,0.00012115397,6.237624e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021924843,0.0000646132,0.0807827,0.00003830361,0.000016239246,0.0000018638096,0.0011607246,0.011987148,0.0047886833,0.0029393998,0.00023532337,0.8979631],"study_design_scores_gemma":[0.0006292894,0.000080765596,0.21890903,0.00015436288,0.0000022856198,0.00008563758,0.000022722636,0.7760258,0.00039849593,0.0035959268,0.000039280487,0.00005646264],"about_ca_topic_score_codex":0.0007911163,"about_ca_topic_score_gemma":0.000057082692,"teacher_disagreement_score":0.8979066,"about_ca_system_score_codex":0.00005540798,"about_ca_system_score_gemma":0.000022371954,"threshold_uncertainty_score":0.20912538},"labels":[],"label_agreement":null},{"id":"W2158259943","doi":"10.5812/iranjradiol.11656","title":"Ensemble Supervised Classification Method Using the Regions of Interest and Grey Level Co-Occurrence Matrices Features for Mammograms Data","year":2015,"lang":"en","type":"article","venue":"Iranian Journal of Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Sandia National Laboratories; Isfahan University of Medical Sciences; University of South Florida; Massachusetts General Hospital","keywords":"Pattern recognition (psychology); Artificial intelligence; Weighted voting; Feature extraction; Medicine; Mammography; Breast cancer; Grey level; Ensemble learning; Computer science; Cancer; Voting; Pixel","score_opus":0.446710032112323,"score_gpt":0.41368233767431,"score_spread":0.03302769443801301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158259943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05156844,0.001301915,0.944396,0.0018624852,0.0006612778,0.00014118623,0.000048123045,0.000008532546,0.00001200421],"genre_scores_gemma":[0.7141465,0.000115781004,0.28545833,0.000079437195,0.00018156957,0.000002069149,0.0000054756238,0.0000055577825,0.000005267673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988513,0.00032499668,0.00035751564,0.00020546562,0.00011275468,0.00014796879],"domain_scores_gemma":[0.99813485,0.00044869506,0.0005371293,0.0005011561,0.0002948665,0.00008328436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016102754,0.0000921898,0.0002389684,0.00013648429,0.00008579508,0.000058228066,0.0012173807,0.00007788017,6.2634103e-7],"category_scores_gemma":[0.0002813513,0.0000637129,0.00004655902,0.00020666188,0.00014044352,0.00048171743,0.00010849773,0.00019619403,2.180326e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011398346,0.00019501772,0.012665555,0.0002510365,0.0005287078,0.00004654232,0.0128135085,0.001194551,0.07187158,0.02371794,0.06331628,0.81225944],"study_design_scores_gemma":[0.010270373,0.006857879,0.05023907,0.0006221182,0.00076241203,0.056976337,0.007996621,0.72822094,0.017543288,0.06847318,0.05071509,0.0013227249],"about_ca_topic_score_codex":0.000024897025,"about_ca_topic_score_gemma":0.00004344706,"teacher_disagreement_score":0.81093675,"about_ca_system_score_codex":0.000049235314,"about_ca_system_score_gemma":0.00018158028,"threshold_uncertainty_score":0.25981367},"labels":[],"label_agreement":null},{"id":"W2158538525","doi":"10.1109/tmi.2007.908686","title":"Registered 3-D Ultrasound and Digital Stereotactic Mammography for Breast Biopsy Guidance","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials","funders":"","keywords":"Mammography; Ultrasound; Medicine; Biopsy; Stereotactic biopsy; Radiology; Digital mammography; Breast biopsy; 3D ultrasound; Breast cancer; Nuclear medicine; Cancer","score_opus":0.01665622580280768,"score_gpt":0.25515637687805026,"score_spread":0.23850015107524258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158538525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012108062,0.00014653135,0.9840869,0.001890639,0.0010098353,0.00020802498,0.00003658039,0.0002732705,0.00024020053],"genre_scores_gemma":[0.98979104,0.000096325646,0.009277863,0.0004884971,0.000106533334,0.00006477858,9.327406e-7,0.000021534266,0.00015247359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998257,0.00003450368,0.000298081,0.00054512953,0.0005218778,0.00034340625],"domain_scores_gemma":[0.9987174,0.0003692011,0.000087590706,0.0004669612,0.000083604464,0.0002751893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020282749,0.000188414,0.00017924521,0.00020580506,0.00040785177,0.00018984261,0.0004207701,0.000069150374,0.000024229299],"category_scores_gemma":[0.00003310654,0.00018348193,0.00012237084,0.00042859354,0.00033488753,0.0010333237,0.0000040281784,0.00028551323,0.000011349933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012246709,0.00030258318,0.0019055185,0.00010655017,0.000114330986,0.00016081388,0.00082732446,0.000088896886,0.0020874036,0.00016137733,0.001383779,0.99273896],"study_design_scores_gemma":[0.023489656,0.0017025189,0.06104324,0.0027452542,0.0004164308,0.18816179,0.0009086643,0.6138004,0.050654784,0.012345968,0.03770538,0.0070258914],"about_ca_topic_score_codex":0.000023575072,"about_ca_topic_score_gemma":0.000006057979,"teacher_disagreement_score":0.98571306,"about_ca_system_score_codex":0.00007029739,"about_ca_system_score_gemma":0.00009128999,"threshold_uncertainty_score":0.7482176},"labels":[],"label_agreement":null},{"id":"W2159013813","doi":"10.1007/s10278-013-9587-6","title":"Automatic Detection of the Nipple in Screen-Film and Full-field Digital Mammograms Using a Novel Hessian-Based Method","year":2013,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Universidade de São Paulo","keywords":"Hessian matrix; Artificial intelligence; Mammography; Digital mammography; Computer vision; Computer science; Pixel; Distortion (music); Pattern recognition (psychology); Mathematics; Breast cancer; Medicine","score_opus":0.013412632597088575,"score_gpt":0.25883200186101674,"score_spread":0.24541936926392816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159013813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3774129,0.00005694753,0.6217397,0.0003927408,0.00017266745,0.00008862503,0.0000012489795,0.000014148583,0.0001210736],"genre_scores_gemma":[0.9573596,6.0747243e-7,0.042496383,0.00008322841,0.000044044613,0.0000019096578,8.6371834e-8,0.00001009165,0.0000040359523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987887,0.00003107376,0.00049218815,0.00015330079,0.00034251186,0.00019219662],"domain_scores_gemma":[0.9988389,0.00020857056,0.0005258016,0.00021615512,0.00014358014,0.0000669841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026999824,0.00012217257,0.00020456953,0.00023496186,0.000060167808,0.00076695526,0.00037904462,0.000034665274,0.0000032752864],"category_scores_gemma":[0.00016998316,0.000091021684,0.000111654175,0.0005142435,0.000052934578,0.0035202582,0.00013496476,0.00023911466,8.414017e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016172804,0.000104994324,0.024452832,0.000047641548,0.000025133306,0.0000064636774,0.00024589853,0.0021345557,0.056104288,0.00003388299,0.000015081803,0.9168131],"study_design_scores_gemma":[0.0006464102,0.00013199284,0.008562878,0.0003037594,0.000012139025,0.0006980418,0.00016285504,0.9678916,0.019748041,0.0016600164,0.000041559404,0.00014075704],"about_ca_topic_score_codex":0.000066158296,"about_ca_topic_score_gemma":0.000009109397,"teacher_disagreement_score":0.965757,"about_ca_system_score_codex":0.0001127323,"about_ca_system_score_gemma":0.00009424376,"threshold_uncertainty_score":0.7395767},"labels":[],"label_agreement":null},{"id":"W2160564923","doi":"10.1109/biocas.2009.5372040","title":"Uniform illumination constraint enhancement and utility weighted voting fusion for ultrasonic breast lesion segmentation","year":2009,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Computer vision; Image segmentation; Speckle pattern; Pattern recognition (psychology); Ultrasound; Breast cancer; Speckle noise; Constraint (computer-aided design); Mathematics; Medicine; Radiology; Cancer","score_opus":0.017768869885344152,"score_gpt":0.2680849155177384,"score_spread":0.25031604563239424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160564923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12825935,0.000018079687,0.86900073,0.0010814203,0.00017841836,0.00047558095,0.0000027948633,0.00012714288,0.0008564906],"genre_scores_gemma":[0.9178264,0.000030438054,0.08182635,0.00016227362,0.000039500123,0.000018750616,0.000012397557,0.0000033084202,0.00008055286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989702,0.000030393318,0.00023748125,0.00035828998,0.00021182213,0.00019178778],"domain_scores_gemma":[0.9994597,0.00006664795,0.00012403865,0.00016042717,0.00013346951,0.000055728997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041058692,0.00011468859,0.00009665939,0.000077387915,0.00022860596,0.00009238613,0.00013129102,0.00005755188,0.000024413986],"category_scores_gemma":[0.000013252052,0.000104805426,0.00003097234,0.00019035283,0.00003496421,0.0005964608,0.000033887154,0.00005974331,0.0000031536456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018133254,0.000042286192,0.000092325135,0.0000150280575,0.0000033887582,2.1313943e-7,0.00025903352,0.0000054414772,0.046686724,0.009057275,0.00006130626,0.94375885],"study_design_scores_gemma":[0.0011899788,0.00059566787,0.02233781,0.00006724405,0.000013582239,0.00005910669,0.00028993617,0.6629485,0.30664104,0.005222556,0.00034751627,0.00028705577],"about_ca_topic_score_codex":0.000019957348,"about_ca_topic_score_gemma":0.000022310523,"teacher_disagreement_score":0.9434718,"about_ca_system_score_codex":0.00019138056,"about_ca_system_score_gemma":0.000042362633,"threshold_uncertainty_score":0.4273841},"labels":[],"label_agreement":null},{"id":"W2161791887","doi":"10.1109/tmi.2010.2076828","title":"Detection of Architectural Distortion in Prior Mammograms","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Health Research Board","keywords":"Artificial intelligence; Pattern recognition (psychology); Linear discriminant analysis; Receiver operating characteristic; Fractal dimension; Mathematics; Feature extraction; Entropy (arrow of time); False positive paradox; Computer science; Computer vision; Fractal; Statistics; Physics","score_opus":0.006442996723981957,"score_gpt":0.24913015602490904,"score_spread":0.24268715930092707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161791887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2248511,0.000011076911,0.771951,0.0006714109,0.0022072508,0.00010741845,7.797801e-7,0.0001271856,0.00007275791],"genre_scores_gemma":[0.9955639,0.0000074332584,0.0041796947,0.00011328402,0.000069202986,0.00003714737,2.4675472e-7,0.000010809864,0.00001823575],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849355,0.00006345913,0.00032405666,0.00031710844,0.0005682557,0.00023358656],"domain_scores_gemma":[0.9992773,0.00011615688,0.00008107684,0.0003493281,0.00004405146,0.00013208708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039624108,0.000118298885,0.000139621,0.00031209644,0.00009798305,0.000031612875,0.00038137572,0.00008684266,0.000050391758],"category_scores_gemma":[0.00003410078,0.000114471804,0.00008559101,0.0005651513,0.00014618154,0.00032919814,0.0000033330355,0.00086527073,0.00001186619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016031641,0.00007759752,0.00010916875,0.000011880577,0.000003966529,0.000007283774,0.00021451815,0.00039017724,0.040003333,0.000022154265,0.0000015581012,0.9591423],"study_design_scores_gemma":[0.0012476799,0.00014367561,0.008093824,0.00012867188,0.000015567146,0.0002957489,0.0000553906,0.43310842,0.5549779,0.0010905209,0.00049998995,0.0003426316],"about_ca_topic_score_codex":0.00029080152,"about_ca_topic_score_gemma":0.0013333956,"teacher_disagreement_score":0.9587997,"about_ca_system_score_codex":0.00009222453,"about_ca_system_score_gemma":0.00007577271,"threshold_uncertainty_score":0.46680248},"labels":[],"label_agreement":null},{"id":"W2164191481","doi":"10.6000/1929-2279.2014.03.04.4","title":"Breast Cancer – Diagnosis and Treatment Prolonging Life: A Review","year":2014,"lang":"en","type":"review","venue":"Journal of cancer research updates","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Medicine; Trastuzumab; Breast cancer; Cancer; Monoclonal antibody; Metastatic breast cancer; Oncology; Internal medicine; Immunology; Antibody","score_opus":0.13012100331948567,"score_gpt":0.4757609813088356,"score_spread":0.3456399779893499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164191481","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051071843,0.99141884,0.00028733254,0.0065188142,0.0006391609,0.0010035655,0.000059591854,0.000027079226,0.000040534418],"genre_scores_gemma":[0.000014782197,0.995579,0.00047564978,0.0001823563,0.0015360159,0.0020386283,0.0000017272706,0.000052071857,0.00011974132],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952888,0.0010125871,0.0011369719,0.0005854136,0.0013020184,0.00067421596],"domain_scores_gemma":[0.9959798,0.0006952414,0.0012466984,0.000663487,0.00092455634,0.00049021776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028815973,0.00044916433,0.0022401684,0.0007304348,0.00023863431,0.00037291914,0.0014837875,0.000188481,0.0001826234],"category_scores_gemma":[0.00016014485,0.0002931308,0.00048908865,0.0012996398,0.00016486824,0.000666271,0.0004149551,0.0011055064,0.000017592998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009919224,0.000037400765,0.000066628425,0.017019829,0.00039803988,0.000028420518,0.000033464104,0.0000023325224,1.52809e-7,0.0000448716,0.020847255,0.9615117],"study_design_scores_gemma":[0.00022766618,0.00029486217,0.000019043657,0.097660765,0.00041655707,0.0004182203,0.000002100965,0.000046669153,0.000006321463,0.00007308663,0.90059507,0.00023963767],"about_ca_topic_score_codex":0.0003740867,"about_ca_topic_score_gemma":0.00016936433,"teacher_disagreement_score":0.96127206,"about_ca_system_score_codex":0.001782207,"about_ca_system_score_gemma":0.003073927,"threshold_uncertainty_score":0.9999521},"labels":[],"label_agreement":null},{"id":"W2164741834","doi":"10.1016/j.eururo.2008.05.024","title":"Prostate Cancer Diagnosis: Importance of Individualized Risk Stratification Models over PSA Alone","year":2008,"lang":"en","type":"letter","venue":"European Urology","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Feature selection; Segmentation; Support vector machine; Feature extraction; Medicine; Preprocessor; Naive Bayes classifier; Computer science","score_opus":0.025994762095703273,"score_gpt":0.25124793399435535,"score_spread":0.22525317189865207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164741834","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05617639,0.020559687,0.27332973,0.5995329,0.012363708,0.0054381727,0.002476609,0.0025094221,0.027613409],"genre_scores_gemma":[0.26718006,0.026955754,0.017082881,0.67675,0.006916284,0.0018558707,0.0005781667,0.0005435043,0.0021374838],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568176,0.0012431142,0.00084737357,0.0011565465,0.0005450109,0.0005262088],"domain_scores_gemma":[0.9964898,0.00021478164,0.0015471213,0.0014959185,0.00018981774,0.00006256568],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052214175,0.0004262008,0.00055014575,0.0002821686,0.00014079176,0.000059892114,0.0015608981,0.0003672877,0.0000832648],"category_scores_gemma":[0.000059075155,0.00043324885,0.00015476604,0.00043752772,0.00024167712,0.00046519304,0.00033324055,0.001602614,0.00006206822],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029779325,0.00004556308,0.0074954126,0.00006541462,0.00016820089,0.00032970522,0.001274685,0.0026922356,0.000029537106,0.00017642467,0.9765333,0.011159741],"study_design_scores_gemma":[0.0014868423,0.00054123276,0.020057553,0.000060723945,0.00018953475,0.00010463406,0.0000036008996,0.012426,0.00042284562,0.0043314365,0.95938426,0.0009913219],"about_ca_topic_score_codex":0.00023354581,"about_ca_topic_score_gemma":0.000045316167,"teacher_disagreement_score":0.25624683,"about_ca_system_score_codex":0.00011627855,"about_ca_system_score_gemma":0.00019983281,"threshold_uncertainty_score":0.99981195},"labels":[],"label_agreement":null},{"id":"W2166134037","doi":"10.1109/nafips.2004.1336329","title":"A fuzzy approach to segmenting the breast region in mammograms","year":2004,"lang":"en","type":"article","venue":"IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04.","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Thresholding; Artificial intelligence; Segmentation; Computer science; Pixel; Image segmentation; Pattern recognition (psychology); Computer vision; Fuzzy logic; Image (mathematics)","score_opus":0.011792257961767187,"score_gpt":0.22704875014040865,"score_spread":0.21525649217864146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166134037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3459865,0.00077941123,0.5808359,0.014973463,0.003571617,0.0034493946,0.000039787454,0.001103177,0.049260788],"genre_scores_gemma":[0.97991335,0.000005509461,0.018793838,0.00091318914,0.00019582495,0.00009097882,0.0000032350306,0.000019430461,0.00006464735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712324,0.00012783082,0.00096150924,0.00033645474,0.0008695075,0.00058142655],"domain_scores_gemma":[0.9976804,0.000065886554,0.0008345494,0.000765565,0.0005591303,0.00009445264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015651024,0.00028898823,0.00026629027,0.0003226965,0.00069151836,0.0004474293,0.0019069936,0.00014076752,2.6976267e-7],"category_scores_gemma":[0.00021102784,0.00020289824,0.000118685115,0.0026032864,0.00014017246,0.0034499017,0.00031161867,0.00043746628,0.000022789593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014309173,0.0003137708,0.003923997,0.0009804836,0.000061417944,0.000002662064,0.117905326,0.52911365,0.0004836867,0.003109402,0.004803331,0.33915916],"study_design_scores_gemma":[0.032317195,0.0029873322,0.11593833,0.040206328,0.00077921874,0.011422661,0.131284,0.24759299,0.15249987,0.1915492,0.05796906,0.015453841],"about_ca_topic_score_codex":0.0004668375,"about_ca_topic_score_gemma":0.000043978678,"teacher_disagreement_score":0.63392687,"about_ca_system_score_codex":0.00039998128,"about_ca_system_score_gemma":0.0003989632,"threshold_uncertainty_score":0.827395},"labels":[],"label_agreement":null},{"id":"W2168164949","doi":"10.1109/iembs.2009.5334517","title":"Detection of architectural distortion in prior mammograms of interval-cancer cases with neural networks","year":2009,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Receiver operating characteristic; Linear discriminant analysis; Mammography; Artificial intelligence; Pattern recognition (psychology); Fractal dimension; Artificial neural network; Breast cancer; Computer science; False positive paradox; Mathematics; Fractal; Statistics; Medicine; Cancer","score_opus":0.012323520599533818,"score_gpt":0.24840324574743936,"score_spread":0.23607972514790554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168164949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.562636,0.00008600533,0.4368509,0.00008553579,0.00015389931,0.00010963176,3.3786966e-7,0.000042996006,0.000034651326],"genre_scores_gemma":[0.9975774,0.000009824385,0.0022864852,0.000047361264,0.000041810705,0.000012605439,4.7318088e-7,0.00000477005,0.000019244411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991008,0.000046742123,0.00027720176,0.00022913322,0.00018200735,0.00016410912],"domain_scores_gemma":[0.99944013,0.00003909647,0.00018049609,0.00024930062,0.000059793394,0.000031168154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000994112,0.00010384008,0.00016679773,0.00013665446,0.000024215056,0.000016579132,0.00021967184,0.000043328306,0.0000055306186],"category_scores_gemma":[0.000008790002,0.00008055693,0.000049865648,0.0005581325,0.00005210534,0.00028493785,0.00003551328,0.0001277178,1.8990148e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015111097,0.00004166881,0.0032196525,0.00001115147,0.0000061852284,0.000004001805,0.00020174793,0.034124237,0.0031161157,0.000054466782,0.000002485173,0.95906717],"study_design_scores_gemma":[0.0007147445,0.0023638508,0.31178918,0.00012502326,0.0000131927245,0.00012266469,0.000036305435,0.6079356,0.07637849,0.00028074672,0.000016758982,0.00022345688],"about_ca_topic_score_codex":0.0008959765,"about_ca_topic_score_gemma":0.0038400101,"teacher_disagreement_score":0.9588437,"about_ca_system_score_codex":0.00010557141,"about_ca_system_score_gemma":0.000017108225,"threshold_uncertainty_score":0.32850164},"labels":[],"label_agreement":null},{"id":"W2169512939","doi":"10.1007/s10278-009-9257-x","title":"Computer-Aided Detection of Architectural Distortion in Prior Mammograms of Interval Cancer","year":2010,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale","keywords":"Artificial intelligence; Linear discriminant analysis; Mammography; Receiver operating characteristic; Pattern recognition (psychology); Support vector machine; False positive paradox; Breast cancer; Computer science; Mathematics; Statistics; Medicine; Cancer","score_opus":0.008164929506778823,"score_gpt":0.2534515078423702,"score_spread":0.24528657833559137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169512939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68297887,0.000060840906,0.31548712,0.00013777812,0.0012386693,0.000047512563,0.0000014620776,0.000011167741,0.000036581663],"genre_scores_gemma":[0.9933846,0.0000040709233,0.00640588,0.000013332843,0.00017784363,0.0000015166142,2.0867076e-7,0.000007951532,0.0000045815273],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987473,0.000024554342,0.0006346444,0.00013563053,0.00030869452,0.00014919853],"domain_scores_gemma":[0.99874276,0.00005788518,0.0007545325,0.0001732247,0.0002166031,0.000055004242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024487427,0.00010080664,0.00023633578,0.00033050138,0.000021243706,0.00009888345,0.0003931548,0.000029208753,0.0000020932064],"category_scores_gemma":[0.000048931277,0.00008997552,0.00014090023,0.0003405325,0.00008405872,0.0015024679,0.000109644985,0.00035750816,4.2759837e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044151537,0.000057308964,0.0234836,0.000030938536,0.000014512027,0.000007983282,0.00049985136,0.0004839769,0.07951588,0.000016236572,0.0000039262027,0.89584166],"study_design_scores_gemma":[0.0026159233,0.0010552646,0.3854104,0.0008400264,0.000040676303,0.0015629856,0.00013464042,0.15216638,0.45062414,0.0045945346,0.00046239034,0.0004926437],"about_ca_topic_score_codex":0.00008114915,"about_ca_topic_score_gemma":0.000116725845,"teacher_disagreement_score":0.89534897,"about_ca_system_score_codex":0.000117407304,"about_ca_system_score_gemma":0.000071389026,"threshold_uncertainty_score":0.3669095},"labels":[],"label_agreement":null},{"id":"W2169850289","doi":"10.1117/1.3099710","title":"Detection of microcalcifications in mammograms using error of prediction and statistical measures","year":2009,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"False positive paradox; Microcalcification; Artificial intelligence; Receiver operating characteristic; Pattern recognition (psychology); Mammography; Sensitivity (control systems); Support vector machine; Computer science; Pixel; Mathematics; Linear discriminant analysis; Feature (linguistics); Statistics; Breast cancer; Medicine","score_opus":0.013182714232517188,"score_gpt":0.27469790275070066,"score_spread":0.26151518851818345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169850289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23342869,0.0009062145,0.76534194,0.00017505811,0.00008026074,0.00004614805,6.89109e-7,0.000006393619,0.000014606957],"genre_scores_gemma":[0.9858969,0.00007517983,0.013975616,0.000013613979,0.000033658347,4.5422095e-7,1.326903e-7,0.0000034710895,9.676883e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898887,0.00006628631,0.00044912676,0.000105850915,0.00021770224,0.00017215729],"domain_scores_gemma":[0.9992593,0.000045034347,0.0003863477,0.00010570688,0.00017368619,0.000029916018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057353626,0.00006304735,0.00015184535,0.00028703452,0.00003612439,0.000020789459,0.00014265926,0.000025304356,7.250054e-7],"category_scores_gemma":[0.000048668557,0.000062024825,0.00003494402,0.0003495818,0.000043137265,0.0004180062,0.000013280594,0.00022733654,5.7515162e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059771726,0.00007724041,0.0029874444,0.000016419866,0.00001744531,0.0000028671213,0.00034128665,0.001337154,0.6887993,0.0015524917,0.000008917257,0.30479962],"study_design_scores_gemma":[0.0014097478,0.0011725656,0.096685044,0.0002465684,0.00007837741,0.0011855871,0.00021355592,0.5522905,0.31774643,0.028498149,0.00027511164,0.00019833907],"about_ca_topic_score_codex":0.00003583844,"about_ca_topic_score_gemma":0.00001768814,"teacher_disagreement_score":0.7524682,"about_ca_system_score_codex":0.00024996672,"about_ca_system_score_gemma":0.00016240332,"threshold_uncertainty_score":0.2529299},"labels":[],"label_agreement":null},{"id":"W2170048895","doi":"10.1002/cpe.3553","title":"A novel technique for detecting suspicious lesions in breast ultrasound images","year":2015,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Utah State University","keywords":"Computer science; Artificial intelligence; Thread (computing); Breast ultrasound; Pattern recognition (psychology); Segmentation; Computer vision; Feature selection; Support vector machine; Mammography; Breast cancer","score_opus":0.04326917197220428,"score_gpt":0.3473463849342993,"score_spread":0.30407721296209506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170048895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026448386,0.0005392189,0.9713776,0.0007401997,0.00027998787,0.00033127167,0.0000033543704,0.00006977253,0.00021021353],"genre_scores_gemma":[0.9206528,0.00007591097,0.07881901,0.00018640769,0.000038260918,0.00021453935,0.0000013000497,0.0000053659146,0.0000064138144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901766,0.000060276165,0.00022154406,0.0003788662,0.0001401859,0.00018144249],"domain_scores_gemma":[0.9986756,0.00074209477,0.0001493453,0.00012546775,0.00021145963,0.00009602064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047007998,0.000115227616,0.000117186486,0.000098352044,0.0001857879,0.00019742691,0.0001551812,0.000055959226,5.441338e-7],"category_scores_gemma":[0.00057824544,0.00011825654,0.00001524729,0.0003152411,0.00008725933,0.0017925726,0.00008588857,0.00013883619,9.309579e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019301396,0.00033166795,0.002250945,0.000116458454,0.000020721407,0.000020302728,0.06201275,0.0009727212,0.07439685,0.012902996,0.00037940973,0.84640217],"study_design_scores_gemma":[0.017918402,0.0048795533,0.028698944,0.0013064893,0.00016568444,0.02737727,0.13134812,0.52851343,0.15587932,0.074682854,0.023837667,0.005392248],"about_ca_topic_score_codex":0.00012859936,"about_ca_topic_score_gemma":0.000008772423,"teacher_disagreement_score":0.89420444,"about_ca_system_score_codex":0.000047167567,"about_ca_system_score_gemma":0.00010193552,"threshold_uncertainty_score":0.48223618},"labels":[],"label_agreement":null},{"id":"W2170854835","doi":"10.1109/tvcg.2010.152","title":"Exploration and Visualization of Segmentation Uncertainty using Shape and Appearance Prior Information","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Visualization; Probabilistic logic; Artificial intelligence; Segmentation; Population; Context (archaeology); Data visualization; Information visualization; Set (abstract data type); Data mining; Image segmentation; Interactive visualization; Pattern recognition (psychology); Machine learning","score_opus":0.021665604188399183,"score_gpt":0.28518122001516016,"score_spread":0.263515615826761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170854835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1832773,0.000023165108,0.8157635,0.00003728817,0.0005065923,0.000278403,0.000004343549,0.00010411047,0.000005333315],"genre_scores_gemma":[0.994064,0.00039467236,0.0051937187,0.00026869806,0.000036449746,0.000020085834,0.000008365041,0.000011355481,0.0000026527935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988493,0.000080807855,0.0003815159,0.0002856893,0.00027585565,0.00012687789],"domain_scores_gemma":[0.9992141,0.0000472211,0.00023716658,0.00018716953,0.00023713178,0.00007716921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002443806,0.0001677623,0.0001554443,0.0004470085,0.00032373957,0.00021982075,0.0000989726,0.00013074283,0.0000030257193],"category_scores_gemma":[0.000004552645,0.00018033978,0.000028908837,0.0006709203,0.00011789592,0.0024392598,0.000007430953,0.0001417232,6.807536e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013653284,0.00026610048,0.00075749535,0.00052965677,0.0000929259,7.88679e-7,0.013078151,0.017394857,0.009149151,0.45963243,0.000028554905,0.49893337],"study_design_scores_gemma":[0.0005867682,0.0001921296,0.00078328577,0.00005407744,0.000020498672,0.000017735001,0.00007329341,0.98727447,0.009715537,0.0009860672,0.00011871624,0.00017744699],"about_ca_topic_score_codex":0.000041037987,"about_ca_topic_score_gemma":0.000046126548,"teacher_disagreement_score":0.96987957,"about_ca_system_score_codex":0.000021882444,"about_ca_system_score_gemma":0.000038386945,"threshold_uncertainty_score":0.73540425},"labels":[],"label_agreement":null},{"id":"W2177078353","doi":"10.4103/2153-3539.170649","title":"Extraction and analysis of discrete synoptic pathology report data using R","year":2015,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Parsing; Computer science; Scripting language; Quality assurance; Information retrieval; Data mining; Data extraction; Simple (philosophy); Natural language processing; Pathology; Medicine; Programming language; MEDLINE","score_opus":0.08520372962763761,"score_gpt":0.3599386390515053,"score_spread":0.2747349094238677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177078353","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4086727,0.000084966254,0.59055686,0.00008954806,0.0004597251,0.000026553756,0.0000045244883,0.0000067612696,0.0000984006],"genre_scores_gemma":[0.6558669,0.00005573743,0.34394452,0.00006402667,0.000050515395,3.5860668e-7,0.0000061732103,0.000003908129,0.000007857237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825037,0.00010051143,0.0011264255,0.000094432624,0.00029363137,0.00013465616],"domain_scores_gemma":[0.99665254,0.00009631299,0.002086842,0.0006994477,0.00037382208,0.000091047164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023829208,0.000089805275,0.00039679982,0.0005991033,0.00004794103,0.000035947694,0.00054523785,0.00011105894,0.0000018977051],"category_scores_gemma":[0.00044433872,0.00007542455,0.00006067094,0.0007055975,0.000109660214,0.0018425185,0.0003319032,0.00023483383,9.3999256e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007151804,0.0008102366,0.22534163,0.0009062795,0.008887754,0.03653389,0.11074541,0.2851684,0.038572095,0.008327485,0.004370072,0.27962157],"study_design_scores_gemma":[0.0005099553,0.00045134424,0.012359032,0.000029256253,0.0010491451,0.060184695,0.0009996842,0.92214304,0.0004421546,0.001040493,0.00063629507,0.00015491278],"about_ca_topic_score_codex":0.0000034116288,"about_ca_topic_score_gemma":0.0000031261748,"teacher_disagreement_score":0.63697463,"about_ca_system_score_codex":0.00007743509,"about_ca_system_score_gemma":0.00017612205,"threshold_uncertainty_score":0.3075724},"labels":[],"label_agreement":null},{"id":"W2181630488","doi":"10.5858/2008-132-1428-itqosp","title":"Improving the quality of surgical pathology reports for breast cancer: a centralized audit with feedback.","year":2008,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St Mary's Hospital Centre","funders":"","keywords":"Breast cancer; Medicine; Surgical pathology; Audit; Quality (philosophy); Pathology; General surgery; Surgery; Cancer; Internal medicine; Business","score_opus":0.028671584605580287,"score_gpt":0.2530341863997369,"score_spread":0.22436260179415662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181630488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8068973,0.00036292875,0.18052231,0.0077922298,0.0015390484,0.0022607925,0.00004703412,0.00023964298,0.0003387358],"genre_scores_gemma":[0.99579334,0.000052060128,0.0019877658,0.00008452804,0.00014806658,0.0017899664,7.8689135e-7,0.000009108184,0.00013435727],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985245,0.00011173523,0.0003496491,0.00037051918,0.00026401997,0.00037956182],"domain_scores_gemma":[0.9986303,0.00016124675,0.00042384525,0.0005447899,0.00016689848,0.00007295701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084673765,0.00010335816,0.00022225095,0.000033387125,0.00014859115,0.000023154116,0.00032294347,0.000055759727,0.0000047387734],"category_scores_gemma":[0.00004640419,0.00006688957,0.00007925382,0.0002619203,0.00016315651,0.00020347426,0.00009331042,0.0000963247,2.509828e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007963126,0.0001536156,0.051305626,0.00013995699,0.00010881244,0.0002984906,0.0010598098,0.00031387695,0.00038110622,0.0020448412,0.0018053795,0.94159216],"study_design_scores_gemma":[0.0015002381,0.000054801167,0.9854676,0.000008513701,0.000018865692,0.0037663549,0.000019090414,0.0010451946,0.003164676,0.0004764567,0.0042572864,0.00022088498],"about_ca_topic_score_codex":0.00058768934,"about_ca_topic_score_gemma":0.00013289195,"teacher_disagreement_score":0.94137126,"about_ca_system_score_codex":0.00012675447,"about_ca_system_score_gemma":0.00014281186,"threshold_uncertainty_score":0.27276772},"labels":[],"label_agreement":null},{"id":"W2186773111","doi":"10.5858/arpa.2014-0606-ra","title":"Telepathology Impacts and Implementation Challenges: A Scoping Review","year":2015,"lang":"en","type":"review","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Telepathology; Scope (computer science); Telemedicine; Context (archaeology); Usability; Computer science; Scale (ratio); Knowledge management; Data science; Management science; Health care; Political science; Engineering","score_opus":0.07922844006289435,"score_gpt":0.4215996550721934,"score_spread":0.342371215009299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186773111","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004291734,0.9938682,0.0029745407,0.00076507893,0.0005228668,0.0013876135,0.000026410387,0.000087312685,0.0003637164],"genre_scores_gemma":[0.000004948535,0.9952584,0.003869516,0.00036955441,0.00022601213,0.00020446768,0.000030024145,0.000032905187,0.0000041905705],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.996063,0.0013395441,0.0011251671,0.0008128448,0.00028139117,0.00037807797],"domain_scores_gemma":[0.9968789,0.0006299846,0.0011758945,0.00096573634,0.00014626377,0.00020320264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017125716,0.00043743767,0.002494163,0.00049681135,0.00006137906,0.000006184661,0.00072190847,0.00019910584,0.000014765361],"category_scores_gemma":[0.0003465065,0.00034115324,0.00010612855,0.0005184208,0.0006591777,0.00020946251,0.00040809697,0.000422841,0.000007966038],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018331474,0.000010777428,0.0000025114048,0.093927495,0.00003492505,0.0001374595,0.0009906276,2.2557844e-8,0.000013013636,0.000854817,0.00019862647,0.9038279],"study_design_scores_gemma":[0.0009842899,0.0018347722,0.000049991744,0.61425966,0.0009250501,0.0016770964,0.00017377676,0.000006299424,0.000012110207,0.001601448,0.3778571,0.0006184019],"about_ca_topic_score_codex":0.00000570653,"about_ca_topic_score_gemma":0.000038989827,"teacher_disagreement_score":0.9032095,"about_ca_system_score_codex":0.00006677204,"about_ca_system_score_gemma":0.0012168838,"threshold_uncertainty_score":0.99990404},"labels":[],"label_agreement":null},{"id":"W2187638577","doi":"10.1109/ipdps.2011.402","title":"HPGC Introduction","year":2011,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Programming language","score_opus":0.027236897133603492,"score_gpt":0.20349906048410524,"score_spread":0.17626216335050174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187638577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016662169,0.000008409757,0.92282,0.0007445705,0.0012588172,0.000029663412,2.1153106e-8,0.0002768171,0.07319553],"genre_scores_gemma":[0.8306962,0.0000047641497,0.16527511,0.00025164973,0.00054004585,0.000008437707,1.1275673e-7,0.0000037747448,0.0032199004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99965495,0.000009599709,0.00005081741,0.00014744616,0.000065562905,0.000071649396],"domain_scores_gemma":[0.99966943,0.000002925714,0.000016052672,0.00026757928,0.000024106268,0.000019879915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006951498,0.000030144598,0.000025713054,0.000033240147,0.000029666782,0.000015866264,0.00020648015,0.000016421023,0.0002622174],"category_scores_gemma":[0.000005155052,0.000026509015,0.000012417269,0.00014829564,0.000010073976,0.00035686427,0.000051908748,0.000034665758,0.0002734577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000666204,0.0000424503,0.00051566545,0.0000040521695,0.000009942643,0.0000023903995,0.0013220597,0.00000826893,0.0037149845,0.476347,0.05665622,0.46137032],"study_design_scores_gemma":[0.00036804058,0.00041810356,0.020987203,0.0000036462582,0.0000064072237,0.00011600162,0.0000795398,0.027997933,0.56128365,0.10482605,0.28345412,0.00045930594],"about_ca_topic_score_codex":0.00005544365,"about_ca_topic_score_gemma":0.0000081823755,"teacher_disagreement_score":0.82903,"about_ca_system_score_codex":0.000025671918,"about_ca_system_score_gemma":0.000009270433,"threshold_uncertainty_score":0.35148367},"labels":[],"label_agreement":null},{"id":"W2192289533","doi":"10.4021/jocmr2009.12.1274","title":"Computer-aided Image Processing of Angiogenic Histological Samples in Ovarian Cancer","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Medicine Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Pathology; Angiogenesis; Differential diagnosis; Anamnesis; Ovarian cancer; Disease; Cancer; Internal medicine","score_opus":0.308933194491132,"score_gpt":0.5426827760945471,"score_spread":0.23374958160341508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2192289533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31397742,0.0073526097,0.5986273,0.07644925,0.0019444693,0.000406319,0.0000012357641,0.000035033772,0.001206357],"genre_scores_gemma":[0.94705486,0.00082570885,0.050087426,0.00033187575,0.001672225,0.0000022766574,1.5491175e-7,0.0000058104383,0.000019680872],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99499404,0.00091710273,0.0019576694,0.00030286502,0.0014372651,0.00039105525],"domain_scores_gemma":[0.9954557,0.0020601,0.00076988136,0.0003253756,0.0011340034,0.00025496358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011800503,0.00011143708,0.0007883898,0.0005981411,0.000064763386,0.000028980572,0.0011928551,0.00015649461,0.00004864516],"category_scores_gemma":[0.0029534423,0.000075679854,0.00017057077,0.001318006,0.00049379986,0.0003929262,0.00014131358,0.0013518542,0.0000021791268],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037987554,0.00038176522,0.0151177,0.00006303039,0.000031078587,0.0002364734,0.00044953686,0.000080010956,0.004972799,0.00082318153,0.00469466,0.9727699],"study_design_scores_gemma":[0.006693228,0.013166076,0.90311575,0.0025746964,0.000037720394,0.00036322343,0.00014416258,0.03257865,0.0027325912,0.033546373,0.004768031,0.00027951002],"about_ca_topic_score_codex":0.00012000546,"about_ca_topic_score_gemma":0.000023633655,"teacher_disagreement_score":0.9724904,"about_ca_system_score_codex":0.00019851835,"about_ca_system_score_gemma":0.0008226225,"threshold_uncertainty_score":0.58732086},"labels":[],"label_agreement":null},{"id":"W2192742520","doi":"10.1089/jwh.2015.5405","title":"Breast Cancer Screening in the Setting of Dense Breast Tissue","year":2015,"lang":"en","type":"article","venue":"Journal of Women s Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Services and Policy Research","funders":"American Cancer Society","keywords":"Breast cancer; Medicine; Breast cancer screening; Mammography; Library science; Cancer; Gerontology; Internal medicine; Computer science","score_opus":0.029217335425758776,"score_gpt":0.3259385738196833,"score_spread":0.2967212383939245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2192742520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83735234,0.0015166464,0.12100502,0.038839683,0.00092631957,0.00020458929,0.000009286215,0.000018645354,0.0001274624],"genre_scores_gemma":[0.9917917,0.00007479728,0.006994783,0.0007896827,0.0003292221,0.000004140578,5.1628156e-8,0.0000063456446,0.000009234862],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99818313,0.0002798353,0.00054603687,0.00010725704,0.00054954353,0.0003341769],"domain_scores_gemma":[0.9984868,0.0000816482,0.0007960309,0.00020697732,0.00023166409,0.00019687963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044899667,0.000077958946,0.000252993,0.00017665731,0.00005950937,0.000043728385,0.00057796686,0.00002965612,0.0000060373222],"category_scores_gemma":[0.00002240639,0.00005504915,0.000031676416,0.0005725166,0.000022101616,0.00043731282,0.00006252549,0.0002986588,0.0000013018598],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001547161,0.000097057215,0.0316139,0.000092730486,0.000032491218,0.000036488404,0.05840582,0.0034706667,0.00011516084,0.00023528,0.0025968268,0.9031489],"study_design_scores_gemma":[0.00548761,0.0026269613,0.9056954,0.0020743243,0.000018443163,0.024870783,0.022672692,0.021943418,0.00054027507,0.0040627043,0.009426997,0.00058039505],"about_ca_topic_score_codex":0.00096770894,"about_ca_topic_score_gemma":0.00019680907,"teacher_disagreement_score":0.90256846,"about_ca_system_score_codex":0.000790221,"about_ca_system_score_gemma":0.00093864085,"threshold_uncertainty_score":0.22448392},"labels":[],"label_agreement":null},{"id":"W2194374335","doi":"","title":"Mammography Image Segmentation Using Combined Fuzzy Logic and Neural Networks for Breast cancer Detection","year":2014,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fuzzy logic; Computer science; Artificial intelligence; Segmentation; Artificial neural network; Mammography; Image segmentation; Breast cancer; Pattern recognition (psychology); Computer vision; Cancer; Medicine","score_opus":0.02639067393351662,"score_gpt":0.3040112248158731,"score_spread":0.2776205508823565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2194374335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29787713,0.0024337366,0.69830096,0.00074902305,0.0004595072,0.00014983422,0.0000013617582,0.000017950331,0.000010481805],"genre_scores_gemma":[0.98690665,0.002105062,0.01026455,0.00026916325,0.00043294876,0.0000137742045,7.947752e-8,0.0000063278644,0.0000014428088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926573,0.000027157173,0.00027876545,0.00015412219,0.00012676576,0.00014745657],"domain_scores_gemma":[0.99932534,0.00010559423,0.00037875146,0.00004926199,0.00009261353,0.00004845892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003519854,0.00011043842,0.00021747066,0.00010215893,0.00023368739,0.000041567233,0.00010386098,0.00007145834,2.0233608e-7],"category_scores_gemma":[0.0000094163215,0.000087360284,0.000039122515,0.00016115146,0.00009383334,0.00032017755,0.00007148064,0.0002589505,2.6263642e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050140586,0.000020020405,0.004511536,0.00016477233,0.00032736294,9.574749e-7,0.0013593982,0.010234884,0.096232876,0.0024346507,0.0002691216,0.883943],"study_design_scores_gemma":[0.0062988494,0.0011519925,0.048387803,0.00024904683,0.00049277366,0.00066485704,0.002583549,0.85454583,0.01630405,0.06836907,0.00015828566,0.0007939134],"about_ca_topic_score_codex":0.0000028308316,"about_ca_topic_score_gemma":0.000002202119,"teacher_disagreement_score":0.8831491,"about_ca_system_score_codex":0.00004398946,"about_ca_system_score_gemma":0.000008048946,"threshold_uncertainty_score":0.3562449},"labels":[],"label_agreement":null},{"id":"W2205638955","doi":"10.1088/0031-9155/60/16/6459","title":"Metastatic liver tumour segmentation from discriminant Grassmannian manifolds","year":2015,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal","funders":"Canada Research Chairs","keywords":"Segmentation; Artificial intelligence; Pattern recognition (psychology); Discriminant; Subspace topology; Grassmannian; Computer science; Pairwise comparison; Cancer; Mathematics; Medicine; Combinatorics","score_opus":0.2838521706015301,"score_gpt":0.3855716444796512,"score_spread":0.10171947387812108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2205638955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2329849,0.0009740148,0.761351,0.0030288012,0.0009011901,0.0001596048,0.0000029489338,0.000046575045,0.0005509816],"genre_scores_gemma":[0.9894412,0.00016193384,0.009585738,0.0004881815,0.00027771812,0.000014553607,0.000014597335,0.0000038192243,0.000012212876],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99931854,0.00009012293,0.00014218136,0.00024171926,0.0000782203,0.00012920222],"domain_scores_gemma":[0.99962705,0.000077768455,0.000064937645,0.00014337333,0.000032677435,0.000054213433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021145868,0.00008591635,0.00016126582,0.00004920497,0.000025434148,0.0000095287005,0.00016845178,0.000024901468,0.0000030364358],"category_scores_gemma":[0.000022313458,0.000061477804,0.000011018056,0.0001593818,0.000085422136,0.00016183537,0.00008760761,0.00008727731,0.000008252803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007452556,0.00021897555,0.022372155,0.00006574151,0.000096784366,0.00010004513,0.023176365,0.00013058017,0.061603907,0.11435987,0.0068194037,0.77098167],"study_design_scores_gemma":[0.003933073,0.0020110533,0.029563777,0.0001603417,0.000097502314,0.00004073893,0.0031154365,0.09621718,0.011465179,0.8493646,0.0035096984,0.00052145624],"about_ca_topic_score_codex":0.0014826589,"about_ca_topic_score_gemma":0.00021214959,"teacher_disagreement_score":0.7704602,"about_ca_system_score_codex":0.000045965047,"about_ca_system_score_gemma":0.000024457762,"threshold_uncertainty_score":0.2506992},"labels":[],"label_agreement":null},{"id":"W2232773008","doi":"10.1186/s13040-015-0078-9","title":"Iteratively refining breast cancer intrinsic subtypes in the METABRIC dataset","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; Australian Research Council; Cancer Research UK","keywords":"Discriminative model; Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Breast cancer; Class (philosophy); Data mining; Pattern recognition (psychology); Cancer; Medicine","score_opus":0.04386414633269161,"score_gpt":0.2884951767383135,"score_spread":0.24463103040562187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232773008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5046088,0.005460222,0.3870594,0.073456556,0.0064642713,0.0010018814,0.018871747,0.00081595406,0.0022611383],"genre_scores_gemma":[0.9847666,0.00012620247,0.013276621,0.0012472902,0.0002996771,0.00008172485,0.000093137736,0.000013123909,0.000095642354],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986773,0.00015001814,0.00021212701,0.00044976553,0.00023999752,0.00027074976],"domain_scores_gemma":[0.9988001,0.00025158655,0.00011550536,0.00076667353,0.000031352407,0.00003480083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006578565,0.0001289336,0.0001283753,0.00013486069,0.00011530317,0.00018506176,0.0012282039,0.000040397674,0.000051162984],"category_scores_gemma":[0.00006078825,0.00007262917,0.000020174148,0.0006225513,0.00005333847,0.0013027688,0.0003569616,0.000097631186,0.00007410496],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023885128,0.000023275617,0.011796654,0.000008783866,0.000022829508,0.000026721425,0.0013581882,0.0000025340507,0.002261038,0.0015491381,0.019813754,0.9631132],"study_design_scores_gemma":[0.002147567,0.0002068578,0.39357874,0.0006967668,0.000052030184,0.0004697305,0.00059287465,0.002609158,0.0070255576,0.0003932452,0.5910686,0.0011588426],"about_ca_topic_score_codex":0.0003516575,"about_ca_topic_score_gemma":0.00039944996,"teacher_disagreement_score":0.96195436,"about_ca_system_score_codex":0.00009965905,"about_ca_system_score_gemma":0.000084498504,"threshold_uncertainty_score":0.29617316},"labels":[],"label_agreement":null},{"id":"W2271359107","doi":"10.1007/978-3-319-07887-8_62","title":"A Regional Web-Based Automated Quality Control Platform","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Computer science; Upload; Software; Mammography; Vendor; Quality (philosophy); Operating system","score_opus":0.025931355102009734,"score_gpt":0.2735371386623486,"score_spread":0.24760578356033885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271359107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007688181,0.00015453187,0.9913719,0.0017886272,0.0027849076,0.0005078265,0.000009121167,0.001433939,0.0018722217],"genre_scores_gemma":[0.6740503,0.000012758533,0.31472817,0.00981776,0.0010038669,0.000043411255,0.000009994755,0.000071540984,0.00026223366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99451256,0.00008555868,0.00083256146,0.0019767939,0.0017580201,0.0008345297],"domain_scores_gemma":[0.99534184,0.0012984426,0.0006474507,0.00204036,0.00041949493,0.00025242436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020594012,0.00067894545,0.00077703985,0.0009560464,0.00035908414,0.00056099147,0.0038041929,0.0005578552,0.00002922715],"category_scores_gemma":[0.00015148739,0.00063736155,0.00023854585,0.0007399961,0.0009325264,0.0005331764,0.00054362346,0.001026527,0.00010123456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006816731,0.000049816015,0.00013608608,0.00013539361,0.00003852358,0.0000651323,0.00028955523,0.17195329,0.00053486007,0.045490988,0.0006164493,0.78062177],"study_design_scores_gemma":[0.0010675641,0.00022639256,0.0002758904,0.0003025681,0.00000845335,0.000046205034,3.427305e-8,0.9451845,0.00049601926,0.045104884,0.006543333,0.00074410916],"about_ca_topic_score_codex":0.00005754324,"about_ca_topic_score_gemma":0.0001808749,"teacher_disagreement_score":0.77987766,"about_ca_system_score_codex":0.00096318097,"about_ca_system_score_gemma":0.0016052347,"threshold_uncertainty_score":0.99960774},"labels":[],"label_agreement":null},{"id":"W2271473780","doi":"10.1007/s11517-015-1411-7","title":"Review of recent advances in segmentation of the breast boundary and the pectoral muscle in mammograms","year":2015,"lang":"en","type":"review","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Segmentation; Thresholding; Computer science; Pectoral muscle; Artificial intelligence; Preprocessor; Image segmentation; Image processing; Mammography; Computer vision; Pattern recognition (psychology); Image (mathematics); Anatomy; Medicine; Breast cancer","score_opus":0.033375819760331535,"score_gpt":0.32044410679049196,"score_spread":0.2870682870301604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271473780","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000568948,0.9839217,0.01474788,0.00020435556,0.00048642672,0.00052551745,0.000002021462,0.000026577278,0.000028614062],"genre_scores_gemma":[0.0008471985,0.9975691,0.0013863142,0.00009095343,0.000070465525,0.00002492028,0.000003696413,0.0000070684837,3.1782002e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777204,0.00043339678,0.0008604244,0.00032280962,0.00039182097,0.00021950778],"domain_scores_gemma":[0.9986799,0.00054830336,0.00036411878,0.00028399008,0.000049531634,0.00007418536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026050769,0.00020699583,0.0010078012,0.00006947257,0.00002606391,0.0000152347075,0.000835121,0.00016927416,0.000010333582],"category_scores_gemma":[0.0007686677,0.000101447826,0.00013909563,0.00096528826,0.00023279886,0.00006451907,0.00057815743,0.00060458574,6.5819813e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016502195,0.00001536484,0.000078466546,0.0075878184,0.0000047022772,0.0000013706025,0.000028858793,0.000090704394,1.8212201e-7,0.00012905475,0.000006935621,0.9920549],"study_design_scores_gemma":[0.0007964983,0.000109282824,0.0014476576,0.15281668,0.000045381134,0.00018647086,0.000013534642,0.024985213,9.597213e-7,0.00019707598,0.8190319,0.0003693201],"about_ca_topic_score_codex":0.000022400018,"about_ca_topic_score_gemma":0.000008415118,"teacher_disagreement_score":0.99168557,"about_ca_system_score_codex":0.000153239,"about_ca_system_score_gemma":0.00018509783,"threshold_uncertainty_score":0.41369224},"labels":[],"label_agreement":null},{"id":"W2285032094","doi":"10.1371/journal.pone.0149893","title":"Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Multispectral image; Artificial intelligence; Pattern recognition (psychology); Texture (cosmology); Computer science; Image texture; Segmentation; Wavelet; Mathematics; Computer vision; Image segmentation; Image (mathematics)","score_opus":0.04746705166442282,"score_gpt":0.2690773212987276,"score_spread":0.22161026963430475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2285032094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78128135,0.00014083655,0.21799977,0.00019640928,0.00011598803,0.000117816424,0.000024753592,0.00008503543,0.000038023823],"genre_scores_gemma":[0.9100039,0.000037033118,0.08966119,0.000035949823,0.00006895357,0.000018562087,5.6305055e-7,0.0000095134055,0.00016435247],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998823,0.000049451122,0.00022858269,0.00034498936,0.00031734473,0.00023661568],"domain_scores_gemma":[0.9991501,0.00009886088,0.00018685224,0.0003249741,0.00017961953,0.00005958662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012375067,0.00011477878,0.00032772004,0.0002515853,0.00005458086,0.00002899972,0.00035868376,0.00006936894,0.00008415661],"category_scores_gemma":[0.00005457287,0.00008818165,0.00011941292,0.0009241246,0.00007907925,0.00036804413,0.00010843507,0.000081759026,0.000007214301],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018045805,0.00023304648,0.030893888,0.000013717577,0.0010113831,0.0000032356454,0.00022636144,0.000060631646,0.9621502,0.000018744899,0.000026799004,0.0053439555],"study_design_scores_gemma":[0.0004601686,0.000048724676,0.067852795,0.000105381034,0.0005464431,8.720198e-7,0.0000065677564,0.2600884,0.6706891,0.000025269715,0.000009936094,0.00016630413],"about_ca_topic_score_codex":0.00036060548,"about_ca_topic_score_gemma":0.0008411268,"teacher_disagreement_score":0.29146108,"about_ca_system_score_codex":0.00021163638,"about_ca_system_score_gemma":0.000066188455,"threshold_uncertainty_score":0.35959435},"labels":[],"label_agreement":null},{"id":"W2296636346","doi":"10.1109/icmla.2015.196","title":"Probabilistic Graphical Models and Deep Belief Networks for Prognosis of Breast Cancer","year":2015,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Graphical model; Computer science; Artificial intelligence; Machine learning; Softmax function; Probabilistic logic; Deep belief network; Support vector machine; Data mining; Deep learning; Microarray analysis techniques","score_opus":0.034063696004649445,"score_gpt":0.26515105725799276,"score_spread":0.2310873612533433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296636346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005362402,0.00034040018,0.9923141,0.0010477062,0.00022732631,0.00041193288,0.0000034659686,0.00008193111,0.00021071987],"genre_scores_gemma":[0.96609646,0.00003880297,0.033387627,0.00010371489,0.00008146698,0.00026195435,4.4375707e-7,0.0000071557956,0.0000223581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922264,0.000020040134,0.00015797323,0.00027270088,0.00015483917,0.00017179949],"domain_scores_gemma":[0.9993467,0.00005613953,0.000059787963,0.0001933997,0.00023729303,0.00010671707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020559531,0.00008296034,0.000126447,0.000045578337,0.00003782354,0.000037227765,0.00022687869,0.00006320156,0.0000021424244],"category_scores_gemma":[0.0000109253015,0.00006832097,0.000032261956,0.0002572309,0.00007168994,0.0003120429,0.00010501342,0.000056430497,1.8773505e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018202621,0.00027210457,0.007707219,0.00020867129,0.00010082139,0.0000011882635,0.0011314019,0.26402986,0.000057654303,0.26428017,0.0030019756,0.4590269],"study_design_scores_gemma":[0.00029438446,0.00012528265,0.0011963674,0.000015584068,0.0000106068255,0.000010961349,0.000008819592,0.9498481,0.00006742516,0.048264496,0.00007019809,0.00008773178],"about_ca_topic_score_codex":0.00016728333,"about_ca_topic_score_gemma":0.00021771957,"teacher_disagreement_score":0.96073407,"about_ca_system_score_codex":0.000047053152,"about_ca_system_score_gemma":0.00006660958,"threshold_uncertainty_score":0.27860484},"labels":[],"label_agreement":null},{"id":"W2302554869","doi":"10.1117/12.2216817","title":"Non-uniform object counting method in large-format pyramid images applied to CD31 vessel counting in whole-mount digital pathology sections","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Block (permutation group theory); Computer science; Mount; Thresholding; Computer vision; Image processing; Artificial intelligence; Segmentation; Mathematical morphology; Computer graphics (images); Image (mathematics); Mathematics; Geometry","score_opus":0.007662148171906888,"score_gpt":0.23834411508267037,"score_spread":0.23068196691076348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302554869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96081686,0.000020891834,0.033252552,0.002969359,0.00035693825,0.000640488,0.000046191977,0.00013166752,0.0017650682],"genre_scores_gemma":[0.79774606,0.000027105485,0.20138764,0.00015204778,0.00026338085,0.00030454414,0.0000028308284,0.00004994022,0.00006643178],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99713,3.3747703e-8,0.000892691,0.000613359,0.0006836676,0.0006802607],"domain_scores_gemma":[0.99818796,0.00024105368,0.00040772225,0.00010637008,0.00094865327,0.000108249194],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015216572,0.00034604975,0.00047078106,0.00035229532,0.000107749045,0.00030054696,0.0014001344,0.00022203298,0.000002701057],"category_scores_gemma":[0.0004978557,0.00027981808,0.00029898243,0.0009397321,0.00012233219,0.0020141543,0.0005209355,0.00040779763,0.0000053436797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008911438,0.00016161185,0.0016106693,0.00035772176,0.00011984023,6.0295355e-7,0.0011108115,0.0010640535,0.7446281,0.24657641,0.0009026038,0.003378502],"study_design_scores_gemma":[0.008033017,0.0009984955,0.019130772,0.0024542657,0.000106635496,0.00019357762,0.0061152983,0.39425355,0.5406983,0.0134683065,0.012418215,0.0021295403],"about_ca_topic_score_codex":0.000020723395,"about_ca_topic_score_gemma":0.000001888957,"teacher_disagreement_score":0.39318952,"about_ca_system_score_codex":0.0008352146,"about_ca_system_score_gemma":0.00006726153,"threshold_uncertainty_score":0.99996537},"labels":[],"label_agreement":null},{"id":"W2317492122","doi":"10.5795/jjscc.47.25","title":"Utility of multi focus virtual slide in cytology","year":2008,"lang":"en","type":"article","venue":"The Journal of the Japanese Society of Clinical Cytology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PCL Construction (Canada)","funders":"","keywords":"Cytology; Focus (optics); Medicine; Computer science; Pathology; Physics; Optics","score_opus":0.09644484412950868,"score_gpt":0.3628596273990836,"score_spread":0.2664147832695749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2317492122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97092974,0.00040022662,0.020247122,0.006739479,0.001425032,0.00014445256,0.0000020585028,0.000010993642,0.00010090112],"genre_scores_gemma":[0.99351656,0.0005107235,0.0052401028,0.00050719007,0.00014966368,9.917344e-7,5.2317223e-8,0.000008016144,0.00006667934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99498475,0.0019827266,0.002082067,0.0002046431,0.00045365078,0.00029218127],"domain_scores_gemma":[0.9927723,0.0038919172,0.0020781318,0.00083654514,0.00034366647,0.00007747743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054806727,0.00015476855,0.00095405075,0.000046616144,0.0001195587,0.000003194414,0.0024857847,0.000355962,0.00001821448],"category_scores_gemma":[0.0013355577,0.00008891699,0.0008699206,0.00046875892,0.001818145,0.00018590318,0.0005626892,0.0012466625,0.0000030781912],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005361461,0.0047449786,0.7655086,0.00023056513,0.0019655628,0.00008560436,0.08797029,0.005817973,0.0117518585,0.0021194657,0.02579605,0.08864758],"study_design_scores_gemma":[0.007288933,0.0026317264,0.9163975,0.000120913704,0.00016118465,0.0030659442,0.0023222428,0.045267373,0.012460419,0.008859532,0.0010911715,0.00033303365],"about_ca_topic_score_codex":0.00024399371,"about_ca_topic_score_gemma":0.00014076059,"teacher_disagreement_score":0.15088892,"about_ca_system_score_codex":0.000039722203,"about_ca_system_score_gemma":0.00039908418,"threshold_uncertainty_score":0.6699031},"labels":[],"label_agreement":null},{"id":"W2326499489","doi":"10.1109/embc.2014.6944665","title":"Development and validation of a fully automated system for detection and diagnosis of mammographic lesions","year":2014,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; False positive paradox; Pattern recognition (psychology); Computer science; Linear discriminant analysis; Mammography; Cluster analysis; Feature extraction; Receiver operating characteristic; Computer-aided diagnosis; Support vector machine; Feature selection; Computer vision; Medicine; Breast cancer; Machine learning; Cancer","score_opus":0.01633093931566964,"score_gpt":0.23518749098662928,"score_spread":0.21885655167095963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326499489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5129924,0.000015470758,0.48661947,0.000021871865,0.00006795681,0.00013374841,4.6280664e-7,0.00011713709,0.00003149541],"genre_scores_gemma":[0.92983675,0.000007285423,0.07004728,0.000004425522,0.00000661904,0.000089905276,4.1475445e-7,0.0000034019208,0.000003918781],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943155,0.000031084255,0.00020491722,0.00016284414,0.000099844736,0.00006978543],"domain_scores_gemma":[0.9995184,0.00011047102,0.00012558127,0.0001231026,0.00009470971,0.000027764572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030230032,0.000056431014,0.000105056715,0.00014681912,0.00006944858,0.000019197007,0.00007289687,0.000040895073,3.9797015e-7],"category_scores_gemma":[0.000024127688,0.000051030598,0.000016355865,0.00022237172,0.00002298944,0.00014403292,0.000045823796,0.000017421486,1.9506726e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040830357,0.00006847669,0.010773644,0.0014257737,0.0000774435,1.7651749e-7,0.0014614408,0.0002242338,0.08550195,0.013998282,0.000060599694,0.88636714],"study_design_scores_gemma":[0.00028474221,0.00015339523,0.01678779,0.00007250706,0.0000108013555,0.000005791348,0.000060862953,0.14997983,0.8321552,0.00014037587,0.00027841312,0.00007023971],"about_ca_topic_score_codex":0.00003654448,"about_ca_topic_score_gemma":0.00004257,"teacher_disagreement_score":0.8862969,"about_ca_system_score_codex":0.000025178073,"about_ca_system_score_gemma":0.000017454475,"threshold_uncertainty_score":0.20809674},"labels":[],"label_agreement":null},{"id":"W2328762559","doi":"10.1097/pai.0000000000000305","title":"An Audit of Failed Immunohistochemical Slides in a Clinical Laboratory: The Role of On-Slide Controls","year":2015,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Medicine; Immunohistochemistry; Pathology; Internal medicine","score_opus":0.009608294644141634,"score_gpt":0.2840687294415905,"score_spread":0.27446043479744886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328762559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9799931,0.0014757931,0.014771708,0.00022380594,0.00031884492,0.0004562915,0.000012899457,0.00007804484,0.002669499],"genre_scores_gemma":[0.99460626,0.0000115795,0.004723588,0.0003498306,0.000050912746,0.00020161408,0.000013544388,0.000031568863,0.0000111189665],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99702525,0.00026010047,0.0011168045,0.00073276204,0.0004540746,0.00041101448],"domain_scores_gemma":[0.9964271,0.0002298376,0.0006979484,0.0022278647,0.00028333272,0.00013388063],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012504692,0.0003102422,0.00070648256,0.00010514617,0.00004977913,0.000022126003,0.0020436398,0.0003798103,0.0000148294375],"category_scores_gemma":[0.0002839148,0.00028614307,0.00017218236,0.00056785677,0.00070690806,0.000100634796,0.0002892031,0.0006782433,0.000017481929],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003568788,0.00026424305,0.00018842398,0.000011005017,0.00005670454,0.000021553758,0.00023575054,0.00018861846,0.99133277,0.0046830936,0.0001892994,0.0024716873],"study_design_scores_gemma":[0.0019436658,0.00041611522,0.00051535055,0.00002443374,0.000027336348,0.000027161175,0.0002503423,0.00074234424,0.9912125,0.0040601995,0.0005005559,0.00027998444],"about_ca_topic_score_codex":0.000098846445,"about_ca_topic_score_gemma":3.602299e-7,"teacher_disagreement_score":0.014613129,"about_ca_system_score_codex":0.00032170676,"about_ca_system_score_gemma":0.0005302191,"threshold_uncertainty_score":0.99995905},"labels":[],"label_agreement":null},{"id":"W2331190967","doi":"10.3804/jjabcs.22.129","title":"Facilities for Mammography Image Evaluation","year":2013,"lang":"en","type":"article","venue":"Nihon Nyugan Kenshin Gakkaishi (Journal of Japan Association of Breast Cancer Screening)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Research Foundation","funders":"","keywords":"Mammography; Computer science; Medical physics; Medicine; Internal medicine; Breast cancer; Cancer","score_opus":0.015491818946787219,"score_gpt":0.2639331037272996,"score_spread":0.2484412847805124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331190967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53592396,0.000965012,0.438503,0.016474543,0.004107442,0.002003003,0.00044785958,0.00020161334,0.0013735432],"genre_scores_gemma":[0.95762914,0.00009676865,0.04059548,0.00027309,0.000731606,0.00014079126,0.000008947893,0.000037395504,0.0004868047],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955893,0.00032903746,0.0012413758,0.00039859922,0.0019349476,0.0005067482],"domain_scores_gemma":[0.99057233,0.00046523122,0.0031838797,0.00043087092,0.005143069,0.00020463514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031238168,0.00029655415,0.0005959948,0.00057673623,0.0001913791,0.00038186272,0.0010104914,0.00023676656,0.00027995664],"category_scores_gemma":[0.00051239255,0.00029861543,0.0004935543,0.00080884824,0.00008308789,0.0028287154,0.00010474472,0.00039880877,0.000010298148],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046713263,0.00030997634,0.24280158,0.00032813166,0.0013854692,0.0000013257443,0.006776749,0.0022722033,0.014005793,0.00089093513,0.1335247,0.597236],"study_design_scores_gemma":[0.0063568223,0.00090378657,0.9264258,0.0005217265,0.00034391144,0.000112213966,0.0011441623,0.03765753,0.0093648,0.00982378,0.0064489148,0.00089651404],"about_ca_topic_score_codex":0.0008089769,"about_ca_topic_score_gemma":0.00014044107,"teacher_disagreement_score":0.68362427,"about_ca_system_score_codex":0.0010605268,"about_ca_system_score_gemma":0.0004669236,"threshold_uncertainty_score":0.9999466},"labels":[],"label_agreement":null},{"id":"W2335119202","doi":"10.1177/153303460500400205","title":"Performance Evaluation of Image Processing Algorithms in CADe","year":2005,"lang":"en","type":"article","venue":"Technology in Cancer Research & Treatment","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Image processing; Context (archaeology); Algorithm; Digital image processing; Process (computing); Machine learning; Key (lock); Artificial intelligence; Image (mathematics); Data mining; Computer security","score_opus":0.11541334340252216,"score_gpt":0.4519292621866488,"score_spread":0.3365159187841267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335119202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874819,0.0032789293,0.0009063907,0.0066271853,0.00006583584,0.00084090914,0.0000021140565,0.000118883036,0.00067788095],"genre_scores_gemma":[0.9858672,0.0012347265,0.011135684,0.000008458311,0.000040069724,0.001654462,7.3280114e-7,0.000010472686,0.000048215577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770933,0.00015424239,0.00031545735,0.00048453064,0.00082086667,0.0005155509],"domain_scores_gemma":[0.9989765,0.000043492968,0.00008404623,0.0005151138,0.0003476935,0.000033133783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017271424,0.00012998022,0.00020018958,0.0013882917,0.00008447845,0.000024136176,0.00060850923,0.00016030457,0.000025297577],"category_scores_gemma":[0.00004605699,0.000119045195,0.00002189896,0.0025047422,0.00025425985,0.00051516143,0.00017047078,0.00037613435,0.000016666985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015963755,0.00018826153,0.010029495,0.000015867903,0.000007624816,0.000004832787,0.0005909327,0.002729288,0.003386162,0.00013634203,0.000017008086,0.9828782],"study_design_scores_gemma":[0.002298523,0.00072043604,0.018361691,0.00022906686,0.000008376566,0.000012701177,0.00017409038,0.66768277,0.30702603,0.0025057462,0.0008101779,0.00017039613],"about_ca_topic_score_codex":0.0010755325,"about_ca_topic_score_gemma":0.001966009,"teacher_disagreement_score":0.9827078,"about_ca_system_score_codex":0.0054424508,"about_ca_system_score_gemma":0.0008757043,"threshold_uncertainty_score":0.9983755},"labels":[],"label_agreement":null},{"id":"W2336972508","doi":"10.1159/000442390","title":"International Telepathology: Promises and Pitfalls","year":2016,"lang":"en","type":"review","venue":"Pathobiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"","keywords":"Telepathology; Workflow; Accreditation; Telemedicine; Business; Health care; Process management; Engineering management; Knowledge management; Computer science; Medicine; Engineering; Medical education; Political science","score_opus":0.03480831132619322,"score_gpt":0.330903347111961,"score_spread":0.2960950357857678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336972508","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001484301,0.9623974,0.03209626,0.0001547743,0.0026429978,0.00031155825,0.000031410127,0.00014981932,0.0022143014],"genre_scores_gemma":[0.0000049285,0.99321645,0.005743958,0.00006943647,0.0004175371,0.0001766741,0.00001048705,0.000017309785,0.00034319743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983554,0.0002641233,0.000345571,0.00071109814,0.00006955582,0.00025429245],"domain_scores_gemma":[0.9988837,0.00024708864,0.00029051583,0.0004743609,0.00004925601,0.000055067816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003001093,0.00026204562,0.0007202272,0.00019872647,0.000053457257,0.00004329492,0.0009876268,0.00039143956,0.00004100181],"category_scores_gemma":[0.00009210464,0.00017480529,0.00012964239,0.000112279464,0.00013979386,0.00014177154,0.0006366,0.0002203729,0.00023026166],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.6639697e-7,0.0000064706223,0.000006499928,0.00028707934,0.00002703772,0.00001944347,0.000016613403,5.815338e-9,0.0000073104766,0.0021558483,0.00026902364,0.9972039],"study_design_scores_gemma":[0.00008712159,0.00007410852,0.0000070220317,0.00084549654,0.00002350928,0.0007954562,4.4968436e-7,0.0000073623305,0.0000030092494,0.0011104132,0.9968349,0.00021120187],"about_ca_topic_score_codex":0.0000017665104,"about_ca_topic_score_gemma":0.0000011400855,"teacher_disagreement_score":0.9969927,"about_ca_system_score_codex":0.000113705355,"about_ca_system_score_gemma":0.00013162258,"threshold_uncertainty_score":0.71283525},"labels":[],"label_agreement":null},{"id":"W2338718259","doi":"","title":"Tissue Segmentation in Medical Images Based on Image Processing Chain Optimization","year":2010,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Image processing; Computer vision; Segmentation; Image segmentation; Feature (linguistics); Sample (material); Pattern recognition (psychology); Feature extraction; Image (mathematics)","score_opus":0.00658104212227689,"score_gpt":0.2803728311839042,"score_spread":0.2737917890616273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338718259","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011370786,0.0000034928682,0.98932767,0.0041726176,0.00032649282,0.00014795324,2.828406e-7,0.0001714913,0.004712915],"genre_scores_gemma":[0.47593608,0.0000021575045,0.5227784,0.0010395534,0.000087960296,0.000035649635,0.0000035942821,0.00000873383,0.00010786797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989733,0.000041624266,0.0001581982,0.0002780985,0.00040945303,0.00013928657],"domain_scores_gemma":[0.99955994,0.00006519067,0.000055462067,0.0002082407,0.0000525287,0.00005864161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042573415,0.00007989983,0.000066901666,0.00015703143,0.000059896396,0.00012807746,0.00028487967,0.000078033285,0.0002678355],"category_scores_gemma":[0.00011867236,0.00007346575,0.000011125412,0.00039239044,0.000034375287,0.00060408714,0.000039555085,0.00020184442,0.000020078045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014020812,0.000116108786,0.00029383085,0.000032305372,0.0000011347514,0.000020802549,0.00025548608,0.04008047,0.032620784,0.00055695727,0.0006163888,0.92539173],"study_design_scores_gemma":[0.00030309765,0.00004819655,0.00040676584,0.000018444172,6.144705e-7,0.0000039653355,0.000009735523,0.88008696,0.11884528,0.00010211167,0.000094664836,0.00008015596],"about_ca_topic_score_codex":0.000043890195,"about_ca_topic_score_gemma":0.000075241514,"teacher_disagreement_score":0.92531157,"about_ca_system_score_codex":0.00006105791,"about_ca_system_score_gemma":0.00012168689,"threshold_uncertainty_score":0.29958463},"labels":[],"label_agreement":null},{"id":"W2338789981","doi":"10.1159/000441192","title":"International Clinical Guidelines for the Adoption of Digital Pathology: A Review of Technical Aspects","year":2016,"lang":"en","type":"review","venue":"Pathobiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Digital pathology; Medicine; Telepathology; Pathology; Food and drug administration; Medicaid; Anatomical pathology; Disease control; Surgical pathology; Telemedicine; Health care; Medical emergency; Environmental health; Political science","score_opus":0.21032914830913482,"score_gpt":0.4756322662583719,"score_spread":0.2653031179492371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338789981","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.69733e-8,0.7621703,0.23371501,0.00090375275,0.001986178,0.0007305913,0.00015739337,0.00003671598,0.0002999512],"genre_scores_gemma":[0.00000608274,0.9886294,0.0101801,0.00020067289,0.00060268585,0.0002857882,0.00004754382,0.000015430142,0.00003229695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99700963,0.00027988074,0.0018490009,0.00053358,0.00014537809,0.0001825402],"domain_scores_gemma":[0.99469393,0.00208079,0.0015926188,0.00085132674,0.0007504234,0.00003088496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020689275,0.00022888482,0.0013938466,0.0001058586,0.000027531034,0.00001026031,0.0017333558,0.0004165043,0.000014498544],"category_scores_gemma":[0.0035158582,0.00012068559,0.000844261,0.00020893016,0.00030060354,0.000107055195,0.00053454045,0.00023447594,0.000023324292],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037889058,0.000023950957,0.000003773322,0.005063943,0.000051472438,0.0000016095157,0.0000012455614,4.2867157e-8,0.0000031713193,0.0027002394,0.0028811344,0.9892656],"study_design_scores_gemma":[0.000117400596,0.00025917194,0.000005248108,0.024896344,0.00012700657,0.00024662336,4.9705034e-7,0.000020664744,0.0000017746727,0.0010660529,0.97313726,0.00012194385],"about_ca_topic_score_codex":4.776118e-7,"about_ca_topic_score_gemma":6.870622e-7,"teacher_disagreement_score":0.98914367,"about_ca_system_score_codex":0.000078377256,"about_ca_system_score_gemma":0.00030642783,"threshold_uncertainty_score":0.49214154},"labels":[],"label_agreement":null},{"id":"W2339617301","doi":"10.6000/1929-2279.2016.05.02.2","title":"Adaptive Edge Detection Technique Towards Features Extraction from Mammogram Images","year":2016,"lang":"en","type":"article","venue":"Journal of cancer research updates","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thresholding; Edge detection; Segmentation; Artificial intelligence; Computer science; Enhanced Data Rates for GSM Evolution; CAD; Computer-aided diagnosis; Breast cancer; Image segmentation; Cancer; Cancer detection; Pattern recognition (psychology); Computer vision; Image (mathematics); Image processing; Medicine; Engineering","score_opus":0.04275532233480395,"score_gpt":0.39135763871105234,"score_spread":0.3486023163762484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339617301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025732342,0.0040345066,0.9606358,0.0066490313,0.0017414247,0.00041698408,0.000028312665,0.00012319525,0.00063840096],"genre_scores_gemma":[0.97961503,0.0027909875,0.01582367,0.000040004434,0.0012566692,0.000115908566,3.310037e-7,0.000023213537,0.00033416422],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970542,0.00043017944,0.0004136772,0.0003576931,0.0012938421,0.00045041376],"domain_scores_gemma":[0.99726534,0.0003786544,0.00039447236,0.0004140605,0.0013581661,0.00018929262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018201311,0.00016751635,0.00024497267,0.00062667346,0.0002276158,0.0002659209,0.0010162768,0.00015683797,0.00010377782],"category_scores_gemma":[0.00025271,0.000109771114,0.00014372615,0.0007657459,0.00018639566,0.0021826501,0.00021896065,0.0008348556,0.000020728596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022170485,0.000030957406,0.00012532777,0.000005224693,0.000057919606,0.000025357584,0.00006549724,0.000011219415,0.38050243,0.00009272969,0.004510923,0.6143507],"study_design_scores_gemma":[0.0004499139,0.00065789727,0.008177947,0.00024196712,0.000012341286,0.0001046536,0.00007012308,0.00009377614,0.9553965,0.017411517,0.017227244,0.0001561599],"about_ca_topic_score_codex":0.0012448757,"about_ca_topic_score_gemma":0.0003883848,"teacher_disagreement_score":0.9538827,"about_ca_system_score_codex":0.0010728578,"about_ca_system_score_gemma":0.0004907999,"threshold_uncertainty_score":0.44763362},"labels":[],"label_agreement":null},{"id":"W2341587220","doi":"10.1136/jclinpath-2015-202914","title":"Overview of contemporary guidelines in digital pathology: what is available in 2015 and what still needs to be addressed?","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"Medical Research Council","keywords":"Telepathology; Digital pathology; Medicine; Pathology; Virtual microscopy; Modalities; Telemedicine; Medical physics; Anatomical pathology; Computer science; Data science; Health care","score_opus":0.40232309320436166,"score_gpt":0.49806771623596874,"score_spread":0.09574462303160708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2341587220","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003828941,0.99119115,0.00063971564,0.0032904658,0.0038921908,0.0004492006,0.000020604975,0.0000122394,0.00012156355],"genre_scores_gemma":[0.000065459775,0.99316627,0.0032247028,0.002925799,0.0004016673,0.000014856171,0.0000034770783,0.000032517994,0.0001652451],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914567,0.0010738625,0.0059094215,0.0006449573,0.00053432025,0.0003807619],"domain_scores_gemma":[0.99285394,0.0015729514,0.0034617647,0.0008182746,0.00087696,0.0004160906],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0088588195,0.0004395988,0.00463131,0.001104941,0.000015130271,0.00031319403,0.0014025624,0.00096949306,0.000029131135],"category_scores_gemma":[0.003454045,0.00034545077,0.00055665587,0.001060749,0.0002621522,0.0041988753,0.00087440043,0.001459983,0.000048467362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005450297,0.00012236227,0.00020957329,0.0009516694,0.00003423562,0.0009640971,0.00026669345,0.0000029661535,3.3476263e-7,0.000024701996,0.033040095,0.96432877],"study_design_scores_gemma":[0.0010234418,0.0013803442,0.00004058351,0.01595284,0.00006171607,0.0015716047,0.00012798664,0.000045890465,8.2116304e-7,0.0009372661,0.9785629,0.00029460594],"about_ca_topic_score_codex":0.000009833354,"about_ca_topic_score_gemma":0.000016321721,"teacher_disagreement_score":0.96403414,"about_ca_system_score_codex":0.00014408161,"about_ca_system_score_gemma":0.002043257,"threshold_uncertainty_score":0.99989974},"labels":[],"label_agreement":null},{"id":"W2343327095","doi":"10.1109/jbhi.2015.2503720","title":"Circular Mixture Modeling of Color Distribution for Blind Stain Separation in Pathology Images","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stain; Artificial intelligence; Hue; Pattern recognition (psychology); Computer science; Matrix decomposition; Pixel; Non-negative matrix factorization; Segmentation; Cluster analysis; Computer vision; Mathematics; Pathology; Staining; Eigenvalues and eigenvectors; Physics","score_opus":0.06466379736720057,"score_gpt":0.36482123590585225,"score_spread":0.3001574385386517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343327095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08991958,0.00024416522,0.9056959,0.0035374456,0.00043988758,0.00013967312,0.000014492747,0.0000046601926,0.00000418685],"genre_scores_gemma":[0.9407126,0.00022563805,0.0585142,0.00038313871,0.00014782535,0.0000042237343,0.000008503484,0.0000024346855,0.0000014543153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850297,0.000041890387,0.000969805,0.0000440722,0.00028798557,0.00015325719],"domain_scores_gemma":[0.9988008,0.000043255208,0.0006247208,0.00007268476,0.0002862715,0.0001722508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023488153,0.00005831343,0.00022303923,0.00014683187,0.000039959286,0.000020696474,0.00014171969,0.00009562751,2.4484203e-7],"category_scores_gemma":[0.00009342092,0.00004606381,0.000029366101,0.00020818485,0.000051635583,0.00043152773,0.00002199527,0.00016609766,2.431036e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019102669,0.0012313554,0.0014847465,0.008150959,0.00017041223,0.00006798669,0.081029326,0.093240924,0.0017439547,0.007877605,0.055609737,0.7474827],"study_design_scores_gemma":[0.001698393,0.0012751066,0.00009620747,0.000095490606,0.000004669626,0.00014600588,0.00043220783,0.98918134,0.00021505074,0.004937816,0.0018638055,0.000053922788],"about_ca_topic_score_codex":0.000009271662,"about_ca_topic_score_gemma":0.0000034407105,"teacher_disagreement_score":0.8959404,"about_ca_system_score_codex":0.00017236319,"about_ca_system_score_gemma":0.0005573232,"threshold_uncertainty_score":0.18784276},"labels":[],"label_agreement":null},{"id":"W2346855685","doi":"10.4103/2153-3539.181770","title":"Evaluation of panoramic digital images using Panoptiq for frozen section diagnosis","year":2016,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Section (typography); Computer science; Frozen section procedure; Computer graphics (images); Digital pathology; Information retrieval; Data mining; Artificial intelligence; Medicine; Pathology; Operating system","score_opus":0.04647088198475145,"score_gpt":0.3130278741211504,"score_spread":0.26655699213639894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2346855685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42149255,0.000037843416,0.577436,0.00008928276,0.00076187233,0.00009949076,0.000008666632,0.000008427381,0.000065906526],"genre_scores_gemma":[0.92654485,0.000049107948,0.07319363,0.000032215055,0.0001601518,0.000008451133,4.1630193e-7,0.0000055438004,0.0000056534154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850225,0.00007252901,0.0007565674,0.00005493311,0.00047682115,0.00013691145],"domain_scores_gemma":[0.99695957,0.00024632618,0.0012806219,0.0001883746,0.00128948,0.00003560977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018331393,0.000084985884,0.0001973334,0.00023942132,0.00005260782,0.00005230115,0.00028877074,0.00009489419,0.000005054651],"category_scores_gemma":[0.00064171286,0.00005894335,0.00010506117,0.00014839927,0.00005976708,0.0023547998,0.00006031047,0.000084130865,0.0000024934548],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053436506,0.0001096639,0.008545429,0.00009351207,0.00014057025,0.000006528465,0.0032105264,0.005069405,0.02275194,0.00031075862,0.0009401097,0.9587681],"study_design_scores_gemma":[0.012665149,0.0063933195,0.02426946,0.0010858766,0.0012220787,0.006370784,0.0016420517,0.57931936,0.28370923,0.07929702,0.002970818,0.0010548484],"about_ca_topic_score_codex":6.9005966e-7,"about_ca_topic_score_gemma":7.4660625e-7,"teacher_disagreement_score":0.95771325,"about_ca_system_score_codex":0.0002941886,"about_ca_system_score_gemma":0.0002452506,"threshold_uncertainty_score":0.240364},"labels":[],"label_agreement":null},{"id":"W2396424965","doi":"10.1007/978-3-319-24888-2_32","title":"Clustering Analysis for Semi-supervised Learning Improves Classification Performance of Digital Pathology","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Cluster analysis; Computer science; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Decision boundary; Classifier (UML); Machine learning; Digital pathology; Artificial neural network","score_opus":0.03434446534795807,"score_gpt":0.2603556148830837,"score_spread":0.2260111495351256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396424965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028154843,0.00022794407,0.9948048,0.0001450033,0.0008938765,0.00037840693,0.000007034356,0.00012453875,0.00060293917],"genre_scores_gemma":[0.84672296,0.00003532031,0.15270048,0.00006136589,0.00021795617,0.00002316098,0.000014575485,0.00002531182,0.00019884021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969869,0.000026613947,0.0006061419,0.0012475896,0.0006760596,0.00045667563],"domain_scores_gemma":[0.997462,0.00033453322,0.0005465607,0.00097625545,0.000573317,0.00010734309],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009582885,0.00036713658,0.00060196203,0.001204037,0.00018125567,0.00029924544,0.0018715783,0.00030916897,0.0000033051801],"category_scores_gemma":[0.00013180157,0.0003595267,0.00019799697,0.0011036966,0.0004405972,0.0009882654,0.0007701952,0.0005139484,0.000004842428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020779184,0.000012239657,0.0006944352,0.00007998843,0.000043266475,0.0000030181945,0.0006135145,0.2582245,0.0012981748,0.00032985705,0.0000024676626,0.7386778],"study_design_scores_gemma":[0.0002292887,0.00047595415,0.0005120199,0.00010033806,0.000043320753,0.000019426088,6.4233876e-7,0.9914723,0.0011133787,0.0054071303,0.00026118453,0.00036499382],"about_ca_topic_score_codex":0.000005104793,"about_ca_topic_score_gemma":0.000022680013,"teacher_disagreement_score":0.84390754,"about_ca_system_score_codex":0.00043028835,"about_ca_system_score_gemma":0.00040607355,"threshold_uncertainty_score":0.9998857},"labels":[],"label_agreement":null},{"id":"W2410047223","doi":"","title":"Optimized quality of histologic images allows the use of neural network scanning in diagnosis of fungal infection of abnormal nails.","year":2006,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Particle Physics","funders":"","keywords":"Fixative; Spore; Fixation (population genetics); Pathology; Microscopy; Gold standard (test); Biology; Staining; Medicine; Radiology; Microbiology","score_opus":0.059181051768974285,"score_gpt":0.25406405737799986,"score_spread":0.19488300560902558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410047223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97841537,0.0003700848,0.02005559,0.00014504878,0.00041870264,0.0004252395,0.00000429711,0.000028863804,0.00013682836],"genre_scores_gemma":[0.9944618,0.000045479443,0.0051096007,0.000020013787,0.00004445374,0.00029794915,8.6716966e-7,0.0000050653475,0.000014797682],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982522,0.00036177706,0.0006792424,0.00019324796,0.00027152125,0.00024201017],"domain_scores_gemma":[0.9982239,0.0005324552,0.0007320292,0.0003588165,0.00013148067,0.000021307036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011169582,0.000099022385,0.00032894025,0.00011232203,0.000033114284,0.000014315617,0.0003192456,0.00006362969,0.000002529522],"category_scores_gemma":[0.00019646,0.00008054367,0.000113989845,0.000643445,0.00018277418,0.00046540593,0.00014618013,0.00012414306,7.615156e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010204433,0.00009942812,0.6173593,0.00006082946,0.000016946708,8.2333514e-7,0.00013107901,0.3294044,0.00014418634,0.0002541194,0.00048975553,0.05193712],"study_design_scores_gemma":[0.0004368091,0.000043981585,0.98142016,0.000015415937,0.000010671977,0.0000024753606,0.000004028582,0.009494225,0.008276333,0.00017501408,0.00005071206,0.000070168295],"about_ca_topic_score_codex":0.0098543875,"about_ca_topic_score_gemma":0.00042208328,"teacher_disagreement_score":0.3640609,"about_ca_system_score_codex":0.0000883865,"about_ca_system_score_gemma":0.000025929554,"threshold_uncertainty_score":0.9967391},"labels":[],"label_agreement":null},{"id":"W2411643652","doi":"10.1097/pap.0000000000000094","title":"Principles of Analytic Validation of Clinical Immunohistochemistry Assays","year":2015,"lang":"en","type":"review","venue":"Advances in Anatomic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Guideline; Immunohistochemistry; Medicine; Pathology; Clinical biochemistry; Medical physics","score_opus":0.10394487947719386,"score_gpt":0.46278130262602635,"score_spread":0.35883642314883246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2411643652","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013918543,0.97326905,0.022066502,0.0000045068996,0.0011049691,0.0002541768,0.00001506359,0.000031581298,0.0031149539],"genre_scores_gemma":[0.00084904104,0.9891983,0.009759154,0.0000051810384,0.000061826824,0.000041463732,0.000018156976,0.000016216849,0.00005060488],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962895,0.00054049934,0.0020673228,0.00063229684,0.00025450345,0.00021588613],"domain_scores_gemma":[0.9960002,0.0004477664,0.002271275,0.0010689218,0.00016273835,0.000049143342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002254572,0.00025217273,0.0021002165,0.00031400457,0.000014534649,0.000005593529,0.0013091527,0.0004609293,0.0000049189853],"category_scores_gemma":[0.00053847773,0.00023761409,0.0003298001,0.0006828261,0.00031142242,0.00029574227,0.00035047904,0.00049605995,0.000008046683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005122079,0.00004933006,0.00010493916,0.0027798475,0.00002283711,0.000022161115,0.000032585605,0.000076860124,0.000008262316,0.0023384492,0.0000092274,0.9945504],"study_design_scores_gemma":[0.00052790315,0.00019591319,0.000026041713,0.003754249,0.00017319358,0.00021731187,0.000012654636,0.0013607771,0.00039134675,0.003756511,0.9891407,0.00044338778],"about_ca_topic_score_codex":0.0000059779745,"about_ca_topic_score_gemma":0.000003297694,"teacher_disagreement_score":0.994107,"about_ca_system_score_codex":0.00028846518,"about_ca_system_score_gemma":0.00080276985,"threshold_uncertainty_score":0.96896213},"labels":[],"label_agreement":null},{"id":"W2416463881","doi":"","title":"Honest assessments of automatic learning algorithm performance.","year":2000,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Variance (accounting); Machine learning; Task (project management); Algorithm; Artificial intelligence; Probabilistic logic; Data mining","score_opus":0.01461906660654779,"score_gpt":0.22862184721499174,"score_spread":0.21400278060844394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2416463881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7679613,0.00009211785,0.2102996,0.00017223961,0.0008549553,0.00054752367,0.0000010306869,0.0005473308,0.019523894],"genre_scores_gemma":[0.97570413,0.00004587222,0.022066457,0.000035922043,0.00005921098,0.00033306205,7.2530565e-7,0.0000075083653,0.0017470863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909616,0.00004264859,0.00017336375,0.00018412646,0.0002624856,0.00024119232],"domain_scores_gemma":[0.9995624,0.000028520066,0.00007917981,0.000246928,0.000029591098,0.000053427786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028826087,0.00007420042,0.00010788419,0.00006876798,0.00007173431,0.00004488846,0.00035834205,0.000034671564,0.00006455398],"category_scores_gemma":[0.000007845814,0.00007299885,0.00003062849,0.00034799584,0.00002496717,0.0005049103,0.000050997565,0.000115603165,0.000043701013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.3484846e-7,0.000015485532,0.0014439202,0.000014772904,0.00000771935,7.896336e-7,0.00006666718,0.00030346142,0.0000042562147,0.000011356056,0.000058380545,0.99807227],"study_design_scores_gemma":[0.00025139697,0.000058253343,0.43870142,0.0000119839815,0.0000056090835,0.000014715609,0.0000065897393,0.5539902,0.0016722264,0.000098381315,0.0050716233,0.00011761281],"about_ca_topic_score_codex":0.00001651556,"about_ca_topic_score_gemma":6.0017317e-7,"teacher_disagreement_score":0.99795467,"about_ca_system_score_codex":0.00007940048,"about_ca_system_score_gemma":0.000024645222,"threshold_uncertainty_score":0.29768068},"labels":[],"label_agreement":null},{"id":"W2430237232","doi":"10.1109/isbi.2016.7493349","title":"Multi-loss convolutional networks for gland analysis in microscopy","year":2016,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Task (project management); Image segmentation; Deep learning; Contextual image classification; Feature extraction; Class (philosophy); Machine learning; Image (mathematics)","score_opus":0.016462002490090968,"score_gpt":0.2824684800869484,"score_spread":0.26600647759685747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2430237232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011904159,0.00005327874,0.98683643,0.0006872909,0.00028752204,0.00011394601,0.0000037714285,0.000059008937,0.000054610045],"genre_scores_gemma":[0.82791054,0.000015726127,0.17103104,0.00015590158,0.000067303044,0.000041747502,0.0000013286367,0.0000034821555,0.00077295356],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928135,0.000021334221,0.00014439102,0.0002783355,0.000081999424,0.00019258402],"domain_scores_gemma":[0.99949527,0.00013996268,0.000042157408,0.00023077223,0.00005520977,0.000036612597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019474865,0.00006576408,0.00010740374,0.00013799196,0.000045564197,0.000033888322,0.0002755286,0.00005176107,0.000029327553],"category_scores_gemma":[0.000014709506,0.000045156798,0.0000707978,0.0005336777,0.000034261433,0.00022577427,0.00006094027,0.00003113786,0.000010115158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021540046,0.00034741877,0.77701604,0.000023767292,0.0009079449,0.000010554497,0.0003418205,0.02770322,0.027175205,0.02553344,0.008881626,0.13184358],"study_design_scores_gemma":[0.0012987085,0.000040853974,0.07083867,0.000008158656,0.000021248117,0.0000020381888,0.0000023257405,0.9219033,0.0028260003,0.0006621295,0.002259893,0.00013664094],"about_ca_topic_score_codex":0.00007918031,"about_ca_topic_score_gemma":0.00074118155,"teacher_disagreement_score":0.8942001,"about_ca_system_score_codex":0.00012427305,"about_ca_system_score_gemma":0.000032080814,"threshold_uncertainty_score":0.18414408},"labels":[],"label_agreement":null},{"id":"W2468789395","doi":"10.5539/gjhs.v9n2p215","title":"A Comparative Study for Modelling the Survival of Breast Cancer Patients in the West of Iran","year":2016,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Vice Chancellor for Research and Technology, Kerman University of Medical Sciences; Hamadan University of Medical Sciences","keywords":"Recursive partitioning; Interpretability; Random forest; Breast cancer; Cancer; Medicine; Algorithm; Mathematics; Statistics; Machine learning; Internal medicine; Computer science","score_opus":0.08237678906920132,"score_gpt":0.38024475231358124,"score_spread":0.2978679632443799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468789395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.820228,0.000117883224,0.176461,0.0020647116,0.0006729203,0.0004077655,0.000021662532,0.0000022029164,0.000023857996],"genre_scores_gemma":[0.998699,0.000035814228,0.001149723,0.000073215386,0.000034290744,0.0000061693518,1.5314182e-8,0.0000012198678,5.210378e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978189,0.00017212413,0.0006394023,0.00016470651,0.00094606366,0.00025881396],"domain_scores_gemma":[0.9979765,0.0001651773,0.0009403038,0.00023835953,0.00062513823,0.00005452684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037137324,0.00007523382,0.00025489964,0.00007603023,0.00018445058,0.000029965124,0.0016905738,0.00001262179,8.8629565e-7],"category_scores_gemma":[0.000022701683,0.000033463624,0.000048217833,0.0010420658,0.00029359205,0.00053409237,0.00008918057,0.00008143739,2.5961802e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045706253,0.0014449039,0.8375976,0.000076448414,0.000039978615,0.0000016551807,0.01788396,0.04698556,0.00028188227,0.0047889766,0.0003004612,0.09014148],"study_design_scores_gemma":[0.0014474948,0.0015257992,0.97206396,0.00023013845,0.0000066319826,0.00003105651,0.0018672385,0.020792197,0.00013944982,0.0017916758,0.000025785448,0.00007857625],"about_ca_topic_score_codex":0.0009278474,"about_ca_topic_score_gemma":0.00039046913,"teacher_disagreement_score":0.17847103,"about_ca_system_score_codex":0.00032340788,"about_ca_system_score_gemma":0.00086541293,"threshold_uncertainty_score":0.3141535},"labels":[],"label_agreement":null},{"id":"W2474314021","doi":"10.11575/prism/1155","title":"Computer-aided diagnosis of architectural distortion in mammograms","year":2007,"lang":"en","type":"article","venue":"PRISM (University of Calgary)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mammography; Artificial intelligence; Distortion (music); Orientation (vector space); False positive paradox; Computer science; Computer vision; Feature (linguistics); Breast cancer; Pattern recognition (psychology); Medicine; Cancer; Mathematics; Geometry","score_opus":0.009163882804771196,"score_gpt":0.19807188805534442,"score_spread":0.18890800525057322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474314021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42334953,0.000034623277,0.5759631,0.00010826928,0.00012891565,0.00007301183,6.60675e-8,0.000031252945,0.0003112947],"genre_scores_gemma":[0.81327546,0.000016853792,0.18664157,0.000015123767,0.000009374383,2.1897141e-7,0.0000012022659,0.0000031213938,0.00003707595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991876,0.000041453135,0.00015149708,0.00021888915,0.00022786997,0.00017269154],"domain_scores_gemma":[0.9993835,0.00009072956,0.00015861182,0.0002672046,0.000041901323,0.000058045374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002601294,0.000076947144,0.00016363143,0.00025908602,0.000046623867,0.0000057711572,0.0004790376,0.000064365384,0.000009968523],"category_scores_gemma":[0.0000075125386,0.00009738103,0.000080206984,0.00040895274,0.00010605813,0.00025663362,0.00019959931,0.00012532667,0.0000033750937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035109446,0.00006441731,0.02533602,0.000024102786,0.000009385644,0.00002248088,0.0014329106,0.000020398167,0.00019687196,0.000668004,0.000051763593,0.9721385],"study_design_scores_gemma":[0.00096041587,0.00034987234,0.88794595,0.00007592761,0.000012978315,0.000010662981,0.000035266326,0.102441795,0.004605795,0.0017273945,0.0016214274,0.0002125274],"about_ca_topic_score_codex":0.0019785834,"about_ca_topic_score_gemma":0.00025774445,"teacher_disagreement_score":0.97192603,"about_ca_system_score_codex":0.00013119067,"about_ca_system_score_gemma":0.000026224401,"threshold_uncertainty_score":0.39710832},"labels":[],"label_agreement":null},{"id":"W2479100523","doi":"10.4172/2157-7420.1000e125","title":"Big Data and Visual Analytics in Health and Medicine: From Pipe Dream to Reality","year":2014,"lang":"en","type":"article","venue":"Journal of Health & Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Dream; Big data; Visual analytics; Analytics; Augmented reality; Data science; Computer science; Visualization; Computer graphics (images); Human–computer interaction; Psychology; Artificial intelligence; Data mining","score_opus":0.08096069610693571,"score_gpt":0.39827496540871443,"score_spread":0.31731426930177875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479100523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027099391,0.0009849933,0.8957062,0.07508128,0.00091695366,0.00013168648,0.0000053808044,0.00001645442,0.000057701294],"genre_scores_gemma":[0.8341168,0.010109946,0.07833108,0.07564563,0.0017504491,0.000002228132,0.00001847984,0.000017657778,0.000007721639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592584,0.00029463004,0.0021388908,0.000142053,0.0011645126,0.0003340627],"domain_scores_gemma":[0.9965755,0.00057792204,0.0011165361,0.00042371658,0.00010648535,0.001199873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009558593,0.000127039,0.00059787044,0.00029486127,0.00011577432,0.00005722474,0.0007491795,0.00009606057,0.0000049706246],"category_scores_gemma":[0.0018235524,0.00009564004,0.000015537667,0.0004434878,0.00011945685,0.00058698835,0.00038331284,0.00060826936,0.0000018412455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019206793,0.00003355727,0.0015335622,0.00026014305,0.000011336072,0.000002850349,0.0054590306,0.000020851423,5.699044e-7,0.00019647076,0.012959076,0.97950333],"study_design_scores_gemma":[0.0020715783,0.0029742608,0.013082727,0.0019803455,0.000008773507,0.0002651625,0.0017500748,0.8954866,0.000005685921,0.0036044547,0.07857104,0.00019929037],"about_ca_topic_score_codex":0.001151064,"about_ca_topic_score_gemma":0.00047333512,"teacher_disagreement_score":0.9793041,"about_ca_system_score_codex":0.00020970627,"about_ca_system_score_gemma":0.0012913361,"threshold_uncertainty_score":0.39000878},"labels":[],"label_agreement":null},{"id":"W2480492606","doi":"10.1117/3.1000499.ch1","title":"Detection of Architectural Distortion in Prior Mammograms Using Statistical Measures of Angular Spread","year":2013,"lang":"en","type":"book-chapter","venue":"Society of Photo-Optical Instrumentation Engineers eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mammography; Breast cancer; Distortion (music); Medicine; Breast cancer screening; Radiology; Cancer; Artificial intelligence; Computer science; Internal medicine; Telecommunications","score_opus":0.024919808469957686,"score_gpt":0.24027057752206724,"score_spread":0.21535076905210954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2480492606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09220164,0.00007683769,0.9029599,0.000014882539,0.0004498231,0.00085428316,0.00004616759,0.00007266106,0.003323828],"genre_scores_gemma":[0.87906957,0.000014467596,0.120105006,0.000016257967,0.000045669734,0.000026051594,0.000018295736,0.0000406508,0.0006640469],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99759746,0.000035747635,0.0009312172,0.00042196675,0.00076151866,0.00025208804],"domain_scores_gemma":[0.9986465,0.0001269065,0.0005615202,0.00036732928,0.00020339648,0.00009436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026692133,0.0003188425,0.00053991494,0.00021178028,0.000039724375,0.000022915801,0.0002975832,0.0003554847,0.00003217108],"category_scores_gemma":[0.000025970676,0.000346251,0.00031851858,0.000085494416,0.0005358459,0.00016741003,0.00008816828,0.00042021612,0.000001691194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001178928,0.00008825178,0.00004694599,0.0012681034,0.0004339935,0.0000028129773,0.0042041945,0.0043645045,0.29787967,0.03556648,0.000022798678,0.65600437],"study_design_scores_gemma":[0.0020725206,0.0010382213,0.0009715365,0.0008982623,0.00023427255,0.000035453657,0.00046944374,0.18963604,0.7826512,0.020825593,0.0002169804,0.0009505018],"about_ca_topic_score_codex":0.0004533853,"about_ca_topic_score_gemma":0.000041852374,"teacher_disagreement_score":0.7868679,"about_ca_system_score_codex":0.0004637247,"about_ca_system_score_gemma":0.00012298538,"threshold_uncertainty_score":0.99989897},"labels":[],"label_agreement":null},{"id":"W2486659465","doi":"10.4018/978-1-4666-0059-1.ch002","title":"Digital Image Processing and Machine Learning Techniques for the Detection of Architectural Distortion in Prior Mammograms","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in bioinformatics and biomedical engineering book series","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"","keywords":"Artificial intelligence; Receiver operating characteristic; Mammography; Pattern recognition (psychology); Computer science; Distortion (music); Computer vision; Fractal dimension; Mathematics; Fractal; Breast cancer; Bandwidth (computing); Cancer; Medicine; Machine learning","score_opus":0.0049515934362276155,"score_gpt":0.20661012913871407,"score_spread":0.20165853570248646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486659465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009287843,0.020181367,0.97841597,0.00008291516,0.00017154447,0.00041226653,0.000013001839,0.00010815994,0.0005219194],"genre_scores_gemma":[0.47973642,0.07100203,0.44362396,0.000101911544,0.0006458535,0.00046463433,0.00011792573,0.00017491284,0.004132351],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991219,0.000002535061,0.00039999408,0.00013035847,0.0001707841,0.00017441953],"domain_scores_gemma":[0.99952936,0.00010278691,0.0001955672,0.0001032926,0.000026196165,0.00004278373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018971536,0.00018318188,0.00021525916,0.00021080094,0.00006513713,0.00008906918,0.00014167755,0.00012026872,5.5621024e-7],"category_scores_gemma":[0.00004820354,0.00013367189,0.000031926986,0.00007687739,0.00023410206,0.0017329741,0.00012223158,0.0002888867,1.06833504e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015857288,0.0000033779522,0.00001225324,0.0006868188,0.000004765971,4.3137737e-7,0.00034173395,0.00003653467,0.0001291002,0.0006962569,1.5891811e-7,0.9980727],"study_design_scores_gemma":[0.00056280184,0.0009174939,0.00026702764,0.0018362105,0.00003073982,0.00019689347,0.0000877203,0.38598642,0.0035093406,0.0023970497,0.60346836,0.0007399394],"about_ca_topic_score_codex":0.000003159271,"about_ca_topic_score_gemma":0.000014318588,"teacher_disagreement_score":0.99733275,"about_ca_system_score_codex":0.000059967693,"about_ca_system_score_gemma":0.000016890848,"threshold_uncertainty_score":0.5450981},"labels":[],"label_agreement":null},{"id":"W2488858564","doi":"10.4018/978-1-4666-0059-1.ch005","title":"Advanced Fuzzy Methods for Mammography Image Analysis","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in bioinformatics and biomedical engineering book series","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Research Canada","funders":"","keywords":"Mammography; Breast cancer; Artificial intelligence; Computer-aided diagnosis; Fuzzy logic; Computer science; Feature (linguistics); Feature extraction; Modality (human–computer interaction); Focus (optics); Pattern recognition (psychology); Machine learning; Cancer; Computer vision; Medicine","score_opus":0.0058485925138106794,"score_gpt":0.26487821986122156,"score_spread":0.25902962734741086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488858564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012091537,0.025281211,0.9635249,0.00013105528,0.00075830496,0.00033442795,0.000041443243,0.00018920517,0.009738238],"genre_scores_gemma":[0.000037408216,0.028071854,0.9688813,0.00010610427,0.00012355548,0.00008419143,0.000052277726,0.00003260406,0.0026106678],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824464,0.0000075630587,0.0007082423,0.0003201753,0.00027831417,0.00044105772],"domain_scores_gemma":[0.99875176,0.0002455234,0.00027633636,0.00045090987,0.00007210147,0.00020337255],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046378386,0.00041366252,0.0006511667,0.0009814501,0.00008161679,0.00010847552,0.00046769204,0.00030161263,0.000014470751],"category_scores_gemma":[0.00005314901,0.00037456234,0.00023119237,0.00040369382,0.00024762563,0.0029347895,0.0002367713,0.00031533308,0.0000030549047],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023853523,0.000013183593,0.0000039646716,0.001050054,0.00031441284,0.000002691927,0.0003818278,0.00040481964,0.000092330134,0.15848082,0.000070845235,0.8391612],"study_design_scores_gemma":[0.0002610915,0.00017821214,0.000012841417,0.000162438,0.00013720819,0.0000149089365,0.0000139388185,0.056424055,0.00017434957,0.007822434,0.9342776,0.00052094716],"about_ca_topic_score_codex":0.0000010761868,"about_ca_topic_score_gemma":0.0000035654468,"teacher_disagreement_score":0.9342067,"about_ca_system_score_codex":0.00008607951,"about_ca_system_score_gemma":0.000037357,"threshold_uncertainty_score":0.99987066},"labels":[],"label_agreement":null},{"id":"W2491150822","doi":"10.4103/2153-3539.186899","title":"Clinically-inspired automatic classification of ovarian carcinoma subtypes","year":2016,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Computer science; Ovarian carcinoma; Pathology; Information retrieval; Medicine; Ovarian cancer; Internal medicine; Cancer","score_opus":0.027631960014601598,"score_gpt":0.2819479004930617,"score_spread":0.25431594047846007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491150822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.471882,0.000017366448,0.52613974,0.0007325779,0.0006659833,0.000052665524,0.0000014252626,0.000022397071,0.00048584788],"genre_scores_gemma":[0.8921359,0.000032412023,0.10759918,0.0001348643,0.00007396264,0.0000016624291,1.654734e-7,0.000004369118,0.000017445114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977844,0.00010871645,0.001596759,0.0000611863,0.00029389645,0.00015503803],"domain_scores_gemma":[0.9966338,0.00029277697,0.0021804832,0.00041718184,0.0004049825,0.00007073195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013320021,0.00009309226,0.00028959452,0.00023727868,0.000041240695,0.000020790347,0.0006862084,0.00013949376,0.000012666638],"category_scores_gemma":[0.0004080316,0.000060176153,0.00011112064,0.00021882741,0.00012137913,0.00091227546,0.000086120424,0.00015856724,0.000027822369],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001234081,0.00024979652,0.08110224,0.00028409384,0.00013723494,0.00012848129,0.011469004,0.00009274599,0.03673653,0.022271587,0.0023735699,0.8450313],"study_design_scores_gemma":[0.005063095,0.004441877,0.8338181,0.00049461867,0.00014829347,0.005401598,0.00084148766,0.10541395,0.020382421,0.020936562,0.0024968628,0.0005611517],"about_ca_topic_score_codex":6.7425464e-7,"about_ca_topic_score_gemma":8.989095e-7,"teacher_disagreement_score":0.84447014,"about_ca_system_score_codex":0.00009657863,"about_ca_system_score_gemma":0.00023252556,"threshold_uncertainty_score":0.24539123},"labels":[],"label_agreement":null},{"id":"W2494142696","doi":"10.1117/3.651880.ch15","title":"AMDI — Indexed Atlas of Digital Mammograms that Integrates Case Studies, E-Learning, and Research Systems via the Web","year":2010,"lang":"en","type":"book-chapter","venue":"SPIE eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Mammography; Context (archaeology); Radiology; Malignancy; Breast cancer; Medical physics; Breast imaging; Digital mammography; Magnetic resonance imaging; Breast cancer screening; Cancer; Pathology","score_opus":0.0635779721025344,"score_gpt":0.31731138547817345,"score_spread":0.25373341337563904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494142696","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040364712,0.01578762,0.007439801,0.0005415398,0.009068122,0.0049554706,0.00009232121,0.0009533676,0.92079705],"genre_scores_gemma":[0.72855115,0.00022310791,0.00034513298,0.000012177364,0.00041957642,0.0000948272,0.000003699203,0.00007703367,0.27027327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753827,0.00006669229,0.0004448067,0.0006938608,0.00084821775,0.00040813698],"domain_scores_gemma":[0.99745136,0.00056627486,0.00042621384,0.000908048,0.0005299021,0.00011822132],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012356505,0.0003807778,0.0004941918,0.00030234834,0.00045036446,0.0005492999,0.0008553415,0.00044240462,0.0000071979935],"category_scores_gemma":[0.000094382725,0.00026117027,0.00012272192,0.00006701982,0.0011748668,0.00016773253,0.0011468218,0.0023052385,0.000030172956],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014285673,0.00004788159,0.00093684037,0.0012468706,0.001586575,0.003395786,0.009595949,0.000010533034,0.00212037,0.23454219,0.0032558977,0.7431182],"study_design_scores_gemma":[0.00084740086,0.0017373131,0.0000120217655,0.0014113579,0.0001244184,0.006738731,0.0018784883,0.0027896469,0.0033229007,0.06461471,0.9152285,0.001294499],"about_ca_topic_score_codex":0.00023039717,"about_ca_topic_score_gemma":0.00047265826,"teacher_disagreement_score":0.9119726,"about_ca_system_score_codex":0.0001594643,"about_ca_system_score_gemma":0.00019298415,"threshold_uncertainty_score":0.9999965},"labels":[],"label_agreement":null},{"id":"W2495798027","doi":"10.1007/978-3-319-20379-9_3","title":"Role in Medicine for Digital Pathology","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital du Saint-Sacrement; Université Laval","funders":"","keywords":"Telepathology; Digital pathology; Licensure; Quality assurance; Health care; Medicine; Standardization; Medical physics; Pathology; Computer science; Medical education; Telemedicine; Political science","score_opus":0.042401629137831263,"score_gpt":0.274835634871477,"score_spread":0.23243400573364573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2495798027","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001267951,0.00047905603,0.28959265,0.0007190524,0.0005520956,0.00019530019,0.000005054756,0.00009230289,0.70836323],"genre_scores_gemma":[0.0033754588,0.000050414445,0.009345978,0.00047824316,0.000757066,0.000052313033,0.000020330463,0.000040718627,0.9858795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908537,0.0000035597316,0.00021341095,0.00037512733,0.00017547242,0.00014706221],"domain_scores_gemma":[0.9992974,0.00006781335,0.00008901155,0.0003965294,0.000096138705,0.00005313389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018084284,0.00014774826,0.00024773774,0.00016859612,0.000014142014,0.000025738918,0.0004520008,0.0002076741,0.00006070665],"category_scores_gemma":[0.000028991013,0.00012387296,0.00003888603,0.000027723683,0.000060370174,0.00020611448,0.00015896607,0.00014477488,0.00007551999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011342067,0.0000051143493,0.000004580389,0.0000137833795,0.000009042152,0.000020726111,0.00019981133,0.000010609524,0.000015177661,0.6311475,0.027854204,0.34070808],"study_design_scores_gemma":[0.0002847703,0.00026039095,0.0000049395744,0.000041447944,0.0000027350475,0.000033849512,0.0000043663986,0.0015897272,0.000009042802,0.4543003,0.5433374,0.00013099759],"about_ca_topic_score_codex":0.000009827697,"about_ca_topic_score_gemma":0.000067449044,"teacher_disagreement_score":0.5154832,"about_ca_system_score_codex":0.00015492855,"about_ca_system_score_gemma":0.000080924445,"threshold_uncertainty_score":0.5051393},"labels":[],"label_agreement":null},{"id":"W2496423522","doi":"10.1007/978-3-319-41546-8_58","title":"Markovian Approach to Automatic Annotation of Breast Mass Spicules Using an A Contrario Model","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Curvilinear coordinates; Computer science; Sponge spicule; Mammography; Artificial intelligence; Annotation; Pattern recognition (psychology); Computer vision; Mathematics; Geometry; Geology; Paleontology; Breast cancer; Medicine","score_opus":0.02511975715220021,"score_gpt":0.24718200159017847,"score_spread":0.22206224443797826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496423522","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005954185,0.000048507154,0.99599427,0.00020785953,0.0007221326,0.0006035301,0.00001891751,0.00016456288,0.0016448197],"genre_scores_gemma":[0.24185257,0.000002555583,0.7575214,0.0003102009,0.00020835466,0.000011058302,0.0000018384621,0.000030773597,0.000061230756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962232,0.000052451156,0.0006313772,0.0014642304,0.0010654492,0.0005632873],"domain_scores_gemma":[0.9973991,0.00014319886,0.00044839818,0.0014020406,0.0003816762,0.00022560236],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080072,0.00047847323,0.00056406774,0.0010014441,0.00018221434,0.0003282308,0.002546633,0.0002943397,0.0000046892756],"category_scores_gemma":[0.000033069693,0.0004095366,0.00010863989,0.00062448904,0.00042757826,0.0012230324,0.0005309045,0.0003595028,0.0000064930396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008191689,0.00003477766,0.000013676144,0.0000682033,0.000010223516,0.0000050831227,0.00091469084,0.44878638,0.0027493348,0.00961354,0.000002132774,0.53779376],"study_design_scores_gemma":[0.000207216,0.00012369358,0.000103940656,0.00041261982,0.000009832761,0.00009260028,2.8031693e-7,0.92026573,0.0011180213,0.07719771,0.000009989704,0.00045835055],"about_ca_topic_score_codex":0.000035513942,"about_ca_topic_score_gemma":0.000035397446,"teacher_disagreement_score":0.5373354,"about_ca_system_score_codex":0.0006978086,"about_ca_system_score_gemma":0.0007870427,"threshold_uncertainty_score":0.99983567},"labels":[],"label_agreement":null},{"id":"W2509908095","doi":"10.1594/ecr2014/b-0060","title":"The 3D mammography: the imaging of the future?","year":2014,"lang":"en","type":"article","venue":"European Society of Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mammography; Medicine; Medical imaging; Medical physics; Remote sensing; Geology; Radiology; Breast cancer; Cancer; Internal medicine","score_opus":0.00470311978884719,"score_gpt":0.19649879842060902,"score_spread":0.19179567863176183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509908095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066423714,0.009275025,0.8069526,0.077013515,0.0105767045,0.00066269207,0.0000068885947,0.00029190606,0.028796947],"genre_scores_gemma":[0.98893243,0.00042134794,0.0077792606,0.001962692,0.0007522987,0.0000032927614,2.8895994e-7,0.000015326788,0.00013304531],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846244,0.0008071493,0.00020419704,0.00018963104,0.0001492966,0.00018728545],"domain_scores_gemma":[0.99849993,0.00030151603,0.00023980136,0.0008808531,0.00006004941,0.000017835806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015524435,0.00008644707,0.0001097026,0.000008873217,0.0003543118,0.000021362222,0.0017650756,0.000021617889,0.0000021743188],"category_scores_gemma":[0.00002441856,0.000040744708,0.00025179057,0.000262758,0.00071577897,0.000059845912,0.00034230834,0.00021665196,0.00000508687],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017827593,0.00003267057,0.02473439,0.00004192425,0.00023153127,8.193979e-7,0.010518871,0.0005510295,0.0068240436,0.04846138,0.35787997,0.55070555],"study_design_scores_gemma":[0.00040907643,0.00011271492,0.14226134,0.000018602057,0.000023008493,0.00012448757,0.0006454689,0.02280066,0.001523543,0.0035483718,0.82836014,0.00017257841],"about_ca_topic_score_codex":0.000008433028,"about_ca_topic_score_gemma":0.0000032489445,"teacher_disagreement_score":0.9225087,"about_ca_system_score_codex":0.000016620896,"about_ca_system_score_gemma":0.00002120831,"threshold_uncertainty_score":0.3279979},"labels":[],"label_agreement":null},{"id":"W2512200971","doi":"","title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2011: 14th International Conference, Toronto, Canada, September 18-22, 2011, ... Vision, Pattern Recognition, and Graphics)","year":2011,"lang":"en","type":"book","venue":"Springer eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Presentation (obstetrics); Computer graphics; Volume (thermodynamics); Graphics; Library science; Computer graphics (images); Medicine; Surgery","score_opus":0.023765847979485673,"score_gpt":0.25642074120757186,"score_spread":0.2326548932280862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512200971","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003219457,0.0014115033,0.5739348,0.00036019873,0.012148977,0.0010953974,0.00020241099,0.0005765389,0.40705073],"genre_scores_gemma":[0.17958762,0.0017987076,0.08782158,0.007445775,0.011564701,0.00035899127,0.0013150839,0.00093737047,0.70917016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99636596,0.00016669251,0.0008667141,0.0011892361,0.0009740996,0.0004372833],"domain_scores_gemma":[0.9976801,0.000121228106,0.00066782424,0.0005836542,0.0005734962,0.00037364545],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006650555,0.00055557577,0.00054629106,0.00022572666,0.000228606,0.00040311605,0.000993825,0.0004856585,0.0021393008],"category_scores_gemma":[0.00001239143,0.00059407315,0.0001486064,0.000024512472,0.0003025072,0.00045014409,0.0013111427,0.0007402362,0.000059452974],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002511244,0.00006366884,0.00030323098,0.00029744694,0.00034407058,0.000121350444,0.0003753675,1.3775539e-7,0.000024101431,0.001011523,0.12598698,0.871447],"study_design_scores_gemma":[0.009772181,0.0016768452,0.052656848,0.011091071,0.0005585884,0.0024202943,0.00015357832,0.14249115,0.0007727813,0.03149926,0.7395512,0.0073561925],"about_ca_topic_score_codex":0.09896086,"about_ca_topic_score_gemma":0.30596015,"teacher_disagreement_score":0.8640908,"about_ca_system_score_codex":0.00063383754,"about_ca_system_score_gemma":0.0007832714,"threshold_uncertainty_score":0.9996511},"labels":[],"label_agreement":null},{"id":"W2516697145","doi":"10.1109/icip.2016.7532835","title":"Multispectral texture analysis of histopathological abnormalities in colorectal tissues","year":2016,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Multispectral image; Artificial intelligence; Pattern recognition (psychology); Wavelet; Random forest; Texture (cosmology); Computer science; Pathology; Gabor wavelet; Medicine; Wavelet transform; Discrete wavelet transform; Image (mathematics)","score_opus":0.010829087089524386,"score_gpt":0.24829962482894344,"score_spread":0.23747053773941906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516697145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.679721,0.00007397568,0.3165516,0.00041349922,0.00014394106,0.000059921866,0.000003514801,0.000102082035,0.0029304475],"genre_scores_gemma":[0.9896425,0.000017237695,0.009713406,0.00003345216,0.00001750254,0.000009222523,3.3719883e-7,0.0000021079525,0.0005642129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991841,0.00006203049,0.00019806098,0.00024092323,0.00015653168,0.00015837846],"domain_scores_gemma":[0.99956244,0.00010565601,0.000060401235,0.00020773968,0.000035513473,0.00002822004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018850609,0.000073468844,0.00019811928,0.0002821325,0.000018610172,0.000012832046,0.00033003517,0.000063449916,0.00016260945],"category_scores_gemma":[0.00003365054,0.000044920154,0.000077724,0.0007418252,0.000080643505,0.00026545647,0.00008737998,0.000049618964,0.000009155767],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011790372,0.0002743257,0.4928968,0.000022219783,0.00026218905,0.0001395839,0.00541722,0.0005659821,0.09277546,0.13802804,0.0008071202,0.26869318],"study_design_scores_gemma":[0.00043221828,0.00028979636,0.9054353,0.00001551359,0.000046004705,0.000016627188,0.00007880605,0.020295078,0.07032511,0.0021555393,0.0006813808,0.00022863345],"about_ca_topic_score_codex":0.00020675057,"about_ca_topic_score_gemma":0.0007994069,"teacher_disagreement_score":0.4125385,"about_ca_system_score_codex":0.00012811077,"about_ca_system_score_gemma":0.00001837713,"threshold_uncertainty_score":0.18317907},"labels":[],"label_agreement":null},{"id":"W2520304734","doi":"10.1007/978-3-319-46604-0_20","title":"Cell Counting by Regression Using Convolutional Neural Network","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Residual; Regression; Cell counting; Pattern recognition (psychology); Artificial neural network; Quantization (signal processing); Deep learning; Machine learning; Computer vision; Statistics; Cancer; Algorithm; Mathematics","score_opus":0.017181402904387112,"score_gpt":0.24176982211921175,"score_spread":0.22458841921482464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520304734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018218937,0.0017020178,0.9894483,0.00044299584,0.0055218632,0.00027683913,0.0000079677575,0.0001971768,0.0022206318],"genre_scores_gemma":[0.3197593,0.00012060368,0.6699928,0.003058131,0.0052029784,0.000015068742,0.000008688896,0.00013057192,0.0017118575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955227,0.00005431291,0.0005500412,0.0016721883,0.0012886296,0.00091217615],"domain_scores_gemma":[0.99742913,0.0004685292,0.00056745677,0.001086214,0.0002806389,0.00016800221],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088099035,0.00055975746,0.00045664498,0.00037186797,0.0005803624,0.0004524127,0.0025699157,0.00039978555,0.000032505373],"category_scores_gemma":[0.00003450596,0.00045686687,0.0001302095,0.0005477855,0.00069787505,0.0009862788,0.0014158717,0.00080549903,0.00003297347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025098398,0.000033354798,0.0003762708,0.0000851972,0.000017415216,0.0000827736,0.00028893817,0.24054238,0.0049148086,0.008448323,0.0018768352,0.7433086],"study_design_scores_gemma":[0.00029605662,0.00009904569,0.00002849526,0.000697644,0.0000073513474,0.00009268211,4.6639364e-8,0.9333669,0.0020707694,0.058386825,0.0042415624,0.0007126534],"about_ca_topic_score_codex":0.000019860014,"about_ca_topic_score_gemma":0.000010803973,"teacher_disagreement_score":0.742596,"about_ca_system_score_codex":0.0009644363,"about_ca_system_score_gemma":0.0006078296,"threshold_uncertainty_score":0.9997883},"labels":[],"label_agreement":null},{"id":"W2525247990","doi":"10.1016/b978-0-12-804076-8.00003-7","title":"Deep learning of brain images and its application to multiple sclerosis","year":2016,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Artificial intelligence; Convolutional neural network; Computer science; Boltzmann machine; Neuroimaging; Feature (linguistics); Focus (optics); Pattern recognition (psychology); Machine learning; Dimensionality reduction; Neuroscience; Psychology","score_opus":0.01791464114269168,"score_gpt":0.22900177241815325,"score_spread":0.21108713127546158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525247990","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006862608,0.0012836161,0.2068884,0.0004693974,0.00025384617,0.0009032716,0.000008913752,0.00019037952,0.78993356],"genre_scores_gemma":[0.055844184,0.00017715635,0.0070944354,0.00030295426,0.0002630376,0.0001522099,0.0000018669573,0.00007293451,0.93609124],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862784,0.000031190037,0.0003040706,0.0005742094,0.0002742823,0.00018842124],"domain_scores_gemma":[0.99880743,0.00017159535,0.00029034057,0.0004795011,0.00014664205,0.000104467304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026090918,0.00023575098,0.00029526444,0.00018189715,0.00010082818,0.00004313251,0.00045602772,0.00017266195,0.000010955189],"category_scores_gemma":[0.000050019647,0.00021837652,0.000076451484,0.000024873134,0.0000521555,0.00012050762,0.00037090463,0.00021260609,0.000094880714],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005066104,0.0000014722749,0.0000065890067,0.000042809806,0.000016663002,4.712169e-7,0.00019675866,0.000008700153,0.0076155206,0.0049327035,0.000016718546,0.9871565],"study_design_scores_gemma":[0.0004927505,0.00025646848,0.00033961478,0.0009169377,0.0000351571,0.000012591371,0.000004651575,0.0038544422,0.01963646,0.01011983,0.9636115,0.00071962783],"about_ca_topic_score_codex":7.132968e-7,"about_ca_topic_score_gemma":0.00001056997,"teacher_disagreement_score":0.9864369,"about_ca_system_score_codex":0.00009554996,"about_ca_system_score_gemma":0.000034470446,"threshold_uncertainty_score":0.8905136},"labels":[],"label_agreement":null},{"id":"W2526499595","doi":"10.1007/978-3-319-46723-8_53","title":"Topology Aware Fully Convolutional Networks for Histology Gland Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; ENCODE; Convolutional neural network; Prior probability; Dice; Pattern recognition (psychology); Deep learning; Object (grammar); Object detection; Network topology; Image segmentation; Computer vision; Pixel; Topology (electrical circuits); Mathematics; Computer network","score_opus":0.01510039814091865,"score_gpt":0.25471358831132535,"score_spread":0.2396131901704067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2526499595","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012510985,0.00047940778,0.98825175,0.0025508404,0.007167813,0.0005854998,0.0000142763865,0.00015000491,0.0007878925],"genre_scores_gemma":[0.13417006,0.00014637278,0.8513325,0.0054636127,0.006004717,0.00022137535,0.000044621393,0.00010300897,0.0025137616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969055,0.000042464926,0.0004793232,0.0014321102,0.0004800718,0.000660516],"domain_scores_gemma":[0.99757475,0.0007844844,0.00037685983,0.0007947753,0.0003501695,0.00011898018],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000578977,0.00040520472,0.00044059285,0.00054201233,0.00033665085,0.00014360208,0.0017830572,0.0004942725,0.00003942658],"category_scores_gemma":[0.000041034225,0.00035776396,0.00012632553,0.00024758524,0.0009057648,0.00046065537,0.00057136174,0.00042154331,0.000020573983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035464873,0.000013289072,0.00008372761,0.000029945497,0.000019906594,0.00001819797,0.00016799386,0.02560913,0.00012413831,0.05350042,0.00031642438,0.9200814],"study_design_scores_gemma":[0.0007757268,0.000488821,0.00010758497,0.00014546831,0.000012867743,0.00019497384,1.2366277e-7,0.71055716,0.00049438013,0.2779468,0.008641042,0.00063503045],"about_ca_topic_score_codex":0.000012614403,"about_ca_topic_score_gemma":0.00012609383,"teacher_disagreement_score":0.91944635,"about_ca_system_score_codex":0.001089609,"about_ca_system_score_gemma":0.0006459719,"threshold_uncertainty_score":0.9998874},"labels":[],"label_agreement":null},{"id":"W2529631604","doi":"10.1038/srep33985","title":"Multi-Pass Adaptive Voting for Nuclei Detection in Histopathological Images","year":2016,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Jiangsu Province; Government of Jiangsu Province; National Natural Science Foundation of China; U.S. Department of Defense; Case Comprehensive Cancer Center, Case Western Reserve University; National Institutes of Health; National Cancer Institute; Case Western Reserve University; Cleveland Clinic; Wallace H. Coulter Foundation; Natural Science Basic Research Program of Shaanxi Province","keywords":"Computer science; H&E stain; Artificial intelligence; Voting; Context (archaeology); Digital pathology; Noise (video); Majority rule; Precision and recall; Ground truth; Pattern recognition (psychology); Computer vision; Staining; Pathology; Image (mathematics); Medicine; Biology","score_opus":0.03103077541111958,"score_gpt":0.26452920782763234,"score_spread":0.23349843241651275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529631604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07657422,0.00003748324,0.9136814,0.00023308942,0.008779928,0.00036162982,0.000001056295,0.00020336424,0.00012782712],"genre_scores_gemma":[0.9331457,8.3564277e-7,0.065579206,0.000016867834,0.00006447854,0.00009917182,4.1839553e-7,0.000009014228,0.001084303],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99783224,0.00006641524,0.00040733302,0.0010508018,0.00029695968,0.00034624588],"domain_scores_gemma":[0.9987584,0.000096238364,0.00029134098,0.00061579276,0.00017082243,0.00006745362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019228422,0.000120783625,0.00014337528,0.00022145869,0.0002718451,0.00018419574,0.00028070546,0.0000794749,0.000007756046],"category_scores_gemma":[0.00041202424,0.000087873836,0.00008210923,0.0004841319,0.00017364294,0.0007116456,0.00015475949,0.00008116115,0.000016543097],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017290979,0.00007579453,0.0019945453,0.000010077476,0.000003344028,0.000222414,0.00030571708,0.00006982496,0.6681328,0.0002678,0.00092020707,0.32798022],"study_design_scores_gemma":[0.0011739084,0.00040353928,0.04915845,0.00019140086,0.0000128267775,0.0009910461,0.000088392684,0.07238436,0.8245441,0.027377577,0.022846108,0.0008283195],"about_ca_topic_score_codex":0.000018701387,"about_ca_topic_score_gemma":0.00009899017,"teacher_disagreement_score":0.8565715,"about_ca_system_score_codex":0.0003961115,"about_ca_system_score_gemma":0.00007371313,"threshold_uncertainty_score":0.3583391},"labels":[],"label_agreement":null},{"id":"W2530808190","doi":"10.1016/j.compbiomed.2016.10.007","title":"Influence of feature set reduction on breast cancer malignancy classification of fine needle aspiration biopsies","year":2016,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Grading (engineering); Malignancy; Feature selection; Pattern recognition (psychology); Artificial intelligence; Computer science; Breast cancer; Feature (linguistics); Support vector machine; Biopsy; Cancer; Radiology; Medicine; Pathology; Internal medicine; Biology","score_opus":0.021393078014968536,"score_gpt":0.30484766430386406,"score_spread":0.2834545862888955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530808190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93431646,0.0003900069,0.054285534,0.010136175,0.000664059,0.00013006707,0.000009399444,0.000026166404,0.000042160005],"genre_scores_gemma":[0.9979978,0.0002860841,0.001461932,0.00009891186,0.000120456294,0.0000123565105,0.0000030593806,0.0000027306014,0.000016630469],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99928427,0.000067702094,0.00022387324,0.00024928612,0.000073868636,0.00010100412],"domain_scores_gemma":[0.99935377,0.00009123642,0.00020716127,0.00021951995,0.0001023633,0.000025968198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020357875,0.000087693756,0.00018279637,0.00019758791,0.000027696242,0.0000017361767,0.00017322334,0.00010898643,0.0000030459723],"category_scores_gemma":[0.000027878024,0.00005603622,0.000012754797,0.0003036421,0.0002994265,0.00014782588,0.00004325763,0.00007105311,4.9872494e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012192293,0.000035624354,0.0307012,0.000067528264,0.000019767123,8.2894206e-7,0.00083933654,0.00040028564,0.4506908,0.019562846,0.00081561186,0.49674425],"study_design_scores_gemma":[0.0012166692,0.0010149934,0.9665865,0.0011822471,0.000009867791,0.000052163632,0.000037091628,0.0029438569,0.021328384,0.0052022375,0.00029692508,0.00012907539],"about_ca_topic_score_codex":0.000078519704,"about_ca_topic_score_gemma":0.000015872278,"teacher_disagreement_score":0.9358853,"about_ca_system_score_codex":0.00005269936,"about_ca_system_score_gemma":0.000031615786,"threshold_uncertainty_score":0.22850907},"labels":[],"label_agreement":null},{"id":"W2535673986","doi":"10.1109/tencon.1993.320144","title":"Use of neural network analysis to diagnose breast cancer patients","year":2002,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Artificial neural network; Breast cancer; Linear discriminant analysis; Logistic regression; Artificial intelligence; Computer science; Multivariate statistics; Set (abstract data type); Statistical analysis; Cancer; Pattern recognition (psychology); Machine learning; Statistics; Medicine; Internal medicine; Mathematics","score_opus":0.02514335091316833,"score_gpt":0.24230100282306366,"score_spread":0.21715765190989533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2535673986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82423335,0.00006743949,0.17206547,0.00179574,0.0009969468,0.00024270431,0.00002064898,0.00016717115,0.00041054148],"genre_scores_gemma":[0.993044,0.000023442055,0.0057596886,0.00077326177,0.00008034592,0.000022619148,5.240216e-7,0.0000047469725,0.00029134282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990918,0.000033997672,0.00017657694,0.00026133613,0.00023701541,0.00019927397],"domain_scores_gemma":[0.99925804,0.00006453394,0.00007113096,0.00039319828,0.00012505955,0.00008806242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000042158452,0.000081920945,0.00014060421,0.00012577264,0.00004590955,0.000058268266,0.00032509436,0.00002737783,0.00038781998],"category_scores_gemma":[0.000010325582,0.000072069575,0.00008218791,0.0020389296,0.000013562501,0.00044586885,0.00015415132,0.00004640361,0.000019205676],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006581439,0.000096983415,0.5934737,0.0000028031257,0.00016120521,0.0000012572754,0.0002456998,0.17712386,0.00001447796,0.00016616093,0.029845564,0.19886172],"study_design_scores_gemma":[0.00009658145,0.000063024345,0.5186706,0.0000051372626,0.00005323955,5.920802e-7,0.0000011765721,0.4795283,0.0001811335,0.000022480532,0.0012563841,0.00012132923],"about_ca_topic_score_codex":0.0013422935,"about_ca_topic_score_gemma":0.000960646,"teacher_disagreement_score":0.30240446,"about_ca_system_score_codex":0.00006809911,"about_ca_system_score_gemma":0.00000504028,"threshold_uncertainty_score":0.4246357},"labels":[],"label_agreement":null},{"id":"W2541938964","doi":"10.1109/tic-sth.2009.5444438","title":"Mass candidate detection and segmentation in digitized mammograms","year":2009,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agfa-Gevaert (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; False positive paradox; Computer vision; Image segmentation; Pattern recognition (psychology); Segmentation; CAD; Filter (signal processing); Image processing; Gabor filter; Image resolution; Image (mathematics); Engineering","score_opus":0.0067116286917265075,"score_gpt":0.23315703520817624,"score_spread":0.22644540651644973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2541938964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15459822,0.000023504987,0.8419692,0.00052118365,0.00015901806,0.00013249848,1.8419904e-7,0.00018246532,0.002413714],"genre_scores_gemma":[0.9839581,0.000024675543,0.015604256,0.000235914,0.000019914176,0.000009860451,5.3616844e-7,0.0000022105298,0.00014450274],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943453,0.000023161383,0.00011130023,0.00020189896,0.00010696564,0.00012211333],"domain_scores_gemma":[0.99977547,0.000013715609,0.00003191483,0.0001303509,0.000015008354,0.000033526798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010702311,0.000060588976,0.000059519967,0.00009635362,0.00004000329,0.0001230368,0.000091733054,0.00003164862,0.0000042986776],"category_scores_gemma":[0.000005101377,0.000058130267,0.000011250815,0.0002913209,0.000009530699,0.0005540033,0.000016142585,0.00005544887,0.0000056667855],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013807624,0.000010637219,0.00078594714,0.0000026402417,0.0000018804487,0.0000035923167,0.00016731619,0.00006598892,0.042539224,0.0010768563,0.000022551692,0.95530957],"study_design_scores_gemma":[0.003595305,0.0009413513,0.13708644,0.000041318188,0.000009144822,0.0000835461,0.00019168074,0.31378126,0.42107773,0.12092707,0.0015672985,0.00069786824],"about_ca_topic_score_codex":0.00014427982,"about_ca_topic_score_gemma":0.00028959216,"teacher_disagreement_score":0.9546117,"about_ca_system_score_codex":0.0000942832,"about_ca_system_score_gemma":0.000010052494,"threshold_uncertainty_score":0.23704836},"labels":[],"label_agreement":null},{"id":"W2545541238","doi":"","title":"Medical Image Computing and Computer-Assisted Intervention - Miccai 2003: 6th International Conference, Montreal, Canada, November 2003: Proceedings (LECTURE NOTES IN COMPUTER SCIENCE)","year":2004,"lang":"en","type":"article","venue":"Medical Image Computing and Computer-Assisted Intervention","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Multimedia; Library science; Data science","score_opus":0.011382677867195377,"score_gpt":0.2738418441167159,"score_spread":0.26245916624952054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545541238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24117032,0.00023940492,0.75131613,0.0020184726,0.0042232196,0.0005069841,0.000010936383,0.00037790678,0.00013660808],"genre_scores_gemma":[0.86602616,0.000057238594,0.13152687,0.0010962647,0.0011364736,0.000018057122,0.0000729012,0.000055067772,0.000010954269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9910215,0.00033283953,0.0021084663,0.0022697991,0.0029650715,0.0013023092],"domain_scores_gemma":[0.99518543,0.00022638896,0.00096167304,0.0005722214,0.0020460826,0.0010082196],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032635606,0.0008783228,0.0010511002,0.00095464103,0.0007445426,0.0019467846,0.0023544987,0.0005214437,0.00011113645],"category_scores_gemma":[0.00060672534,0.0008762875,0.00023516071,0.002790909,0.0011179382,0.0015368618,0.0030074522,0.001633641,0.000012419904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000700225,0.0011337426,0.0020478212,0.0003746197,0.00016612929,0.0003843739,0.0010869897,0.00034748807,0.00026334848,0.0010768492,0.001400251,0.9916484],"study_design_scores_gemma":[0.005199047,0.0006898094,0.07019214,0.0039027391,0.00003910899,0.0014482738,0.000068757545,0.9163297,0.0006020172,0.00049546245,0.0002041939,0.00082875893],"about_ca_topic_score_codex":0.044207815,"about_ca_topic_score_gemma":0.040840585,"teacher_disagreement_score":0.99081963,"about_ca_system_score_codex":0.001277088,"about_ca_system_score_gemma":0.0013939582,"threshold_uncertainty_score":0.9993688},"labels":[],"label_agreement":null},{"id":"W2548283510","doi":"10.1109/ccece.2016.7726763","title":"Human blastocyst segmentation using neural network","year":2016,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial neural network; Discrete cosine transform; Backpropagation; JPEG; Artificial intelligence; Segmentation; Pattern recognition (psychology); Image segmentation; Feedforward neural network; Computer vision; Data compression; Image (mathematics)","score_opus":0.03263712937762351,"score_gpt":0.2871942406956451,"score_spread":0.25455711131802156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548283510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15644461,0.0000072598386,0.84144205,0.0002905408,0.00057149545,0.00006968321,1.267925e-7,0.00016901715,0.0010052097],"genre_scores_gemma":[0.9549121,7.0652476e-7,0.044023458,0.00022007227,0.00029543432,0.000005263794,9.635089e-8,0.0000053406447,0.0005375294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993897,0.000029943829,0.00010442092,0.00018769456,0.00012733082,0.00016091407],"domain_scores_gemma":[0.9996493,0.000023436054,0.00004984832,0.0002183435,0.000025974074,0.000033112796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009189686,0.000058291258,0.00004721754,0.000028089775,0.00013398583,0.000056162717,0.00021349963,0.000022833095,0.000055666525],"category_scores_gemma":[0.0000030153076,0.00004007801,0.000022229477,0.00016067899,0.000018947847,0.00055286987,0.0000885272,0.000026567792,0.000034413046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009863335,0.000031506752,0.0063047744,0.000010364709,0.000028923352,0.0000086068585,0.00029206937,0.025488911,0.39069253,0.03129232,0.009201014,0.5366391],"study_design_scores_gemma":[0.001955987,0.0005528903,0.018933117,0.000111276524,0.000019743784,0.00011122341,0.00004195501,0.86447114,0.08561397,0.022415634,0.0048830523,0.00089002476],"about_ca_topic_score_codex":0.000034598663,"about_ca_topic_score_gemma":0.000028157487,"teacher_disagreement_score":0.8389822,"about_ca_system_score_codex":0.000119110846,"about_ca_system_score_gemma":0.000013118195,"threshold_uncertainty_score":0.16343339},"labels":[],"label_agreement":null},{"id":"W2559193574","doi":"10.4103/2153-3539.194841","title":"A multisite validation of whole slide imaging for primary diagnosis using standardized data collection and analysis","year":2016,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto General Hospital","funders":"","keywords":"Computer science; Information retrieval; Data collection; Data mining; Data science; Medical physics; Statistics; Medicine; Mathematics","score_opus":0.029422479462186252,"score_gpt":0.3053794351649015,"score_spread":0.2759569557027153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559193574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2908597,0.00006213916,0.7085644,0.0001863021,0.0001895634,0.00008361602,0.000040092684,0.000007046688,0.000007153333],"genre_scores_gemma":[0.36197144,0.00019139258,0.6376845,0.00008432171,0.000047732283,0.0000042543684,0.0000058001283,0.000005367253,0.0000051652487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987654,0.00006886639,0.00074985996,0.000081048995,0.00021865914,0.00011615364],"domain_scores_gemma":[0.99762464,0.00032828707,0.0012655564,0.0003309993,0.00041132243,0.00003920544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014166759,0.00007686015,0.0003020196,0.0005003745,0.00008708421,0.000047890604,0.00034011778,0.000048818412,0.0000015863468],"category_scores_gemma":[0.0002958158,0.00005645562,0.000075441574,0.00044449067,0.00005649824,0.0020737688,0.00018061405,0.00006712908,2.464854e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004370019,0.00015209516,0.37934926,0.00044498514,0.0013780376,0.00004307468,0.009860887,0.005377999,0.05625318,0.00016814904,0.0029156753,0.54361963],"study_design_scores_gemma":[0.007464123,0.00082822546,0.04491647,0.00040251407,0.0021403192,0.0017336082,0.00063300045,0.8620436,0.07420164,0.0022403332,0.002912141,0.0004840339],"about_ca_topic_score_codex":0.0000032626097,"about_ca_topic_score_gemma":0.0000027495767,"teacher_disagreement_score":0.8566656,"about_ca_system_score_codex":0.0001540133,"about_ca_system_score_gemma":0.000091282855,"threshold_uncertainty_score":0.23021933},"labels":[],"label_agreement":null},{"id":"W2559576502","doi":"10.1594/ecr2011/c-1825","title":"'One-day' diagnosis: the underestimation rate of rapid histological processing","year":2011,"lang":"en","type":"article","venue":"European Society of Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Neurotrauma Foundation","funders":"","keywords":"Medicine","score_opus":0.07313269383872499,"score_gpt":0.2510317453237448,"score_spread":0.17789905148501978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559576502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038393088,0.0019681216,0.9516473,0.0015511878,0.00038358386,0.00019111308,0.0000015661682,0.00014448803,0.005719584],"genre_scores_gemma":[0.9504311,0.0002838735,0.048693456,0.00048087814,0.00006812092,0.000009447245,9.712286e-7,0.000009376083,0.000022790979],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985235,0.00069871923,0.00029063888,0.00024393383,0.000085189626,0.000158052],"domain_scores_gemma":[0.9990127,0.00018339072,0.00035033774,0.0003431322,0.00008409189,0.000026357493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204712,0.00008852783,0.00018031758,0.000019438145,0.00010829998,0.000008590835,0.00070476637,0.00005236526,0.00002241773],"category_scores_gemma":[0.000073136536,0.00006798022,0.00011622016,0.00019496963,0.0004631939,0.00016099191,0.0001550476,0.00015067687,0.000011235427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066136345,0.00038643696,0.0075566247,0.00029563956,0.00027977917,0.000008775376,0.054306313,0.0005096174,0.012653763,0.022834241,0.06043415,0.8406685],"study_design_scores_gemma":[0.00288772,0.003913565,0.76194173,0.00036346557,0.00021850229,0.00030718616,0.0019793955,0.109514825,0.056074884,0.03306309,0.028497593,0.0012380165],"about_ca_topic_score_codex":0.000011237603,"about_ca_topic_score_gemma":7.3927487e-7,"teacher_disagreement_score":0.912038,"about_ca_system_score_codex":0.000043367596,"about_ca_system_score_gemma":0.000041784875,"threshold_uncertainty_score":0.27721527},"labels":[],"label_agreement":null},{"id":"W2560028940","doi":"10.1098/rsos.160558","title":"Automatic prediction of tumour malignancy in breast cancer with fractal dimension","year":2016,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Histopathology; Support vector machine; Breast cancer; Fractal dimension; Artificial intelligence; Malignancy; Pattern recognition (psychology); Cancer; Computer science; Fractal; Medicine; Machine learning; Mathematics; Pathology; Internal medicine","score_opus":0.010223948910085042,"score_gpt":0.25450669782716234,"score_spread":0.2442827489170773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560028940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9193459,0.000031325064,0.0766802,0.002465001,0.00037286794,0.00043801856,0.000020686133,0.000089715475,0.000556279],"genre_scores_gemma":[0.9838091,0.000019568752,0.015844427,0.0001137933,0.000027299686,0.00005365617,1.5090554e-7,0.0000067983515,0.00012520063],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99806136,0.00003558229,0.00025115415,0.0005848982,0.00072400615,0.00034301664],"domain_scores_gemma":[0.9990314,0.000051746345,0.0001957585,0.00044350504,0.00018417201,0.000093410614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009188451,0.00012168542,0.00017192478,0.000053216136,0.00020510917,0.00014728395,0.0019168278,0.000047320576,0.000057034995],"category_scores_gemma":[0.00001645869,0.00007729089,0.000043086537,0.0012001848,0.00038354885,0.0019513376,0.0007912855,0.000088849076,0.000009725723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000736105,0.00041421116,0.2693755,0.000116401505,0.000040681265,0.00001307143,0.0060012,0.002525275,0.31452495,0.0032676754,0.0035781139,0.4000693],"study_design_scores_gemma":[0.0008589972,0.00015251624,0.71995413,0.00057489146,0.0000052882892,0.000023172895,0.00009693098,0.2507299,0.026990354,0.000383874,0.000046174333,0.00018375965],"about_ca_topic_score_codex":0.0009720195,"about_ca_topic_score_gemma":0.000055711265,"teacher_disagreement_score":0.45057863,"about_ca_system_score_codex":0.00048451807,"about_ca_system_score_gemma":0.00061373896,"threshold_uncertainty_score":0.35619748},"labels":[],"label_agreement":null},{"id":"W2561944749","doi":"10.1093/ajcp/138.suppl1.178","title":"Recommendations for Validating Whole Slide Imaging in Pathology: College of American Pathologists Pathology and Laboratory Quality Center","year":2012,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Pathology; Medicine; Center (category theory); Anatomical pathology; Medical physics; Medical laboratory; Surgical pathology","score_opus":0.07600714967257086,"score_gpt":0.43130690415238176,"score_spread":0.3552997544798109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561944749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8410392,0.00023567959,0.1507959,0.0058386796,0.0016533866,0.0001994962,0.00016116303,0.00002899548,0.00004750787],"genre_scores_gemma":[0.84368616,0.00018672638,0.15389623,0.0018826226,0.00029805425,0.000020715397,0.000003891122,0.000020596475,0.0000049783775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992762,0.003302826,0.002610041,0.0004924756,0.00021443111,0.0006181844],"domain_scores_gemma":[0.9917028,0.003228362,0.0038001975,0.0005452902,0.00047368408,0.0002496698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0097220335,0.00024058299,0.0013786871,0.00037716754,0.000094671115,0.000015339492,0.0006408649,0.00012049181,0.000004731479],"category_scores_gemma":[0.0033309488,0.00022569671,0.00024012342,0.0007065449,0.0016790305,0.0005972746,0.0003036203,0.00072285574,0.0000029349703],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002314387,0.00052895996,0.64142394,0.000022181886,0.000027289132,0.00027625542,0.0014160676,0.0000125376055,0.00392286,0.0012920703,0.00059105875,0.35025537],"study_design_scores_gemma":[0.0042470256,0.0046572406,0.96610504,0.00011978716,0.000072334886,0.0035686446,0.0049322033,0.000456574,0.0010302997,0.003931801,0.010226429,0.00065263774],"about_ca_topic_score_codex":0.000020166348,"about_ca_topic_score_gemma":0.000028750763,"teacher_disagreement_score":0.34960273,"about_ca_system_score_codex":0.00009151441,"about_ca_system_score_gemma":0.00021123161,"threshold_uncertainty_score":0.9203645},"labels":[],"label_agreement":null},{"id":"W2573532050","doi":"10.1109/isai.2016.0075","title":"A Novel Deep Model for Biopsy Image Grading","year":2016,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Grading (engineering); Convolutional neural network; Artificial intelligence; Computer science; Sigmoid function; Pattern recognition (psychology); Feature extraction; Support vector machine; Benchmark (surveying); Deep learning; Image (mathematics); Artificial neural network","score_opus":0.0323159210229287,"score_gpt":0.2668271930389873,"score_spread":0.2345112720160586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573532050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060536916,0.0000061256605,0.9955631,0.0017888696,0.0002515813,0.000111935966,0.0000019100767,0.00021474641,0.0014563835],"genre_scores_gemma":[0.31851232,0.0000015723006,0.67998105,0.00014377035,0.000049878934,0.000036925143,6.708468e-8,0.000006172956,0.0012682574],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939054,0.000003193106,0.00009116476,0.00024561182,0.000092561735,0.00017691925],"domain_scores_gemma":[0.99952674,0.00005923804,0.000032253723,0.000286036,0.000053671516,0.000042038915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011236588,0.00006348212,0.000056965993,0.000050631003,0.00006372976,0.000051846284,0.00035144878,0.000028108176,0.000007301588],"category_scores_gemma":[0.000021551188,0.000041455154,0.000042727956,0.00010956178,0.000019783807,0.00056295353,0.00008456966,0.000019350344,0.000027764803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000092444825,0.000028197514,0.000023698296,0.000010566482,0.000010563321,5.928892e-7,0.00025032007,0.00022224188,0.6511116,0.1396262,0.001536918,0.20716986],"study_design_scores_gemma":[0.00030999005,0.000021751723,0.000026356503,0.0000063228977,0.0000014766134,0.000012781037,0.0000024767382,0.95392025,0.026531521,0.018786687,0.00029132632,0.000089084395],"about_ca_topic_score_codex":0.000009557949,"about_ca_topic_score_gemma":0.0000107856595,"teacher_disagreement_score":0.953698,"about_ca_system_score_codex":0.000078790945,"about_ca_system_score_gemma":0.000026357453,"threshold_uncertainty_score":0.16904922},"labels":[],"label_agreement":null},{"id":"W2580480204","doi":"10.1016/j.media.2017.01.009","title":"A deep learning approach for the analysis of masses in mammograms with minimal user intervention","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":342,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Pattern recognition (psychology); Classifier (UML); Mammography; Bayesian probability; Visualization; Test set; Machine learning; Breast cancer","score_opus":0.015229905149617709,"score_gpt":0.2996650691174222,"score_spread":0.2844351639678045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580480204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030088583,0.00012770329,0.96894246,0.00049419614,0.00002806774,0.00011563235,8.6709775e-7,0.00002463617,0.00017787512],"genre_scores_gemma":[0.94865525,0.000026200265,0.05104491,0.000029454297,0.000025631449,0.00008480731,0.000011726134,0.0000060485827,0.00011596881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983015,0.00012562232,0.000347569,0.00039198936,0.000620665,0.00021266426],"domain_scores_gemma":[0.9983851,0.00023935325,0.00037873856,0.0008012974,0.00013553324,0.000060010436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013832393,0.00011184327,0.00041535666,0.00055425137,0.00022158248,0.00024678325,0.0012449963,0.00007220101,0.000091421105],"category_scores_gemma":[0.0005245175,0.00007164352,0.00050611794,0.00215417,0.00023104943,0.00042074762,0.00022233395,0.0002079539,8.86334e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113195674,0.00035482924,0.2773192,0.000075824464,0.013057338,0.00002414859,0.0010306275,0.031781513,0.0000806455,0.0001955004,0.00003838651,0.6759288],"study_design_scores_gemma":[0.00032273628,0.00006774389,0.110815614,0.00001056731,0.003110214,9.609045e-7,0.00018691589,0.88510156,0.00013526966,0.000017384196,0.00015092694,0.00008012694],"about_ca_topic_score_codex":0.0010119533,"about_ca_topic_score_gemma":0.0024381378,"teacher_disagreement_score":0.91856664,"about_ca_system_score_codex":0.000046264813,"about_ca_system_score_gemma":0.000026106452,"threshold_uncertainty_score":0.29215378},"labels":[],"label_agreement":null},{"id":"W2582207877","doi":"10.1109/tbme.2017.2649481","title":"Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Jaccard index; Segmentation; Mammography; Pectoral muscle; Artificial intelligence; Hausdorff distance; Computer-aided diagnosis; Sørensen–Dice coefficient; Pattern recognition (psychology); Computer science; Breast cancer; Breast tissue; Image segmentation; Computer vision; Medicine; Cancer; Anatomy","score_opus":0.023163224668705955,"score_gpt":0.2649810204851122,"score_spread":0.24181779581640622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582207877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019978184,0.000025984687,0.9750134,0.00067596766,0.0036715115,0.00015542694,0.000021323001,0.00043560227,0.000022642516],"genre_scores_gemma":[0.9186703,0.000015424443,0.08089941,0.000101754216,0.00017704703,0.000075215736,0.0000049693044,0.000021278702,0.00003461106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985672,0.000021066764,0.0002449791,0.0004124215,0.0004615105,0.0002927872],"domain_scores_gemma":[0.9987936,0.00009103216,0.00009104875,0.0007859809,0.000031051626,0.00020729087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001627622,0.00018675008,0.00017101046,0.00027449324,0.00034249152,0.000258753,0.00072042784,0.00013442784,0.00009412732],"category_scores_gemma":[0.000014179913,0.00018975692,0.00012055575,0.00030609104,0.00006969986,0.00048174022,0.000004945984,0.00031725407,0.000080652695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014724173,0.00019657439,0.000015351248,0.000026547274,0.00005447638,0.000019955643,0.00013712364,0.04501315,0.055397794,0.000035053577,0.00015896016,0.8989303],"study_design_scores_gemma":[0.0009806522,0.0002098531,0.0022773477,0.00008369123,0.000023512863,0.0000037695518,0.000008549771,0.90001565,0.08322015,0.00003901951,0.012784464,0.00035331486],"about_ca_topic_score_codex":0.00023542067,"about_ca_topic_score_gemma":0.000035285506,"teacher_disagreement_score":0.89869213,"about_ca_system_score_codex":0.00020923968,"about_ca_system_score_gemma":0.000051395084,"threshold_uncertainty_score":0.7738063},"labels":[],"label_agreement":null},{"id":"W2582554538","doi":"10.1016/j.medengphy.2017.01.004","title":"A novel fully automatic measurement of apparent breast volume from trunk surface mesh","year":2017,"lang":"en","type":"article","venue":"Medical Engineering & Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine; National Research Council Canada","funders":"","keywords":"Voxel; Trunk; Computer science; Artificial intelligence; Segmentation; Torso; Interpolation (computer graphics); Curvature; Volume (thermodynamics); Position (finance); Computer vision; Mathematics; Anatomy; Medicine; Geometry; Physics; Image (mathematics)","score_opus":0.016983103504243764,"score_gpt":0.2208772315691825,"score_spread":0.20389412806493873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582554538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028722197,0.000051173232,0.9690985,0.0006258882,0.0011101644,0.00010204335,0.0000097677,0.00021064501,0.0000696049],"genre_scores_gemma":[0.9724883,0.00000486131,0.027137531,0.00002402781,0.00030140995,0.000011813069,0.0000016943923,0.000018095609,0.000012264881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977175,0.000012960669,0.00028768522,0.00030498003,0.0014181377,0.00025872845],"domain_scores_gemma":[0.99850804,0.00004327554,0.00017731919,0.0009642972,0.00011895237,0.00018811223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039952024,0.00017012047,0.00027459752,0.000019671894,0.00009080635,0.00008894271,0.0012862496,0.000080669226,0.000028059281],"category_scores_gemma":[0.00018189159,0.0001670397,0.000086835236,0.00010567389,0.000062441344,0.00029284015,0.00030528603,0.00023014899,0.00002003909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020137275,0.0008824453,0.00097132986,0.00063163147,0.0005615385,0.00003264866,0.0017742305,0.079354964,0.09294909,0.01253949,0.0023199646,0.80796254],"study_design_scores_gemma":[0.00042412148,0.000036628462,0.011995949,0.00026424622,0.000015735113,0.000007728229,0.000002841824,0.9818164,0.004431772,0.00030867578,0.0005184772,0.00017740062],"about_ca_topic_score_codex":0.0003346851,"about_ca_topic_score_gemma":0.0000105873405,"teacher_disagreement_score":0.9437661,"about_ca_system_score_codex":0.00017668895,"about_ca_system_score_gemma":0.00017523982,"threshold_uncertainty_score":0.68116814},"labels":[],"label_agreement":null},{"id":"W2588546842","doi":"10.21474/ijar01/3099","title":"Severity Analysis of Cervical Cancer in Pap Smear Images by using EEETCM, ERSTCM & CFE method based Texture Features and Hybrid Kernel based Support Vector Machine Classifier.","year":2016,"lang":"en","type":"article","venue":"International Journal of Advanced Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital","funders":"","keywords":"Support vector machine; Cervical cancer; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Kernel (algebra); Gynecology; Medicine; Computer science; Mathematics; Cancer; Internal medicine; Combinatorics","score_opus":0.04058341667895639,"score_gpt":0.4176277151781351,"score_spread":0.3770442984991787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588546842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0781841,0.00066346256,0.90666425,0.013401786,0.00056118064,0.00016126933,0.00025252553,0.000017192897,0.00009424594],"genre_scores_gemma":[0.942527,0.00030059172,0.056675255,0.00016542006,0.00012564832,0.0000072903654,0.0000046148675,0.00001522815,0.00017896829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963768,0.00061497756,0.00053463195,0.00037592667,0.0017672521,0.00033038482],"domain_scores_gemma":[0.9966501,0.0010015292,0.0003853196,0.00029704676,0.0014895828,0.0001764496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021427267,0.00015541771,0.00037732697,0.0013331868,0.00008132944,0.00009763088,0.001043074,0.00008813313,0.00022765818],"category_scores_gemma":[0.00046538288,0.00011699705,0.00017603261,0.0010030023,0.00020068242,0.000698718,0.00019407719,0.0006119826,8.8132384e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002625968,0.0005415126,0.048599843,0.00009114963,0.0015746843,0.00029342467,0.000525644,0.047984835,0.42508334,0.0002551553,0.00466094,0.4677635],"study_design_scores_gemma":[0.009483264,0.0008168002,0.23034948,0.0011501447,0.00028949443,0.00025260245,0.00017076617,0.48862505,0.24222927,0.0027722574,0.022876345,0.0009845255],"about_ca_topic_score_codex":0.00052308134,"about_ca_topic_score_gemma":0.00047949806,"teacher_disagreement_score":0.86434287,"about_ca_system_score_codex":0.0008970999,"about_ca_system_score_gemma":0.0005900272,"threshold_uncertainty_score":0.4771001},"labels":[],"label_agreement":null},{"id":"W2592740045","doi":"10.1117/12.2254320","title":"Automated assessment of breast tissue density in non-contrast 3D CT images without image segmentation based on a deep CNN","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Breast tissue; Convolutional neural network; Breast density; Segmentation; Ground truth; Pattern recognition (psychology); Contrast (vision); Breast imaging; Deep learning; Robustness (evolution); Tomography; Mammography; Computer vision; Breast cancer; Radiology; Medicine","score_opus":0.00762455197650479,"score_gpt":0.2643549811413109,"score_spread":0.2567304291648061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592740045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862274,0.00000752136,0.009508981,0.0015974331,0.00028144286,0.00067230867,0.0000258082,0.00013743974,0.001541686],"genre_scores_gemma":[0.72745353,0.000009524017,0.27225456,0.000040757815,0.000096812015,0.0000980979,0.0000029200778,0.000025884225,0.000017931674],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976481,4.8836508e-8,0.00065001455,0.0004917245,0.0008609952,0.00034909928],"domain_scores_gemma":[0.997494,0.00012561434,0.00078972353,0.00015756053,0.0013390217,0.000094103816],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008392718,0.00030246217,0.00044021127,0.00016262247,0.00014333679,0.0002889779,0.0015697394,0.000109048946,0.0000051654074],"category_scores_gemma":[0.00031231839,0.00027325618,0.0002803606,0.00024177671,0.00024423894,0.0013204782,0.00024984754,0.00030421282,0.0000010567962],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081604536,0.00023939415,0.0059388513,0.0004952929,0.0001649199,5.946359e-7,0.00014999718,0.0009784146,0.9620779,0.026634812,0.00035142474,0.0028867954],"study_design_scores_gemma":[0.0012163355,0.00025408788,0.075702906,0.00033245442,0.000041274336,0.000013360683,0.00012034918,0.6049742,0.31690657,0.00020747444,0.000016108563,0.00021484517],"about_ca_topic_score_codex":0.000063485444,"about_ca_topic_score_gemma":0.0000015492576,"teacher_disagreement_score":0.64517134,"about_ca_system_score_codex":0.0004114536,"about_ca_system_score_gemma":0.00006851164,"threshold_uncertainty_score":0.999972},"labels":[],"label_agreement":null},{"id":"W2592781864","doi":"10.4103/jpi.jpi_47_16","title":"Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network","year":2017,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Convolution (computer science); Colorectal cancer; Feature extraction; Multispectral image; Biopsy; Feature (linguistics); Pooling; Cancer; Artificial neural network; Pathology; Medicine; Internal medicine","score_opus":0.04585763472105722,"score_gpt":0.3320876772956466,"score_spread":0.2862300425745894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592781864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6896355,0.00014992233,0.3076602,0.0002837262,0.0020105953,0.00006858908,0.0000033766005,0.00001211053,0.00017599572],"genre_scores_gemma":[0.8966674,0.00009299117,0.10292763,0.00004124304,0.00025648458,0.0000017990437,2.7781806e-7,0.000003904046,0.000008246082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880964,0.000049917726,0.0007009371,0.000051177678,0.00020060962,0.00018771645],"domain_scores_gemma":[0.99704957,0.000052746833,0.0022107654,0.00029941008,0.00033459938,0.000052935062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044409014,0.00008653684,0.00023514705,0.00010039968,0.00029349103,0.00007658013,0.00071727164,0.000099442565,0.000005470678],"category_scores_gemma":[0.00009876135,0.000077126024,0.00007971213,0.00009286583,0.00020708171,0.0013329842,0.000115949595,0.0002566255,0.0000020169891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032057607,0.00033511387,0.23520605,0.00034775567,0.00050192064,0.00029833062,0.033913583,0.44220436,0.064135455,0.025909085,0.0054386132,0.19138916],"study_design_scores_gemma":[0.00070000975,0.0003819354,0.104425326,0.00009123554,0.00005634979,0.0015305349,0.00023434925,0.88413954,0.006528287,0.0013483412,0.0004118078,0.0001522777],"about_ca_topic_score_codex":0.00001814405,"about_ca_topic_score_gemma":0.000027118569,"teacher_disagreement_score":0.44193518,"about_ca_system_score_codex":0.00013642706,"about_ca_system_score_gemma":0.00016671233,"threshold_uncertainty_score":0.3145108},"labels":[],"label_agreement":null},{"id":"W2594182012","doi":"10.1097/pai.0000000000000469","title":"Evolution of Quality Assurance for Clinical Immunohistochemistry in the Era of Precision Medicine: Part 4: Tissue Tools for Quality Assurance in Immunohistochemistry","year":2016,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver General Hospital; University of Toronto; University of British Columbia; University Health Network","funders":"","keywords":"Quality assurance; Immunohistochemistry; Quality (philosophy); Medicine; Medical physics; Computer science; Pathology; External quality assessment","score_opus":0.03336247895482582,"score_gpt":0.3716047691341914,"score_spread":0.3382422901793656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594182012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60108787,0.004020193,0.39061007,0.0011200213,0.00059244136,0.0016045022,0.00009934503,0.000056460747,0.00080910296],"genre_scores_gemma":[0.9838124,0.00020806702,0.013578934,0.00017247685,0.00013459756,0.0018923741,0.00006356413,0.000047028934,0.000090583824],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9932084,0.0004384755,0.0033788735,0.001476249,0.0007344948,0.0007634977],"domain_scores_gemma":[0.989415,0.0048333844,0.0020840308,0.0030326655,0.00055112015,0.00008379614],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005823562,0.0005627121,0.0014440675,0.00010440644,0.00013161993,0.00002461825,0.0028436559,0.00077720603,0.000026159147],"category_scores_gemma":[0.003936784,0.00047126412,0.00041238446,0.00070442405,0.0011800235,0.00026763044,0.00028604944,0.0007050013,0.0000031526768],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093471946,0.00029338797,0.00019107052,0.00051984494,0.000053045937,0.000004815059,0.00019724324,0.0000377967,0.9781229,0.0024436088,0.000960507,0.016241096],"study_design_scores_gemma":[0.0058567505,0.00033587747,0.007617025,0.0005420393,0.000046020312,0.000048874695,0.00018808927,0.000049120346,0.97720206,0.0067221713,0.0007421385,0.0006498069],"about_ca_topic_score_codex":0.00022885735,"about_ca_topic_score_gemma":0.0000017732941,"teacher_disagreement_score":0.3827245,"about_ca_system_score_codex":0.001077319,"about_ca_system_score_gemma":0.0006698697,"threshold_uncertainty_score":0.9997739},"labels":[],"label_agreement":null},{"id":"W2604440528","doi":"10.1016/j.patcog.2018.09.007","title":"Sparse autoencoder for unsupervised nucleus detection and representation in histopathology images","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"AI in cancer detection","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Concordia University","funders":"U.S. National Library of Medicine; National Cancer Institute","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Computer science; Feature extraction; Convolutional neural network; Feature (linguistics); Feature vector; ENCODE; Feature learning; Unsupervised learning; Computer vision; Deep learning; Biology","score_opus":0.04444275579844309,"score_gpt":0.28412431342655975,"score_spread":0.23968155762811666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604440528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.308931,0.000018736255,0.68962663,0.00025686718,0.0006103736,0.00026962676,0.0000067825713,0.000101485064,0.00017851323],"genre_scores_gemma":[0.9815507,0.000025525756,0.01770852,0.0002826952,0.0002224633,0.00017072767,0.000009784018,0.000012676286,0.000016885286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989859,0.00009509477,0.00020550432,0.00043256773,0.00009690898,0.00018402425],"domain_scores_gemma":[0.99946564,0.000075010714,0.00009288796,0.00020005704,0.0001313596,0.00003504654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025189182,0.00009890122,0.0001077637,0.0001976318,0.000104849954,0.000065228465,0.00011466632,0.00008083006,0.000019501684],"category_scores_gemma":[0.00006211191,0.0001115487,0.00002810936,0.0002081157,0.000062155326,0.0004582055,0.00005183121,0.00007884713,0.000044550907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031084543,0.0000202431,0.0022077456,0.00002042942,0.0000023899522,0.0000032835574,0.000623686,0.0000056852696,0.020638354,0.0000051793627,0.000053243293,0.9763887],"study_design_scores_gemma":[0.0032473763,0.0012638568,0.29866812,0.000116512,0.000034403925,0.00021443296,0.00018765175,0.41728964,0.23987943,0.037544888,0.00091419823,0.00063949125],"about_ca_topic_score_codex":0.00018098087,"about_ca_topic_score_gemma":0.00045822907,"teacher_disagreement_score":0.9757492,"about_ca_system_score_codex":0.000115958464,"about_ca_system_score_gemma":0.000013959015,"threshold_uncertainty_score":0.4548824},"labels":[],"label_agreement":null},{"id":"W2605617537","doi":"10.1007/978-3-319-57351-9_7","title":"Somatic Copy Number Alteration-Based Prediction of Molecular Subtypes of Breast Cancer Using Deep Learning Model","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation","funders":"","keywords":"Computer science; Support vector machine; Artificial intelligence; Deep learning; Random forest; Machine learning; Breast cancer; Artificial neural network; Single-nucleotide polymorphism; Deep neural networks; Cancer; Computational biology; Pattern recognition (psychology); Gene; Biology; Genetics; Genotype","score_opus":0.016647420864551846,"score_gpt":0.2623248012187453,"score_spread":0.24567738035419345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605617537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033701183,0.00017916424,0.9947472,0.000108308144,0.0009162449,0.00029175455,0.000017879618,0.00007049346,0.0002987966],"genre_scores_gemma":[0.76201785,0.000019024914,0.23770739,0.00007354749,0.00011953711,0.0000079996535,0.0000028144464,0.000026381933,0.00002545993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971126,0.00004712447,0.00059830595,0.00090031157,0.0009918072,0.00034985144],"domain_scores_gemma":[0.9971169,0.00015848246,0.0009684618,0.001094712,0.000578542,0.00008290499],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052789546,0.00036475976,0.00051409577,0.00045597114,0.00026977214,0.00019729635,0.0016589751,0.00026354674,0.000019572224],"category_scores_gemma":[0.00004951381,0.0003683563,0.00013598416,0.00025160942,0.0005820266,0.00068327796,0.0003782746,0.0005093985,0.0000024234325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009090318,0.000014322781,0.0010300911,0.00010159383,0.000014192036,0.0000044444128,0.00031203032,0.89768183,0.005697707,0.0004942248,5.077669e-7,0.09463997],"study_design_scores_gemma":[0.00023412195,0.000063163796,0.00026175188,0.0008236901,0.000023046308,0.000025903004,1.1187417e-7,0.9510171,0.03129265,0.01599201,0.000004606284,0.00026188724],"about_ca_topic_score_codex":0.0001456988,"about_ca_topic_score_gemma":0.000057937752,"teacher_disagreement_score":0.75864774,"about_ca_system_score_codex":0.0004415447,"about_ca_system_score_gemma":0.0009909621,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W2605810678","doi":"10.1111/his.13146","title":"Image editing for pathologists","year":2017,"lang":"en","type":"article","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Library science; Medicine; Citation; New england; Political science; Law; Computer science","score_opus":0.029957119518381106,"score_gpt":0.3023403698002165,"score_spread":0.2723832502818354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605810678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007406265,0.000082487,0.9754661,0.0023302338,0.0045533143,0.00016095252,0.0000045067814,0.00021195292,0.009784244],"genre_scores_gemma":[0.6303884,0.000008724745,0.36729142,0.00044553113,0.0008184745,0.00015219927,0.0000017666224,0.000015972328,0.0008775394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907887,0.000037404756,0.00014487359,0.00039605534,0.00007717629,0.00026560202],"domain_scores_gemma":[0.99851686,0.000049568593,0.0002334894,0.0010722415,0.000087751185,0.000040068673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004174726,0.00009310011,0.00013940792,0.000054205448,0.0006780675,0.00011638912,0.0010893323,0.00008879681,0.0000075601342],"category_scores_gemma":[0.00042425757,0.000096446776,0.00006226226,0.000025681435,0.00021523442,0.0004393552,0.0002827684,0.00010277015,0.0000630388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006719541,0.00015519913,0.010598881,0.00017131864,0.0000058859864,0.0011917915,0.0028732743,0.000016151445,0.24652337,0.15495622,0.057094973,0.52634573],"study_design_scores_gemma":[0.0025404831,0.0011571544,0.37552446,0.000047752816,0.000034268465,0.0017975736,0.000057193196,0.033409536,0.016259741,0.108185574,0.45986015,0.0011261161],"about_ca_topic_score_codex":0.000013189207,"about_ca_topic_score_gemma":0.000017582057,"teacher_disagreement_score":0.6229821,"about_ca_system_score_codex":0.00009843241,"about_ca_system_score_gemma":0.000035101453,"threshold_uncertainty_score":0.52152157},"labels":[],"label_agreement":null},{"id":"W2605960745","doi":"10.1016/j.cmpb.2017.04.012","title":"Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification","year":2017,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Multi-objective optimization; Autoencoder; Discriminative model; Pattern recognition (psychology); Sorting; Artificial intelligence; Encoder; Genetic algorithm; Pareto principle; Dimensionality reduction; Mean squared error; Artificial neural network; Reduction (mathematics); Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics","score_opus":0.11657610167002051,"score_gpt":0.4079050726891905,"score_spread":0.29132897101917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605960745","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008063685,0.00047788263,0.9861084,0.0017599207,0.0025493295,0.0008620577,0.0000019079523,0.00015090434,0.000025892365],"genre_scores_gemma":[0.1413314,0.000064326414,0.85787195,0.00007154237,0.00039502833,0.0002259723,0.000012651616,0.000012500955,0.000014604776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793947,0.00028996967,0.00040370633,0.00081469095,0.00021648908,0.00033569452],"domain_scores_gemma":[0.998295,0.00017784024,0.00034238255,0.0008480388,0.0002076192,0.0001291391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023961256,0.00022009999,0.00033084868,0.0002578433,0.00052261585,0.00025220905,0.0005807742,0.00016336783,0.0000012130549],"category_scores_gemma":[0.00007048303,0.00018772324,0.00008715308,0.00035057144,0.00043986738,0.0005272055,0.0002799975,0.00021619805,7.263656e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039726303,0.000110552144,0.002735876,0.000047993864,0.00003145081,0.0000018798852,0.0007197103,0.00001318397,0.0015670848,0.0015224256,0.000053467917,0.9931567],"study_design_scores_gemma":[0.0016943148,0.0007566568,0.13415198,0.00012161614,0.000026111498,0.000050842795,0.00011170309,0.8468347,0.00079143944,0.008557696,0.0066002067,0.0003026858],"about_ca_topic_score_codex":0.000099631376,"about_ca_topic_score_gemma":0.00001547163,"teacher_disagreement_score":0.99285394,"about_ca_system_score_codex":0.00009053663,"about_ca_system_score_gemma":0.00003920708,"threshold_uncertainty_score":0.7655132},"labels":[],"label_agreement":null},{"id":"W2608035196","doi":"10.5858/arpa.2016-0074-oa","title":"Implementation of Whole Slide Imaging for Clinical Purposes: Issues to Consider From the Perspective of Early Adopters","year":2017,"lang":"en","type":"review","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Workflow; Digital pathology; Context (archaeology); Quality assurance; Medical physics; Medicine; Early adopter; Computer science; Pathology","score_opus":0.12599173094426502,"score_gpt":0.49355483182367843,"score_spread":0.3675631008794134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608035196","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006279182,0.9628074,0.03112808,0.0022505522,0.0011237763,0.0014148364,0.00052839564,0.000024423845,0.00009462634],"genre_scores_gemma":[0.002710844,0.96730417,0.028685706,0.00039174143,0.0006381616,0.00018182627,0.000032052118,0.000038550173,0.00001692365],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996963,0.0007640694,0.0012160207,0.00060356775,0.00023887004,0.00021446295],"domain_scores_gemma":[0.9935408,0.0028942255,0.0018735672,0.0012366674,0.00037958776,0.0000751276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011614874,0.0002636433,0.0016368724,0.00022189975,0.00009133759,0.000010373448,0.0012936437,0.00009575559,0.000008022603],"category_scores_gemma":[0.000887218,0.00018225105,0.00025032496,0.00019815439,0.0013697705,0.00015788939,0.00031492303,0.000282126,0.00000220786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003243984,0.000029966297,0.0012262863,0.00074794237,0.00023782662,0.000023630126,0.0096925385,4.0453156e-7,0.00020549544,0.0021711478,0.0014743083,0.98415804],"study_design_scores_gemma":[0.0027189597,0.0034739703,0.011419161,0.014442028,0.0018718732,0.000039298906,0.00902551,0.000029029537,0.00066986884,0.011423199,0.9442744,0.0006126682],"about_ca_topic_score_codex":0.0004611206,"about_ca_topic_score_gemma":0.00012020341,"teacher_disagreement_score":0.98354536,"about_ca_system_score_codex":0.000040764116,"about_ca_system_score_gemma":0.0006826459,"threshold_uncertainty_score":0.7431982},"labels":[],"label_agreement":null},{"id":"W2612377680","doi":"10.1016/j.media.2017.04.008","title":"A structured latent model for ovarian carcinoma subtyping from histopathology slides","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Subtyping; Computer science; Discriminative model; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature vector; Histopathology; Machine learning; Pathology; Medicine","score_opus":0.025349649899223437,"score_gpt":0.29035625491355294,"score_spread":0.2650066050143295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612377680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062121805,0.00008651273,0.9338486,0.0033352505,0.0003150627,0.000087719694,0.000014221706,0.000073924886,0.0001169107],"genre_scores_gemma":[0.8799938,0.00000852259,0.119195215,0.00041113136,0.0001738456,0.00003226249,0.000013058845,0.000008698624,0.00016344523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983593,0.000060409664,0.00028527624,0.0005838092,0.00042132623,0.0002898341],"domain_scores_gemma":[0.99806285,0.000091562215,0.00023155523,0.0012972091,0.00012549279,0.00019134258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004373124,0.00013929504,0.0003666365,0.000182073,0.000445455,0.00023809649,0.0014947538,0.00015007108,0.00010585914],"category_scores_gemma":[0.0005582748,0.00012440646,0.00028274438,0.00020418588,0.00016145967,0.000408502,0.00035206223,0.00017841537,0.0000089378045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026129483,0.00028512426,0.17847763,0.00011709478,0.0030990574,0.0012118757,0.008224704,0.0074879746,0.027749445,0.008624752,0.007060622,0.75740045],"study_design_scores_gemma":[0.00035257186,0.000017556076,0.060594454,0.000004872985,0.0003354112,0.0000040884856,0.0000049211435,0.929603,0.0008250804,0.008010904,0.00011563074,0.00013152148],"about_ca_topic_score_codex":0.0011999471,"about_ca_topic_score_gemma":0.0010952501,"teacher_disagreement_score":0.922115,"about_ca_system_score_codex":0.0001254923,"about_ca_system_score_gemma":0.00012667371,"threshold_uncertainty_score":0.5073148},"labels":[],"label_agreement":null},{"id":"W2619003201","doi":"10.1038/s41588-018-0084-1","title":"Refining the accuracy of validated target identification through coding variant fine-mapping in type 2 diabetes","year":2018,"lang":"en","type":"review","venue":"Nature Genetics","topic":"AI in cancer detection","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université de Sherbrooke","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; NIHR Cambridge Biomedical Research Centre; Helmholtz Zentrum München; Korea Centers for Disease Control and Prevention; Korea National Institute of Health; National Center for Advancing Translational Sciences; Medical Research Council; Münchner Zentrum für Gesundheitswissenschaften; Erasmus Medisch Centrum; Genentech; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Centers for Disease Control and Prevention; Regeneron Pharmaceuticals; National Institutes of Health; Hjartavernd; Novo Nordisk Fonden; Eli Lilly and Company; Lundbeckfonden; ZonMw; British Heart Foundation; European Commission; Steno Diabetes Center Copenhagen; Wellcome Trust; Bundesministerium für Bildung und Forschung; National Institute on Aging; National Institute for Health and Care Research; National Institute of Diabetes and Digestive and Kidney Diseases; Sanofi; GlaxoSmithKline; Pfizer; Incyte; Yale University","keywords":"Biology; Computational biology; Identification (biology); Coding (social sciences); Refining (metallurgy); Type 2 diabetes; Genetics; Diabetes mellitus; Statistics; Endocrinology; Mathematics","score_opus":0.05926589266483752,"score_gpt":0.34457261975839104,"score_spread":0.28530672709355354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619003201","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045601748,0.96188414,0.034571745,0.00007322823,0.0028923736,0.00032708372,0.000011797782,0.000055086795,0.00013895397],"genre_scores_gemma":[0.0012194903,0.9652811,0.03288934,0.000063946456,0.0003982146,0.000034580993,0.000043597873,0.000033074222,0.000036644557],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977183,0.00028579083,0.00077674986,0.00055996975,0.0003733066,0.0002859115],"domain_scores_gemma":[0.9970704,0.0005060299,0.0009857613,0.0011372006,0.00027683066,0.00002381317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009233176,0.00027801783,0.0006209395,0.00018514988,0.000112060254,0.00014068455,0.00165048,0.0006375229,0.0000067228193],"category_scores_gemma":[0.0006110623,0.00020801958,0.00013487488,0.0019460531,0.000064142274,0.00018678467,0.00039453647,0.0009891066,0.00001931108],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013340903,0.00002380079,0.00004158022,0.0036522981,0.00011872008,0.0000040564705,0.00067832123,0.00010571162,0.00009808018,0.0007251492,0.0020514482,0.9924995],"study_design_scores_gemma":[0.000069137954,0.000033405562,0.00006594674,0.0039257654,0.000079672776,0.000008749255,0.000005665936,0.0034465843,0.000827429,0.0009086941,0.99036103,0.00026789168],"about_ca_topic_score_codex":0.0000062497443,"about_ca_topic_score_gemma":0.0000070879264,"teacher_disagreement_score":0.9922316,"about_ca_system_score_codex":0.00016666361,"about_ca_system_score_gemma":0.00030973105,"threshold_uncertainty_score":0.84827924},"labels":[],"label_agreement":null},{"id":"W2623064764","doi":"10.1097/pap.0000000000000153","title":"Clinical Applications of Whole-slide Imaging in Anatomic Pathology","year":2017,"lang":"en","type":"review","venue":"Advances in Anatomic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Workflow; Medical physics; Clinical imaging; Medicine; Transformative learning; Imaging technology; Computer science; Pathology; Data science; Radiology; Psychology","score_opus":0.05278987777683543,"score_gpt":0.44964199462598153,"score_spread":0.3968521168491461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623064764","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042725605,0.9089913,0.087164156,0.00007823707,0.0016526555,0.00091236114,0.000037290254,0.00008573438,0.0010355654],"genre_scores_gemma":[0.0012271024,0.98640525,0.01130643,0.000110427594,0.0001672581,0.00067307573,0.000023996927,0.000047705584,0.000038730603],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941188,0.0010902425,0.0022634354,0.0016418148,0.00020710788,0.00067859085],"domain_scores_gemma":[0.99443275,0.00080215704,0.00206436,0.0025186192,0.00008614719,0.00009596108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021743844,0.00052009564,0.002700603,0.0012462008,0.00009817897,0.00003724813,0.0034355433,0.00064223865,0.0000058529954],"category_scores_gemma":[0.00031638768,0.00052923965,0.00043175308,0.00080722896,0.00083249365,0.0007710998,0.00089707674,0.0013576715,0.000087092296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003625174,0.00006853789,0.0013530611,0.00085947587,0.0000075352395,0.0003945567,0.000047348018,0.000012015256,0.000001458629,0.0030997351,0.000025543637,0.9941271],"study_design_scores_gemma":[0.00056227826,0.000053038704,0.0003382641,0.0017759397,0.00004913216,0.00078511616,0.0000166412,0.0007585969,0.0000030130802,0.014149623,0.9810178,0.00049053825],"about_ca_topic_score_codex":0.000027626622,"about_ca_topic_score_gemma":0.0003339754,"teacher_disagreement_score":0.99363655,"about_ca_system_score_codex":0.0004640559,"about_ca_system_score_gemma":0.0006376641,"threshold_uncertainty_score":0.9997159},"labels":[],"label_agreement":null},{"id":"W2624968784","doi":"10.1038/s41698-017-0022-1","title":"Precision histology: how deep learning is poised to revitalize histomorphology for personalized cancer care","year":2017,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Histology; Cancer; Medicine; Medical education; Artificial intelligence; Computer science; Internal medicine","score_opus":0.04098294206365456,"score_gpt":0.36580947135908837,"score_spread":0.3248265292954338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624968784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027446374,0.0053907116,0.9150169,0.035241164,0.009775323,0.002245484,0.000033688062,0.0003928251,0.0044575417],"genre_scores_gemma":[0.73125637,0.001173855,0.23319772,0.005915736,0.0010333426,0.0025376312,0.000024727682,0.00013883968,0.024721779],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965657,0.00041794486,0.0004670952,0.0014100602,0.00044303513,0.00069615984],"domain_scores_gemma":[0.9957441,0.00082490814,0.00076692895,0.001612006,0.00077138585,0.00028064894],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00082889694,0.0003575835,0.0007989609,0.0003169943,0.0013101201,0.00023478229,0.002446747,0.00061259326,0.0002880453],"category_scores_gemma":[0.001745042,0.00035038622,0.00026724584,0.00017865612,0.00026093845,0.0006020535,0.0009425767,0.0004679591,0.00013298499],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062648754,0.0000493013,0.0007026998,0.000040864117,0.0000368603,0.00003177287,0.0051980144,0.00012433366,0.005465769,0.0009845969,0.049355503,0.9373838],"study_design_scores_gemma":[0.002546257,0.0019529362,0.0018755444,0.00008025412,0.0000459845,0.000084791376,0.0001523279,0.005216651,0.0026958098,0.001569645,0.9833567,0.0004230733],"about_ca_topic_score_codex":0.0001590138,"about_ca_topic_score_gemma":0.00040426617,"teacher_disagreement_score":0.9369607,"about_ca_system_score_codex":0.0023533574,"about_ca_system_score_gemma":0.00041946006,"threshold_uncertainty_score":0.99999005},"labels":[],"label_agreement":null},{"id":"W2625194996","doi":"10.1002/cncy.21826","title":"Cytopathology is the Nexus for patient‐centered care","year":2017,"lang":"en","type":"article","venue":"Cancer Cytopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Fine-needle aspiration; Cytopathology; Information overload; Biopsy; Medical physics; Radiology; Pathology; Computer science","score_opus":0.032107359640378585,"score_gpt":0.31353846998183327,"score_spread":0.2814311103414547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625194996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3523633,0.0101111075,0.5533508,0.036633026,0.03488811,0.002957409,0.00034637057,0.0006930585,0.008656789],"genre_scores_gemma":[0.9903869,0.0001125958,0.0040219724,0.0038175222,0.00051951903,0.0008482178,0.0000037611462,0.000029032735,0.00026045894],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981333,0.00011695216,0.00028533148,0.0007500009,0.0001639735,0.000550434],"domain_scores_gemma":[0.9969577,0.00008764067,0.00039342482,0.0021466406,0.00033656065,0.000078027166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001761557,0.00022958871,0.00029620182,0.00007314431,0.0011558858,0.00022100707,0.0022205145,0.00018342084,0.000030102454],"category_scores_gemma":[0.00010504234,0.00018098552,0.00016006369,0.00008675741,0.0003623352,0.0004045363,0.0006717255,0.00023632849,0.000037662987],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022664074,0.00006850768,0.021720625,0.00013529412,0.000055457745,0.00021057384,0.029069493,0.00013882136,0.007954339,0.016099446,0.016732413,0.90758836],"study_design_scores_gemma":[0.0055555627,0.0027701468,0.085972294,0.00015682822,0.00018130952,0.0012111563,0.0026446995,0.009243884,0.088207684,0.038481448,0.7636993,0.001875677],"about_ca_topic_score_codex":0.00008570973,"about_ca_topic_score_gemma":0.00017735666,"teacher_disagreement_score":0.9057127,"about_ca_system_score_codex":0.00023625008,"about_ca_system_score_gemma":0.00017049146,"threshold_uncertainty_score":0.8890255},"labels":[],"label_agreement":null},{"id":"W2632480913","doi":"10.1007/s11548-017-1627-0","title":"Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations","year":2017,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; National Institute for Health and Care Research","keywords":"Computer science; Deep learning; Prostate cancer; Artificial intelligence; Visualization; Feature (linguistics); Grading (engineering); Ultrasound; Prostate; Pattern recognition (psychology); Medicine; Radiology; Cancer; Biology","score_opus":0.025184310243750455,"score_gpt":0.2991378061046637,"score_spread":0.2739534958609132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2632480913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55362564,0.00045616293,0.44394758,0.00014833025,0.0017796697,0.000032393804,9.1872414e-7,0.0000072197886,0.0000020789046],"genre_scores_gemma":[0.99315864,0.0002581239,0.006119499,0.00007201881,0.00038098832,0.0000012164418,9.525912e-7,0.0000072441903,0.000001325299],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889725,0.0001334272,0.00047288917,0.00019590801,0.00015813975,0.00014240295],"domain_scores_gemma":[0.99789476,0.0007062564,0.0009564985,0.00012292407,0.00025406046,0.000065487904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004243528,0.00012098308,0.00031168366,0.00026356042,0.0003027489,0.00021262697,0.0002485001,0.00008646773,0.0000013133479],"category_scores_gemma":[0.0000640789,0.0001153739,0.000052253603,0.000051860283,0.00018591838,0.00081819494,0.00011798846,0.00022102015,1.831373e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017973737,0.00003205221,0.2393748,0.00002552305,0.00039829072,0.0000655227,0.00092929194,0.055663068,0.018487334,0.00009043066,0.000012808729,0.68474114],"study_design_scores_gemma":[0.00047360145,0.00008059274,0.20946014,0.00013331944,0.000025486892,0.0021007461,0.000016033624,0.78455967,0.0026138925,0.00037921563,0.000029192457,0.00012811144],"about_ca_topic_score_codex":0.00006286247,"about_ca_topic_score_gemma":0.000042392505,"teacher_disagreement_score":0.7288966,"about_ca_system_score_codex":0.000059021142,"about_ca_system_score_gemma":0.000037788628,"threshold_uncertainty_score":0.4704811},"labels":[],"label_agreement":null},{"id":"W2690746351","doi":"10.1002/cyto.a.23151","title":"Computer‐aided diagnostics in digital pathology","year":2017,"lang":"en","type":"editorial","venue":"Cytometry Part A","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; Occupational Cancer Research Centre","funders":"","keywords":"Digital pathology; Computer science; Pathology; Medical physics; Medicine; Computer graphics (images)","score_opus":0.015946682136610116,"score_gpt":0.2836435746872094,"score_spread":0.2676968925505993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2690746351","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002596547,0.00046461102,0.12840234,0.00006678213,0.8692779,0.00021305225,0.00011049065,0.00022658762,0.0009785757],"genre_scores_gemma":[0.0047518727,0.0007328234,0.004372158,0.00005931506,0.9891027,0.00009423835,0.00014759538,0.00006070857,0.0006785375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970067,0.00006649278,0.00050262857,0.0010611921,0.00078073924,0.0005822534],"domain_scores_gemma":[0.99555945,0.0016876648,0.00047887536,0.0019066563,0.00022842859,0.00013889355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046741887,0.000403133,0.0006599882,0.0006699445,0.00015998464,0.00092937396,0.0027094593,0.0010515454,0.000009285113],"category_scores_gemma":[0.0024470955,0.000436436,0.00014369338,0.00056027673,0.0001644976,0.00085984234,0.0012387295,0.001217661,0.00036903468],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071895943,0.000050676088,0.00048688403,0.000044743465,0.00001706612,0.0004811924,0.00007258513,0.00001587167,0.000001840977,0.000047013873,0.95989174,0.03888321],"study_design_scores_gemma":[0.00054820627,0.00024045733,0.00053294405,0.0002393896,0.000009441218,0.00002437395,0.0000017208802,0.0015250426,0.000035858702,0.000966421,0.99538815,0.0004879845],"about_ca_topic_score_codex":0.000014516128,"about_ca_topic_score_gemma":0.000023556355,"teacher_disagreement_score":0.12403018,"about_ca_system_score_codex":0.00039418665,"about_ca_system_score_gemma":0.00046140584,"threshold_uncertainty_score":0.9998087},"labels":[],"label_agreement":null},{"id":"W2716665989","doi":"10.1038/s41598-017-04075-z","title":"Breast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":675,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Project of Shandong Province Higher Educational Science and Technology Program; Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Breast cancer; Artificial intelligence; Fibroadenoma; Cancer; Deep learning; Invasive lobular carcinoma; Lobular carcinoma; Computer science; Contextual image classification; Binary classification; Medicine; Pattern recognition (psychology); Ductal carcinoma; Pathology; Invasive ductal carcinoma; Support vector machine; Internal medicine; Image (mathematics)","score_opus":0.03145578864690726,"score_gpt":0.2777013429502791,"score_spread":0.24624555430337183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2716665989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22761336,0.00010868871,0.7660797,0.00053807837,0.0048088282,0.00019634895,0.0000050126623,0.00026599676,0.00038396413],"genre_scores_gemma":[0.93568325,0.000006063542,0.06260211,0.0000145630975,0.00008256962,0.00004768931,0.0000074753143,0.000012295928,0.0015439737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975458,0.00005117765,0.0002893928,0.0012660212,0.00055797066,0.00028965247],"domain_scores_gemma":[0.9968474,0.0000141631845,0.0007533547,0.0019923104,0.0002790788,0.0001136995],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005714305,0.00016724778,0.00017158713,0.0000873338,0.0015597944,0.0014492028,0.0007639187,0.00008833518,0.000033479737],"category_scores_gemma":[0.00006590615,0.00013062144,0.000053274613,0.00015018722,0.0004345268,0.0011267883,0.00025630824,0.00024251448,0.000008997393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057905527,0.00015113759,0.14176746,0.000025550944,0.000043004096,0.0008836477,0.0024552715,0.06853153,0.27703446,0.00037487893,0.002039126,0.506636],"study_design_scores_gemma":[0.00020387626,0.000016694275,0.28942654,0.00003065098,0.000015744912,0.00041978736,0.000027570597,0.69526345,0.008583203,0.0051613026,0.0005772293,0.000273942],"about_ca_topic_score_codex":0.000299176,"about_ca_topic_score_gemma":0.0002876357,"teacher_disagreement_score":0.7080699,"about_ca_system_score_codex":0.00022469275,"about_ca_system_score_gemma":0.0001791583,"threshold_uncertainty_score":0.99974006},"labels":[],"label_agreement":null},{"id":"W2725268319","doi":"10.2200/s00776ed1v01y201704bme056","title":"Computerized Analysis of Mammographic Images for Detection and Characterization of Breast Cancer","year":2017,"lang":"en","type":"article","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Università degli Studi di Roma Tor Vergata","keywords":"Breast cancer; Mammography; Characterization (materials science); Cancer detection; Artificial intelligence; Cancer; Computer vision; Computer science; Pattern recognition (psychology); Medicine; Internal medicine; Physics; Optics","score_opus":0.006733878626666594,"score_gpt":0.23254368948699242,"score_spread":0.2258098108603258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725268319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24262604,0.00002668372,0.75650615,0.00034458196,0.00026969714,0.00010781273,0.0000688452,0.000047927057,0.0000022954637],"genre_scores_gemma":[0.9958794,0.00007082164,0.0038963,0.000014281897,0.00006855862,0.00005706004,0.00000251973,0.000009807741,0.0000012471427],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914366,0.000017705303,0.0002282072,0.00025695018,0.00021068324,0.00014281821],"domain_scores_gemma":[0.9990752,0.00018346867,0.00023945168,0.00037180734,0.00006918424,0.00006092992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019048832,0.00012006008,0.0003149164,0.000589854,0.000098292825,0.000055837005,0.00035056088,0.00009027379,0.000005649731],"category_scores_gemma":[0.000109380824,0.00010675015,0.00011940727,0.00041179813,0.00009361621,0.00016094811,0.00006481256,0.0000641702,7.208945e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003583647,0.00002093282,0.00018444326,0.00010406306,0.00033677512,3.1959644e-7,0.000037224294,0.0005750124,0.7931759,0.000076637356,0.0000016511316,0.20545122],"study_design_scores_gemma":[0.00017829084,0.000061324965,0.27782133,0.00009408126,0.0001670479,0.0000024963797,7.487086e-7,0.40272298,0.31869897,0.000025211268,0.00011150679,0.00011601932],"about_ca_topic_score_codex":0.000059486178,"about_ca_topic_score_gemma":0.000005771386,"teacher_disagreement_score":0.75325334,"about_ca_system_score_codex":0.000029651676,"about_ca_system_score_gemma":0.000015665693,"threshold_uncertainty_score":0.43531448},"labels":[],"label_agreement":null},{"id":"W2725817408","doi":"10.1007/978-3-319-61188-4","title":"Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging","year":2017,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Medical imaging; Graphical model; Computer graphics (images); Artificial intelligence; Bayesian probability; Computer vision; Human–computer interaction; Data science","score_opus":0.010003029096094957,"score_gpt":0.27294491078032607,"score_spread":0.2629418816842311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725817408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004174075,0.00078914413,0.990241,0.005255408,0.002788115,0.00053221063,0.0000067327123,0.00016432087,0.00018134614],"genre_scores_gemma":[0.10000243,0.00025840473,0.8940414,0.0031004087,0.0023872922,0.000049335475,0.000011530791,0.000063659776,0.00008551872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947542,0.000075322925,0.00054696616,0.0022215967,0.0015927634,0.00080916716],"domain_scores_gemma":[0.9966986,0.00096906826,0.00030018692,0.0012684234,0.00019956744,0.0005641407],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019594706,0.0005534241,0.00067252567,0.0009068269,0.0007268992,0.0012826868,0.0030828982,0.0005680132,0.0000034316813],"category_scores_gemma":[0.000162508,0.00047422273,0.0001136228,0.00042039805,0.0028567668,0.0012745766,0.0027097622,0.0010144068,0.0000015385275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011007828,0.000026479413,0.000036588903,0.00010130449,0.0000088745965,0.00007620126,0.0002795546,0.0007064146,0.000013131363,0.002942971,0.0005156651,0.9952818],"study_design_scores_gemma":[0.00048803235,0.00026352395,0.0000986958,0.0005432664,0.000007864533,0.00037837386,6.594366e-8,0.78599215,0.000026749098,0.20994973,0.0018317661,0.00041975762],"about_ca_topic_score_codex":0.0000259177,"about_ca_topic_score_gemma":0.00005152825,"teacher_disagreement_score":0.994862,"about_ca_system_score_codex":0.00027143655,"about_ca_system_score_gemma":0.001225767,"threshold_uncertainty_score":0.9998569},"labels":[],"label_agreement":null},{"id":"W2735666957","doi":"10.1007/s10278-017-9997-y","title":"Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network","year":2017,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":389,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"Saskatchewan Health Research Foundation; Compute Canada; University of Saskatchewan","keywords":"Convolutional neural network; Nodule (geology); Computer science; Ultrasound; Radiology; Thyroid; Artificial intelligence; Medicine; Pattern recognition (psychology); Internal medicine; Geology","score_opus":0.01618639259369834,"score_gpt":0.2612800436195284,"score_spread":0.24509365102583006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735666957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19582486,0.0021410184,0.78778297,0.0062725977,0.0024538154,0.00012912702,0.000008908976,0.00006697842,0.0053197066],"genre_scores_gemma":[0.9945939,0.000021192469,0.004811641,0.00008313859,0.0004100797,0.00000157428,0.00000198708,0.000010389433,0.00006609805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987494,0.000030494783,0.00041348703,0.00019452946,0.00034141942,0.00027069764],"domain_scores_gemma":[0.99852735,0.00014673502,0.00073031103,0.00033338708,0.00018044964,0.000081766004],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00036010717,0.00012048655,0.00016465392,0.00010216675,0.00027540332,0.0015961861,0.0008872387,0.000027925997,0.0000036075805],"category_scores_gemma":[0.0002603777,0.0001168355,0.000083889325,0.00012618322,0.00011338218,0.006224265,0.00013512174,0.0003103774,0.000006746397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007945564,0.00018927336,0.64182955,0.000024915786,0.00006511698,0.00015812654,0.0005722557,0.0110740075,0.06359628,0.001458621,0.028266273,0.25268608],"study_design_scores_gemma":[0.0025197652,0.0002367037,0.5420917,0.0002867164,0.000026342937,0.002191848,0.0002009377,0.42348948,0.0047359904,0.019460104,0.003981198,0.0007791697],"about_ca_topic_score_codex":0.0000086657,"about_ca_topic_score_gemma":0.0000052033606,"teacher_disagreement_score":0.79876906,"about_ca_system_score_codex":0.00018919818,"about_ca_system_score_gemma":0.00006780255,"threshold_uncertainty_score":0.99944025},"labels":[],"label_agreement":null},{"id":"W2737119926","doi":"10.1007/978-3-319-67558-9_17","title":"Transitioning Between Convolutional and Fully Connected Layers in Neural Networks","year":2017,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Pooling; Convolutional neural network; Computer science; Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Digital pathology; Computer vision","score_opus":0.02106876533934275,"score_gpt":0.2667063455484795,"score_spread":0.24563758020913673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737119926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07918042,0.00053555594,0.9150313,0.0021130482,0.0026089263,0.00037237437,0.0000055390155,0.00014298239,0.000009851378],"genre_scores_gemma":[0.89731187,0.000022436112,0.10171353,0.00036821698,0.0005367962,0.000027061536,0.000006951022,0.000012908467,2.4602318e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963568,0.0001702777,0.0004765437,0.0016512653,0.0006272094,0.00071789406],"domain_scores_gemma":[0.99771523,0.0005380629,0.0003107391,0.0011029465,0.00017646339,0.00015658296],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012163789,0.00039266894,0.0004947919,0.0006466627,0.00046074291,0.0011452008,0.0026622275,0.0003795372,0.0000025418124],"category_scores_gemma":[0.00014052266,0.00041517895,0.000074204385,0.0008679292,0.000829191,0.000852152,0.002019307,0.001562113,0.0000012670107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006439176,0.000011273878,0.010008482,0.000026693435,0.0000060895745,0.000026742875,0.0006717045,0.7001424,0.00004046417,0.00010464004,0.000002513965,0.2889526],"study_design_scores_gemma":[0.0003809648,0.00007067256,0.07451472,0.00024101246,0.00000482721,0.000036640187,4.0318676e-7,0.90720737,0.00021398276,0.016923252,0.000006965463,0.00039919058],"about_ca_topic_score_codex":0.00035952174,"about_ca_topic_score_gemma":0.00043511798,"teacher_disagreement_score":0.81813145,"about_ca_system_score_codex":0.00046497013,"about_ca_system_score_gemma":0.000498095,"threshold_uncertainty_score":0.9998917},"labels":[],"label_agreement":null},{"id":"W2738332719","doi":"10.1111/his.13313","title":"Pathology Imagebase—a reference image database for standardization of pathology","year":2017,"lang":"en","type":"article","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"Cancerföreningen i Stockholm; Stockholms Läns Landsting; Cancerfonden","keywords":"Standardization; Pathology; Anatomical pathology; Gastrointestinal pathology; Medicine; Molecular pathology; Computer science; Information retrieval; Biology; Immunohistochemistry","score_opus":0.033824668524459214,"score_gpt":0.3100867712186621,"score_spread":0.2762621026942029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738332719","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012097248,0.0002113885,0.98153263,0.000989802,0.0016547163,0.00033243987,0.00019316768,0.000120662706,0.002867964],"genre_scores_gemma":[0.6444075,0.00012953424,0.35429317,0.00028736613,0.00015594267,0.00018525918,0.000058477424,0.000031705018,0.00045102637],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99808747,0.00019571697,0.00043373692,0.0007348278,0.00016701785,0.0003812123],"domain_scores_gemma":[0.9964328,0.00012559473,0.0006957034,0.0022585192,0.000419071,0.00006835779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009418526,0.00018990716,0.00040046708,0.00018802182,0.00047538686,0.00005540256,0.0014394124,0.00019299908,0.000026855163],"category_scores_gemma":[0.0007576128,0.00020023379,0.00008554933,0.0000853828,0.00064879394,0.0007334268,0.00052011036,0.00018971576,0.000024861289],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002423802,0.00016152434,0.001108354,0.00020467937,0.0000062469226,0.0010958947,0.0008265712,0.000039800663,0.8133212,0.12438545,0.0065877032,0.052020237],"study_design_scores_gemma":[0.011717133,0.0061353566,0.13323322,0.00020999358,0.00026462073,0.0076464433,0.00015773237,0.020722922,0.3659301,0.11962567,0.33148235,0.0028744712],"about_ca_topic_score_codex":0.00002151285,"about_ca_topic_score_gemma":0.000055391934,"teacher_disagreement_score":0.6323103,"about_ca_system_score_codex":0.00013171847,"about_ca_system_score_gemma":0.00017181007,"threshold_uncertainty_score":0.8165297},"labels":[],"label_agreement":null},{"id":"W2740871063","doi":"10.1038/bdjopen.2017.13","title":"Emerging paradigm of virtual-microscopy for histopathology diagnosis: survey of US and Canadian oral pathology trainees","year":2017,"lang":"en","type":"article","venue":"BDJ Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Texas Health Science Center at Houston","keywords":"Virtual microscopy; Histopathology; Oral and maxillofacial pathology; Oral and maxillofacial surgery; Enthusiasm; Medicine; Medical education; Family medicine; Medical physics; Psychology; Pathology; Dentistry","score_opus":0.05559217988248905,"score_gpt":0.3445395524206001,"score_spread":0.28894737253811104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740871063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95862323,0.00031976655,0.037106697,0.0013521996,0.0010807714,0.0007750832,0.00015962898,0.000015472908,0.0005671291],"genre_scores_gemma":[0.99216896,0.00004823109,0.0074414946,0.00012446847,0.000015941107,0.00011246157,0.0000040969994,0.000009132272,0.00007519848],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990417,0.00013991333,0.00022980208,0.00030673313,0.000058202713,0.00022369414],"domain_scores_gemma":[0.9987709,0.00015121342,0.0002694558,0.0006448885,0.00008096928,0.00008259238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011013754,0.00009288747,0.0002951835,0.00009617169,0.00021350433,0.00008503614,0.0013320715,0.00007837955,0.000007606372],"category_scores_gemma":[0.00032973237,0.000096611846,0.000026386659,0.00006355535,0.00018580614,0.00037309746,0.0003198949,0.000056374756,0.0000010041824],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019722844,0.000097444274,0.7182852,0.00009581324,0.000047031106,0.00005917981,0.004317492,0.00009351498,0.0060577225,0.015093785,0.005564629,0.25009093],"study_design_scores_gemma":[0.00067390484,0.00043852004,0.9843709,0.000028342165,0.000009410998,0.000025234973,0.000019088875,0.0012125211,0.0058506466,0.0013078506,0.00591598,0.0001476225],"about_ca_topic_score_codex":0.2314695,"about_ca_topic_score_gemma":0.4344102,"teacher_disagreement_score":0.26608565,"about_ca_system_score_codex":0.00006211052,"about_ca_system_score_gemma":0.00025356663,"threshold_uncertainty_score":0.7736482},"labels":[],"label_agreement":null},{"id":"W2750605898","doi":"10.1007/978-3-319-67534-3_17","title":"Uncertainty Driven Multi-loss Fully Convolutional Networks for Histopathology","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Weighting; Computer science; Leverage (statistics); Convolutional neural network; Inference; Term (time); Artificial intelligence; Function (biology); Algorithm; Pattern recognition (psychology); Machine learning","score_opus":0.025259219229532618,"score_gpt":0.2695038431022251,"score_spread":0.24424462387269247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750605898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018260147,0.0005539814,0.98888373,0.0009875952,0.007999025,0.00075067696,0.000019106881,0.00020606576,0.0005815841],"genre_scores_gemma":[0.13489829,0.00009421431,0.85876983,0.0018404131,0.0024161187,0.00012567957,0.000025405447,0.00007798236,0.0017520649],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99570686,0.000057461435,0.0005611159,0.002070677,0.0006966155,0.00090726913],"domain_scores_gemma":[0.9958506,0.00072034006,0.0006596204,0.0020195388,0.0005578717,0.00019202675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012779577,0.00059526425,0.00065461925,0.0005549803,0.00086356455,0.00046534793,0.004861777,0.0006350995,0.000013305756],"category_scores_gemma":[0.00022428883,0.0005937719,0.00024102631,0.00016890335,0.0018113145,0.0006295825,0.0014076565,0.000945749,0.000021973177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003870725,0.00003215657,0.00011777898,0.00004088683,0.000014874036,0.000090928945,0.00030897913,0.51805836,0.00007258038,0.019637458,0.0001464246,0.46144086],"study_design_scores_gemma":[0.0005882034,0.00024781964,0.00043166452,0.00017444219,0.00001142648,0.00016385183,4.7758274e-8,0.93082446,0.0000675872,0.057382684,0.009466279,0.0006415622],"about_ca_topic_score_codex":0.000039994786,"about_ca_topic_score_gemma":0.00039537766,"teacher_disagreement_score":0.4607993,"about_ca_system_score_codex":0.0012544508,"about_ca_system_score_gemma":0.00102986,"threshold_uncertainty_score":0.9996514},"labels":[],"label_agreement":null},{"id":"W2751783141","doi":"10.5858/arpa.2017-0139-oa","title":"Integrated Pathology Informatics Enables High-Quality Personalized and Precision Medicine: Digital Pathology and Beyond","year":2017,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakeridge Health; University Health Network","funders":"","keywords":"Digital pathology; Subspecialty; Workload; Hematopathology; Pathology; Precision medicine; Computer science; Medicine; Quality assurance; Personalized medicine; Informatics; Medical physics; Medical laboratory; Health informatics; Telepathology; Data science; Health care; Bioinformatics; External quality assessment; Telemedicine; Engineering","score_opus":0.01617967339655678,"score_gpt":0.2882883895018667,"score_spread":0.2721087161053099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751783141","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87943447,0.0023071817,0.11070861,0.004141602,0.00096432056,0.00031738073,0.00008825491,0.00011365772,0.0019245265],"genre_scores_gemma":[0.9797744,0.0016780994,0.01733276,0.00087096717,0.00017986112,0.000026278907,0.000030353347,0.00002026554,0.0000869765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99735415,0.00048747807,0.0008873975,0.00056857575,0.00031349697,0.0003888999],"domain_scores_gemma":[0.99631125,0.0011285582,0.0009390378,0.0011923801,0.00022406019,0.0002047343],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0013285626,0.0003337783,0.0008914844,0.00036191984,0.00039222842,0.000048090977,0.0008842724,0.0002237346,0.00001881997],"category_scores_gemma":[0.0023809772,0.00024897294,0.000035578185,0.00019012422,0.0065103527,0.0008202148,0.0007115963,0.00043187817,0.0000029782645],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006891,0.00019000984,0.03650141,0.0005850325,0.00016630469,0.0020235176,0.07075271,0.0000060070843,0.18559335,0.09595567,0.0014284161,0.6061085],"study_design_scores_gemma":[0.024499258,0.011974226,0.6728655,0.0016875446,0.00037235935,0.00583022,0.014122403,0.0045693535,0.011182372,0.23098503,0.019890945,0.0020207711],"about_ca_topic_score_codex":0.00003315093,"about_ca_topic_score_gemma":0.000028256643,"teacher_disagreement_score":0.6363641,"about_ca_system_score_codex":0.000026144187,"about_ca_system_score_gemma":0.00015077752,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W2757076989","doi":"10.1002/cncy.21921","title":"Application of microscope‐based scanning software (Panoptiq) for the interpretation of cervicovaginal cytology specimens","year":2017,"lang":"en","type":"article","venue":"Cancer Cytopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Japan Agency for Medical Research and Development","keywords":"Medicine; Cytology; Microscope; Interpretation (philosophy); Pathology; Medical physics; Gynecology; Computer science","score_opus":0.02266293800308339,"score_gpt":0.32582898561764245,"score_spread":0.30316604761455906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757076989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028578721,0.0005036321,0.96816766,0.0012234756,0.0009514534,0.00042813932,0.00002781839,0.00003996699,0.00007915208],"genre_scores_gemma":[0.947822,0.000023585604,0.05144598,0.00021231842,0.00010691741,0.0003518343,0.0000030576314,0.000012533676,0.000021813545],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989336,0.000057213052,0.00031815303,0.0003686862,0.00011178678,0.0002105712],"domain_scores_gemma":[0.9976749,0.00022726107,0.00071410486,0.0010603374,0.00029702563,0.000026367694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032370526,0.00012219754,0.00026497187,0.0000895959,0.00025787685,0.000032825636,0.0012335513,0.00010159395,0.000007675788],"category_scores_gemma":[0.000110585606,0.00010522837,0.00008220461,0.000102675986,0.00037298107,0.0002155702,0.00017356523,0.000111437876,0.0000024966084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005604001,0.00009114852,0.110407785,0.00039698262,0.00007867524,0.0000049151663,0.002100264,0.017277017,0.2895823,0.009414721,0.00039728705,0.5696885],"study_design_scores_gemma":[0.0019807694,0.00071882084,0.24239938,0.00013389769,0.00012249908,0.000048557875,0.000071697454,0.33287677,0.41224182,0.0049668276,0.004080653,0.00035830852],"about_ca_topic_score_codex":0.00015789566,"about_ca_topic_score_gemma":0.0001228802,"teacher_disagreement_score":0.9192432,"about_ca_system_score_codex":0.00011180467,"about_ca_system_score_gemma":0.00018525314,"threshold_uncertainty_score":0.42910883},"labels":[],"label_agreement":null},{"id":"W2761423763","doi":"10.1109/ssci.2017.8280803","title":"Learning autoencoded radon projections","year":2017,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Waterloo","funders":"","keywords":"Autoencoder; Artificial intelligence; Computer science; Pattern recognition (psychology); Radon; Histogram of oriented gradients; Perceptron; Deep learning; Curse of dimensionality; Histogram; Encoding (memory); Artificial neural network; Image (mathematics)","score_opus":0.03729994829164604,"score_gpt":0.3041358632811418,"score_spread":0.26683591498949577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761423763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082851463,0.000056400397,0.92111915,0.0012804249,0.004452111,0.00032252542,7.534225e-7,0.0014155136,0.07052462],"genre_scores_gemma":[0.7078447,0.00019075979,0.24304016,0.00013854491,0.000986261,0.00036298577,0.000008576452,0.000046849364,0.047381178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983978,0.00008855486,0.00020617225,0.0007573239,0.00030144007,0.0002486955],"domain_scores_gemma":[0.99789894,0.00003645207,0.00031854655,0.0015608015,0.00012184809,0.00006340959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033611126,0.00020782625,0.00021164837,0.00017750556,0.0005629064,0.0007504087,0.0017386412,0.00026565255,0.00003835707],"category_scores_gemma":[0.00010050794,0.0002036008,0.00013103009,0.000095470874,0.000047537087,0.0003745921,0.0023126048,0.0011475416,0.00013568657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015932388,0.00014278769,0.0018645222,0.00036604344,0.0002437239,0.000043530094,0.0046093967,0.081156805,0.000624781,0.028905084,0.024487618,0.8575398],"study_design_scores_gemma":[0.00021282639,0.00014033326,0.0018552281,0.00014737569,0.000019679333,0.00003970748,0.00003262182,0.9185884,0.0022095083,0.024496313,0.0516432,0.0006147829],"about_ca_topic_score_codex":0.00086293364,"about_ca_topic_score_gemma":0.00009519763,"teacher_disagreement_score":0.856925,"about_ca_system_score_codex":0.00026792873,"about_ca_system_score_gemma":0.00040746768,"threshold_uncertainty_score":0.83026},"labels":[],"label_agreement":null},{"id":"W2764279517","doi":"10.1002/cyto.a.23244","title":"Automatic cellularity assessment from post‐treated breast surgical specimens","year":2017,"lang":"en","type":"article","venue":"Cytometry Part A","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Sunnybrook Hospital; University of Toronto","funders":"National Cancer Institute; National Institutes of Health; Canadian Cancer Society","keywords":"Medicine; Breast cancer; H&E stain; Gold standard (test); Adjuvant therapy; Surgical pathology; Pagetoid; Cancer; Radiology; Pathology; Internal medicine; Staining; Immunohistochemistry","score_opus":0.022204802024439044,"score_gpt":0.297592169810755,"score_spread":0.27538736778631595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2764279517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93766624,0.00007947769,0.04423279,0.0015057233,0.0018886641,0.0002570591,0.00007305218,0.00058300205,0.013713971],"genre_scores_gemma":[0.989671,0.000008468143,0.009455595,0.00005707717,0.0004190562,0.000020597203,0.00001609785,0.000014884293,0.0003372401],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99816746,0.000102274666,0.0002805291,0.00058492296,0.0004997676,0.00036504335],"domain_scores_gemma":[0.9974382,0.00012358253,0.00025185695,0.0018819358,0.00011468971,0.0001897639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034044898,0.000203617,0.0002851848,0.00014187006,0.00055581046,0.00071655534,0.0013618957,0.00012692815,0.0005122733],"category_scores_gemma":[0.000034646175,0.00019121009,0.000115988914,0.00028638123,0.000112441114,0.00072768354,0.0005728344,0.0002671298,0.00044674892],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097670294,0.0015733081,0.51987576,0.00013242468,0.00077441405,0.002711091,0.000763365,0.00005141706,0.025444431,0.015119941,0.010535474,0.4229207],"study_design_scores_gemma":[0.0010555068,0.00013208653,0.89845645,0.00006507899,0.00003289698,0.00017641472,0.0000144386695,0.082223825,0.0065212944,0.0011064855,0.009784011,0.0004315301],"about_ca_topic_score_codex":0.00036908276,"about_ca_topic_score_gemma":0.00002471498,"teacher_disagreement_score":0.42248917,"about_ca_system_score_codex":0.00028164434,"about_ca_system_score_gemma":0.00010380027,"threshold_uncertainty_score":0.7797321},"labels":[],"label_agreement":null},{"id":"W2766877747","doi":"10.1158/0008-5472.can-17-0323","title":"An Image Analysis Resource for Cancer Research: PIIP—Pathology Image Informatics Platform for Visualization, Analysis, and Management","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"National Cancer Institute; Instituto Tecnológico de Costa Rica; Sunnybrook Research Institute","keywords":"Computer science; Plug-in; Digital pathology; Visualization; Resource (disambiguation); Informatics; Software; World Wide Web; Health informatics; Multimedia; Pathology; Artificial intelligence; Medicine; Programming language","score_opus":0.13866535845606107,"score_gpt":0.49729864132371504,"score_spread":0.35863328286765395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766877747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06494418,0.00034807855,0.9297735,0.0016243398,0.0001694173,0.0019581786,0.00017192008,0.00010056188,0.00090980524],"genre_scores_gemma":[0.8480141,0.0050162026,0.1312111,0.00040031658,0.00093225064,0.011102814,0.0002006963,0.000120074335,0.0030024138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598014,0.00025518017,0.0005492488,0.0008641932,0.0012094199,0.0011418383],"domain_scores_gemma":[0.9946133,0.00044829748,0.00030392033,0.0023410239,0.0019900512,0.00030340772],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006810416,0.00022281456,0.0004813327,0.0025773146,0.0027932709,0.0018892513,0.0025738445,0.00015925046,0.000043265158],"category_scores_gemma":[0.00029862393,0.00021721286,0.00019980897,0.0033072862,0.0007664698,0.0020569775,0.0010358274,0.0003930753,0.0000058717237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027559183,0.00081828475,0.025207985,0.0057045855,0.018262751,0.000104318264,0.036636412,0.010691477,0.033385944,0.13232577,0.0834713,0.65063524],"study_design_scores_gemma":[0.003262085,0.0010973196,0.034044173,0.00013018589,0.0016151629,0.0000051074717,0.0024524091,0.7885335,0.03822209,0.013447931,0.11615899,0.0010310488],"about_ca_topic_score_codex":0.001154656,"about_ca_topic_score_gemma":0.004356174,"teacher_disagreement_score":0.7985624,"about_ca_system_score_codex":0.0007137356,"about_ca_system_score_gemma":0.00027179281,"threshold_uncertainty_score":0.9991469},"labels":[],"label_agreement":null},{"id":"W2767173690","doi":"10.1186/s12859-018-2111-8","title":"ATMAD: robust image analysis for Automatic Tissue MicroArray De-arraying","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Artificial intelligence; Thresholding; Computer science; Computer vision; Pattern recognition (psychology); Bright-field microscopy; Preprocessor; Sample (material); Biomedical engineering; Microscope; Image (mathematics); Engineering; Optics","score_opus":0.027508111410899483,"score_gpt":0.2767364041537164,"score_spread":0.24922829274281694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767173690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023375307,0.000025013725,0.99475735,0.00015948495,0.00042681795,0.00034456028,0.000009604409,0.00037852136,0.0015611234],"genre_scores_gemma":[0.019920427,0.0000040746977,0.9793491,0.00029272202,0.00017183766,0.000047548547,0.0000067503897,0.0000135917535,0.00019394615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856967,0.000031103802,0.0005063094,0.0002118035,0.00024138944,0.0004397079],"domain_scores_gemma":[0.998441,0.00014625749,0.00028892452,0.0008039846,0.00020661428,0.00011326698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006054324,0.00017970073,0.00025398217,0.00031648434,0.00030260408,0.00036155642,0.0008144082,0.000108364664,0.000044109507],"category_scores_gemma":[0.00012331748,0.00017097579,0.00015415555,0.001205403,0.000103969134,0.0010252226,0.00015409994,0.00008911932,0.00020059252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011783693,0.0004446918,0.013043965,0.005683153,0.0030244587,0.000010263407,0.07967668,0.045971718,0.020504545,0.013152972,0.07280579,0.7455639],"study_design_scores_gemma":[0.00025927636,0.0001283072,0.0009762864,0.00002009004,0.0001147738,0.000014707836,0.00017681086,0.983682,0.00990435,0.00042198368,0.004075191,0.0002262279],"about_ca_topic_score_codex":0.000021580805,"about_ca_topic_score_gemma":0.0000913223,"teacher_disagreement_score":0.9377103,"about_ca_system_score_codex":0.00022042432,"about_ca_system_score_gemma":0.0001634534,"threshold_uncertainty_score":0.6972191},"labels":[],"label_agreement":null},{"id":"W2767236661","doi":"10.1148/rg.2017170077","title":"Deep Learning: A Primer for Radiologists","year":2017,"lang":"en","type":"review","venue":"Radiographics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1099,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Hôpital Saint-Luc; Centre Hospitalier de l’Université de Montréal","funders":"Mitacs","keywords":"Medicine; Primer (cosmetics); Medical physics; Deep learning; Artificial intelligence; Radiology","score_opus":0.12370988590453998,"score_gpt":0.38176009757887086,"score_spread":0.2580502116743309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767236661","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0924137e-8,0.6300775,0.36730182,0.000023961826,0.0013046702,0.0007068886,0.000002893911,0.00024887198,0.00033339657],"genre_scores_gemma":[0.0000031796592,0.97540903,0.02297873,0.000022027776,0.000597439,0.0005399172,0.000026484111,0.00006171871,0.00036149696],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975604,0.00022272473,0.00050619326,0.00092805986,0.00027261596,0.0005100347],"domain_scores_gemma":[0.9966093,0.00047829185,0.0009425575,0.0017207377,0.00011528964,0.0001338658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007905466,0.00048174584,0.0014318641,0.0006652181,0.00055733963,0.000358643,0.0027810128,0.0006505682,0.000002319159],"category_scores_gemma":[0.00026861878,0.00041895348,0.0013824776,0.00067356013,0.0002046654,0.00029144823,0.00024095552,0.0007993646,0.000019931977],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012480192,0.000010556074,0.000008118586,0.0025249042,0.00016807954,0.0000056251256,0.000025990266,0.0000064802935,2.4083466e-8,0.0035742745,0.0006786713,0.99299604],"study_design_scores_gemma":[0.00013619696,0.00015978821,0.0000049427426,0.0012765095,0.00025539656,0.00012552727,6.552369e-7,0.0021519654,2.5438266e-7,0.0008266165,0.9945924,0.00046970008],"about_ca_topic_score_codex":0.000011449889,"about_ca_topic_score_gemma":0.0000066094826,"teacher_disagreement_score":0.99391377,"about_ca_system_score_codex":0.00014690492,"about_ca_system_score_gemma":0.00026256478,"threshold_uncertainty_score":0.99982625},"labels":[],"label_agreement":null},{"id":"W2772723798","doi":"10.1001/jama.2017.14585","title":"Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer","year":2017,"lang":"en","type":"article","venue":"JAMA","topic":"AI in cancer detection","field":"Computer Science","cited_by":3297,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Lymph node; Algorithm; H&E stain; Receiver operating characteristic; Deep learning; Test set; Artificial intelligence; Breast cancer; Lymph; Machine learning; Pathology; Cancer; Radiology; Staining; Internal medicine; Computer science","score_opus":0.014400447588375477,"score_gpt":0.29216061758367734,"score_spread":0.27776016999530184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772723798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37247756,0.00005888139,0.6267817,0.00021355033,0.00019498979,0.00017903905,0.00001483447,0.000021725147,0.000057687204],"genre_scores_gemma":[0.9823082,0.000042422307,0.017247122,0.000020243577,0.000067326444,0.00029378888,4.4857794e-7,0.000009629247,0.000010836888],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99912226,0.000048401285,0.00019057635,0.00023383995,0.0002140573,0.00019089105],"domain_scores_gemma":[0.998808,0.00024298087,0.00037980426,0.00036670236,0.00016589448,0.00003656235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036367262,0.000091070244,0.0001931867,0.00009971694,0.000120818935,0.000072435345,0.00037816758,0.000041949614,0.000006585088],"category_scores_gemma":[0.00013494538,0.00007967902,0.00002741686,0.00013131673,0.00005767585,0.0005579962,0.00009793872,0.00008650346,3.1936983e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007187126,0.000047447087,0.027133076,0.00008217011,0.00003704731,0.000002304867,0.0003408923,0.008476986,0.0029305036,0.000056118763,0.0000019481713,0.96081966],"study_design_scores_gemma":[0.0014111613,0.00022512957,0.7976634,0.00011908083,0.000013599158,0.0000109331395,0.000095221556,0.17951599,0.02057381,0.00017367257,0.000090534515,0.000107471715],"about_ca_topic_score_codex":0.000901347,"about_ca_topic_score_gemma":0.00027099898,"teacher_disagreement_score":0.96071213,"about_ca_system_score_codex":0.00030637317,"about_ca_system_score_gemma":0.000091983355,"threshold_uncertainty_score":0.3249216},"labels":[],"label_agreement":null},{"id":"W2772926238","doi":"10.1109/tmi.2017.2781228","title":"Adversarial Stain Transfer for Histopathology Image Analysis","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Normalization (sociology); Segmentation; Image segmentation; Stain; Discriminative model; Computer vision; Classifier (UML); Pathology","score_opus":0.014112633381263517,"score_gpt":0.29827479287364284,"score_spread":0.28416215949237933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772926238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001126155,0.000018704905,0.98731184,0.007976618,0.0027082432,0.00020225934,0.0000164999,0.00019574145,0.00044394165],"genre_scores_gemma":[0.97674847,0.000023241599,0.021974368,0.0006966238,0.00019452155,0.000110883906,0.0000013560699,0.000017433189,0.00023313305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816835,0.00010889989,0.0002871815,0.0005574232,0.0005055202,0.00037260214],"domain_scores_gemma":[0.99843574,0.00024111678,0.00006625722,0.0009383496,0.000103735525,0.00021483061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087607955,0.00016549163,0.00027435267,0.0003177174,0.00088488794,0.00020407364,0.0011398274,0.00010352203,0.00017060971],"category_scores_gemma":[0.00008164362,0.00016534812,0.00033392123,0.00023931364,0.00029752945,0.00075596175,0.00000472002,0.00037204122,0.000022499567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021926878,0.00027496877,0.00010735045,0.000043405187,0.00030454347,0.00016344478,0.001032796,0.0019614298,0.0053182775,0.00098537,0.0008748569,0.9887143],"study_design_scores_gemma":[0.0027857155,0.00014768561,0.0010454163,0.00003601401,0.0005945714,0.00006067187,0.000066813605,0.9632975,0.022819962,0.0015689952,0.00707419,0.0005024987],"about_ca_topic_score_codex":0.00014594675,"about_ca_topic_score_gemma":0.00016326256,"teacher_disagreement_score":0.9882118,"about_ca_system_score_codex":0.00018313967,"about_ca_system_score_gemma":0.00015985375,"threshold_uncertainty_score":0.6805932},"labels":[],"label_agreement":null},{"id":"W2774301822","doi":"10.1109/icassp.2018.8461430","title":"Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks","year":2018,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Convolutional neural network; Generative adversarial network; Artificial intelligence; Computer science; Generalization; Deep learning; Image (mathematics); Adversarial system; Representation (politics); Generative grammar; Pattern recognition (psychology); Artificial neural network; Contextual image classification; Machine learning; Mathematics","score_opus":0.054170842657326024,"score_gpt":0.2980515653299317,"score_spread":0.2438807226726057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774301822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014991873,0.00017430434,0.9776985,0.00013570715,0.005827481,0.0009820256,0.000004028905,0.00009830638,0.00008773983],"genre_scores_gemma":[0.7599354,0.000049640563,0.2377446,0.00014537513,0.0018397071,0.00015705124,0.00009015983,0.000028243521,0.000009863368],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749744,0.0003051271,0.00071936904,0.0009175622,0.00019651711,0.00036399468],"domain_scores_gemma":[0.9979245,0.000106811356,0.00073856435,0.0007625252,0.00041403965,0.00005357799],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061527925,0.00029937716,0.0004298453,0.0002525418,0.000110311725,0.00010024908,0.00075339834,0.0007130599,0.000009485109],"category_scores_gemma":[0.00005043159,0.00031644956,0.0001320172,0.00043194633,0.00012504723,0.0003001498,0.0006224239,0.0003777083,4.6950586e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004519082,0.000030986004,0.00048748348,0.000028891409,0.000018755589,0.0000011524884,0.00030334748,0.98193836,0.00055204495,0.0022842898,0.00008221999,0.014227276],"study_design_scores_gemma":[0.000493937,0.00012055415,0.002009764,0.000025987038,0.000025541134,0.000005944363,0.000016706132,0.9944423,0.00051225006,0.0020366136,0.000029303535,0.0002811211],"about_ca_topic_score_codex":0.00014078051,"about_ca_topic_score_gemma":0.0004542209,"teacher_disagreement_score":0.7449435,"about_ca_system_score_codex":0.00043685263,"about_ca_system_score_gemma":0.000119913086,"threshold_uncertainty_score":0.9999288},"labels":[],"label_agreement":null},{"id":"W2781875990","doi":"10.1089/tmj.2017.0212","title":"The Influence of Telepathology on Coordination Practices","year":2018,"lang":"en","type":"article","venue":"Telemedicine Journal and e-Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Toronto Metropolitan University","funders":"","keywords":"Telepathology; Context (archaeology); Accreditation; Presentation (obstetrics); Work (physics); Health care; Knowledge management; Process management; Medical education; Computer science; Medicine; Engineering; Telemedicine; Political science; Surgery","score_opus":0.033039992078221184,"score_gpt":0.3613567928461452,"score_spread":0.328316800767924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781875990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72786623,0.0017590133,0.04721619,0.22098148,0.0012475882,0.00021419623,5.6410494e-7,0.000045126853,0.00066963537],"genre_scores_gemma":[0.9923523,0.0016454028,0.0021884711,0.0032199898,0.0005208032,0.0000020221069,1.0020717e-7,0.0000031126203,0.0000678132],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99894947,0.00013798347,0.00032645863,0.00012556747,0.00026861246,0.00019188749],"domain_scores_gemma":[0.9982853,0.00016356978,0.0010791017,0.0001722418,0.00020091758,0.00009888966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025172818,0.00006321472,0.00013147424,0.00008729314,0.0005170152,0.0000345375,0.00026876913,0.000023168077,0.0000035942744],"category_scores_gemma":[0.00025762102,0.0000367364,0.00001357144,0.00023150777,0.00016886127,0.00025720368,0.000048440208,0.00025444946,0.000004208294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005453214,0.000041753086,0.003885088,0.00004087294,0.00001879565,0.0000051482466,0.002770685,0.000027265201,0.00095543487,0.007092046,0.025493264,0.9596151],"study_design_scores_gemma":[0.0022731046,0.026799379,0.7234856,0.0006778135,0.000015612048,0.003654802,0.0011057552,0.008831465,0.0015085451,0.022916917,0.20844747,0.0002835784],"about_ca_topic_score_codex":0.00012828312,"about_ca_topic_score_gemma":0.00008047745,"teacher_disagreement_score":0.9593315,"about_ca_system_score_codex":0.00007419303,"about_ca_system_score_gemma":0.00021468713,"threshold_uncertainty_score":0.39765155},"labels":[],"label_agreement":null},{"id":"W2784010554","doi":"10.1093/ajcp/aqx118.099","title":"100 Creating a Multiplatform Educational Digital Slide Library Using Panoramic Digital Imaging System (Panoptiq): An Institutional Experience","year":2018,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Upload; Computer science; Workflow; Digital pathology; Software; Digital imaging; Telepathology; Technician; Multimedia; Mobile device; Modality (human–computer interaction); Computer graphics (images); Digital image; Artificial intelligence; World Wide Web; Image processing; Telemedicine; Operating system","score_opus":0.04211781166067842,"score_gpt":0.37229122038466006,"score_spread":0.33017340872398165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784010554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7443169,0.00003704356,0.25251716,0.00024492966,0.0016917272,0.00006231004,0.000009532549,0.00006801209,0.0010523904],"genre_scores_gemma":[0.9191746,0.00000532051,0.0784038,0.0003715046,0.0020007624,0.0000032808982,0.0000038675557,0.000019618921,0.000017224042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693775,0.00017199207,0.0015734573,0.00049802364,0.00043477424,0.00038401],"domain_scores_gemma":[0.99649554,0.00074781664,0.0016417603,0.00043540058,0.00034525953,0.00033424702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005573111,0.00021290318,0.0005676685,0.00024456985,0.0003037962,0.00050494884,0.0010630805,0.000075068456,0.000016142967],"category_scores_gemma":[0.00070258294,0.00019121676,0.00022381103,0.0005404925,0.001756175,0.007000668,0.00031478904,0.0004716294,0.000027780157],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029530795,0.00041115953,0.3739333,0.00001429613,0.000060796625,0.0003837771,0.0023159138,0.00041683431,0.00059308903,0.0044326014,0.000052895117,0.61709005],"study_design_scores_gemma":[0.005069437,0.012621072,0.3594185,0.0011632104,0.00012059699,0.06231841,0.012532794,0.5289984,0.001096318,0.008290022,0.005984816,0.0023864352],"about_ca_topic_score_codex":0.00001412606,"about_ca_topic_score_gemma":9.1433304e-7,"teacher_disagreement_score":0.6147036,"about_ca_system_score_codex":0.0001645113,"about_ca_system_score_gemma":0.0010775734,"threshold_uncertainty_score":0.77975935},"labels":[],"label_agreement":null},{"id":"W2784192669","doi":"10.1136/jclinpath-2017-204808","title":"Digital pathology access and usage in the UK: results from a national survey on behalf of the National Cancer Research Institute’s CM-Path initiative","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"Medical Research Council","keywords":"Digital pathology; Respondent; Medicine; Surgical pathology; Telepathology; Service (business); Pathology; Medical education; Family medicine; Medical physics; Health care; Business; Telemedicine; Political science; Marketing","score_opus":0.44421447468161296,"score_gpt":0.5362336585974493,"score_spread":0.09201918391583636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784192669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98564076,0.000052142004,0.0023505373,0.005650589,0.002189507,0.00016865364,0.0002958304,0.0000043239347,0.0036476282],"genre_scores_gemma":[0.99679923,0.00009965909,0.0005020133,0.0016487307,0.00091657724,0.000007641162,0.0000036087167,0.0000049647183,0.0000175751],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99431664,0.002687649,0.0012685538,0.00035828227,0.0011564478,0.0002124064],"domain_scores_gemma":[0.9883576,0.0084660305,0.0009791654,0.0002610848,0.0018787145,0.000057376048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01424226,0.00010662997,0.00035164194,0.00023202885,0.00014246917,0.000100037585,0.0015343835,0.00021145519,0.000009288525],"category_scores_gemma":[0.016657244,0.00006309307,0.00009864759,0.0006524121,0.0013401567,0.000652981,0.0004860695,0.0011700286,0.0000041567296],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005695171,0.0019397271,0.85743815,0.000016240876,0.00020380257,0.0006041716,0.008871006,0.000715451,0.00055027555,0.014477991,0.02858301,0.080905005],"study_design_scores_gemma":[0.0013851352,0.00088864425,0.95907676,0.00006631714,0.0000038791504,0.00009715603,0.000025336707,0.0003608783,0.00011064667,0.03717098,0.00074847357,0.000065800086],"about_ca_topic_score_codex":0.00012350685,"about_ca_topic_score_gemma":0.0014752981,"teacher_disagreement_score":0.10163861,"about_ca_system_score_codex":0.000118580356,"about_ca_system_score_gemma":0.0010413585,"threshold_uncertainty_score":0.99162585},"labels":[],"label_agreement":null},{"id":"W2786454739","doi":"","title":"Performance Comparison of Machine Learning Techniques for Breast Cancer Detection","year":2018,"lang":"en","type":"article","venue":"Nova Journal of Engineering and Applied Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"C4.5 algorithm; Machine learning; AdaBoost; Artificial intelligence; Breast cancer; Decision tree; Support vector machine; Logistic regression; Naive Bayes classifier; Computer science; Cancer; Statistical classification; Algorithm; Medicine; Internal medicine","score_opus":0.023676860638824546,"score_gpt":0.2826173394445058,"score_spread":0.2589404788056812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786454739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45869097,0.00015300512,0.5405926,0.00006325221,0.00033305612,0.000050310482,8.159426e-7,0.000030643747,0.00008534155],"genre_scores_gemma":[0.9523074,0.00003547324,0.047441524,0.0000060397037,0.00019917048,0.0000036211152,2.161475e-8,0.000003655946,0.000003087478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993331,0.000004772776,0.00023128385,0.00011656366,0.00019044435,0.00012384541],"domain_scores_gemma":[0.99949586,0.000049652535,0.00023149098,0.000054502478,0.00013472234,0.00003374451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005670496,0.000071020964,0.00014697162,0.00017285082,0.00014149814,0.000043669665,0.00025456073,0.0000306032,0.0000022771528],"category_scores_gemma":[0.000013145087,0.000057260135,0.000024400391,0.00036191713,0.000096661715,0.000255524,0.000034381836,0.00012509263,1.5330787e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036745874,0.000015780382,0.0032437658,0.00006481144,0.000014075277,7.953509e-8,0.00041298597,0.017823314,0.29670826,0.000509512,0.0000092604605,0.6811614],"study_design_scores_gemma":[0.00011728996,0.00046322148,0.002937467,0.00006454751,0.000005692262,0.000041381365,0.000024362165,0.5029489,0.49285415,0.000029714214,0.00044059192,0.00007270224],"about_ca_topic_score_codex":0.000007682677,"about_ca_topic_score_gemma":0.000004752625,"teacher_disagreement_score":0.6810887,"about_ca_system_score_codex":0.000028176435,"about_ca_system_score_gemma":0.00003295891,"threshold_uncertainty_score":0.23350005},"labels":[],"label_agreement":null},{"id":"W2789567894","doi":"10.1101/259002","title":"Candidate SNP analyses integrated with mRNA expression and hormone levels reveal influence on mammographic density and breast cancer risk","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Single-nucleotide polymorphism; SNP; Breast cancer; Candidate gene; Biology; Gene; Genotype; Gene expression; Bioinformatics; Genetic association; Genetics; Oncology; Cancer; Medicine","score_opus":0.01843534684581842,"score_gpt":0.251228294581503,"score_spread":0.23279294773568454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789567894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97501236,0.0011783032,0.022038039,0.00013467364,0.0003882962,0.0005058688,0.00034203375,0.00039892358,0.0000014814677],"genre_scores_gemma":[0.98682445,0.0016630251,0.010949979,0.00014958238,0.00020793213,0.00013836799,1.5483789e-7,0.000064625594,0.0000018884144],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9964017,0.0002832196,0.00044061983,0.0017681222,0.00056474225,0.0005415675],"domain_scores_gemma":[0.9964049,0.00007823721,0.0007404768,0.0015733511,0.00082637626,0.00037667167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049596437,0.0006934897,0.0006259754,0.00051600457,0.0004398733,0.00057507935,0.00075824524,0.00044005265,0.0000052887117],"category_scores_gemma":[0.00006636451,0.000583008,0.000065612345,0.0011004804,0.00042868775,0.00058667175,0.00090719847,0.0010474406,0.000004826165],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041516524,0.000099228775,0.19247693,0.00028536207,0.0004084429,0.0000916902,0.00007614617,0.00057165907,0.8050323,0.000060362363,0.00035673197,0.00012598166],"study_design_scores_gemma":[0.0005577199,0.00018384475,0.7951754,0.001035354,0.00012924257,4.1021949e-7,0.0000018283829,0.0024841726,0.19958137,0.000009063968,0.00009387992,0.00074774347],"about_ca_topic_score_codex":0.0018682639,"about_ca_topic_score_gemma":0.0001277072,"teacher_disagreement_score":0.6054509,"about_ca_system_score_codex":0.0002967232,"about_ca_system_score_gemma":0.0005290651,"threshold_uncertainty_score":0.99966216},"labels":[],"label_agreement":null},{"id":"W2790535226","doi":"10.1109/ipta.2017.8310152","title":"Coarse-to-fine texture analysis for inner cell mass identification in human blastocyst microscopic images","year":2017,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Centre for Reproductive Medicine; Simon Fraser University","funders":"","keywords":"Inner cell mass; Blastocyst; Jaccard index; Embryo; Pattern recognition (psychology); Computer science; Artificial intelligence; Identification (biology); Biology; Cell biology; Embryogenesis","score_opus":0.01651862513567778,"score_gpt":0.30041876582766924,"score_spread":0.2839001406919915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790535226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073504195,0.000015675068,0.9235417,0.0011300658,0.00040392263,0.00036483174,0.000007717012,0.00007008195,0.00096178474],"genre_scores_gemma":[0.9587727,0.0000015851916,0.035168856,0.000101982056,0.00008554359,0.000106575295,0.000005863778,0.000009048113,0.0057478184],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988458,0.000025313751,0.00026329866,0.00049590843,0.00015435819,0.00021530125],"domain_scores_gemma":[0.9983968,0.000034283603,0.00020290943,0.0011961369,0.00011566015,0.000054190317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031081296,0.000118490454,0.00017990136,0.00034538252,0.0003524742,0.00059428805,0.0011133824,0.00006992798,0.00002404403],"category_scores_gemma":[0.000037168276,0.00011402986,0.000082923725,0.0004213701,0.000039664214,0.000552995,0.00016274131,0.00008744304,0.000037231923],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001323406,0.00007647867,0.015523182,0.00004886531,0.00006230999,0.0000026899356,0.00040305385,0.0023682192,0.96439135,0.0010917035,0.005879776,0.010139147],"study_design_scores_gemma":[0.000899161,0.00013436713,0.14818938,0.000020326717,0.000083435334,8.74643e-7,0.000041034233,0.06281552,0.78152204,0.0026261283,0.0032753407,0.00039237365],"about_ca_topic_score_codex":0.0002496281,"about_ca_topic_score_gemma":0.002011385,"teacher_disagreement_score":0.8883729,"about_ca_system_score_codex":0.00012342414,"about_ca_system_score_gemma":0.000024473755,"threshold_uncertainty_score":0.5730733},"labels":[],"label_agreement":null},{"id":"W2793336655","doi":"10.1007/978-3-319-93000-8_81","title":"Two-Stage Convolutional Neural Network for Breast Cancer Histology Image Classification","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Convolutional neural network; Pattern recognition (psychology); Contextual image classification; Artificial neural network; Salient; Deep learning; Breast cancer; Image (mathematics)","score_opus":0.026107074356104498,"score_gpt":0.28056397095869867,"score_spread":0.2544568966025942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793336655","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000073743955,0.00045860774,0.9869769,0.0026326866,0.008005698,0.0006764779,0.00009495023,0.0002241513,0.0008567613],"genre_scores_gemma":[0.09296504,0.00007375393,0.89286005,0.00396452,0.008047879,0.00022106899,0.00003331989,0.000105149404,0.0017291966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958418,0.000051592782,0.000584872,0.0019076195,0.00073209754,0.00088204496],"domain_scores_gemma":[0.9968519,0.00045810835,0.0005640669,0.0012314151,0.0007292501,0.00016524584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000815161,0.0005261461,0.00050470757,0.00046670844,0.00051514065,0.0003422527,0.002663216,0.00035978694,0.00015209237],"category_scores_gemma":[0.00003909043,0.0005262097,0.00017056608,0.0005561364,0.0015674125,0.00080074207,0.00071746856,0.0006386681,0.00003948318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107671425,0.000042678428,0.0002702904,0.00011567793,0.000046081626,0.000026558617,0.0005068322,0.10321975,0.001025882,0.07860812,0.0023401326,0.8136903],"study_design_scores_gemma":[0.0004441696,0.0001575961,0.0010464406,0.00013118814,0.000013883793,0.0001304165,1.4543821e-7,0.9089589,0.00017899692,0.08208574,0.006254151,0.0005983848],"about_ca_topic_score_codex":0.00007557028,"about_ca_topic_score_gemma":0.00049443677,"teacher_disagreement_score":0.81309193,"about_ca_system_score_codex":0.0014351826,"about_ca_system_score_gemma":0.0010139003,"threshold_uncertainty_score":0.99971896},"labels":[],"label_agreement":null},{"id":"W2794596664","doi":"10.48550/arxiv.1803.11241","title":"Improve the performance of transfer learning without fine-tuning using dissimilarity-based multi-view learning for breast cancer histology images","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transfer of learning; Feature (linguistics); Artificial intelligence; Extractor; Computer science; Deep learning; Context (archaeology); Breast cancer; Pattern recognition (psychology); Random forest; Machine learning; Cancer; Medicine; Biology","score_opus":0.06915254186653698,"score_gpt":0.231507616544222,"score_spread":0.162355074677685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794596664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41404098,0.000106311214,0.58472914,0.00008578741,0.00054568605,0.00035355403,0.000021499376,0.00009395151,0.000023109164],"genre_scores_gemma":[0.9924895,0.00014817361,0.006848127,0.000043165583,0.00013629171,0.000009733859,0.0000058467194,0.000041118456,0.00027805447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977556,0.0003063113,0.00031807367,0.0010367694,0.00012208261,0.0004611904],"domain_scores_gemma":[0.99812627,0.0001875676,0.00042552347,0.0007187913,0.00045500524,0.00008686158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056970195,0.00038253443,0.0005044417,0.00022705895,0.00064511684,0.00007105059,0.0013469771,0.00030145017,0.000023751161],"category_scores_gemma":[0.000036492325,0.00036512018,0.0002696855,0.000443395,0.00040140245,0.00031816977,0.00054784113,0.0011264887,0.000001792994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016094619,0.00003557521,0.03886241,0.00060417276,0.00010664661,0.000006257263,0.00044241807,0.9511478,0.0032895196,0.00020016183,0.000006458623,0.0051376238],"study_design_scores_gemma":[0.0007875608,0.00015661989,0.0037727593,0.00040402188,0.00018452709,0.000007282875,0.000041731706,0.99024993,0.0035573107,0.000080176906,0.00034303582,0.000415013],"about_ca_topic_score_codex":0.0004599251,"about_ca_topic_score_gemma":0.00011749145,"teacher_disagreement_score":0.57844853,"about_ca_system_score_codex":0.0005135378,"about_ca_system_score_gemma":0.00053639023,"threshold_uncertainty_score":0.9998801},"labels":[],"label_agreement":null},{"id":"W2794917520","doi":"10.1007/978-3-319-78723-7_29","title":"Predicting Tumor Locations in Prostate Cancer Tissue Using Gene Expression","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Prostate cancer; Computer science; Expression (computer science); Cancer; Medicine; Internal medicine; Programming language","score_opus":0.021398727667973093,"score_gpt":0.2797690182318267,"score_spread":0.25837029056385363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794917520","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005108206,0.0006981976,0.9896044,0.000246815,0.0031890352,0.00065925857,0.000008948704,0.00017944771,0.00030565844],"genre_scores_gemma":[0.29669297,0.00008591624,0.7004536,0.0007392714,0.001596282,0.00007300737,0.000003927139,0.00007819268,0.0002768414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592555,0.000050341467,0.00063183927,0.0017451555,0.000928621,0.0007185017],"domain_scores_gemma":[0.9976643,0.00018787202,0.0004523187,0.0012377658,0.00031278914,0.00014499361],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007688465,0.00048057965,0.00042714807,0.0010172398,0.0003607388,0.000419466,0.0022127526,0.00020637197,0.00004129124],"category_scores_gemma":[0.000063648695,0.0004728914,0.000057587284,0.0010072035,0.00058141036,0.0010322065,0.0013081532,0.0007694986,0.000020663798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028123928,0.000056840006,0.0020380467,0.00015619122,0.000013633822,0.0001816519,0.0059817443,0.43744484,0.02783966,0.0004225951,0.00004347281,0.5257932],"study_design_scores_gemma":[0.0002810767,0.00016668411,0.00019893909,0.001571467,0.0000071700433,0.00011105775,5.589584e-7,0.8757997,0.09417507,0.026407214,0.00060899433,0.0006720454],"about_ca_topic_score_codex":0.00033026322,"about_ca_topic_score_gemma":0.00070255535,"teacher_disagreement_score":0.52512115,"about_ca_system_score_codex":0.0013164378,"about_ca_system_score_gemma":0.0011201411,"threshold_uncertainty_score":0.99977225},"labels":[],"label_agreement":null},{"id":"W2796393343","doi":"10.2196/mhealth.9518","title":"Development of Whole Slide Imaging on Smartphones and Evaluation With ThinPrep Cytology Test Samples: Follow-Up Study","year":2018,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai Jiao Tong University","keywords":"Android (operating system); Telepathology; Computer science; Android application; Photogrammetry; Multimedia; Artificial intelligence; Real-time computing; Computer hardware; Computer vision; Operating system; Health care","score_opus":0.07019617203025377,"score_gpt":0.37658876469225505,"score_spread":0.30639259266200125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796393343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97949857,0.00015583434,0.0178673,0.001006192,0.00037258226,0.0008752388,0.0000024941364,0.00007092203,0.00015089074],"genre_scores_gemma":[0.9796349,0.000017280181,0.019600954,0.0005183191,0.00008832872,0.00011164497,0.0000023882983,0.000010500992,0.00001567916],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99815893,0.00016239834,0.000391624,0.0005284709,0.00041843747,0.00034011528],"domain_scores_gemma":[0.9987971,0.00017041477,0.0002838736,0.00035696232,0.00021031173,0.000181328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013701705,0.00015360906,0.00024519773,0.00016532515,0.0004412629,0.00004247351,0.00017372018,0.000040039544,0.000003931025],"category_scores_gemma":[0.000047239595,0.00012572506,0.000010072041,0.00029595656,0.00010210238,0.00022103128,0.000094468385,0.00013201011,0.000005630881],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003692165,0.0004297189,0.2166062,0.00046533166,0.00002528534,0.0000028157622,0.05565519,0.0000070633478,0.00024573875,0.00046179217,0.00052131916,0.7252103],"study_design_scores_gemma":[0.0031815579,0.0035643056,0.9773948,0.00013095394,0.00003443505,0.000041837113,0.002587926,0.009938659,0.0006635609,0.0006454191,0.0015625681,0.00025394253],"about_ca_topic_score_codex":0.00023661683,"about_ca_topic_score_gemma":0.0016151102,"teacher_disagreement_score":0.7607886,"about_ca_system_score_codex":0.00017996982,"about_ca_system_score_gemma":0.00082339224,"threshold_uncertainty_score":0.5126919},"labels":[],"label_agreement":null},{"id":"W2799291955","doi":"10.1016/j.compbiomed.2018.04.004","title":"Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning","year":2018,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Computer science; Artificial intelligence; CAD; Convolutional neural network; Mammography; Pattern recognition (psychology); Digital Breast Tomosynthesis; Digital mammography; Voxel; Artificial neural network; Deep learning; Breast cancer; Computer vision; Cancer","score_opus":0.02959589168776544,"score_gpt":0.28766001068283964,"score_spread":0.2580641189950742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799291955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31983477,0.0004391335,0.6786383,0.00023371763,0.0007373368,0.00006170317,0.0000016354024,0.000030647712,0.000022804878],"genre_scores_gemma":[0.9947004,0.00006258169,0.00470344,0.00016739703,0.0003521856,0.0000013613211,0.0000071775808,0.000003963153,0.0000015233676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906445,0.00007170522,0.00018632905,0.00042669653,0.0000527148,0.00019808524],"domain_scores_gemma":[0.99936944,0.0002776738,0.00006997925,0.0002060877,0.000030451154,0.000046391826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032489546,0.000101437836,0.00016622397,0.00014153769,0.00011024127,0.000021086596,0.00025720045,0.00009410341,0.000001211102],"category_scores_gemma":[0.00008942948,0.00009089314,0.00000585042,0.00026449317,0.00045662024,0.00040237026,0.00030189272,0.00021219296,2.8136924e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011100507,0.00001746628,0.29196167,0.0000136604995,0.000015001381,0.000013041032,0.00033837394,0.0025161938,0.0017720627,0.0005303004,0.000024223331,0.702687],"study_design_scores_gemma":[0.00062648766,0.00015552733,0.037987668,0.000075135955,0.0000023389903,0.00016967092,0.000029591714,0.9598666,0.00002754234,0.0007902236,0.0001811768,0.00008807411],"about_ca_topic_score_codex":0.000095190575,"about_ca_topic_score_gemma":0.00013661827,"teacher_disagreement_score":0.9573504,"about_ca_system_score_codex":0.00006122708,"about_ca_system_score_gemma":0.000014240777,"threshold_uncertainty_score":0.37065148},"labels":[],"label_agreement":null},{"id":"W2800292742","doi":"10.1038/s41598-018-24876-0","title":"A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Cluster (spacecraft); Image (mathematics); Contextual image classification; Pathology; Machine learning; Medicine","score_opus":0.034882807138943865,"score_gpt":0.28126456010336326,"score_spread":0.2463817529644194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800292742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0384492,0.000029121826,0.94878596,0.00033863864,0.007187861,0.0006132704,7.5106055e-7,0.00036799096,0.00422719],"genre_scores_gemma":[0.71191275,0.0000016141641,0.28293097,0.00009571276,0.00035496434,0.00023467906,0.00003420333,0.000024314077,0.0044107707],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708265,0.00013126226,0.00049342675,0.001412735,0.00043481743,0.0004451208],"domain_scores_gemma":[0.99746495,0.000059394817,0.0004132326,0.0013996575,0.00055725663,0.00010550888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028276902,0.00016418096,0.00018186546,0.00023513084,0.00085781934,0.00064367923,0.0005245732,0.00012276517,0.000014790904],"category_scores_gemma":[0.00026987118,0.00014150211,0.00007806522,0.00082786224,0.0004370208,0.0007493588,0.00023144044,0.00016925107,0.000042515727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054286225,0.00039279598,0.0008971314,0.00015148416,0.000039892646,0.00008099739,0.0071535455,0.0003607919,0.71827865,0.0016695178,0.05060351,0.2203174],"study_design_scores_gemma":[0.00044041633,0.00023887538,0.00029687147,0.000016777174,0.000015054785,0.00060410076,0.00015835227,0.9078276,0.036498923,0.008537378,0.04503932,0.0003263123],"about_ca_topic_score_codex":0.0000060741277,"about_ca_topic_score_gemma":0.0000037024638,"teacher_disagreement_score":0.9074668,"about_ca_system_score_codex":0.00013667661,"about_ca_system_score_gemma":0.00017639635,"threshold_uncertainty_score":0.65977395},"labels":[],"label_agreement":null},{"id":"W2801876365","doi":"10.5858/arpa.2017-0496-cp","title":"US Food and Drug Administration Approval of Whole Slide Imaging for Primary Diagnosis: A Key Milestone Is Reached and New Questions Are Raised","year":2018,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Milestone; Food and drug administration; Digital pathology; Medicine; Administration (probate law); Companion diagnostic; Pathology; Surgical pathology; Medical physics; Drug administration; Clinical pathology; Medical education; Medical emergency; Political science; History; Internal medicine","score_opus":0.014968389923164835,"score_gpt":0.27113939458057534,"score_spread":0.2561710046574105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801876365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82574177,0.004360734,0.16060859,0.008297838,0.00030220492,0.00042864916,0.00006929009,0.00006076366,0.00013017586],"genre_scores_gemma":[0.93643385,0.00023803706,0.062317964,0.00063260546,0.00026295634,0.00007392368,0.000008961296,0.000012742239,0.000018941171],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988522,0.00011687237,0.00033605137,0.00040144537,0.00012913473,0.000164295],"domain_scores_gemma":[0.99868846,0.0003857051,0.00032074066,0.00036061511,0.00013568597,0.00010877664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028637366,0.00013834715,0.00032429982,0.00018017275,0.000093764276,0.00000772242,0.00018877072,0.000043434487,0.0000020826083],"category_scores_gemma":[0.00022712503,0.00012902451,0.000024286797,0.00020967999,0.0010397759,0.00020250119,0.00008068636,0.00008832776,3.0005458e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007301938,0.00047046927,0.122763455,0.0009618716,0.000178554,0.000082311075,0.07217994,0.0000039261213,0.55054367,0.007397245,0.008413621,0.23627476],"study_design_scores_gemma":[0.009087616,0.00864049,0.7297155,0.0012887823,0.0002838283,0.00027570326,0.0019344412,0.0030487375,0.20579171,0.026995054,0.012294354,0.00064378994],"about_ca_topic_score_codex":0.00001919368,"about_ca_topic_score_gemma":0.000056199566,"teacher_disagreement_score":0.6069521,"about_ca_system_score_codex":0.000014489253,"about_ca_system_score_gemma":0.0002201524,"threshold_uncertainty_score":0.5261467},"labels":[],"label_agreement":null},{"id":"W2802494476","doi":"10.7717/peerj-cs.154","title":"Supervised deep learning embeddings for the prediction of cervical cancer diagnosis","year":2018,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"European Regional Development Fund","keywords":"Machine learning; Artificial intelligence; Computer science; Deep learning; Dimensionality reduction; Cervical cancer; Supervised learning; Embedding; Population; Cancer; Medicine; Artificial neural network","score_opus":0.023992634840560037,"score_gpt":0.27990829277563234,"score_spread":0.2559156579350723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802494476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032975852,0.00013478647,0.9617395,0.0016017314,0.002987118,0.00031084853,0.0000045811685,0.00018115118,0.00006445648],"genre_scores_gemma":[0.9115713,0.00004654744,0.0868746,0.00035184645,0.0008253533,0.00028894783,4.714581e-7,0.0000095726045,0.000031343076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979133,0.00004256903,0.00027716186,0.0006401314,0.0007056095,0.00042119826],"domain_scores_gemma":[0.998015,0.0003966088,0.00015315242,0.0005783819,0.0007568931,0.000099995224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097343075,0.00013992783,0.000158841,0.0001588623,0.0008118585,0.00026649237,0.002087623,0.000050484094,0.000031052565],"category_scores_gemma":[0.00009998571,0.00010558745,0.00008467063,0.0014137033,0.0006983176,0.0009566864,0.00060760055,0.00015282832,0.0000093675635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024747484,0.00005523857,0.014897228,0.000040332972,0.000025395044,5.2721305e-7,0.004847244,0.0069969012,0.0025577422,0.0033002156,0.0017366528,0.96551776],"study_design_scores_gemma":[0.0002425048,0.00036977604,0.031181592,0.00002967859,0.000010776605,0.000006303905,0.000017894297,0.94225216,0.019529805,0.00045110955,0.0058000917,0.00010832707],"about_ca_topic_score_codex":0.00015905431,"about_ca_topic_score_gemma":0.000042572174,"teacher_disagreement_score":0.96540946,"about_ca_system_score_codex":0.00015475726,"about_ca_system_score_gemma":0.00016676712,"threshold_uncertainty_score":0.62442416},"labels":[],"label_agreement":null},{"id":"W2803004744","doi":"10.1007/s40846-018-0415-9","title":"Computer-Aided Detection of Mammographic Masses Using Hybrid Region Growing Controlled by Multilevel Thresholding","year":2018,"lang":"en","type":"article","venue":"Journal of Medical and Biological Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Thresholding; Artificial intelligence; Mammography; False positive paradox; Computer vision; Pattern recognition (psychology); Computer science; Mathematics; Breast cancer; Image (mathematics); Medicine; Cancer","score_opus":0.025821957320882036,"score_gpt":0.2453580820256755,"score_spread":0.21953612470479344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803004744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45765486,0.0003831846,0.5412757,0.00015376601,0.00047502472,0.000035459238,2.3083099e-7,0.00002045763,0.0000013340909],"genre_scores_gemma":[0.984932,0.0002844229,0.014157076,0.00008910708,0.00053104904,0.000001079188,1.2164202e-7,0.000004637361,5.274058e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864596,0.000056907713,0.0005155672,0.00016673647,0.00042798687,0.00018683725],"domain_scores_gemma":[0.999097,0.00025671825,0.0002793467,0.00008649637,0.00012210311,0.00015835911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008993496,0.00012305091,0.00037901694,0.00016234492,0.00006662976,0.00003787511,0.00032969375,0.00013459452,0.0000038069286],"category_scores_gemma":[0.00023462679,0.00008037819,0.00011776172,0.00019995237,0.00010296395,0.00028882027,0.00012721439,0.00030425543,1.4853275e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039325195,0.0001561969,0.0016847958,0.00012855316,0.00026330163,0.00021552424,0.00011923524,0.0015821432,0.5989618,0.0008474023,0.000095566174,0.39555222],"study_design_scores_gemma":[0.00200664,0.0009452953,0.00090045895,0.00034403912,0.000016973541,0.001127941,0.000010364482,0.94976264,0.04409327,0.00020825583,0.00044084532,0.00014327005],"about_ca_topic_score_codex":0.000009968667,"about_ca_topic_score_gemma":2.769857e-7,"teacher_disagreement_score":0.9481805,"about_ca_system_score_codex":0.000036253645,"about_ca_system_score_gemma":0.000024005325,"threshold_uncertainty_score":0.32777274},"labels":[],"label_agreement":null},{"id":"W2803405718","doi":"10.1186/s12859-018-2184-4","title":"Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Brain Tumour Foundation of Canada; Brain Tumour Research; Nvidia","keywords":"Dimensionality reduction; Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer science; Nonlinear dimensionality reduction; Anomaly (physics); Reduction (mathematics); Feature vector; Space (punctuation); Curse of dimensionality; Physics; Mathematics","score_opus":0.03943739908664989,"score_gpt":0.2879302342849939,"score_spread":0.24849283519834403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803405718","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24078546,0.000079919315,0.75779915,0.00007422459,0.00064233656,0.0001410116,4.785681e-7,0.00022208621,0.0002553532],"genre_scores_gemma":[0.46933618,0.000016346674,0.5303384,0.00003122237,0.00021291964,0.0000043368454,0.0000027511674,0.0000081848875,0.00004963793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885714,0.000101675774,0.00029404057,0.0002646575,0.00026199405,0.0002205107],"domain_scores_gemma":[0.99899125,0.000041180636,0.0003662718,0.00032406847,0.00020857753,0.000068627945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005418698,0.00015601305,0.00013750583,0.0001649333,0.00061838387,0.00016572452,0.00017019444,0.00017031487,0.0000024093329],"category_scores_gemma":[0.00011516986,0.00015189858,0.0000405549,0.00047974914,0.00013932004,0.001154023,0.00014540342,0.00024688555,0.000021376743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031012634,0.00022882022,0.020702615,0.0010691573,0.00007508204,0.000006950402,0.0204426,0.010430364,0.3088359,0.010088249,0.0002355987,0.62757456],"study_design_scores_gemma":[0.00016263888,0.00017388858,0.011829604,0.00002721054,0.000013805982,0.00022808855,0.0004527431,0.97951555,0.0059055225,0.00020681878,0.0013026886,0.00018146256],"about_ca_topic_score_codex":0.000022321628,"about_ca_topic_score_gemma":0.0000249332,"teacher_disagreement_score":0.96908516,"about_ca_system_score_codex":0.00030745514,"about_ca_system_score_gemma":0.000056200544,"threshold_uncertainty_score":0.6194244},"labels":[],"label_agreement":null},{"id":"W2804859730","doi":"10.1016/j.neucom.2018.05.047","title":"Deep learning for biological/clinical data","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning","score_opus":0.18201589520180755,"score_gpt":0.3901749811389061,"score_spread":0.20815908593709853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804859730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023252212,0.00003319876,0.9734049,0.0003323408,0.0017042257,0.00018278544,3.1684786e-7,0.00048379583,0.0006062221],"genre_scores_gemma":[0.80929464,0.000009114258,0.18780462,0.0008156101,0.0020282238,0.000005516688,0.0000035440994,0.000012434961,0.00002630179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983097,0.00015389048,0.00031780163,0.00078742293,0.00012268059,0.00030851393],"domain_scores_gemma":[0.99813306,0.0007524774,0.00016006363,0.00078707,0.000099478755,0.000067865876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009640105,0.00010460846,0.00014732307,0.000042474046,0.00035584284,0.00012406372,0.0016885481,0.000076002565,0.0000051810844],"category_scores_gemma":[0.000673627,0.00009517861,0.000051219744,0.00024936066,0.00008587936,0.0002574082,0.0013934283,0.0002495752,0.00006399616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009234326,0.000021892729,0.004355939,0.000005830554,0.000007815689,0.0000024284209,0.00008157222,0.00033324995,0.00036765577,0.0007512941,0.0009541814,0.9931089],"study_design_scores_gemma":[0.00022320519,0.00044692942,0.0058487626,0.000008147844,0.000002533748,0.000014561492,0.0000053881445,0.9078721,0.00027321218,0.00064680155,0.08454527,0.000113103095],"about_ca_topic_score_codex":0.000003287219,"about_ca_topic_score_gemma":0.0000025550476,"teacher_disagreement_score":0.9929958,"about_ca_system_score_codex":0.00001618517,"about_ca_system_score_gemma":0.000026276566,"threshold_uncertainty_score":0.38812712},"labels":[],"label_agreement":null},{"id":"W2805001284","doi":"10.1109/ijcnn.2018.8489329","title":"Comparing LBP, HOG and Deep Features for Classification of Histopathology Images","year":2018,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Local binary patterns; Support vector machine; Histogram; Computer science; Feature (linguistics); Feature vector; Contextual image classification; Artificial neural network; Feature extraction; Histogram of oriented gradients; Histopathology; Image (mathematics); Pathology; Medicine","score_opus":0.04533836441189806,"score_gpt":0.2975678723868821,"score_spread":0.252229507974984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805001284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015483995,0.0006325617,0.97836775,0.00049842393,0.0012657304,0.00033891498,0.0000034479813,0.00012753141,0.0032816245],"genre_scores_gemma":[0.79954016,0.00005707473,0.19985253,0.000046644225,0.00014963996,0.00008271616,0.000005807453,0.000009344061,0.00025608926],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989455,0.000045811994,0.00022789274,0.0005326849,0.000111884176,0.00013625962],"domain_scores_gemma":[0.9987993,0.0000855902,0.00028135523,0.0006099005,0.00019149073,0.000032335192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027252687,0.00013715668,0.00025535683,0.00012982733,0.00006557113,0.00006458349,0.0005427264,0.0001946551,0.0000036079798],"category_scores_gemma":[0.000040496492,0.00013237298,0.00005530382,0.000060886436,0.00014772628,0.000112949674,0.00068213244,0.00017282604,0.0000018006934],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033306578,0.00033586903,0.04178425,0.004106772,0.00021306438,0.000007506924,0.0073422436,0.0013521163,0.13167523,0.1794495,0.05844806,0.5749523],"study_design_scores_gemma":[0.0006613311,0.00037927623,0.5692441,0.00014000545,0.00006675076,0.00006649585,0.000058581918,0.29908386,0.048825845,0.07694008,0.0038772349,0.0006564619],"about_ca_topic_score_codex":0.000050877534,"about_ca_topic_score_gemma":0.00009016695,"teacher_disagreement_score":0.7840562,"about_ca_system_score_codex":0.00010331048,"about_ca_system_score_gemma":0.000054302287,"threshold_uncertainty_score":0.53980136},"labels":[],"label_agreement":null},{"id":"W2864124816","doi":"10.1109/mecbme.2018.8402431","title":"Simple net: Convolutional neural network to perform differential diagnosis of ampullary tumors","year":2018,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Convolutional neural network; Task (project management); Artificial intelligence; Net (polyhedron); Deep learning; Simple (philosophy); Artificial neural network; Field (mathematics); Differential (mechanical device); Machine learning; Pattern recognition (psychology); Mathematics; Engineering","score_opus":0.014804267085754332,"score_gpt":0.2459236842502768,"score_spread":0.23111941716452247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2864124816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6988037,0.000023185647,0.2981582,0.0005029803,0.0012529675,0.0001638567,0.0000032498806,0.00012425364,0.0009676191],"genre_scores_gemma":[0.9913225,0.000003557631,0.006743567,0.0006853527,0.0011051624,0.000034904155,0.0000025006239,0.000008444961,0.00009399677],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879104,0.000033746815,0.0002398798,0.00031399712,0.00030481038,0.00031652057],"domain_scores_gemma":[0.99922067,0.000081890284,0.000074949916,0.0003761383,0.000133067,0.000113305956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000106123225,0.00011848779,0.00015116918,0.00006499214,0.00015755706,0.000047360205,0.00054079335,0.00004563095,0.0006543837],"category_scores_gemma":[0.000018301922,0.00010762249,0.00006528568,0.00042994812,0.00008639739,0.0002550602,0.00036946396,0.00008150318,0.00006696221],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020679302,0.0002740803,0.46465725,0.000057124143,0.00012011527,0.000009622918,0.0012133301,0.012041863,0.0018104448,0.047691938,0.2617409,0.21017654],"study_design_scores_gemma":[0.00042989166,0.0011896227,0.3975093,0.00002696694,0.000011494612,0.000018770892,0.000019414172,0.5721006,0.013938021,0.0040870365,0.010296104,0.0003727808],"about_ca_topic_score_codex":0.00018878048,"about_ca_topic_score_gemma":0.0001625149,"teacher_disagreement_score":0.5600587,"about_ca_system_score_codex":0.000073563715,"about_ca_system_score_gemma":0.000053174757,"threshold_uncertainty_score":0.7165042},"labels":[],"label_agreement":null},{"id":"W2887263930","doi":"10.1007/978-3-030-27272-2_33","title":"TriResNet: A Deep Triple-Stream Residual Network for Histopathology Grading","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Histopathology; Grading (engineering); Computer science; Artificial intelligence; Residual; Convolutional neural network; Benchmark (surveying); Pattern recognition (psychology); Pathology; Algorithm; Medicine; Engineering","score_opus":0.020361686194451372,"score_gpt":0.27259240158698334,"score_spread":0.25223071539253195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887263930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051176827,0.001265117,0.97115505,0.001251199,0.019439198,0.0013970847,0.00000907362,0.00033480037,0.00003079378],"genre_scores_gemma":[0.4347518,0.000028651766,0.56246305,0.0009370354,0.0016355969,0.00014246558,0.000007446996,0.000028601038,0.0000053540084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941239,0.00028592726,0.00074429554,0.0027156293,0.0007897474,0.0013405111],"domain_scores_gemma":[0.99530065,0.0013736364,0.0005476965,0.0023222845,0.00028631993,0.00016943904],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029854882,0.00059755193,0.00079816714,0.0007888253,0.00041225954,0.0006808993,0.005190473,0.0005719413,0.0000036578513],"category_scores_gemma":[0.00043495203,0.0005936025,0.00022868009,0.0019267203,0.00047090204,0.00051675376,0.0034776723,0.001257535,0.000012667445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003852257,0.000030723906,0.00080928125,0.00008367319,0.0000065298946,0.000019926225,0.0010651135,0.628345,0.00012817344,0.00040417552,0.00014230156,0.36892655],"study_design_scores_gemma":[0.00060117675,0.00034638622,0.0017452706,0.00021897141,0.000012564465,0.000074460906,4.729717e-7,0.9185821,0.0016600298,0.07553834,0.0005783886,0.00064187375],"about_ca_topic_score_codex":0.000093926574,"about_ca_topic_score_gemma":0.00023056289,"teacher_disagreement_score":0.42963412,"about_ca_system_score_codex":0.0011209594,"about_ca_system_score_gemma":0.0011597339,"threshold_uncertainty_score":0.99965155},"labels":[],"label_agreement":null},{"id":"W2888696592","doi":"10.1038/s41379-018-0109-4","title":"An international multicenter study to evaluate reproducibility of automated scoring for assessment of Ki67 in breast cancer","year":2018,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Juravinski Cancer Centre; Sinai Health System; University of Toronto; Ontario Institute for Cancer Research; Queen's University; Alberta Health Services; McMaster University; Juravinski Hospital; University of British Columbia","funders":"Cure Brain Cancer Foundation; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Government of Ontario; Ontario Institute for Cancer Research; Cancer Research UK; Breast Cancer Research Foundation","keywords":"Intraclass correlation; Reproducibility; Medicine; Correlation coefficient; Breast cancer; Coefficient of variation; Confidence interval; Nuclear medicine; Medical physics; Radiology; Statistics; Cancer; Mathematics; Internal medicine","score_opus":0.059686799818928195,"score_gpt":0.42190952613878935,"score_spread":0.36222272631986113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888696592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.731652,0.0000026225864,0.26679817,0.00023371135,0.00075343956,0.00046463005,0.000016858901,0.000056449953,0.00002210288],"genre_scores_gemma":[0.9708888,9.349099e-7,0.028822092,0.000058402624,0.000074556556,0.00014202272,9.793172e-7,0.0000074255136,0.0000048204774],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982016,0.0001849298,0.0003653747,0.00088842097,0.00020145015,0.00015821097],"domain_scores_gemma":[0.99815834,0.000032028238,0.00015801787,0.0011845649,0.00043567983,0.0000313675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019440196,0.00008316845,0.0001930157,0.0001580981,0.000025228086,0.0000113493625,0.0005347642,0.00003248142,0.0000097605],"category_scores_gemma":[0.000067931855,0.00008191223,0.000026541387,0.00017113023,0.00005073056,0.00024256496,0.00021579159,0.000057279045,7.8346795e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019354775,0.0011268802,0.8384342,0.000026863814,0.000030690244,0.0000043446253,0.0077138715,0.012385905,0.096671626,0.000070296825,0.000012279448,0.043329474],"study_design_scores_gemma":[0.00045203604,0.00034036423,0.50609076,0.000012017925,0.0000038311937,0.000002598369,0.00002555584,0.48774654,0.005106559,0.00017768546,0.0000013840279,0.000040648516],"about_ca_topic_score_codex":0.00031112053,"about_ca_topic_score_gemma":0.0005413903,"teacher_disagreement_score":0.47536063,"about_ca_system_score_codex":0.00020595716,"about_ca_system_score_gemma":0.00009063094,"threshold_uncertainty_score":0.33402836},"labels":[],"label_agreement":null},{"id":"W2888878191","doi":"10.3389/fonc.2018.00348","title":"The Pan-Cytokeratin Staining Intensity and Fractal Computational Analysis of Breast Tumor Malignant Growth Patterns Prognosticate the Occurrence of Distant Metastasis","year":2018,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja","keywords":"Cytokeratin; Metastasis; Medicine; Staining; Fractal; Pathology; Oncology; Fractal analysis; Breast tumor; Fractal dimension; Intensity (physics); Immunohistochemistry; Internal medicine; Breast cancer; Cancer research; Cancer; Mathematics","score_opus":0.012847052443808162,"score_gpt":0.2700923653336044,"score_spread":0.25724531288979624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888878191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34148073,0.00009919571,0.656473,0.0010962104,0.00056783465,0.00016552671,0.00008323604,0.0000118065245,0.000022489783],"genre_scores_gemma":[0.979779,0.000027204624,0.020031437,0.0001048883,0.000025730413,0.000021565142,0.000005900813,0.0000031417687,0.0000011214604],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998542,0.00028243687,0.00042479014,0.00029813297,0.00023599915,0.00021662362],"domain_scores_gemma":[0.9984188,0.00052756374,0.00040133198,0.00026902393,0.00034823714,0.000035024328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009030599,0.00010895776,0.00035784589,0.00018620996,0.0001604134,0.000036448215,0.0005196757,0.000038569484,0.0000030789793],"category_scores_gemma":[0.00015157207,0.000069118745,0.00006438236,0.0008266636,0.00070373504,0.00014001841,0.00027531717,0.00015847936,3.3914904e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003465341,0.00019648904,0.77802163,0.000040234096,0.0010913181,0.000025625897,0.009648377,0.0007380078,0.00019402168,0.0040723016,0.0014197518,0.20420568],"study_design_scores_gemma":[0.00038450205,0.0006088156,0.5483948,0.000030092373,0.0002682215,0.000048605543,0.0023657577,0.4420888,0.0010632521,0.0043529603,0.00024491322,0.0001492471],"about_ca_topic_score_codex":0.0001777129,"about_ca_topic_score_gemma":0.00025498617,"teacher_disagreement_score":0.6382983,"about_ca_system_score_codex":0.0001325146,"about_ca_system_score_gemma":0.00016406602,"threshold_uncertainty_score":0.28185806},"labels":[],"label_agreement":null},{"id":"W2890039732","doi":"10.1038/s41374-018-0123-7","title":"Ki67 reproducibility using digital image analysis: an inter-platform and inter-operator study","year":2018,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; Rosztoczy Foundation; Breast Cancer Research Foundation","keywords":"Reproducibility; Intraclass correlation; Breast cancer; Medicine; Digital image analysis; Tissue microarray; Standardization; Cancer; Nuclear medicine; Pathology; Radiology; Medical physics; Internal medicine; Computer science; Mathematics; Statistics; Computer vision","score_opus":0.03432860143619437,"score_gpt":0.29688180500336553,"score_spread":0.26255320356717116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890039732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8830277,0.000013680416,0.11592498,0.000086891785,0.0003882948,0.0002774196,0.000016007501,0.00022934774,0.00003571383],"genre_scores_gemma":[0.9863717,4.8824205e-7,0.013086235,0.00023798423,0.00025377772,0.000016710284,0.000010780484,0.000013505771,0.0000088186025],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771595,0.00015749955,0.0003948613,0.001279561,0.00025262858,0.00019951668],"domain_scores_gemma":[0.99726707,0.000025749443,0.00019248073,0.001760553,0.00057448325,0.00017969082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012140317,0.00018581345,0.00021611164,0.00025546266,0.00024558662,0.00079519954,0.00039246734,0.00006931433,0.0000065309705],"category_scores_gemma":[0.00028716488,0.0001831771,0.000032134423,0.0019566324,0.0003116772,0.005238703,0.00024317135,0.000155361,0.000017130555],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070581205,0.0004985078,0.82008135,0.000060519586,0.0005923228,0.000019980213,0.03314901,0.000114476185,0.11994956,0.000982763,0.00028351665,0.024197437],"study_design_scores_gemma":[0.0015634598,0.0038729776,0.24800037,0.0000970105,0.0005778526,0.000022166489,0.005188071,0.53489095,0.19413333,0.009072338,0.0009418919,0.0016395602],"about_ca_topic_score_codex":0.0000944202,"about_ca_topic_score_gemma":0.00033699308,"teacher_disagreement_score":0.57208097,"about_ca_system_score_codex":0.0002064875,"about_ca_system_score_gemma":0.0001622978,"threshold_uncertainty_score":0.76681274},"labels":[],"label_agreement":null},{"id":"W2890139949","doi":"10.1016/j.media.2019.101552","title":"Generative adversarial network in medical imaging: A review","year":2019,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":1852,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); University of Saskatchewan","funders":"","keywords":"Adversarial system; Computer science; Discriminator; Artificial intelligence; Generative grammar; Consistency (knowledge bases); Machine learning; Image translation; Segmentation; Domain (mathematical analysis); Image (mathematics); Translation (biology); Adaptation (eye); Medical imaging; Deep learning; Mathematics","score_opus":0.02797709482192573,"score_gpt":0.36800618248329203,"score_spread":0.3400290876613663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890139949","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.538938e-9,0.6523762,0.34369504,0.0019003688,0.0007967545,0.0003939196,0.0000035249388,0.00007762618,0.00075656106],"genre_scores_gemma":[3.9361643e-7,0.98970515,0.00470129,0.003613498,0.0014432351,0.0001888014,0.000098987526,0.000035106255,0.00021355346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913112,0.0015971193,0.0017491216,0.0014770558,0.003118228,0.00074729556],"domain_scores_gemma":[0.9961624,0.00074673764,0.0006832541,0.0016599699,0.00015120384,0.00059641514],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004195503,0.00061191735,0.004240989,0.0007069933,0.000083435385,0.00014548318,0.0033563587,0.000570989,0.0032509097],"category_scores_gemma":[0.0018185297,0.0004730886,0.0018966753,0.008316054,0.00021241728,0.00042218296,0.0011237294,0.0017648537,0.000617102],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.244154e-7,0.000034373286,0.000006664361,0.0050234837,0.00080977095,0.00053035334,0.000015115462,0.0000042982742,3.9976573e-9,0.000082863044,0.024344208,0.96914804],"study_design_scores_gemma":[0.00020485788,0.0000141584815,0.000001718492,0.023526844,0.004485098,0.000071857925,0.0000011024828,0.05479938,5.0260947e-8,0.00006791797,0.9163786,0.00044838764],"about_ca_topic_score_codex":0.00016497457,"about_ca_topic_score_gemma":0.00021059571,"teacher_disagreement_score":0.96869963,"about_ca_system_score_codex":0.00051635195,"about_ca_system_score_gemma":0.0023134262,"threshold_uncertainty_score":0.9997721},"labels":[],"label_agreement":null},{"id":"W2890554424","doi":"10.1007/978-3-030-00934-2_15","title":"Predicting Cancer with a Recurrent Visual Attention Model for Histopathology Images","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Discriminative model; Computer science; Histopathology; Digital pathology; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Scalability; Computer vision; Pathology; Medicine","score_opus":0.021116930453384246,"score_gpt":0.28400159260883145,"score_spread":0.2628846621554472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890554424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000718645,0.00044351132,0.99411714,0.00050873746,0.0029786616,0.00072476163,0.000016750439,0.00022993168,0.00026183343],"genre_scores_gemma":[0.14354363,0.000094767696,0.85216326,0.0009141153,0.0018807469,0.0002574757,0.000009212252,0.0000936731,0.0010431309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962419,0.000035322762,0.00045475995,0.0018479415,0.00074847107,0.0006715888],"domain_scores_gemma":[0.9977652,0.00024846956,0.0004748529,0.0008275846,0.000561529,0.00012238201],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094048603,0.0004924215,0.00045689166,0.00062698463,0.0003714713,0.00028930718,0.0017021091,0.00031860333,0.0000105254985],"category_scores_gemma":[0.00005968816,0.00043352888,0.00011490472,0.00038557034,0.00081349554,0.00069156033,0.00067918847,0.00060103345,0.000007594102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011947137,0.000046405614,0.000301395,0.00014951371,0.000018979632,0.000023441356,0.001623193,0.097469606,0.0009516787,0.0011041941,0.00013524154,0.89805686],"study_design_scores_gemma":[0.0003501006,0.0007310538,0.00015364253,0.0004985021,0.00002054211,0.00006522319,1.6124936e-7,0.9682138,0.00073632004,0.028470492,0.00025992125,0.0005002329],"about_ca_topic_score_codex":0.000026067222,"about_ca_topic_score_gemma":0.0003911458,"teacher_disagreement_score":0.89755666,"about_ca_system_score_codex":0.0010124685,"about_ca_system_score_gemma":0.0008346841,"threshold_uncertainty_score":0.99981165},"labels":[],"label_agreement":null},{"id":"W2892938835","doi":"10.1016/j.media.2018.09.005","title":"Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Richmond Hospital; Vancouver General Hospital; BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Grading (engineering); Histopathology; Artificial intelligence; Prostate cancer; Computer science; Computer vision; Prostate; Pattern recognition (psychology); Medicine; Medical physics; Cancer; Pathology; Internal medicine; Biology","score_opus":0.010282521718145456,"score_gpt":0.2790481769492846,"score_spread":0.2687656552311391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892938835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57407963,0.00024093581,0.42449048,0.0006080413,0.00019617802,0.000078091914,0.0000031161737,0.00014213042,0.00016139053],"genre_scores_gemma":[0.98735905,0.000078259705,0.012138971,0.00014749417,0.00009886085,0.000051448595,0.0000054917673,0.000010114406,0.00011031121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793553,0.000253992,0.00049161137,0.00048030066,0.0005461574,0.000292386],"domain_scores_gemma":[0.99882025,0.00031452652,0.00022422287,0.0004054414,0.00011099547,0.00012459052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005227965,0.00013469355,0.00046711272,0.00045647696,0.000078510275,0.000050498114,0.0005539363,0.000089256435,0.0007168854],"category_scores_gemma":[0.00082784327,0.00012171533,0.00014542624,0.0014263034,0.00032138047,0.00040461565,0.00021073449,0.00020448906,0.000015389063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040056202,0.00019569091,0.26089963,0.00005305672,0.00044065824,0.00037378585,0.014187894,0.00035633106,0.033561256,0.000020145684,0.00085567066,0.6890158],"study_design_scores_gemma":[0.00067361526,0.00006506781,0.031332236,0.00007365064,0.00012712028,0.000003431756,0.00014919392,0.94927645,0.017472776,0.00038299925,0.00027005485,0.00017342],"about_ca_topic_score_codex":0.003235901,"about_ca_topic_score_gemma":0.0013242096,"teacher_disagreement_score":0.94892013,"about_ca_system_score_codex":0.000183668,"about_ca_system_score_gemma":0.00010420291,"threshold_uncertainty_score":0.7849392},"labels":[],"label_agreement":null},{"id":"W2897173759","doi":"10.1007/s11517-018-1906-0","title":"Automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms","year":2018,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Institut national de la recherche scientifique; Harvard University","keywords":"Segmentation; Cluster analysis; Segmentation-based object categorization; Scale-space segmentation; Artificial intelligence; Computer science; Image segmentation; Pattern recognition (psychology); Process (computing); Digital pathology; Region growing; Algorithm; Computer vision","score_opus":0.01242833648930586,"score_gpt":0.2561747570024166,"score_spread":0.24374642051311074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897173759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3317567,0.000075395685,0.6665002,0.00021798769,0.0006841542,0.00014380515,6.046716e-7,0.0005253743,0.000095725925],"genre_scores_gemma":[0.83030015,0.000003046968,0.16891468,0.00042281795,0.0003199448,0.000017391283,0.0000050721815,0.000012029095,0.000004858332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739766,0.000215499,0.0005674837,0.00070093916,0.0005108277,0.0006075991],"domain_scores_gemma":[0.99872684,0.0005336563,0.000102242055,0.00033910127,0.000062475454,0.00023566729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013602567,0.00027649783,0.00035388637,0.00017849634,0.00013708978,0.00007131526,0.0008468341,0.00024698922,0.0002012855],"category_scores_gemma":[0.00042964835,0.00022335559,0.00009051523,0.000667217,0.0001969327,0.00013743424,0.00034822096,0.00058707525,0.00010369833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026395637,0.0006586043,0.021628201,0.00019227066,0.000019632687,0.0006044934,0.0008800254,0.029345373,0.10799527,0.0004738045,0.00024006359,0.83793586],"study_design_scores_gemma":[0.0007101858,0.00035083923,0.018316485,0.000078970515,0.0000027261453,0.000037386948,0.000008415244,0.97039384,0.009593762,0.00009516694,0.00012824383,0.00028399582],"about_ca_topic_score_codex":0.000033853008,"about_ca_topic_score_gemma":0.0000022040667,"teacher_disagreement_score":0.94104844,"about_ca_system_score_codex":0.00030455214,"about_ca_system_score_gemma":0.00006962193,"threshold_uncertainty_score":0.9108177},"labels":[],"label_agreement":null},{"id":"W2901030517","doi":"10.1109/tmi.2018.2881415","title":"Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Representation (politics); Pattern recognition (psychology); Generative adversarial network; Medical diagnosis; Computer vision; Machine learning; Pathology; Medicine","score_opus":0.02430001427786206,"score_gpt":0.2765578876928069,"score_spread":0.2522578734149449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901030517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008313025,0.000086582564,0.9901171,0.0035605284,0.0044496376,0.00018674714,0.0000019347474,0.00057982723,0.00018635919],"genre_scores_gemma":[0.9615992,0.000011271216,0.03519203,0.0021702738,0.0008325887,0.000119877586,7.2493424e-7,0.000045173525,0.00002889799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980546,0.00011347957,0.00032672728,0.0005420692,0.0004242728,0.0005388386],"domain_scores_gemma":[0.99857694,0.0006481308,0.000083995255,0.00033161676,0.00012365074,0.00023567982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067455816,0.00018471087,0.00020675904,0.00015684174,0.00046791192,0.0000819102,0.0005610455,0.00012850355,0.00019117803],"category_scores_gemma":[0.00006555361,0.00018653295,0.00013269896,0.00031539032,0.00041832682,0.000426743,0.000004925758,0.00047058062,0.00003865122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037430706,0.000068205016,0.000016844071,0.0000135536,0.000029863902,0.000027896673,0.0008976382,0.014430973,0.0005532201,0.0004243978,0.00046562267,0.9830344],"study_design_scores_gemma":[0.00047076136,0.000099818695,0.00007960854,0.000047240737,0.000018734412,0.00018793171,0.000116363466,0.99574333,0.0013261468,0.00030899266,0.0014064976,0.00019458901],"about_ca_topic_score_codex":0.000010731997,"about_ca_topic_score_gemma":0.00002899032,"teacher_disagreement_score":0.98283976,"about_ca_system_score_codex":0.000116490795,"about_ca_system_score_gemma":0.00010649941,"threshold_uncertainty_score":0.7606593},"labels":[],"label_agreement":null},{"id":"W2901946084","doi":"10.4103/jpi.jpi_53_18","title":"Artificial Intelligence and Digital Pathology: Challenges and Opportunities","year":2018,"lang":"en","type":"review","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":540,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jacobs (Canada); University of Waterloo","funders":"","keywords":"Digital pathology; Computer science; Exploit; Data science; Artificial intelligence; Applications of artificial intelligence; Computer security","score_opus":0.2132836934452924,"score_gpt":0.33964165174277916,"score_spread":0.12635795829748675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901946084","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040628714,0.90761846,0.09061876,0.00015848178,0.0009682732,0.00011524633,0.00000938235,0.000022978591,0.00044779162],"genre_scores_gemma":[0.00005198594,0.9881392,0.011413628,0.00007712643,0.00028871623,0.000004493101,0.0000013851203,0.000011869611,0.000011608605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977538,0.00012323518,0.0015363334,0.0001342149,0.0002185235,0.00023389625],"domain_scores_gemma":[0.9971489,0.000283766,0.0019009542,0.00032298025,0.0002177249,0.00012572877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011052609,0.00028476704,0.0010584558,0.00048673866,0.00008684732,0.00019204228,0.0006109871,0.00039444392,0.0000019714469],"category_scores_gemma":[0.00016230594,0.00021740122,0.00014149075,0.00009269412,0.0004707565,0.0013153448,0.00044757797,0.0005854425,0.000013118237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001830678,0.000010302589,1.8277582e-7,0.0016820931,0.00003282739,0.00025344183,0.0025118128,2.9410378e-7,2.1301231e-8,0.00400606,0.000056194724,0.99144495],"study_design_scores_gemma":[0.00006278685,0.0015609567,0.000003294125,0.004348077,0.00026205718,0.082726896,0.0013871196,0.0005114983,0.0000031156212,0.024209103,0.8844331,0.0004920288],"about_ca_topic_score_codex":4.939469e-8,"about_ca_topic_score_gemma":4.9907925e-7,"teacher_disagreement_score":0.9909529,"about_ca_system_score_codex":0.00005733545,"about_ca_system_score_gemma":0.0002518544,"threshold_uncertainty_score":0.8865364},"labels":[],"label_agreement":null},{"id":"W2903631572","doi":"10.1093/ilar/ily007","title":"Digital Microscopy, Image Analysis, and Virtual Slide Repository","year":2018,"lang":"en","type":"article","venue":"ILAR Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Virtual microscopy; Digitization; Workflow; Digital pathology; Computer science; Telepathology; Digital imaging; Image analysis; Digital image analysis; Digital image; Microscopy; Automation; Computer vision; Artificial intelligence; Image processing; Pathology; Medicine; Image (mathematics); Engineering","score_opus":0.003959413196593032,"score_gpt":0.2381349684765753,"score_spread":0.23417555527998227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903631572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23187438,0.00015509613,0.76440936,0.00021633819,0.0008837499,0.00002542019,0.0000015097415,0.000049718466,0.00238441],"genre_scores_gemma":[0.9768361,0.000023132241,0.021497088,0.00013300478,0.00079059525,8.2176973e-7,2.9275796e-7,0.0000070873543,0.0007119213],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991061,0.00004408514,0.00020649016,0.000225182,0.00023157675,0.00018657123],"domain_scores_gemma":[0.9992963,0.000029442934,0.00013951858,0.0002677277,0.00013790406,0.00012912012],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002334532,0.00008949931,0.00012045014,0.00019030912,0.00035486443,0.0011526524,0.00037003643,0.000042705415,0.000014022788],"category_scores_gemma":[0.000027179281,0.00008072514,0.00008278672,0.000417499,0.00013013989,0.00125508,0.0001467123,0.00021590198,0.00003055344],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106610554,0.00015130399,0.057687834,0.000012641289,0.0013511849,0.0006362983,0.0033180618,0.00003420709,0.59109974,0.00073584024,0.022534344,0.32233194],"study_design_scores_gemma":[0.0019225704,0.0024287195,0.14065185,0.000098310884,0.00049537834,0.012828026,0.0003464449,0.032015152,0.71890455,0.003680889,0.08534924,0.0012788675],"about_ca_topic_score_codex":0.0000058889473,"about_ca_topic_score_gemma":0.00000607079,"teacher_disagreement_score":0.7449617,"about_ca_system_score_codex":0.000075622855,"about_ca_system_score_gemma":0.00006374611,"threshold_uncertainty_score":0.99988425},"labels":[],"label_agreement":null},{"id":"W2904004553","doi":"10.1148/radiol.2018181426","title":"Impact of Digital Mammography on Cancer Detection and Recall Rates: 11.3 Million Screening Episodes in the English National Health Service Breast Cancer Screening Program","year":2018,"lang":"en","type":"article","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Hospital Foundation","funders":"Public Health England; Cancer Research UK","keywords":"Medicine; Mammography; Cancer detection; Breast cancer; Breast cancer screening; Gynecology; Cancer screening; Family medicine; Cancer; Recall; Obstetrics; Medical physics; Internal medicine","score_opus":0.028080408641976,"score_gpt":0.3347723505787126,"score_spread":0.30669194193673655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904004553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9484064,0.00042989975,0.047659006,0.0022674904,0.00043360793,0.00053775014,0.00006212195,0.0001262493,0.000077504665],"genre_scores_gemma":[0.9964991,0.0001443513,0.002237072,0.0004916789,0.00046003173,0.00014884576,0.0000052884134,0.00001175047,0.0000018339338],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984648,0.00023966379,0.00028519737,0.00042060795,0.00024627883,0.00034342118],"domain_scores_gemma":[0.9989532,0.00019707053,0.00023476231,0.00021333442,0.00033803182,0.00006359749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005747923,0.000165369,0.00022412182,0.0003013679,0.00017195003,0.000085703534,0.0003459373,0.00010546699,0.0000058215014],"category_scores_gemma":[0.00003891321,0.0001248733,0.00006809725,0.0011261743,0.00015833983,0.00047575994,0.00006424006,0.00021554768,5.986519e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021143245,0.000076975375,0.22216184,0.00003296771,0.000071575225,0.000001228025,0.002701388,0.0027397526,0.0002149899,0.00012995236,0.00027860864,0.7713793],"study_design_scores_gemma":[0.00065569964,0.0012429125,0.92827904,0.00012170872,0.0000050142344,0.00011303387,0.00012714333,0.06834207,0.00013534189,0.00030105762,0.000494911,0.00018205216],"about_ca_topic_score_codex":0.004283741,"about_ca_topic_score_gemma":0.0061308667,"teacher_disagreement_score":0.7711972,"about_ca_system_score_codex":0.00021630616,"about_ca_system_score_gemma":0.0001512912,"threshold_uncertainty_score":0.64757633},"labels":[],"label_agreement":null},{"id":"W2906465680","doi":"10.4103/jpi.jpi_70_18","title":"The Importance of eSlide Macro Images for Primary Diagnosis with Whole Slide Imaging","year":2018,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network","funders":"National Cancer Institute","keywords":"Computer science; Macro; Digital pathology; Scanner; Digitization; Computer vision; Artificial intelligence; Image quality; Rendering (computer graphics); Digital image; Image processing; Computer graphics (images); Image (mathematics)","score_opus":0.007945628112338001,"score_gpt":0.25285538174432504,"score_spread":0.24490975363198703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906465680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13562557,0.0003207121,0.8604073,0.002090712,0.0007222579,0.00016732974,0.0000075689904,0.000018910858,0.0006396222],"genre_scores_gemma":[0.40965736,0.00030334413,0.5871933,0.0023147857,0.00041679596,0.000035107092,9.541134e-7,0.000018762912,0.000059609927],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860215,0.000036506255,0.0008092475,0.00006204932,0.00025925325,0.00023078456],"domain_scores_gemma":[0.9970336,0.00038653548,0.0015153944,0.0003561936,0.0006599732,0.00004830921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011374281,0.00010623105,0.00022835535,0.00010913448,0.00019012451,0.00007454809,0.00073879876,0.000041717703,0.0000016393234],"category_scores_gemma":[0.00016884784,0.00006571715,0.00008221576,0.00019649607,0.00030101812,0.0010382852,0.000119401884,0.00018511007,0.0000031744203],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061255123,0.00021298899,0.2807924,0.0006000303,0.00035591278,0.00029068568,0.022361457,0.00082746305,0.006023431,0.004349972,0.09039175,0.5931814],"study_design_scores_gemma":[0.012097311,0.015213545,0.22397466,0.0014903551,0.00062622345,0.03170482,0.009147483,0.0639626,0.3113515,0.059329562,0.26900622,0.0020957044],"about_ca_topic_score_codex":6.3003847e-7,"about_ca_topic_score_gemma":0.0000049355544,"teacher_disagreement_score":0.5910857,"about_ca_system_score_codex":0.00008371589,"about_ca_system_score_gemma":0.0001740075,"threshold_uncertainty_score":0.26798677},"labels":[],"label_agreement":null},{"id":"W2907274433","doi":"10.2174/2213275912666190101121058","title":"Importance of Feature Selection and Data Visualization Towards Prediction of Breast Cancer","year":2019,"lang":"en","type":"article","venue":"Recent Patents on Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Random forest; Feature selection; Artificial intelligence; Support vector machine; Breast cancer; Multilayer perceptron; Artificial neural network; Classifier (UML); Visualization; Perceptron; Principal component analysis; Data mining; Pattern recognition (psychology); Cancer; Medicine","score_opus":0.03270891608972389,"score_gpt":0.2985276057406025,"score_spread":0.2658186896508786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907274433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5386846,0.00008694181,0.45785514,0.0004984925,0.0022452078,0.00038720536,0.00008036171,0.00009481322,0.00006725531],"genre_scores_gemma":[0.9879439,0.00050753274,0.0113018695,0.00011607889,0.000087647255,0.000005580871,0.0000105316785,0.000008132353,0.000018716382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978196,0.000048568276,0.00028749008,0.0008196589,0.0007998108,0.00022485603],"domain_scores_gemma":[0.9982694,0.000019894538,0.000352953,0.00082089734,0.00045934002,0.00007752901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061450346,0.00013632694,0.00018846513,0.00023792351,0.000089495166,0.00007968469,0.001184694,0.000056290774,0.000011639159],"category_scores_gemma":[0.000013305823,0.00012227561,0.000019647892,0.0016323813,0.00010696761,0.0015848426,0.0005921227,0.00010764117,0.00000256145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065010914,0.00021018078,0.22199105,0.00015813917,0.000032294443,6.976567e-7,0.00033675518,0.004499151,0.031044837,0.0015534746,0.00065768184,0.73945075],"study_design_scores_gemma":[0.0002574121,0.00020459607,0.36953217,0.00011595211,0.0000051249476,0.0000167755,0.0000025371414,0.61757946,0.011878944,0.00006314897,0.0002543485,0.00008950307],"about_ca_topic_score_codex":0.00005834576,"about_ca_topic_score_gemma":0.000010895359,"teacher_disagreement_score":0.7393612,"about_ca_system_score_codex":0.0001684917,"about_ca_system_score_gemma":0.0002470872,"threshold_uncertainty_score":0.49862546},"labels":[],"label_agreement":null},{"id":"W2908040054","doi":"10.1093/ajcp/142.suppl1.196","title":"Pathology Informatics Trends in Anatomical Pathology: Analysis of 11 Years of United States and Canadian Academy of Pathology Abstracts","year":2014,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pathology; Anatomical pathology; Medicine; Bone pathology; Surgical pathology; Molecular pathology; Renal pathology; Clinical pathology; Biology; Internal medicine; Immunohistochemistry; Kidney","score_opus":0.028679468948394016,"score_gpt":0.3568480397958585,"score_spread":0.3281685708474645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908040054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98928285,0.00006643356,0.00915839,0.0010764868,0.000249975,0.00005322904,0.00003565197,0.0000087301505,0.00006823371],"genre_scores_gemma":[0.9817626,0.00048707277,0.016562514,0.0011195841,0.000042715146,0.0000018093799,0.000008512841,0.000012367681,0.0000028154905],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937079,0.0015643383,0.0036726582,0.00031811275,0.00028242037,0.00045457357],"domain_scores_gemma":[0.9927994,0.002018588,0.004149562,0.00042179707,0.00028134653,0.0003292772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050637163,0.0002053957,0.002092928,0.0035185108,0.000024665107,0.000007835057,0.00085999054,0.0004099987,0.000012706239],"category_scores_gemma":[0.0012672872,0.00019745054,0.0003371119,0.002804747,0.0021154569,0.00021147104,0.00018325775,0.0009128384,0.0000010603925],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024966933,0.00027144293,0.45392916,0.000030538413,0.00029538368,0.0006770753,0.0033071511,0.00656684,0.00058974273,0.001635684,0.000091052905,0.53235626],"study_design_scores_gemma":[0.0010765002,0.0024000667,0.9824654,0.00002522607,0.00025005228,0.00073955226,0.0003873865,0.010382658,0.00019034331,0.0012691101,0.0006405468,0.00017315152],"about_ca_topic_score_codex":0.0015580864,"about_ca_topic_score_gemma":0.0037743158,"teacher_disagreement_score":0.5321831,"about_ca_system_score_codex":0.000059767906,"about_ca_system_score_gemma":0.00022811859,"threshold_uncertainty_score":0.80517995},"labels":[],"label_agreement":null},{"id":"W2908173197","doi":"10.1002/mp.13375","title":"An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U‐nets","year":2019,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"FedDev Ontario; Sunnybrook Research Institute","keywords":"Ground truth; Segmentation; Curse of dimensionality; Artificial intelligence; Breast MRI; Breast cancer; Computer science; Pattern recognition (psychology); Digital mammography; Hyperparameter; Image quality; Data set; Breast imaging; Mammography; Medicine; Image (mathematics); Cancer; Internal medicine","score_opus":0.014561310603029018,"score_gpt":0.28275464719064214,"score_spread":0.26819333658761313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908173197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97184,0.0000071002883,0.027306024,0.00039218427,0.00022561611,0.0002097831,0.0000029249195,0.0000065601866,0.000009764499],"genre_scores_gemma":[0.9996294,0.0000017642834,0.00023576402,0.00009113066,0.000034334145,0.000002254433,0.000001544213,0.0000030382732,7.9672486e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99875444,0.0002836149,0.0001571968,0.0001331715,0.0006137384,0.000057841968],"domain_scores_gemma":[0.9988266,0.0005338666,0.00022624478,0.00033259284,0.00004738982,0.000033287215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044123043,0.000059926566,0.00010975849,0.0000109781395,0.000040780957,0.00000640441,0.0002359605,0.00004013265,0.0000067989504],"category_scores_gemma":[0.000059101563,0.000031437135,0.000029454643,0.00017510814,0.00015232386,0.00020565084,0.00010989607,0.00010266879,5.009816e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099246354,0.00008018539,0.12542775,0.00029543485,0.000030010147,2.1511346e-7,0.0018621597,0.0030309893,0.7923376,0.0023163194,0.00017007827,0.07435],"study_design_scores_gemma":[0.0002795987,0.00020679517,0.06547656,0.00023257518,0.000009248463,0.0000019098024,0.000009795094,0.10773703,0.82278645,0.003220518,0.0000012072809,0.000038327933],"about_ca_topic_score_codex":0.00006979769,"about_ca_topic_score_gemma":0.000001047506,"teacher_disagreement_score":0.10470604,"about_ca_system_score_codex":0.000022855014,"about_ca_system_score_gemma":0.00004137454,"threshold_uncertainty_score":0.12819691},"labels":[],"label_agreement":null},{"id":"W2908949428","doi":"10.1067/j.cpsurg.2018.12.006","title":"The history of cancer screening","year":2019,"lang":"en","type":"article","venue":"Current Problems in Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Breast cancer; Pessimism; Medicine; Disease; Cancer; Random forest; Family history; Fuzzy logic; Computer science; Data mining; Artificial intelligence; Statistics; Machine learning; Mathematics; Internal medicine","score_opus":0.05253100685452825,"score_gpt":0.2766126723954117,"score_spread":0.22408166554088346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908949428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21072787,0.3084466,0.34142688,0.0017168847,0.13052687,0.0016617852,0.0000055931846,0.0004674662,0.0050200727],"genre_scores_gemma":[0.9940884,0.0035228995,0.00079230015,0.000053061976,0.00014799146,0.00016364007,0.0000010278453,0.000018351315,0.0012123076],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889094,0.00006957529,0.00032159465,0.00024131579,0.00025143463,0.00022516293],"domain_scores_gemma":[0.9988264,0.00043311735,0.00020608027,0.000448045,0.000059779886,0.000026615699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007967597,0.00008429258,0.00015407742,0.00011902648,0.000027048345,0.000019113351,0.00042479887,0.00003163567,0.000021713957],"category_scores_gemma":[0.00003552276,0.00006648433,0.000073219875,0.0002987551,0.000056780926,0.00030956173,0.00013913175,0.00018421974,0.000013570116],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047198773,0.00002499963,0.16538544,0.00011394172,0.000008665217,3.0235003e-7,0.00042581957,0.0016582347,0.00034229504,0.000784994,0.013509662,0.8177409],"study_design_scores_gemma":[0.00021329016,0.000019707864,0.03545621,0.0007931922,0.000003936988,0.0000018806244,0.000016045557,0.032171957,0.0005819633,0.0016974852,0.92876333,0.00028102723],"about_ca_topic_score_codex":0.00014360661,"about_ca_topic_score_gemma":0.000067619265,"teacher_disagreement_score":0.91525364,"about_ca_system_score_codex":0.0003881549,"about_ca_system_score_gemma":0.0002847011,"threshold_uncertainty_score":0.27111524},"labels":[],"label_agreement":null},{"id":"W2910145701","doi":"10.1080/10408363.2018.1536111","title":"Deep learning for image analysis: Personalizing medicine closer to the point of care","year":2019,"lang":"en","type":"review","venue":"Critical Reviews in Clinical Laboratory Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Brain Tumour Foundation of Canada","keywords":"Transformative learning; Artificial intelligence; Precision medicine; Deep learning; Convolutional neural network; Personalized medicine; Computer science; Data science; Objectivity (philosophy); Machine learning; Psychology; Medicine; Pathology; Bioinformatics","score_opus":0.1953004419729409,"score_gpt":0.5215904743394969,"score_spread":0.32629003236655596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910145701","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.522132e-7,0.8968813,0.09865187,0.0012032711,0.0014179678,0.0015119426,0.000011211583,0.00003010731,0.00029137856],"genre_scores_gemma":[0.00007011914,0.9721839,0.026011996,0.0009110587,0.00045373227,0.00032888024,0.000004318107,0.000017990775,0.000018002585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913784,0.00274324,0.003029184,0.001477243,0.00080295006,0.0005689696],"domain_scores_gemma":[0.9846817,0.012437626,0.00079989526,0.0011525173,0.0006867264,0.00024152179],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017541893,0.00042763154,0.003767514,0.0004889096,0.00027319373,0.00015396201,0.0033182004,0.00029998325,0.000043890253],"category_scores_gemma":[0.032972943,0.00024172933,0.0011969759,0.007030811,0.0013328724,0.00043641077,0.00048811157,0.0010085537,0.000091592534],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002774473,0.000025118248,0.000056597,0.010638092,0.00005387711,0.000002577409,0.00034915752,0.00002705912,1.7454872e-7,0.008731034,0.00041719573,0.97969633],"study_design_scores_gemma":[0.0000830213,0.0006616657,0.000020584059,0.0117726335,0.0010111164,0.0000015525317,0.0002625827,0.0018332052,3.9222456e-7,0.00026986192,0.9837856,0.0002977496],"about_ca_topic_score_codex":0.000009856619,"about_ca_topic_score_gemma":0.00006919586,"teacher_disagreement_score":0.98336846,"about_ca_system_score_codex":0.00017360825,"about_ca_system_score_gemma":0.00072426035,"threshold_uncertainty_score":0.9857436},"labels":[],"label_agreement":null},{"id":"W2910452544","doi":"10.1109/isbi.2019.8759410","title":"Multi-Level Batch Normalization in Deep Networks for Invasive Ductal Carcinoma Cell Discrimination in Histopathology Images","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Histopathology; Breast cancer; Normalization (sociology); Ductal carcinoma; Pattern recognition (psychology); Feature extraction; Convolutional neural network","score_opus":0.021128857876777304,"score_gpt":0.24066431277917624,"score_spread":0.21953545490239895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910452544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26543623,0.00007010826,0.7328576,0.0001535492,0.0006602665,0.00043672769,0.0000011402503,0.00003447788,0.00034988718],"genre_scores_gemma":[0.9337845,0.000015834561,0.06546095,0.00012763955,0.000039303333,0.00009084927,0.000013286441,0.000010931505,0.00045672327],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889046,0.00007638843,0.00025994057,0.00041326165,0.00010329353,0.000256631],"domain_scores_gemma":[0.99940556,0.00011227807,0.00010238641,0.00026368804,0.00008842776,0.000027659325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026034794,0.00011754605,0.00014293633,0.00023229938,0.000034068536,0.000038096383,0.0003166251,0.00010628432,0.000012022141],"category_scores_gemma":[0.00003526431,0.00012201238,0.000032514712,0.00035078393,0.000021906688,0.00073452387,0.00012142894,0.000110507,0.000012550065],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112265814,0.0004377806,0.78582025,0.0002912135,0.000003948158,0.000053422275,0.009997796,0.11067701,0.04338181,0.004751961,0.00056025886,0.043912258],"study_design_scores_gemma":[0.0008525464,0.000092377755,0.394096,0.000008892367,0.0000017277172,0.000008991454,0.00012701844,0.5971606,0.0072884983,0.0002181218,0.000013727113,0.000131561],"about_ca_topic_score_codex":0.00030677288,"about_ca_topic_score_gemma":0.0045873537,"teacher_disagreement_score":0.66834825,"about_ca_system_score_codex":0.00035580582,"about_ca_system_score_gemma":0.00005984809,"threshold_uncertainty_score":0.49755207},"labels":[],"label_agreement":null},{"id":"W2910902387","doi":"10.3390/jimaging5010021","title":"Efficient FPGA Implementation of Automatic Nuclei Detection in Histopathology Images","year":2019,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Field-programmable gate array; Computer science; Pixel; Image processing; Blob detection; Gate array; Artificial intelligence; Software; Computer vision; Field (mathematics); Computer hardware; Embedded system; Pattern recognition (psychology); Edge detection; Image (mathematics)","score_opus":0.00570820510555473,"score_gpt":0.2685417341854779,"score_spread":0.26283352907992313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910902387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7441053,0.00012651285,0.25443143,0.00029228706,0.00085544796,0.00007279955,2.2327988e-7,0.00001391768,0.000102125145],"genre_scores_gemma":[0.9896908,0.000005434178,0.010208481,0.000047138306,0.00003620507,0.0000012030915,4.2976033e-8,0.000005673948,0.000005062063],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989646,0.00008244609,0.00047808042,0.0001118834,0.0002319326,0.00013102072],"domain_scores_gemma":[0.99905574,0.000048856946,0.0005906217,0.00015574231,0.00012461051,0.000024445568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006812353,0.00006492415,0.0001624093,0.00040077238,0.00002213712,0.00002653478,0.00024241887,0.000016785922,0.000024025116],"category_scores_gemma":[0.00002196653,0.000062092346,0.00005871977,0.0002812117,0.000019976036,0.00032504986,0.000055709304,0.00014230316,0.000007341064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009710585,0.000037912083,0.013759751,0.000052583568,0.0000054097522,0.00002472813,0.0014759519,0.0044076024,0.22994223,0.000037659836,0.000046248093,0.7502002],"study_design_scores_gemma":[0.0016230382,0.00032382397,0.35671917,0.000160246,0.000017037237,0.0008055592,0.00092116714,0.2515592,0.3867802,0.00076821406,0.00015331991,0.00016903837],"about_ca_topic_score_codex":0.00004488644,"about_ca_topic_score_gemma":0.000009017852,"teacher_disagreement_score":0.7500312,"about_ca_system_score_codex":0.00032164896,"about_ca_system_score_gemma":0.000070183916,"threshold_uncertainty_score":0.25320524},"labels":[],"label_agreement":null},{"id":"W2912814480","doi":"10.1002/cjp2.127","title":"The use of digital pathology and image analysis in clinical trials","year":2019,"lang":"en","type":"article","venue":"The Journal of Pathology Clinical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Barts and The London School of Medicine and Dentistry; Medical Research Council; Newcastle upon Tyne Hospitals NHS Foundation Trust; Queen's University; Cancer Research UK; Queen's University Belfast; University of Oxford; University of Southampton; Newcastle University; National Cancer Research Institute; Bristol-Myers Squibb; UK Research and Innovation; University of Leeds; National Institute for Health and Care Research","keywords":"Digital pathology; Digital image analysis; Computer science; Medical physics; Clinical trial; Data science; Key (lock); Digital image; Pathology; Medicine; Artificial intelligence; Image processing; Image (mathematics); Computer vision","score_opus":0.517263181926019,"score_gpt":0.5866856574035789,"score_spread":0.06942247547755998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912814480","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704572,0.00046742288,0.022978732,0.0050614085,0.0007033745,0.0002522807,0.0000052740456,0.0000052073774,0.000069089205],"genre_scores_gemma":[0.9934434,0.0040964396,0.0020583342,0.00011728041,0.00016919462,0.000002327656,2.6702526e-7,0.000006017456,0.000106703796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97301555,0.021958716,0.003493275,0.0003393754,0.0007535703,0.0004394879],"domain_scores_gemma":[0.9023555,0.09435867,0.0013350975,0.0010304055,0.00077691965,0.00014341694],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14304964,0.00010220561,0.001037052,0.00042469028,0.00010970092,0.00014038212,0.0015537638,0.00026691158,0.000013521231],"category_scores_gemma":[0.04919907,0.000051279894,0.00048021672,0.0012094526,0.0017568477,0.0004844748,0.0008393769,0.0022625686,0.00002983121],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002726243,0.0005061388,0.572199,0.00001566047,0.0006470263,0.00091764354,0.0006707614,0.0002275954,0.0013047392,0.0015576545,0.002158177,0.41706935],"study_design_scores_gemma":[0.004770603,0.008185878,0.93305486,0.00007304479,0.00034785995,0.0013183771,0.00044015847,0.017926482,0.00024797767,0.028519737,0.0048655774,0.00024945423],"about_ca_topic_score_codex":0.000008266292,"about_ca_topic_score_gemma":0.000034171724,"teacher_disagreement_score":0.4168199,"about_ca_system_score_codex":0.000038616952,"about_ca_system_score_gemma":0.00030155762,"threshold_uncertainty_score":0.9829861},"labels":[],"label_agreement":null},{"id":"W2913027157","doi":"10.1101/538512","title":"SUBSTRA: Supervised Bayesian Patient Stratification","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Benchmark (surveying); Bayesian probability; Machine learning; Computer science; Artificial intelligence; Stratification (seeds); Data mining; Biology; Geography","score_opus":0.013864591703883034,"score_gpt":0.2093865887277793,"score_spread":0.19552199702389625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913027157","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3742716,0.0007483373,0.6139936,0.0007141426,0.0069271578,0.0017422485,0.00008991928,0.0014403308,0.00007270462],"genre_scores_gemma":[0.9667747,0.000092533184,0.032240897,0.00020081605,0.00033182857,0.00026292392,3.398738e-7,0.00009197477,0.0000039573183],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99602,0.00019825144,0.0007133271,0.001705597,0.00074404484,0.0006187716],"domain_scores_gemma":[0.9950935,0.00006708468,0.00058255304,0.0034125817,0.00057967,0.0002645713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004708522,0.0006056537,0.0004982434,0.00033879757,0.00018608262,0.0007024138,0.0017916687,0.0006276103,0.000036593538],"category_scores_gemma":[0.000065755565,0.0006922848,0.00018990862,0.00074353826,0.00007402863,0.0006125403,0.0007506814,0.00091868674,0.00024261129],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006160994,0.00062308635,0.009776388,0.0014456852,0.00043600533,0.00010110937,0.00023780028,0.0054745306,0.9604537,0.018447086,0.0025232467,0.0004197864],"study_design_scores_gemma":[0.0007721718,0.00028175395,0.0952268,0.0005510437,0.00009233471,5.1146266e-8,0.000006898615,0.10261121,0.79304117,0.000060450868,0.004997696,0.0023584052],"about_ca_topic_score_codex":0.00006935324,"about_ca_topic_score_gemma":0.0000043295813,"teacher_disagreement_score":0.59250313,"about_ca_system_score_codex":0.00069199566,"about_ca_system_score_gemma":0.0010017907,"threshold_uncertainty_score":0.99955285},"labels":[],"label_agreement":null},{"id":"W2913478113","doi":"10.1016/j.acra.2018.11.022","title":"RE: A Methodological Issue in Prediction of Cancer Masking in Screening Mammography Using Density and Textural Features - Authors’ Response","year":2019,"lang":"en","type":"letter","venue":"Academic Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Masking (illustration); Mammography; MAMMOGRAPHIC DENSITY; Computer science; Cancer; Medicine; Medical physics; Breast cancer; Internal medicine; Art","score_opus":0.10110749086239845,"score_gpt":0.36576313534366556,"score_spread":0.2646556444812671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913478113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61618453,0.009985825,0.12159561,0.24745248,0.0035810813,0.0009835426,0.000029988381,0.00015714491,0.000029770978],"genre_scores_gemma":[0.48617986,0.0064995065,0.23239286,0.2665184,0.0074856016,0.00023330751,0.000052867108,0.00015664024,0.00048095454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99398214,0.0034864738,0.00068790274,0.0010094726,0.00027068803,0.0005633555],"domain_scores_gemma":[0.9966381,0.0023085927,0.0005302703,0.0004403446,0.00004506129,0.000037617356],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0034711466,0.00032781932,0.0008538801,0.002031681,0.000057406087,0.000018432494,0.0007362473,0.003069523,0.0000065519216],"category_scores_gemma":[0.0005826805,0.00030983565,0.000097923745,0.0014481192,0.0002652777,0.00029006202,0.00035991563,0.005606299,5.796606e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002780048,0.000018413908,0.527404,0.0006055767,0.00030686436,0.00078972126,0.0071506514,0.009927501,0.05071586,0.00014460417,0.3494333,0.050723433],"study_design_scores_gemma":[0.0020113743,0.0005901563,0.8355429,0.0015555018,0.00011994597,0.0016532253,0.00017441023,0.056868892,0.0032531514,0.0037099596,0.09335988,0.001160606],"about_ca_topic_score_codex":0.0013970969,"about_ca_topic_score_gemma":0.000088334964,"teacher_disagreement_score":0.30813888,"about_ca_system_score_codex":0.0002919922,"about_ca_system_score_gemma":0.00010913416,"threshold_uncertainty_score":0.9999354},"labels":[],"label_agreement":null},{"id":"W2913510405","doi":"10.1016/j.media.2019.01.013","title":"Weakly supervised mitosis detection in breast histopathology images using concentric loss","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"National Science Foundation of Sri Lanka; National Natural Science Foundation of China","keywords":"Histopathology; Concentric; Artificial intelligence; Pattern recognition (psychology); Mathematics; Computer vision; Computer science; Medicine; Pathology; Geometry","score_opus":0.006263077141884169,"score_gpt":0.2467378444246055,"score_spread":0.24047476728272132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913510405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43387732,0.00013899141,0.56438345,0.00091301656,0.0003560812,0.00008726415,0.00000243992,0.00008305985,0.00015836617],"genre_scores_gemma":[0.9917947,0.000061027175,0.0075609107,0.00037558266,0.00010533874,0.000011582956,0.0000035501353,0.000011778084,0.00007550117],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974316,0.00031073167,0.00044061075,0.000680641,0.00072002923,0.00041642162],"domain_scores_gemma":[0.99877334,0.0001317588,0.00013654145,0.00064571324,0.00013138885,0.0001812733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069814123,0.00017916187,0.0004551699,0.0006697836,0.00007696652,0.0000917824,0.00072432484,0.00017901354,0.00064585306],"category_scores_gemma":[0.00011785402,0.0001737124,0.0002432212,0.003940582,0.00014715668,0.0006324168,0.00023555296,0.0003456446,0.0001369069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008690777,0.00041021543,0.43224734,0.00010714205,0.0005081025,0.001147412,0.0010048838,0.0011961731,0.2169334,0.00008478644,0.0002629126,0.3460107],"study_design_scores_gemma":[0.0008313375,0.00005618789,0.09784705,0.000027692493,0.0003045065,0.00024641768,0.000051943764,0.88513625,0.014760848,0.0001434862,0.00024518793,0.00034911252],"about_ca_topic_score_codex":0.0011333437,"about_ca_topic_score_gemma":0.00020441707,"teacher_disagreement_score":0.88394004,"about_ca_system_score_codex":0.0004481769,"about_ca_system_score_gemma":0.000119301396,"threshold_uncertainty_score":0.7083786},"labels":[],"label_agreement":null},{"id":"W2918677731","doi":"10.1016/j.trecan.2019.02.002","title":"Rise of the Machines: Advances in Deep Learning for Cancer Diagnosis","year":2019,"lang":"en","type":"review","venue":"Trends in cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":212,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Machine learning; Digital pathology; Software deployment; Image processing; Image (mathematics)","score_opus":0.06572414473466588,"score_gpt":0.4060355071008296,"score_spread":0.3403113623661637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918677731","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000065794156,0.9940466,0.0014494247,0.00012222193,0.003311439,0.000564877,0.000046780966,0.00003672042,0.0004153222],"genre_scores_gemma":[0.00013788366,0.9919739,0.0005371941,0.000032386164,0.00026721822,0.0064376034,0.0000037192704,0.000046305737,0.00056378316],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761367,0.00023845985,0.00071132864,0.0007189128,0.0003161471,0.0004014821],"domain_scores_gemma":[0.99798,0.00047299036,0.0007603211,0.0006967368,0.000055588287,0.00003434513],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034742817,0.00038304247,0.001234272,0.00039551008,0.000058781858,0.000035043362,0.0015122037,0.00023753561,0.00014999342],"category_scores_gemma":[0.000051133487,0.00027049557,0.00042579215,0.0021672954,0.00006945865,0.00038141367,0.0002870979,0.0006533243,0.000003265904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046159553,0.000021958025,0.0021971117,0.0039751166,0.000022662787,5.160152e-7,0.00020696037,0.0037643735,4.195185e-8,0.000062913714,0.0001788369,0.9895649],"study_design_scores_gemma":[0.00031994123,0.00004433491,0.00026674764,0.008711689,0.000095443145,0.0000013392022,0.000005036969,0.0053904895,0.0000056833965,0.00010857999,0.98474395,0.0003067491],"about_ca_topic_score_codex":0.0012794822,"about_ca_topic_score_gemma":0.014368659,"teacher_disagreement_score":0.98925817,"about_ca_system_score_codex":0.0010747919,"about_ca_system_score_gemma":0.00026788056,"threshold_uncertainty_score":0.9999747},"labels":[],"label_agreement":null},{"id":"W2920834488","doi":"10.1016/j.compmedimag.2019.03.003","title":"Special issue on machine learning in medical imaging","year":2019,"lang":"en","type":"editorial","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Encoder; Discriminative model; Ground truth; Deep learning; Similarity (geometry); Computer vision; Encoding (memory); Noise (video); Set (abstract data type); Backpropagation; Artificial neural network; Image (mathematics)","score_opus":0.006347021992782732,"score_gpt":0.2697452148390441,"score_spread":0.26339819284626137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920834488","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036208003,0.0014750785,0.109611325,0.00902867,0.8775748,0.0002798528,0.000011217757,0.0005080526,0.0014748222],"genre_scores_gemma":[0.00031287794,0.0034654057,0.0017505095,0.0025793365,0.9913961,0.000024622828,0.000112510505,0.00009128434,0.00026733635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921349,0.0005426903,0.00087930536,0.0015851718,0.004005183,0.00085274724],"domain_scores_gemma":[0.99548554,0.0024982875,0.00034847547,0.0007944379,0.00018355151,0.00068970956],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002537468,0.0006699969,0.0010214441,0.0008857829,0.00026289237,0.0004715193,0.0021262267,0.00089650945,0.00016254265],"category_scores_gemma":[0.0023154847,0.0006453791,0.00020097675,0.00085390324,0.00045864854,0.00036897926,0.001419949,0.0059940796,0.000064707594],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038156788,0.00004712113,0.00033709273,0.00013097534,0.000021272945,0.00057760166,0.00017499496,0.000008483559,9.2528825e-7,0.0002666444,0.6200646,0.37833214],"study_design_scores_gemma":[0.0015750516,0.00005255663,0.000054859313,0.00095474964,0.000009965241,0.000057886202,0.000004608463,0.38844606,0.0000017727207,0.00038211705,0.6080592,0.00040117025],"about_ca_topic_score_codex":0.00025026465,"about_ca_topic_score_gemma":0.000050985167,"teacher_disagreement_score":0.38843757,"about_ca_system_score_codex":0.0001976949,"about_ca_system_score_gemma":0.0011029672,"threshold_uncertainty_score":0.99959975},"labels":[],"label_agreement":null},{"id":"W2920892325","doi":"10.48550/arxiv.1903.07011","title":"Deep Features for Tissue-Fold Detection in Histopathology Images","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Digital pathology; Computer science; Magnification; Pattern recognition (psychology); Digitization; H&E stain; Classifier (UML); Support vector machine; Feature (linguistics); Feature vector; Pathology; Computer vision; Medicine; Immunohistochemistry","score_opus":0.037475915862535215,"score_gpt":0.19707822738878697,"score_spread":0.15960231152625176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920892325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045861885,0.0002410341,0.94912887,0.0001029547,0.0027383443,0.00065294123,0.0000066449293,0.0002266957,0.0010406282],"genre_scores_gemma":[0.9938101,0.00011813196,0.0034043752,0.00007196924,0.0001215821,0.000008749229,0.000005949239,0.000022989956,0.0024361156],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804264,0.00013113879,0.00017995728,0.0012246021,0.00006838312,0.00035324664],"domain_scores_gemma":[0.99839586,0.00012989379,0.00024838856,0.0010332358,0.00012723928,0.000065370914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002589766,0.00027387397,0.00032956788,0.00048537273,0.00009476353,0.00006950014,0.0011963688,0.00046705434,0.00000812797],"category_scores_gemma":[0.000042513053,0.00034710404,0.00014424189,0.000432993,0.00007025986,0.00036198995,0.00089527096,0.0005858655,0.000044888493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003500923,0.00018732503,0.003988309,0.00062549737,0.00007242668,0.00048681375,0.0009803617,0.89066184,0.0068063345,0.028291835,0.0012617399,0.06628742],"study_design_scores_gemma":[0.002160894,0.00061481213,0.02880526,0.0001670961,0.00012167259,0.000072532705,0.000110010966,0.8206964,0.03035674,0.1081189,0.0072105625,0.0015650929],"about_ca_topic_score_codex":0.00028217208,"about_ca_topic_score_gemma":0.000668215,"teacher_disagreement_score":0.9479483,"about_ca_system_score_codex":0.0008654888,"about_ca_system_score_gemma":0.00011857758,"threshold_uncertainty_score":0.9998981},"labels":[],"label_agreement":null},{"id":"W2921041073","doi":"10.1101/571190","title":"Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Vector Institute; Sunnybrook Health Science Centre","funders":"National Cancer Institute; National Institutes of Health; Nvidia","keywords":"Workflow; Digital pathology; Computer science; Artificial intelligence; Automated method; Deep learning; Artificial neural network; Digital image analysis; Machine learning; Medical physics; Medicine; Computer vision; Database","score_opus":0.018114799899143132,"score_gpt":0.2607471663728931,"score_spread":0.24263236647374994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921041073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6965045,0.00024432715,0.3002661,0.0001814087,0.0010168857,0.0011295107,0.00015405791,0.0004976358,0.0000056026133],"genre_scores_gemma":[0.97096604,0.000041772775,0.028601611,0.000014335317,0.00012694934,0.0001966736,7.2303175e-7,0.000048669386,0.000003245385],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973769,0.00007904795,0.0006726606,0.0010963079,0.00039765608,0.00037738393],"domain_scores_gemma":[0.9975406,0.00013864103,0.0006651283,0.0010602683,0.00048774105,0.00010761977],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008562348,0.00037502474,0.0005358085,0.00037918775,0.00007386458,0.00046558483,0.0008654419,0.00035201808,0.0000016709013],"category_scores_gemma":[0.00012891715,0.00043168155,0.0000989423,0.00043930253,0.00007581207,0.00059392734,0.0007133737,0.00044430405,0.000007147553],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030160547,0.0001584295,0.013960018,0.001318236,0.00006604562,0.00001128424,0.000039367922,0.0023807616,0.9767384,0.005145576,0.00012392909,0.000027786828],"study_design_scores_gemma":[0.0006667765,0.00012230536,0.30387223,0.00043889383,0.00003397555,3.7298825e-8,0.000006403302,0.37752178,0.31638208,0.000058755613,0.0002552346,0.0006415186],"about_ca_topic_score_codex":0.00010690426,"about_ca_topic_score_gemma":0.000003366266,"teacher_disagreement_score":0.66035634,"about_ca_system_score_codex":0.0004236797,"about_ca_system_score_gemma":0.00065176847,"threshold_uncertainty_score":0.9998135},"labels":[],"label_agreement":null},{"id":"W2921108820","doi":"10.1117/12.2512819","title":"Reliability of computer-aided diagnosis tools with multi-center MR datasets: impact of training protocol","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; Ontario Brain Institute; Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Computer science; Protocol (science); Cross-validation; Artificial intelligence; Classifier (UML); Data set; CAD; Computer-aided diagnosis; Reliability (semiconductor); Data mining; Data collection; Set (abstract data type); Pattern recognition (psychology); Machine learning; Medicine; Statistics; Mathematics; Pathology","score_opus":0.026107668268694196,"score_gpt":0.31950672220234855,"score_spread":0.29339905393365434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921108820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1754101,0.000058660862,0.79722196,0.0013488102,0.0014091277,0.023593435,0.00040557896,0.00049521413,0.000057131812],"genre_scores_gemma":[0.7406021,0.00005942901,0.23585801,0.0010854626,0.0005653795,0.02152459,0.00017038951,0.00012440188,0.000010238022],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928449,0.0006321872,0.0017306482,0.0017339548,0.0019875804,0.0010707565],"domain_scores_gemma":[0.99254185,0.0025463568,0.0011064317,0.002587368,0.00053719804,0.00068081764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018623876,0.0007646655,0.0014643786,0.00047494943,0.00014110612,0.00028100747,0.0029936398,0.00025364445,0.00031910907],"category_scores_gemma":[0.00049491826,0.000608828,0.00052869436,0.0011960155,0.00060303474,0.002221081,0.0015278131,0.0008120701,0.00007397561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001929545,0.0037121766,0.4980934,0.000738577,0.00032641052,0.000095180774,0.0014003352,0.00362548,0.00015010698,0.000092286624,0.030348506,0.4612246],"study_design_scores_gemma":[0.0147845205,0.003120409,0.18828532,0.004087225,0.00008264255,0.00019014519,0.00004930957,0.7746182,0.0051543904,0.0001981671,0.007923574,0.0015060733],"about_ca_topic_score_codex":0.0010151054,"about_ca_topic_score_gemma":0.000030929863,"teacher_disagreement_score":0.77099276,"about_ca_system_score_codex":0.0004653622,"about_ca_system_score_gemma":0.00076183473,"threshold_uncertainty_score":0.9996363},"labels":[],"label_agreement":null},{"id":"W2921127880","doi":"10.1117/12.2513063","title":"Use of convolutional neural networks to predict risk of masking by mammographic density","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Sunnybrook Hospital","funders":"","keywords":"Masking (illustration); Convolutional neural network; Computer science; Transfer of learning; Mammography; Artificial intelligence; Pattern recognition (psychology); Breast cancer; Medicine; Cancer; Internal medicine","score_opus":0.008057301152431104,"score_gpt":0.2213516015046537,"score_spread":0.21329430035222258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921127880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31990498,0.0003197824,0.6760562,0.001172573,0.0020573786,0.00031239106,0.000023917584,0.00014412274,0.000008655576],"genre_scores_gemma":[0.97017366,0.00019803183,0.028072314,0.0012044387,0.0002605552,0.000037197857,0.000014097528,0.000026268388,0.000013409052],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621505,0.00035770793,0.00077333796,0.0007926008,0.0013079891,0.0005533296],"domain_scores_gemma":[0.9961972,0.0016874797,0.00046570794,0.00090774335,0.00031131788,0.00043053261],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008993017,0.00029639294,0.0005651427,0.00033498957,0.000102083686,0.000106434694,0.0012505378,0.00015155786,0.00007458252],"category_scores_gemma":[0.0003219731,0.00029381338,0.00024389334,0.00096430926,0.00024959736,0.0007293516,0.0009805044,0.0005223722,0.000020125703],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002579911,0.00019327209,0.799383,0.000045216813,0.000098474724,0.000012941684,0.00009806187,0.019939473,0.00008279979,0.00023518573,0.048637047,0.13124873],"study_design_scores_gemma":[0.000538276,0.00017426292,0.121376015,0.0002584248,0.000035051868,0.000026777447,0.0000031722873,0.87491506,0.0008460803,0.00015211174,0.0014201023,0.00025466288],"about_ca_topic_score_codex":0.0012135345,"about_ca_topic_score_gemma":0.000023839917,"teacher_disagreement_score":0.8549756,"about_ca_system_score_codex":0.00010344988,"about_ca_system_score_gemma":0.000104651976,"threshold_uncertainty_score":0.9999514},"labels":[],"label_agreement":null},{"id":"W2921197949","doi":"10.1001/jamanetworkopen.2019.0442","title":"Comparison of Artificial Intelligence Techniques to Evaluate Performance of a Classifier for Automatic Grading of Prostate Cancer From Digitized Histopathologic Images","year":2019,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Richmond Hospital; Vancouver Coastal Health; Simon Fraser University; BC Cancer Agency; Vancouver General Hospital; University of British Columbia","funders":"","keywords":"McNemar's test; Artificial intelligence; Prostatectomy; Prostate cancer; Classifier (UML); Convolutional neural network; Grading (engineering); Computer science; Medicine; Pattern recognition (psychology); Machine learning; Cancer; Mathematics; Statistics; Internal medicine","score_opus":0.0690392427908858,"score_gpt":0.36951251319744727,"score_spread":0.30047327040656147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921197949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83548486,0.00018498594,0.16110343,0.00031386147,0.00047485007,0.0020200121,0.000024402007,0.000070604656,0.00032297382],"genre_scores_gemma":[0.8643624,0.00003525747,0.13505216,0.000057733752,0.00006730959,0.000336919,0.0000031816862,0.0000124067465,0.00007258725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816555,0.00011921416,0.0007811118,0.00038950882,0.00028720175,0.00025742],"domain_scores_gemma":[0.9981027,0.00028691912,0.00075631693,0.0005543741,0.00025625608,0.00004341145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011198987,0.00015029506,0.0005903223,0.00008976835,0.000056637564,0.000087115615,0.0012863602,0.00007914314,0.000028522429],"category_scores_gemma":[0.000055870176,0.00013502374,0.000073269905,0.00045491374,0.00007649465,0.0005866108,0.0005195056,0.000119961296,0.0000046335713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005251966,0.00009097883,0.034879252,0.0002586607,0.000037689057,4.2903903e-7,0.0019779704,0.014110342,0.020338299,0.00087387796,0.0013634595,0.92554384],"study_design_scores_gemma":[0.000184801,0.0008844024,0.012113467,0.0008880792,0.0000261382,7.614086e-7,0.000070626,0.56915534,0.4084015,0.0077649616,0.00031510065,0.0001948593],"about_ca_topic_score_codex":0.00020146949,"about_ca_topic_score_gemma":0.000026941745,"teacher_disagreement_score":0.925349,"about_ca_system_score_codex":0.00013413999,"about_ca_system_score_gemma":0.00013501497,"threshold_uncertainty_score":0.55061084},"labels":[],"label_agreement":null},{"id":"W2925365986","doi":"10.48550/arxiv.1904.00740","title":"Projectron -- A Shallow and Interpretable Network for Classifying Medical Images","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Radon; MNIST database; Computer science; Equidistant; Encoding (memory); Artificial intelligence; Radon transform; Pattern recognition (psychology); Layer (electronics); Image (mathematics); Artificial neural network; Domain (mathematical analysis); Computer vision; Mathematics","score_opus":0.05754061096976197,"score_gpt":0.20602612493601388,"score_spread":0.14848551396625193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925365986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024451284,0.0002469126,0.97098786,0.00028625334,0.001407497,0.0006534801,0.0000073371707,0.00024561014,0.0017137501],"genre_scores_gemma":[0.9901268,0.00035209997,0.007573505,0.00015698926,0.00025495948,0.000007473794,0.000006184467,0.00002255207,0.0014994529],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979984,0.00009778653,0.00017487154,0.0011592382,0.00012882047,0.00044088135],"domain_scores_gemma":[0.99854356,0.00021982657,0.00020829708,0.00078016106,0.00010339665,0.00014473364],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004876579,0.00026213442,0.00033352184,0.00014001945,0.00014486474,0.00016565261,0.0012854378,0.00039524582,0.000016866577],"category_scores_gemma":[0.000055165627,0.0002935666,0.00014534898,0.00028502403,0.000098579076,0.00042241786,0.0021819903,0.0006348425,0.000013778002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088280847,0.0003187652,0.06260911,0.0034469534,0.0012710078,0.00048126944,0.0018520742,0.58656806,0.00021795566,0.25306314,0.028076923,0.06121192],"study_design_scores_gemma":[0.0004944884,0.00013146766,0.0006472042,0.00031684135,0.000050095845,0.000011135086,0.000026784737,0.96906537,0.000062314546,0.02621356,0.0026181373,0.0003626188],"about_ca_topic_score_codex":0.00009810935,"about_ca_topic_score_gemma":0.0000865406,"teacher_disagreement_score":0.9656755,"about_ca_system_score_codex":0.00030574243,"about_ca_system_score_gemma":0.0004257104,"threshold_uncertainty_score":0.99995166},"labels":[],"label_agreement":null},{"id":"W2927467691","doi":"10.1002/cpe.5252","title":"Deep learning models for diagnosing spleen and stomach diseases in smart Chinese medicine with cloud computing","year":2019,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"AI in cancer detection","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Cloud computing; Computer science; Spleen; Stomach; Deep learning; Modern medicine; Traditional Chinese medicine; Artificial intelligence; Medicine; Pathology; Internal medicine; Intensive care medicine","score_opus":0.019429412356215373,"score_gpt":0.31814882606554995,"score_spread":0.2987194137093346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2927467691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42152235,0.0023580918,0.5751727,0.00038324617,0.00022094912,0.00021165902,2.5163348e-7,0.000039842216,0.000090887166],"genre_scores_gemma":[0.9918812,0.0003528623,0.0074246274,0.00022902706,0.000065236185,0.00003120789,0.0000033960084,0.0000070377273,0.0000054104776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988734,0.00010047024,0.00021481264,0.00046290812,0.00016754578,0.00018085414],"domain_scores_gemma":[0.99812084,0.0014047727,0.00018443736,0.00010062044,0.00010664791,0.00008267381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025076856,0.0001447757,0.00019993617,0.00008840271,0.00022924782,0.00014536017,0.00010732486,0.000035483987,0.0000014113934],"category_scores_gemma":[0.00021417302,0.000120903096,0.000009936682,0.00027798067,0.00011399029,0.0019231215,0.0001023582,0.0001489514,4.9136565e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022379422,0.00009553066,0.12975961,0.0002773359,0.000028155355,0.000015448757,0.089011446,0.054331176,0.00011082988,0.010486149,0.000022968628,0.71563756],"study_design_scores_gemma":[0.0010278933,0.00044836284,0.012608715,0.00014199383,0.0000122386755,0.000062777064,0.003307363,0.98009527,0.000010055477,0.0018193389,0.00028528762,0.00018068371],"about_ca_topic_score_codex":0.000079941325,"about_ca_topic_score_gemma":0.000009156762,"teacher_disagreement_score":0.92576414,"about_ca_system_score_codex":0.000021731432,"about_ca_system_score_gemma":0.000029713134,"threshold_uncertainty_score":0.49302852},"labels":[],"label_agreement":null},{"id":"W2930120357","doi":"10.3390/cancers11040494","title":"Association Analysis of Deep Genomic Features Extracted by Denoising Autoencoders in Breast Cancer","year":2019,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Health Research Council","keywords":"Breast cancer; Artificial intelligence; Proportional hazards model; Data set; Deep learning; Test set; Pattern recognition (psychology); Computer science; Cancer; Computational biology; Medicine; Biology; Internal medicine","score_opus":0.004827881346927863,"score_gpt":0.2344452934275575,"score_spread":0.22961741208062963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930120357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9564219,0.0011463654,0.039499186,0.00081784057,0.0010553653,0.0002294676,0.00006611204,0.00009456884,0.0006692079],"genre_scores_gemma":[0.9984687,0.00015627082,0.0008520983,0.00021400399,0.000032774533,0.000021344402,0.000007633224,0.000009923404,0.00023723976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99874806,0.000060897706,0.0002461662,0.00037011006,0.0003063625,0.0002684074],"domain_scores_gemma":[0.99913764,0.00007495517,0.00032501717,0.00031863688,0.000096575,0.000047172834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022702948,0.0001175072,0.00027392065,0.0003635205,0.000035508245,0.000051886233,0.00039922583,0.000110863824,0.00009235202],"category_scores_gemma":[0.000010999946,0.00012908285,0.0000974401,0.0018377157,0.00001832795,0.00039690785,0.000049048762,0.000170506,0.000005691002],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000370086,0.00001274423,0.35509983,0.000027617602,0.0007676613,0.0000012973621,0.0016893415,0.5727045,0.039830007,0.0000637009,0.002998229,0.026768055],"study_design_scores_gemma":[0.00038346974,0.000018064566,0.6102896,0.0000271108,0.00015692718,0.0000011465645,0.00009619055,0.38579282,0.0024869202,0.000046618436,0.00049262797,0.00020851086],"about_ca_topic_score_codex":0.0069795162,"about_ca_topic_score_gemma":0.004390725,"teacher_disagreement_score":0.25518975,"about_ca_system_score_codex":0.0077441395,"about_ca_system_score_gemma":0.00032876543,"threshold_uncertainty_score":0.9996331},"labels":[],"label_agreement":null},{"id":"W2931227804","doi":"10.1007/978-3-030-32226-7_91","title":"Improved Inference via Deep Input Transfer","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Leverage (statistics); Dice; Boosting (machine learning); Inference; Pattern recognition (psychology); Convolutional neural network; Transfer of learning; Deep learning; Machine learning; Image segmentation; Mathematics","score_opus":0.013743988802244127,"score_gpt":0.257565635406607,"score_spread":0.24382164660436287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931227804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009048298,0.0003299408,0.97820276,0.0009928137,0.010026814,0.00091812987,0.0000035592536,0.000436213,0.00004146509],"genre_scores_gemma":[0.702083,0.0000302384,0.29633248,0.0011107817,0.00036044157,0.00005500512,0.0000025473116,0.000024211064,0.0000013210642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939451,0.00016880482,0.00072342023,0.0028679345,0.0011599011,0.0011348415],"domain_scores_gemma":[0.99543273,0.00056380604,0.00021040394,0.0031650444,0.0003981824,0.00022984874],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012540108,0.00071445084,0.0006963679,0.0009589972,0.00024028773,0.001173651,0.007313195,0.00059644226,0.000015290561],"category_scores_gemma":[0.00015826414,0.0006857417,0.00020249591,0.0025528201,0.00055247825,0.0011121585,0.0045999787,0.0021144159,0.000055171608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075723356,0.000043267864,0.0004628223,0.00009211835,0.000009466781,0.000011402673,0.0014332397,0.38048464,0.0025174571,0.00011205796,0.0000018204807,0.6148241],"study_design_scores_gemma":[0.0003205877,0.00019038633,0.0011936779,0.00019040119,0.0000068250915,0.000029630106,2.2871224e-7,0.94131154,0.027113201,0.028836088,0.000045582907,0.00076185475],"about_ca_topic_score_codex":0.00029906747,"about_ca_topic_score_gemma":0.00034309877,"teacher_disagreement_score":0.69303465,"about_ca_system_score_codex":0.0008554691,"about_ca_system_score_gemma":0.0014035068,"threshold_uncertainty_score":0.9998632},"labels":[],"label_agreement":null},{"id":"W2931795883","doi":"10.4103/jpi.jpi_5_19","title":"National Society for Histotechnology and Digital Pathology Association Online Self-Paced Digital Pathology Certificate of Completion Program","year":2019,"lang":"en","type":"review","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Manitoba Health","funders":"","keywords":"Digital pathology; Certificate; Computer science; Popularity; Association (psychology); Pathology; Multimedia; Medicine; Psychology","score_opus":0.07991333721793673,"score_gpt":0.33676224087752465,"score_spread":0.2568489036595879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931795883","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040562935,0.5615635,0.42282733,0.0010108239,0.004711389,0.0035285286,0.0016306745,0.00043489257,0.00023658553],"genre_scores_gemma":[0.0007830797,0.83040726,0.16772956,0.00016396792,0.00032529503,0.00009812949,0.0003641423,0.000058381476,0.00007018613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995944,0.000120863966,0.0026684033,0.0002797947,0.0005406107,0.00044627843],"domain_scores_gemma":[0.9902305,0.0007766667,0.0071656704,0.00040213708,0.0013449661,0.000080083024],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014000641,0.00042692985,0.0020346076,0.00061304413,0.00010615263,0.00014694486,0.00088718894,0.0013654704,0.0000015333136],"category_scores_gemma":[0.0007452544,0.0003709183,0.0008789967,0.0004500045,0.00023285985,0.001283245,0.00035734422,0.0010321803,0.000011232958],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016325252,0.00033704276,0.00006326904,0.004730296,0.0003879477,0.000028202312,0.0011155984,0.000030023812,0.000006940221,0.0008410808,0.001440351,0.9910029],"study_design_scores_gemma":[0.0019490083,0.0037102206,0.0001024763,0.0015046049,0.00087657437,0.01574275,0.00025892176,0.011519454,0.0000079990305,0.0032450373,0.9603348,0.00074817555],"about_ca_topic_score_codex":1.4523022e-7,"about_ca_topic_score_gemma":5.769566e-7,"teacher_disagreement_score":0.99025476,"about_ca_system_score_codex":0.0010121168,"about_ca_system_score_gemma":0.0007778414,"threshold_uncertainty_score":0.999931},"labels":[],"label_agreement":null},{"id":"W2939203921","doi":"10.1109/ijcnn.2019.8852092","title":"Double Transfer Learning for Breast Cancer Histopathologic Image Classification","year":2019,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transfer of learning; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Computer science; Breast cancer; Classifier (UML); Feature extraction; Magnification; Feature vector; Contextual image classification; Machine learning; Cancer; Image (mathematics); Medicine","score_opus":0.04793985607655581,"score_gpt":0.29817395685202225,"score_spread":0.25023410077546643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939203921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042254627,0.0001690917,0.9831982,0.002861247,0.002984237,0.00097103696,0.000021692105,0.0005672825,0.0050017154],"genre_scores_gemma":[0.9548238,0.00020043166,0.035310116,0.00023215498,0.00039247514,0.0011558164,0.000022752147,0.000041929183,0.007820527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812317,0.000059430065,0.00029682778,0.0009796474,0.00024183595,0.00029909902],"domain_scores_gemma":[0.9987178,0.00005171251,0.00012759307,0.00078310317,0.0002657929,0.00005400156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037385055,0.0002550246,0.00028225395,0.00013677646,0.0001317202,0.00023732656,0.00095649203,0.0003237876,0.00012034574],"category_scores_gemma":[0.0000054321804,0.00023867731,0.00018352823,0.00014446882,0.00004350327,0.00034830446,0.0003063935,0.00061244913,0.00006798483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005899467,0.0002634346,0.0037913024,0.0023030506,0.00016427175,0.000009548036,0.0034536393,0.122288585,0.07267765,0.052602187,0.011447737,0.73040867],"study_design_scores_gemma":[0.0020262701,0.00019078224,0.02871664,0.00021404614,0.00009083905,0.00006163463,0.000075332326,0.9252792,0.010215125,0.005870536,0.025894577,0.0013649871],"about_ca_topic_score_codex":0.00023365815,"about_ca_topic_score_gemma":0.00004481566,"teacher_disagreement_score":0.95059836,"about_ca_system_score_codex":0.00065932155,"about_ca_system_score_gemma":0.00030128576,"threshold_uncertainty_score":0.97329783},"labels":[],"label_agreement":null},{"id":"W2940900531","doi":"10.1038/s41746-019-0106-0","title":"Physician perspectives on integration of artificial intelligence into diagnostic pathology","year":2019,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":305,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Brain Tumour Research; Brain Tumour Foundation of Canada; Conquer Cancer Foundation","keywords":"Workflow; Cohort; Workload; Enthusiasm; Psychology; Health care; Medicine; Medical laboratory; Medical education; Pathology; Family medicine; Computer science; Social psychology","score_opus":0.01716213315268671,"score_gpt":0.27697750791596953,"score_spread":0.2598153747632828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940900531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3368481,0.00016674954,0.64587003,0.0018835218,0.001309603,0.00029723422,0.0000023020038,0.00011348778,0.013508986],"genre_scores_gemma":[0.9985616,0.000021934115,0.0008952439,0.00019947885,0.00024742444,0.00001168365,0.000003297074,0.000008144014,0.000051160565],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988869,0.000029923107,0.00026634327,0.00036774206,0.00030241278,0.00014670451],"domain_scores_gemma":[0.9987557,0.00050876685,0.00013643509,0.00041829856,0.0001350793,0.000045724366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013547328,0.0001267516,0.00021249217,0.00015956114,0.000029202645,0.00003009811,0.00036529705,0.00005272294,0.000020956264],"category_scores_gemma":[0.00065196236,0.00010025305,0.000039781487,0.00042005721,0.00018513853,0.00049047766,0.00007294423,0.00015214559,0.00016418874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026751663,0.000098396195,0.00010856902,0.000015752375,0.00000859732,0.0000070205474,0.008315265,0.00010016551,0.009038318,0.13489424,0.000075308824,0.8473116],"study_design_scores_gemma":[0.0010009824,0.022858677,0.0144679295,0.0020167031,0.000052650248,0.0000800666,0.037573442,0.068836115,0.20906764,0.6405617,0.0021822818,0.0013018115],"about_ca_topic_score_codex":0.000019753548,"about_ca_topic_score_gemma":0.0000062613776,"teacher_disagreement_score":0.8460098,"about_ca_system_score_codex":0.000104764506,"about_ca_system_score_gemma":0.00003221187,"threshold_uncertainty_score":0.40882006},"labels":[],"label_agreement":null},{"id":"W2943148339","doi":"10.5539/cis.v12n2p146","title":"Image Processing &amp; Neural Network Based Breast Cancer Detection","year":2019,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Breast cancer; Artificial neural network; Mammography; Artificial intelligence; Image processing; Pattern recognition (psychology); Wavelet; Transformation (genetics); Cancer; Computer vision; Computer-aided diagnosis; Machine learning; Image (mathematics); Medicine","score_opus":0.009275305412454004,"score_gpt":0.24458755018979977,"score_spread":0.23531224477734577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943148339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054688532,0.000025539535,0.94236225,0.00046740283,0.0014254445,0.00017703953,0.000001558143,0.00018532942,0.00066689483],"genre_scores_gemma":[0.9428546,0.00000818848,0.0553247,0.0016200432,0.00016508436,0.000014756186,0.0000010199457,0.000003168318,0.000008431133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875045,0.000019477044,0.00023593676,0.00026094625,0.00043293159,0.00030027836],"domain_scores_gemma":[0.99909186,0.00002277643,0.00016044361,0.00030176048,0.00032441545,0.00009872176],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00049240177,0.00011407447,0.00009836208,0.0002132026,0.00039177397,0.0010573119,0.00053948216,0.000034925182,0.00001600203],"category_scores_gemma":[0.0000053215745,0.00010229145,0.000024221057,0.0013530309,0.00013887194,0.017311007,0.00023017412,0.000120219716,0.00007519478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009491738,0.000005115535,0.0015461993,0.00004941564,0.0000012941714,1.13489854e-7,0.00047801246,0.023860088,0.0010150688,0.0003024054,0.00020244483,0.97253036],"study_design_scores_gemma":[0.00020560849,0.000031825322,0.05072063,0.000030197552,0.0000013078752,0.0000351661,0.0000047879676,0.94429594,0.0004237061,0.00006648019,0.0040469775,0.0001373439],"about_ca_topic_score_codex":0.000022443503,"about_ca_topic_score_gemma":0.0000042654046,"teacher_disagreement_score":0.97239304,"about_ca_system_score_codex":0.000113680806,"about_ca_system_score_gemma":0.00017794859,"threshold_uncertainty_score":0.9999797},"labels":[],"label_agreement":null},{"id":"W2944052783","doi":"10.1109/tmi.2019.2914656","title":"Adaptive Augmentation of Medical Data Using Independently Conditional Variational Auto-Encoders","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Segmentation; Sørensen–Dice coefficient; Generative model; Pattern recognition (psychology); Image segmentation; Residual; Latent variable; Data modeling; Medical imaging; Artificial neural network; Test data; Machine learning; Generative grammar; Algorithm","score_opus":0.04094005066835326,"score_gpt":0.32495137226292553,"score_spread":0.28401132159457226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944052783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035178442,0.000023536068,0.9916022,0.0024983776,0.0018107359,0.00018818842,0.000052635136,0.000109521476,0.00019698688],"genre_scores_gemma":[0.97761595,0.000018130379,0.021331279,0.0008411429,0.0001122214,0.00001191824,0.00002535265,0.000014617085,0.00002941292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99531573,0.00015984799,0.00045726937,0.00056988734,0.0032532872,0.00024395491],"domain_scores_gemma":[0.9984907,0.00038662172,0.00017485041,0.00058916875,0.00012919027,0.00022946933],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011096344,0.00015325159,0.00019523985,0.0002571441,0.00014928886,0.000055630797,0.0013411855,0.00014637843,0.0016744608],"category_scores_gemma":[0.000047765825,0.0001590507,0.00006656819,0.00043489411,0.00016153128,0.0013762078,0.000027475011,0.00058862736,0.00007046185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031778397,0.0016876474,0.0011111189,0.00021318163,0.00079324254,0.00017382442,0.002436513,0.436767,0.0052567176,0.020812035,0.0022705216,0.5281604],"study_design_scores_gemma":[0.0010787952,0.00004063989,0.00028504754,0.00012363927,0.00002380411,0.000108831744,0.00011672597,0.994848,0.0018278715,0.0013006455,0.00009536434,0.00015060086],"about_ca_topic_score_codex":0.0002493429,"about_ca_topic_score_gemma":0.000029396995,"teacher_disagreement_score":0.9740981,"about_ca_system_score_codex":0.00023672667,"about_ca_system_score_gemma":0.0010438609,"threshold_uncertainty_score":0.99923813},"labels":[],"label_agreement":null},{"id":"W2944714746","doi":"10.1109/isivc.2018.8709214","title":"Breast Cancer Diagnosis using Quality Control Charts and Logistic Regression","year":2018,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Visualization; Dimensionality reduction; Logistic regression; Confusion matrix; Receiver operating characteristic; Principal component analysis; Outlier; Machine learning; Breast cancer; Data mining; Pattern recognition (psychology); Cancer; Medicine","score_opus":0.07999619502835428,"score_gpt":0.36759362515076904,"score_spread":0.2875974301224148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944714746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14289378,0.00023206764,0.85236496,0.0025016193,0.0012082806,0.00016227564,0.000014353334,0.00018569545,0.00043699384],"genre_scores_gemma":[0.9946495,0.0000469568,0.0043308623,0.00054949726,0.00031760827,0.00003993078,1.0141645e-7,0.0000051673283,0.000060342914],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991042,0.00007913173,0.00014553548,0.00032456653,0.0001688599,0.00017769085],"domain_scores_gemma":[0.99932235,0.0001045058,0.000089469955,0.00029628733,0.00011432778,0.000073028816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002458986,0.000093125884,0.00012295188,0.000041604577,0.00017831384,0.000089296635,0.00018791578,0.00004930009,0.00013433732],"category_scores_gemma":[0.000023653882,0.00007073425,0.000020408826,0.00015699792,0.00012359199,0.00034125577,0.000108129854,0.000058048856,0.000011111962],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010815778,0.00009679543,0.21969102,0.00007274835,0.000058766032,0.000009211089,0.000878142,0.000078901125,0.0063226116,0.010703591,0.006084453,0.7558956],"study_design_scores_gemma":[0.0021941955,0.0002527488,0.4864729,0.00035405366,0.000046169112,0.0002092296,0.000053617856,0.47990862,0.020814875,0.0061277244,0.0027579663,0.00080791273],"about_ca_topic_score_codex":0.0017216529,"about_ca_topic_score_gemma":0.0002020144,"teacher_disagreement_score":0.85175574,"about_ca_system_score_codex":0.00010626436,"about_ca_system_score_gemma":0.000043994005,"threshold_uncertainty_score":0.28844592},"labels":[],"label_agreement":null},{"id":"W2945046785","doi":"10.5858/arpa.2018-0463-ra","title":"Needle Biopsy Adequacy in the Era of Precision Medicine and Value-Based Health Care","year":2019,"lang":"en","type":"review","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Medicine; Biopsy; Medical physics; Modalities; Health care; Radiology; Intensive care medicine","score_opus":0.0429941918952295,"score_gpt":0.35722152577895194,"score_spread":0.3142273338837224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945046785","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015733713,0.9859628,0.009996227,0.0018852879,0.00070375984,0.0009700536,0.000047947342,0.000027654933,0.00024889485],"genre_scores_gemma":[0.0014958157,0.9917997,0.0054876897,0.0008617227,0.00021302424,0.000057657853,0.000052086878,0.000028127564,0.0000041890953],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954242,0.0019331855,0.001194445,0.00067302916,0.00046485267,0.00031028403],"domain_scores_gemma":[0.994678,0.0026175047,0.0011881212,0.0013250208,0.000100626494,0.00009073035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015881881,0.0003781415,0.002138712,0.00068469334,0.000062574654,0.0000041093917,0.0012767587,0.00018879827,0.000005550299],"category_scores_gemma":[0.00033799745,0.00022327743,0.000102348575,0.0012154425,0.0012305429,0.000092221104,0.00019643943,0.00082115835,0.0000019635406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018867404,0.000038046714,0.00004749309,0.012621924,0.000023474075,0.000049663846,0.013809921,0.000005743413,0.00006363397,0.0015582769,0.00021044479,0.9715525],"study_design_scores_gemma":[0.0067431154,0.013568418,0.0031289565,0.16480851,0.00088435324,0.0005614784,0.0044990755,0.0007568207,0.000056440327,0.0024099892,0.8014709,0.0011119884],"about_ca_topic_score_codex":0.00011000285,"about_ca_topic_score_gemma":0.00001930951,"teacher_disagreement_score":0.9704405,"about_ca_system_score_codex":0.000069901216,"about_ca_system_score_gemma":0.0011781057,"threshold_uncertainty_score":0.9104989},"labels":[],"label_agreement":null},{"id":"W2945330811","doi":"10.1007/s10552-019-01182-2","title":"Artificial intelligence (AI) and cancer prevention: the potential application of AI in cancer control programming needs to be explored in population laboratories such as COMPASS","year":2019,"lang":"en","type":"article","venue":"Cancer Causes & Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Waterloo","funders":"","keywords":"Big data; Cancer prevention; Population; Cancer; Medicine; Artificial intelligence; Risk analysis (engineering); Data science; Machine learning; Computer science; Data mining; Environmental health","score_opus":0.02223634387860045,"score_gpt":0.31920956118396837,"score_spread":0.2969732173053679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945330811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57679033,0.0023561034,0.40377906,0.012880947,0.001280137,0.0027915519,0.000037427504,0.00007795764,0.0000064570386],"genre_scores_gemma":[0.9947964,0.00014538658,0.00014835478,0.0015178008,0.00025974878,0.0030901486,0.0000036629353,0.000021003485,0.000017483957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781764,0.00018235206,0.0006489369,0.00052952673,0.0004284942,0.00039304016],"domain_scores_gemma":[0.99870425,0.000098254175,0.00030008852,0.00046077717,0.00035269652,0.000083915496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042588546,0.00023607518,0.00043383383,0.00027654733,0.00009693627,0.00016188766,0.0004669369,0.00011833877,0.000025237285],"category_scores_gemma":[0.00003453172,0.0002126368,0.000057131627,0.001504687,0.00008284321,0.000748509,0.00007814025,0.0002954693,0.000003758964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000744045,0.0001367352,0.2655548,0.00013354894,0.000113427806,0.0000030314618,0.0044668913,0.106984146,0.014032671,0.014209022,0.000060758975,0.59356093],"study_design_scores_gemma":[0.004698091,0.0009950681,0.33298376,0.00082811754,0.00026033516,0.000009977309,0.0022727516,0.61008227,0.023876714,0.014034603,0.008415735,0.0015425746],"about_ca_topic_score_codex":0.013398255,"about_ca_topic_score_gemma":0.022752961,"teacher_disagreement_score":0.59201837,"about_ca_system_score_codex":0.000535511,"about_ca_system_score_gemma":0.00038481902,"threshold_uncertainty_score":0.9950793},"labels":[],"label_agreement":null},{"id":"W2946147212","doi":"10.1038/s41585-019-0193-3","title":"A new era: artificial intelligence and machine learning in prostate cancer","year":2019,"lang":"en","type":"review","venue":"Nature Reviews Urology","topic":"AI in cancer detection","field":"Computer Science","cited_by":510,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Workflow; Artificial intelligence; Precision medicine; Computer science; Big data; Medicine; Digital pathology; Robotics; Clinical decision support system; Machine learning; Decision support system; Data science; Pathology; Data mining; Robot; Database","score_opus":0.06821984601436493,"score_gpt":0.3641277639898978,"score_spread":0.2959079179755329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946147212","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1064669e-7,0.9735057,0.02234404,0.000640746,0.0017230277,0.0015914198,0.000004018051,0.00007649403,0.00011444121],"genre_scores_gemma":[0.0000051942648,0.9948056,0.0038883635,0.00040225024,0.00032908877,0.00021745791,0.000009185448,0.00003604056,0.00030684637],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964588,0.0008287992,0.00096507015,0.001106329,0.00018722004,0.00045377616],"domain_scores_gemma":[0.9982391,0.0002679123,0.00072750775,0.00062108494,0.000041476975,0.00010288961],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009664011,0.0005052095,0.0021815612,0.00040406876,0.000058720252,0.00008181145,0.0009062165,0.00087182794,0.00004383724],"category_scores_gemma":[0.00023354881,0.00038974057,0.00024413281,0.001191441,0.000044180604,0.00020298352,0.00043082394,0.00439763,0.00015298292],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000420574,0.000006167633,0.000008627925,0.0042513865,0.000016819686,0.000013091088,0.000060097456,0.000017859607,1.3265324e-7,0.0015719762,0.00020782473,0.9938418],"study_design_scores_gemma":[0.00003498785,0.00012216475,0.0000020810612,0.0025444801,0.00012044642,0.00016406413,3.3408406e-7,0.0009907583,5.8763135e-7,0.00095641974,0.99474096,0.0003227243],"about_ca_topic_score_codex":0.00010891561,"about_ca_topic_score_gemma":0.00039457643,"teacher_disagreement_score":0.9945331,"about_ca_system_score_codex":0.0002101173,"about_ca_system_score_gemma":0.0006095409,"threshold_uncertainty_score":0.99985546},"labels":[],"label_agreement":null},{"id":"W2947130496","doi":"10.1007/978-3-030-27272-2_13","title":"A Compact Representation of Histopathology Images Using Digital Stain Separation and Frequency-Based Encoded Local Projections","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pattern recognition (psychology); Digital pathology; Histogram; Grayscale; Digital image; Representation (politics); Subpixel rendering; Histopathology; Computation","score_opus":0.023925576894095447,"score_gpt":0.296501023215198,"score_spread":0.27257544632110253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947130496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019444394,0.00016628628,0.9952157,0.00020143136,0.0009601913,0.0005398022,0.000019699055,0.00009330758,0.0008591051],"genre_scores_gemma":[0.8035365,0.0000057497623,0.19613153,0.00012535763,0.00010475151,0.000004177153,0.000009620834,0.000021413034,0.000060947645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734557,0.000060830735,0.0005126109,0.0011405153,0.00061740476,0.0003230986],"domain_scores_gemma":[0.9979055,0.00035089313,0.0004917679,0.00085030386,0.00032791105,0.00007361302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040617143,0.00033503602,0.00046341287,0.00091691164,0.00016696558,0.0002936327,0.0007964573,0.00024360066,0.000004691122],"category_scores_gemma":[0.00007606816,0.00033688225,0.000089711866,0.00065740495,0.0010036635,0.0011412932,0.00027428116,0.00043807813,0.0000040404107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005134653,0.00008681985,0.0023806745,0.00022090241,0.000021930568,0.0000681145,0.0017093157,0.56413436,0.015282684,0.0084848385,0.000021183138,0.40753785],"study_design_scores_gemma":[0.00032574305,0.00036688684,0.0004667882,0.0002106546,0.000012800718,0.00012860906,8.8345587e-7,0.9376566,0.011735453,0.048671633,0.00003674301,0.00038721284],"about_ca_topic_score_codex":0.00015457996,"about_ca_topic_score_gemma":0.00008289357,"teacher_disagreement_score":0.801592,"about_ca_system_score_codex":0.000731632,"about_ca_system_score_gemma":0.0011006173,"threshold_uncertainty_score":0.9999083},"labels":[],"label_agreement":null},{"id":"W2947272707","doi":"10.1186/s13104-019-4121-7","title":"BreCaHAD: a dataset for breast cancer histopathological annotation and diagnosis","year":2019,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"AI in cancer detection","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Breast cancer; Histopathology; H&E stain; Cancer; Medicine; Pathology; Histology; Mammography; Artificial intelligence; Computer science; Immunohistochemistry; Internal medicine","score_opus":0.19611778588675116,"score_gpt":0.4389822763232035,"score_spread":0.24286449043645236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947272707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6342739,0.0016293968,0.34361085,0.012410375,0.0011196765,0.0026686033,0.0039370437,0.00021013328,0.00014004296],"genre_scores_gemma":[0.97595155,0.0002497779,0.022278424,0.00017452145,0.0002090893,0.00095311436,0.00006473063,0.000012100162,0.00010671067],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99849665,0.00017759271,0.000121834135,0.00048964535,0.00038502555,0.0003292301],"domain_scores_gemma":[0.9978051,0.0014583471,0.000038402985,0.0004152735,0.0001994074,0.000083477265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011005593,0.00008081042,0.00011130463,0.00014004599,0.00016431532,0.0001663733,0.00042264568,0.000064433145,0.000060832972],"category_scores_gemma":[0.00032674233,0.000069294816,0.000024792758,0.00033340623,0.00009658203,0.00049964973,0.00028622252,0.00016149294,0.00004859791],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025578315,0.00014893769,0.32704163,0.00035440424,0.00001562227,0.000008351885,0.000596162,0.00025532176,0.005698349,0.0056007393,0.043610472,0.61641425],"study_design_scores_gemma":[0.0015119702,0.00085969904,0.83213794,0.00012883257,0.000009208697,0.00008239663,0.00006608147,0.08402421,0.0067492523,0.010952477,0.063005984,0.00047196815],"about_ca_topic_score_codex":0.00040300316,"about_ca_topic_score_gemma":0.00020090176,"teacher_disagreement_score":0.6159423,"about_ca_system_score_codex":0.00014979896,"about_ca_system_score_gemma":0.000121525634,"threshold_uncertainty_score":0.28257608},"labels":[],"label_agreement":null},{"id":"W2947547484","doi":"10.1200/jco.2019.37.15_suppl.9577","title":"Prediction of distant melanoma recurrence from primary tumor digital H&amp;E images using deep learning.","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Medicine; Cohort; Melanoma; Hazard ratio; Proportional hazards model; Artificial intelligence; Deep learning; Convolutional neural network; Internal medicine; Confidence interval; Computer science; Cancer research","score_opus":0.0936605936633298,"score_gpt":0.38124786233482677,"score_spread":0.287587268671497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947547484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73040617,0.00033338423,0.26335868,0.00024807325,0.004434391,0.00008283521,0.000007891728,0.000019438978,0.001109129],"genre_scores_gemma":[0.95534366,0.00012369233,0.043706935,0.00012017926,0.0006428902,7.370887e-7,0.0000020765424,0.000009219031,0.000050635],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996844,0.0003800198,0.0018648345,0.0002747423,0.00045589686,0.00018050043],"domain_scores_gemma":[0.9943476,0.0020007521,0.0028449462,0.00028551614,0.00037472695,0.0001464633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017127941,0.00011552755,0.00079766504,0.00010260667,0.00003856429,0.00004922133,0.0006111141,0.0001770032,0.000041585125],"category_scores_gemma":[0.001396873,0.000094632494,0.00028360842,0.00020488995,0.0001467991,0.0010107914,0.00020946414,0.0008968472,0.000024056531],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010051095,0.0006523666,0.2687859,0.000037904923,0.00019311365,0.0000863799,0.00033550456,0.0013380685,0.004381588,0.00012831933,0.0005307181,0.72252506],"study_design_scores_gemma":[0.0065318523,0.020576334,0.8026262,0.0004779179,0.00019868875,0.0007510833,0.00016477992,0.04868437,0.0015240022,0.010985319,0.1070005,0.0004789557],"about_ca_topic_score_codex":0.000019124644,"about_ca_topic_score_gemma":0.0000046389437,"teacher_disagreement_score":0.7220461,"about_ca_system_score_codex":0.00026858377,"about_ca_system_score_gemma":0.00074671797,"threshold_uncertainty_score":0.38964048},"labels":[],"label_agreement":null},{"id":"W2948363035","doi":"10.1007/978-3-030-33391-1_24","title":"Learning to Segment Skin Lesions from Noisy Annotations","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Robustness (evolution); Segmentation; Annotation; Pixel; Deep learning; Ground truth; Pattern recognition (psychology); Limiting; Noise (video); Deep neural networks; Set (abstract data type); Task (project management); Machine learning; Image (mathematics)","score_opus":0.016512429753644517,"score_gpt":0.27419352120635654,"score_spread":0.257681091452712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948363035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06511858,0.00012540455,0.92435306,0.0025459079,0.0067713577,0.0007107138,0.000010391458,0.00032677443,0.00003781195],"genre_scores_gemma":[0.56281334,0.0000108628055,0.43567806,0.001065123,0.00035393564,0.000051907977,0.0000065674003,0.000016115042,0.0000040791742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99496716,0.0001929768,0.0005355965,0.0023628052,0.0011703214,0.0007711473],"domain_scores_gemma":[0.9964743,0.00068109954,0.00028096026,0.0020469117,0.00027005593,0.0002466373],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00086058135,0.000472449,0.00046552328,0.00095304457,0.0004155858,0.0011284869,0.0044239764,0.00029382334,0.000015104631],"category_scores_gemma":[0.00023315866,0.00047959152,0.00013564577,0.0025800723,0.00018806421,0.0005680969,0.0063302834,0.001602787,0.00017075367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022583433,0.000022793487,0.0005846752,0.000010898963,0.0000052061714,0.0000059244585,0.0033685337,0.6275564,0.00044021587,0.00002782655,0.000023338178,0.36795193],"study_design_scores_gemma":[0.00018690852,0.0001778446,0.010355128,0.0003282839,0.000006427716,0.000007451565,0.0000032008181,0.96626264,0.009006147,0.012675241,0.00038330426,0.0006074149],"about_ca_topic_score_codex":0.0007760644,"about_ca_topic_score_gemma":0.00029922652,"teacher_disagreement_score":0.49769476,"about_ca_system_score_codex":0.0009809699,"about_ca_system_score_gemma":0.0010192195,"threshold_uncertainty_score":0.99990845},"labels":[],"label_agreement":null},{"id":"W2948367142","doi":"10.1109/cybermatics_2018.2018.00172","title":"Visualization and Analysis of Breast Cancer Data","year":2018,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Computer science; Dashboard; Consistency (knowledge bases); Scalability; Data science; Process (computing); Data visualization; Visualization; Breast cancer; Resource (disambiguation); World Wide Web; Data mining; Cancer; Database; Medicine","score_opus":0.035185306732688444,"score_gpt":0.34225354764825583,"score_spread":0.3070682409155674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948367142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019267496,0.000031678544,0.97967607,0.00019940057,0.000114287766,0.00002424575,0.0000205138,0.00003852192,0.00062781316],"genre_scores_gemma":[0.99474883,0.000035095418,0.0049653044,0.00011349647,0.00004869139,0.0000013173076,0.0000052420323,0.0000017539463,0.00008024768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999558,0.000013581302,0.000080284335,0.00019834923,0.00009929812,0.00005050258],"domain_scores_gemma":[0.999349,0.0000120352615,0.00004635254,0.00048673208,0.00008730212,0.00001855268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010511111,0.000030530384,0.000066881235,0.000119201344,0.000029418003,0.000025757507,0.0003250597,0.000015670952,0.0001066006],"category_scores_gemma":[0.000004297446,0.000026175057,0.0000083709365,0.0010140957,0.000040437913,0.00039684217,0.00025174086,0.000010759597,0.0000018401113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002721486,0.00007859324,0.1737123,0.000036101475,0.0013095373,6.5325537e-7,0.001966679,0.00019931837,0.0064177425,0.077558726,0.008924361,0.72976875],"study_design_scores_gemma":[0.000042454114,0.000015087304,0.13022844,0.0000026460448,0.00007208845,0.0000011525887,0.0000069167468,0.8672559,0.001677553,0.000103962804,0.00055561546,0.00003814511],"about_ca_topic_score_codex":0.00060984364,"about_ca_topic_score_gemma":0.0007510118,"teacher_disagreement_score":0.97548133,"about_ca_system_score_codex":0.0000143655125,"about_ca_system_score_gemma":0.000020588814,"threshold_uncertainty_score":0.11672018},"labels":[],"label_agreement":null},{"id":"W2949003314","doi":"10.1155/2019/3041250","title":"Direct Cellularity Estimation on Breast Cancer Histopathology Images Using Transfer Learning","year":2019,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Science and Technology Planning Project of Guangdong Province; National Cancer Institute; National Institutes of Health; Natural Science Foundation of Guangdong Province; Canadian Cancer Society; Sunnybrook Research Institute; SPIE; Guangzhou Science and Technology Program key projects; American Association of Physicists in Medicine","keywords":"Artificial intelligence; Intraclass correlation; Breast cancer; Histopathology; Support vector machine; Pattern recognition (psychology); Segmentation; Correlation; H&E stain; Medicine; Gradient boosting; Mathematics; Cancer; Computer science; Statistics; Pathology; Reproducibility; Random forest; Internal medicine","score_opus":0.04572080182304022,"score_gpt":0.39508650607256734,"score_spread":0.3493657042495271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949003314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034385376,0.00016058527,0.96256185,0.0013764069,0.00029640706,0.00017042257,0.0000011108932,0.00005999727,0.0009878421],"genre_scores_gemma":[0.26791912,0.000011948649,0.7316763,0.00025161,0.000053541084,0.000014191486,0.0000012957724,0.00000829818,0.0000637015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985896,0.0003817722,0.00029715354,0.00033421596,0.00024331307,0.00015396274],"domain_scores_gemma":[0.9985242,0.0011718125,0.000054644788,0.0001282569,0.0000632921,0.00005778614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012579599,0.00012785304,0.00031451107,0.00016011701,0.00006677653,0.000017587157,0.00013990517,0.000064711676,0.00010277952],"category_scores_gemma":[0.00014983803,0.00010181251,0.000025505968,0.00025190733,0.00011523762,0.00015236827,0.000048698108,0.00024343896,0.00000763816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007442072,0.00018004148,0.0017093262,0.0006535245,0.000025187015,0.000024902834,0.0029326188,0.31005377,0.022674942,0.17794761,0.000050116403,0.48367354],"study_design_scores_gemma":[0.00041891198,0.000101221405,0.006521813,0.00022955865,0.000011209276,0.00008860087,0.000018932747,0.83662915,0.00055042986,0.15528582,0.000039737242,0.000104636725],"about_ca_topic_score_codex":0.000020867332,"about_ca_topic_score_gemma":4.3701883e-7,"teacher_disagreement_score":0.5265754,"about_ca_system_score_codex":0.00011073529,"about_ca_system_score_gemma":0.00003566262,"threshold_uncertainty_score":0.41517937},"labels":[],"label_agreement":null},{"id":"W2949096937","doi":"10.2196/12660","title":"Computer-Aided Detection for Breast Cancer Screening in Clinical Settings: Scoping Review","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Breast cancer; CAD; Medicine; MEDLINE; Medical physics; Breast cancer screening; Cancer; Mammography; Internal medicine","score_opus":0.03051195587498435,"score_gpt":0.37524238750403477,"score_spread":0.3447304316290504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949096937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010206963,0.0006016209,0.9828934,0.0021209694,0.0016833107,0.002108637,0.0000055306864,0.00021580003,0.0001637631],"genre_scores_gemma":[0.3273197,0.013499608,0.5577168,0.0936581,0.004261916,0.0032379117,0.00003383577,0.00013616841,0.00013599358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719954,0.000086427906,0.0014264128,0.00023116136,0.00068503106,0.00037142768],"domain_scores_gemma":[0.9983466,0.0004121004,0.00047031263,0.0004355699,0.00013671252,0.0001987043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021521628,0.00016353991,0.00044553928,0.000121354475,0.00006933438,0.00008158059,0.00068973645,0.00021263014,0.00006894153],"category_scores_gemma":[0.00012089307,0.00014763029,0.0001348844,0.00052452955,0.0000517353,0.0009765535,0.00028475575,0.0004990649,0.000051662366],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000133585945,0.000026440603,0.0008319502,0.0055350587,0.000013586154,0.0000010923005,0.0003154404,0.00008697377,0.0000020460798,0.00008016547,0.0009405707,0.99215335],"study_design_scores_gemma":[0.0014303845,0.00019156361,0.003811814,0.058088113,0.000009703989,0.00007837802,0.00005237333,0.9341876,0.00006560364,0.0000849349,0.0017059005,0.00029364263],"about_ca_topic_score_codex":0.000015849924,"about_ca_topic_score_gemma":0.00004216641,"teacher_disagreement_score":0.9918597,"about_ca_system_score_codex":0.00010725971,"about_ca_system_score_gemma":0.00030498081,"threshold_uncertainty_score":0.60201883},"labels":[],"label_agreement":null},{"id":"W2951024126","doi":"10.1007/s10278-019-00244-w","title":"Deep-Learning-Based Semantic Labeling for 2D Mammography and Comparison of Complexity for Machine Learning Tasks","year":2019,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Mammography; Artificial intelligence; Convolutional neural network; Computer science; Digital mammography; Laterality; Triage; Pattern recognition (psychology); Receiver operating characteristic; Machine learning; Workflow; Deep learning; Radiology; Medicine; Breast cancer; Database","score_opus":0.023449750539718636,"score_gpt":0.28848795190532794,"score_spread":0.2650382013656093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951024126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16918738,0.0009234845,0.82897085,0.00036095528,0.00027455154,0.00019347391,0.0000035071425,0.00003136871,0.000054439122],"genre_scores_gemma":[0.9491107,0.0000052447986,0.050750405,0.00004200879,0.00005562955,0.0000025457998,0.000003141975,0.00001672008,0.000013630507],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987888,0.000032585285,0.00050499354,0.00019242048,0.00025637337,0.00022486514],"domain_scores_gemma":[0.9982485,0.000435558,0.0007787612,0.00012531753,0.00033749838,0.00007435999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004666561,0.00013261074,0.0003606503,0.0002733071,0.000120445664,0.000299081,0.00029627196,0.000027589573,0.0000017615582],"category_scores_gemma":[0.00015750335,0.00012511601,0.0001853823,0.00021970196,0.00006400458,0.0010061028,0.00007548573,0.00028020798,6.874742e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002546137,0.00015703496,0.7529847,0.0005751828,0.00012689916,0.0000034576683,0.0008749245,0.052389793,0.0045899306,0.00048377013,0.00007558138,0.1874841],"study_design_scores_gemma":[0.0014072085,0.00060539943,0.0023512319,0.00016192827,0.00003003192,0.000037430847,0.00013456482,0.9887978,0.0026712627,0.002048631,0.0016055186,0.00014902718],"about_ca_topic_score_codex":0.000005098869,"about_ca_topic_score_gemma":0.0000026696293,"teacher_disagreement_score":0.936408,"about_ca_system_score_codex":0.000042683558,"about_ca_system_score_gemma":0.00004026627,"threshold_uncertainty_score":0.5102083},"labels":[],"label_agreement":null},{"id":"W2954679106","doi":"10.59275/j.melba.2021-gfgg","title":"PathologyGAN: Learning deep representations of cancer tissue","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; University of Glasgow","keywords":"Artificial intelligence; Cancer; Computer science; Breast cancer; Colorectal cancer; Deep learning; Feature (linguistics); Feature vector; Pattern recognition (psychology); Stromal cell; Machine learning; Medicine; Pathology; Internal medicine","score_opus":0.014307464974859305,"score_gpt":0.33815447274286375,"score_spread":0.32384700776800446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954679106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01843929,0.010146979,0.9594012,0.009404274,0.0022814337,0.00018975484,0.000003684572,0.000059445014,0.00007393053],"genre_scores_gemma":[0.9401147,0.0015942479,0.0569635,0.0001874375,0.0008472603,0.000021811627,0.000019859006,0.000046652032,0.00020453805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689347,0.00079756544,0.00094264414,0.0003279496,0.00071170676,0.00032665202],"domain_scores_gemma":[0.99596876,0.0009067448,0.0019384314,0.0004371221,0.0006180759,0.00013084467],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028175975,0.00023775424,0.0005568969,0.00035473472,0.0003062861,0.0001301567,0.0014472598,0.00014743724,0.00005619454],"category_scores_gemma":[0.0013442031,0.0001786095,0.0002699672,0.00044470982,0.00030091056,0.0002480181,0.0011768751,0.002745102,0.0000011562862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012445837,0.00012943713,0.00710723,0.00047408105,0.00041515706,0.00011304101,0.008751136,0.18050405,0.020693123,0.00013939488,0.00051067263,0.7810382],"study_design_scores_gemma":[0.0012362858,0.00047998814,0.002895739,0.0010731502,0.00043578472,0.00096584857,0.0008754188,0.963227,0.0070314365,0.0026930762,0.018659458,0.0004268228],"about_ca_topic_score_codex":0.0004405843,"about_ca_topic_score_gemma":0.000022977449,"teacher_disagreement_score":0.9216754,"about_ca_system_score_codex":0.0001618547,"about_ca_system_score_gemma":0.0003977673,"threshold_uncertainty_score":0.9995556},"labels":[],"label_agreement":null},{"id":"W2955570969","doi":"10.1007/978-3-030-23937-4_8","title":"Automated Segmentation of DCIS in Whole Slide Images","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Pipeline (software); Artificial neural network; Pattern recognition (psychology); Test set; Net (polyhedron)","score_opus":0.011426354768060486,"score_gpt":0.2552363559027142,"score_spread":0.24381000113465373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955570969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006206244,0.0002549599,0.99457026,0.00046828267,0.0019427557,0.00047733236,0.000007668947,0.00026203337,0.0013960692],"genre_scores_gemma":[0.37237912,0.00004859523,0.62584853,0.00070379087,0.00024180187,0.000017160963,0.000009968237,0.000053939882,0.00069707556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967721,0.00004562721,0.0006238146,0.0011979176,0.0009123499,0.00044816837],"domain_scores_gemma":[0.9978246,0.00032631223,0.0004450881,0.0011271707,0.00020854181,0.00006825565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007572344,0.00037518222,0.0004956714,0.0011994567,0.00007077214,0.00020995185,0.002138826,0.00026985168,0.000014577917],"category_scores_gemma":[0.000050509316,0.0003744027,0.000091238406,0.0009404325,0.00035860253,0.00089026697,0.00079668965,0.00053794816,0.00005613379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001216008,0.000036694306,0.00059774116,0.000135884,0.000011956862,0.000039971852,0.0011992378,0.14468724,0.007291519,0.0015995756,0.000118637174,0.8442694],"study_design_scores_gemma":[0.00046319017,0.00026005303,0.0016683268,0.00060468254,0.0000058163023,0.00003274736,3.8520363e-7,0.93297046,0.037455242,0.02560059,0.0003932591,0.000545266],"about_ca_topic_score_codex":0.00007998761,"about_ca_topic_score_gemma":0.00012809156,"teacher_disagreement_score":0.84372413,"about_ca_system_score_codex":0.0005091441,"about_ca_system_score_gemma":0.00061428087,"threshold_uncertainty_score":0.9998708},"labels":[],"label_agreement":null},{"id":"W2956998909","doi":"10.1038/s42256-019-0068-6","title":"Intelligent feature engineering and ontological mapping of brain tumour histomorphologies by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Brain Tumour Charity; Princess Margaret Cancer Foundation","keywords":"Interpretability; Artificial intelligence; Deep learning; Transparency (behavior); Transformative learning; Computer science; Salient; Feature (linguistics); Feature engineering; Machine learning; Psychology; Computer security","score_opus":0.006696904013917719,"score_gpt":0.23549843561668682,"score_spread":0.2288015316027691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956998909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05560475,0.013813275,0.92715544,0.0016204511,0.0008505442,0.00024652152,0.0000029743678,0.00028964347,0.0004163939],"genre_scores_gemma":[0.9742304,0.00024380005,0.024761999,0.00027697574,0.00003877066,0.000008523135,0.0000043443424,0.00001494541,0.00042023408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841064,0.00007841276,0.0002916906,0.000578853,0.00032501807,0.0003153661],"domain_scores_gemma":[0.9988348,0.0004511595,0.0001844661,0.0003537975,0.000097500866,0.000078286896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004258596,0.000250055,0.00032013815,0.00017802339,0.00006483917,0.00006424663,0.0008118296,0.0003637634,0.000036788184],"category_scores_gemma":[0.00046677495,0.00021884912,0.000076321376,0.0004905098,0.00006734638,0.00024252583,0.0003953791,0.0016170936,0.000018531759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009888182,0.00013402013,0.017517837,0.00048389393,0.0001271125,0.00007519207,0.0033126522,0.027548946,0.21844265,0.03272341,0.0030445005,0.6964909],"study_design_scores_gemma":[0.0001982489,0.000668143,0.005689246,0.00022105551,0.000012225103,0.00034526817,0.00026532877,0.72405154,0.2225957,0.0014348546,0.04371507,0.0008032911],"about_ca_topic_score_codex":0.000046340163,"about_ca_topic_score_gemma":0.000010834754,"teacher_disagreement_score":0.91862565,"about_ca_system_score_codex":0.0001361176,"about_ca_system_score_gemma":0.000020773141,"threshold_uncertainty_score":0.8924408},"labels":[],"label_agreement":null},{"id":"W2957964466","doi":"","title":"Segmentation of Breast Cancer Ultrasound Images","year":2019,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"McMaster University; Lawson Health Research Institute","keywords":"Breast cancer; Ultrasound; Segmentation; Computer vision; Artificial intelligence; Medicine; Computer science; Medical physics; Cancer; Radiology; Internal medicine","score_opus":0.00794762795977336,"score_gpt":0.21856877682824238,"score_spread":0.21062114886846903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957964466","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019503474,0.00068386336,0.08970894,0.00023229785,0.0066822534,0.0013001395,0.00041202854,0.0004456305,0.8810314],"genre_scores_gemma":[0.08002722,0.00040658607,0.0039475607,0.00005704888,0.0001349419,0.000004642491,0.00012888337,0.000054021144,0.9152391],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99852055,0.0000793389,0.0002178239,0.00056285574,0.00037808096,0.00024134397],"domain_scores_gemma":[0.99873954,0.000063666266,0.00045825166,0.00043783223,0.0002362544,0.00006444792],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006220227,0.00027690482,0.00030810232,0.00025685417,0.00008677803,0.000079849415,0.00090219156,0.00023311468,0.017351624],"category_scores_gemma":[0.0000033593692,0.00032305528,0.00014305026,0.00074319093,0.000036572772,0.0008474011,0.000090558424,0.00024477925,0.00006353523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002570856,0.000083006475,0.0037460627,0.0007180873,0.00028213483,0.000022363061,0.0020790005,0.00062222034,0.041411012,0.001190355,0.0021416852,0.947447],"study_design_scores_gemma":[0.010163361,0.0011105989,0.21292049,0.004008955,0.001664725,0.00018641625,0.029637381,0.0038928338,0.51542556,0.0013624358,0.21311164,0.006515614],"about_ca_topic_score_codex":0.00061781355,"about_ca_topic_score_gemma":0.00048441856,"teacher_disagreement_score":0.9409314,"about_ca_system_score_codex":0.00041595704,"about_ca_system_score_gemma":0.00025058203,"threshold_uncertainty_score":0.99992216},"labels":[],"label_agreement":null},{"id":"W2963442459","doi":"10.1109/mipr.2019.00023","title":"Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond","year":2019,"lang":"en","type":"preprint","venue":"2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Transfer of learning; Artificial intelligence; Machine learning; Segmentation; Rendering (computer graphics); Volume rendering; Online machine learning; Image segmentation; Class (philosophy); Semi-supervised learning","score_opus":0.013272485835065125,"score_gpt":0.26085725343755495,"score_spread":0.24758476760248982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963442459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09737776,0.0013500925,0.86350816,0.0032829451,0.008439673,0.0026353085,0.00014225273,0.0020132235,0.021250572],"genre_scores_gemma":[0.99240106,0.0024166703,0.002450067,0.00038447083,0.00023716738,0.000041732914,0.000295032,0.00004615959,0.0017276274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606496,0.00033176504,0.00090897654,0.00097192347,0.001121965,0.00060040207],"domain_scores_gemma":[0.9974212,0.00039967988,0.0008091363,0.00041966722,0.00062075246,0.00032958598],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009964113,0.0007310359,0.0007504503,0.0008091779,0.0005546595,0.0014109478,0.00070408767,0.0008683025,0.000046712415],"category_scores_gemma":[0.00054419244,0.0006440037,0.00012309744,0.00043794996,0.00039882117,0.002124386,0.00039193113,0.0049598664,0.00022917624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012489088,0.00020156434,0.001603478,0.0021333478,0.00019058055,0.000012867946,0.023059793,0.019687545,0.002105859,0.000435958,0.0009751722,0.94834495],"study_design_scores_gemma":[0.0018558727,0.0013495887,0.0007933621,0.0014181793,0.000045775643,0.000031356598,0.0005327225,0.9729275,0.0029551578,0.00022425836,0.016982518,0.0008836804],"about_ca_topic_score_codex":0.000055607463,"about_ca_topic_score_gemma":0.000001911505,"teacher_disagreement_score":0.95324,"about_ca_system_score_codex":0.00024096982,"about_ca_system_score_gemma":0.0006152341,"threshold_uncertainty_score":0.9996257},"labels":[],"label_agreement":null},{"id":"W2964004560","doi":"10.1371/journal.pone.0190783","title":"Automatic labeling of molecular biomarkers of immunohistochemistry images using fully convolutional networks","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Occupational Cancer Research Centre; University of British Columbia","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); RGB color model; Deep learning; Biomarker; Immunohistochemistry; Computer vision; Digital pathology; Image (mathematics); Scanner; Imaging biomarker; Pathology; Biology; Medicine; Magnetic resonance imaging; Radiology","score_opus":0.024496113175894077,"score_gpt":0.24459547901280002,"score_spread":0.22009936583690592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964004560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6246442,0.00054600183,0.37439984,0.000031095708,0.000074815005,0.000070206195,0.0000020194113,0.000048914666,0.00018290096],"genre_scores_gemma":[0.77437943,0.000005523094,0.22553797,0.000015667612,0.00004285711,0.0000036036713,9.1001243e-7,0.000006621242,0.000007437594],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905556,0.000031030995,0.00026888496,0.00018471315,0.00031179856,0.00014802213],"domain_scores_gemma":[0.9990378,0.00004357816,0.00023136045,0.00036888412,0.00028858497,0.000029811561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001875593,0.0000821158,0.00016643491,0.000060204595,0.000055170985,0.000013385946,0.00035166641,0.00005852779,0.000028685441],"category_scores_gemma":[0.000051453437,0.0000942624,0.000042854193,0.00031265145,0.0002064841,0.000137125,0.00013302578,0.0000686774,0.0000023530479],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070974434,0.00010103123,0.00016702038,0.000102387065,0.00015395564,9.348221e-7,0.000047315967,0.00020708566,0.9980647,0.00008989488,0.000018095414,0.0010404666],"study_design_scores_gemma":[0.00011550873,0.000047067388,0.00015822143,0.00019744312,0.00002864614,0.0000027654958,0.000004274883,0.41064593,0.58850664,0.00023218516,4.40149e-7,0.0000608918],"about_ca_topic_score_codex":0.00003597564,"about_ca_topic_score_gemma":2.6018307e-7,"teacher_disagreement_score":0.41043884,"about_ca_system_score_codex":0.00010623194,"about_ca_system_score_gemma":0.00009780744,"threshold_uncertainty_score":0.38439092},"labels":[],"label_agreement":null},{"id":"W2964047652","doi":"10.1001/jamanetworkopen.2019.7700","title":"Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer","year":2019,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Tissue microarray; Biomarker; Medicine; Cancer; H&E stain; Immunohistochemistry; Pathology; Oncology; Receiver operating characteristic; Internal medicine; Cohort; Molecular biomarkers; Bioinformatics; Biology","score_opus":0.02484134312206902,"score_gpt":0.28306843585722224,"score_spread":0.2582270927351532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964047652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66478956,0.00011216197,0.32794422,0.0016647709,0.0022200402,0.0019199635,0.00012704571,0.00008427489,0.0011379743],"genre_scores_gemma":[0.93258655,0.000016857699,0.065762624,0.0007962217,0.0005484473,0.00014399673,0.000022463615,0.000028852392,0.00009400433],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977684,0.00011886609,0.00033839446,0.00075322087,0.00042906206,0.0005920723],"domain_scores_gemma":[0.99878013,0.0001001521,0.00015072446,0.0006326038,0.00016144667,0.0001749487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034260974,0.00020969124,0.00027910856,0.000074876625,0.00008695979,0.0007131569,0.0016415468,0.00010268216,0.00025160672],"category_scores_gemma":[0.000006809281,0.0001885963,0.00002122581,0.000974549,0.00002632203,0.0012152632,0.00088469835,0.00029158554,0.00031894076],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045086272,0.00009233448,0.25398338,0.000004221087,0.000031482927,0.0000060340144,0.00054161856,0.031890597,0.00007869537,0.0004621184,0.0014962143,0.7109624],"study_design_scores_gemma":[0.0003916896,0.00033503355,0.9647792,0.00022047937,0.0000067851197,0.0000017276668,0.000041118295,0.02644738,0.0009917358,0.0014583477,0.004869969,0.0004565135],"about_ca_topic_score_codex":0.005554855,"about_ca_topic_score_gemma":0.0019187864,"teacher_disagreement_score":0.7107958,"about_ca_system_score_codex":0.0003107768,"about_ca_system_score_gemma":0.00022076219,"threshold_uncertainty_score":0.8397316},"labels":[],"label_agreement":null},{"id":"W2964469964","doi":"10.1109/cvprw.2019.00115","title":"Siamese CNNs for RGB-LWIR Disparity Estimation.","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; RGB color model; Estimation; Computer graphics (images); Remote sensing; Geology; Engineering","score_opus":0.0098210496776771,"score_gpt":0.24074919703421335,"score_spread":0.23092814735653625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964469964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024183849,0.0003084636,0.96582067,0.0054312563,0.0006248895,0.0015167898,0.000026274576,0.0013613276,0.00072645245],"genre_scores_gemma":[0.5776691,0.000029172785,0.41866836,0.0015362535,0.000113938906,0.0008168902,0.00001168403,0.000042605927,0.0011120185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755305,0.000086104454,0.000447313,0.00073961343,0.0004278947,0.0007460499],"domain_scores_gemma":[0.99748147,0.00024454467,0.0002645087,0.0015853569,0.00017397823,0.00025013712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071409426,0.00032243255,0.0003496802,0.00033624328,0.00025869254,0.00037243965,0.0012962567,0.00026513217,0.000033655666],"category_scores_gemma":[0.00019392584,0.00033533643,0.00021163012,0.0007143099,0.000055652814,0.001209128,0.00036504492,0.0003443803,0.00010736629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022577953,0.00058155175,0.041718673,0.00034275424,0.00015344759,0.000023664888,0.000967135,0.059939537,0.015619038,0.50543636,0.02410676,0.35088527],"study_design_scores_gemma":[0.0005804056,0.00024045659,0.01622867,0.000040577732,0.000014259315,0.00004875058,0.00001752997,0.94128364,0.01259377,0.020583551,0.007936347,0.0004320291],"about_ca_topic_score_codex":0.0018464741,"about_ca_topic_score_gemma":0.0006739766,"teacher_disagreement_score":0.88134414,"about_ca_system_score_codex":0.0007262362,"about_ca_system_score_gemma":0.0002856893,"threshold_uncertainty_score":0.9999099},"labels":[],"label_agreement":null},{"id":"W2966346124","doi":"10.1200/cci.19.00032","title":"Learning Health System for Breast Cancer: Pilot Project Experience","year":2019,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); McMaster University","funders":"","keywords":"Breast cancer; Timeline; Stage (stratigraphy); Medicine; Chart; Medical record; Cancer; Artificial intelligence; Oncology; Internal medicine; Computer science","score_opus":0.09098198724353973,"score_gpt":0.4211197638589951,"score_spread":0.33013777661545535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966346124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15962715,0.0010495418,0.7982595,0.0046749264,0.022884553,0.006651268,0.000317723,0.002198388,0.004336922],"genre_scores_gemma":[0.9694495,0.0008708967,0.025112279,0.0025367963,0.00081458356,0.00072267867,0.0000056471404,0.000031657397,0.0004559406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967831,0.000119961616,0.0015754892,0.00037264693,0.0005365881,0.0006122596],"domain_scores_gemma":[0.9973197,0.00041949027,0.0010765028,0.00069415534,0.00029527326,0.00019487849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013574243,0.00024626963,0.0005658864,0.00011188939,0.0002599796,0.0002216099,0.0010305343,0.00012593775,0.000034248755],"category_scores_gemma":[0.000069873226,0.00021860046,0.00017146967,0.0005490209,0.00007501794,0.0012254679,0.000217603,0.0005131834,0.00007055125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026768536,0.00007732846,0.05713617,0.0022362657,0.00007417112,6.8678094e-7,0.007730392,0.009203758,0.0000066698713,0.0021563775,0.004805961,0.9163045],"study_design_scores_gemma":[0.0033612435,0.0031541346,0.019334108,0.0010449957,0.00002445458,0.000053521348,0.0034838403,0.87399286,0.00014870592,0.000078962024,0.09448147,0.00084170955],"about_ca_topic_score_codex":0.00095591915,"about_ca_topic_score_gemma":0.00015112628,"teacher_disagreement_score":0.91546285,"about_ca_system_score_codex":0.0006809845,"about_ca_system_score_gemma":0.0013383357,"threshold_uncertainty_score":0.8914268},"labels":[],"label_agreement":null},{"id":"W2966871904","doi":"","title":"University of Waterloo Docker Images for OSIRRC at SIGIR 2019.","year":2019,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.050179689870954475,"score_gpt":0.30716641146086665,"score_spread":0.2569867215899122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966871904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92625487,0.000021697015,0.053622127,0.0039908965,0.0011097176,0.0011932468,0.0000660844,0.000079863275,0.013661476],"genre_scores_gemma":[0.9802588,0.000118026765,0.016066428,0.000076571,0.000017635313,0.000007544958,0.00006679326,0.0000039888823,0.0033841643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839807,0.000039511404,0.00029956887,0.00021472937,0.0008030778,0.00024503877],"domain_scores_gemma":[0.9982619,0.0004018965,0.00012356481,0.00024991433,0.0008919132,0.000070796326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007941608,0.00009852243,0.00012345998,0.0005178876,0.000109491266,0.00014589637,0.0008850322,0.00007589978,0.00018830383],"category_scores_gemma":[0.00023679608,0.000096353964,0.000022948423,0.0002371673,0.00007941747,0.0013312042,0.0005885015,0.00017523313,0.00025978417],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01316136,0.0007657258,0.11498085,0.0009747362,0.00045015992,0.000026008636,0.033906706,0.0011368967,0.024802558,0.2906839,0.057871383,0.46123973],"study_design_scores_gemma":[0.011371391,0.0023797285,0.18526053,0.0007160233,0.0000041598014,0.00003176432,0.0023439117,0.0580682,0.28789002,0.03275065,0.41789755,0.0012860555],"about_ca_topic_score_codex":0.000069608286,"about_ca_topic_score_gemma":0.000019066541,"teacher_disagreement_score":0.45995367,"about_ca_system_score_codex":0.00037830285,"about_ca_system_score_gemma":0.00033930474,"threshold_uncertainty_score":0.39292008},"labels":[],"label_agreement":null},{"id":"W2969254250","doi":"10.2196/15799","title":"Correction: Computer-Aided Detection for Breast Cancer Screening in Clinical Settings: Scoping Review","year":2019,"lang":"en","type":"erratum","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Breast cancer; Medical physics; Medicine; Computer science; Data science; Cancer; Internal medicine","score_opus":0.03176949105467257,"score_gpt":0.37180701494589186,"score_spread":0.3400375238912193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969254250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009703901,0.0035498443,0.876167,0.0019282724,0.113141805,0.0034337111,0.000029956349,0.0003902527,0.0013494685],"genre_scores_gemma":[0.0010806508,0.29709074,0.33304843,0.19211146,0.111550674,0.018228034,0.001393102,0.0010080739,0.04448882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939441,0.00021223021,0.0030687815,0.000558283,0.0015378556,0.00067873317],"domain_scores_gemma":[0.99575377,0.0007914622,0.0017715929,0.0009306755,0.00041059148,0.00034191145],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0030770614,0.00049884984,0.0013169318,0.00035355348,0.00017554792,0.00022243377,0.0015249157,0.0013495797,0.00009674309],"category_scores_gemma":[0.00042944774,0.0004763722,0.0004062473,0.0009820625,0.00012421502,0.0011405813,0.00062744995,0.0030290533,0.00006341243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011741694,0.000024585457,0.000021469388,0.011933539,0.000030267911,0.0000022272388,0.00016032306,0.000036677575,3.5347863e-8,0.000005711919,0.44894466,0.5388288],"study_design_scores_gemma":[0.0008844084,0.00022299563,0.00036348667,0.21847399,0.000039275732,0.00019419842,0.00003644521,0.6943559,0.0000037099223,0.000020289277,0.08485566,0.00054962904],"about_ca_topic_score_codex":0.000045849934,"about_ca_topic_score_gemma":0.00021792248,"teacher_disagreement_score":0.69431925,"about_ca_system_score_codex":0.0004240783,"about_ca_system_score_gemma":0.0019476261,"threshold_uncertainty_score":0.9999469},"labels":[],"label_agreement":null},{"id":"W2971002574","doi":"10.18632/oncotarget.26996","title":"<i>A priori</i> prediction of breast tumour response to chemotherapy using quantitative ultrasound imaging and artificial neural networks","year":2019,"lang":"en","type":"article","venue":"Oncotarget","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Medicine; Artificial neural network; Ultrasound; Chemotherapy; Oncology; Radiology; Internal medicine; Machine learning; Computer science","score_opus":0.013289244178779374,"score_gpt":0.2615212130659725,"score_spread":0.2482319688871931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971002574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71597826,0.00006813555,0.28240162,0.00046002163,0.0007918883,0.0002009502,0.000010400482,0.000056993205,0.000031713775],"genre_scores_gemma":[0.9768693,0.000005826775,0.022668716,0.00027049694,0.00014224512,0.0000041487415,0.0000013179362,0.000015930538,0.000022040755],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880075,0.00013421905,0.00024238572,0.00036706025,0.00022844513,0.00022713795],"domain_scores_gemma":[0.99924517,0.00016169572,0.00013945572,0.00027320627,0.00010430619,0.00007619204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050972035,0.00013000685,0.00017573082,0.00011131646,0.000082846585,0.00008692405,0.000210993,0.00004155439,0.0000095183705],"category_scores_gemma":[0.000029764236,0.00013454276,0.000039183848,0.00040733567,0.00004378271,0.00052053446,0.00006924344,0.0001289333,0.00000482247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012593698,0.000053897398,0.05543923,0.000018192464,0.000022923445,0.000004284823,0.0022030924,0.025325656,0.90486073,0.00033862982,0.00031423787,0.0101597635],"study_design_scores_gemma":[0.0003649509,0.00026045213,0.17293203,0.000040720697,0.000006404771,0.00010820389,0.00012746645,0.8188308,0.006596195,0.00026391158,0.00031222697,0.0001566652],"about_ca_topic_score_codex":0.00012909653,"about_ca_topic_score_gemma":0.000008142111,"teacher_disagreement_score":0.8982645,"about_ca_system_score_codex":0.00012418823,"about_ca_system_score_gemma":0.000063496824,"threshold_uncertainty_score":0.5486495},"labels":[],"label_agreement":null},{"id":"W2972137171","doi":"10.1007/978-3-030-33391-1_3","title":"Multi-layer Domain Adaptation for Deep Convolutional Networks","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Domain adaptation; Domain (mathematical analysis); Generalization; Convolutional neural network; Artificial intelligence; Variance (accounting); Adaptation (eye); Layer (electronics); Sample (material); Deep learning; Test data; Machine learning; Class (philosophy); Pattern recognition (psychology); Data mining; Mathematics","score_opus":0.031642173008878074,"score_gpt":0.2798066813761105,"score_spread":0.24816450836723242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972137171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013144119,0.000687495,0.98234916,0.0007925802,0.013236955,0.0013773051,0.0000054245834,0.00023276272,0.00000393144],"genre_scores_gemma":[0.46123362,0.000014897893,0.53752923,0.00057975785,0.0005023403,0.0001159313,0.000007678233,0.00001539416,0.0000011223705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956656,0.00012152351,0.00054852664,0.0020234173,0.00080936536,0.00083156803],"domain_scores_gemma":[0.99676013,0.00078061863,0.00040034187,0.001452901,0.00046981772,0.00013616485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012547276,0.00046069844,0.00043890218,0.000563825,0.0003087628,0.0006946292,0.0033625062,0.0004640672,0.0000032541134],"category_scores_gemma":[0.00015525943,0.00046408255,0.00017986026,0.0012337461,0.0003598342,0.0006865055,0.0023480924,0.0009535956,0.000013748466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010041525,0.00003814369,0.00020181997,0.000052760686,0.00000881952,0.0000029789674,0.00083003804,0.8568591,0.0001929287,0.00031627674,0.000008823057,0.14147826],"study_design_scores_gemma":[0.00062135357,0.000114140916,0.0030224386,0.00015856921,0.000005908135,0.000016404416,8.3604783e-7,0.96025455,0.0006687449,0.034531433,0.00009475273,0.00051088113],"about_ca_topic_score_codex":0.000075601536,"about_ca_topic_score_gemma":0.00020530914,"teacher_disagreement_score":0.4599192,"about_ca_system_score_codex":0.00095490983,"about_ca_system_score_gemma":0.0009721098,"threshold_uncertainty_score":0.9997811},"labels":[],"label_agreement":null},{"id":"W2972185346","doi":"10.59275/j.melba.2023-5g54","title":"Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Artificial intelligence; Computer science; Pooling; Deep learning; Pattern recognition (psychology); Pixel; Classifier (UML); Grading (engineering); Computer vision; Machine learning","score_opus":0.03556278911581747,"score_gpt":0.36143888786230915,"score_spread":0.3258760987464917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972185346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040519168,0.0008277859,0.9893259,0.0050792075,0.00044896489,0.00019357282,7.2457175e-7,0.00006091482,0.000011060083],"genre_scores_gemma":[0.8598207,0.00039510464,0.13918327,0.0002541117,0.00018252379,0.000025792498,0.000025458556,0.000037032347,0.000075961056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974545,0.0013318284,0.0005177754,0.0002005908,0.00021376481,0.00028151684],"domain_scores_gemma":[0.99617314,0.0029586256,0.00044162903,0.00013210128,0.00021308905,0.000081435246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010548067,0.00012017946,0.0002507897,0.00047792975,0.00030224316,0.00007075253,0.00044307124,0.00006172396,0.0000032469052],"category_scores_gemma":[0.0037672974,0.00009086243,0.000064735876,0.00085092,0.00015847688,0.00025344646,0.000119967845,0.0005325216,0.0000013876053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021931926,0.000032892505,0.020814808,0.00009302149,0.000033849054,0.0000036882204,0.002104809,0.013029853,0.0158267,0.00018359757,0.00047138764,0.94718605],"study_design_scores_gemma":[0.00084641064,0.00021377981,0.014488664,0.0000424032,0.000019893212,0.000086766995,0.00017429052,0.97169924,0.0001432246,0.0014779029,0.010712665,0.0000947382],"about_ca_topic_score_codex":0.000095936455,"about_ca_topic_score_gemma":0.000015107934,"teacher_disagreement_score":0.9586694,"about_ca_system_score_codex":0.00013132008,"about_ca_system_score_gemma":0.00007395902,"threshold_uncertainty_score":0.4510079},"labels":[],"label_agreement":null},{"id":"W2972222924","doi":"10.3389/fbioe.2019.00226","title":"IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation","year":2019,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"Ryerson University","keywords":"Digital pathology; Computer science; Artificial intelligence; Ground truth; Histogram; Histogram equalization; Pattern recognition (psychology); Proliferation index; Proliferative index; Computer vision; Pathology; Image (mathematics); Medicine; Immunohistochemistry","score_opus":0.005247886707092191,"score_gpt":0.19608934247268253,"score_spread":0.19084145576559033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972222924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15031865,0.0003562395,0.84599257,0.0011931538,0.0013800251,0.0004513238,0.000001364987,0.00029604204,0.000010666026],"genre_scores_gemma":[0.87937963,0.000048308644,0.12036073,0.0000424097,0.00003025337,0.00007569126,0.000004262527,0.0000095521755,0.000049173548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992132,0.000009403246,0.00016123173,0.00032920734,0.00007118778,0.00021573232],"domain_scores_gemma":[0.9996539,0.000013295779,0.000040851744,0.00024205835,0.00002486061,0.0000250613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013035553,0.00011130438,0.00015748675,0.00036440764,0.00003849898,0.000033370266,0.00020998114,0.00031844192,5.21574e-7],"category_scores_gemma":[0.000020051404,0.00011451415,0.000025265597,0.00039327648,0.00003699505,0.00017045705,0.00005627644,0.0001465304,0.0000015629118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019920975,0.0001224228,0.13050465,0.00048171007,0.00011927494,0.000006241042,0.0007276595,0.037068896,0.076336674,0.030850945,0.0029269732,0.7206553],"study_design_scores_gemma":[0.000616625,0.00021069116,0.0031749003,0.000019559238,0.000003364615,0.0000074412737,0.000021610524,0.97470784,0.01048878,0.0007306959,0.009855961,0.00016250418],"about_ca_topic_score_codex":0.000014736483,"about_ca_topic_score_gemma":0.0000067863502,"teacher_disagreement_score":0.937639,"about_ca_system_score_codex":0.00015856528,"about_ca_system_score_gemma":0.000019628606,"threshold_uncertainty_score":0.46697515},"labels":[],"label_agreement":null},{"id":"W2972681325","doi":"","title":"Integration of Genomic and Medical Data into a 3D Atlas of Human Anatomy. Studies in Health Technology and Informatics","year":2008,"lang":"en","type":"article","venue":"Medicine Meets Virtual Reality","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"","keywords":"Atlas (anatomy); Informatics; Health informatics; Data science; Human anatomy; Computer science; Genomic medicine; Medicine; Computational biology; Anatomy; Biology; Engineering; Pathology; Public health","score_opus":0.10323048989923998,"score_gpt":0.40643798243855056,"score_spread":0.30320749253931056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972681325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9395877,0.0025381492,0.05141078,0.0060105203,0.00013011262,0.00020048869,0.000003393262,0.000038547303,0.00008031207],"genre_scores_gemma":[0.99300456,0.0033705465,0.0034521108,0.00012406547,0.00002857977,0.000005122204,0.0000076842825,0.0000033785739,0.000003959749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982812,0.000114493945,0.00083600415,0.00022835832,0.00041114606,0.00012882159],"domain_scores_gemma":[0.9986871,0.00016985822,0.00036770687,0.0006032051,0.00009496415,0.000077150326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016663654,0.00010680822,0.00046202453,0.00040189162,0.000077717035,0.0000023081175,0.0004968387,0.000091487906,0.0000019613335],"category_scores_gemma":[0.00086675264,0.00008264234,0.0000072047646,0.00052005553,0.0012376873,0.0002502785,0.0007253218,0.0002045852,1.9514633e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007399666,0.0001862575,0.016168585,0.0014444584,0.00012587072,0.000027739883,0.111772716,0.000027790356,0.0067851613,0.060724027,0.002670073,0.79999334],"study_design_scores_gemma":[0.014246439,0.018605178,0.32359582,0.0070175296,0.000101507285,0.0010990982,0.05154665,0.501795,0.008248378,0.060221877,0.012190276,0.001332261],"about_ca_topic_score_codex":0.0018137887,"about_ca_topic_score_gemma":0.0019443396,"teacher_disagreement_score":0.79866105,"about_ca_system_score_codex":0.00011281747,"about_ca_system_score_gemma":0.00016791807,"threshold_uncertainty_score":0.45603102},"labels":[],"label_agreement":null},{"id":"W2975180264","doi":"10.1016/j.media.2021.101996","title":"Multi-scale fully convolutional neural networks for histopathology image segmentation: From nuclear aberrations to the global tissue architecture","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Olympus","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Scale (ratio); Histopathology; Image segmentation; Image (mathematics); Computer vision; Architecture; Pathology; Cartography; Medicine; Geography","score_opus":0.00989152442796864,"score_gpt":0.28675368304538734,"score_spread":0.2768621586174187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975180264","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028864706,0.00021199184,0.961089,0.034787863,0.00060407177,0.00017630462,0.00006849968,0.0000948513,0.00008095775],"genre_scores_gemma":[0.16919623,0.00001654714,0.8188562,0.010071841,0.0010234329,0.0001563378,0.00029461892,0.000017979157,0.00036681656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794465,0.00030552116,0.00033051692,0.0006006903,0.00052021677,0.0002983858],"domain_scores_gemma":[0.99858737,0.00023149037,0.00009587428,0.0005849956,0.00027011716,0.00023013203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036795813,0.00015079975,0.00026447332,0.000071247436,0.00036935465,0.0001876396,0.00070867874,0.00011687185,0.0007389437],"category_scores_gemma":[0.00033114673,0.00012453085,0.0002299606,0.0014438144,0.0001445301,0.00020663401,0.00029241497,0.00024190532,0.000046474936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030466318,0.0012393289,0.008394262,0.000049870607,0.0026741163,0.0012439535,0.008800188,0.17333779,0.041427318,0.002333329,0.14052315,0.619672],"study_design_scores_gemma":[0.0003796519,0.000048347847,0.012869955,0.0000038353583,0.0003292808,0.000043566077,0.00009483048,0.975547,0.00019605324,0.00033213492,0.01000017,0.00015513839],"about_ca_topic_score_codex":0.00020810693,"about_ca_topic_score_gemma":0.003605209,"teacher_disagreement_score":0.80220926,"about_ca_system_score_codex":0.00020978539,"about_ca_system_score_gemma":0.000120151184,"threshold_uncertainty_score":0.80909157},"labels":[],"label_agreement":null},{"id":"W2978261321","doi":"10.1038/s41598-019-50568-4","title":"Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Hospital; Vector Institute; Sunnybrook Health Science Centre","funders":"National Cancer Institute; National Institutes of Health; Nvidia","keywords":"Workflow; Digital pathology; Computer science; Artificial intelligence; Automated method; Digital image analysis; Deep learning; Artificial neural network; Machine learning; Medical physics; Pathology; Medicine; Computer vision; Database","score_opus":0.016181895506381744,"score_gpt":0.287415599299021,"score_spread":0.2712337037926392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978261321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91594595,0.000043392378,0.07914078,0.00013737936,0.0035690444,0.00062525005,0.0000041461867,0.00017007682,0.00036395734],"genre_scores_gemma":[0.991822,9.322382e-7,0.0075036413,0.0000031754992,0.00002223954,0.000029830404,0.000019940588,0.000007649,0.0005906159],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799275,0.000025500458,0.0005388113,0.000786152,0.00043429632,0.00022247013],"domain_scores_gemma":[0.99857724,0.00006344134,0.00041754724,0.0006732019,0.00021356645,0.00005498098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015923397,0.00011001592,0.00019034685,0.00024000558,0.00009360365,0.0005146832,0.00025073986,0.00005547353,0.000005289423],"category_scores_gemma":[0.00007738679,0.00010870304,0.000050312145,0.0005048015,0.000090557034,0.000890629,0.00015169769,0.00007907007,0.0000057085513],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017428703,0.00018194648,0.057775475,0.00031912123,0.000017642587,0.00006616087,0.0010678344,0.0026261285,0.917542,0.004967852,0.0020719483,0.013346485],"study_design_scores_gemma":[0.0004585928,0.00016752009,0.09996716,0.00012579354,0.000010474919,0.0001783256,0.00023516495,0.6310433,0.23301955,0.031801853,0.0026106297,0.00038166117],"about_ca_topic_score_codex":0.00005752795,"about_ca_topic_score_gemma":0.000014436514,"teacher_disagreement_score":0.68452245,"about_ca_system_score_codex":0.00010590644,"about_ca_system_score_gemma":0.00019031818,"threshold_uncertainty_score":0.49631017},"labels":[],"label_agreement":null},{"id":"W2978639826","doi":"10.1109/jbhi.2019.2944643","title":"Deep Learning-Based Gleason Grading of Prostate Cancer From Histopathology Images—Role of Multiscale Decision Aggregation and Data Augmentation","year":2019,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Histopathology; Prostate cancer; Grading (engineering); Artificial intelligence; Prostate; Computer science; Medicine; Radiology; Medical physics; Cancer; Pathology; Internal medicine","score_opus":0.02124589333563531,"score_gpt":0.3210817892733692,"score_spread":0.2998358959377339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978639826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5144713,0.0014885508,0.48276627,0.00064252625,0.00048949337,0.00011741766,0.0000151905915,0.0000056458834,0.0000035955998],"genre_scores_gemma":[0.90661234,0.0018724763,0.09127283,0.0001666926,0.000057535697,0.0000012235628,0.000010388163,0.0000039541355,0.0000025643253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984464,0.000054612334,0.0009065613,0.00008480064,0.00038808532,0.00011953563],"domain_scores_gemma":[0.99799484,0.00012879558,0.0014778539,0.00015913238,0.000115854134,0.00012351197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095286313,0.00007070593,0.00025779754,0.00017870782,0.000054978336,0.000019317935,0.00023931406,0.000060921404,0.0000055756436],"category_scores_gemma":[0.00004721794,0.00005659332,0.000018991177,0.00013873634,0.000096181204,0.0006421262,0.00007262168,0.0001921548,6.6340397e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070482754,0.000029371171,0.0072977487,0.000267016,0.0000072729767,6.9003926e-7,0.00275233,0.00055948185,0.0009410721,0.000006791198,0.00014033141,0.98792744],"study_design_scores_gemma":[0.0020205649,0.0012207361,0.030144678,0.0007241738,0.000017496382,0.0000373618,0.00046543952,0.9579898,0.004675317,0.0006939207,0.0019225354,0.00008796738],"about_ca_topic_score_codex":0.00023752307,"about_ca_topic_score_gemma":0.000020423757,"teacher_disagreement_score":0.98783946,"about_ca_system_score_codex":0.00009291753,"about_ca_system_score_gemma":0.00021265508,"threshold_uncertainty_score":0.23078085},"labels":[],"label_agreement":null},{"id":"W2978969543","doi":"10.1109/ijcnn.2019.8851758","title":"Projectron – A Shallow and Interpretable Network for Classifying Medical Images","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Radon; Computer science; MNIST database; Equidistant; Encoding (memory); Artificial intelligence; Radon transform; Pattern recognition (psychology); Layer (electronics); Image (mathematics); Artificial neural network; Medical imaging; Domain (mathematical analysis); Computer vision; Mathematics","score_opus":0.008838301136692836,"score_gpt":0.25433844319757215,"score_spread":0.2455001420608793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978969543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007177267,0.00017835395,0.98134804,0.0016787449,0.0006504941,0.00034175493,3.1182398e-7,0.00017244303,0.008452595],"genre_scores_gemma":[0.8534278,0.00003735265,0.14238049,0.00089561695,0.00023778879,0.000084557505,6.470788e-7,0.000011278573,0.0029244556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991522,0.000020410414,0.00010935568,0.00029581517,0.00018071297,0.00024154443],"domain_scores_gemma":[0.99953955,0.000125126,0.000034094905,0.00021522571,0.000027879187,0.000058100435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036550767,0.000072645824,0.00010340602,0.000029008474,0.00005342923,0.00010565337,0.00030528815,0.000061935476,0.00006057113],"category_scores_gemma":[0.00002798498,0.0000592557,0.0000283685,0.00011767776,0.000020336061,0.00037931555,0.00019336256,0.00009612843,0.000016371974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012989341,0.00006929302,0.03567269,0.00034762316,0.00010846322,0.0000066832263,0.00096680375,0.0003615354,0.0032960682,0.10123809,0.06275605,0.7950468],"study_design_scores_gemma":[0.0006017349,0.0003855043,0.0017699172,0.00009454901,0.000005318092,0.00003727397,0.000030651267,0.9593039,0.0014753258,0.0068481867,0.0292353,0.00021232477],"about_ca_topic_score_codex":0.000021928072,"about_ca_topic_score_gemma":0.000049931932,"teacher_disagreement_score":0.95894235,"about_ca_system_score_codex":0.000042779036,"about_ca_system_score_gemma":0.00007829789,"threshold_uncertainty_score":0.24163774},"labels":[],"label_agreement":null},{"id":"W2979618473","doi":"10.1109/ccece.2019.8861896","title":"Hardware Accelerator for Nuclei Detection in Histopathology Images","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Field-programmable gate array; Blob detection; Hardware acceleration; Image processing; Artificial intelligence; Process (computing); Task (project management); Gaussian process; Computer vision; Computational science; Gaussian; Computer hardware; Image (mathematics); Edge detection","score_opus":0.012824878605746907,"score_gpt":0.2447668272297305,"score_spread":0.2319419486239836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979618473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17821386,0.000037564012,0.8156879,0.0004503243,0.001708171,0.00039968558,0.000001341359,0.0002297818,0.0032713672],"genre_scores_gemma":[0.97666454,0.000003487891,0.021568285,0.00030074333,0.000060239483,0.00007304341,3.992756e-7,0.000009066328,0.0013201884],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992519,0.000026520998,0.00013366231,0.0003295044,0.00007891827,0.00017946537],"domain_scores_gemma":[0.99951667,0.00004414654,0.000045233774,0.00031665317,0.0000522195,0.000025071919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015936156,0.00007569458,0.00010402402,0.000120596436,0.0000379016,0.000034433462,0.00030757638,0.00006560277,0.000050550432],"category_scores_gemma":[0.000017879074,0.00007442406,0.000037811955,0.00019957066,0.000012024766,0.00048041865,0.0000784603,0.00008016623,0.0001331661],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009307992,0.00009244545,0.012173655,0.00010154201,0.0000073658944,0.000010908176,0.0007781455,0.000268442,0.42452326,0.009456801,0.003258181,0.5492362],"study_design_scores_gemma":[0.0022814842,0.0009832104,0.101816885,0.00002610868,0.000005969728,0.000072816394,0.00011063443,0.097329885,0.7065383,0.008066768,0.08211329,0.0006546476],"about_ca_topic_score_codex":0.000035600842,"about_ca_topic_score_gemma":0.0001221884,"teacher_disagreement_score":0.79845065,"about_ca_system_score_codex":0.00019338314,"about_ca_system_score_gemma":0.000029338971,"threshold_uncertainty_score":0.30349252},"labels":[],"label_agreement":null},{"id":"W2979634944","doi":"10.1007/978-3-030-32692-0_3","title":"Globally-Aware Multiple Instance Classifier for Breast Cancer Screening","year":2019,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Computer science; Artificial intelligence; Classifier (UML); Residual neural network; Mammography; Pixel; Pattern recognition (psychology); Artificial neural network; Breast cancer; Contextual image classification; Computer vision; Machine learning; Image (mathematics); Cancer; Medicine","score_opus":0.01585183058171993,"score_gpt":0.26409172332605363,"score_spread":0.2482398927443337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979634944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019332636,0.0001620113,0.9739141,0.0024015335,0.0033057947,0.0006221827,0.000021722451,0.0002164281,0.000023617098],"genre_scores_gemma":[0.68829244,0.000007246728,0.30967197,0.0017187629,0.00024651314,0.000046962028,6.477264e-7,0.000012220343,0.000003268745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967753,0.000044888668,0.0003258625,0.0013059358,0.0007433926,0.00080456183],"domain_scores_gemma":[0.9979964,0.00039003105,0.00016805982,0.0009873327,0.00031839692,0.00013979663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006771925,0.00027905995,0.00028339276,0.00029382526,0.00027604486,0.00048655597,0.0026444395,0.00012720819,0.00001612678],"category_scores_gemma":[0.00005543913,0.000259024,0.00009076151,0.0023334413,0.00022315861,0.0014858516,0.0006896109,0.00030578088,0.000017229588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002664204,0.00002497133,0.02154021,0.000029994513,0.000006053788,0.0000029412784,0.00029975086,0.14575176,0.0017331215,0.0002686077,0.00003407952,0.83028185],"study_design_scores_gemma":[0.0007236145,0.00009328723,0.02787184,0.00015068681,0.0000022684505,0.000037270136,0.0000011358825,0.961357,0.006155666,0.0026750218,0.0005730865,0.00035914942],"about_ca_topic_score_codex":0.00015149667,"about_ca_topic_score_gemma":0.0004214398,"teacher_disagreement_score":0.82992274,"about_ca_system_score_codex":0.0004981892,"about_ca_system_score_gemma":0.00041370408,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W2980381023","doi":"10.1002/path.2957","title":"Breast cancer survival stratified by automated versus visual analysis of ER and PR immunohistochemistry","year":2011,"lang":"en","type":"article","venue":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Immunohistochemistry; Medicine; Breast cancer; Cancer; Tissue microarray; Oncology; Internal medicine; Univariate analysis; Multivariate analysis; Progesterone receptor; Cohort; Gynecology; Pathology; Estrogen receptor","score_opus":0.024256690669922303,"score_gpt":0.28839366975035435,"score_spread":0.26413697908043204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980381023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986791,0.0005373162,0.010421024,0.000112148264,0.0008618994,0.0001204065,0.000060762806,0.00042388204,0.0006715201],"genre_scores_gemma":[0.9970547,0.00011797997,0.0025783703,0.00002828886,0.00007619569,0.000017216184,0.00001543382,0.000026506776,0.00008528293],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977314,0.00014150431,0.0006047917,0.000648614,0.00045779065,0.00041590544],"domain_scores_gemma":[0.9984477,0.00014910316,0.00045757496,0.0005496694,0.0002478693,0.0001480635],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005106375,0.00031087926,0.0004986865,0.0003452865,0.0002499292,0.00012380342,0.000701235,0.00017127526,0.000043483324],"category_scores_gemma":[0.000029808967,0.00030630536,0.00018611943,0.0013954787,0.00016335062,0.0003924705,0.00017838654,0.00034117757,0.0000031453542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011732487,0.00054715853,0.011205478,0.00013938003,0.0059047383,0.000057728495,0.013309925,0.0004714897,0.93591565,0.00096716284,0.001739346,0.028568681],"study_design_scores_gemma":[0.0047357474,0.00083383516,0.06891578,0.00034099168,0.0026875425,0.00016555563,0.0013309255,0.3633033,0.5549596,0.00030479938,0.0002663345,0.0021555691],"about_ca_topic_score_codex":0.0007952633,"about_ca_topic_score_gemma":0.00005499227,"teacher_disagreement_score":0.38095605,"about_ca_system_score_codex":0.00018897047,"about_ca_system_score_gemma":0.00019864229,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W2981953956","doi":"10.3390/app9214492","title":"A Novel Bio-Inspired Method for Early Diagnosis of Breast Cancer through Mammographic Image Analysis","year":2019,"lang":"en","type":"article","venue":"Applied Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Maximization; Computer science; Image segmentation; Artificial intelligence; Breast cancer; Heuristics; Pattern recognition (psychology); Mathematics; Medicine; Cancer; Mathematical optimization","score_opus":0.02151344844375577,"score_gpt":0.3031006696960022,"score_spread":0.28158722125224644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981953956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14200294,0.00007760762,0.8551579,0.000769813,0.00030922747,0.00049235154,0.000053513624,0.00009147136,0.0010451658],"genre_scores_gemma":[0.6767611,0.000024470857,0.32267043,0.00016171702,0.00003452347,0.0003232258,6.560842e-7,0.000005942808,0.000017940834],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.997939,0.000027419306,0.00031177755,0.0008045905,0.0005394018,0.00037781155],"domain_scores_gemma":[0.99866605,0.00031208745,0.00029789703,0.00052886433,0.00013739565,0.000057694204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008312894,0.00016866307,0.00035587876,0.00041402085,0.00020817468,0.00016761421,0.0013346528,0.00007019437,0.000045364588],"category_scores_gemma":[0.000008994411,0.0001421884,0.00022433797,0.0055840192,0.00028695588,0.00070569816,0.00017532754,0.00007601699,0.000009215758],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013417851,0.00050922186,0.2948419,0.00025378953,0.0014186605,0.0000010183117,0.0055158543,0.009679495,0.36604998,0.15589459,0.0006585663,0.16504277],"study_design_scores_gemma":[0.0023927945,0.000696461,0.4445346,0.00009443459,0.00083692116,0.000012656478,0.00062066,0.22894455,0.29381847,0.024936588,0.0016121314,0.0014997136],"about_ca_topic_score_codex":0.0018045926,"about_ca_topic_score_gemma":0.000247229,"teacher_disagreement_score":0.53475815,"about_ca_system_score_codex":0.000048176807,"about_ca_system_score_gemma":0.00012292694,"threshold_uncertainty_score":0.5798275},"labels":[],"label_agreement":null},{"id":"W2982011997","doi":"10.3389/fbioe.2019.00300","title":"Assessing the Impact of Color Normalization in Convolutional Neural Network-Based Nuclei Segmentation Frameworks","year":2019,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto Metropolitan University","funders":"Mitacs","keywords":"Convolutional neural network; Segmentation; Normalization (sociology); Preprocessor; Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology); Image segmentation; Data pre-processing; Digital pathology; Machine learning","score_opus":0.006116925565723242,"score_gpt":0.24380651640577988,"score_spread":0.23768959084005664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982011997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4823295,0.0002232986,0.516537,0.0003098824,0.00044692145,0.0001031722,5.5936783e-7,0.000046005967,0.000003643638],"genre_scores_gemma":[0.94857776,0.000032175543,0.051326413,0.000028174805,0.000017457576,0.000008743529,0.0000026632629,0.0000052981536,0.0000012889611],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999341,0.000031270934,0.00018001626,0.00018149539,0.00007632969,0.00018984983],"domain_scores_gemma":[0.99968016,0.00003810415,0.00007898139,0.00017195311,0.000018030152,0.000012785349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019829185,0.00008906127,0.00013433475,0.00025477837,0.00002819203,0.000035457415,0.0002085443,0.00030185262,0.0000015643861],"category_scores_gemma":[0.000016743994,0.000072413655,0.000026219648,0.00072281796,0.00007039253,0.0002376918,0.000054985,0.0003301449,3.4071357e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009542301,0.000012835574,0.16345829,0.000014931337,0.000009227037,9.5280285e-7,0.00005041338,0.81760603,0.004009831,0.0007002846,0.00008861821,0.014039039],"study_design_scores_gemma":[0.00027130186,0.0000959113,0.08728314,0.000036202193,0.0000014343649,0.0000038825806,0.00003989827,0.9100435,0.0018466309,0.00028891757,0.00001827481,0.00007090739],"about_ca_topic_score_codex":0.00006434539,"about_ca_topic_score_gemma":0.0000048853863,"teacher_disagreement_score":0.46624827,"about_ca_system_score_codex":0.00017446149,"about_ca_system_score_gemma":0.00003391061,"threshold_uncertainty_score":0.2952943},"labels":[],"label_agreement":null},{"id":"W2982036840","doi":"10.3390/cancers11101615","title":"Size and Shape Filtering of Malignant Cell Clusters within Breast Tumors Identifies Scattered Individual Epithelial Cells as the Most Valuable Histomorphological Clue in the Prognosis of Distant Metastasis Risk","year":2019,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja","keywords":"Breast cancer; Stroma; Cytokeratin; Metastasis; Medicine; Receiver operating characteristic; Pathology; Oncology; Internal medicine; Cancer; Immunohistochemistry","score_opus":0.015364683523284937,"score_gpt":0.22662079044602526,"score_spread":0.21125610692274033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982036840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99700814,0.0002055321,0.0010184682,0.00028338295,0.0005594996,0.0006235624,0.00016056669,0.000020417046,0.00012044589],"genre_scores_gemma":[0.9985066,0.00007145579,0.0010858519,0.00018073691,0.000023409497,0.00007274698,0.0000015982575,0.000012013704,0.000045601322],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979348,0.00035034903,0.00046948498,0.00045312117,0.00051219045,0.0002800344],"domain_scores_gemma":[0.9984484,0.00038915762,0.000519218,0.00052997173,0.00006728289,0.00004599242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013030004,0.00018910452,0.00031012818,0.000079475256,0.00011465986,0.00010163174,0.0010760045,0.000059657646,0.00005367943],"category_scores_gemma":[0.000035771445,0.00011744543,0.00008061337,0.0005163293,0.00034401575,0.0002599114,0.000339439,0.00023677063,0.0000049414402],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014452449,0.00038906815,0.040430423,0.0015397631,0.0005312144,0.00012110746,0.12587996,0.09660555,0.68858945,0.0007504834,0.0036613385,0.040056422],"study_design_scores_gemma":[0.00325728,0.0014900685,0.076921724,0.00072506594,0.00032339102,0.00025073814,0.014955273,0.07026597,0.8287822,0.0016334645,0.00042509436,0.0009697017],"about_ca_topic_score_codex":0.0024221349,"about_ca_topic_score_gemma":0.00017027308,"teacher_disagreement_score":0.14019279,"about_ca_system_score_codex":0.00030513646,"about_ca_system_score_gemma":0.00024895315,"threshold_uncertainty_score":0.47892857},"labels":[],"label_agreement":null},{"id":"W2985641961","doi":"10.3390/cancers11111700","title":"Segmentation and Grade Prediction of Colon Cancer Digital Pathology Images Across Multiple Institutions","year":2019,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Digital pathology; Segmentation; Colorectal cancer; Digital image analysis; Cancer; Pathology; Medicine; Computer science; Artificial intelligence; Internal medicine; Computer vision","score_opus":0.023588891500079354,"score_gpt":0.2938673322260061,"score_spread":0.2702784407259267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985641961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9082003,0.0003653319,0.08916439,0.00012206871,0.0013998828,0.0002658484,0.00019442516,0.0000811941,0.00020651768],"genre_scores_gemma":[0.99819136,0.00023107829,0.0012995454,0.000058610807,0.00004893963,0.00007153714,0.00000858177,0.0000054681373,0.00008487486],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992913,0.000017251086,0.00014697251,0.00026614664,0.00012419825,0.00015413997],"domain_scores_gemma":[0.9995614,0.000035463385,0.00010987161,0.00019200407,0.00006214087,0.00003910554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006570996,0.0000793113,0.00010601674,0.000045960023,0.00008345564,0.000051881412,0.00014421163,0.000054000768,0.0000064320934],"category_scores_gemma":[0.000013165127,0.000082055725,0.00002478742,0.00021268365,0.00013081807,0.00083900924,0.000078213205,0.00007607533,0.000004941695],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011158119,0.000049604398,0.3231346,0.00025104434,0.0001094697,0.000009664151,0.008406341,0.055821173,0.3104929,0.0014805108,0.0017996938,0.29833344],"study_design_scores_gemma":[0.007469662,0.0014792044,0.302796,0.00036912903,0.00006027248,0.00014095275,0.002330626,0.2269493,0.43660304,0.0014809485,0.019394228,0.0009266132],"about_ca_topic_score_codex":0.00032355802,"about_ca_topic_score_gemma":0.000119264914,"teacher_disagreement_score":0.29740682,"about_ca_system_score_codex":0.00067826844,"about_ca_system_score_gemma":0.00023867979,"threshold_uncertainty_score":0.33461353},"labels":[],"label_agreement":null},{"id":"W2989606058","doi":"10.18280/ria.330307","title":"A New Triplet Convolutional Neural Network for Classification of Lesions on Mammograms","year":2019,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology)","score_opus":0.06582292878497507,"score_gpt":0.2927013670083966,"score_spread":0.22687843822342152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989606058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014862252,0.00012346535,0.98033446,0.0013371687,0.0015328442,0.0006225396,0.0000063943767,0.00009240317,0.0010884467],"genre_scores_gemma":[0.96592146,0.000018334787,0.031034833,0.00013663435,0.00026567746,0.00005100061,0.000010586814,0.000013721391,0.0025477298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857724,0.000045681118,0.00042379313,0.00044684482,0.000210207,0.00029621014],"domain_scores_gemma":[0.9985295,0.00035921193,0.00022064117,0.0006658199,0.00013923697,0.000085578824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032976348,0.00013044968,0.00018882252,0.00009078687,0.000110625355,0.000046606496,0.00059611985,0.000086017004,0.00010166929],"category_scores_gemma":[0.000058177073,0.00013205531,0.00014293478,0.00060111046,0.00004117852,0.00020412292,0.00006637603,0.00013432023,0.00024165814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012325948,0.000112004636,0.000896389,0.00006206853,0.000021635422,6.2871106e-7,0.0003829906,0.31363633,0.010336038,0.3209716,0.010194771,0.34326226],"study_design_scores_gemma":[0.000088808374,0.00045524412,0.0009166456,0.00006722683,0.000006227976,0.0000065236873,0.000067464985,0.9569997,0.014611123,0.010049328,0.016578665,0.00015305127],"about_ca_topic_score_codex":0.000033199038,"about_ca_topic_score_gemma":0.000012851514,"teacher_disagreement_score":0.9510592,"about_ca_system_score_codex":0.00008794796,"about_ca_system_score_gemma":0.000105793224,"threshold_uncertainty_score":0.5385059},"labels":[],"label_agreement":null},{"id":"W2989864840","doi":"10.1145/3357729.3357742","title":"A Large-scale and Extensible Platform for Precision Medicine Research","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure","funders":"","keywords":"Precision medicine; Scalability; Computer science; Big data; Personalization; Cloud computing; Data science; Volume (thermodynamics); Scale (ratio); Personalized medicine; Random forest; Data mining; Machine learning; Database; Bioinformatics; World Wide Web; Operating system","score_opus":0.0685604593790065,"score_gpt":0.36641951032197945,"score_spread":0.29785905094297294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989864840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06444393,0.0001764875,0.91335136,0.003131943,0.0006085574,0.0006811409,9.2260586e-7,0.00011646951,0.017489212],"genre_scores_gemma":[0.89524966,0.00008885012,0.089210086,0.0005256839,0.00024442238,0.00007316377,0.0000013851978,0.000014729047,0.01459199],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890697,0.0000179357,0.000119589924,0.00034205717,0.00034986544,0.00026356176],"domain_scores_gemma":[0.9989356,0.00036737637,0.000022752885,0.00041742212,0.00019299668,0.00006388054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014181158,0.000057755587,0.00010333122,0.000140706,0.00011838346,0.00004725039,0.00028590468,0.00005217885,0.00007988923],"category_scores_gemma":[0.00006187448,0.00004195904,0.00001542912,0.00031926596,0.000035607467,0.00040829118,0.00024357789,0.00010792386,0.00006351568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003032861,0.00012467473,0.0029956524,0.0002435421,0.00003061525,0.0000036448905,0.0093457,0.00006815523,0.026654255,0.20671652,0.18398692,0.56952703],"study_design_scores_gemma":[0.0023870463,0.0020071745,0.0029046994,0.000119423006,0.0000034830737,0.000030797135,0.0008429341,0.6190914,0.016875997,0.11387878,0.2416412,0.0002171102],"about_ca_topic_score_codex":0.00004418074,"about_ca_topic_score_gemma":0.0000750998,"teacher_disagreement_score":0.8308058,"about_ca_system_score_codex":0.00004962627,"about_ca_system_score_gemma":0.00003346118,"threshold_uncertainty_score":0.171104},"labels":[],"label_agreement":null},{"id":"W2990106615","doi":"10.48550/arxiv.1911.09863","title":"Shape Detection In 2D Ultrasound Images","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Medical diagnosis; Convolutional neural network; Deep learning; Pattern recognition (psychology); Path (computing); Artificial neural network; Ultrasound; Scanner; Computer vision; Data mining; Machine learning; Radiology","score_opus":0.04343205173879234,"score_gpt":0.18340075417162305,"score_spread":0.13996870243283072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990106615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41387287,0.00005665515,0.58096486,0.00003561237,0.0017146693,0.00031389116,0.000005849682,0.00027418157,0.0027614227],"genre_scores_gemma":[0.99800575,0.00022175178,0.00064258487,0.000055483168,0.000096407086,0.000001855588,0.0000035860364,0.000020086238,0.0009524695],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795634,0.00014722272,0.00019560849,0.0012478043,0.000109252585,0.0003437686],"domain_scores_gemma":[0.9982067,0.00015700427,0.00023175779,0.001217922,0.00010382982,0.00008279945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026763036,0.00028693432,0.00028005088,0.0004657697,0.0000865964,0.00014823035,0.0014451359,0.00035879607,0.00004224081],"category_scores_gemma":[0.000038781425,0.00036820743,0.00015374253,0.00082554703,0.000070098955,0.000658655,0.0010829942,0.00081849366,0.0002479843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014395503,0.00022616865,0.025272192,0.00037438798,0.00015988472,0.00046300038,0.00093623565,0.9359587,0.0070297304,0.008742349,0.0005368225,0.020156575],"study_design_scores_gemma":[0.0010445936,0.00016813852,0.036259174,0.00020253962,0.00005614239,0.000033221997,0.00013612,0.90975976,0.014489747,0.035844535,0.0008242443,0.0011817964],"about_ca_topic_score_codex":0.00044895706,"about_ca_topic_score_gemma":0.00026977475,"teacher_disagreement_score":0.5841329,"about_ca_system_score_codex":0.0008165143,"about_ca_system_score_gemma":0.00016106368,"threshold_uncertainty_score":0.999877},"labels":[],"label_agreement":null},{"id":"W2990357513","doi":"10.14740/gr1210","title":"Diagnosis of Liver Neoplasms by Computational and Statistical Image Analysis","year":2019,"lang":"en","type":"article","venue":"Gastroenterology Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hepatocellular carcinoma; Medicine; Nuclear medicine; H&E stain; Pattern recognition (psychology); Pathology; Artificial intelligence; Internal medicine; Computer science; Staining","score_opus":0.018292514922896082,"score_gpt":0.3185760461565273,"score_spread":0.3002835312336312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990357513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61937326,0.00003762531,0.37992492,0.00041962368,0.00003809014,0.00009969184,0.00002955349,0.00001375453,0.00006346115],"genre_scores_gemma":[0.9686983,0.00003448101,0.031090016,0.000075331045,0.000010300284,0.000029277808,0.000012512867,0.000004602685,0.000045142264],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99826455,0.00038275035,0.00018485662,0.00038597535,0.00043746992,0.00034439497],"domain_scores_gemma":[0.9987826,0.00059727166,0.000050550378,0.00027184168,0.00020915485,0.00008860454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067515066,0.00007284531,0.00020229841,0.00035181176,0.000058885766,0.000045044075,0.00036989243,0.000048461196,0.00018013206],"category_scores_gemma":[0.00004512618,0.00007194521,0.00003853189,0.0004905107,0.00030652163,0.00018630282,0.0003621505,0.00024043574,0.00005337018],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009238185,0.00008361145,0.9880146,0.000026885491,0.00019650663,0.000008723593,0.00015128705,0.00046149842,0.00048015738,0.0014612193,0.005246942,0.003776227],"study_design_scores_gemma":[0.0005493859,0.000758222,0.80117214,0.000005461002,0.000027112495,0.000019857309,0.000019203391,0.19512251,0.0003833405,0.0017514293,0.0001367791,0.00005453611],"about_ca_topic_score_codex":0.00015390398,"about_ca_topic_score_gemma":0.00006359469,"teacher_disagreement_score":0.34932506,"about_ca_system_score_codex":0.000046117973,"about_ca_system_score_gemma":0.000030320236,"threshold_uncertainty_score":0.29338402},"labels":[],"label_agreement":null},{"id":"W2990510514","doi":"10.1038/s41598-019-53911-x","title":"Automated detection and quantification of breast cancer brain metastases in an animal model using democratized machine learning tools","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Government of Canada; Université de Sherbrooke","keywords":"Computer science; Workflow; Artificial intelligence; Digital pathology; Segmentation; Machine learning; Automated method; Leverage (statistics); H&E stain; Pathology; Medical physics; Medicine; Immunohistochemistry; Database","score_opus":0.034313449760801806,"score_gpt":0.3018731944707787,"score_spread":0.2675597447099769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990510514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89252466,0.00008339119,0.10572044,0.00007716291,0.0010661059,0.00030050156,0.000005242725,0.00021012632,0.0000123880845],"genre_scores_gemma":[0.9921146,0.000002767345,0.007753295,0.000009234914,0.000012024276,0.0000148577055,0.00000934608,0.000011877064,0.0000719926],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978531,0.00017290229,0.0005278377,0.00081994594,0.00040451973,0.00022170748],"domain_scores_gemma":[0.99856585,0.00004469622,0.0005207834,0.000597385,0.00020685195,0.00006440673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001885356,0.00013282531,0.00021940665,0.0003675779,0.00018526222,0.00038708607,0.00016889986,0.00006385936,0.000013358519],"category_scores_gemma":[0.000072709605,0.00013182744,0.00003698716,0.0009936477,0.00008769133,0.0017761877,0.00010098065,0.00013612631,0.0000012922775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022532666,0.000027891181,0.010251623,0.000027167778,0.000005688217,0.0000065484005,0.00025732967,0.1491207,0.829826,0.000033218977,0.000009255059,0.010412061],"study_design_scores_gemma":[0.00016214802,0.0000406209,0.0120060975,0.000039249542,0.000007606528,0.00015797815,0.00002529463,0.8986066,0.08823892,0.00056665513,0.000019956466,0.0001288576],"about_ca_topic_score_codex":0.00044858165,"about_ca_topic_score_gemma":0.00042266227,"teacher_disagreement_score":0.7494859,"about_ca_system_score_codex":0.00014208659,"about_ca_system_score_gemma":0.00019179948,"threshold_uncertainty_score":0.53757674},"labels":[],"label_agreement":null},{"id":"W2990892814","doi":"10.1109/isbi45749.2020.9098533","title":"Learning with Less Data Via Weakly Labeled Patch Classification in Digital Pathology","year":2020,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Labeled data; Digital pathology; Annotation; Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.08152226970198607,"score_gpt":0.28601526755049694,"score_spread":0.20449299784851088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990892814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03969282,0.000039192837,0.95434105,0.0029490641,0.00044717104,0.00031874978,0.000011808271,0.00045185382,0.0017482972],"genre_scores_gemma":[0.9692157,0.000040489547,0.030039232,0.0001226536,0.000112643465,0.000058682625,0.00021403864,0.000024622579,0.00017192139],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754906,0.00010489114,0.00033947756,0.0014348393,0.00031710314,0.00025464196],"domain_scores_gemma":[0.99775136,0.00008286912,0.00027507072,0.0017251202,0.000095587464,0.000070024005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002893877,0.00024024583,0.00030330764,0.00013344407,0.000057880254,0.00039585348,0.0023643486,0.00025154656,0.000007396187],"category_scores_gemma":[0.00007120623,0.00021978005,0.000025825233,0.000422594,0.000057733847,0.00078840833,0.0038223045,0.001162995,0.000057602094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007926974,0.00012526994,0.031157112,0.00019071998,0.00006167135,0.00019304838,0.0017483722,0.003966195,0.001571298,0.0030032573,0.0006757287,0.95722806],"study_design_scores_gemma":[0.00045675802,0.00026005277,0.015547282,0.00012766242,0.0000128432575,0.000063088366,0.00023071456,0.97513026,0.00035721998,0.004482475,0.002734607,0.0005970291],"about_ca_topic_score_codex":0.00023672185,"about_ca_topic_score_gemma":0.0004496648,"teacher_disagreement_score":0.97116405,"about_ca_system_score_codex":0.00018586525,"about_ca_system_score_gemma":0.00027083547,"threshold_uncertainty_score":0.896237},"labels":[],"label_agreement":null},{"id":"W2991289251","doi":"10.1038/s41746-020-0238-2","title":"Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence","year":2020,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto General Hospital; Jacobs (Canada); Toronto Western Hospital; MaRS; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario; Ontario Research Foundation; Dell EMC","keywords":"Digital pathology; Telepathology; Computer science; Histopathology; Dermatopathology; Medical diagnosis; Artificial intelligence; Pathology; Medicine","score_opus":0.1344635809798248,"score_gpt":0.36839954069882636,"score_spread":0.23393595971900155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991289251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019527905,0.0014268106,0.9525582,0.01491321,0.0059805056,0.00059577415,0.00008334645,0.00044485505,0.0044693705],"genre_scores_gemma":[0.9714648,0.0002911713,0.02490913,0.0007270247,0.0024240036,0.00007180581,0.000022700702,0.00005474429,0.000034617446],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961301,0.00018098995,0.00084539375,0.0014184751,0.0008047051,0.00062034745],"domain_scores_gemma":[0.9964906,0.001699185,0.00046114225,0.00094844523,0.00018225069,0.00021836034],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003211328,0.00051652023,0.0007824957,0.00020789854,0.00018155128,0.00028662037,0.0014545199,0.00019381453,0.000026075966],"category_scores_gemma":[0.0026547168,0.00048083437,0.00015006866,0.0004360826,0.00095631456,0.00035981473,0.0023259963,0.0015645733,0.000055974302],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009628956,0.000109842294,0.00031253122,0.00053531444,0.00008932517,0.0012278347,0.0054953857,0.004975955,0.0057859337,0.029214464,0.0012661325,0.950891],"study_design_scores_gemma":[0.00026134835,0.0007272248,0.0016900301,0.0022043504,0.00013489557,0.00046416503,0.0002730593,0.08862531,0.006779724,0.8959275,0.0017711993,0.0011412255],"about_ca_topic_score_codex":0.000460829,"about_ca_topic_score_gemma":0.000012659977,"teacher_disagreement_score":0.9519369,"about_ca_system_score_codex":0.0004846593,"about_ca_system_score_gemma":0.00055864383,"threshold_uncertainty_score":0.9997643},"labels":[],"label_agreement":null},{"id":"W2992910467","doi":"","title":"Analysis of brain lesions in multiple sclerosis using invivo5.4 medical design suite by anatomage","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Multiple sclerosis; Grey matter; Suite; Volume (thermodynamics); Computer science; Visualization; Medical physics; Medicine; Magnetic resonance imaging; Artificial intelligence; Radiology; White matter; Psychiatry","score_opus":0.07012773555529327,"score_gpt":0.2806738145709358,"score_spread":0.21054607901564254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992910467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40919572,0.00002604816,0.59010834,0.0003325268,0.00007697115,0.00011048079,0.0000034932136,0.000044217377,0.000102176746],"genre_scores_gemma":[0.96597767,0.000012204927,0.03343815,0.00047874905,0.0000058662804,0.0000050467547,0.0000015323407,0.000006768179,0.000074025374],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983701,0.00018751233,0.00032461947,0.00037509116,0.0005235808,0.0002190673],"domain_scores_gemma":[0.99868274,0.0005878666,0.00010149414,0.00048350188,0.000047046968,0.00009737623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008472603,0.00010024739,0.00026524108,0.00054841576,0.00004507626,0.000027984286,0.00059702987,0.00010910152,0.0002325908],"category_scores_gemma":[0.00016894052,0.00009449428,0.00009325053,0.0029035066,0.000046171288,0.00036705114,0.0002158617,0.00012656391,0.000013152729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000637641,0.0005797831,0.29909593,0.00006557062,0.00082891464,0.000019198877,0.0015386646,0.08355509,0.38536358,0.0022029874,0.0067310156,0.2199555],"study_design_scores_gemma":[0.00032850896,0.00004041688,0.017902626,0.000024960613,0.000023427316,8.8929005e-7,0.00002643592,0.9604635,0.020930259,0.00006462975,0.00008218572,0.000112149915],"about_ca_topic_score_codex":0.0019938955,"about_ca_topic_score_gemma":0.00086654694,"teacher_disagreement_score":0.8769084,"about_ca_system_score_codex":0.00013950323,"about_ca_system_score_gemma":0.0000909054,"threshold_uncertainty_score":0.3853365},"labels":[],"label_agreement":null},{"id":"W2995663464","doi":"10.1111/his.13991","title":"The coming 15 years in gynaecological pathology: digitisation, artificial intelligence, and new technologies","year":2019,"lang":"en","type":"review","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency; Vancouver General Hospital","funders":"","keywords":"Cornerstone; Modalities; Pathology; Morphology (biology); Medicine; Surgical pathology; Anatomical pathology; Biology; History; Zoology","score_opus":0.10751113436181899,"score_gpt":0.3203510805771286,"score_spread":0.2128399462153096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995663464","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021197895,0.945611,0.05052166,0.00038895436,0.0022929606,0.0005417843,0.0000026992934,0.0002855971,0.00033416486],"genre_scores_gemma":[0.00031830146,0.99553907,0.003640668,0.000052470223,0.00007906558,0.0001253966,0.0000039036486,0.000020167288,0.00022095266],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761856,0.00034050594,0.0006928703,0.0007929979,0.00013959665,0.0004154615],"domain_scores_gemma":[0.9979728,0.0007695379,0.00038504807,0.00080436753,0.00003054395,0.000037720656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006817342,0.000288577,0.00090307364,0.00037111892,0.0001488471,0.00010782559,0.0012485818,0.0007101378,0.0000068462264],"category_scores_gemma":[0.000454163,0.00022178613,0.00012034748,0.00059182756,0.0004964534,0.00014770216,0.0007523914,0.000803005,0.00014064864],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013831129,0.000009252234,0.000017596165,0.00014870705,0.000001563378,0.00016002206,0.0001069698,0.000002520969,4.0372234e-7,0.023389041,0.00022105763,0.9759415],"study_design_scores_gemma":[0.000037571113,0.0001521446,0.000459552,0.00020855298,0.000031583688,0.0007389542,0.00003995009,0.00013169329,0.0000010358386,0.03725806,0.9606608,0.00028010327],"about_ca_topic_score_codex":0.000011049413,"about_ca_topic_score_gemma":0.00011446528,"teacher_disagreement_score":0.9756614,"about_ca_system_score_codex":0.00042211468,"about_ca_system_score_gemma":0.00035672664,"threshold_uncertainty_score":0.9044176},"labels":[],"label_agreement":null},{"id":"W2995811766","doi":"10.1038/s41379-019-0434-2","title":"Assessment of individual tumor buds using keratin immunohistochemistry: moderate interobserver agreement suggests a role for machine learning","year":2019,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"KWF Kankerbestrijding","keywords":"Cytokeratin; Tumor budding; Kappa; Categorization; Digital image analysis; Immunohistochemistry; Colorectal cancer; Pathology; Biology; Medicine; Cancer; Artificial intelligence; Computer science; Internal medicine; Mathematics; Metastasis","score_opus":0.02034512352745948,"score_gpt":0.2911442806440596,"score_spread":0.27079915711660013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995811766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5148589,0.000109660075,0.4843867,0.000034496745,0.00020494938,0.00022528986,0.000010261197,0.000036755933,0.0001329412],"genre_scores_gemma":[0.9163201,0.0000025216596,0.083262205,0.00010083447,0.000032074713,0.00006640659,0.000019153647,0.000019563171,0.00017714936],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983646,0.00012841317,0.00037612807,0.0005503034,0.00025936894,0.0003211523],"domain_scores_gemma":[0.9989225,0.00006173723,0.000317974,0.00052606885,0.0001292841,0.000042407697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058060477,0.00019080102,0.0003281136,0.00008764333,0.00010581806,0.00006303287,0.000594826,0.00009369797,0.0000257699],"category_scores_gemma":[0.000022501537,0.00019993976,0.00009251817,0.00011014421,0.000043281158,0.00021411193,0.000452338,0.00026601143,0.000004177142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057366495,0.00011597533,0.008734638,0.00011144868,0.00006441446,0.0000141742885,0.0016359425,0.091832295,0.88404477,0.0007153701,0.000013463033,0.012660138],"study_design_scores_gemma":[0.00082621526,0.0004072169,0.0033947653,0.00003413662,0.00001691595,0.00006757941,0.000027735929,0.94903207,0.044515915,0.0014399863,0.00004801388,0.00018947787],"about_ca_topic_score_codex":0.0000411803,"about_ca_topic_score_gemma":0.000009284551,"teacher_disagreement_score":0.8571997,"about_ca_system_score_codex":0.00024385283,"about_ca_system_score_gemma":0.00014428677,"threshold_uncertainty_score":0.8153307},"labels":[],"label_agreement":null},{"id":"W2995911746","doi":"10.5539/cis.v13n1p1","title":"Performance Evaluation of a Classification Model for Oral Tumor Diagnosis","year":2019,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mucoepidermoid carcinoma; Histopathology; Artificial intelligence; Computer science; Medicine; Pathology; Carcinoma","score_opus":0.06293883624948812,"score_gpt":0.30493784961454384,"score_spread":0.24199901336505572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995911746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38110417,0.0000064722076,0.6175188,0.00008686272,0.0003083464,0.00037485652,0.0000016425697,0.000029480037,0.00056936784],"genre_scores_gemma":[0.9341573,0.000015148288,0.06548557,0.00022490206,0.000014904291,0.00009391193,0.0000020815987,0.0000016103536,0.0000045636084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873865,0.000015947051,0.00025608504,0.00019012463,0.0006513253,0.00014789077],"domain_scores_gemma":[0.9985782,0.00004234573,0.00021465115,0.00031383274,0.0008046097,0.000046378354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017970966,0.00007299966,0.000094912975,0.0002657578,0.00013672608,0.00016870588,0.00047409613,0.000022421516,0.000003090348],"category_scores_gemma":[0.00003610664,0.00006715626,0.000023066817,0.00060115167,0.00009586958,0.011177953,0.00013357267,0.00003995386,0.000013294269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009667879,0.000015155187,0.0047038035,0.0000699968,0.000002891678,4.1011337e-9,0.0017821372,0.074023455,0.0005353964,0.017650707,0.00022619656,0.9009806],"study_design_scores_gemma":[0.00037897652,0.000108737346,0.036949247,0.000019473186,0.000004040061,0.0000023798916,0.000014663919,0.95988643,0.0018015532,0.00030674232,0.00044520886,0.00008257212],"about_ca_topic_score_codex":0.000001798295,"about_ca_topic_score_gemma":3.0622436e-7,"teacher_disagreement_score":0.90089804,"about_ca_system_score_codex":0.000103533035,"about_ca_system_score_gemma":0.00028075775,"threshold_uncertainty_score":0.8103746},"labels":[],"label_agreement":null},{"id":"W2996583486","doi":"10.1136/jclinpath-2019-206155","title":"Current opinion, status and future development of digital pathology in Switzerland","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Current (fluid); Pathology; Medicine; Data science; Bioinformatics; Computer science; Biology; Engineering","score_opus":0.043669679845875164,"score_gpt":0.3758514600080569,"score_spread":0.33218178016218175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996583486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96993417,0.0018506012,0.020443944,0.0005890876,0.00700074,0.00008418198,0.0000015070832,0.0000066579505,0.00008910385],"genre_scores_gemma":[0.9844293,0.0016575748,0.013312736,0.00006407788,0.00052228535,0.000001289596,7.0079557e-7,0.000006128912,0.0000059167414],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976886,0.00019486822,0.0014712503,0.00023736487,0.00019863366,0.00020929685],"domain_scores_gemma":[0.9983041,0.00032841717,0.0008836951,0.00021411134,0.00016093711,0.00010869939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001469053,0.00009946089,0.0005215308,0.00017665575,0.000016420568,0.000019547051,0.0003157136,0.00016226881,0.000007684861],"category_scores_gemma":[0.00020007242,0.00007827845,0.00008515154,0.00016324807,0.00008747083,0.00032303264,0.00018616176,0.0005362864,0.000008702606],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104039886,0.00014776479,0.4241225,0.000033791588,0.000010781866,0.000037841997,0.00064018555,0.00001154488,0.0000802593,0.0004414541,0.00009066148,0.5742791],"study_design_scores_gemma":[0.002239054,0.0011881423,0.9401663,0.000083166844,0.000004342862,0.00051995827,0.00007479482,0.00016913815,0.00007369477,0.0041635074,0.051184963,0.00013296929],"about_ca_topic_score_codex":2.7533665e-7,"about_ca_topic_score_gemma":0.0000026801006,"teacher_disagreement_score":0.5741462,"about_ca_system_score_codex":0.00003605889,"about_ca_system_score_gemma":0.0003413924,"threshold_uncertainty_score":0.31921026},"labels":[],"label_agreement":null},{"id":"W2997833216","doi":"10.1186/s12911-019-1014-6","title":"A new concordant partial AUC and partial c statistic for imbalanced data in the evaluation of machine learning algorithms","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"AI in cancer detection","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; University of Ottawa; Public Health Ontario; Institute for Clinical Evaluative Sciences; Statistics Canada; University of Waterloo; Ottawa Hospital","funders":"","keywords":"Receiver operating characteristic; False positives and false negatives; Statistics; Statistic; Benchmark (surveying); Measure (data warehouse); Artificial intelligence; Computer science; Polytomous Rasch model; Plot (graphics); False positive paradox; Mathematics; Data mining; Pattern recognition (psychology); Algorithm; Item response theory","score_opus":0.128810891563631,"score_gpt":0.3971672971741072,"score_spread":0.2683564056104762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997833216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014586738,0.0001895363,0.98463297,0.00013787684,0.00012415588,0.00028345492,0.000009246434,0.00001383359,0.000022202683],"genre_scores_gemma":[0.52423877,0.000049492573,0.4752685,0.00033541347,0.00008431949,0.000011435372,0.000008738116,0.0000029866876,3.0700667e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980433,0.00009908502,0.0005466533,0.00015302967,0.0010261905,0.00013175825],"domain_scores_gemma":[0.99753785,0.0018326415,0.00022167031,0.00024310303,0.000064601714,0.00010011139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030620536,0.000078577184,0.0001674113,0.00004103823,0.00007824681,0.000113414506,0.00046498727,0.000047575202,0.000013633283],"category_scores_gemma":[0.0024705846,0.000054020333,0.0000146597595,0.00018721464,0.000038215312,0.00034309598,0.00037255423,0.00015338682,8.722493e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052353193,0.0000046807563,0.00032371914,0.00005272652,0.0000036865345,7.2292977e-7,0.0018113335,0.0014939937,0.0000022796753,0.00093641126,0.00025800665,0.9950601],"study_design_scores_gemma":[0.0013639057,0.00015208629,0.00040383884,0.000111034744,0.00001544797,0.000011913328,0.00026278355,0.9938995,0.000011511116,0.0029958484,0.00070854824,0.00006357351],"about_ca_topic_score_codex":0.00001904662,"about_ca_topic_score_gemma":0.000041546566,"teacher_disagreement_score":0.9949965,"about_ca_system_score_codex":0.000014903846,"about_ca_system_score_gemma":0.000289377,"threshold_uncertainty_score":0.2957699},"labels":[],"label_agreement":null},{"id":"W2999944568","doi":"10.1186/s13104-019-4866-z","title":"CACTUS: cancer image annotating, calibrating, testing, understanding and sharing in breast cancer histopathology","year":2020,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"Nvidia","keywords":"Grading (engineering); Breast cancer; Medicine; Concordance; Medical physics; Workload; Intraclass correlation; Quality assurance; Cohen's kappa; Pathology; Computer science; Cancer; Machine learning; Internal medicine; External quality assessment","score_opus":0.37747207815434847,"score_gpt":0.42313969250125194,"score_spread":0.04566761434690347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999944568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49046662,0.0026648056,0.47525325,0.027520474,0.0006607334,0.0010072462,0.00005858325,0.00062179414,0.0017464828],"genre_scores_gemma":[0.9741341,0.00012922085,0.024837662,0.00035414405,0.0003179176,0.00015648874,8.0358336e-7,0.000031779833,0.000037894977],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734485,0.00027348023,0.0002982687,0.00086670776,0.00052379374,0.0006929041],"domain_scores_gemma":[0.99826443,0.00090877915,0.00011025247,0.00031980206,0.000174315,0.00022241032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010071263,0.00017235942,0.00022714335,0.0002593154,0.00033187895,0.0003510085,0.00070487824,0.00009115189,0.000060624403],"category_scores_gemma":[0.00109868,0.00017391243,0.000027374479,0.0013853682,0.00025937989,0.00081674516,0.0008500489,0.0006745005,0.00000820375],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061548366,0.00003114086,0.9236996,0.00037275595,0.00000891671,0.00011269549,0.0071393605,0.0014023115,0.04449362,0.0033576926,0.0010250055,0.01829531],"study_design_scores_gemma":[0.0010424817,0.00023361392,0.19521257,0.00047847015,0.0000065134827,0.000075105774,0.0007314196,0.78889495,0.004684304,0.007802455,0.00028242634,0.00055568694],"about_ca_topic_score_codex":0.008319015,"about_ca_topic_score_gemma":0.0026971134,"teacher_disagreement_score":0.78749263,"about_ca_system_score_codex":0.0008140296,"about_ca_system_score_gemma":0.0004434538,"threshold_uncertainty_score":0.9982847},"labels":[],"label_agreement":null},{"id":"W3001935802","doi":"10.1109/isbi45749.2020.9098685","title":"Breast Lesion Segmentation in Ultrasound Images with Limited Annotated Data","year":2020,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Segmentation; Convolutional neural network; Artificial intelligence; Speckle noise; Breast ultrasound; Modality (human–computer interaction); Deep learning; Image segmentation; Artificial neural network; Pattern recognition (psychology); Speckle pattern; Computer vision; Mammography; Medicine","score_opus":0.06075567194011501,"score_gpt":0.29929023323511844,"score_spread":0.23853456129500344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001935802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009688962,0.000051086707,0.9846414,0.0028213013,0.00045941578,0.0005978402,0.00012532853,0.00054923084,0.0010654497],"genre_scores_gemma":[0.77642816,0.00020655358,0.22157742,0.00036737576,0.00015359223,0.000059816382,0.001047125,0.00003653346,0.00012342235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772125,0.00012301488,0.00030667486,0.0012222696,0.00041441055,0.00021237407],"domain_scores_gemma":[0.9979069,0.0000995114,0.00021296507,0.0015991491,0.00010538113,0.000076042794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023558519,0.00025651124,0.00023297605,0.00018620506,0.000053050437,0.0003928502,0.0018415521,0.00014069477,0.000020567857],"category_scores_gemma":[0.000022501408,0.00022413116,0.000022527407,0.00067708635,0.000042604668,0.0009072556,0.002038471,0.0005267291,0.000032014985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009836947,0.0008099581,0.02301119,0.0014264355,0.00052317826,0.0005335095,0.0062572844,0.047553048,0.13843192,0.001105382,0.052514218,0.7268502],"study_design_scores_gemma":[0.0036229144,0.0005858119,0.16836952,0.0012284782,0.00011629622,0.0010346262,0.0006197325,0.73531204,0.079505004,0.0060767992,0.00075216027,0.0027766011],"about_ca_topic_score_codex":0.00090160803,"about_ca_topic_score_gemma":0.00036470962,"teacher_disagreement_score":0.7667392,"about_ca_system_score_codex":0.00022392954,"about_ca_system_score_gemma":0.00023102069,"threshold_uncertainty_score":0.91398036},"labels":[],"label_agreement":null},{"id":"W3003488448","doi":"10.2196/16334","title":"Performance of Computer-Aided Diagnosis in Ultrasonography for Detection of Breast Lesions Less and More Than 2 cm: Prospective Comparative Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"McNemar's test; Medicine; CAD; Receiver operating characteristic; Radiology; Breast MRI; Ultrasonography; Breast imaging; Prospective cohort study; Computer-aided diagnosis; Mammography; Breast cancer; Surgery; Internal medicine; Cancer","score_opus":0.030992351291989042,"score_gpt":0.29945640015440983,"score_spread":0.2684640488624208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003488448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8777629,0.000013342188,0.12072799,0.0001802805,0.00009098073,0.0011433649,0.000012976079,0.000044662847,0.000023499133],"genre_scores_gemma":[0.99295646,0.000032350308,0.006550973,0.000080637314,0.000042753054,0.00032959672,0.0000018369897,0.000005056188,3.3407605e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984419,0.000045653396,0.0006744667,0.0001604381,0.0005031371,0.0001744454],"domain_scores_gemma":[0.9989027,0.00025387216,0.00033571772,0.00019155772,0.00016817742,0.00014802087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027438227,0.00014475039,0.00038596793,0.00016707371,0.00007003881,0.00002437471,0.0003899667,0.00009033408,0.0000016632339],"category_scores_gemma":[0.00002925892,0.00012638145,0.000058022975,0.00082248816,0.00018708743,0.0006123175,0.00016556926,0.00023009056,6.0176177e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003793799,0.0011595984,0.5348186,0.0015331572,0.00016871006,0.0000021215976,0.2500224,0.0008797562,0.00023735949,0.00031437227,0.00016852701,0.21031602],"study_design_scores_gemma":[0.0015669552,0.0021230078,0.36205873,0.00018974952,0.000012850891,0.000011690282,0.008052367,0.62117964,0.004610185,0.000033428554,0.000016217657,0.00014515803],"about_ca_topic_score_codex":0.000028917204,"about_ca_topic_score_gemma":0.000042704563,"teacher_disagreement_score":0.6202999,"about_ca_system_score_codex":0.000041352385,"about_ca_system_score_gemma":0.0000738418,"threshold_uncertainty_score":0.5153686},"labels":[],"label_agreement":null},{"id":"W3005104074","doi":"10.1109/bibm47256.2019.8983349","title":"Shearlet-Based Techniques for Histological Image Classification","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Shearlet; Pattern recognition (psychology); Artificial intelligence; Computer science; Support vector machine; Local binary patterns; Feature vector; Feature extraction; Classifier (UML); Segmentation; Contextual image classification; Feature (linguistics); Image texture; Image segmentation; Wavelet; Image (mathematics); Histogram","score_opus":0.027697891814077332,"score_gpt":0.28263920198239906,"score_spread":0.2549413101683217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005104074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013735445,0.000008873873,0.98089164,0.0028516122,0.00024486007,0.00039121494,6.117768e-7,0.0006006143,0.013637008],"genre_scores_gemma":[0.47390625,8.3529704e-7,0.5246516,0.00060626504,0.000033448458,0.00011570078,0.0000015504312,0.0000046574787,0.0006796843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993485,0.000020449997,0.00011260218,0.000281973,0.00011038916,0.00012604916],"domain_scores_gemma":[0.9993791,0.000080219594,0.000050205555,0.00038751238,0.00007638554,0.00002657382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017763348,0.00006242009,0.000075736476,0.000055307668,0.000041818017,0.00005501789,0.00034138956,0.00006533507,0.00006244303],"category_scores_gemma":[0.000020290685,0.00005217256,0.000046007397,0.00012646378,0.00002400481,0.0002509855,0.00003323164,0.000055966997,0.00010811971],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057104142,0.00012942689,0.00097101304,0.00007213072,0.000008764372,0.0000011828021,0.000061642546,0.000015015999,0.31329992,0.23036085,0.036412053,0.4186109],"study_design_scores_gemma":[0.00042231352,0.00063570595,0.003997129,0.000012728341,0.000004427293,0.0000061954825,0.00001219601,0.5142943,0.3057543,0.009219628,0.16533919,0.00030185582],"about_ca_topic_score_codex":0.000009064485,"about_ca_topic_score_gemma":0.0000020206605,"teacher_disagreement_score":0.5142793,"about_ca_system_score_codex":0.00013542235,"about_ca_system_score_gemma":0.00004634949,"threshold_uncertainty_score":0.21275353},"labels":[],"label_agreement":null},{"id":"W3005546201","doi":"10.1016/j.ultrasmedbio.2020.01.001","title":"Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning","year":2020,"lang":"en","type":"article","venue":"Ultrasound in Medicine & Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":187,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Korea Health Industry Development Institute","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Transfer of learning; Feature extraction; Breast ultrasound; Computer-aided diagnosis; Breast cancer; Deep learning; Principal component analysis; Artificial neural network; Feature (linguistics); Mammography; Cancer; Medicine","score_opus":0.03549737938746034,"score_gpt":0.2970620853001939,"score_spread":0.26156470591273356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005546201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83512956,0.0013588677,0.15300915,0.008181477,0.0007922829,0.000577017,0.000026144106,0.0007953376,0.00013017083],"genre_scores_gemma":[0.99638784,0.00029131657,0.0016407213,0.0009758221,0.0005840671,0.000050386137,0.000039297825,0.000027003109,0.0000035300836],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746644,0.00047198645,0.0005399678,0.0007298632,0.00023445174,0.0005572776],"domain_scores_gemma":[0.9986942,0.00069432874,0.00013567288,0.00021716108,0.000121020996,0.00013763834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048243857,0.00028002908,0.00046775406,0.00015164631,0.00013225617,0.000028210272,0.000438249,0.00016547086,0.000083161955],"category_scores_gemma":[0.00010661865,0.00022591504,0.000037636335,0.0014999165,0.00040458862,0.0003461656,0.000031083408,0.0006400458,0.000005782034],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003452792,0.000087124805,0.7440101,0.000084138155,0.00006481323,0.000021731308,0.0029404203,0.13900839,0.07993861,0.0017646358,0.00039480397,0.03133995],"study_design_scores_gemma":[0.001776434,0.00031503444,0.48077825,0.0002476688,0.000022283377,0.00095670164,0.00017769185,0.51437426,0.000043680677,0.00014473255,0.000837953,0.00032532465],"about_ca_topic_score_codex":0.0014366622,"about_ca_topic_score_gemma":0.0009316576,"teacher_disagreement_score":0.37536588,"about_ca_system_score_codex":0.00035386614,"about_ca_system_score_gemma":0.00021233098,"threshold_uncertainty_score":0.92125475},"labels":[],"label_agreement":null},{"id":"W3005891124","doi":"10.1016/j.acra.2020.01.012","title":"Noninterpretive Uses of Artificial Intelligence in Radiology","year":2020,"lang":"en","type":"review","venue":"Academic Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Artificial intelligence; Task (project management); Applications of artificial intelligence; Action (physics); Expert system; Medical physics; Radiology; Medicine; Engineering","score_opus":0.07048308614967656,"score_gpt":0.3710884946957462,"score_spread":0.3006054085460696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005891124","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000049712116,0.8498719,0.1475957,0.00024552902,0.001488035,0.00047357165,0.000010502329,0.00007925971,0.00023058282],"genre_scores_gemma":[0.00019711873,0.99527466,0.0037959695,0.00012668657,0.00042722738,0.00013154508,0.0000069269277,0.000029079227,0.000010810163],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99566174,0.0011096151,0.001557147,0.0010367625,0.00014604905,0.0004887122],"domain_scores_gemma":[0.99691397,0.0014537937,0.00090175594,0.00059405685,0.000041819032,0.000094632946],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0006338153,0.0004320854,0.002430048,0.0012005005,0.000028842578,0.000008438881,0.0027233358,0.0014251957,0.000022015378],"category_scores_gemma":[0.0005343005,0.00039369144,0.00031774119,0.00219339,0.00043904482,0.00017895964,0.00054187584,0.002328607,0.00011740618],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009022677,0.000006487464,0.0000037761135,0.0006305445,0.0000571659,0.00003412214,0.00047499544,0.000030742194,0.000008173428,0.024606757,0.00032983313,0.9738084],"study_design_scores_gemma":[0.00004063645,0.0003787179,0.0000032893995,0.0023482412,0.000088025634,0.0014297267,0.000025058554,0.003397971,0.00008677928,0.011021126,0.980714,0.00046641886],"about_ca_topic_score_codex":0.000040298666,"about_ca_topic_score_gemma":0.000007120418,"teacher_disagreement_score":0.9803842,"about_ca_system_score_codex":0.0003484362,"about_ca_system_score_gemma":0.0005248617,"threshold_uncertainty_score":0.99997306},"labels":[],"label_agreement":null},{"id":"W3006062690","doi":"10.1016/j.media.2020.101640","title":"SDAE-GAN: Enable high-dimensional pathological images in liver cancer survival prediction with a policy gradient based data augmentation method","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Computer science; Immunohistochemistry; Pattern recognition (psychology); Artificial intelligence; Stage (stratigraphy); Pathology; Medicine; Biology","score_opus":0.04969742740291736,"score_gpt":0.335134612735509,"score_spread":0.2854371853325916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006062690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091910055,0.000108304324,0.97082895,0.019244349,0.00012373074,0.0001670541,0.00009477514,0.00015630234,0.000085514446],"genre_scores_gemma":[0.80914384,0.00010663305,0.1855109,0.004254009,0.0005120173,0.00010131278,0.0003117367,0.000019389441,0.000040137886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961427,0.0005854215,0.0004255631,0.001060054,0.0014197457,0.00036651056],"domain_scores_gemma":[0.9983916,0.00024370253,0.00016332467,0.0007057901,0.00014311115,0.0003524599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012202811,0.00021160196,0.00043277943,0.00040561383,0.00011526048,0.00012999891,0.0009864927,0.00012070202,0.00057076936],"category_scores_gemma":[0.00046560194,0.00016387866,0.00009704547,0.0037796416,0.00014301621,0.0009106534,0.00039522062,0.000373805,0.000018039616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014086916,0.0022934445,0.08285283,0.00039519215,0.003574009,0.0058040842,0.0036735442,0.21038815,0.02481025,0.0013707657,0.02430962,0.6391194],"study_design_scores_gemma":[0.0009865502,0.00017672204,0.022560712,0.000022933418,0.0003251782,0.0000076239844,0.000028919228,0.9718389,0.0035166019,0.00009187361,0.00025754422,0.00018644184],"about_ca_topic_score_codex":0.0055138664,"about_ca_topic_score_gemma":0.0010139439,"teacher_disagreement_score":0.79995286,"about_ca_system_score_codex":0.00026936724,"about_ca_system_score_gemma":0.0004392602,"threshold_uncertainty_score":0.8335354},"labels":[],"label_agreement":null},{"id":"W3006735766","doi":"10.1109/icmla.2019.00077","title":"Computer-Aided Diagnosis using Class-Weighted Deep Neural Network","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Mammography; Artificial neural network; Breast cancer; Computer-aided diagnosis; Feature selection; Class (philosophy); Feature (linguistics); Feature extraction; Pattern recognition (psychology); Machine learning; Cancer; Medicine","score_opus":0.019568786235306515,"score_gpt":0.2429766816121507,"score_spread":0.2234078953768442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006735766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23343666,0.000083347375,0.76093304,0.00039041144,0.0032606497,0.00021747698,2.198345e-7,0.00039310302,0.0012850782],"genre_scores_gemma":[0.79620624,0.000008655588,0.20173214,0.0013374159,0.00058359746,0.000013827189,8.939595e-7,0.000015994327,0.00010124911],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847144,0.000087019835,0.00024246136,0.00050256815,0.00027840823,0.0004180793],"domain_scores_gemma":[0.99889815,0.00016724804,0.00010556613,0.0006609909,0.00007317313,0.000094845534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016211657,0.00016730741,0.00019804112,0.00007538168,0.00012611377,0.00021335372,0.0006886597,0.00008623083,0.00015393892],"category_scores_gemma":[0.000003431617,0.00015476948,0.00008596066,0.0006666079,0.000024497931,0.000712175,0.00038329372,0.00016560928,0.00022221172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026924972,0.00011713692,0.08843448,0.000047080535,0.00010011747,0.000032414064,0.00040826603,0.33000705,0.00063022005,0.022021526,0.00895048,0.5492243],"study_design_scores_gemma":[0.0002635702,0.00011975877,0.0053301286,0.000014790968,0.0000054371235,0.000022185766,0.0000034179936,0.9888099,0.0007836187,0.0011843423,0.0032498522,0.00021301054],"about_ca_topic_score_codex":0.00014232092,"about_ca_topic_score_gemma":0.000046552337,"teacher_disagreement_score":0.65880287,"about_ca_system_score_codex":0.0001537139,"about_ca_system_score_gemma":0.00003110193,"threshold_uncertainty_score":0.6311316},"labels":[],"label_agreement":null},{"id":"W3007027538","doi":"10.1002/ima.22410","title":"Enhancing breast pectoral muscle segmentation performance by using skip connections in fully convolutional network","year":2020,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Higher Education Commission, Pakistan","keywords":"Segmentation; Computer science; Sørensen–Dice coefficient; Artificial intelligence; Pectoral muscle; Convolutional neural network; Deep learning; Ground truth; Computer vision; Image segmentation; Pattern recognition (psychology); Anatomy; Medicine","score_opus":0.00906573006438285,"score_gpt":0.24142702681904998,"score_spread":0.23236129675466713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007027538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46973008,0.0010374556,0.52084273,0.0064902785,0.001745,0.00007460672,0.0000050376407,0.000053632757,0.000021212036],"genre_scores_gemma":[0.9947792,0.00003962265,0.004669722,0.00012144682,0.0003746703,0.0000037589737,0.000001052356,0.000006547959,0.0000039756674],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894065,0.000036812642,0.00043564188,0.0001715554,0.00026328943,0.00015203284],"domain_scores_gemma":[0.9991139,0.00003597591,0.00037789735,0.00006622201,0.0003600981,0.000045870707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024802814,0.00008996673,0.00015178519,0.00027118062,0.00007857439,0.00011535138,0.0003604191,0.000048701808,0.0000041589774],"category_scores_gemma":[0.000030315809,0.00009220552,0.000026790765,0.00037469284,0.000051216055,0.0007041373,0.000102634855,0.000237495,0.0000015318228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001418498,0.00016088418,0.45601273,0.00012290076,0.000353038,0.000243584,0.0013413194,0.04810792,0.33317402,0.021959443,0.0030917018,0.13529064],"study_design_scores_gemma":[0.0019246353,0.00020840856,0.009936173,0.0005263423,0.000018413546,0.007415184,0.00074914424,0.969034,0.005906239,0.0007998,0.0031556776,0.00032594195],"about_ca_topic_score_codex":0.000074392716,"about_ca_topic_score_gemma":0.000008710172,"teacher_disagreement_score":0.92092615,"about_ca_system_score_codex":0.00025651976,"about_ca_system_score_gemma":0.0000995682,"threshold_uncertainty_score":0.37600318},"labels":[],"label_agreement":null},{"id":"W3007406909","doi":"10.1101/2020.02.25.965038","title":"Predicting Endometrial Cancer Subtypes and Molecular Features from Histopathology Images Using Multi-resolution Deep Learning Models","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Subtyping; Histopathology; Endometrial cancer; Computational biology; Mutation; Digital pathology; Pathology; Computer science; Biology; Artificial intelligence; Cancer; Medicine; Gene; Internal medicine; Genetics","score_opus":0.028086746597276536,"score_gpt":0.24315340077505448,"score_spread":0.21506665417777796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007406909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33601493,0.011233484,0.6495854,0.00016455178,0.0019651582,0.00038531554,0.00005675569,0.00059283973,0.0000015572634],"genre_scores_gemma":[0.8147143,0.00055603177,0.18378899,0.00011177638,0.00063508336,0.000106068284,2.8192767e-7,0.00008669077,7.492203e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962633,0.0004339387,0.00050763687,0.0017635865,0.00047237257,0.00055912527],"domain_scores_gemma":[0.99772763,0.00014481557,0.0006807809,0.00084294495,0.00035720796,0.0002466072],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048376416,0.00056619674,0.0006468612,0.00040807176,0.000347923,0.00045010992,0.0008562861,0.000610394,0.0000049670325],"category_scores_gemma":[0.00046853855,0.0006723434,0.00014044048,0.0006670994,0.00014749041,0.000571222,0.0015434377,0.0014663439,0.0000033895296],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056388435,0.00003410618,0.007785509,0.00014826575,0.00012292402,0.00013354604,0.00011733801,0.05157573,0.93966883,0.00028643888,0.000011663696,0.00005927783],"study_design_scores_gemma":[0.0009596,0.00006861844,0.030696385,0.00028901346,0.00018097747,1.4440413e-7,0.0000037343273,0.7922844,0.1745101,0.00004867114,0.00012333087,0.0008350214],"about_ca_topic_score_codex":0.0016957049,"about_ca_topic_score_gemma":0.000020064981,"teacher_disagreement_score":0.7651587,"about_ca_system_score_codex":0.0007715024,"about_ca_system_score_gemma":0.00042577923,"threshold_uncertainty_score":0.99957275},"labels":[],"label_agreement":null},{"id":"W3007464329","doi":"10.1038/s41746-020-0232-8","title":"Impact of a deep learning assistant on the histopathologic classification of liver cancer","year":2020,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":309,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Medicine; H&E stain; Workflow; Test (biology); Machine learning; Set (abstract data type); Diagnostic accuracy; Test set; Medical physics; Computer science; Pathology; Radiology; Staining","score_opus":0.05833074722149878,"score_gpt":0.2945620820779027,"score_spread":0.2362313348564039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007464329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7919111,0.000933737,0.1823411,0.0077970442,0.00028816305,0.00029814275,0.000007685279,0.00013275263,0.016290227],"genre_scores_gemma":[0.9995698,0.00003984721,0.000094239964,0.00015544081,0.00008939498,0.000010552817,0.0000012072089,0.000005412144,0.000034151984],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99914443,0.00004157204,0.00021628906,0.0001947681,0.00030149703,0.000101452075],"domain_scores_gemma":[0.9992081,0.0001730836,0.00024882876,0.00021772178,0.00010011789,0.000052159343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013473775,0.00008618803,0.00016516176,0.0000436768,0.00003341892,0.000012643899,0.0003297108,0.000033230368,0.00006217748],"category_scores_gemma":[0.0004129692,0.00004857645,0.000057028272,0.00037954003,0.00014332551,0.0001805533,0.000054083852,0.00015367933,0.000006690914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019377627,0.000108780216,0.026043534,0.00009058497,0.000062662686,0.000018671048,0.0072676204,0.0014648297,0.07094273,0.00832,0.0018970049,0.8835898],"study_design_scores_gemma":[0.0007666305,0.0063654827,0.82071525,0.00026278407,0.00003392936,0.000015585401,0.00032262856,0.164651,0.0029736608,0.0007836193,0.002882026,0.00022740226],"about_ca_topic_score_codex":0.00004730945,"about_ca_topic_score_gemma":0.0000027968426,"teacher_disagreement_score":0.8833624,"about_ca_system_score_codex":0.00014145144,"about_ca_system_score_gemma":0.00004497809,"threshold_uncertainty_score":0.19808902},"labels":[],"label_agreement":null},{"id":"W3007602809","doi":"10.1101/2020.02.24.963645","title":"Whole Slide Preview Image Segmentation and Setup for Digital Pathology Scanners","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"S2e Technologies (Canada); University of Toronto","funders":"","keywords":"Scanner; Computer vision; Artifact (error); Artificial intelligence; Computer science; Segmentation; Focus (optics); Image segmentation; Digital pathology; Identification (biology); Region of interest; Computer graphics (images); Optics","score_opus":0.016712867055052507,"score_gpt":0.24019338578385477,"score_spread":0.22348051872880226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007602809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078817435,0.0030339272,0.9093691,0.0027211464,0.0022273303,0.0023621786,0.0005230846,0.00093284686,0.000012928438],"genre_scores_gemma":[0.8292401,0.0007153386,0.1677452,0.00070689555,0.0005336136,0.00093674194,0.0000015141007,0.00011514026,0.0000054674724],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997447,0.00009388769,0.00046719142,0.0013192327,0.00026412687,0.00040854895],"domain_scores_gemma":[0.99800515,0.000082444545,0.00044158855,0.0009448448,0.0002984321,0.00022753653],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037648602,0.00041992962,0.00048757478,0.00015000594,0.00015461551,0.0008180246,0.0007664819,0.00028302282,0.0000034157479],"category_scores_gemma":[0.00019381587,0.00048168137,0.00012946692,0.0003783858,0.00010979118,0.00084864954,0.0009204046,0.00040238336,0.000037637674],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005180716,0.000110383044,0.0013372696,0.003573536,0.00023757771,0.000108012486,0.00011436397,0.00009029048,0.9879232,0.0017171311,0.003894406,0.0008419958],"study_design_scores_gemma":[0.004685434,0.0014144599,0.051760487,0.003486622,0.0006659473,0.0000010251255,0.00002800174,0.05733105,0.7759992,0.000680589,0.09765932,0.0062878523],"about_ca_topic_score_codex":0.0000061232163,"about_ca_topic_score_gemma":7.503351e-7,"teacher_disagreement_score":0.75042266,"about_ca_system_score_codex":0.00028510942,"about_ca_system_score_gemma":0.00036890514,"threshold_uncertainty_score":0.9997635},"labels":[],"label_agreement":null},{"id":"W3008308481","doi":"10.1101/2020.02.24.963553","title":"Synthesis of diagnostic quality cancer pathology images","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; William Osler Health System; Canada's Michael Smith Genome Sciences Centre; Brampton Civic Hospital; University of British Columbia","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Deep learning; Medical physics; Quality assurance; Set (abstract data type); Pattern recognition (psychology); Machine learning; Pathology; Medicine","score_opus":0.024305240626659484,"score_gpt":0.2627697601764269,"score_spread":0.2384645195497674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008308481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5165151,0.0058609624,0.460022,0.0053340527,0.0079003675,0.0014935815,0.00095570646,0.0018804626,0.00003780633],"genre_scores_gemma":[0.97497636,0.0011316824,0.0224895,0.00027120108,0.0004258548,0.0006333233,3.930101e-8,0.00007098447,0.000001068726],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9962645,0.0004816149,0.0007963706,0.0014454046,0.00052624167,0.00048587794],"domain_scores_gemma":[0.9950696,0.0011219659,0.000937846,0.0020806054,0.0005568472,0.0002331138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00081868476,0.0005000006,0.0008650791,0.00017078305,0.00010642486,0.0001527917,0.0018956544,0.000487131,0.00003138934],"category_scores_gemma":[0.002717409,0.0005584122,0.00022018164,0.00070915045,0.0002051635,0.0002728504,0.001611282,0.00075813784,0.000043132168],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003566095,0.00020177368,0.015555326,0.002008337,0.00033121457,0.00020414102,0.000056002715,0.00046288848,0.97542876,0.004233968,0.0012589666,0.00022294918],"study_design_scores_gemma":[0.00016391218,0.00004307092,0.18784265,0.00038762033,0.0000878826,1.6636367e-8,0.000001109283,0.0007504814,0.80928695,0.000033981334,0.00076742575,0.0006348669],"about_ca_topic_score_codex":0.00034277624,"about_ca_topic_score_gemma":0.0000066089765,"teacher_disagreement_score":0.45846128,"about_ca_system_score_codex":0.00039453126,"about_ca_system_score_gemma":0.00092260673,"threshold_uncertainty_score":0.9996867},"labels":[],"label_agreement":null},{"id":"W3008562940","doi":"10.48550/arxiv.2002.08438","title":"Fine tuning U-Net for ultrasound image segmentation: which layers?","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Segmentation; Speckle noise; Artificial intelligence; Artifact (error); Modality (human–computer interaction); Computer vision; Speckle pattern; Noise (video); Salient; Ultrasound; Layer (electronics); Image (mathematics); Pattern recognition (psychology); Geology; Materials science; Acoustics; Physics","score_opus":0.07502057494079693,"score_gpt":0.21276813243163534,"score_spread":0.1377475574908384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008562940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021425154,0.000030617393,0.97418886,0.0006935887,0.0011164105,0.00054368854,0.00004302667,0.000401186,0.0015574421],"genre_scores_gemma":[0.9665218,0.0000546468,0.032340948,0.00015256525,0.00027489284,0.000006741394,0.00005612327,0.000027914444,0.00056438334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980438,0.000089574154,0.00020463808,0.0012287336,0.000113941016,0.00031931174],"domain_scores_gemma":[0.99816865,0.00024835375,0.00029153787,0.00084460917,0.0002901678,0.00015668185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020145677,0.00029856563,0.0002841913,0.00016396232,0.00022489805,0.00024136098,0.0014134896,0.00021427755,0.000047158177],"category_scores_gemma":[0.00008446368,0.00038784067,0.0001674901,0.00078528863,0.000058236834,0.00063124223,0.00095097604,0.00047822075,0.00006812377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062306947,0.00034906075,0.0046187956,0.0019574026,0.0013139236,0.00094902585,0.0058976416,0.73463356,0.027094819,0.17588429,0.03851475,0.008163659],"study_design_scores_gemma":[0.0016048157,0.00028277573,0.00073596113,0.00014045919,0.00018377263,0.000027673823,0.00026756022,0.9137116,0.007887988,0.070537426,0.0035039005,0.0011160446],"about_ca_topic_score_codex":0.00008335038,"about_ca_topic_score_gemma":0.00014398353,"teacher_disagreement_score":0.9450966,"about_ca_system_score_codex":0.0004243199,"about_ca_system_score_gemma":0.00025881172,"threshold_uncertainty_score":0.99985737},"labels":[],"label_agreement":null},{"id":"W3011014312","doi":"10.1016/j.path.2020.01.002","title":"Unsupervised Machine Learning in Pathology","year":2020,"lang":"en","type":"review","venue":"Surgical pathology clinics","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"Brain Tumour Charity; Princess Margaret Cancer Foundation","keywords":"Workflow; Artificial intelligence; Computer science; Unsupervised learning; Deep learning; Machine learning; Pathology; Data science; Medicine; Database","score_opus":0.06632603134284286,"score_gpt":0.3633848483618555,"score_spread":0.2970588170190126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011014312","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013179636,0.9886011,0.0069820993,0.00038157724,0.0020594113,0.0004869561,0.000016056041,0.0004556803,0.0010039321],"genre_scores_gemma":[0.000033071483,0.9954455,0.0034856445,0.0002604408,0.00034891645,0.00012254146,0.00005824944,0.00006575591,0.00017988973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928624,0.0028976856,0.001648756,0.0016359295,0.000276673,0.0006785379],"domain_scores_gemma":[0.99621135,0.001954017,0.0006346223,0.00093590503,0.000058699556,0.00020539593],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0017920829,0.0006065603,0.0029609741,0.00037541828,0.00010772551,0.000054260992,0.0017337039,0.001499965,0.00006242883],"category_scores_gemma":[0.000626971,0.0005387505,0.00071953004,0.001360694,0.00021491281,0.00015405777,0.0011198086,0.003750696,0.00069079135],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008650794,0.000049415532,0.00007189359,0.0007492706,0.000017852537,0.011968307,0.00007794818,0.000013103924,5.949229e-8,0.0010112234,0.000027745224,0.98600453],"study_design_scores_gemma":[0.0005940374,0.00034348475,0.000010712302,0.00062015164,0.00006841847,0.002295248,0.000002627306,0.002566443,1.2831289e-7,0.00087127247,0.9921476,0.00047986506],"about_ca_topic_score_codex":0.0000044765593,"about_ca_topic_score_gemma":0.0000139516405,"teacher_disagreement_score":0.99211985,"about_ca_system_score_codex":0.00021493917,"about_ca_system_score_gemma":0.0005050798,"threshold_uncertainty_score":0.9997963},"labels":[],"label_agreement":null},{"id":"W3011527702","doi":"10.3390/ijerph17061982","title":"Modeling the Research Landscapes of Artificial Intelligence Applications in Diabetes (GAPRESEARCH)","year":2020,"lang":"en","type":"article","venue":"International Journal of Environmental Research and Public Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Diabetes mellitus; Latent Dirichlet allocation; Artificial intelligence; Medicine; Diabetes management; Data science; Computer science; Type 2 diabetes; Topic model","score_opus":0.20093691950247503,"score_gpt":0.41967941402196696,"score_spread":0.21874249451949193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011527702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64938915,0.0022350112,0.23402864,0.113600746,0.00011768529,0.00043621782,0.000020997444,0.000007905898,0.00016366136],"genre_scores_gemma":[0.9968417,0.0016756969,0.0010986058,0.00014881357,0.00020893132,0.000015427036,0.0000016945298,0.000005479985,0.000003618127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644154,0.0005711024,0.00050249667,0.00019712163,0.0018931468,0.0003945909],"domain_scores_gemma":[0.9984788,0.00072502054,0.00010589753,0.00015768662,0.00024203713,0.00029055984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005952217,0.00005886502,0.00012485604,0.00044717852,0.00017513485,0.00018776892,0.0014853828,0.00003307343,0.000033947417],"category_scores_gemma":[0.00044219493,0.000043618234,0.00003431466,0.00056361285,0.00025962252,0.0005006756,0.0005821583,0.00083901134,0.0000065288773],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110772264,0.0008087899,0.011954637,0.00005827862,0.000082269566,0.000012668254,0.0071285786,0.0034959647,0.0036559382,0.039714217,0.00030385208,0.93267405],"study_design_scores_gemma":[0.00038810394,0.0023378509,0.008246705,0.00011650293,0.0000011321364,0.000028245162,0.010455275,0.8770777,0.003156525,0.08904714,0.008972965,0.00017186308],"about_ca_topic_score_codex":0.00010684368,"about_ca_topic_score_gemma":0.000044593813,"teacher_disagreement_score":0.93250215,"about_ca_system_score_codex":0.00029061607,"about_ca_system_score_gemma":0.0003899605,"threshold_uncertainty_score":0.36451334},"labels":[],"label_agreement":null},{"id":"W3011545441","doi":"10.1111/ajt.15850","title":"Banff Digital Pathology Working Group: Going digital in transplant pathology","year":2020,"lang":"en","type":"article","venue":"American Journal of Transplantation","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Digital pathology; Medicine; Standardization; Pathology; Medical physics; Computer science","score_opus":0.011719212363089095,"score_gpt":0.21854024224649463,"score_spread":0.20682102988340553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011545441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4486058,0.00006627779,0.5498935,0.0009541705,0.00021557021,0.000049434966,0.00000899705,0.000031424097,0.00017479347],"genre_scores_gemma":[0.9923265,0.00029507314,0.006788801,0.00042033632,0.00014281632,0.000002744998,0.000008490415,0.000014038371,0.0000012114798],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985154,0.000100369645,0.00057672616,0.00027269646,0.00027170894,0.00026305643],"domain_scores_gemma":[0.99912,0.00017858729,0.00041964208,0.00011273731,0.00004486156,0.0001241695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019553545,0.00015328101,0.00032702062,0.0002116484,0.0000428334,0.0001487026,0.00046638152,0.00004771439,0.0000028138134],"category_scores_gemma":[0.000019290206,0.00014885106,0.00011131212,0.00060437096,0.00011643937,0.0013620025,0.000014792603,0.0003525479,0.00000991245],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007988546,0.00008987054,0.04929431,0.000057586476,0.00004490798,0.004805632,0.018117059,0.0022374566,0.0052137566,0.0004934886,0.000013491463,0.91883355],"study_design_scores_gemma":[0.03548686,0.050001435,0.5746272,0.005715313,0.00075880036,0.1367572,0.009887431,0.12676553,0.030837359,0.014079832,0.007880327,0.007202672],"about_ca_topic_score_codex":0.000004521771,"about_ca_topic_score_gemma":0.0000096165095,"teacher_disagreement_score":0.9116309,"about_ca_system_score_codex":0.000070329006,"about_ca_system_score_gemma":0.00005729821,"threshold_uncertainty_score":0.606997},"labels":[],"label_agreement":null},{"id":"W3012745096","doi":"10.1101/2020.03.17.994210","title":"Validating a semi-quantitative method to assess the degree of methylene blue staining in sentinel lymph nodes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Staining; Stain; Lymph; Kappa; Medicine; Methylene blue; Pathology; Cohen's kappa; Sentinel lymph node; Nuclear medicine; Mathematics; Chemistry; Statistics; Internal medicine; Geometry","score_opus":0.1020939532917445,"score_gpt":0.31903564110138644,"score_spread":0.21694168780964193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012745096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.244222,0.00026787433,0.7531534,0.0008636737,0.000621416,0.0005495947,0.000036012047,0.00027115387,0.000014866012],"genre_scores_gemma":[0.60723174,0.00002141076,0.39208505,0.00027449641,0.00012362564,0.00020194064,5.990987e-8,0.00006086587,8.22785e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949399,0.0011492105,0.0009769034,0.0015311323,0.00077911007,0.00062372605],"domain_scores_gemma":[0.99529034,0.0010171956,0.0009601136,0.0017615387,0.000755563,0.00021522459],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036641886,0.0005771232,0.00085491023,0.0004916521,0.0001734569,0.0003979466,0.0024255018,0.00033168588,0.000005499475],"category_scores_gemma":[0.0012691211,0.00054748665,0.0001883365,0.0024949114,0.000084688,0.00039092675,0.0027680662,0.0009507102,0.000015053483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041569092,0.000076948054,0.008154604,0.0005821946,0.00024629905,0.000055281074,0.000651603,0.013740921,0.96729004,0.009013375,0.00003571108,0.000111435475],"study_design_scores_gemma":[0.00048686974,0.000048495975,0.073068105,0.0009148134,0.0000803021,4.9719116e-8,0.00009089377,0.11904383,0.8051378,0.00006366685,0.00021984123,0.00084530615],"about_ca_topic_score_codex":0.00026794922,"about_ca_topic_score_gemma":0.0000040484124,"teacher_disagreement_score":0.36300972,"about_ca_system_score_codex":0.00060496206,"about_ca_system_score_gemma":0.0010661174,"threshold_uncertainty_score":0.9996977},"labels":[],"label_agreement":null},{"id":"W3012882457","doi":"10.32768/abc.20207122-28","title":"Accurate Detection of Breast Cancer Metastasis Using a Hybrid Model of Artificial Intelligence Algorithm","year":2020,"lang":"en","type":"article","venue":"Archives of Breast Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Breast cancer; Computer science; Artificial intelligence; Algorithm; Metastasis; Cancer; Machine learning; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.05170118406221385,"score_gpt":0.2915836875612417,"score_spread":0.23988250349902784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012882457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042926956,0.00028854917,0.954423,0.0007234738,0.0002819203,0.00020427775,0.0010689383,0.000050604092,0.00003224705],"genre_scores_gemma":[0.9492762,0.00024678293,0.050170437,0.00008040837,0.00016594256,0.000032602507,0.0000013470543,0.000023331986,0.0000029653527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979644,0.000094907715,0.0006773168,0.0005262815,0.00043016172,0.00030696017],"domain_scores_gemma":[0.99849737,0.000088687346,0.00065823284,0.00041064815,0.00020755826,0.00013749834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012310798,0.00023031901,0.00045599043,0.00020331563,0.000076212564,0.000024134348,0.0007284369,0.000040008224,0.000033727945],"category_scores_gemma":[0.000013105245,0.00023325568,0.0002059476,0.00067102164,0.00028215756,0.0005512117,0.00031134515,0.00019321273,0.000001130154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017342543,0.00004150232,0.00004467131,0.00010765391,0.00009522368,9.437909e-7,0.00090973824,0.1355874,0.18573585,0.00016948087,0.0000029878736,0.6771311],"study_design_scores_gemma":[0.0000913697,0.000049953367,0.00074124866,0.00010461226,0.00005174805,0.000027356127,0.00005280937,0.688767,0.30805206,0.001912316,0.000004756768,0.00014473315],"about_ca_topic_score_codex":0.0024294748,"about_ca_topic_score_gemma":0.00011774607,"teacher_disagreement_score":0.90634924,"about_ca_system_score_codex":0.00008414436,"about_ca_system_score_gemma":0.00040322889,"threshold_uncertainty_score":0.95118904},"labels":[],"label_agreement":null},{"id":"W3014394476","doi":"10.1007/978-3-030-50516-5_23","title":"Studying the Effect of Digital Stain Separation of Histopathology Images on Image Search Performance","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Histopathology; Stain; RGB color model; Artificial intelligence; Digital image; Computer science; Digital pathology; Grayscale; Pattern recognition (psychology); Computer vision; Image (mathematics); Image processing; Pathology; Staining; Medicine","score_opus":0.01936835830922021,"score_gpt":0.30073635603740817,"score_spread":0.28136799772818794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014394476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30794376,0.00007338441,0.68974704,0.0006950219,0.00096515904,0.00048622346,0.0000054305183,0.000052560463,0.000031458305],"genre_scores_gemma":[0.9557592,0.000012172555,0.043943644,0.00008952654,0.00015187374,0.000028885288,0.0000019866707,0.0000120993445,6.1208243e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664694,0.000321436,0.00051028014,0.001106344,0.0010077772,0.0004071959],"domain_scores_gemma":[0.9969909,0.0010230812,0.00038678857,0.0013039497,0.00023538136,0.000059905473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001836704,0.00032325787,0.000505846,0.00042716894,0.00017255468,0.0003079747,0.003309629,0.00014038583,0.0000013403821],"category_scores_gemma":[0.00029887387,0.00023382012,0.0001136547,0.001483883,0.0009297264,0.00061237364,0.0030565355,0.0010095523,0.0000049563855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008026936,0.000043382148,0.005995572,0.00041943407,0.000009529977,0.000017471919,0.0038611335,0.41907445,0.014233322,0.00005149131,0.000011031683,0.55620295],"study_design_scores_gemma":[0.00022777909,0.0015296937,0.0072871796,0.00017490923,0.000006227162,0.000015371632,0.0000011138948,0.7171179,0.27187902,0.0015551978,0.0000039148467,0.00020168492],"about_ca_topic_score_codex":0.000030387388,"about_ca_topic_score_gemma":0.0000038563785,"teacher_disagreement_score":0.64781547,"about_ca_system_score_codex":0.00035078026,"about_ca_system_score_gemma":0.0003987715,"threshold_uncertainty_score":0.95349073},"labels":[],"label_agreement":null},{"id":"W3015450039","doi":"10.1109/tmi.2020.2986331","title":"ANHIR: Automatic Non-Rigid Histological Image Registration Challenge","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Russian Science Foundation; Narodowe Centrum Nauki; Grantová Agentura České Republiky; Ministerstvo Školství, Mládeže a Tělovýchovy; National Cancer Institute; National Institutes of Health; Ministerio de Economía y Competitividad; Academy of Finland; Compute Canada","keywords":"Image registration; Landmark; Artificial intelligence; Computer science; Computer vision; Image (mathematics); Diagonal; Pattern recognition (psychology); Mathematics","score_opus":0.023081953823145773,"score_gpt":0.27363807566345166,"score_spread":0.2505561218403059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015450039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088806276,0.00005355835,0.94593775,0.04889706,0.0010189501,0.00018102015,0.0000019165584,0.0007984486,0.0022232495],"genre_scores_gemma":[0.9723686,0.0000711985,0.023724578,0.0035131264,0.00020015497,0.000057022775,9.0274807e-7,0.000018351919,0.000046040946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976706,0.000106689375,0.0004012832,0.0006013932,0.00088218943,0.00033783153],"domain_scores_gemma":[0.99884623,0.00014859652,0.0001087964,0.0004104658,0.00006431453,0.00042159003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030961304,0.00020341539,0.00023120466,0.00010099235,0.00025166702,0.000119855955,0.00071073044,0.000114538765,0.0003675455],"category_scores_gemma":[0.000060839775,0.00019216261,0.00012996631,0.00044539996,0.0001865404,0.0007163569,0.000006411768,0.00069655123,0.00028369357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022468106,0.00025097467,0.000007577319,0.00010035431,0.000033819448,0.00029207012,0.0015232507,0.00041210197,0.003361199,0.00036007757,0.004616973,0.98901916],"study_design_scores_gemma":[0.00059308915,0.00016659246,0.00006495114,0.00006877107,0.000019939785,0.000095129064,0.000063869324,0.9899864,0.0057130144,0.00041902452,0.0025532562,0.0002559245],"about_ca_topic_score_codex":0.000026936581,"about_ca_topic_score_gemma":0.000010043583,"teacher_disagreement_score":0.9895743,"about_ca_system_score_codex":0.00018024196,"about_ca_system_score_gemma":0.00017841521,"threshold_uncertainty_score":0.78361636},"labels":[],"label_agreement":null},{"id":"W3015579574","doi":"10.2196/18251","title":"Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"McNemar's test; Medicine; CAD; Radiology; Breast imaging; Receiver operating characteristic; Ultrasound; Computer-aided diagnosis; Breast MRI; Prospective cohort study; Single Center; Breast cancer; Mammography; Surgery; Internal medicine; Mathematics; Cancer","score_opus":0.04075394251272753,"score_gpt":0.3238627744901269,"score_spread":0.2831088319773994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015579574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66845095,0.000024043215,0.32792306,0.0012343236,0.00029679106,0.0018168997,0.000029464307,0.000060199007,0.00016428412],"genre_scores_gemma":[0.9875309,0.0000059881013,0.011899299,0.00032927922,0.000038064234,0.0001878203,0.0000030162755,0.000005255959,3.951657e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965867,0.00042003748,0.00077457546,0.00014589433,0.0019116307,0.0001611972],"domain_scores_gemma":[0.9985308,0.00032496138,0.00040999486,0.0003328141,0.00028881847,0.000112617454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001490318,0.00012762852,0.00027279678,0.00009375219,0.000048330538,0.000029464358,0.0007703862,0.00009169013,0.000025806406],"category_scores_gemma":[0.00019804286,0.000091170674,0.000078427576,0.0010114406,0.000100544916,0.00039776723,0.00023971614,0.00027045855,0.0000024737508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000488043,0.0030923604,0.36576042,0.00030439446,0.00020399908,0.00000154417,0.10298772,0.0016056839,0.00014244697,0.00025512176,0.003499897,0.52209765],"study_design_scores_gemma":[0.0033414944,0.0010788492,0.12788673,0.00033125983,0.00007064567,0.000027595248,0.00328321,0.86029124,0.0029556337,0.0003604174,0.00014417643,0.00022876557],"about_ca_topic_score_codex":0.00004815666,"about_ca_topic_score_gemma":0.0000484807,"teacher_disagreement_score":0.85868555,"about_ca_system_score_codex":0.00010401007,"about_ca_system_score_gemma":0.00017200821,"threshold_uncertainty_score":0.37178323},"labels":[],"label_agreement":null},{"id":"W3015943301","doi":"10.1109/ijcnn48605.2020.9206833","title":"Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Linear discriminant analysis; MNIST database; Pattern recognition (psychology); Discriminant; Artificial intelligence; Subspace topology; Computer science; Metric (unit); Artificial neural network; Feature (linguistics); Kernel Fisher discriminant analysis; Multiple discriminant analysis; Feature extraction; Fisher kernel; Mathematics; Engineering","score_opus":0.058247174890906306,"score_gpt":0.2528135293446994,"score_spread":0.1945663544537931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015943301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017980924,0.00011914286,0.99002653,0.0064985324,0.00025278504,0.0002363079,0.0000022192894,0.00012346833,0.00094292907],"genre_scores_gemma":[0.9735511,0.000016451098,0.02376711,0.002271698,0.00022891,0.0000409627,8.3817804e-7,0.000008056627,0.00011487734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992928,0.000018382027,0.00011989783,0.0002986196,0.000078198864,0.00019208761],"domain_scores_gemma":[0.99955726,0.00016991812,0.00004246174,0.00010114106,0.000033946646,0.00009525038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009137542,0.00008884262,0.00013136784,0.000015744208,0.00008076019,0.0001167918,0.00018407425,0.000037805326,0.000011640122],"category_scores_gemma":[0.00006665813,0.00007246559,0.00003292014,0.00013122763,0.000039738195,0.00031479436,0.00007015228,0.00007031456,0.0000013065631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017662397,0.000028233284,0.00044935473,0.00006026985,0.00006760177,0.000013590508,0.012000386,0.0018356406,0.00070606713,0.028944526,0.02740597,0.92831177],"study_design_scores_gemma":[0.0006717168,0.0003481904,0.0009290822,0.000011877778,0.000010103054,0.000007224382,0.00048903865,0.9845156,0.00063102914,0.001086668,0.011145163,0.00015430883],"about_ca_topic_score_codex":0.000011916632,"about_ca_topic_score_gemma":0.000018195651,"teacher_disagreement_score":0.98267996,"about_ca_system_score_codex":0.000017585515,"about_ca_system_score_gemma":0.000029041232,"threshold_uncertainty_score":0.2955061},"labels":[],"label_agreement":null},{"id":"W3016423692","doi":"","title":"Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening.","year":2020,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Dropout (neural networks); Artificial neural network; Computer science; Task (project management); Artificial intelligence; Deep learning; Modality (human–computer interaction); Process (computing); Breast cancer; Machine learning; Deep neural networks; Cancer; Medicine; Engineering","score_opus":0.03285758993667223,"score_gpt":0.21859279806680593,"score_spread":0.1857352081301337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016423692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19584657,0.000048309048,0.7988594,0.004013008,0.00036527234,0.0007803659,0.00001989647,0.000058578742,0.000008588184],"genre_scores_gemma":[0.99437135,0.0000031031532,0.0026507087,0.0019935123,0.00008104367,0.00089363573,0.000002239573,0.0000040788277,3.127876e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990185,0.0000948878,0.00028502187,0.00018792602,0.00019818959,0.00021547385],"domain_scores_gemma":[0.9992548,0.00015382997,0.00015291793,0.0003074255,0.000047555455,0.0000834236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030276424,0.00007890686,0.00011269127,0.000036190664,0.00006067509,0.00009735752,0.00051924377,0.000029762245,0.0000088575935],"category_scores_gemma":[0.00013648538,0.00006403458,0.000037649916,0.00055958645,0.000019839741,0.0012956843,0.00034050338,0.00017470957,7.5435287e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004477367,0.000004313382,0.047991745,0.000004414762,0.0000034077148,1.441069e-7,0.0010009973,0.084132485,0.000027086879,0.0000036864358,0.000048453192,0.8667385],"study_design_scores_gemma":[0.00011436862,0.000004389704,0.48825356,8.267637e-7,0.0000014418606,3.0617446e-7,0.000019769026,0.5111856,0.00004961592,0.000004280883,0.00032751315,0.000038311187],"about_ca_topic_score_codex":0.0066016996,"about_ca_topic_score_gemma":0.0008515348,"teacher_disagreement_score":0.8667002,"about_ca_system_score_codex":0.00012089894,"about_ca_system_score_gemma":0.000011947226,"threshold_uncertainty_score":0.99798393},"labels":[],"label_agreement":null},{"id":"W3016759068","doi":"10.2196/17364","title":"Predicting Breast Cancer in Chinese Women Using Machine Learning Techniques: Algorithm Development","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Machine learning; Breast cancer; Random forest; Artificial intelligence; Logistic regression; Receiver operating characteristic; Algorithm; Artificial neural network; Medicine; Computer science; Area under curve; Cancer; Internal medicine","score_opus":0.012479042026264297,"score_gpt":0.2835731275679739,"score_spread":0.2710940855417096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016759068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30466777,0.000045358363,0.6928104,0.0010240284,0.00024304676,0.00035400916,0.000006063327,0.0006274451,0.0002218376],"genre_scores_gemma":[0.48259923,0.00011212198,0.51169884,0.004442472,0.0006544399,0.0004123554,0.000007802018,0.000041470525,0.000031267144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997842,0.000044008622,0.00069688127,0.00016145586,0.0008511379,0.00040448227],"domain_scores_gemma":[0.9991628,0.000049072365,0.00022186372,0.00015607281,0.000058621652,0.00035160244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005450815,0.00017964604,0.0002397712,0.00013023593,0.00012354259,0.00008619085,0.00063796574,0.00014825405,0.000104881874],"category_scores_gemma":[0.000077902645,0.00015291845,0.000027587324,0.0008825269,0.000045044715,0.0008196764,0.0005156416,0.0007476508,0.00001269822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010392063,0.000033264954,0.024177017,0.00019870642,0.000020477015,0.000016993275,0.061897635,0.00045985027,0.00004972126,0.000011826312,0.00002495866,0.91309917],"study_design_scores_gemma":[0.00033996394,0.000044577733,0.0017808586,0.00017158808,0.0000011146001,0.000060309754,0.0005351421,0.9941911,0.00028596874,0.000022352611,0.0023829371,0.00018405683],"about_ca_topic_score_codex":0.000081220714,"about_ca_topic_score_gemma":0.000023713665,"teacher_disagreement_score":0.99373126,"about_ca_system_score_codex":0.00058117654,"about_ca_system_score_gemma":0.00047781886,"threshold_uncertainty_score":0.6235834},"labels":[],"label_agreement":null},{"id":"W3016852577","doi":"10.1109/cvprw50498.2020.00502","title":"Representation Learning of Histopathology Images using Graph Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pooling; Computer science; Histopathology; Artificial intelligence; Pattern recognition (psychology); Graph; Lung cancer; Convolutional neural network; Adenocarcinoma; Representation (politics); Digital pathology; Pathology; Cancer; Medicine; Theoretical computer science","score_opus":0.050435083382192596,"score_gpt":0.30784924489980764,"score_spread":0.25741416151761504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016852577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0124687,0.00031940293,0.98346275,0.00046184304,0.0020522424,0.00016695356,5.8085385e-7,0.000287564,0.0007799619],"genre_scores_gemma":[0.8984425,0.00005342368,0.10109289,0.00010157665,0.00021400003,0.000011206671,0.0000056392737,0.000015833772,0.00006293162],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829143,0.0002688866,0.00036622924,0.0006789585,0.00021222966,0.00018226414],"domain_scores_gemma":[0.9987408,0.00007876352,0.00047056246,0.00053849607,0.00012273598,0.00004865024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020492275,0.00017129644,0.00031823103,0.00015837495,0.00007479326,0.0000716467,0.00066246383,0.0001911689,0.000012733069],"category_scores_gemma":[0.00006548102,0.00018582617,0.0001489067,0.0003913677,0.00007745467,0.00021272115,0.0014643014,0.0007631797,0.0000014522577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000117313275,0.000009091133,0.0028737972,0.000058145903,0.000013981788,0.00002295976,0.00038489143,0.96185446,0.004579272,0.0010060803,0.00024860117,0.028936975],"study_design_scores_gemma":[0.00008220548,0.000053900065,0.0028995026,0.000021274518,0.000017507993,0.000027494043,0.000017627926,0.98949176,0.0025711614,0.004627203,0.000030553812,0.00015980424],"about_ca_topic_score_codex":0.00041604775,"about_ca_topic_score_gemma":0.0000051142847,"teacher_disagreement_score":0.8859738,"about_ca_system_score_codex":0.00010379201,"about_ca_system_score_gemma":0.00005666302,"threshold_uncertainty_score":0.7577771},"labels":[],"label_agreement":null},{"id":"W3018308144","doi":"10.1111/tbj.13858","title":"Review of the current state of digital image analysis in breast pathology","year":2020,"lang":"en","type":"article","venue":"The Breast Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto","funders":"","keywords":"Digital pathology; Workflow; Medicine; Grading (engineering); Digital image analysis; Medical physics; Data science; Pathology; Computer science; Computer vision","score_opus":0.014253482689446352,"score_gpt":0.2627208368352065,"score_spread":0.24846735414576013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018308144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15437883,0.04418249,0.6742896,0.12386585,0.0014002649,0.0007035572,0.0003106758,0.00006510876,0.0008036682],"genre_scores_gemma":[0.99656177,0.0027549753,0.00026509017,0.0003362709,0.00007198272,0.0000017574055,3.953456e-7,0.000004585332,0.0000031503582],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988333,0.00021237454,0.0004200513,0.00012549687,0.00027207905,0.00013667892],"domain_scores_gemma":[0.99898803,0.000039740953,0.00044900234,0.00032713125,0.00014405712,0.000052025185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005324543,0.00007903439,0.00023994014,0.000066887456,0.00004474959,0.000042665943,0.0009934093,0.000008846586,0.0000146529155],"category_scores_gemma":[0.000031089006,0.000042779324,0.00021044009,0.0013289356,0.00010121599,0.00029037302,0.00026332992,0.000336201,0.000004529914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029108143,0.00005504156,0.007362209,0.00029420038,0.00010442946,0.000009717694,0.00075830455,0.00039039482,0.0003978688,0.000044658467,0.0006349224,0.9899191],"study_design_scores_gemma":[0.0012588118,0.00023616749,0.93206275,0.004683419,0.0006622877,0.013065512,0.00006349638,0.033084378,0.001143892,0.011193227,0.0020557872,0.0004902713],"about_ca_topic_score_codex":0.0000043461364,"about_ca_topic_score_gemma":0.000003253234,"teacher_disagreement_score":0.9894289,"about_ca_system_score_codex":0.000040896397,"about_ca_system_score_gemma":0.00010713977,"threshold_uncertainty_score":0.18460183},"labels":[],"label_agreement":null},{"id":"W3021100205","doi":"10.1371/journal.pone.0240530","title":"How much off-the-shelf knowledge is transferable from natural images to pathology images?","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Computer science; Transfer of learning; Transferability; Artificial intelligence; Exploit; Deep learning; Machine learning; Metric (unit); Image (mathematics); Digital pathology; Reuse; Data science; Pattern recognition (psychology); Information retrieval","score_opus":0.03878594830679787,"score_gpt":0.2283006553058496,"score_spread":0.1895147069990517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021100205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3695866,0.005532787,0.33368674,0.2862763,0.0009945465,0.0009697523,0.00011679936,0.00086337514,0.0019730942],"genre_scores_gemma":[0.9609426,0.000100492696,0.03253888,0.004639925,0.0005239487,0.0000739241,0.0000037912416,0.000023509681,0.0011528842],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984916,0.000114088645,0.00016179647,0.00060603884,0.00029647668,0.00033001121],"domain_scores_gemma":[0.9989873,0.00013145391,0.000040736555,0.0005538465,0.00014595935,0.00014066829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110382505,0.00017586478,0.00025416713,0.00005093179,0.00015994727,0.0002552338,0.001026569,0.00007417758,0.000047562866],"category_scores_gemma":[0.000087068125,0.00015027494,0.000073944735,0.0004898304,0.000058186324,0.00050197035,0.00023016169,0.00035732676,0.00031228416],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059281265,0.00036282378,0.00023176408,0.00007647553,0.00017813068,0.000050742212,0.011206455,0.000003851018,0.8891422,0.00025410668,0.024572283,0.07386185],"study_design_scores_gemma":[0.00042433795,0.0002916442,0.0010140588,0.00003669875,0.000048776765,0.000004617164,0.000085694584,0.01104617,0.9804829,0.0011568562,0.005123903,0.00028438328],"about_ca_topic_score_codex":0.000029713729,"about_ca_topic_score_gemma":0.000019650784,"teacher_disagreement_score":0.59135604,"about_ca_system_score_codex":0.000069819915,"about_ca_system_score_gemma":0.000052264513,"threshold_uncertainty_score":0.6128034},"labels":[],"label_agreement":null},{"id":"W3021233705","doi":"10.1016/j.joca.2020.05.002","title":"Automating three-dimensional osteoarthritis histopathological grading of human osteochondral tissue using machine learning on contrast-enhanced micro-computed tomography","year":2020,"lang":"en","type":"article","venue":"Osteoarthritis and Cartilage","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"Seventh Framework Programme; KAUTE-Säätiö; Sigrid Juséliuksen Säätiö; Academy of Finland; Oulun Yliopisto; H2020 European Research Council; Helsingin Yliopisto","keywords":"Osteoarthritis; Grading (engineering); Computed tomography; Contrast (vision); Medicine; Biomedical engineering; Radiology; Nuclear medicine; Computer science; Artificial intelligence; Pathology; Engineering","score_opus":0.01646793862732827,"score_gpt":0.23494669562730164,"score_spread":0.21847875699997338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021233705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805736,0.0021216138,0.015726166,0.00021217116,0.00036156664,0.00038225608,0.000025780459,0.0003475661,0.00024926482],"genre_scores_gemma":[0.9884391,0.000008050991,0.0110063525,0.00030630094,0.00016150613,0.000019623956,0.000014981403,0.000032527456,0.000011577372],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974217,0.00022167072,0.00060327887,0.00082252745,0.0004504102,0.00048042613],"domain_scores_gemma":[0.9988998,0.0001150052,0.00034052174,0.00029948362,0.00010550002,0.00023964631],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025526315,0.000346022,0.00056878716,0.00016494811,0.00054319075,0.00015813393,0.00035534348,0.00016220068,0.00003759887],"category_scores_gemma":[0.000050810744,0.00037097753,0.00015297096,0.0004696749,0.0002064545,0.00040925285,0.00029363803,0.00046461183,0.0000073699525],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036544425,0.000024178335,0.00094919,0.000039850347,0.0000032266166,0.00010416134,0.00051569805,0.00025172316,0.9251073,0.0003139434,0.000009664282,0.072644524],"study_design_scores_gemma":[0.0025460927,0.004521649,0.0010137378,0.0004096928,0.000024190269,0.00020958734,0.00004477645,0.009876132,0.98033184,0.0002880808,0.00020449895,0.0005297183],"about_ca_topic_score_codex":0.000031698055,"about_ca_topic_score_gemma":0.0000952624,"teacher_disagreement_score":0.0721148,"about_ca_system_score_codex":0.00005654532,"about_ca_system_score_gemma":0.00003413619,"threshold_uncertainty_score":0.99987423},"labels":[],"label_agreement":null},{"id":"W3021454079","doi":"10.1007/s11548-020-02158-3","title":"Two-stage ultrasound image segmentation using U-Net and test time augmentation","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nuance Communications (Canada); Concordia University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Sørensen–Dice coefficient; Breast ultrasound; Computer science; Stage (stratigraphy); Artificial intelligence; Ultrasound; Image segmentation; Dice; Pattern recognition (psychology); Computer vision; Radiology; Medicine; Mammography; Breast cancer; Mathematics; Cancer","score_opus":0.023696613735899777,"score_gpt":0.28010226158510304,"score_spread":0.2564056478492033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021454079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4844085,0.0001178068,0.5126697,0.0018395693,0.00088082603,0.00004002823,0.0000052439186,0.00002153946,0.000016834842],"genre_scores_gemma":[0.91168404,0.00013614922,0.08529797,0.0020970749,0.0007577514,0.0000011270587,0.000007838865,0.000008259328,0.000009763382],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988128,0.00016683675,0.00045719178,0.00020376979,0.00024538249,0.00011399844],"domain_scores_gemma":[0.99781996,0.0013334565,0.00044928605,0.00006564764,0.00022732565,0.00010429765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041941172,0.00011530716,0.00023486573,0.0001996483,0.00007336295,0.00017865107,0.00023258364,0.00005469194,0.000018103496],"category_scores_gemma":[0.00011325305,0.0001098459,0.00007042248,0.0001190809,0.00009033402,0.00085734803,0.00007686522,0.00016484456,0.0000029745042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075659394,0.00022719002,0.12941569,0.000081982485,0.0013686976,0.001188189,0.0045647896,0.00509122,0.6002664,0.0011096745,0.008730654,0.2471989],"study_design_scores_gemma":[0.004081598,0.0007520049,0.2569915,0.00020018958,0.00011434692,0.01960925,0.00019461982,0.6954136,0.01930504,0.0006845652,0.0018971829,0.000756104],"about_ca_topic_score_codex":0.00000568442,"about_ca_topic_score_gemma":5.76355e-7,"teacher_disagreement_score":0.69032234,"about_ca_system_score_codex":0.00008199427,"about_ca_system_score_gemma":0.00008206276,"threshold_uncertainty_score":0.4479386},"labels":[],"label_agreement":null},{"id":"W3021508389","doi":"10.1109/jbhi.2020.2992878","title":"Multi-Task Pre-Training of Deep Neural Networks for Digital Pathology","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Innovation for Defence Excellence and Security","keywords":"Feature extraction; Digital pathology; Feature (linguistics); Pattern recognition (psychology); Deep learning; Artificial neural network; Feature selection; Scheme (mathematics)","score_opus":0.057539323955570654,"score_gpt":0.3197855143351173,"score_spread":0.26224619037954666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021508389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011223182,0.00029104023,0.98208034,0.0054980866,0.00077055127,0.00011210421,0.000006381207,0.000013791355,0.0000045200622],"genre_scores_gemma":[0.861075,0.00016360372,0.1347658,0.0035442894,0.0004427066,0.0000019065052,0.0000014095117,0.0000044742283,8.337837e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983728,0.000018078952,0.0010868993,0.000055060926,0.00024051119,0.00022664852],"domain_scores_gemma":[0.99845475,0.00010604243,0.00089691137,0.000071645496,0.000108331486,0.0003622927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057481596,0.00007880182,0.00029456546,0.00007886384,0.000068988666,0.00004392577,0.0002826583,0.00007949365,8.4311614e-7],"category_scores_gemma":[0.000080387974,0.000059852006,0.000061603525,0.00017931768,0.00010767487,0.0005339323,0.00005503279,0.00024632184,2.8942222e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046162364,0.000032907185,0.00013800415,0.00039788766,0.000019866173,0.0000048175834,0.014299765,0.0015160951,0.000023707657,0.000044267566,0.0007848499,0.98269165],"study_design_scores_gemma":[0.0008505839,0.0019115503,0.00042849532,0.00005053274,0.0000044497847,0.0002340942,0.0002925727,0.99347,0.000013533728,0.00011310795,0.0025742825,0.000056776647],"about_ca_topic_score_codex":0.0000010020613,"about_ca_topic_score_gemma":7.510245e-7,"teacher_disagreement_score":0.9919539,"about_ca_system_score_codex":0.000030058749,"about_ca_system_score_gemma":0.0001381686,"threshold_uncertainty_score":0.2440694},"labels":[],"label_agreement":null},{"id":"W3022955423","doi":"10.1007/s11548-020-02168-1","title":"Multiple instance learning combined with label invariant synthetic data for guiding systematic prostate biopsy: a feasibility study","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Prostate biopsy; Computer science; Prostate; Artificial intelligence; Health informatics; Data science; Medical physics; Machine learning; Medicine; Pathology; Internal medicine; Public health","score_opus":0.09503609136637572,"score_gpt":0.294972971465891,"score_spread":0.1999368800995153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022955423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2911621,0.00022922686,0.7051145,0.0019951118,0.0010223471,0.0004223346,0.000007330995,0.00004290107,0.0000041784847],"genre_scores_gemma":[0.97348386,0.000021187543,0.025879364,0.0003654929,0.00021448263,0.000015489357,0.0000068896243,0.000010595058,0.000002659957],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773085,0.00055764575,0.00078639603,0.0004205626,0.00033162662,0.00017290116],"domain_scores_gemma":[0.9960765,0.0021027909,0.0008272442,0.00031869646,0.0005660922,0.00010862802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019352909,0.00016163998,0.0005884869,0.0001814675,0.00012710803,0.00018947043,0.0010170323,0.00005580147,0.0000010820438],"category_scores_gemma":[0.0007772949,0.00012200715,0.000065994594,0.00020162766,0.000072997995,0.00070892036,0.00029265654,0.00021487814,6.477022e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014989763,0.0031109408,0.8842309,0.0054772403,0.009870834,0.0038598278,0.01372512,0.010253865,0.0034322515,0.0018033498,0.0050706677,0.04417525],"study_design_scores_gemma":[0.0039812825,0.0021261456,0.037054513,0.0015548975,0.00011519571,0.0039491556,0.00024932154,0.950225,0.00007297738,0.00018734176,0.00015520149,0.00032894287],"about_ca_topic_score_codex":0.000003825765,"about_ca_topic_score_gemma":0.0000041244994,"teacher_disagreement_score":0.93997115,"about_ca_system_score_codex":0.00008876354,"about_ca_system_score_gemma":0.00018437635,"threshold_uncertainty_score":0.49753073},"labels":[],"label_agreement":null},{"id":"W3023010843","doi":"10.1016/j.eururo.2020.04.010","title":"Re: Artificial Intelligence for Diagnosis and Grading of Prostate Cancer in Biopsies: A Population-based, Diagnostic Study","year":2020,"lang":"en","type":"letter","venue":"European Urology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Sinai Health System; Princess Margaret Cancer Centre; Toronto Metropolitan University; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Prostate cancer; Grading (engineering); Prostate; Gynecology; Cancer; Oncology; Radiology; Internal medicine","score_opus":0.045175037710329616,"score_gpt":0.2888313898830617,"score_spread":0.24365635217273207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023010843","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06270206,0.001336283,0.094459645,0.8324597,0.0036226015,0.0048253625,0.00020247349,0.00032076286,0.00007111365],"genre_scores_gemma":[0.90610653,0.00011546497,0.0010079135,0.09124051,0.0009067593,0.00052907947,0.00002093451,0.00006472165,0.000008095562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974129,0.00061345403,0.0006201783,0.00083519187,0.0001925516,0.00032570295],"domain_scores_gemma":[0.9968594,0.002259467,0.00037279603,0.0004039604,0.000063234074,0.00004116909],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038352713,0.0002577718,0.0003976582,0.0003201693,0.00007865558,0.00006409655,0.00061808474,0.00010899063,0.000009837965],"category_scores_gemma":[0.0007004167,0.0002713893,0.000060175025,0.0004152547,0.00008213144,0.0001095011,0.00022578405,0.0006274815,0.0000066886137],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003143575,0.0005712253,0.39419726,0.001358051,0.00025634078,0.0027073512,0.01413713,0.020280255,0.000024266465,0.00030997867,0.11591087,0.44993293],"study_design_scores_gemma":[0.0038567977,0.025430128,0.2462553,0.0013628597,0.0010681782,0.00005666831,0.00097115757,0.3461294,0.0024871628,0.03182447,0.3342142,0.0063437093],"about_ca_topic_score_codex":0.0003196868,"about_ca_topic_score_gemma":0.00049680925,"teacher_disagreement_score":0.8434045,"about_ca_system_score_codex":0.00008724771,"about_ca_system_score_gemma":0.00006675689,"threshold_uncertainty_score":0.99997383},"labels":[],"label_agreement":null},{"id":"W3023448049","doi":"10.1007/978-3-030-45385-5_25","title":"Cancer Detection Based on Image Classification by Using Convolution Neural Network","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Convolution (computer science); Artificial intelligence; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Contextual image classification; Image (mathematics)","score_opus":0.02783409588187205,"score_gpt":0.2607649675246651,"score_spread":0.23293087164279305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023448049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011219704,0.0002884173,0.99235815,0.0014711852,0.004416924,0.00052514364,0.0000103457405,0.00032006312,0.0004975649],"genre_scores_gemma":[0.83670723,0.000039828745,0.15686148,0.004195811,0.0020069277,0.00004420666,0.000012537566,0.00008107586,0.000050875184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580854,0.000086267224,0.00052176166,0.0018594066,0.0011008544,0.0006231696],"domain_scores_gemma":[0.9977204,0.00026943188,0.0005286958,0.001030227,0.0002667683,0.00018444657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005290997,0.000550953,0.00042727435,0.00044267206,0.00047371915,0.00053011137,0.0016638712,0.00038504734,0.000017280961],"category_scores_gemma":[0.000055061293,0.0005717467,0.00013553834,0.0010875774,0.000478838,0.0007978465,0.00036439722,0.001067936,0.000023419043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026082413,0.000012743865,0.000026478105,0.00002793111,0.0000063903103,0.000009502879,0.00006303917,0.4885868,0.007041803,0.00042318658,0.00008660479,0.5036894],"study_design_scores_gemma":[0.00025223874,0.000240463,0.00010671231,0.00022502085,0.000013600279,0.000011972187,7.706675e-8,0.9845042,0.006071245,0.0071871593,0.00083430303,0.00055297173],"about_ca_topic_score_codex":0.00009113205,"about_ca_topic_score_gemma":0.0000969307,"teacher_disagreement_score":0.83659506,"about_ca_system_score_codex":0.0017966413,"about_ca_system_score_gemma":0.0005516342,"threshold_uncertainty_score":0.9996734},"labels":[],"label_agreement":null},{"id":"W3023826944","doi":"10.1109/tmi.2020.2992108","title":"Class-Agnostic Weighted Normalization of Staining in Histopathology Images Using a Spatially Constrained Mixture Model","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Normalization (sociology); Artificial intelligence; Computer science; Pattern recognition (psychology); Stain; Computer vision; Cluster analysis; Pathology; Staining","score_opus":0.01773384363119628,"score_gpt":0.26508989427222096,"score_spread":0.24735605064102467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023826944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011091527,0.000051951123,0.9839987,0.003980166,0.000409926,0.0001570704,0.000007939698,0.00014918282,0.00015353026],"genre_scores_gemma":[0.9440179,0.000022146827,0.054560415,0.0013229682,0.00004182742,0.000011932872,0.0000013523281,0.000016323726,0.000005162718],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981734,0.0001512864,0.00047274726,0.00040899627,0.0005179273,0.0002756539],"domain_scores_gemma":[0.99916786,0.00018840161,0.00014343996,0.00021145264,0.000113545015,0.00017531047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029674656,0.00016273132,0.0002592204,0.00025544534,0.00009854115,0.000029795992,0.00038244223,0.0001089671,0.00004698355],"category_scores_gemma":[0.000095240444,0.0001736524,0.00006820906,0.0006793388,0.00020214332,0.00045891217,0.000007351599,0.00050669175,0.0000029698704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010875181,0.00023778713,0.00034279143,0.00016589453,0.000023008668,0.00031676202,0.006633616,0.714082,0.0729625,0.0005906285,0.00006309373,0.2044732],"study_design_scores_gemma":[0.0007383183,0.00005496448,0.00003312853,0.00011864369,0.000018062634,0.000056283665,0.000043948967,0.9800154,0.018423129,0.00033175288,0.000018770977,0.00014759324],"about_ca_topic_score_codex":0.00007721277,"about_ca_topic_score_gemma":0.00003197412,"teacher_disagreement_score":0.93292636,"about_ca_system_score_codex":0.00021271862,"about_ca_system_score_gemma":0.00059846276,"threshold_uncertainty_score":0.7081339},"labels":[],"label_agreement":null},{"id":"W3024162587","doi":"10.1109/tbme.2020.2993278","title":"Optimizing Survival Analysis of XGBoost for Ties to Predict Disease Progression of Breast Cancer","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Breast cancer; Oncology; Medicine; Internal medicine; Disease; Survival analysis; Cancer","score_opus":0.015836345415356643,"score_gpt":0.2635330840708754,"score_spread":0.24769673865551875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024162587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00567995,0.00004190671,0.99142706,0.0015616033,0.0005952365,0.00021500247,0.0003496809,0.00012710472,0.0000024573965],"genre_scores_gemma":[0.9742083,0.00002577191,0.025519606,0.000046177476,0.0000676457,0.000112160014,0.0000026664381,0.00001310476,0.000004596486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988466,0.000013361529,0.00028789748,0.00027826353,0.0003954303,0.00017844391],"domain_scores_gemma":[0.9992288,0.00009795592,0.00006249583,0.0002031545,0.00008183876,0.00032578767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010954611,0.0001203368,0.00026535898,0.00037421947,0.00004143743,0.000014169459,0.0002996428,0.000055010514,0.000018117826],"category_scores_gemma":[0.000012880392,0.00011312498,0.00017558051,0.0017023149,0.00003900776,0.00013705739,0.000005370239,0.000106046995,5.9443425e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001407434,0.000085557134,0.00002449192,0.00018910588,0.0003786117,0.0000012791858,0.00051788264,0.9216834,0.01809649,0.00003684358,0.000031406966,0.058814216],"study_design_scores_gemma":[0.0002605716,0.00018970366,0.0007618119,0.00011618708,0.00021851392,3.831294e-7,0.000014973744,0.9807999,0.017242514,0.0000018003198,0.00027840785,0.00011521538],"about_ca_topic_score_codex":0.000024427398,"about_ca_topic_score_gemma":0.000004295951,"teacher_disagreement_score":0.96852833,"about_ca_system_score_codex":0.0000665354,"about_ca_system_score_gemma":0.00007242641,"threshold_uncertainty_score":0.46131027},"labels":[],"label_agreement":null},{"id":"W3028015151","doi":"10.1016/j.ins.2020.05.013","title":"A GPU-based residual network for medical image classification in smart medicine","year":2020,"lang":"en","type":"article","venue":"Information Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science; Convolutional neural network; Pooling; Artificial intelligence; Deep learning; Contextual image classification; Graphics processing unit; Pattern recognition (psychology); Dropout (neural networks); Residual; Set (abstract data type); Analytics; Residual neural network; Reduction (mathematics); Machine learning; Image (mathematics); Data mining; Algorithm","score_opus":0.058163718680216796,"score_gpt":0.3221192640737534,"score_spread":0.2639555453935366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028015151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017104435,0.000021001993,0.91765857,0.076542564,0.0004333845,0.00026893686,0.0000017710904,0.00012832407,0.003234985],"genre_scores_gemma":[0.8969859,0.000012347844,0.08581886,0.016562952,0.00046238358,0.0001327543,0.000014412881,0.000003721913,0.0000066747675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981886,0.000052300966,0.0004825199,0.0001974635,0.0008494217,0.00022967858],"domain_scores_gemma":[0.9991109,0.00028802757,0.00020120069,0.0001552035,0.00012600762,0.000118707925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019612934,0.00008203932,0.00011709911,0.0001489137,0.00019208131,0.00015816902,0.0008428685,0.00006484376,0.000038948983],"category_scores_gemma":[0.00090500765,0.00006703755,0.000023089779,0.0014622028,0.00025734687,0.002696437,0.000061015093,0.00010670039,0.000046753757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018709747,0.00005037804,0.008134752,0.00025235937,0.00001287024,0.000004089258,0.014709028,0.023504341,0.0006419475,0.13813472,0.19236639,0.622002],"study_design_scores_gemma":[0.00055209355,0.00023788704,0.0055944175,0.000038978003,0.0000013477044,0.00000197645,0.00019695716,0.9623416,0.00026104102,0.0018498227,0.028829742,0.0000941051],"about_ca_topic_score_codex":0.000053173637,"about_ca_topic_score_gemma":0.000052032716,"teacher_disagreement_score":0.9388373,"about_ca_system_score_codex":0.000059721384,"about_ca_system_score_gemma":0.00040168763,"threshold_uncertainty_score":0.2733712},"labels":[],"label_agreement":null},{"id":"W3028510827","doi":"10.17577/ijertv9is050444","title":"Breast Cancer Prediction using ML Techniques","year":2020,"lang":"en","type":"article","venue":"International Journal of Engineering Research and","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Breast cancer; Cancer; Medicine; Internal medicine","score_opus":0.05525081393954889,"score_gpt":0.35813352085132727,"score_spread":0.3028827069117784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028510827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08238138,0.00042710925,0.9100391,0.0063436036,0.00062998844,0.000058824622,0.000011480859,0.000057157988,0.000051353],"genre_scores_gemma":[0.9765609,0.000332619,0.021988561,0.000035675428,0.0010680625,0.0000022641877,1.4389425e-7,0.0000066697885,0.000005084533],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990608,0.0000151328795,0.00015402568,0.000094794916,0.0005680023,0.000107228],"domain_scores_gemma":[0.9990946,0.00004755575,0.000053416818,0.00004913663,0.00065030745,0.000104970844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032220062,0.000045072873,0.00006143746,0.00021457471,0.000028007333,0.00013433097,0.0004041867,0.000026245652,0.000009577764],"category_scores_gemma":[0.000057162797,0.000042022384,0.000021375936,0.00016770088,0.00002140311,0.00055045186,0.00012912479,0.0002757323,7.431929e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042531977,0.000116358744,0.010824207,0.00013122421,0.0005948331,0.00042554887,0.0017940131,0.06391268,0.4780154,0.00645807,0.00505204,0.43225032],"study_design_scores_gemma":[0.0005177911,0.00045423917,0.007130609,0.00035225006,0.0000054534776,0.0018658651,0.000028972907,0.9253658,0.053893007,0.0009924407,0.009242272,0.00015130157],"about_ca_topic_score_codex":0.00002350672,"about_ca_topic_score_gemma":3.4396302e-7,"teacher_disagreement_score":0.8941795,"about_ca_system_score_codex":0.00016422228,"about_ca_system_score_gemma":0.000081844795,"threshold_uncertainty_score":0.17136231},"labels":[],"label_agreement":null},{"id":"W3029272675","doi":"10.1038/s41379-020-0540-1","title":"Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media","year":2020,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Spinal Cord Injury BC","funders":"National Institute of General Medical Sciences; U.S. Department of Health and Human Services; National Cancer Institute; National Institutes of Health; Chiba University; Weill Cornell Medical College","keywords":"Pathology; Digital pathology; Social media; Medicine; Computer science; Artificial intelligence; World Wide Web","score_opus":0.03251994904213234,"score_gpt":0.2930630265485612,"score_spread":0.26054307750642886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029272675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1498045,0.000108932,0.84288454,0.0051886467,0.0005937848,0.00045797043,0.000022745851,0.00054237235,0.0003965087],"genre_scores_gemma":[0.9811791,0.000043388252,0.016071418,0.0017762197,0.00047963078,0.00020077752,0.00003385319,0.000055099492,0.00016048839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690956,0.00053475547,0.0003557069,0.0011521231,0.00030833718,0.00073951395],"domain_scores_gemma":[0.99853086,0.0005176617,0.00014172232,0.00043232198,0.00014248455,0.00023493626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004827597,0.0002855773,0.00044350277,0.00014020964,0.00034231224,0.000077773206,0.00084548024,0.0002490682,0.00005035327],"category_scores_gemma":[0.0004506659,0.00030609334,0.00013695947,0.00023894953,0.00016974859,0.00026090784,0.0004671943,0.0005422472,0.0003086797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082411984,0.00016196092,0.00037587454,0.000076040735,0.000037212296,0.0009060982,0.027969604,0.008383078,0.11773176,0.0014012016,0.0016717069,0.8404614],"study_design_scores_gemma":[0.0012692377,0.0008471352,0.004436469,0.0000129418995,0.000028128272,0.000057529734,0.00007947212,0.98140305,0.005087241,0.0043863864,0.0019274708,0.00046491862],"about_ca_topic_score_codex":0.000012286463,"about_ca_topic_score_gemma":0.000012493538,"teacher_disagreement_score":0.97302,"about_ca_system_score_codex":0.00014987456,"about_ca_system_score_gemma":0.00012222925,"threshold_uncertainty_score":0.99993914},"labels":[],"label_agreement":null},{"id":"W3033039186","doi":"10.1016/j.neucom.2020.05.070","title":"A survey on U-shaped networks in medical image segmentations","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Convolutional neural network; Computer science; Mechanism (biology); Artificial intelligence; Hyperintensity; Image segmentation; Pattern recognition (psychology); Image (mathematics); Artificial neural network; Machine learning; Magnetic resonance imaging; Medicine; Radiology","score_opus":0.03573220986309367,"score_gpt":0.29240481617822783,"score_spread":0.25667260631513417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033039186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050120935,0.00001127163,0.9441684,0.004376349,0.00042796816,0.0001572724,7.2184105e-7,0.00026294394,0.00047417817],"genre_scores_gemma":[0.9855249,0.000003952242,0.005336309,0.008871644,0.00023955516,0.0000059344507,0.0000024368371,0.000012240732,0.0000030586634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843544,0.00025468634,0.00025324285,0.00043677405,0.00036828517,0.00025155873],"domain_scores_gemma":[0.99911046,0.00045202623,0.0000745638,0.00018555386,0.00003167048,0.00014570661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003909552,0.00010639493,0.00012537157,0.000061075734,0.00009176425,0.00010044499,0.00058161246,0.00005427389,0.000017927137],"category_scores_gemma":[0.00025188865,0.00011445657,0.000031826803,0.00083903363,0.000021135282,0.00016207433,0.00027943173,0.00040935603,0.000044154964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103521925,0.00030659424,0.054667562,0.000061229555,0.00003136426,0.00079650484,0.0040589576,0.16861936,0.0026296452,0.0014901961,0.010262626,0.75697243],"study_design_scores_gemma":[0.0003032669,0.00008705882,0.09850425,0.000018561086,6.002186e-7,0.000004361371,0.0000036647123,0.9007314,0.00010263415,0.000018424675,0.00013711135,0.0000886734],"about_ca_topic_score_codex":0.00006344479,"about_ca_topic_score_gemma":0.000058997837,"teacher_disagreement_score":0.93883204,"about_ca_system_score_codex":0.000045264518,"about_ca_system_score_gemma":0.000061538114,"threshold_uncertainty_score":0.46674034},"labels":[],"label_agreement":null},{"id":"W3033108855","doi":"10.18280/isi.250216","title":"Revised Grey Wolf Optimized SVM-KNN Ensemble Based Automated Diagnosis of Breast Cancer","year":2020,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Support vector machine; Breast cancer; Pattern recognition (psychology); Computer science; Cancer; Medicine; Internal medicine","score_opus":0.01721738603898206,"score_gpt":0.24172404117507332,"score_spread":0.22450665513609125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033108855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039675534,0.00015609278,0.9533333,0.0020147925,0.00063732424,0.00076506956,0.00009027252,0.0018156584,0.0015119639],"genre_scores_gemma":[0.96544755,0.00008217295,0.032890618,0.0011850282,0.00007681167,0.00027214197,0.000025180974,0.000015346559,0.0000051697643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980957,0.000108923625,0.0008029952,0.00023258498,0.00045220793,0.00030759795],"domain_scores_gemma":[0.9981069,0.00011052027,0.00066145346,0.0004061284,0.00056128064,0.00015370219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003176637,0.00022526101,0.000360455,0.00021090287,0.00016937336,0.00026176666,0.00060183206,0.0001295013,0.000097792334],"category_scores_gemma":[0.00020535203,0.00022472232,0.00012024546,0.0012318965,0.00008821427,0.0041070688,0.00013114742,0.00014160384,0.00006299835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008716746,0.00015781687,0.013385073,0.0045082965,0.00034028233,0.000013346045,0.024765683,0.23976137,0.0035787544,0.0030668639,0.026555058,0.6829958],"study_design_scores_gemma":[0.0012033957,0.00012572117,0.007242263,0.00035493207,0.000025950703,0.0000126507575,0.00009486945,0.972719,0.016484953,0.0001601715,0.0012787936,0.00029726198],"about_ca_topic_score_codex":0.00024346015,"about_ca_topic_score_gemma":0.000006212441,"teacher_disagreement_score":0.925772,"about_ca_system_score_codex":0.00040034286,"about_ca_system_score_gemma":0.00028649165,"threshold_uncertainty_score":0.916391},"labels":[],"label_agreement":null},{"id":"W3033951167","doi":"10.1109/crv50864.2020.00022","title":"Histological Image Classification using Deep Features and Transfer Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Convolutional neural network; Transfer of learning; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Deep learning; Block (permutation group theory); Feature (linguistics); Feature extraction; Contextual image classification; Feature vector; Machine learning; Domain (mathematical analysis); Class (philosophy); Image (mathematics); Mathematics","score_opus":0.049088962439343846,"score_gpt":0.2665864291321732,"score_spread":0.21749746669282932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033951167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04541029,0.00012175791,0.94912845,0.0031397403,0.000063433836,0.000050910596,5.8014027e-8,0.00020314888,0.0018822179],"genre_scores_gemma":[0.92801714,0.000012371567,0.07138829,0.000494216,0.00004623232,0.0000022316947,2.6143687e-7,0.0000035218868,0.000035720546],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944067,0.000045124874,0.0000767871,0.00024884092,0.00009563186,0.00009297246],"domain_scores_gemma":[0.9998007,0.000026884527,0.000014229331,0.00007840757,0.00002308211,0.00005669348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058064335,0.000057853817,0.00006470961,0.000020165906,0.00010168267,0.000082059814,0.00013824207,0.0000460514,0.000021681864],"category_scores_gemma":[0.000025124647,0.000049692335,0.000018553172,0.00014565462,0.00003644325,0.00028755522,0.00003877231,0.00014780006,0.0000073060796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004380181,0.000026449852,0.0020201376,0.000048274043,0.000020462356,0.000019370646,0.004817378,0.0015152186,0.66050905,0.046090018,0.00070716505,0.28418267],"study_design_scores_gemma":[0.00018922401,0.00012049998,0.011242741,0.0000031787108,0.000006940704,0.000046022167,0.0001264283,0.97557896,0.009717752,0.00042606067,0.0023965838,0.00014561888],"about_ca_topic_score_codex":0.000011069346,"about_ca_topic_score_gemma":0.0000029488901,"teacher_disagreement_score":0.97406375,"about_ca_system_score_codex":0.00003815609,"about_ca_system_score_gemma":0.000012586895,"threshold_uncertainty_score":0.20263946},"labels":[],"label_agreement":null},{"id":"W3034319212","doi":"10.48550/arxiv.2006.06531","title":"A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Digitization; Network topology; Digital pathology; Telepathology; Workflow; Artificial intelligence; Identification (biology); Pattern recognition (psychology); Machine learning; Computer vision; Biology; Computer network","score_opus":0.20460934456640634,"score_gpt":0.2630195378859566,"score_spread":0.058410193319550274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034319212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62423384,0.00005528356,0.37358734,0.00010308796,0.0005523529,0.0006654807,0.000012596377,0.00009589199,0.0006941415],"genre_scores_gemma":[0.9944484,0.000028705414,0.005234657,0.000027994427,0.000040504925,0.000006603198,0.0000036455463,0.000008823014,0.00020063024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815375,0.00025624243,0.0002652102,0.0010300018,0.00006844662,0.00022632926],"domain_scores_gemma":[0.99849,0.00022192272,0.00035261936,0.000742728,0.00014316816,0.0000495584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021812611,0.00023217719,0.0005765217,0.0002725221,0.000063926076,0.000030485708,0.0013593406,0.00017618899,0.000005083611],"category_scores_gemma":[0.000029702078,0.00027874866,0.000113061964,0.00048892247,0.00016860334,0.00023060375,0.001583081,0.00040672944,0.000005784141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025266304,0.00335428,0.035153203,0.0011638504,0.0006124981,0.0046782624,0.045571428,0.70418763,0.0031890166,0.19184475,0.004376666,0.0033418078],"study_design_scores_gemma":[0.007889457,0.0057641556,0.07086059,0.0002109461,0.00032075573,0.00005951721,0.022431504,0.60084605,0.0033360396,0.28487456,0.0013736397,0.0020328027],"about_ca_topic_score_codex":0.00044064363,"about_ca_topic_score_gemma":0.00049640506,"teacher_disagreement_score":0.3702146,"about_ca_system_score_codex":0.00040438274,"about_ca_system_score_gemma":0.00016424328,"threshold_uncertainty_score":0.99996644},"labels":[],"label_agreement":null},{"id":"W3035509602","doi":"10.5121/csit.2020.100605","title":"Melanoma Detection in Histopathological Images using Deep Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Digital pathology; Pixel; Segmentation; Deep learning; Support vector machine; H&E stain; Pattern recognition (psychology); Image segmentation; Classifier (UML); Computer vision; Melanoma; Histopathological examination; Pathology; Medicine; Immunohistochemistry","score_opus":0.029827264481414106,"score_gpt":0.24818858402499738,"score_spread":0.2183613195435833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035509602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15186207,0.000057123834,0.8459138,0.00037898408,0.00015246564,0.000050094444,2.8785738e-8,0.00024530187,0.0013400823],"genre_scores_gemma":[0.9503189,0.000005061921,0.049302083,0.00027096705,0.00006781587,0.000004205585,8.2549676e-8,0.0000047276417,0.000026196494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992014,0.00009113032,0.00013377506,0.0003043239,0.00011931357,0.0001500538],"domain_scores_gemma":[0.99974984,0.000029997744,0.000044714936,0.00010567245,0.0000203678,0.00004942253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013862477,0.000072275514,0.00008997284,0.000058679358,0.00007262354,0.000053840122,0.0002188512,0.000052695217,0.00002662113],"category_scores_gemma":[0.00007460863,0.00006853914,0.00002821812,0.00039662814,0.000019587145,0.00034574387,0.00013326296,0.00021518685,0.000032795346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028028657,0.000025324478,0.0101127615,0.000017575838,0.0000034938491,0.00013654934,0.0016081874,0.013737415,0.24341533,0.0008360202,0.000020409007,0.7300589],"study_design_scores_gemma":[0.00019711444,0.00021682207,0.011877614,0.000004090612,0.000001924198,0.000055926615,0.00005835039,0.92701393,0.05903444,0.00045359673,0.0009351157,0.00015105803],"about_ca_topic_score_codex":0.00005183154,"about_ca_topic_score_gemma":0.000023596229,"teacher_disagreement_score":0.91327655,"about_ca_system_score_codex":0.0001528071,"about_ca_system_score_gemma":0.000012546429,"threshold_uncertainty_score":0.27949452},"labels":[],"label_agreement":null},{"id":"W3036501325","doi":"10.2196/18143","title":"Incorporating Breast Cancer Recurrence Events Into Population-Based Cancer Registries Using Medical Claims: Cohort Study","year":2020,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; Kaiser Permanente; American Cancer Society","keywords":"Medicine; Breast cancer; Cancer; Cohort; Oncology; Cancer recurrence; Cohort study; Population; Internal medicine; Cancer registry; Environmental health","score_opus":0.03432072456900001,"score_gpt":0.3464802537043374,"score_spread":0.3121595291353374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036501325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9085304,0.0007746171,0.069555864,0.015330378,0.0030846123,0.0020444095,0.00009932493,0.0005386425,0.00004173745],"genre_scores_gemma":[0.99346715,0.000073951065,0.0018077752,0.0019026349,0.001134769,0.0015415602,0.000007500713,0.000041997362,0.000022685499],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959777,0.00022764801,0.00065393676,0.0011135446,0.001575605,0.0004515755],"domain_scores_gemma":[0.99801135,0.00008515867,0.0005753722,0.000600377,0.00033858663,0.00038914732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041849609,0.0003646474,0.00046046317,0.00011676856,0.000436714,0.00015296458,0.001145339,0.00017868969,0.00036528838],"category_scores_gemma":[0.0000729579,0.00035884918,0.000097557204,0.0015452565,0.00009551185,0.0008273988,0.00033875817,0.0005306161,0.0000092147375],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006244529,0.000076634,0.9417015,0.00008546866,0.000067470995,0.000013742782,0.0008843538,0.008291015,0.00008029792,0.000048487298,0.0010379318,0.047650687],"study_design_scores_gemma":[0.0011955976,0.0001719123,0.6349976,0.0006223093,0.000064969994,0.000009924835,0.00014051728,0.3608268,0.0002770816,0.0003467635,0.00061557227,0.0007309372],"about_ca_topic_score_codex":0.035451297,"about_ca_topic_score_gemma":0.009383725,"teacher_disagreement_score":0.35253578,"about_ca_system_score_codex":0.0016527553,"about_ca_system_score_gemma":0.0020904073,"threshold_uncertainty_score":0.99988633},"labels":[],"label_agreement":null},{"id":"W3036832166","doi":"10.1038/s41598-020-66849-2","title":"Histologic tissue components provide major cues for machine learning-based prostate cancer detection and grading on prostatectomy specimens","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Western University","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada; Government of Canada","keywords":"Grading (engineering); Prostatectomy; Prostate cancer; Artificial intelligence; Computer science; Transfer of learning; Cancer detection; Deep learning; Digital pathology; Pattern recognition (psychology); Prostate; Machine learning; Cancer; Medicine","score_opus":0.02582360075406547,"score_gpt":0.25995924620297584,"score_spread":0.23413564544891036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036832166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73450994,0.0009090651,0.24356931,0.0051259995,0.010460306,0.0041131033,0.000015842857,0.0011630061,0.00013343527],"genre_scores_gemma":[0.9943578,0.0000062351205,0.004271616,0.00017514064,0.000097930635,0.00035130946,0.000017657783,0.000024905818,0.00069736864],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99727887,0.00008216939,0.0004319807,0.001338209,0.00047501508,0.00039377352],"domain_scores_gemma":[0.99866575,0.000065672735,0.00048059176,0.00043614395,0.00016869625,0.00018313786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069169886,0.00022665,0.00024091327,0.00018938618,0.0007325157,0.0004909806,0.00021985201,0.00006326196,0.000011819338],"category_scores_gemma":[0.00018425196,0.0002057038,0.000059007434,0.0006156038,0.00015794467,0.00039051307,0.000109825836,0.0002267157,0.000008045828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004248829,0.00016868488,0.013889153,0.0006411644,0.000062009734,0.00041691528,0.003742004,0.012993377,0.8206933,0.00008416747,0.0033226635,0.14356168],"study_design_scores_gemma":[0.0007587655,0.00090746174,0.0014198062,0.00008925336,0.00002770186,0.000088960616,0.000023513749,0.25294062,0.5593077,0.0021936863,0.18178673,0.0004557813],"about_ca_topic_score_codex":0.000120327466,"about_ca_topic_score_gemma":0.00013967772,"teacher_disagreement_score":0.2613856,"about_ca_system_score_codex":0.0002661314,"about_ca_system_score_gemma":0.00012388332,"threshold_uncertainty_score":0.8388357},"labels":[],"label_agreement":null},{"id":"W3037059984","doi":"10.1097/01.cot.0000470195.08621.80","title":"Seeking Ways to Improve Interpretation of Mammograms","year":2015,"lang":"en","type":"article","venue":"Oncology Times","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Epistemology; Psychology; Computer science; Philosophy; Programming language","score_opus":0.02302443355636791,"score_gpt":0.2930341767842796,"score_spread":0.2700097432279117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037059984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004699985,0.000043374097,0.96676964,0.00084032444,0.0012111174,0.00012531233,6.36772e-7,0.000096188865,0.026213443],"genre_scores_gemma":[0.8638263,0.0000014075991,0.1352316,0.00034861988,0.000077511206,0.000028410528,6.2155635e-7,0.000005727556,0.00047982702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934787,0.000038505725,0.00015677731,0.00020148946,0.0001229464,0.00013244514],"domain_scores_gemma":[0.99939334,0.00006869989,0.00009807165,0.00024696908,0.000117402866,0.000075540906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031476608,0.0000618692,0.00012911136,0.0000879783,0.00001817367,0.00001783946,0.00033932502,0.00007107716,0.000009669776],"category_scores_gemma":[0.00007318583,0.00005977459,0.000028342365,0.00022789932,0.00003249297,0.00020987405,0.00017262412,0.00007242261,0.00009436051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004852033,0.00004467768,0.00022623701,0.000008185562,0.000018855815,0.000004799925,0.004790986,0.0007673251,0.0072011584,0.007595661,0.0075058956,0.9717877],"study_design_scores_gemma":[0.0013999973,0.006390365,0.00081446895,0.000064928805,0.000033364147,0.00006648173,0.0005009784,0.6924301,0.06331458,0.04247584,0.19204685,0.000462094],"about_ca_topic_score_codex":0.00005295427,"about_ca_topic_score_gemma":0.000027975162,"teacher_disagreement_score":0.9713256,"about_ca_system_score_codex":0.00021394831,"about_ca_system_score_gemma":0.00014427841,"threshold_uncertainty_score":0.2437537},"labels":[],"label_agreement":null},{"id":"W3037731665","doi":"10.1016/j.media.2020.101757","title":"Yottixel – An Image Search Engine for Large Archives of Histopathology Whole Slide Images","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Hamilton Health Sciences; Toronto General Hospital; Jacobs (Canada); Northern Digital (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario","keywords":"Computer science; Search engine indexing; Digital pathology; Pixel; Information retrieval; Mosaic; Atlas (anatomy); Search engine; Image retrieval; Artificial intelligence; Computer vision; Image (mathematics); Biology","score_opus":0.015046636709015432,"score_gpt":0.2963813551718508,"score_spread":0.2813347184628354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037731665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005392466,0.00017669838,0.98400986,0.009654927,0.000077216566,0.00013262914,0.00005398196,0.00013323875,0.00036895994],"genre_scores_gemma":[0.6767409,0.00006410496,0.32082158,0.0015651438,0.0003596691,0.000055414675,0.000072840914,0.000027337433,0.00029303867],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976258,0.00024337422,0.0004330622,0.00065006013,0.0006242075,0.0004234513],"domain_scores_gemma":[0.9983828,0.000312198,0.00012207245,0.0006219155,0.00014678811,0.00041421686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007698418,0.00016515295,0.00051274884,0.00034962277,0.00010553442,0.00006181462,0.0011824353,0.000087801716,0.00023284588],"category_scores_gemma":[0.00070507976,0.00015268484,0.00035603816,0.0013345766,0.00022910425,0.0004686275,0.00035397868,0.00027748133,0.000024662018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023264396,0.0010172667,0.0042609023,0.0005717288,0.0012524547,0.00065239595,0.011597867,0.0005515531,0.5126089,0.0018482995,0.010470485,0.4549355],"study_design_scores_gemma":[0.0008043276,0.00038952174,0.00319775,0.000010820227,0.00034751708,0.000009664359,0.00014840357,0.9412728,0.04809556,0.0005291622,0.00495751,0.00023694447],"about_ca_topic_score_codex":0.00005744,"about_ca_topic_score_gemma":0.00003693903,"teacher_disagreement_score":0.9407213,"about_ca_system_score_codex":0.00003229098,"about_ca_system_score_gemma":0.00012853584,"threshold_uncertainty_score":0.62263066},"labels":[],"label_agreement":null},{"id":"W3039055707","doi":"10.1007/978-3-030-64556-4_26","title":"Offline Versus Online Triplet Mining Based on Extreme Distances of Histopathology Patches","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Online and offline; Generalization; Proxy (statistics); Artificial intelligence; Machine learning; Mathematics","score_opus":0.06415590714013483,"score_gpt":0.2905021397773382,"score_spread":0.22634623263720335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039055707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023213465,0.00030006882,0.9641947,0.004189572,0.0075051505,0.0003328163,0.00003091016,0.0002044312,0.000028878212],"genre_scores_gemma":[0.58669376,0.000011139841,0.41224873,0.00068261835,0.00032631253,0.000014699189,0.00000894543,0.000013424777,3.8841296e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953498,0.00021172648,0.00074390275,0.0020336155,0.0010777388,0.0005831723],"domain_scores_gemma":[0.996149,0.0011110754,0.00064249337,0.0017034567,0.00024179378,0.00015219652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008655192,0.0004969437,0.0007431619,0.00068948366,0.00014074675,0.00018069701,0.004032309,0.0002981731,0.00000657594],"category_scores_gemma":[0.0005926259,0.000475347,0.0001710569,0.0020542059,0.0007335204,0.00026480336,0.002016724,0.0010228422,0.0000029059397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019367074,0.0001623505,0.00071632426,0.00015027387,0.0000065235467,0.000074025105,0.0014191107,0.5165994,0.0018277778,0.0001074238,0.000019017978,0.4787241],"study_design_scores_gemma":[0.0008061523,0.0007579713,0.0027843008,0.00033706846,0.000009732721,0.000005476839,0.0000014935421,0.9819931,0.007706517,0.005027053,0.0001266097,0.00044451628],"about_ca_topic_score_codex":0.00007656606,"about_ca_topic_score_gemma":0.0002572525,"teacher_disagreement_score":0.56348026,"about_ca_system_score_codex":0.0006191965,"about_ca_system_score_gemma":0.0010735181,"threshold_uncertainty_score":0.9997698},"labels":[],"label_agreement":null},{"id":"W3039305869","doi":"10.1136/jclinpath-2020-206762","title":"Establishment of a remote diagnostic histopathology service using whole slide imaging (digital pathology)","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Workflow; Digital pathology; Histopathology; Service (business); Medicine; Medical physics; Operations management; Computer science; Pathology; Business; Engineering; Marketing; Database","score_opus":0.06732565157410773,"score_gpt":0.35218332599565144,"score_spread":0.2848576744215437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039305869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46160445,0.0006021126,0.5248623,0.010322275,0.0023009225,0.000105973224,0.0000072928624,0.00003801024,0.00015669828],"genre_scores_gemma":[0.8805982,0.00011365508,0.11230207,0.006174341,0.0007791104,9.209675e-7,0.00000104549,0.000023965711,0.000006674747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956628,0.0006181534,0.0024238687,0.00051988196,0.0003867688,0.0003885411],"domain_scores_gemma":[0.9945291,0.0016882733,0.002280514,0.00051565067,0.00067840214,0.00030805825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021333527,0.00022035393,0.0010364301,0.00019763436,0.00006564377,0.000057216424,0.0011936111,0.00023757723,0.000012295137],"category_scores_gemma":[0.0064398916,0.00020461976,0.00035716442,0.0005618298,0.0002646225,0.00087330444,0.0005569583,0.00095058075,0.000026861731],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078353053,0.00079776015,0.095696725,0.00026015696,0.00011100324,0.026164867,0.0042914734,0.004606624,0.037970517,0.0006101389,0.003131594,0.8255756],"study_design_scores_gemma":[0.022556117,0.018802224,0.29149684,0.0014932225,0.0010476606,0.08369447,0.0012752981,0.40786698,0.007731862,0.054742403,0.106143236,0.003149679],"about_ca_topic_score_codex":0.0000064448764,"about_ca_topic_score_gemma":0.0000031276184,"teacher_disagreement_score":0.82242596,"about_ca_system_score_codex":0.00009652901,"about_ca_system_score_gemma":0.00041111172,"threshold_uncertainty_score":0.83441514},"labels":[],"label_agreement":null},{"id":"W3040812295","doi":"10.1136/jclinpath-2020-206763","title":"Use of whole slide imaging (WSI) for distance teaching","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Distance education; Teleconference; Coronavirus disease 2019 (COVID-19); Medical education; Process (computing); West indies; Videoconferencing; Computer science; Medicine; Psychology; Multimedia; Sociology; Pathology; Mathematics education","score_opus":0.2390733598205427,"score_gpt":0.4864103414361558,"score_spread":0.2473369816156131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040812295","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032027908,0.49184874,0.5048142,0.0005766539,0.0025347623,0.00016432961,0.000014198647,0.0000143367215,0.000029540563],"genre_scores_gemma":[0.00007810759,0.8596207,0.13847342,0.00034105493,0.0013896605,0.000009261432,0.0000017460131,0.00003331608,0.000052749063],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99415064,0.001167365,0.0036573617,0.0004578309,0.00030450226,0.00026228942],"domain_scores_gemma":[0.98868054,0.0048631085,0.005462061,0.00054723845,0.000275022,0.00017204435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037520102,0.0002662534,0.0030586836,0.00017871079,0.00006545393,0.00006984234,0.0013823655,0.00030672224,0.0000020843065],"category_scores_gemma":[0.005755009,0.00020750884,0.0016302598,0.0002055615,0.00014986657,0.0005416307,0.00029859753,0.0018485402,0.000007264856],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021049036,0.000047954807,0.000037333117,0.0011274653,0.0000593347,0.00020349867,0.00003358226,0.000006618246,0.0000016257285,0.00071948825,0.0023366297,0.99540544],"study_design_scores_gemma":[0.0002971369,0.0004650022,0.000023008157,0.0029214376,0.00026033315,0.0008516559,0.0000032151963,0.0007692745,0.0000011588105,0.0013730404,0.99286485,0.0001699175],"about_ca_topic_score_codex":0.0000010978179,"about_ca_topic_score_gemma":0.0000013122402,"teacher_disagreement_score":0.9952355,"about_ca_system_score_codex":0.00009857139,"about_ca_system_score_gemma":0.00061893,"threshold_uncertainty_score":0.8461965},"labels":[],"label_agreement":null},{"id":"W3041755437","doi":"10.1109/icpr48806.2021.9412478","title":"Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Embedding; Prior probability; Computer science; Bayesian probability; MNIST database; Sampling (signal processing); Gibbs sampling; Subspace topology; Data mining; Artificial intelligence; Hierarchy; Bayesian network; Pattern recognition (psychology); Machine learning; Deep learning; Detector","score_opus":0.09326980976450137,"score_gpt":0.3227602744669691,"score_spread":0.2294904647024677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041755437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004669238,0.00027455643,0.9858865,0.00031091904,0.0054164147,0.0010812851,0.00001762865,0.0005611779,0.0017822678],"genre_scores_gemma":[0.4765153,0.000020663489,0.521662,0.0003844911,0.0011334284,0.0001132991,0.00007441088,0.000058627866,0.00003777932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956662,0.00024183643,0.0009895964,0.0016666586,0.00053643185,0.0008992634],"domain_scores_gemma":[0.9971717,0.0005021244,0.00067473674,0.0012488152,0.00021929597,0.00018334283],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019799923,0.0005871064,0.0007713104,0.00024745194,0.00056822924,0.0013885832,0.0015733879,0.0005182107,0.000108142034],"category_scores_gemma":[0.00016666681,0.000636391,0.0004833139,0.00050845864,0.00006269,0.0005794177,0.0020249302,0.0010164225,0.0000011283482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103157276,0.000092553964,0.00019634434,0.00044760594,0.00054254563,0.000027907727,0.005308105,0.49690536,0.003969085,0.027748771,0.00054554216,0.46411303],"study_design_scores_gemma":[0.00069136237,0.000060046383,0.00002582505,0.00041226848,0.000059245052,0.000044551158,0.001483304,0.9894798,0.001904995,0.0045998697,0.00051722623,0.00072150934],"about_ca_topic_score_codex":0.00025696502,"about_ca_topic_score_gemma":0.00011407141,"teacher_disagreement_score":0.49257445,"about_ca_system_score_codex":0.0008056943,"about_ca_system_score_gemma":0.00080243754,"threshold_uncertainty_score":0.9996481},"labels":[],"label_agreement":null},{"id":"W3042296427","doi":"10.5858/arpa.2020-0034-oa","title":"A Digital Pathology Solution to Resolve the Tissue Floater Conundrum","year":2020,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jacobs (Canada); University of Waterloo","funders":"","keywords":"Digital pathology; Computer science; Context (archaeology); Troubleshooting; Artificial intelligence; Information retrieval; Computer vision; Search engine indexing; Digital image; Matching (statistics); Pattern recognition (psychology); Image (mathematics); Pathology; Image processing; Medicine; Biology","score_opus":0.015460475193024022,"score_gpt":0.2569784741930125,"score_spread":0.2415179989999885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042296427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058401003,0.00088651315,0.8501401,0.08556144,0.000993635,0.00046970154,0.000046509933,0.000205933,0.0032951816],"genre_scores_gemma":[0.97574705,0.000055672568,0.012249393,0.011210047,0.0005635964,0.000049359453,0.000008334342,0.000021095135,0.00009543621],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982832,0.00028704462,0.00037909026,0.00051005254,0.00021933237,0.00032128044],"domain_scores_gemma":[0.9986059,0.00034497192,0.00016418255,0.00062063884,0.000091597794,0.00017272889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028829384,0.00017388245,0.00032557655,0.0001255198,0.0001146277,0.000015454038,0.00086936716,0.000074718875,0.000020381978],"category_scores_gemma":[0.00044916547,0.00012278711,0.000036479785,0.0005399385,0.00083223375,0.00020972015,0.0004172224,0.0002713958,0.00006879153],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022277987,0.00006210031,0.0015338799,0.00006366293,0.000049087033,0.00093259604,0.03599626,0.00009774527,0.7909765,0.008036875,0.010647406,0.15138106],"study_design_scores_gemma":[0.007398757,0.021282118,0.06090892,0.0005499106,0.00021627676,0.0014513967,0.0036004223,0.013879681,0.28005868,0.020541683,0.58828276,0.0018293792],"about_ca_topic_score_codex":0.0000048273873,"about_ca_topic_score_gemma":0.000010298396,"teacher_disagreement_score":0.91734606,"about_ca_system_score_codex":0.000019906729,"about_ca_system_score_gemma":0.00011459433,"threshold_uncertainty_score":0.5007113},"labels":[],"label_agreement":null},{"id":"W3043602140","doi":"10.1136/gutjnl-2019-319866","title":"Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning","year":2020,"lang":"en","type":"article","venue":"Gut","topic":"AI in cancer detection","field":"Computer Science","cited_by":272,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"NIHR Oxford Biomedical Research Centre; Medical Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Wellcome Trust; Academy of Medical Sciences; Biomedical Research Council; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Cancer Research UK; National Science Foundation","keywords":"Colorectal cancer; Random forest; Grading (engineering); Medicine; Tumour heterogeneity; Precision medicine; Gene expression profiling; Pathology; Oncology; Internal medicine; Artificial intelligence; Computational biology; Bioinformatics; Cancer; Biology; Gene expression; Gene; Computer science; Genetics","score_opus":0.03426763760177132,"score_gpt":0.28072470833077506,"score_spread":0.24645707072900375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043602140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4479643,0.00012264121,0.5504913,0.00087397464,0.00015383888,0.00008681689,0.0000011011563,0.00009085804,0.00021518959],"genre_scores_gemma":[0.94696164,0.000004185184,0.052794542,0.00017680477,0.00003938771,0.000008572273,0.0000013050351,0.000010770496,0.000002802182],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911326,0.00008879673,0.00017410879,0.00026844017,0.00021143397,0.00014394528],"domain_scores_gemma":[0.99941784,0.00004983904,0.00017163558,0.00014985616,0.00015044677,0.00006038238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010307654,0.00008498266,0.00011850695,0.000047739257,0.00006862889,0.000036996145,0.00024195967,0.000052860978,0.00001881296],"category_scores_gemma":[0.00008863315,0.00009465934,0.00004690409,0.00044673195,0.00006459409,0.00008542235,0.000055112218,0.00014461135,0.0000138194355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031972926,0.000008698417,0.001882874,0.00002948657,0.000012230446,0.000007641499,0.00030058945,0.024310054,0.96244675,0.0002706186,0.000033899247,0.010665211],"study_design_scores_gemma":[0.00020806344,0.0000741685,0.0033426653,0.0000119271435,0.000010604258,0.000002482288,0.000027179121,0.84733516,0.1485718,0.000046646855,0.00027779845,0.00009147747],"about_ca_topic_score_codex":0.00012366458,"about_ca_topic_score_gemma":0.000015313815,"teacher_disagreement_score":0.8230251,"about_ca_system_score_codex":0.000117193435,"about_ca_system_score_gemma":0.00018011327,"threshold_uncertainty_score":0.38600957},"labels":[],"label_agreement":null},{"id":"W3044753181","doi":"10.1002/path.5509","title":"Synthesis of diagnostic quality cancer pathology images by generative adversarial networks","year":2020,"lang":"en","type":"article","venue":"The Journal of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; William Osler Health System; Canada's Michael Smith Genome Sciences Centre; Brampton Civic Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Adversarial system; Generative grammar; Pathology; Quality (philosophy); Cancer; Artificial intelligence; Computer science; Medicine; Internal medicine; Epistemology; Philosophy","score_opus":0.023501909961873808,"score_gpt":0.28961479217787695,"score_spread":0.26611288221600315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044753181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13593988,0.0026290333,0.84980947,0.010076419,0.0013434626,0.00009720949,0.000019203588,0.00001780007,0.00006754415],"genre_scores_gemma":[0.9927504,0.0015297261,0.0038745846,0.0012038631,0.0006173146,0.000007766499,2.500398e-7,0.00000910386,0.0000069990506],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973528,0.0014857646,0.00056965864,0.00017081984,0.0002116988,0.00020925426],"domain_scores_gemma":[0.9960717,0.002487291,0.0008892047,0.00025615242,0.00021694286,0.000078706355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012808453,0.00012610559,0.00040662964,0.000035023695,0.00008151134,0.000013053158,0.0008596935,0.00010958184,0.00003168336],"category_scores_gemma":[0.0013878974,0.00008726815,0.00010440476,0.00023068022,0.00024529212,0.00019961277,0.00018874505,0.00038227445,0.0000032167168],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016336961,0.00036732983,0.0077498406,0.00011469242,0.00059147406,0.0014960039,0.020820562,0.10533978,0.5131393,0.0029183326,0.06691427,0.27891472],"study_design_scores_gemma":[0.0052263183,0.0065346262,0.049979795,0.00023629669,0.0010278,0.0048766956,0.0015327755,0.053436384,0.8614661,0.009725087,0.0045372527,0.001420842],"about_ca_topic_score_codex":0.000038893944,"about_ca_topic_score_gemma":0.000012628325,"teacher_disagreement_score":0.8568105,"about_ca_system_score_codex":0.00006177783,"about_ca_system_score_gemma":0.00011502976,"threshold_uncertainty_score":0.35586917},"labels":[],"label_agreement":null},{"id":"W3045125794","doi":"10.4103/jpi.jpi_10_20","title":"Deep Learning to Estimate Human Epidermal Growth Factor Receptor 2 Status from Hematoxylin and Eosin-Stained Breast Tissue Images","year":2020,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"H&E stain; Immunohistochemistry; Breast cancer; Stain; Digital pathology; Pathology; Medicine; Human Epidermal Growth Factor Receptor 2; Artificial intelligence; Computer science; Staining; Internal medicine; Cancer","score_opus":0.013144957108756404,"score_gpt":0.2807509058362703,"score_spread":0.2676059487275139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045125794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35979584,0.000090440466,0.63772184,0.0018792212,0.00027555352,0.000089021705,0.000012839021,0.000056352128,0.00007888823],"genre_scores_gemma":[0.7358937,0.000044462115,0.26297796,0.0008524662,0.00020332335,0.0000023659575,0.0000037236293,0.000013829442,0.000008149103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830043,0.0001161754,0.00085861015,0.00012075778,0.000283004,0.00032104025],"domain_scores_gemma":[0.99830925,0.00014377189,0.00078247575,0.0001503632,0.000273987,0.00034016938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029519005,0.00017738342,0.00037810986,0.00015991366,0.00017007155,0.00016716638,0.00042179256,0.00010578358,0.00004011682],"category_scores_gemma":[0.00030860782,0.00015877916,0.000062771556,0.00022505016,0.00006617649,0.0012152792,0.00027414915,0.000523394,0.000039841565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036869114,0.00018092313,0.042560846,0.0007722399,0.0004231319,0.0015369408,0.28885308,0.016634332,0.10008194,0.002040426,0.0064285398,0.5401189],"study_design_scores_gemma":[0.01279298,0.016073283,0.33037877,0.0007981651,0.00042612295,0.019248577,0.017553091,0.39642242,0.17192358,0.009457772,0.020872688,0.0040525557],"about_ca_topic_score_codex":0.0000069761645,"about_ca_topic_score_gemma":0.0000024571711,"teacher_disagreement_score":0.53606635,"about_ca_system_score_codex":0.00009114812,"about_ca_system_score_gemma":0.00006601245,"threshold_uncertainty_score":0.64748263},"labels":[],"label_agreement":null},{"id":"W3045506901","doi":"10.1016/j.future.2020.07.045","title":"SEENS: Nuclei segmentation in Pap smear images with selective edge enhancement","year":2020,"lang":"en","type":"article","venue":"Future Generation Computer Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"National Natural Science Foundation of China; European Research Consortium for Informatics and Mathematics","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Image segmentation; Canny edge detector; Enhanced Data Rates for GSM Evolution; Region of interest; Pattern recognition (psychology); Edge detection; Scale-space segmentation; Image (mathematics); Image processing","score_opus":0.016409758292133935,"score_gpt":0.22102800517712748,"score_spread":0.20461824688499355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045506901","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005282714,0.00036008056,0.97839606,0.0023079407,0.012599077,0.0006920869,0.0000032816843,0.00020827421,0.00015048072],"genre_scores_gemma":[0.72875804,0.00005971003,0.19734757,0.0027075496,0.070524074,0.00037572975,0.000057340672,0.00005206796,0.00011793085],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805665,0.00023082126,0.00038105404,0.0006660189,0.00042140495,0.00024406634],"domain_scores_gemma":[0.99917614,0.000020151027,0.00020365439,0.00030692265,0.00019546173,0.000097644224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001994102,0.00022120928,0.00023057441,0.00010871452,0.0001401935,0.0004021408,0.00035114452,0.000085026586,0.000005739631],"category_scores_gemma":[0.000002604771,0.00019813386,0.000035504934,0.0006953436,0.00001568422,0.00076653226,0.000093372575,0.00018138898,0.000050347306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013780456,0.00024526517,0.002335007,0.0003907818,0.00026439107,0.00008927755,0.0299501,0.2019988,0.07616536,0.0055803466,0.53668433,0.14615852],"study_design_scores_gemma":[0.0010923416,0.0008387286,0.0009650728,0.00006197005,0.000009766304,0.000032863358,0.00020829935,0.92466444,0.041020326,0.0000044127514,0.030663643,0.00043810884],"about_ca_topic_score_codex":0.000045816007,"about_ca_topic_score_gemma":0.000044345816,"teacher_disagreement_score":0.7810485,"about_ca_system_score_codex":0.0002821989,"about_ca_system_score_gemma":0.00009899349,"threshold_uncertainty_score":0.8079664},"labels":[],"label_agreement":null},{"id":"W3047561574","doi":"10.1038/s41379-020-0640-y","title":"Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists","year":2020,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"National Cancer Institute; KWF Kankerbestrijding; Barts Charity","keywords":"Grading (engineering); Prostate cancer; Prostate; Biopsy; Anatomical pathology; Prostate biopsy; Applications of artificial intelligence; Needle biopsy","score_opus":0.03552973169698858,"score_gpt":0.2573289568775067,"score_spread":0.2217992251805181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047561574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2044029,0.00051166,0.7923607,0.0018229161,0.0003346452,0.00021040351,0.000025496467,0.00021475802,0.00011648148],"genre_scores_gemma":[0.9795328,0.00006580768,0.019852955,0.00039507932,0.00006369846,0.000043596552,0.000004212695,0.000018683982,0.000023163828],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99788004,0.00017226874,0.0004945212,0.00080932,0.00024536572,0.0003985013],"domain_scores_gemma":[0.9989034,0.00009759016,0.0003218225,0.00047782113,0.00009395645,0.00010542918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031575782,0.00021460665,0.00033556073,0.00007341707,0.000105208885,0.000061673694,0.00079568406,0.00014437964,0.000005271424],"category_scores_gemma":[0.00015058072,0.00021270048,0.00007910466,0.00037388984,0.00030258816,0.00032594174,0.00024305774,0.00025485622,0.000025750636],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006759251,0.000052853073,0.0003688971,0.00005313613,0.000009182561,0.000088159955,0.0033733568,0.00037117692,0.6692168,0.002779347,0.00022886765,0.3233906],"study_design_scores_gemma":[0.00007941488,0.0007295424,0.0006996165,0.000019851346,0.000011428711,0.00005036648,0.0001507361,0.212592,0.7496263,0.035384163,0.00030404358,0.00035258316],"about_ca_topic_score_codex":0.000015509419,"about_ca_topic_score_gemma":0.000009237077,"teacher_disagreement_score":0.7751299,"about_ca_system_score_codex":0.000060123217,"about_ca_system_score_gemma":0.000063034524,"threshold_uncertainty_score":0.8673674},"labels":[],"label_agreement":null},{"id":"W3047754369","doi":"10.1007/978-3-030-59137-3_21","title":"Forming Local Intersections of Projections for Classifying and Searching Histopathology Images","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Waterloo","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Histogram; Benchmark (surveying); Equidistant; Computer science; Intersection (aeronautics); Invariant (physics); Image (mathematics); Mathematics; Geography; Cartography; Geometry","score_opus":0.03894854888260255,"score_gpt":0.31298152556645553,"score_spread":0.27403297668385296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047754369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006667363,0.00018328342,0.9876081,0.0019026714,0.0028096705,0.0006444382,0.000008162767,0.00015965801,0.000016653603],"genre_scores_gemma":[0.5648912,0.000010687467,0.43474528,0.00013595773,0.00014539309,0.00006095525,9.2168415e-7,0.000009253945,3.4387438e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736446,0.00009435109,0.0004422746,0.0012947392,0.0003495725,0.00045461784],"domain_scores_gemma":[0.99821156,0.0005425336,0.0002772766,0.00064026937,0.00022723226,0.000101122045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00085661974,0.00026535438,0.00039348603,0.0007727008,0.0003540565,0.00026326158,0.0014237352,0.00018857892,6.148611e-7],"category_scores_gemma":[0.00028996982,0.00026891,0.00010587233,0.0011198464,0.00083862536,0.00052324176,0.0030009458,0.0009443089,4.847544e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015185153,0.0000325419,0.0005533997,0.0003696003,0.000008784432,0.000008918327,0.0056103934,0.09078558,0.007221776,0.0005923227,0.000010597626,0.8947909],"study_design_scores_gemma":[0.00018676047,0.00024352933,0.0009788212,0.0002273272,0.000008341573,0.00009550463,0.0000075014245,0.9299238,0.018682836,0.049357533,0.00003948552,0.00024861383],"about_ca_topic_score_codex":0.00017701599,"about_ca_topic_score_gemma":0.00019809637,"teacher_disagreement_score":0.8945423,"about_ca_system_score_codex":0.0004799717,"about_ca_system_score_gemma":0.0006848363,"threshold_uncertainty_score":0.99997634},"labels":[],"label_agreement":null},{"id":"W3048220234","doi":"10.1016/j.jsb.2020.107598","title":"Deep learning for 3D imaging and image analysis in biomineralization research","year":2020,"lang":"en","type":"review","venue":"Journal of Structural Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Object Research Systems (Canada)","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Biomineralization; Segmentation; Data science; Cognitive science; Human–computer interaction; Psychology; Biology; Paleontology","score_opus":0.05837722521677868,"score_gpt":0.41831037603634247,"score_spread":0.3599331508195638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048220234","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034682664,0.7776733,0.22158882,0.00023346447,0.00029827017,0.00015371758,0.0000014998483,0.000008080448,0.000008180782],"genre_scores_gemma":[0.0011959309,0.95364505,0.044774838,0.000014906429,0.00033508532,0.0000072134594,0.000010479074,0.000011437892,0.0000050413028],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980079,0.00058370264,0.0007005353,0.00031786037,0.00014078931,0.00024919026],"domain_scores_gemma":[0.9983241,0.00044261955,0.000736948,0.0001269261,0.00030160506,0.00006777951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009012607,0.00016735707,0.0010351969,0.0013936406,0.000099683,0.00011903396,0.0005185901,0.00014300925,0.000005708933],"category_scores_gemma":[0.0003535557,0.00012106175,0.00025052714,0.0017920058,0.000098663746,0.00030401256,0.0001971511,0.0006963458,7.3774737e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006557977,8.677493e-7,0.0002215993,0.00042034494,0.00013205309,0.0000115158355,0.00008551821,0.000034107634,0.000041992556,0.00016989915,0.000014969136,0.9988606],"study_design_scores_gemma":[0.0005749761,0.0005432176,0.0005515733,0.0009191731,0.00072659214,0.0007126577,0.000048054808,0.2009897,0.0000109990715,0.0045111007,0.7899883,0.00042365436],"about_ca_topic_score_codex":0.000026873533,"about_ca_topic_score_gemma":0.000017349577,"teacher_disagreement_score":0.9984369,"about_ca_system_score_codex":0.00024410321,"about_ca_system_score_gemma":0.00012295842,"threshold_uncertainty_score":0.49367547},"labels":[],"label_agreement":null},{"id":"W3048549272","doi":"10.1007/s10439-020-02585-y","title":"Stochastic Sequential Modeling: Toward Improved Prostate Cancer Diagnosis Through Temporal-Ultrasound","year":2020,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials; London Health Sciences Centre; University of British Columbia; Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Science Foundation of Sri Lanka; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Science Foundation; National Institutes of Health; National Institute of General Medical Sciences; California HIV/AIDS Research Program","keywords":"Malignancy; Prostate cancer; Computer science; Artificial intelligence; Cancer; Ultrasound; Hidden Markov model; Pattern recognition (psychology); Medicine; Radiology; Pathology; Internal medicine","score_opus":0.07263612052667848,"score_gpt":0.3043334567195237,"score_spread":0.23169733619284524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048549272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01345253,0.00073040585,0.97516614,0.009563718,0.00060350966,0.00018821345,0.000027994707,0.0002605762,0.000006905232],"genre_scores_gemma":[0.9834042,0.00030692344,0.015093178,0.0006727049,0.0003380824,0.00015271065,0.000006429409,0.000022513572,0.0000032372432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842083,0.000016857943,0.0003848891,0.00040010014,0.0004109534,0.00036636466],"domain_scores_gemma":[0.99924195,0.00008359043,0.000095574396,0.0002233592,0.000110628,0.00024490157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016257292,0.00018324761,0.0002605439,0.00006907621,0.000036640766,0.000050937175,0.00051662384,0.00010168279,0.000026820457],"category_scores_gemma":[0.00022447195,0.0001783089,0.00010275001,0.0006131272,0.000055388868,0.00044082507,0.00017799014,0.00022016933,0.0000052257656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013258544,0.0002611354,0.00014320038,0.0013052224,0.0005574351,0.000048798043,0.012787392,0.7762266,0.111518405,0.002487504,0.0067846747,0.0877471],"study_design_scores_gemma":[0.00025644334,0.00020070924,0.000010100049,0.00007223238,0.000009527239,0.0000035933992,0.000023659897,0.97950155,0.016812637,0.00029009124,0.002610053,0.00020939381],"about_ca_topic_score_codex":0.00024079462,"about_ca_topic_score_gemma":0.000001259999,"teacher_disagreement_score":0.9699517,"about_ca_system_score_codex":0.0000350587,"about_ca_system_score_gemma":0.00011640704,"threshold_uncertainty_score":0.7271226},"labels":[],"label_agreement":null},{"id":"W3048601286","doi":"10.22215/etd/2020-14102","title":"A Deep Representation Learning Framework for Medical Imaging Data Analysis","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Research Council Canada","keywords":"Deep learning; Artificial intelligence; Convolutional neural network; Computer science; Feature learning; Spectrogram; Representation (politics); Feature (linguistics); Pattern recognition (psychology); Recurrent neural network; Medical imaging; Transfer of learning; Artificial neural network; Machine learning","score_opus":0.03186756229081452,"score_gpt":0.374005309829211,"score_spread":0.3421377475383965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048601286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003370715,0.00026818702,0.99398535,0.0018082453,0.001176612,0.0002502654,0.000002581801,0.00039661588,0.002078434],"genre_scores_gemma":[0.06269157,0.0002373898,0.9254786,0.00092477014,0.0012014222,0.00020896207,0.0073556937,0.0000734353,0.0018282116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971326,0.00009971755,0.0004230229,0.0012532843,0.0008571267,0.0002342483],"domain_scores_gemma":[0.9975408,0.00056952453,0.00034717203,0.0012388058,0.00015965998,0.00014407009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004717227,0.00020124494,0.00035756282,0.00031360073,0.00019673171,0.00033570774,0.002217494,0.0002568716,0.00019887737],"category_scores_gemma":[0.0020596185,0.00020859,0.00018045596,0.0017756458,0.000014443463,0.0006471384,0.00031761613,0.00064346794,0.000026593929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000767205,0.000031593856,0.0015406394,0.0001958612,0.0012190553,0.000024671343,0.0033053115,0.0023248876,0.000033012027,0.028614527,0.0034479229,0.9591858],"study_design_scores_gemma":[0.000105940366,0.000017320743,0.0004836097,0.000042403815,0.00035856685,0.0000019104473,0.0005799285,0.9871441,0.00018966469,0.0073810657,0.0034712255,0.00022426232],"about_ca_topic_score_codex":0.00013855755,"about_ca_topic_score_gemma":0.0005159719,"teacher_disagreement_score":0.98481923,"about_ca_system_score_codex":0.00007975751,"about_ca_system_score_gemma":0.00021774735,"threshold_uncertainty_score":0.85060537},"labels":[],"label_agreement":null},{"id":"W3048913829","doi":"10.32920/22734344","title":"An Efficient Confidence Measure-Based Evaluation Metric for Breast Cancer Screening Using Bayesian Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperparameter; Computer science; Artificial neural network; Metric (unit); Transfer of learning; Machine learning; Artificial intelligence; Bayesian network; Feature (linguistics); Coverage probability; Confidence interval; Pattern recognition (psychology); Data mining; Statistics; Mathematics","score_opus":0.10654218833104377,"score_gpt":0.37683245118835923,"score_spread":0.27029026285731544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048913829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002199901,0.00036422088,0.9889952,0.0006409768,0.0049155788,0.0020412814,0.000043980708,0.00078045204,0.000018432338],"genre_scores_gemma":[0.8907208,0.0000056596637,0.10765121,0.00023140984,0.00068618194,0.00060811895,0.00002313441,0.00006322135,0.00001029558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995367,0.00041646586,0.0005877047,0.0015609297,0.0014416084,0.0006262739],"domain_scores_gemma":[0.9962624,0.0003184845,0.00055368175,0.0013465292,0.0013118716,0.0002070836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032018013,0.00044157455,0.00043022216,0.0007576346,0.0003862277,0.00072122965,0.0015162989,0.00036930168,0.000039248847],"category_scores_gemma":[0.00010755713,0.0004521623,0.00024757045,0.0015826239,0.000059547867,0.0003267435,0.00046862217,0.0005845103,0.0000013968705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003710466,0.00001905736,0.00015783522,0.000044465174,0.000032426342,0.000001028014,0.00003815061,0.8294241,0.000057604917,0.00010236992,0.000033265624,0.17005263],"study_design_scores_gemma":[0.0005078968,0.00007085184,0.0029143116,0.0002752228,0.00013503002,0.000008307288,0.00001793137,0.9946971,0.0004166147,0.00044224426,0.0000032250116,0.00051128515],"about_ca_topic_score_codex":0.0030228118,"about_ca_topic_score_gemma":0.0005133666,"teacher_disagreement_score":0.88852084,"about_ca_system_score_codex":0.0011289167,"about_ca_system_score_gemma":0.0009221033,"threshold_uncertainty_score":0.999793},"labels":[],"label_agreement":null},{"id":"W3080655609","doi":"10.1016/j.cmpb.2020.105724","title":"White learning methodology: A case study of cancer-related disease factors analysis in real-time PACS environment","year":2020,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; Universidade de Macau","keywords":"Machine learning; Artificial intelligence; Deep learning; Black box; Computer science; White box; Bayesian network; Naive Bayes classifier; Support vector machine","score_opus":0.11361901328764357,"score_gpt":0.3892890498358598,"score_spread":0.27567003654821626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080655609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55528617,0.00035901763,0.44340655,0.00037199102,0.000105468025,0.00039124567,7.29447e-7,0.00007624326,0.000002579408],"genre_scores_gemma":[0.5621566,0.00015467349,0.43755642,0.000035228048,0.000037631526,0.00004166154,0.0000041530925,0.000009387097,0.0000042530223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959399,0.0021414584,0.0006498541,0.0007477941,0.00023925917,0.00028171492],"domain_scores_gemma":[0.99862975,0.00046260664,0.0002694599,0.0003582047,0.000028536204,0.00025144956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002048754,0.00023202805,0.0007220173,0.0005507635,0.00005789113,0.0000328876,0.0003141574,0.00008871344,0.00001457292],"category_scores_gemma":[0.00004015098,0.00019260605,0.00007640343,0.0029215384,0.00011714507,0.00012452516,0.00038933672,0.0003175051,3.9566115e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003056643,0.00025693336,0.43528807,0.00005175443,0.00026315212,0.00047857064,0.025619615,0.0032966593,0.00018548177,0.000008031322,0.000001974378,0.5345192],"study_design_scores_gemma":[0.0017077785,0.002280697,0.17846471,0.000054960426,0.00037900382,0.0000238205,0.0016408917,0.8147529,0.00004756829,0.0001382797,0.00022964006,0.00027978542],"about_ca_topic_score_codex":0.0017996733,"about_ca_topic_score_gemma":0.00007602111,"teacher_disagreement_score":0.8114562,"about_ca_system_score_codex":0.00009308424,"about_ca_system_score_gemma":0.000032710952,"threshold_uncertainty_score":0.7854247},"labels":[],"label_agreement":null},{"id":"W3080854745","doi":"10.4103/jpi.jpi_68_19","title":"Colorectal Cancer Detection Based on Deep Learning","year":2020,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital","funders":"","keywords":"H&E stain; Digital pathology; Medical diagnosis; Computer science; Artificial intelligence; Deep learning; Colorectal cancer; Segmentation; Cancer detection; Medicine; Cancer; Pathology; Radiology; Medical physics; Staining; Internal medicine","score_opus":0.013314632489788286,"score_gpt":0.24765586314894503,"score_spread":0.23434123065915674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080854745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16795935,0.000029532828,0.8297203,0.00089851656,0.0008145902,0.000050351082,4.2239148e-7,0.000046200716,0.00048074048],"genre_scores_gemma":[0.97460186,0.000031369356,0.023285363,0.0018661327,0.00020334487,0.0000034729671,1.7511e-7,0.000005823691,0.0000024825388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989243,0.00008375398,0.0004995414,0.000059091886,0.00027972888,0.00015359456],"domain_scores_gemma":[0.9988309,0.000098104574,0.00070667395,0.00008558754,0.0001808325,0.00009786412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003624321,0.000094836425,0.00017893933,0.00014635795,0.000099456556,0.000049511917,0.00035087546,0.00009677685,0.000014318732],"category_scores_gemma":[0.00020548324,0.000082173705,0.00008110198,0.000308196,0.000033764612,0.0005523224,0.000048547023,0.00058828265,0.000025092799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025715015,0.00004968028,0.00268881,0.00009136219,0.000045488086,0.00021303026,0.01343566,0.5002948,0.009295886,0.00018690719,0.00031602557,0.4731252],"study_design_scores_gemma":[0.00060403283,0.001919856,0.0019017691,0.000023121542,0.000014678068,0.00033984077,0.00022103878,0.97515744,0.017553577,0.00008628221,0.002070885,0.00010746283],"about_ca_topic_score_codex":7.855992e-7,"about_ca_topic_score_gemma":0.000002754206,"teacher_disagreement_score":0.8066425,"about_ca_system_score_codex":0.00013766882,"about_ca_system_score_gemma":0.000097815624,"threshold_uncertainty_score":0.33509463},"labels":[],"label_agreement":null},{"id":"W3081573058","doi":"10.1177/0846537120949974","title":"Computational Radiology in Breast Cancer Screening and Diagnosis Using Artificial Intelligence","year":2020,"lang":"en","type":"review","venue":"Canadian Association of Radiologists Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; London Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Research Institute","keywords":"Medicine; Mammography; Breast cancer screening; Digital mammography; Workflow; Breast cancer; Breast imaging; Medical physics; Artificial intelligence; Applications of artificial intelligence; Radiology; Medical imaging; Tomosynthesis; Machine learning; Computer science; Cancer; Internal medicine","score_opus":0.07734392421739672,"score_gpt":0.3372911480318645,"score_spread":0.2599472238144678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081573058","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002202573,0.8091009,0.18697493,0.0024961845,0.0009555492,0.00025112624,0.00016285658,0.000019295809,0.000017095863],"genre_scores_gemma":[0.0014667743,0.984053,0.013735299,0.00015992415,0.00052610075,0.000025847747,0.000009436337,0.000020381256,0.0000032084797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971496,0.00068400236,0.0010063784,0.0004277144,0.00027547847,0.00045686326],"domain_scores_gemma":[0.99711233,0.0006444111,0.0015335669,0.00013634597,0.00021074251,0.00036260713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011109734,0.00027838678,0.001151848,0.00079380174,0.0001932564,0.00015324626,0.00063875056,0.0004532476,0.000027786326],"category_scores_gemma":[0.00035129275,0.00028338045,0.00020779384,0.0008686962,0.000096845375,0.0003024806,0.00007250596,0.0009322847,0.0000027947133],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020869336,0.000005229662,0.0022863138,0.00018128497,0.00012563061,0.00005815745,0.00009256191,0.004680647,6.07008e-8,0.0014163426,0.0003785797,0.9907731],"study_design_scores_gemma":[0.0006071687,0.0002946375,0.008389701,0.011701275,0.0007236944,0.011763325,0.00012992899,0.25565115,0.0000020035804,0.022147555,0.68626255,0.002326999],"about_ca_topic_score_codex":0.005442984,"about_ca_topic_score_gemma":0.0076912344,"teacher_disagreement_score":0.9884461,"about_ca_system_score_codex":0.004962541,"about_ca_system_score_gemma":0.002884192,"threshold_uncertainty_score":0.99996185},"labels":[],"label_agreement":null},{"id":"W3081619705","doi":"10.48550/arxiv.2008.12904","title":"On segmentation of pectoralis muscle in digital mammograms by means of deep learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Mammography; Convolutional neural network; Digital mammography; Pattern recognition (psychology); Pectoralis major muscle; Graph; Shortest path problem; Pectoral muscle; Image segmentation; Computer vision; Anatomy; Medicine; Breast cancer","score_opus":0.041395820831939316,"score_gpt":0.18686135229115833,"score_spread":0.145465531459219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081619705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49944055,0.000015601387,0.49950957,0.000029858205,0.00015496925,0.00013903277,0.000011936995,0.000063604624,0.0006348849],"genre_scores_gemma":[0.9992877,0.000035914753,0.0005516489,0.000014873558,0.000012530465,6.831139e-7,0.000022313168,0.000010981721,0.000063328254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888515,0.00006650111,0.00020266954,0.00057839934,0.0001227981,0.0001444988],"domain_scores_gemma":[0.9990562,0.00008188305,0.00034607193,0.0003683264,0.00007854938,0.00006896993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008841135,0.00015724637,0.00023669418,0.00019888121,0.000029108453,0.000039753962,0.00066410186,0.0001266098,0.000015489311],"category_scores_gemma":[0.000045254885,0.00020186373,0.00011298792,0.0006510665,0.00006262266,0.0003606008,0.00052901893,0.00038038244,0.0000068185623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011180145,0.00021400236,0.017481862,0.00025938198,0.00008213556,0.000062250925,0.0022131032,0.93680304,0.0024131124,0.012025971,0.0001088074,0.028224556],"study_design_scores_gemma":[0.0011236148,0.00063071365,0.005608483,0.00022992963,0.00004432348,0.0000010711576,0.0006062924,0.95420927,0.00964915,0.02715012,0.0001852467,0.00056178984],"about_ca_topic_score_codex":0.0003081807,"about_ca_topic_score_gemma":0.00007239541,"teacher_disagreement_score":0.49984717,"about_ca_system_score_codex":0.00025996423,"about_ca_system_score_gemma":0.000052993022,"threshold_uncertainty_score":0.8231764},"labels":[],"label_agreement":null},{"id":"W3082121907","doi":"10.1109/embc44109.2020.9175867","title":"Alternative Techniques for Breast Tumour Detection using Ultrasound","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Ultrasound; Breast ultrasound; Machine learning; Noise (video); Pattern recognition (psychology); Filter (signal processing); Mammography; Computer vision; Radiology; Image (mathematics); Breast cancer; Medicine","score_opus":0.033144930740811665,"score_gpt":0.2797965111103083,"score_spread":0.24665158036949664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082121907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009845507,0.000006974609,0.98817307,0.00045170798,0.00023664236,0.0002606678,0.000004698566,0.00052182673,0.00049891317],"genre_scores_gemma":[0.84537977,0.0000021628282,0.15376706,0.0004751099,0.00032614195,0.000025512078,2.4985005e-7,0.000008956546,0.000015006812],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927884,0.000021752228,0.000122221,0.0003018438,0.00013091516,0.00014443438],"domain_scores_gemma":[0.99957466,0.000063974425,0.00006941446,0.00013158379,0.00009850692,0.00006183697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000950785,0.000089140645,0.00008333081,0.00004455297,0.00010871689,0.0001062255,0.0003038679,0.000036848825,0.0000101204],"category_scores_gemma":[0.000031286185,0.00008552589,0.000049431896,0.00025700935,0.000018067067,0.00052997813,0.00006367041,0.000073131334,0.0000068587956],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000399836,0.00001861792,0.000105320585,0.000028385763,0.000025533984,0.0000020833947,0.0006327285,0.0004527138,0.72631496,0.003865027,0.00018103365,0.2683336],"study_design_scores_gemma":[0.00009815336,0.00013095661,0.0001366563,0.0000059560925,0.000004039991,0.00007888022,0.000022535498,0.28662273,0.7087237,0.0034367212,0.0006274022,0.00011221094],"about_ca_topic_score_codex":0.00012040394,"about_ca_topic_score_gemma":0.00001624728,"teacher_disagreement_score":0.8355343,"about_ca_system_score_codex":0.00012115133,"about_ca_system_score_gemma":0.000029441047,"threshold_uncertainty_score":0.34876445},"labels":[],"label_agreement":null},{"id":"W3082372604","doi":"10.1109/embc44109.2020.9175653","title":"Recognizing Magnification Levels in Microscopic Snapshots","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huron Technologies (Canada); University of Waterloo","funders":"","keywords":"Magnification; Digital pathology; Computer science; Artificial intelligence; Classifier (UML); Computer vision; Feature extraction; Pattern recognition (psychology); Workload; Microscope; Perceptron; Artificial neural network; Pathology; Medicine","score_opus":0.07815639221187538,"score_gpt":0.2681742715335136,"score_spread":0.19001787932163822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082372604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067270316,0.000056554574,0.9156301,0.010304533,0.0003249661,0.00015055684,5.463493e-7,0.0002082772,0.006054126],"genre_scores_gemma":[0.93524134,0.000009734698,0.06296384,0.0016264626,0.0000538998,0.00001031017,5.3986264e-7,0.0000042829624,0.00008958951],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933803,0.000027058466,0.00014147366,0.00027753066,0.000093188704,0.00012271176],"domain_scores_gemma":[0.9996963,0.00002379759,0.00003506926,0.00017546685,0.000024331617,0.000045016535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009561646,0.00005649391,0.00006306026,0.000044580112,0.000027735343,0.000067410554,0.00031786738,0.0000336851,0.000063489526],"category_scores_gemma":[0.00003012965,0.000058501704,0.000014989863,0.00044661315,0.000009036012,0.00037722793,0.000076258286,0.00008678524,0.00016085172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013158313,0.00005864194,0.011606667,0.000119826735,0.000010125426,0.000017194063,0.0056098504,0.0003335327,0.35265714,0.010644089,0.006085653,0.6128441],"study_design_scores_gemma":[0.0010127273,0.00022969692,0.14284305,0.00005080903,0.000004125365,0.000011370213,0.00014467616,0.17293543,0.6618145,0.005839117,0.014575163,0.00053933717],"about_ca_topic_score_codex":0.00003017317,"about_ca_topic_score_gemma":0.000025045585,"teacher_disagreement_score":0.867971,"about_ca_system_score_codex":0.00005937877,"about_ca_system_score_gemma":0.00003473719,"threshold_uncertainty_score":0.23856303},"labels":[],"label_agreement":null},{"id":"W3082666061","doi":"10.1038/s41379-020-00674-w","title":"High throughput assessment of biomarkers in tissue microarrays using artificial intelligence: PTEN loss as a proof-of-principle in multi-center prostate cancer cohorts","year":2020,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Queen's University","funders":"National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Movember Foundation; U.S. Department of Health and Human Services","keywords":"PTEN; Tissue microarray; Prostate cancer; Tensin; Cohort; Biomarker; Medicine; Cancer; Artificial intelligence; Pathology; Internal medicine; Oncology; Computer science; Biology","score_opus":0.06443303697614562,"score_gpt":0.3652866337155228,"score_spread":0.30085359673937717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082666061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49415925,0.000106781044,0.504523,0.00044854195,0.00028667314,0.00042527984,0.000013231004,0.00001985539,0.000017424307],"genre_scores_gemma":[0.92581594,0.000026303313,0.07389335,0.00013751618,0.000027193953,0.00007577526,0.000003317117,0.000017360102,0.0000032617922],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785894,0.00020403114,0.0006810159,0.0006795282,0.00022404145,0.00035244814],"domain_scores_gemma":[0.99914926,0.000032802618,0.00030447746,0.0003629204,0.00009260252,0.00005792778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036481404,0.00018569572,0.00042656998,0.00019140617,0.000031059953,0.000019768855,0.00046217832,0.00014343116,0.000015273685],"category_scores_gemma":[0.000031443127,0.00019396552,0.000045274777,0.0005756761,0.0001722219,0.00024044309,0.00035591391,0.00023520121,0.000002535693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041830484,0.0014747708,0.14020428,0.00048369943,0.00010697345,0.001025913,0.026123242,0.20458195,0.36849377,0.0025883669,0.00001055885,0.25448817],"study_design_scores_gemma":[0.0005473453,0.00025433738,0.0052598044,0.00009605474,0.000008420006,0.000039346876,0.00007359005,0.74576527,0.24436465,0.0033239801,0.00004515814,0.0002220317],"about_ca_topic_score_codex":0.000855826,"about_ca_topic_score_gemma":0.00070732814,"teacher_disagreement_score":0.54118335,"about_ca_system_score_codex":0.00022126528,"about_ca_system_score_gemma":0.00028468974,"threshold_uncertainty_score":0.7909684},"labels":[],"label_agreement":null},{"id":"W3085224565","doi":"10.1007/s10439-020-02601-1","title":"Correction to: Stochastic Sequential Modeling: Toward Improved Prostate Cancer Diagnosis Through Temporal-Ultrasound","year":2020,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials; London Health Sciences Centre; University of British Columbia; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; California HIV/AIDS Research Program; National Science Foundation","keywords":"Prostate cancer; Work (physics); Computer science; Cancer; Medicine; Engineering; Internal medicine; Mechanical engineering","score_opus":0.05980623264547989,"score_gpt":0.3045071678577414,"score_spread":0.2447009352122615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085224565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011643652,0.00026426848,0.9770191,0.0080225235,0.0025076119,0.00024184506,0.000017923981,0.0002750162,0.000008096198],"genre_scores_gemma":[0.9869659,0.00013510208,0.011407342,0.0008473505,0.0004043972,0.00020356268,0.000005766976,0.00002206827,0.000008496205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847895,0.000017457993,0.0003627871,0.00041276708,0.0003887459,0.0003392716],"domain_scores_gemma":[0.9991972,0.00010459819,0.00008233388,0.00019928881,0.00013122984,0.00028539036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016327658,0.0001748697,0.00023743627,0.00009070822,0.00004129313,0.00005408447,0.0004069024,0.00007951991,0.000020570084],"category_scores_gemma":[0.00041656368,0.0001763082,0.00008922605,0.00081467896,0.000031786316,0.00038981196,0.00015680342,0.00021901783,0.0000076009346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008814667,0.00010544334,0.000062571475,0.0003046987,0.00016832666,0.00001109389,0.0065962328,0.84865904,0.061705478,0.00025755228,0.01515066,0.06689076],"study_design_scores_gemma":[0.00018188186,0.00030541283,0.000018553748,0.00010226642,0.000008186541,0.000004058439,0.000029904942,0.9736113,0.02259359,0.000085444495,0.0028603731,0.00019904904],"about_ca_topic_score_codex":0.00046622203,"about_ca_topic_score_gemma":0.0000040810055,"teacher_disagreement_score":0.97532225,"about_ca_system_score_codex":0.000054203367,"about_ca_system_score_gemma":0.000108744454,"threshold_uncertainty_score":0.7189639},"labels":[],"label_agreement":null},{"id":"W3086921797","doi":"10.5121/sipij.2020.11401","title":"Melanoma Cell Detection in Lymph Nodes Histopathological Images using Deep Learning","year":2020,"lang":"en","type":"article","venue":"Signal & Image Processing An International Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Lymph; Melanoma; Pathology; Deep learning; Medicine; Artificial intelligence; Computer science; Cancer research","score_opus":0.02175112502726661,"score_gpt":0.28150491708934805,"score_spread":0.25975379206208143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086921797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20008445,0.00023547643,0.7981098,0.00054907263,0.00039599393,0.000037531856,7.29296e-7,0.00012992819,0.00045697964],"genre_scores_gemma":[0.903913,0.000022920654,0.09493069,0.00034068522,0.00074399135,0.000004224415,0.0000014747411,0.000019843408,0.000023142611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976621,0.00028578975,0.0004517575,0.00047364336,0.0008182345,0.00030847406],"domain_scores_gemma":[0.9986661,0.000048957423,0.00038858302,0.000092401824,0.0006214921,0.00018246079],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076141575,0.00019675115,0.00017985774,0.0002766075,0.0003415725,0.001221786,0.001038897,0.00009143338,0.000053424053],"category_scores_gemma":[0.00019526089,0.00019505297,0.00008769542,0.00035728648,0.00008254872,0.0031567498,0.00018586531,0.00075916905,0.00001821476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012016186,0.00009677827,0.006791954,0.000022086133,0.000010150673,0.0006260207,0.0021173726,0.008371547,0.47454974,0.000017050168,0.0000055213877,0.5072716],"study_design_scores_gemma":[0.00081872754,0.00019945086,0.0066886083,0.00007695928,0.000010354759,0.0015939696,0.00030698473,0.91003007,0.078676075,0.0011199545,0.00015277126,0.00032610388],"about_ca_topic_score_codex":0.000026767268,"about_ca_topic_score_gemma":0.0000022706324,"teacher_disagreement_score":0.9016585,"about_ca_system_score_codex":0.00058446196,"about_ca_system_score_gemma":0.00018519536,"threshold_uncertainty_score":0.99981505},"labels":[],"label_agreement":null},{"id":"W3087002346","doi":"10.1016/j.jmir.2020.06.010","title":"Developing an AI project","year":2020,"lang":"en","type":"review","venue":"Journal of medical imaging and radiation sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Laptop; Computer science; Identification (biology); Task (project management); Artificial intelligence; Cluster analysis; Software engineering; Human–computer interaction; Data science; Systems engineering; Engineering; Operating system","score_opus":0.08516367348870987,"score_gpt":0.4330829148469902,"score_spread":0.34791924135828034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087002346","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.6484275e-7,0.75526917,0.23308991,0.010137018,0.0013825193,0.00006447004,3.5096025e-7,0.000022384853,0.000033406355],"genre_scores_gemma":[0.000019339072,0.98492014,0.013219337,0.00081181,0.0010181552,0.0000024806993,3.0549415e-7,0.000005516241,0.000002935362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969871,0.00028801282,0.00067648944,0.0003034671,0.0015690267,0.00017591471],"domain_scores_gemma":[0.9984916,0.00027049897,0.0008005096,0.000106290776,0.00010345999,0.0002276268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029789181,0.00015259901,0.0005957658,0.00043417493,0.00021772282,0.00056091964,0.0014038264,0.00009670127,0.0000045952297],"category_scores_gemma":[0.0006252063,0.000097966935,0.00011337337,0.0010674332,0.00021644587,0.0014196017,0.0001426619,0.00055653765,0.0000027225794],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.4572907e-7,0.0000040886976,0.0000046222317,0.00026408673,0.000009186598,0.000028486458,0.00019177048,7.798609e-7,3.641041e-8,0.00084346184,0.0012313691,0.99742186],"study_design_scores_gemma":[0.00008646473,0.000068335234,0.0000047715453,0.0024858632,0.000034021567,0.001418747,0.0000832284,0.017449008,6.85967e-7,0.00044809357,0.977787,0.00013378284],"about_ca_topic_score_codex":0.000009810628,"about_ca_topic_score_gemma":8.4689793e-7,"teacher_disagreement_score":0.9972881,"about_ca_system_score_codex":0.00012758713,"about_ca_system_score_gemma":0.004248315,"threshold_uncertainty_score":0.7536328},"labels":[],"label_agreement":null},{"id":"W3087137785","doi":"10.1200/cci.20.00035","title":"Unsupervised Resolution of Histomorphologic Heterogeneity in Renal Cell Carcinoma Using a Brain Tumor–Educated Neural Network","year":2020,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Brain Tumour Charity","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Cluster analysis; Feature (linguistics); Context (archaeology); Pattern recognition (psychology); Deep learning; Machine learning; Biology","score_opus":0.1325694908421961,"score_gpt":0.35372715185114584,"score_spread":0.22115766100894974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087137785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94880706,0.00031820947,0.048284266,0.0010030128,0.0009692824,0.00032244384,0.0000115723915,0.00008936933,0.00019480452],"genre_scores_gemma":[0.9696891,0.000025580752,0.024404947,0.0055365604,0.00030467223,0.000018033048,0.000004901988,0.000012250217,0.000004002608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969038,0.00027184768,0.0017300968,0.00028716432,0.00037685217,0.0004302743],"domain_scores_gemma":[0.9981034,0.0003022434,0.00076567143,0.00047671128,0.0001456003,0.00020640447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009396786,0.00020356076,0.0004883381,0.00007919359,0.000082524944,0.000047364563,0.0007982889,0.00016413625,0.000020081485],"category_scores_gemma":[0.00021382338,0.00019942867,0.0001676722,0.0010748155,0.00015039498,0.00056165946,0.00036750294,0.00056036405,0.000008810137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078761415,0.00034135065,0.25852272,0.00080238766,0.000042919204,0.000055548684,0.006736157,0.6925271,0.0018021698,0.00026331702,0.014341781,0.023776913],"study_design_scores_gemma":[0.0011452216,0.00048139688,0.026982779,0.00004323535,0.00001602779,0.000009772798,0.000060443504,0.96839166,0.0013094435,0.00008277347,0.0012444532,0.0002327748],"about_ca_topic_score_codex":0.0003339193,"about_ca_topic_score_gemma":0.00011044313,"teacher_disagreement_score":0.27586454,"about_ca_system_score_codex":0.00033708394,"about_ca_system_score_gemma":0.00047317613,"threshold_uncertainty_score":0.81324655},"labels":[],"label_agreement":null},{"id":"W3088016248","doi":"10.1016/j.jasc.2020.09.008","title":"Evidence-based diagnostic accuracy measurement in urine cytology using likelihood ratios","year":2020,"lang":"en","type":"article","venue":"Journal of the American Society of Cytopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"Royal College of Physicians and Surgeons of Canada; McGill University","keywords":"Medicine; Urine cytology; Cytology; Urine; Chromatography; Urinary system; Pathology; Internal medicine","score_opus":0.092810806060055,"score_gpt":0.30469417057956505,"score_spread":0.21188336451951006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088016248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5533014,0.00074840256,0.41495606,0.030526577,0.00031731089,0.0001335741,6.8976203e-7,0.000012266938,0.0000037004615],"genre_scores_gemma":[0.9432045,0.0002965463,0.05015944,0.0061413203,0.00018545397,0.0000034331126,3.126125e-8,0.000008853712,3.835139e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99772066,0.000572564,0.0006760609,0.00021882367,0.0005555298,0.00025638985],"domain_scores_gemma":[0.99655056,0.00085508265,0.0017846848,0.00034225362,0.0003814083,0.000086004846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012335399,0.00013744817,0.00051656394,0.000061342995,0.00006673768,0.000019405079,0.0011390174,0.000049085924,0.000004694068],"category_scores_gemma":[0.0020481842,0.0001058568,0.00034269982,0.00084217335,0.0003685741,0.0003532426,0.00023713446,0.00043294913,0.0000014152681],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003966596,0.0003330092,0.16775736,0.00016892655,0.00013764788,0.00014226614,0.00584637,0.03793802,0.7027784,0.00009893351,0.0034444164,0.08095798],"study_design_scores_gemma":[0.004714633,0.007919893,0.56627274,0.0016393436,0.00031014098,0.0019542328,0.0015480592,0.19342369,0.21651483,0.003032664,0.0017474215,0.00092234445],"about_ca_topic_score_codex":0.000052921332,"about_ca_topic_score_gemma":0.000009845431,"teacher_disagreement_score":0.48626357,"about_ca_system_score_codex":0.00033942718,"about_ca_system_score_gemma":0.0006908779,"threshold_uncertainty_score":0.4316715},"labels":[],"label_agreement":null},{"id":"W3089090082","doi":"10.1016/j.media.2020.101813","title":"Deep neural network models for computational histopathology: A survey","year":2020,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":727,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Cancer Institute; Canadian Cancer Society","keywords":"Artificial intelligence; Artificial neural network; Computer science; Deep learning; Pattern recognition (psychology); Machine learning","score_opus":0.0621987312965477,"score_gpt":0.3509627319969386,"score_spread":0.28876400070039093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089090082","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6954435e-8,0.46812782,0.5310004,0.0002661695,0.0002693466,0.00019424692,0.000018873887,0.00009284675,0.000030291043],"genre_scores_gemma":[0.000020579522,0.8949793,0.10220981,0.0008832692,0.00077344396,0.0002854836,0.00074353564,0.000045771743,0.00005884251],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567,0.0009309958,0.0009276632,0.0010856485,0.0009219204,0.00046375723],"domain_scores_gemma":[0.9966986,0.001537223,0.0005034455,0.00063698145,0.00024840032,0.0003753242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016665603,0.00040267067,0.0022881995,0.0003464367,0.00017900634,0.00015529562,0.0018036413,0.00038474024,0.00009212264],"category_scores_gemma":[0.0005963183,0.00034852893,0.0014366329,0.0037009427,0.00015764502,0.00029301664,0.0004708187,0.0006069004,0.000045273788],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028591382,0.00001956075,0.000004191076,0.00053246395,0.0006191214,0.00008623459,0.00002438275,0.0312806,2.169676e-9,0.0002138272,0.0030323018,0.96418446],"study_design_scores_gemma":[0.00009106142,0.000034699144,0.000011219009,0.00011389578,0.0019848738,0.000028904271,4.0771948e-7,0.79121536,5.0824567e-9,0.0012692604,0.2050026,0.00024773867],"about_ca_topic_score_codex":0.00006638058,"about_ca_topic_score_gemma":0.00018160562,"teacher_disagreement_score":0.96393675,"about_ca_system_score_codex":0.00026855967,"about_ca_system_score_gemma":0.00048820267,"threshold_uncertainty_score":0.99989665},"labels":[],"label_agreement":null},{"id":"W3089850879","doi":"10.1007/978-3-030-59716-0_5","title":"Improved Resection Margins in Surgical Oncology Using Intraoperative Mass Spectrometry","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Perioperative; Prospective cohort study; Resection; Radiology; Surgery; Surgical resection","score_opus":0.024779867940828593,"score_gpt":0.2828160949736791,"score_spread":0.2580362270328505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089850879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025359614,0.00024727237,0.98926383,0.0013271202,0.0032261866,0.00054429617,0.0000038692037,0.00014831625,0.0049855104],"genre_scores_gemma":[0.2880272,0.00015256739,0.70899266,0.0009177441,0.0017125291,0.00002029872,0.000004020505,0.00006408528,0.00010886769],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99545336,0.00014212208,0.0007064279,0.0021078787,0.0008265581,0.0007636749],"domain_scores_gemma":[0.9978486,0.00048459918,0.0003457718,0.0009097721,0.00020182198,0.00020947671],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010314997,0.00056065305,0.0007602908,0.001483082,0.00022267867,0.00041078278,0.002227852,0.00060617214,0.000034140343],"category_scores_gemma":[0.000080853344,0.0005583931,0.00013316753,0.0019914985,0.000617346,0.0008490379,0.0011092459,0.0020901065,0.000020031095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018112709,0.00008850619,0.000102147205,0.00010024422,0.000043089603,0.0015656223,0.0022487035,0.07895353,0.019313008,0.0142024,0.000011857988,0.8831898],"study_design_scores_gemma":[0.0005647511,0.00092911493,0.00004960591,0.00019777443,0.0000067948113,0.00029239416,7.9713755e-7,0.9439054,0.010201677,0.04096052,0.0022231606,0.0006679934],"about_ca_topic_score_codex":0.0001230244,"about_ca_topic_score_gemma":0.0005726678,"teacher_disagreement_score":0.88252175,"about_ca_system_score_codex":0.0029702904,"about_ca_system_score_gemma":0.0013819169,"threshold_uncertainty_score":0.9996868},"labels":[],"label_agreement":null},{"id":"W3090736188","doi":"10.1109/ijcnn48605.2020.9207018","title":"A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Digitization; Network topology; Digital pathology; Telepathology; Artificial intelligence; Workflow; Identification (biology); Pattern recognition (psychology); Computer vision; Computer network; Telemedicine","score_opus":0.11112992849322377,"score_gpt":0.34809364985319674,"score_spread":0.23696372135997296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090736188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5696868,0.00007085954,0.42596257,0.0014117282,0.00021730484,0.00045463373,0.000001481086,0.00008604723,0.002108633],"genre_scores_gemma":[0.94913465,0.0000019548086,0.05053847,0.00017912041,0.000025623951,0.000038410453,2.519725e-7,0.0000025292072,0.00007898862],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999236,0.000079803955,0.00020004786,0.0002807816,0.000085041655,0.00011832644],"domain_scores_gemma":[0.99952525,0.00013808715,0.000074609925,0.00018821529,0.00005220927,0.000021603268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013203043,0.00007180315,0.00022091223,0.000053163993,0.000026599495,0.000015571291,0.00037561083,0.00002821526,0.000008604653],"category_scores_gemma":[0.000026208592,0.00006454266,0.000023763741,0.00023719594,0.000055586363,0.00018862197,0.00016078868,0.000065410284,0.000003970657],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028137567,0.0053320793,0.0551984,0.00058622967,0.00025331072,0.0006817576,0.41776416,0.013267898,0.14261536,0.16384135,0.079436116,0.11820958],"study_design_scores_gemma":[0.01838708,0.042784914,0.28306466,0.000050399012,0.000077373035,0.00022864237,0.12968306,0.31754082,0.15161614,0.036583625,0.017962666,0.0020206086],"about_ca_topic_score_codex":0.000103358754,"about_ca_topic_score_gemma":0.0002796261,"teacher_disagreement_score":0.3794479,"about_ca_system_score_codex":0.00005499184,"about_ca_system_score_gemma":0.00003077023,"threshold_uncertainty_score":0.26319736},"labels":[],"label_agreement":null},{"id":"W3091106624","doi":"10.3390/app10228298","title":"Deep-Learning-Based Computer-Aided Systems for Breast Cancer Imaging: A Critical Review","year":2020,"lang":"en","type":"review","venue":"Applied Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mammography; CAD; Computer science; Breast cancer; Deep learning; Breast imaging; Breast tumor; Artificial intelligence; Computer-aided diagnosis; Feature extraction; Process (computing); Medical physics; Medicine; Cancer; Engineering drawing; Engineering","score_opus":0.056407442004357586,"score_gpt":0.35221509900398956,"score_spread":0.29580765699963196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091106624","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9666516e-9,0.5743491,0.42152095,0.0012248877,0.0011715573,0.0012675064,0.000018922696,0.00026869512,0.00017838339],"genre_scores_gemma":[0.00003303952,0.9811727,0.014265897,0.0011998301,0.0008451779,0.0024199036,0.0000076920305,0.000043812735,0.000011978413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99533933,0.00027088076,0.00092250406,0.001809977,0.0009024555,0.00075485854],"domain_scores_gemma":[0.9970399,0.0012103107,0.0006309965,0.0006219946,0.00020765097,0.0002891321],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014047235,0.00061780727,0.0019177395,0.00023160233,0.00066577666,0.0008172466,0.0030668504,0.00015725556,0.00002284695],"category_scores_gemma":[0.00009479597,0.00049511786,0.0004706742,0.0021322137,0.00051841064,0.00034436202,0.00038585806,0.00054626673,0.00008578876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014085515,0.000015841704,5.1989633e-7,0.031887375,0.000020911173,0.000005161806,0.00001567417,0.00032779673,2.1043105e-7,0.0066480967,0.0022735756,0.9588034],"study_design_scores_gemma":[0.00009954826,0.00006504851,5.6047077e-7,0.01891061,0.00021498637,0.000091107504,0.0000047935123,0.18668859,5.160448e-7,0.00010969575,0.7933004,0.00051417114],"about_ca_topic_score_codex":0.000033733948,"about_ca_topic_score_gemma":0.000003008625,"teacher_disagreement_score":0.95828927,"about_ca_system_score_codex":0.0003622343,"about_ca_system_score_gemma":0.0013975287,"threshold_uncertainty_score":0.99975},"labels":[],"label_agreement":null},{"id":"W3091129043","doi":"10.1109/ijcnn48605.2020.9206855","title":"Data augmentation for histopathological images based on gaussian-laplacian pyramid blending","year":2020,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Pyramid (geometry); Artificial intelligence; Laplace operator; Gaussian process; Computer science; Gaussian; Image (mathematics); Pattern recognition (psychology); Process (computing); Function (biology); Gaussian function; Laplacian matrix; Class (philosophy); Computer vision; Algorithm; Machine learning; Mathematics","score_opus":0.056636248269656526,"score_gpt":0.30696380715864824,"score_spread":0.2503275588889917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091129043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014841094,0.000044313656,0.9658029,0.02983148,0.00077331235,0.00040059836,0.00006915203,0.00037428527,0.0012198141],"genre_scores_gemma":[0.8959494,0.00000909975,0.09941319,0.0038035684,0.000378457,0.00006952339,0.00006913909,0.000025359977,0.00028223605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983171,0.0000868647,0.00018464643,0.00080759084,0.00031745582,0.00028629624],"domain_scores_gemma":[0.9987247,0.00016871643,0.00013801974,0.0007999518,0.000037008645,0.00013159255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000350765,0.0001703638,0.00016571628,0.00008805096,0.00019819476,0.0001761962,0.0010611613,0.000077476674,0.000037475376],"category_scores_gemma":[0.0002274844,0.00016335679,0.000051151706,0.0003295411,0.00005162859,0.0006334532,0.00025763636,0.0001721488,0.00009016826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018774465,0.0006579738,0.002571861,0.00059587037,0.000082967614,0.00046141646,0.005440534,0.026485719,0.106430255,0.028696138,0.35273302,0.4739668],"study_design_scores_gemma":[0.0013318965,0.00083337724,0.0024629189,0.000050213253,0.000023867302,0.000010992183,0.00011255806,0.8957072,0.019674182,0.00043575562,0.078930564,0.00042649097],"about_ca_topic_score_codex":0.0000049244595,"about_ca_topic_score_gemma":0.000008391839,"teacher_disagreement_score":0.8944653,"about_ca_system_score_codex":0.00019548682,"about_ca_system_score_gemma":0.000078217956,"threshold_uncertainty_score":0.6661496},"labels":[],"label_agreement":null},{"id":"W3091941748","doi":"10.1038/s41467-020-18883-x","title":"Identification of 31 loci for mammographic density phenotypes and their associations with breast cancer risk","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute on Aging; Cancer Research UK; Horizon 2020 Framework Programme; European Commission; Ellison Medical Foundation; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; Kaiser Permanente; Wayne and Gladys Valley Foundation; U.S. Department of Health and Human Services; National Institutes of Health; Government of Canada","keywords":"Breast cancer; Phenotype; MAMMOGRAPHIC DENSITY; Identification (biology); Genome-wide association study; Genetics; Cancer; Mammography; Oncology; Biology; Medicine; Bioinformatics; Single-nucleotide polymorphism; Gene; Genotype","score_opus":0.014962488347751277,"score_gpt":0.26374288293788495,"score_spread":0.24878039459013368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091941748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12982681,0.008630924,0.7928497,0.065448575,0.00023726924,0.0012676035,0.0012025189,0.00037197545,0.00016459884],"genre_scores_gemma":[0.9836604,0.00073937996,0.015155888,0.00027474636,0.00003685084,0.000094512805,0.000023195822,0.000008737108,0.0000062945123],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992899,0.00008590648,0.00019440992,0.00021785525,0.00011315982,0.00009880332],"domain_scores_gemma":[0.9979437,0.00027145533,0.00034140522,0.0009149757,0.00047748667,0.000050953233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021357491,0.000091792,0.00013213202,0.00006356995,0.00037570662,0.000068072455,0.0008980943,0.00012108375,8.051136e-7],"category_scores_gemma":[0.000086637854,0.00007804356,0.00004644343,0.0006859946,0.00012436928,0.0002854841,0.00020248975,0.0003805667,6.995254e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022825078,0.0006121971,0.4396705,0.00026467515,0.0013879864,3.126596e-7,0.020383688,0.0012797092,0.035583388,0.24256131,0.013555692,0.2444723],"study_design_scores_gemma":[0.00091219705,0.00013524115,0.8289439,0.000041826097,0.00018731391,0.000008813954,0.00033244287,0.14255224,0.009436878,0.008920803,0.008100186,0.00042813388],"about_ca_topic_score_codex":0.00009200913,"about_ca_topic_score_gemma":0.0009904007,"teacher_disagreement_score":0.85383356,"about_ca_system_score_codex":0.0000537299,"about_ca_system_score_gemma":0.00009292156,"threshold_uncertainty_score":0.3182524},"labels":[],"label_agreement":null},{"id":"W3092020643","doi":"10.1016/j.nic.2020.06.003","title":"Overview of Machine Learning: Part 2","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"AI in cancer detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University Health Centre; McGill University; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Convolutional neural network; Machine learning; Generative grammar; Adversarial system; Computer science; Deep neural networks; Artificial neural network; Software deployment; Data science; Software engineering","score_opus":0.10365653277130599,"score_gpt":0.3698207546230629,"score_spread":0.2661642218517569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092020643","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013872447,0.9858889,0.012061574,0.00017380339,0.0010001691,0.00033469847,0.000046884925,0.00018606645,0.00030653918],"genre_scores_gemma":[0.00001767662,0.99429893,0.0050831777,0.00028307652,0.00015757466,0.000018397286,0.000030527965,0.00006475802,0.0000459034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961374,0.00048834254,0.0016003696,0.00090640195,0.00055468036,0.00031281877],"domain_scores_gemma":[0.99481255,0.0008690985,0.0028403483,0.0011701387,0.00015808,0.0001497803],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024741446,0.00045325593,0.0024035445,0.00022042269,0.00006156125,0.00003773069,0.0019877322,0.00008657692,0.000016715572],"category_scores_gemma":[0.0005746604,0.00043628464,0.00084146066,0.0017386506,0.00019340625,0.00020940782,0.000837706,0.0012035783,0.000062294384],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022564218,0.00003559946,0.0002279072,0.005447964,0.000055141696,0.000016787528,0.00002837683,0.000039441624,3.395505e-8,0.000018260087,0.000331344,0.9937969],"study_design_scores_gemma":[0.00009282743,0.00031803563,0.00003174512,0.001915218,0.00021569406,0.000021511789,5.706104e-7,0.004957874,3.9942094e-7,0.000021522126,0.992139,0.00028562898],"about_ca_topic_score_codex":0.000034431538,"about_ca_topic_score_gemma":0.0000030188442,"teacher_disagreement_score":0.99351126,"about_ca_system_score_codex":0.000046731006,"about_ca_system_score_gemma":0.00051740295,"threshold_uncertainty_score":0.9998089},"labels":[],"label_agreement":null},{"id":"W3092224781","doi":"10.1007/978-3-030-58526-6_27","title":"On Transferability of Histological Tissue Labels in Computational Pathology","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jacobs (Canada); St. Michael's Hospital; University of Toronto","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Transferability; Workflow; Transfer of learning; Domain (mathematical analysis); Deep learning; Task (project management); Pattern recognition (psychology); Pathology; Machine learning; Medicine","score_opus":0.022524198242228833,"score_gpt":0.2618781675710318,"score_spread":0.23935396932880293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092224781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009490527,0.00016734813,0.99364316,0.0024525558,0.0010997669,0.00039696696,0.00000988437,0.00009496586,0.0011863055],"genre_scores_gemma":[0.7983616,0.000009975006,0.2001729,0.0013050707,0.00010289435,0.000010429564,0.0000037897921,0.000016164317,0.000017147295],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963745,0.00010559922,0.00069647026,0.0015819917,0.0008474962,0.000393925],"domain_scores_gemma":[0.99774224,0.0009947477,0.00022828022,0.00075583236,0.00016707076,0.000111854526],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007190743,0.00039052413,0.0007014906,0.00060882425,0.00008167653,0.00006518868,0.0020589707,0.0003952009,0.000032102656],"category_scores_gemma":[0.00015561597,0.00037263156,0.00009610326,0.0007030453,0.00094387325,0.00024047382,0.00044360934,0.0010142893,0.00002236379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040893705,0.00009092008,0.0001084244,0.00007389696,0.0000068298327,0.00024098062,0.0008975838,0.27204874,0.00041093724,0.115228176,0.000012391306,0.61084026],"study_design_scores_gemma":[0.00044113275,0.000995444,0.0010131451,0.00015433105,0.000003641996,0.00007300381,8.3569276e-8,0.298017,0.002004425,0.696625,0.00022894598,0.00044385841],"about_ca_topic_score_codex":0.000017040742,"about_ca_topic_score_gemma":0.00008644852,"teacher_disagreement_score":0.7974126,"about_ca_system_score_codex":0.000575494,"about_ca_system_score_gemma":0.0005014647,"threshold_uncertainty_score":0.99987257},"labels":[],"label_agreement":null},{"id":"W3092248730","doi":"10.1007/978-3-030-59830-3_56","title":"An Integrated Deep Architecture for Lesion Detection in Breast MRI","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Detector; Object detection; Process (computing); Computer vision; Architecture; Deep learning; Set (abstract data type); Object (grammar); Pattern recognition (psychology); Operating system","score_opus":0.014547379438402525,"score_gpt":0.24691594693178331,"score_spread":0.23236856749338078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092248730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000087273744,0.00013827777,0.9944377,0.0016721794,0.0021747013,0.00092300295,0.000011377405,0.00034411458,0.00021139756],"genre_scores_gemma":[0.44726676,0.000030831172,0.5499769,0.0015873912,0.00093725865,0.00007053092,0.000018318158,0.00008315104,0.00002884939],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954935,0.000078580226,0.0006254493,0.0022938969,0.00081752025,0.00069109764],"domain_scores_gemma":[0.99757874,0.000329003,0.00032911063,0.0012592737,0.0002602597,0.00024359842],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076287694,0.0006552094,0.00059190404,0.0012761491,0.0002633226,0.00053897314,0.0030483129,0.0005469137,0.000008359987],"category_scores_gemma":[0.000062948435,0.00061843265,0.000158412,0.001351573,0.00038584604,0.0007472913,0.0005543338,0.0013919255,0.000014802716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005318385,0.000021886684,0.000017279714,0.000038507143,0.0000051428615,0.000024294766,0.0005774755,0.10275959,0.0014774373,0.00095354026,0.0000044911926,0.89406717],"study_design_scores_gemma":[0.00046729154,0.0005781074,0.00016689167,0.00029303122,0.0000073919055,0.00018676075,5.767749e-7,0.90335095,0.00647638,0.08580309,0.0019594932,0.0007100368],"about_ca_topic_score_codex":0.00008631692,"about_ca_topic_score_gemma":0.001854637,"teacher_disagreement_score":0.89335716,"about_ca_system_score_codex":0.0009654811,"about_ca_system_score_gemma":0.0005149113,"threshold_uncertainty_score":0.9996267},"labels":[],"label_agreement":null},{"id":"W3092489655","doi":"10.1016/j.nic.2020.06.002","title":"Knowledge Based Versus Data Based","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Deep learning; Big data; Data science; Relevance (law); Complementarity (molecular biology); Data-driven; Artificial intelligence; Medicine; Field (mathematics); Medical knowledge; Computer science; Data mining","score_opus":0.18952495168388397,"score_gpt":0.41193944291022333,"score_spread":0.22241449122633936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092489655","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0840352e-7,0.8076984,0.18688445,0.00032915597,0.0034504721,0.0004736608,0.00025459827,0.0003910342,0.0005179855],"genre_scores_gemma":[0.000021146716,0.9591711,0.03938426,0.0006056004,0.000366519,0.00003165909,0.0003038301,0.00010464331,0.000011216246],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531114,0.0005306886,0.0012947115,0.0018670891,0.0005469269,0.00044942764],"domain_scores_gemma":[0.990399,0.002941874,0.0015828362,0.0046455623,0.00018279477,0.00024794636],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00033370382,0.00060032064,0.0019378695,0.00033773034,0.00010880651,0.00012375283,0.0068884287,0.00011767771,0.00001311137],"category_scores_gemma":[0.0010476697,0.0006111329,0.000546504,0.0023526563,0.00023867672,0.00041970372,0.0017738313,0.0011267139,0.00023631028],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013830303,0.000070538204,0.000019519657,0.0025982868,0.00004131286,0.000029974262,0.000007866563,0.000060023187,1.4773855e-8,0.0000032677106,0.0025801898,0.9945752],"study_design_scores_gemma":[0.00036818435,0.00025664482,0.000010974772,0.0009090612,0.0002867056,0.0000027397343,4.0049324e-7,0.16470437,1.8308415e-7,0.0000022460326,0.83307666,0.00038183393],"about_ca_topic_score_codex":0.000017905511,"about_ca_topic_score_gemma":0.000011193613,"teacher_disagreement_score":0.9941933,"about_ca_system_score_codex":0.00011699382,"about_ca_system_score_gemma":0.0028073057,"threshold_uncertainty_score":0.999634},"labels":[],"label_agreement":null},{"id":"W3092560349","doi":"10.3390/cancers12102934","title":"Integrative Data Augmentation with U-Net Segmentation Masks Improves Detection of Lymph Node Metastases in Breast Cancer Patients","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; CancerCare Manitoba Foundation; Manitoba Medical Service Foundation","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Lymph node; Histopathology; Pattern recognition (psychology); Breast cancer; Image segmentation; Medicine; Cancer; Pathology; Internal medicine","score_opus":0.021664223550062933,"score_gpt":0.2719270725993069,"score_spread":0.25026284904924395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092560349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50203925,0.00019620768,0.4951216,0.0006931401,0.00061255833,0.0006279994,0.0005232301,0.00010434883,0.00008163142],"genre_scores_gemma":[0.9945961,0.00008510291,0.00468228,0.0003840984,0.000056471024,0.00010773767,0.000069606824,0.000013764174,0.000004823985],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986387,0.000079683676,0.00027333872,0.0005179754,0.0003184999,0.0001718324],"domain_scores_gemma":[0.9991334,0.00003375159,0.00029180138,0.00033071195,0.00014155518,0.00006877296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009568323,0.00015983621,0.000182353,0.000105021485,0.000050706356,0.000047145855,0.00048739053,0.00003899411,0.000014214624],"category_scores_gemma":[0.000012991998,0.00013799992,0.000021359207,0.00076357636,0.00006446218,0.0014112816,0.0001341384,0.00010076656,0.000002257424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015044517,0.000104641564,0.03647137,0.00033819984,0.0003485996,0.0000061775286,0.013445592,0.050245345,0.19376023,0.00012303596,0.0007291587,0.7029232],"study_design_scores_gemma":[0.0068859155,0.00091425213,0.15621026,0.0003858928,0.00017732153,0.000007428894,0.0037426797,0.37160328,0.45874846,0.00020925234,0.00024837136,0.0008668901],"about_ca_topic_score_codex":0.004596122,"about_ca_topic_score_gemma":0.0012231674,"teacher_disagreement_score":0.7020563,"about_ca_system_score_codex":0.0015287886,"about_ca_system_score_gemma":0.00042024205,"threshold_uncertainty_score":0.69479924},"labels":[],"label_agreement":null},{"id":"W3093420096","doi":"10.1016/j.compbiomed.2020.104053","title":"Improving prostate cancer classification in H&amp;E tissue micro arrays using Ki67 and P63 histopathology","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC; University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Prostate cancer; Prostatectomy; Stain; Histopathology; H&E stain; Artificial intelligence; Medicine; Pathology; Prostate; Biopsy; Receiver operating characteristic; Digital pathology; Cancer; Pattern recognition (psychology); Computer science; Immunohistochemistry; Staining; Internal medicine","score_opus":0.04887575959474036,"score_gpt":0.334170937419649,"score_spread":0.28529517782490865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093420096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4399156,0.0031469348,0.54647106,0.009294827,0.0009066898,0.0001959821,0.000001030099,0.00004115767,0.00002674829],"genre_scores_gemma":[0.9475025,0.00064286246,0.049267977,0.0023165767,0.00023416805,0.000017635008,0.000003962115,0.000006668887,0.000007660108],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989647,0.00010629579,0.00023791674,0.0004593429,0.00003796792,0.00019377508],"domain_scores_gemma":[0.99958915,0.00007804641,0.000105509935,0.00013640625,0.000023380975,0.000067524714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478785,0.00011198484,0.00023187973,0.00014129197,0.000053576605,0.000008047522,0.00016730392,0.000107417574,0.0000021644234],"category_scores_gemma":[0.000044156528,0.00010006754,0.0000063409125,0.00025952523,0.00026757867,0.00010456452,0.00013878159,0.00020595807,6.2384385e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005908677,0.000015806268,0.08337526,0.000107207175,0.0000051841666,0.000026912176,0.007955812,0.00011258389,0.4976522,0.0017907622,0.00020752392,0.40869167],"study_design_scores_gemma":[0.007101746,0.0018047523,0.31453145,0.0006758183,0.000039788305,0.00034734988,0.0004358605,0.6324068,0.006252422,0.009325827,0.026090113,0.0009881252],"about_ca_topic_score_codex":0.00031976204,"about_ca_topic_score_gemma":0.00011496351,"teacher_disagreement_score":0.6322942,"about_ca_system_score_codex":0.00010236058,"about_ca_system_score_gemma":0.000044181805,"threshold_uncertainty_score":0.4080636},"labels":[],"label_agreement":null},{"id":"W3093754645","doi":"10.5858/arpa.2020-0168-le","title":"Issues to Consider When Implementing Digital Pathology for Primary Diagnosis","year":2020,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Digital pathology; Pathology; Medicine; Medical physics","score_opus":0.02698780952294372,"score_gpt":0.30460142424857417,"score_spread":0.27761361472563045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093754645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22211954,0.0030109098,0.69140595,0.07893208,0.0010062974,0.0011907557,0.0001927594,0.000591446,0.0015502364],"genre_scores_gemma":[0.7261931,0.0002154222,0.24412282,0.027858788,0.00092438114,0.0004773107,0.000037094986,0.00010554747,0.000065539156],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982097,0.00014373135,0.0004861276,0.00059561734,0.00017110986,0.00039369933],"domain_scores_gemma":[0.9981774,0.0008488905,0.00021938,0.00044099955,0.00012398855,0.00018932647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003056177,0.00018927442,0.00047118738,0.00015926723,0.000080916194,0.00001563532,0.0005858656,0.00006222352,0.000046024892],"category_scores_gemma":[0.00076632097,0.0001727503,0.00005772077,0.00028126605,0.00040839854,0.00026342183,0.00041480223,0.00014673539,0.000020441967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003994453,0.00023378043,0.09061255,0.0007219513,0.00024223213,0.00095572893,0.09622836,0.00006766549,0.34984744,0.019070853,0.16144732,0.28017268],"study_design_scores_gemma":[0.009334818,0.016525537,0.058807008,0.0006731305,0.00027597946,0.00029010177,0.0045984313,0.0022381023,0.14502698,0.04990466,0.7104912,0.0018340723],"about_ca_topic_score_codex":0.0000048121524,"about_ca_topic_score_gemma":0.0000059765653,"teacher_disagreement_score":0.54904383,"about_ca_system_score_codex":0.00001746496,"about_ca_system_score_gemma":0.00011138293,"threshold_uncertainty_score":0.70445526},"labels":[],"label_agreement":null},{"id":"W3094581989","doi":"10.1109/access.2020.3033492","title":"Class-Aware Image Search for Interpretable Cancer Identification","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Research Foundation","keywords":"Computer science; Metadata; Classifier (UML); Class (philosophy); Image retrieval; Artificial intelligence; Identification (biology); Contextual image classification; Information retrieval; Pattern recognition (psychology); Machine learning; Image (mathematics); Data mining; World Wide Web","score_opus":0.07552827989904269,"score_gpt":0.3792257880732647,"score_spread":0.303697508174222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094581989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010199145,0.000060613263,0.98167896,0.0058503146,0.0013282626,0.00034775035,0.000017954419,0.00020517997,0.00031181957],"genre_scores_gemma":[0.9959375,0.00002725008,0.0020247425,0.00118272,0.00039097693,0.00024946252,0.000002597635,0.000015271436,0.00016945852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989087,0.000031997086,0.00018705257,0.00043465028,0.00021839574,0.00021918125],"domain_scores_gemma":[0.9992243,0.00005648614,0.000080096885,0.00034596026,0.00020806618,0.000085078726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015335823,0.000091671645,0.00010779063,0.000052150706,0.00011772103,0.0006271046,0.0014039037,0.000046849018,0.00003563338],"category_scores_gemma":[0.000018508126,0.000094216695,0.000052210737,0.00045153254,0.000028886248,0.002015327,0.00018601038,0.000117797455,0.000054854572],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022357864,0.0001065022,0.003411409,0.0009172801,0.00015404708,0.000012333954,0.0060572666,0.013841181,0.2906717,0.0032364195,0.16937448,0.51199377],"study_design_scores_gemma":[0.0002308986,0.00004539881,0.00071703194,0.00002016693,0.000007902811,0.0000011841022,0.000020739657,0.5226422,0.46829802,0.0005295361,0.007333596,0.00015332247],"about_ca_topic_score_codex":0.0001640258,"about_ca_topic_score_gemma":0.000037044076,"teacher_disagreement_score":0.9857384,"about_ca_system_score_codex":0.00012765417,"about_ca_system_score_gemma":0.00010851712,"threshold_uncertainty_score":0.6047184},"labels":[],"label_agreement":null},{"id":"W3095595608","doi":"10.1016/j.compbiomed.2020.104089","title":"Application of decision tree-based ensemble learning in the classification of breast cancer","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":245,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Random forest; Decision tree; Computer science; Artificial intelligence; Breast cancer; Machine learning; Ensemble learning; Identification (biology); Diameter at breast height; Data mining; Cancer; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.02670427814717933,"score_gpt":0.31615610318075915,"score_spread":0.2894518250335798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095595608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13257286,0.0002917933,0.8578419,0.00901333,0.00010792374,0.000112119706,4.363716e-7,0.000011061689,0.0000485447],"genre_scores_gemma":[0.9948197,0.00009338648,0.0044474676,0.0005684317,0.000052357304,0.00001437304,0.0000023895245,0.0000016044037,2.693807e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993625,0.00010908913,0.00021199526,0.00018272774,0.00006604451,0.0000676218],"domain_scores_gemma":[0.9993749,0.000320678,0.0001264096,0.00012680891,0.000033206547,0.000017979173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034670476,0.000051204664,0.0001418806,0.00008773182,0.000019209581,0.0000015612295,0.00024411564,0.000053308293,9.956184e-7],"category_scores_gemma":[0.000032051423,0.000034832192,0.000010213618,0.0004155182,0.00012583543,0.000036930236,0.000033589735,0.00011731065,2.0991743e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072662144,0.000020570142,0.08212645,0.000030920626,0.0000030808512,6.387832e-7,0.0013994502,0.0013933145,0.0270744,0.0046964316,0.00007563412,0.88310647],"study_design_scores_gemma":[0.00078143744,0.0002583743,0.44995463,0.00009300583,0.0000033481392,0.000003682451,0.000079105994,0.546252,0.0005859179,0.0016224036,0.00032544296,0.00004061309],"about_ca_topic_score_codex":0.00011191992,"about_ca_topic_score_gemma":0.00004862815,"teacher_disagreement_score":0.8830658,"about_ca_system_score_codex":0.000020941428,"about_ca_system_score_gemma":0.000027490314,"threshold_uncertainty_score":0.14204155},"labels":[],"label_agreement":null},{"id":"W3095903828","doi":"10.48550/arxiv.2010.15865","title":"Ink Marker Segmentation in Histopathology Images Using Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Histopathology; Digital pathology; Pixel; Artificial intelligence; Computer science; Segmentation; Image segmentation; Computer vision; Pattern recognition (psychology); Process (computing); Digital image; Image processing; Pathology; Image (mathematics); Medicine","score_opus":0.073377194391096,"score_gpt":0.20610999964459784,"score_spread":0.13273280525350184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095903828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25581336,0.00006492868,0.74242425,0.00008534706,0.00059286784,0.00015470955,9.968504e-7,0.00016320261,0.0007003599],"genre_scores_gemma":[0.9860062,0.0001122103,0.013505905,0.000083929786,0.00006416478,0.0000010898559,0.0000059152508,0.000017032018,0.00020354953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981804,0.00033214482,0.0001875161,0.0009752881,0.0000753632,0.00024928214],"domain_scores_gemma":[0.99908966,0.000061301274,0.0002685697,0.0004370933,0.00006918978,0.00007421635],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022861827,0.00021345765,0.0002432397,0.0003345492,0.00010902671,0.00006944889,0.0007642236,0.00022495928,0.000023174242],"category_scores_gemma":[0.00003865364,0.00029490655,0.00009129383,0.00062393857,0.00007147446,0.00044665136,0.0013797177,0.0008293302,0.0000324201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064311855,0.00003994618,0.047900137,0.00012427702,0.000026737343,0.0010879963,0.0012856673,0.9330498,0.0043062796,0.0039682947,0.00004208854,0.008104453],"study_design_scores_gemma":[0.000377854,0.00004915212,0.01632881,0.000055267774,0.00002979467,0.00001473764,0.000116078816,0.96904534,0.0005890073,0.012887606,0.00015396038,0.00035240172],"about_ca_topic_score_codex":0.00024643313,"about_ca_topic_score_gemma":0.00006077541,"teacher_disagreement_score":0.73019284,"about_ca_system_score_codex":0.0010450578,"about_ca_system_score_gemma":0.00012549569,"threshold_uncertainty_score":0.9999503},"labels":[],"label_agreement":null},{"id":"W3096661578","doi":"10.1002/path.5577","title":"Generative models in pathology: synthesis of diagnostic quality pathology images<sup>†</sup>","year":2020,"lang":"en","type":"letter","venue":"The Journal of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Deep learning; Artificial intelligence; Generative model; Computer science; Field (mathematics); Confidentiality; Quality (philosophy); Pathology; Medicine","score_opus":0.04101185343288608,"score_gpt":0.2866458827667333,"score_spread":0.24563402933384723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096661578","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023265632,0.0022363719,0.48055992,0.49135056,0.0015894236,0.00048393355,0.00011357148,0.000058730668,0.00034184824],"genre_scores_gemma":[0.5097541,0.005159256,0.049296852,0.4294968,0.005807489,0.00014413106,0.00001590609,0.00019311743,0.0001323476],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9881971,0.0077802856,0.002027777,0.0006575552,0.000659551,0.0006777336],"domain_scores_gemma":[0.987349,0.0081949,0.002651238,0.0012227722,0.0004905065,0.00009161718],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037341095,0.00054028624,0.0017864222,0.0006131174,0.0001199473,0.00003733269,0.0029951152,0.0010086814,0.000026459658],"category_scores_gemma":[0.0031050674,0.00040424115,0.00039714554,0.0006134407,0.00077641464,0.0004561052,0.00071089476,0.0041326564,0.000025128003],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075534725,0.0005916497,0.00078279345,0.00093333237,0.0006851513,0.17524685,0.041280713,0.084581465,0.019088535,0.0022101628,0.61026067,0.06358332],"study_design_scores_gemma":[0.009022197,0.012477931,0.008619529,0.0023467017,0.0027973843,0.16767806,0.0026730313,0.08928431,0.05870034,0.6086077,0.03131066,0.00648215],"about_ca_topic_score_codex":0.000034329263,"about_ca_topic_score_gemma":0.000011616134,"teacher_disagreement_score":0.60639757,"about_ca_system_score_codex":0.0002902647,"about_ca_system_score_gemma":0.00045546624,"threshold_uncertainty_score":0.999841},"labels":[],"label_agreement":null},{"id":"W3096916126","doi":"10.1088/1742-6596/1646/1/012069","title":"U-shaped Feature Extractor Used on Mask R-CNN for Cell Nuclei Image Segmentation","year":2020,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Feature (linguistics); Segmentation; Pattern recognition (psychology); Extractor; Image (mathematics); Noise (video); Data set; Set (abstract data type); Computer vision","score_opus":0.035931844278312364,"score_gpt":0.2646383047354992,"score_spread":0.22870646045718684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096916126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022475172,0.000022190228,0.97127134,0.00511473,0.000584601,0.00020729958,0.000012982984,0.00004848711,0.00026317334],"genre_scores_gemma":[0.93170905,0.000029476134,0.067170896,0.0004021478,0.00058650103,0.0000071476875,0.000002440138,0.000016441658,0.00007591672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989526,0.00005481235,0.00025607384,0.0002063389,0.0003589612,0.00017118828],"domain_scores_gemma":[0.99873465,0.00010198181,0.00050223275,0.00017054324,0.0003771661,0.00011341117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013061213,0.00015807326,0.00024209853,0.000037082853,0.00009867031,0.0002983261,0.00050114124,0.000058485064,0.000014956968],"category_scores_gemma":[0.000033141874,0.00014148952,0.00013249522,0.00019838619,0.0000426365,0.0018975761,0.00005012409,0.0002821459,0.000014771601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003506818,0.00008364647,0.00004419802,0.00012042569,0.00003789452,0.000010532482,0.0039568674,0.00007774412,0.9390664,0.010829615,0.0016374319,0.043784525],"study_design_scores_gemma":[0.0010702867,0.0017797734,0.00043126562,0.00006518992,0.000027558724,0.000008597217,0.0005148968,0.007254408,0.97643703,0.010014465,0.0021746557,0.00022188007],"about_ca_topic_score_codex":0.0000011066727,"about_ca_topic_score_gemma":9.942274e-7,"teacher_disagreement_score":0.90923387,"about_ca_system_score_codex":0.00007293221,"about_ca_system_score_gemma":0.00020696108,"threshold_uncertainty_score":0.57697755},"labels":[],"label_agreement":null},{"id":"W3098301945","doi":"10.1101/396663","title":"Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Spinal Cord Injury BC","funders":"Chiba University; Weill Cornell Medical College; National Cancer Institute; National Institutes of Health; Pfizer; Amgen","keywords":"Social media; Classifier (UML); Artificial intelligence; Disease; Deep learning; Computer science; Machine learning; Digital pathology; Medicine; Pathology; World Wide Web","score_opus":0.019530085433410952,"score_gpt":0.2628129422653458,"score_spread":0.24328285683193485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098301945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58271325,0.00042978846,0.40367782,0.0010412893,0.0069403104,0.0024215132,0.00023707795,0.0024916711,0.000047265865],"genre_scores_gemma":[0.96197045,0.0001720184,0.034732074,0.00025522482,0.0019107226,0.0007498154,0.0000015228977,0.00018659719,0.00002156707],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99462914,0.000564564,0.0006734296,0.002229715,0.0007462389,0.0011568898],"domain_scores_gemma":[0.9958926,0.00053856213,0.0005272329,0.0016840982,0.00094194314,0.00041556603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001514666,0.0007476555,0.00079728384,0.0004979574,0.0006165718,0.00051736325,0.001999717,0.00074853795,0.000063845444],"category_scores_gemma":[0.0008138392,0.0008596244,0.00026501456,0.0005826937,0.00029640502,0.00039256996,0.0016089027,0.0013179674,0.00038019745],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011649233,0.0008359704,0.002025619,0.0013438235,0.00056662044,0.00052843336,0.001155033,0.0022940792,0.9772031,0.0026073086,0.007108666,0.003166466],"study_design_scores_gemma":[0.0037948606,0.001330553,0.15363798,0.00129105,0.00039405478,2.4230857e-7,0.000019494895,0.36242682,0.44973794,0.00016361507,0.021841772,0.005361632],"about_ca_topic_score_codex":0.000053007734,"about_ca_topic_score_gemma":0.000005161338,"teacher_disagreement_score":0.5274651,"about_ca_system_score_codex":0.00089392194,"about_ca_system_score_gemma":0.0009192064,"threshold_uncertainty_score":0.9993855},"labels":[],"label_agreement":null},{"id":"W3100061827","doi":"10.2196/19069","title":"Multidimensional Machine Learning Personalized Prognostic Model in an Early Invasive Breast Cancer Population-Based Cohort in China: Algorithm Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"West China Hospital, Sichuan University; Sichuan University; Department of Science and Technology of Sichuan Province; University of Cambridge","keywords":"Breast cancer; Computer science; Machine learning; Population; Cohort; Medicine; Algorithm; Artificial intelligence; Cancer; Internal medicine; Environmental health","score_opus":0.018467885150590477,"score_gpt":0.29089977678874923,"score_spread":0.27243189163815873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100061827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8116262,0.000008182528,0.18648782,0.00073141995,0.00009452894,0.00090599706,0.000010270539,0.00012444073,0.000011121794],"genre_scores_gemma":[0.97872025,0.0000055159194,0.020251082,0.000565404,0.00005809431,0.00031778394,0.000062666586,0.000013791832,0.000005429551],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973035,0.00017989313,0.000708686,0.00025245495,0.0012820563,0.00027341596],"domain_scores_gemma":[0.99907243,0.00013758492,0.00023244988,0.0001819324,0.00010296876,0.00027264722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005309494,0.00019138273,0.0002902812,0.00019003452,0.00009456754,0.00008081838,0.00040172582,0.00013198228,0.000052582112],"category_scores_gemma":[0.00017922928,0.00017800198,0.000038261398,0.0007391812,0.00003946381,0.0011386615,0.00014373651,0.0006647284,0.0000106385305],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003868777,0.00024348545,0.856901,0.000054870696,0.000012403378,0.000014895593,0.015843138,0.10799862,0.0000071478084,0.000047383415,0.000007896883,0.018830476],"study_design_scores_gemma":[0.0012792111,0.00014534689,0.3495199,0.00006695891,0.0000051123666,0.0000022220324,0.00020544475,0.64861405,0.0000093144345,0.00002187613,0.0000018445379,0.00012872054],"about_ca_topic_score_codex":0.0008970667,"about_ca_topic_score_gemma":0.00032289542,"teacher_disagreement_score":0.54061544,"about_ca_system_score_codex":0.00029350404,"about_ca_system_score_gemma":0.00047212554,"threshold_uncertainty_score":0.725871},"labels":[],"label_agreement":null},{"id":"W3101763508","doi":"10.1101/2020.11.19.390401","title":"piNET: An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Guelph; Toronto Metropolitan University","funders":"","keywords":"False positive paradox; Computer science; Artificial intelligence; Workflow; Segmentation; Pattern recognition (psychology); Proliferation index; Calculator; Medicine; Pathology","score_opus":0.017698729335239947,"score_gpt":0.27325284244129516,"score_spread":0.2555541131060552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101763508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061248314,0.00041861428,0.9235581,0.0032981404,0.0038592103,0.0020540585,0.00071558787,0.00484666,0.0000012840429],"genre_scores_gemma":[0.88157874,0.000068950656,0.11384884,0.0008025236,0.0019267215,0.0016101749,7.7045985e-7,0.0001619968,0.0000012885168],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958176,0.00017937669,0.00068006624,0.0019778947,0.00063460955,0.00071045477],"domain_scores_gemma":[0.99581206,0.0000766265,0.0006822651,0.0019404319,0.0010120327,0.00047658413],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004566426,0.0007275799,0.0006649033,0.00028287838,0.00032819962,0.001009783,0.0016667624,0.000908458,0.00002161421],"category_scores_gemma":[0.00016447446,0.00081086543,0.00019345082,0.00097256276,0.00009706126,0.00093116565,0.0007407712,0.0010169911,0.000027029231],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059838494,0.0009594508,0.03646196,0.0045501213,0.0014777805,0.00013142789,0.00034831217,0.019789048,0.89276433,0.032784577,0.009718183,0.00041643568],"study_design_scores_gemma":[0.0007768057,0.00016881447,0.20238212,0.0006976387,0.0001192721,1.176084e-7,0.0000019220363,0.6334148,0.15901549,0.00017803171,0.0015490428,0.0016959406],"about_ca_topic_score_codex":0.00014586898,"about_ca_topic_score_gemma":0.0000073666133,"teacher_disagreement_score":0.82033044,"about_ca_system_score_codex":0.00082583004,"about_ca_system_score_gemma":0.00155531,"threshold_uncertainty_score":0.99943423},"labels":[],"label_agreement":null},{"id":"W3104370314","doi":"10.1007/978-3-319-67558-9","title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","year":2017,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1132,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Generalization; Normalization (sociology); Deep learning; Machine learning; Pattern recognition (psychology); Domain (mathematical analysis); Representation (politics); Mathematics","score_opus":0.02024162509865219,"score_gpt":0.3487750863579071,"score_spread":0.3285334612592549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104370314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006289174,0.0002491761,0.9962004,0.00039291824,0.0016972475,0.00040797505,8.2318894e-7,0.00014242632,0.00028015513],"genre_scores_gemma":[0.12868372,0.0004207204,0.8688595,0.00052666,0.0009852214,0.00004331167,0.0000149773405,0.00004666295,0.0004192038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99405515,0.00022929789,0.0010235023,0.0023470332,0.0015288598,0.0008161373],"domain_scores_gemma":[0.99364734,0.0039087418,0.00066410424,0.001163582,0.00028626784,0.00032996607],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006641333,0.00047027346,0.0010316273,0.0016624288,0.00060938776,0.00095416565,0.003630531,0.0007709617,0.000021238293],"category_scores_gemma":[0.0037583646,0.0004466799,0.00030267035,0.0012841558,0.0011302881,0.00093585864,0.0021321678,0.0024997655,0.0000111179925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021500844,0.00002510265,0.008081738,0.000027088745,0.000028619543,0.00008821085,0.00037319653,0.034870267,0.0000047932594,0.000024859377,0.000024092054,0.95643055],"study_design_scores_gemma":[0.0007678116,0.00038883262,0.01223352,0.00021843202,0.000039685274,0.00004436056,3.419495e-7,0.9771528,0.00004512467,0.0067979903,0.0018353881,0.00047566803],"about_ca_topic_score_codex":0.000060315957,"about_ca_topic_score_gemma":0.0009454709,"teacher_disagreement_score":0.95595485,"about_ca_system_score_codex":0.00051717414,"about_ca_system_score_gemma":0.0015580169,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W3104447992","doi":"","title":"Segmentation Of Spiculated Masses In Mammographic Images","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Segmentation; Mammography; Artificial intelligence; False positive paradox; Computer science; Pattern recognition (psychology); Computer-aided diagnosis; Image segmentation; Linear discriminant analysis; Breast cancer; Computer vision; Cancer; Medicine","score_opus":0.014857129078638264,"score_gpt":0.24958951562715315,"score_spread":0.2347323865485149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104447992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15313438,0.0012748761,0.81592643,0.009343797,0.000688485,0.00071740494,0.000032023003,0.00031233247,0.01857026],"genre_scores_gemma":[0.8715971,0.0007388535,0.12656897,0.000021586206,0.000013063474,0.00007739264,0.00007523534,0.000023658748,0.00088411936],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99531484,0.0025155775,0.0005959237,0.00080946967,0.00048208988,0.00028209735],"domain_scores_gemma":[0.99395883,0.00050604116,0.0010363017,0.003071958,0.0013403554,0.00008654102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037539236,0.00027890346,0.00037545635,0.00062893477,0.00020144426,0.00049140665,0.0025382359,0.0002696407,0.00003075041],"category_scores_gemma":[0.0005845946,0.000314771,0.00017685242,0.00060747215,0.0003128584,0.0004550433,0.0018336434,0.00054269435,0.000009494261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046148958,0.0016793454,0.07918236,0.001561372,0.00033244884,0.000048686656,0.020820234,0.0024238857,0.053376146,0.14035644,0.001293532,0.6988794],"study_design_scores_gemma":[0.0014605834,0.000001856134,0.09632849,0.0052884417,0.000060812607,0.000021282858,0.00015153826,0.07980605,0.76966727,0.044630762,0.0014950956,0.0010878134],"about_ca_topic_score_codex":0.0030265301,"about_ca_topic_score_gemma":0.0019621486,"teacher_disagreement_score":0.71846277,"about_ca_system_score_codex":0.0001603403,"about_ca_system_score_gemma":0.00027688305,"threshold_uncertainty_score":0.99993044},"labels":[],"label_agreement":null},{"id":"W3105141008","doi":"10.1109/tmi.2021.3123461","title":"Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Discriminative model; Artificial intelligence; Pattern recognition (psychology); Computer science; Segmentation; Kullback–Leibler divergence; Support vector machine; Robustness (evolution); Contextual image classification; Machine learning; Image (mathematics)","score_opus":0.011602836616250028,"score_gpt":0.2640108282827661,"score_spread":0.25240799166651606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105141008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063585434,0.0002818609,0.9882078,0.0036815314,0.0010155883,0.00010531099,0.000002524915,0.00008750203,0.0002593297],"genre_scores_gemma":[0.9747064,0.00017966553,0.024419181,0.0005311224,0.000029665327,0.00004107879,0.0000026989155,0.000011499176,0.00007867102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984123,0.00017816797,0.00034807847,0.00043407915,0.00042287595,0.0002044888],"domain_scores_gemma":[0.99907255,0.00020736855,0.0000979285,0.00034341952,0.00014648125,0.00013227855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002856539,0.00013101782,0.00019379963,0.00015373537,0.00013985849,0.00004727464,0.00025511076,0.00008040859,0.00020855479],"category_scores_gemma":[0.00003008764,0.00013706989,0.000063216874,0.00038055668,0.00019518333,0.00037336114,0.000007298294,0.00029995583,0.000010662805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018704297,0.000116158895,0.00009732353,0.000052860083,0.000029630412,0.000020377664,0.0007349251,0.0012836187,0.16565165,0.0001042049,0.0000793435,0.8318112],"study_design_scores_gemma":[0.00047865926,0.000040425286,0.00031635436,0.000067481604,0.000029848314,0.00015323932,0.0003171218,0.8561912,0.14155276,0.00052851846,0.00018706784,0.00013732346],"about_ca_topic_score_codex":0.00010531349,"about_ca_topic_score_gemma":0.00007184078,"teacher_disagreement_score":0.96834785,"about_ca_system_score_codex":0.0001852424,"about_ca_system_score_gemma":0.00014856188,"threshold_uncertainty_score":0.5589548},"labels":[],"label_agreement":null},{"id":"W3105158752","doi":"10.1007/s12553-020-00506-6","title":"Automatic suspicions lesions segmentation based on variable-size windows in mammography images","year":2020,"lang":"en","type":"article","venue":"Health and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Thresholding; False positive paradox; Mammography; Segmentation; Computer science; Artificial intelligence; Histogram; Pixel; Pattern recognition (psychology); False positives and false negatives; Variable (mathematics); Computer vision; Breast cancer; Image (mathematics); Mathematics; Cancer; Medicine","score_opus":0.013629253939995428,"score_gpt":0.26460737760668257,"score_spread":0.25097812366668715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105158752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05905735,0.00058331655,0.7068603,0.23020084,0.00032946587,0.0010086461,0.000013875811,0.0015430963,0.00040308316],"genre_scores_gemma":[0.9072506,0.00006091234,0.085419804,0.0071363486,0.000017243672,0.00010207376,0.0000022899137,0.000007238064,0.0000035222633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990816,0.000059187718,0.00020763028,0.00030598458,0.00010096104,0.00024460853],"domain_scores_gemma":[0.9994342,0.00011739637,0.0000837259,0.00022656996,0.000020912354,0.00011719491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013279304,0.000088198816,0.00014572153,0.0003329423,0.0001344395,0.000022130384,0.00019928251,0.00009429099,0.000012203341],"category_scores_gemma":[0.0001045677,0.00008838322,0.000013730522,0.0015641713,0.000053729218,0.00010135468,0.000058952573,0.00022434237,0.0000056393437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004320456,0.00021652688,0.025111191,0.00048440014,0.000013874413,0.000029215611,0.00081012823,0.0006132393,0.0020811362,0.06307818,0.003699868,0.903819],"study_design_scores_gemma":[0.0039878744,0.004570027,0.016617745,0.00030831087,0.000009916103,0.00003852388,0.0006520524,0.9223687,0.005602218,0.03725472,0.008016952,0.00057293347],"about_ca_topic_score_codex":0.000049339942,"about_ca_topic_score_gemma":0.000018545745,"teacher_disagreement_score":0.9217555,"about_ca_system_score_codex":0.000064572225,"about_ca_system_score_gemma":0.00019668015,"threshold_uncertainty_score":0.3604163},"labels":[],"label_agreement":null},{"id":"W3105293757","doi":"10.1101/2020.11.12.20230623","title":"Relation of Quantitative Histologic and Radiologic Breast Tissue Composition Metrics with Invasive Breast Cancer Risk","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Breast Cancer Research Foundation; Division of Cancer Epidemiology and Genetics, National Cancer Institute; U.S. Department of Health and Human Services","keywords":"Breast cancer; Medicine; Odds ratio; Breast disease; Confidence interval; Stroma; Oncology; Biopsy; Cancer; Internal medicine; Risk factor; Case-control study; Immunohistochemistry","score_opus":0.03187650729287215,"score_gpt":0.27337849090136906,"score_spread":0.24150198360849692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105293757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5099571,0.0017775934,0.48493913,0.0017100198,0.0006750113,0.0005074207,0.00017800866,0.00015546136,0.000100276135],"genre_scores_gemma":[0.9658446,0.0013119784,0.032584596,0.000060814928,0.000073464515,0.00007890595,0.000021431366,0.000017554094,0.0000066859047],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978054,0.00040400474,0.00038697332,0.0008456799,0.00036568844,0.0001922411],"domain_scores_gemma":[0.99771094,0.00036107042,0.0010180476,0.00047671702,0.00033627538,0.00009693791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034529238,0.00029560865,0.0005201991,0.0002891349,0.00012237036,0.000059465154,0.00055873155,0.0002586843,0.000011742411],"category_scores_gemma":[0.00007647273,0.00024784438,0.00005689111,0.00078132655,0.00022904828,0.00026667127,0.00052054843,0.0006706299,0.0000059069916],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006154424,0.00017726018,0.8865567,0.0011681152,0.0006476193,0.00011881478,0.0056334888,0.026090693,0.014406116,0.008800872,0.0003612317,0.055423692],"study_design_scores_gemma":[0.0004784292,0.0005308228,0.96168005,0.00031363274,0.00016903204,0.00025928923,0.000054594184,0.025601896,0.0037587476,0.0066647506,0.00003585494,0.00045287036],"about_ca_topic_score_codex":0.00087967276,"about_ca_topic_score_gemma":0.000116102034,"teacher_disagreement_score":0.4558875,"about_ca_system_score_codex":0.00034877774,"about_ca_system_score_gemma":0.00022256107,"threshold_uncertainty_score":0.9999974},"labels":[],"label_agreement":null},{"id":"W3106174756","doi":"10.1109/access.2020.3036662","title":"On Segmentation of Pectoral Muscle in Digital Mammograms by Means of Deep Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Deep learning; Mammography; Convolutional neural network; Digital mammography; Pattern recognition (psychology); Pectoral muscle; Image segmentation; Shortest path problem; Graph; Artificial neural network; Computer vision; Anatomy; Breast cancer; Medicine","score_opus":0.022427694370021747,"score_gpt":0.27874375782394273,"score_spread":0.256316063453921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106174756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64321536,0.000016911648,0.35614005,0.000107031745,0.00014386396,0.00007400013,0.0000020676162,0.000036339523,0.0002644023],"genre_scores_gemma":[0.9993019,0.0000035419866,0.00057560846,0.00007618564,0.000023309383,0.0000062420536,0.0000023263713,0.00000586525,0.000005015795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929595,0.000022346345,0.0001785485,0.00018743164,0.0002179063,0.00009779323],"domain_scores_gemma":[0.9996329,0.000050291586,0.000128976,0.00011247149,0.000035951452,0.000039428483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000054613483,0.000061799474,0.00010198713,0.000052193926,0.000017484143,0.00007511573,0.000432217,0.000027538239,0.000011201941],"category_scores_gemma":[0.000037354337,0.00006466142,0.000029105964,0.00045051964,0.000022275586,0.0008740322,0.00006432455,0.0000976014,0.0000036394456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008136402,0.00016410596,0.04335748,0.00012499733,0.000021146827,0.0000068440445,0.004993633,0.06064969,0.051692,0.00032671986,0.00047377817,0.83810824],"study_design_scores_gemma":[0.0016425698,0.0013246178,0.026880216,0.000089804766,0.000009763226,0.0000018397674,0.00033438872,0.3919678,0.5749685,0.0019260376,0.00044388787,0.0004105555],"about_ca_topic_score_codex":0.00009020107,"about_ca_topic_score_gemma":0.00002860685,"teacher_disagreement_score":0.8376977,"about_ca_system_score_codex":0.000043070846,"about_ca_system_score_gemma":0.000014031824,"threshold_uncertainty_score":0.26368162},"labels":[],"label_agreement":null},{"id":"W3107625569","doi":"10.1016/j.media.2020.101912","title":"Learning to segment images with classification labels","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society","keywords":"Computer science; Segmentation; Artificial intelligence; Ground truth; Annotation; Class (philosophy); Task (project management); Pattern recognition (psychology); Image segmentation; Labeled data; Machine learning","score_opus":0.015341976670133681,"score_gpt":0.2692718852778553,"score_spread":0.2539299086077216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107625569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008840118,0.00002329205,0.9540822,0.035966113,0.000027653055,0.000071418785,6.296569e-7,0.00021008386,0.0007784931],"genre_scores_gemma":[0.9284187,0.000022077866,0.06730404,0.0038483397,0.00013718149,0.00003339992,0.000006288426,0.000009626745,0.00022035743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814165,0.00011047806,0.00020028555,0.0004772985,0.0008706614,0.00019962677],"domain_scores_gemma":[0.9990355,0.000064738255,0.000076923374,0.00030558257,0.00011825275,0.00039904608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033020444,0.000104877254,0.00020625126,0.00015053319,0.0001036131,0.00014905522,0.000563387,0.00004493176,0.00030005616],"category_scores_gemma":[0.00029778396,0.00008383366,0.000080857484,0.0028404456,0.000049161867,0.0003058654,0.00016868852,0.00023408102,0.00021474269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066290915,0.00016249742,0.023711646,0.00006184959,0.0017964663,0.00029099573,0.006902458,0.0075078364,0.026462086,0.00039182222,0.013859446,0.9187866],"study_design_scores_gemma":[0.00039934914,0.00048514464,0.01603515,0.000020763171,0.00043071277,0.00000578009,0.00036769328,0.95983356,0.012184679,0.000039000664,0.009863051,0.00033512147],"about_ca_topic_score_codex":0.000042132135,"about_ca_topic_score_gemma":0.000019204092,"teacher_disagreement_score":0.9523257,"about_ca_system_score_codex":0.000069181915,"about_ca_system_score_gemma":0.00006813659,"threshold_uncertainty_score":0.34186372},"labels":[],"label_agreement":null},{"id":"W3108039948","doi":"10.1038/s41598-020-78061-3","title":"VISTA: VIsual Semantic Tissue Analysis for pancreatic disease quantification in murine cohorts","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pancreas Centre (Canada)","funders":"National Cancer Institute; Oregon Clinical and Translational Research Institute; Oregon Health and Science University","keywords":"Immunostaining; Pathology; H&E stain; Dysplasia; Staining; Medicine; Biology; Immunohistochemistry","score_opus":0.024169816089894526,"score_gpt":0.2971887034555074,"score_spread":0.27301888736561286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108039948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2831382,0.0001398675,0.7121418,0.0013246018,0.0022957162,0.00071703986,0.0000025326756,0.00018712453,0.00005312943],"genre_scores_gemma":[0.9956106,0.0000036007523,0.0035664542,0.00008768804,0.000087797685,0.0001479228,0.000069654154,0.000013283259,0.00041298548],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968495,0.00006725384,0.00069274387,0.0014458122,0.00060176343,0.00034293497],"domain_scores_gemma":[0.99807256,0.000054342865,0.0003850395,0.0010552652,0.00019451961,0.00023828051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011468524,0.00016929752,0.00033337076,0.000438974,0.00024124936,0.00058657455,0.00035117165,0.00004568919,0.000022775603],"category_scores_gemma":[0.00033677858,0.00017248506,0.00014792322,0.0037602456,0.00009985986,0.0005614682,0.00013239797,0.00008546977,0.000019579888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032107593,0.0012832158,0.69259036,0.001671677,0.0009466512,0.0034965042,0.0066551575,0.08342443,0.07691716,0.004014458,0.028114647,0.100564666],"study_design_scores_gemma":[0.00027203205,0.00011340432,0.08990462,0.000045393885,0.00033261228,0.000023902743,0.000046137684,0.8660855,0.021094697,0.0053488417,0.016234618,0.00049819663],"about_ca_topic_score_codex":0.000058187474,"about_ca_topic_score_gemma":0.00008463772,"teacher_disagreement_score":0.78266114,"about_ca_system_score_codex":0.00012455408,"about_ca_system_score_gemma":0.00017616492,"threshold_uncertainty_score":0.7033737},"labels":[],"label_agreement":null},{"id":"W3108122746","doi":"10.1007/978-3-030-64984-5_4","title":"Novel Block Diagonalization for Reducing Features and Computations in Medical Diagnosis","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Computation; Block (permutation group theory); Theoretical computer science; Algorithm; Combinatorics; Mathematics","score_opus":0.020956887789508636,"score_gpt":0.2721678922696865,"score_spread":0.25121100448017786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108122746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008408886,0.0006847014,0.9904335,0.0064680795,0.0013604834,0.0006254891,0.000010618212,0.00012285655,0.00021017704],"genre_scores_gemma":[0.27719584,0.00029397078,0.71653104,0.0045447387,0.0011352544,0.00016296485,0.000018556893,0.00006545188,0.000052186628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966362,0.000027213637,0.00050456764,0.0014715963,0.0009481995,0.00041222834],"domain_scores_gemma":[0.9976065,0.001280817,0.0002323794,0.0004827396,0.00018638758,0.00021118492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006636264,0.00037531863,0.00043679064,0.0006865981,0.00022951385,0.00038520625,0.0014414666,0.00036823357,0.000005704003],"category_scores_gemma":[0.0004508105,0.00038179927,0.000077378754,0.0007898189,0.00042783743,0.00045454976,0.0008041669,0.0006767852,0.0000026068687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011598043,0.000049799113,0.00028058628,0.00014852286,0.000015162407,0.000035925354,0.001740778,0.1362653,0.000085918204,0.023716588,0.00015057054,0.83749926],"study_design_scores_gemma":[0.00053508615,0.00018613134,0.0009913493,0.0007405213,0.000008993223,0.00014393407,2.9882486e-7,0.9326397,0.00066910405,0.06274442,0.0008418342,0.0004986357],"about_ca_topic_score_codex":0.0000661154,"about_ca_topic_score_gemma":0.000353636,"teacher_disagreement_score":0.8370006,"about_ca_system_score_codex":0.00035284317,"about_ca_system_score_gemma":0.0006422982,"threshold_uncertainty_score":0.9998634},"labels":[],"label_agreement":null},{"id":"W3109976697","doi":"10.21203/rs.3.rs-125179/v1","title":"Overcoming the Limitations of Patch-Based Learning to Detect Cancer in Whole Slide Images","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of British Columbia; Sunnybrook Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Workflow; Artificial intelligence; Context (archaeology); Task (project management); Binary classification; Deep learning; Image (mathematics); Machine learning; Pattern recognition (psychology); Class (philosophy)","score_opus":0.138877638261455,"score_gpt":0.40324785538592683,"score_spread":0.26437021712447184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109976697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10531562,0.0025548954,0.8087855,0.07696416,0.0009853877,0.003684404,0.00013451124,0.00039256178,0.0011829949],"genre_scores_gemma":[0.98729527,0.0002257737,0.011319464,0.00010464098,0.00014626412,0.0007678636,0.000004317951,0.000029302615,0.00010711962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962728,0.0009605109,0.00035759594,0.0007219001,0.0011824666,0.0005046947],"domain_scores_gemma":[0.996592,0.0017360608,0.00014150293,0.00087015977,0.000527669,0.00013261038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017773703,0.00018552328,0.0002786092,0.000519762,0.0002525668,0.00027388264,0.00167038,0.00014586031,0.00001354202],"category_scores_gemma":[0.0018779171,0.00016233284,0.0001258168,0.0016818367,0.000103291946,0.00016154836,0.002029623,0.0022536507,0.00003329637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008096065,0.000039708735,0.00532852,0.0006977526,0.000042283726,0.00003374866,0.0076926393,0.5434914,0.01869688,0.0002156038,0.0024375727,0.4212429],"study_design_scores_gemma":[0.0011199341,0.0011813596,0.10404893,0.004921602,0.000024325303,0.0000025783927,0.0022721428,0.67549443,0.13724071,0.014226623,0.05838929,0.0010780513],"about_ca_topic_score_codex":0.0039752456,"about_ca_topic_score_gemma":0.002444952,"teacher_disagreement_score":0.88197964,"about_ca_system_score_codex":0.00069308904,"about_ca_system_score_gemma":0.0011076827,"threshold_uncertainty_score":0.9791116},"labels":[],"label_agreement":null},{"id":"W3110138119","doi":"10.18280/ria.340516","title":"Medical Image Data Classification Using Deep Learning Based Hybrid Model with CNN and Encoder","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Deep learning; Artificial intelligence; Encoder; Benchmark (surveying); Field (mathematics); Key (lock); Machine learning; Image (mathematics); Medical imaging; Pattern recognition (psychology); Data mining; Computer security; Mathematics","score_opus":0.11357538390313844,"score_gpt":0.30621383060567303,"score_spread":0.1926384467025346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110138119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006939328,0.00013304311,0.98868173,0.0034955826,0.00007387845,0.00015405341,0.000002459841,0.0001736633,0.0003462441],"genre_scores_gemma":[0.8693118,0.000045683602,0.12998982,0.00049288635,0.00008694445,0.000008090504,0.000012022158,0.000018638588,0.000034140532],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981432,0.00008436263,0.0003130747,0.0008014421,0.00039650174,0.00026142938],"domain_scores_gemma":[0.9986411,0.00012921149,0.00013867277,0.0007675263,0.00010478688,0.00021873244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046860686,0.0001542707,0.00016450802,0.00006195072,0.00022946336,0.00017792976,0.0010409986,0.000061344814,0.000060602728],"category_scores_gemma":[0.0002616022,0.00014645503,0.000023815766,0.0004349479,0.00014523919,0.0007767263,0.00038428602,0.0003515514,0.000057405512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037924,0.000051874595,0.0002524608,0.000092735485,0.000014160449,0.000038529673,0.0012559728,0.85041076,0.009397981,0.001127828,0.00015366415,0.1371661],"study_design_scores_gemma":[0.000048788916,0.00008624574,0.0000101705455,0.000053050015,0.000010722842,0.000037082467,0.00017867054,0.9806409,0.01790304,0.00021121482,0.0006362915,0.00018385613],"about_ca_topic_score_codex":0.000019550967,"about_ca_topic_score_gemma":0.000008626701,"teacher_disagreement_score":0.86237246,"about_ca_system_score_codex":0.000054791595,"about_ca_system_score_gemma":0.00017050606,"threshold_uncertainty_score":0.59722626},"labels":[],"label_agreement":null},{"id":"W3110379578","doi":"10.3390/app10228298","title":"Deep-Learning-Based Computer-Aided Systems for Breast Cancer Imaging: A Critical Review","year":2020,"lang":"en","type":"review","venue":"MDPI (MDPI AG)","topic":"AI in cancer detection","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medical diagnosis; Breast cancer; Mammography; Computer science; CAD; Medical physics; Breast imaging; Medicine; Artificial intelligence; Breast cancer screening; Cancer; Radiology; Engineering drawing; Engineering","score_opus":0.046539732693732114,"score_gpt":0.346106267884423,"score_spread":0.2995665351906909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110379578","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4903584e-9,0.570295,0.42272937,0.0020059037,0.002706108,0.0016459506,0.00008135014,0.0004795526,0.000056825862],"genre_scores_gemma":[0.000008184754,0.9861701,0.007024581,0.0016349538,0.0022299152,0.0026180744,0.000056418085,0.00016351207,0.00009425429],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941536,0.0008093163,0.0014272808,0.0018824082,0.00079424895,0.0009331275],"domain_scores_gemma":[0.9957168,0.0011441183,0.0008174751,0.0012970889,0.0005585117,0.00046598125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008509089,0.0009892937,0.0031137546,0.00026047006,0.00035442464,0.0006544198,0.002369029,0.00032077509,0.000070401875],"category_scores_gemma":[0.00024652522,0.00088520127,0.0011719081,0.0012008661,0.00015230455,0.0004321318,0.0004859801,0.0011176136,0.00021743649],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043092864,0.0000348191,0.0000012120482,0.10372432,0.00008934415,0.000049831368,0.000020492502,0.00015621156,7.4016064e-8,0.00060788135,0.011911374,0.88340014],"study_design_scores_gemma":[0.0002258967,0.000098914505,0.0000015191673,0.06376533,0.0005896874,0.00030161397,0.0000014669157,0.17171958,2.4314124e-7,0.000031732307,0.76254493,0.0007190997],"about_ca_topic_score_codex":0.00011010604,"about_ca_topic_score_gemma":0.000008063361,"teacher_disagreement_score":0.882681,"about_ca_system_score_codex":0.0010744918,"about_ca_system_score_gemma":0.0012189159,"threshold_uncertainty_score":0.99935985},"labels":[],"label_agreement":null},{"id":"W3111489609","doi":"10.1109/cvprw53098.2021.00203","title":"D-LEMA: Deep Learning Ensembles from Multiple Annotations - Application to Skin Lesion Segmentation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Segmentation; Artificial intelligence; Annotation; Ground truth; Generalization; Task (project management); Machine learning; Bayesian probability; Image (mathematics); Pattern recognition (psychology); Convolutional neural network; Mathematics","score_opus":0.02092375196183573,"score_gpt":0.28206216264560574,"score_spread":0.26113841068377003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111489609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07497038,0.00014145192,0.9217331,0.0007039715,0.0008263494,0.000695483,0.0000065206996,0.00050501275,0.00041775685],"genre_scores_gemma":[0.6393281,0.000082968785,0.35919765,0.00021743144,0.00019725351,0.00048619707,0.0003301052,0.00002246601,0.00013779568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751014,0.0001956561,0.0004315518,0.001155607,0.00046960328,0.00023745533],"domain_scores_gemma":[0.9981796,0.00024509945,0.0002878552,0.0008755987,0.000295123,0.00011672218],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022204129,0.00026976227,0.00025040685,0.00022405913,0.00028026704,0.0005358585,0.00066959026,0.0002463946,0.00004465735],"category_scores_gemma":[0.000096651864,0.00030741456,0.00011087457,0.0004966439,0.000015508143,0.00043928216,0.0011630178,0.00047441348,0.00012756529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010317016,0.000068608846,0.0010290188,0.000048624293,0.00004899217,0.0000032668174,0.0056418255,0.27627882,0.05079359,0.00029131127,0.00030093637,0.66548467],"study_design_scores_gemma":[0.00033226743,0.000057817004,0.014291437,0.000113259295,0.00003082899,0.0000034482632,0.0011368544,0.8705246,0.108633965,0.002076134,0.0022160742,0.00058332563],"about_ca_topic_score_codex":0.0025880602,"about_ca_topic_score_gemma":0.002173091,"teacher_disagreement_score":0.6649014,"about_ca_system_score_codex":0.00044042122,"about_ca_system_score_gemma":0.00012600649,"threshold_uncertainty_score":0.9999378},"labels":[],"label_agreement":null},{"id":"W3111503343","doi":"10.1038/s41746-021-00507-3","title":"Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation","year":2021,"lang":"en","type":"preprint","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"GlaxoSmithKline","keywords":"Overfitting; Synthetic data; Computer science; Benchmark (surveying); Medical imaging; Artificial intelligence; Image synthesis; Generative model; Machine learning; Aggregate (composite); Data mining; Image (mathematics); Pattern recognition (psychology); Data science; Generative grammar; Artificial neural network","score_opus":0.11388781899955881,"score_gpt":0.3576403586010562,"score_spread":0.2437525396014974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111503343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048620325,0.0006114906,0.93044126,0.010899607,0.0032002712,0.0009455317,0.000035237546,0.00025533192,0.0049909423],"genre_scores_gemma":[0.9670559,0.00004774244,0.026333492,0.0027616676,0.0025450056,0.00015586238,0.0009887598,0.000049690185,0.0000618442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943208,0.00008881567,0.0005504138,0.0018917733,0.0028048567,0.00034333195],"domain_scores_gemma":[0.99490416,0.00017857445,0.00023952874,0.0031790668,0.0007867898,0.00071185286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009745936,0.000374587,0.000523007,0.0002180778,0.00015402069,0.0008195219,0.0029852062,0.00022872462,0.0004069384],"category_scores_gemma":[0.0028490268,0.0003194575,0.000043018972,0.0005415936,0.0001559867,0.0015758588,0.006413485,0.0007251471,0.00001736368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012081386,0.00011788186,0.0011049485,0.00056833297,0.0007366937,0.00091758743,0.010463165,0.0074746255,0.0033363816,0.0008721277,0.051364955,0.9229225],"study_design_scores_gemma":[0.0012376062,0.0002997212,0.00058761897,0.002475723,0.00010129309,0.00022654903,0.0005049418,0.988213,0.0005454804,0.0004954643,0.00473346,0.0005791559],"about_ca_topic_score_codex":0.00014276413,"about_ca_topic_score_gemma":0.00015237203,"teacher_disagreement_score":0.98073834,"about_ca_system_score_codex":0.00047974742,"about_ca_system_score_gemma":0.0016053336,"threshold_uncertainty_score":0.99992573},"labels":[],"label_agreement":null},{"id":"W3112688606","doi":"10.1038/s41467-021-26216-9","title":"Annotation-efficient deep learning for automatic medical image segmentation","year":2021,"lang":"en","type":"preprint","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Cancer Institute; Youth Innovation Promotion Association; Recruitment Program of Global Experts; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Annotation; Segmentation; Artificial intelligence; Deep learning; Machine learning; Imperfect","score_opus":0.01927901963085485,"score_gpt":0.3411973967394062,"score_spread":0.3219183771085513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112688606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026042417,0.0059900773,0.9777756,0.009849876,0.0016190676,0.0008815291,0.000007994514,0.000581176,0.000690466],"genre_scores_gemma":[0.5261452,0.0005005651,0.4715025,0.0003865406,0.000102226084,0.0008081849,0.0004920353,0.000025947633,0.00003677232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746484,0.000456363,0.0005153676,0.00058392953,0.0007278132,0.00025170468],"domain_scores_gemma":[0.9946973,0.001000599,0.00045969654,0.002934305,0.00078975584,0.00011836295],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00086520583,0.00024245,0.0002779654,0.00021890929,0.00063441985,0.00049482705,0.0036915923,0.000807716,0.000034865127],"category_scores_gemma":[0.0012747261,0.00027102907,0.00019603655,0.00054384035,0.000118494245,0.00024360132,0.0029882696,0.0030154497,0.000014077851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000130879225,0.001016145,0.0004262496,0.0010200413,0.0005306753,0.000012378015,0.01685714,0.06506067,0.0020758575,0.036443766,0.0049620233,0.871582],"study_design_scores_gemma":[0.00025707931,0.00002451124,0.0011292308,0.00018331702,0.000039998762,0.000013423191,0.0002809993,0.993464,0.00054229266,0.0008614689,0.0029391267,0.00026456112],"about_ca_topic_score_codex":0.000021715126,"about_ca_topic_score_gemma":0.0002617758,"teacher_disagreement_score":0.9284033,"about_ca_system_score_codex":0.0004572484,"about_ca_system_score_gemma":0.0006180102,"threshold_uncertainty_score":0.9999742},"labels":[],"label_agreement":null},{"id":"W3112799341","doi":"10.1186/s12911-020-01327-3","title":"Texture features in the Shearlet domain for histopathological image classification","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Shearlet; Pattern recognition (psychology); Artificial intelligence; Computer science; Local binary patterns; Support vector machine; Feature extraction; Feature (linguistics); Feature vector; Curvelet; Feature selection; Contextual image classification; Wavelet; Histogram; Image (mathematics); Wavelet transform","score_opus":0.04767099481009848,"score_gpt":0.3276397137797245,"score_spread":0.27996871896962605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112799341","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013612557,0.00010471406,0.9836417,0.001514561,0.00013686978,0.00023478668,0.000001521731,0.000039591494,0.0007136883],"genre_scores_gemma":[0.31200686,0.00002543781,0.68171114,0.006115003,0.00010388362,0.000031817694,0.0000014834476,0.000003089241,0.0000012578456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986563,0.00005589596,0.00039541497,0.00014776138,0.00059080083,0.00015383936],"domain_scores_gemma":[0.9982553,0.0012780149,0.00011792793,0.00022466319,0.000038342798,0.00008574713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012272828,0.00008869725,0.00013256562,0.000053556472,0.00012376558,0.0002155253,0.00059408596,0.00013227906,0.000009597927],"category_scores_gemma":[0.0007884117,0.00005307116,0.000043458902,0.00026244821,0.0000642773,0.0003040515,0.00016892869,0.00026021473,0.000006753192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073957744,0.000019917115,0.00019265209,0.00009381881,0.0000014579881,0.000009365233,0.0051722936,0.000065814726,0.000027478196,0.033924475,0.012635943,0.9477828],"study_design_scores_gemma":[0.00051069673,0.00011420817,0.004865212,0.000082627295,0.0000023040952,0.00007043178,0.001003994,0.9582578,0.0000041452836,0.027120922,0.007865881,0.00010178153],"about_ca_topic_score_codex":5.408071e-7,"about_ca_topic_score_gemma":0.0000073924216,"teacher_disagreement_score":0.958192,"about_ca_system_score_codex":0.000030347343,"about_ca_system_score_gemma":0.00006994135,"threshold_uncertainty_score":0.2164179},"labels":[],"label_agreement":null},{"id":"W3115680971","doi":"10.1007/978-3-030-64556-4_28","title":"Ink Marker Segmentation in Histopathology Images Using Deep Learning","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Histopathology; Digital pathology; Pixel; Artificial intelligence; Segmentation; Image segmentation; Computer vision; Pattern recognition (psychology); Process (computing); Digital image; Image processing; Image (mathematics); Pathology; Medicine","score_opus":0.01709739416420251,"score_gpt":0.2532742017611951,"score_spread":0.23617680759699258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115680971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036238052,0.0005601214,0.9947295,0.0005489942,0.0019919397,0.00032146412,9.1502534e-7,0.00016775275,0.0013168993],"genre_scores_gemma":[0.21643388,0.0000755897,0.78140146,0.0013951622,0.0004919449,0.000014056773,0.000004319533,0.000054058677,0.00012950465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651074,0.00011600542,0.0005453865,0.0015929108,0.00070247706,0.00053248013],"domain_scores_gemma":[0.9984663,0.00027943662,0.00037203537,0.00063677697,0.00013311303,0.00011232778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008025284,0.00043631325,0.0004671305,0.0009874946,0.00021480079,0.0003118231,0.0017012705,0.00031091576,0.000021878783],"category_scores_gemma":[0.00011616763,0.00047177888,0.00008725586,0.00087264384,0.00045521578,0.00084185274,0.0011186798,0.0013081105,0.000028232276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012614998,0.000011731525,0.0008350949,0.000047131092,0.0000039434317,0.00025862563,0.00146806,0.14722611,0.0038090013,0.0010777627,0.0000044929466,0.8452454],"study_design_scores_gemma":[0.00031246754,0.00018699701,0.0011767903,0.00022408566,0.000007431914,0.00017111763,6.3502193e-7,0.9551868,0.0025446117,0.039068192,0.00049647,0.0006244348],"about_ca_topic_score_codex":0.000049695085,"about_ca_topic_score_gemma":0.00009751441,"teacher_disagreement_score":0.844621,"about_ca_system_score_codex":0.0013628376,"about_ca_system_score_gemma":0.0003575792,"threshold_uncertainty_score":0.9997734},"labels":[],"label_agreement":null},{"id":"W3115970425","doi":"10.3390/cancers13010011","title":"piNET–An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Guelph; Toronto Metropolitan University","funders":"","keywords":"False positive paradox; Computer science; Artificial intelligence; Workflow; Pattern recognition (psychology); Segmentation; Proliferation index; Pathology; Medicine; Database","score_opus":0.020338773412539226,"score_gpt":0.3078196422032692,"score_spread":0.28748086879073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115970425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0125596775,0.00019292175,0.976251,0.007442247,0.0012926497,0.0006443507,0.00008466921,0.0014811612,0.00005132193],"genre_scores_gemma":[0.9648402,0.000030630512,0.029433647,0.0039351294,0.0011737131,0.0005198234,0.000007979065,0.00003476711,0.00002412134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985416,0.00004115314,0.00022684337,0.0005900753,0.00026613983,0.00033422417],"domain_scores_gemma":[0.99902064,0.000037487825,0.00014145585,0.00036536108,0.00019523784,0.0002398073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000929304,0.00018761877,0.00019217971,0.000053602133,0.00017758751,0.00019227475,0.0005361313,0.00013730091,0.000042860564],"category_scores_gemma":[0.00004300741,0.00019000746,0.00006632504,0.0005404321,0.00005267629,0.00081464497,0.000069292524,0.00018679735,0.000011922039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009498188,0.00007515835,0.015003348,0.0007478282,0.00041283408,0.00002194135,0.0104886,0.48481107,0.019513395,0.027371673,0.1013955,0.33920884],"study_design_scores_gemma":[0.00046282457,0.00015117489,0.0059826938,0.00004918892,0.00001422864,0.0000068080994,0.00003958736,0.9816165,0.006684758,0.0010521358,0.0036453567,0.0002947583],"about_ca_topic_score_codex":0.0003078946,"about_ca_topic_score_gemma":0.00005511927,"teacher_disagreement_score":0.9522805,"about_ca_system_score_codex":0.001218832,"about_ca_system_score_gemma":0.00089135516,"threshold_uncertainty_score":0.77482796},"labels":[],"label_agreement":null},{"id":"W3117993121","doi":"10.23919/eusipco47968.2020.9287435","title":"Deep Learning Methods for Image Decomposition of Cervical Cells","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Segmentation; Pattern recognition (psychology); Image segmentation; Image (mathematics); Deep learning; Computer vision; Image processing; Permutation (music)","score_opus":0.023496346904034,"score_gpt":0.35385477329570714,"score_spread":0.3303584263916731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117993121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039535866,0.000029835337,0.9965698,0.0012129104,0.00016217268,0.00011842756,1.8456267e-7,0.00013622642,0.0013750701],"genre_scores_gemma":[0.12575237,0.0000042388433,0.8738076,0.00033924135,0.00005678404,0.0000107590695,5.6416934e-7,0.0000054342595,0.000022994196],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936515,0.00009288795,0.00014760939,0.0002083977,0.00007866491,0.000107284824],"domain_scores_gemma":[0.9994936,0.0001955468,0.00006485534,0.00011643215,0.00007263738,0.000056939047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021198805,0.000056478653,0.000102476544,0.000026073212,0.00004828845,0.000034507004,0.0002670556,0.00003533532,0.00004072963],"category_scores_gemma":[0.000032383563,0.000054557,0.00006093656,0.00019581933,0.000015609965,0.00023342685,0.00010308821,0.000078268,0.000013718047],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022135142,0.000015542295,0.000019283912,0.00006643144,0.000011692976,5.513703e-7,0.0007088011,0.002115087,0.54739666,0.0043967287,0.00025613088,0.44499096],"study_design_scores_gemma":[0.000105691346,0.00014380532,0.000045313347,0.0000017657517,0.0000030542808,0.0000010644974,0.000015081668,0.5743368,0.4223632,0.00091152446,0.002029723,0.000042950574],"about_ca_topic_score_codex":0.000007583735,"about_ca_topic_score_gemma":9.890471e-7,"teacher_disagreement_score":0.57222176,"about_ca_system_score_codex":0.000024775287,"about_ca_system_score_gemma":0.0000135592645,"threshold_uncertainty_score":0.22247699},"labels":[],"label_agreement":null},{"id":"W3118409517","doi":"","title":"Détermination de la corrélation entre deux mesures de la qualité des images en mammographie numérique","year":2007,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Physics","score_opus":0.013145320551168488,"score_gpt":0.2932263256840992,"score_spread":0.28008100513293066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118409517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17472707,0.0020426477,0.77228713,0.003750399,0.00050494936,0.000568566,0.00004757869,0.0004907477,0.045580924],"genre_scores_gemma":[0.78152645,0.0037810612,0.20718263,0.0001302496,0.00013226407,0.00013943427,0.00015033854,0.00009069506,0.0068668635],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9619667,0.03362377,0.0010845651,0.0014423314,0.00092145824,0.0009611693],"domain_scores_gemma":[0.98173046,0.011617161,0.0011703803,0.0025067548,0.0025430997,0.0004321271],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.031472057,0.0007160239,0.0005717354,0.00071639963,0.0009348312,0.0019088143,0.002621115,0.0012386633,0.00013330998],"category_scores_gemma":[0.004145695,0.0008749944,0.0004555346,0.0014344323,0.0016355844,0.0009359469,0.0015681449,0.0015259132,0.00004040884],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006965585,0.0012002211,0.07328412,0.00069968816,0.00022342574,0.00006785538,0.09397378,0.0023450379,0.012845152,0.35804796,0.001909303,0.4553338],"study_design_scores_gemma":[0.0016127174,0.0000054857987,0.4422103,0.0053477786,0.00016290577,0.00057627715,0.0012691871,0.11468592,0.2307338,0.14777622,0.0537312,0.0018882346],"about_ca_topic_score_codex":0.00559703,"about_ca_topic_score_gemma":0.004626587,"teacher_disagreement_score":0.6067994,"about_ca_system_score_codex":0.0014229516,"about_ca_system_score_gemma":0.0011017598,"threshold_uncertainty_score":0.9993701},"labels":[],"label_agreement":null},{"id":"W3119222090","doi":"10.1109/bibm49941.2020.9313247","title":"Using Machine Learning to Automate Mammogram Images Analysis","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Feature selection; Pattern recognition (psychology); Mammography; Feature extraction; Linear discriminant analysis; Naive Bayes classifier; Daubechies wavelet; Wavelet transform; Entropy (arrow of time); Wavelet; Breast cancer; Discrete wavelet transform; Support vector machine; Cancer","score_opus":0.03545473649679716,"score_gpt":0.292316294198424,"score_spread":0.25686155770162683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119222090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022422694,0.000030490157,0.9730625,0.002625959,0.00008127938,0.000061469036,7.0841685e-7,0.0007836261,0.00093126117],"genre_scores_gemma":[0.70527977,0.0000022602194,0.2935851,0.0009271177,0.000046048466,0.0000026632838,6.1306184e-7,0.0000060419165,0.00015040132],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910873,0.000048924485,0.00013246763,0.00034023714,0.00019122679,0.00017843276],"domain_scores_gemma":[0.9995489,0.000021646763,0.00004528206,0.00020919509,0.000039198418,0.0001357372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011816056,0.00008745838,0.00013707539,0.00015216651,0.00010835164,0.00018863093,0.00037687368,0.000023290859,0.00008819374],"category_scores_gemma":[0.00003190006,0.00008183265,0.000082632,0.0022587304,0.000008963696,0.00027372147,0.0002767767,0.00010242362,0.0000838057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021912294,0.000034099274,0.04576001,0.00003562206,0.0006066598,0.000051822153,0.0030821725,0.6727732,0.05643173,0.0011611833,0.0009557085,0.21908592],"study_design_scores_gemma":[0.00005270074,0.00005756235,0.0015900299,0.0000015829016,0.00004062102,0.0000023768164,0.000016285205,0.98347604,0.012033453,0.000032429187,0.0025863512,0.00011058279],"about_ca_topic_score_codex":0.00039191227,"about_ca_topic_score_gemma":0.000040890558,"teacher_disagreement_score":0.6828571,"about_ca_system_score_codex":0.00005040728,"about_ca_system_score_gemma":0.000017269473,"threshold_uncertainty_score":0.33370388},"labels":[],"label_agreement":null},{"id":"W3119837896","doi":"","title":"Fully Automated Fibroglandular Tissue Segmentation and Bias Correction in Breast MR Images Using Level Set Method","year":2016,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Segmentation; Artificial intelligence; Image segmentation; Computer vision; Background subtraction; Computer science; Image processing; Breast tissue; Intensity (physics); Subtraction; Data set; Breast MRI; Magnetic resonance imaging; Pattern recognition (psychology); Mathematics; Pixel; Mammography; Image (mathematics); Physics; Radiology; Optics; Medicine; Breast cancer","score_opus":0.04949817675404282,"score_gpt":0.32331275711647484,"score_spread":0.273814580362432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119837896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5078411,0.00004192304,0.49043474,0.00048246846,0.00048046577,0.0002070686,0.0000074305453,0.00041570596,0.00008912365],"genre_scores_gemma":[0.8682822,0.000025007244,0.13131164,0.000053919273,0.0001089642,0.000024591105,0.0000015360415,0.000018060926,0.00017407388],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998904,0.000027351582,0.00021306591,0.00043049935,0.00020213712,0.00022298323],"domain_scores_gemma":[0.99949867,0.000052110143,0.00014133786,0.00009442242,0.00015505166,0.000058402817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043799714,0.00014595152,0.00014048653,0.00021756114,0.00011005773,0.00018700123,0.00017461227,0.00008741711,0.0000057382663],"category_scores_gemma":[0.00005635782,0.000119879674,0.000017916393,0.0004748316,0.00004026643,0.0012018565,0.000121376834,0.000075731376,0.0000075412477],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031382566,0.000016422526,0.019039284,0.00005474226,0.000011757016,0.0000030531282,0.0010785161,0.000033484957,0.7864296,0.00012609764,0.0018971934,0.19127849],"study_design_scores_gemma":[0.0011532747,0.00020904434,0.07390021,0.0003845767,0.000018418736,0.0010311963,0.00026804613,0.27197668,0.6492643,0.00085494184,0.00051007065,0.00042926267],"about_ca_topic_score_codex":0.00018699978,"about_ca_topic_score_gemma":0.0000107120695,"teacher_disagreement_score":0.36044112,"about_ca_system_score_codex":0.0002255843,"about_ca_system_score_gemma":0.00004045652,"threshold_uncertainty_score":0.48885512},"labels":[],"label_agreement":null},{"id":"W3120059284","doi":"10.15388/20-infor442","title":"Deep Learning Model for Cell Nuclei Segmentation and Lymphocyte Identification in Whole Slide Histology Images","year":2021,"lang":"en","type":"article","venue":"Informatica","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Information Technology Research Centre","keywords":"Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Perceptron; H&E stain; Deep learning; Ground truth; Pathology; Artificial neural network; Medicine","score_opus":0.010674788741891728,"score_gpt":0.2412726812827887,"score_spread":0.23059789254089696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120059284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014279078,0.00016345302,0.9841909,0.00032013268,0.00013056627,0.00014425008,0.0000010830873,0.000047018053,0.0007235213],"genre_scores_gemma":[0.84026587,0.000073610005,0.15864967,0.00034063298,0.000014831106,0.00009205955,0.000013225963,0.00000764263,0.00054243853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930006,0.000026778338,0.0002894136,0.00014090972,0.00010216735,0.00014068937],"domain_scores_gemma":[0.99952435,0.0000684538,0.0001317697,0.00016948534,0.00007687535,0.000029086186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019319511,0.00006653175,0.00009008434,0.000092481365,0.000108865665,0.00012885395,0.00013399588,0.000045943445,0.000002724805],"category_scores_gemma":[0.000050609255,0.00007613145,0.000020254927,0.000153295,0.000022063381,0.00088917353,0.00007981934,0.000067598514,0.000023517307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004197255,0.0000734145,0.0005588438,0.00055911776,0.000016915263,0.0000061469677,0.037498392,0.20939441,0.06353062,0.0031529244,0.0006581429,0.6845091],"study_design_scores_gemma":[0.00046446023,0.000021755393,0.0002978694,0.00000917083,0.0000040410396,0.0000124643675,0.0003515895,0.97823155,0.017482687,0.0019169975,0.0011266582,0.00008074968],"about_ca_topic_score_codex":0.000007642888,"about_ca_topic_score_gemma":0.000017866569,"teacher_disagreement_score":0.8259868,"about_ca_system_score_codex":0.00019978367,"about_ca_system_score_gemma":0.00006744918,"threshold_uncertainty_score":0.31045505},"labels":[],"label_agreement":null},{"id":"W3120506657","doi":"10.1109/siu49456.2020.9302453","title":"Nuclei Segmentation in Hematoxylin and Eosin (H&amp;E)-Stained Histopathological Images Using a Deep Neural Network","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; H&E stain; Task (project management); Artificial neural network; Pattern recognition (psychology); Breast cancer; Image segmentation; Histopathological examination; Cancer; Computer vision; Pathology; Medicine; Immunohistochemistry; Internal medicine","score_opus":0.041678720556687865,"score_gpt":0.2736185101027486,"score_spread":0.23193978954606076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120506657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30503723,0.00016484881,0.692721,0.0015719447,0.00011926483,0.00012759399,2.3766628e-7,0.0001383677,0.00011949416],"genre_scores_gemma":[0.74678004,0.000008689573,0.2517525,0.0013441349,0.0000890747,0.000006830629,7.551925e-7,0.000006480961,0.000011477073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989849,0.00010043172,0.00020432052,0.0003645936,0.00013663656,0.00020916005],"domain_scores_gemma":[0.9996476,0.000048709044,0.00006474856,0.00013936711,0.00002293644,0.000076600256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001663559,0.00010588307,0.0001366369,0.00003946874,0.00008398262,0.00011039902,0.00018276986,0.000049475206,0.000019694508],"category_scores_gemma":[0.000033197986,0.00009829992,0.000023805203,0.0004104911,0.000041211162,0.00041549467,0.00018984491,0.00012460347,0.000006405309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041478776,0.00024935068,0.09956495,0.00027909927,0.000031428743,0.00056903146,0.018380689,0.17710565,0.24097542,0.017026454,0.0037711726,0.44163197],"study_design_scores_gemma":[0.00044432972,0.00011103324,0.008692675,0.000009350674,0.0000042660986,0.000064859254,0.000067840956,0.98667693,0.0017358587,0.0017672536,0.00023475804,0.00019084518],"about_ca_topic_score_codex":0.000040094277,"about_ca_topic_score_gemma":0.000039940656,"teacher_disagreement_score":0.80957127,"about_ca_system_score_codex":0.000111426496,"about_ca_system_score_gemma":0.000015168436,"threshold_uncertainty_score":0.40085545},"labels":[],"label_agreement":null},{"id":"W3121575412","doi":"10.1016/j.csbj.2021.01.022","title":"QuPath: The global impact of an open source digital pathology system","year":2021,"lang":"en","type":"review","venue":"Computational and Structural Biotechnology Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; Invest Northern Ireland","keywords":"Open source; Digital pathology; Computer science; Environmental science; Pathology; Medicine; Operating system","score_opus":0.026678181239515406,"score_gpt":0.3404428545416728,"score_spread":0.31376467330215735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121575412","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017128945,0.8749338,0.12194881,0.000239324,0.00064315036,0.00029196523,0.00011224798,0.00009174146,0.000026089816],"genre_scores_gemma":[0.049700566,0.9233648,0.02615527,0.000056869634,0.0005120903,0.000024873847,0.00012075954,0.000045834124,0.000018891544],"study_design_codex":"design_other","study_design_gemma":"case_report","domain_scores_codex":[0.9979954,0.00028706974,0.0006918137,0.00049102044,0.00025900835,0.00027569773],"domain_scores_gemma":[0.9982235,0.00014812419,0.0008869745,0.00043131868,0.00020594933,0.00010412954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028029497,0.00033861538,0.0010355497,0.00015827663,0.00041487563,0.0007362974,0.0024605931,0.00052151317,0.0000053836625],"category_scores_gemma":[0.000050846018,0.00019676585,0.00030185774,0.0006378838,0.00035108783,0.0005806913,0.0013785483,0.000818389,0.0000026141045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034553939,0.000005783022,0.000014036177,0.00016909046,0.0001600256,0.00007794388,0.00002449953,0.0005815873,2.5561928e-7,0.01021503,0.00003484825,0.98871344],"study_design_scores_gemma":[0.0016878397,0.003307382,0.0015816229,0.008667236,0.0006527108,0.6422193,0.00035850122,0.09392343,0.000007225754,0.098391995,0.1472552,0.0019475507],"about_ca_topic_score_codex":0.000014863951,"about_ca_topic_score_gemma":0.0000019739787,"teacher_disagreement_score":0.9867659,"about_ca_system_score_codex":0.0004622914,"about_ca_system_score_gemma":0.0008158246,"threshold_uncertainty_score":0.80238783},"labels":[],"label_agreement":null},{"id":"W3122230257","doi":"10.1016/j.neucom.2020.04.157","title":"Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement and perspectives","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":395,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Francis Xavier University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Image (mathematics); Pattern recognition (psychology); Medical imaging; Segmentation; Image segmentation; Image retrieval; Computer vision; Machine learning","score_opus":0.013266338785356959,"score_gpt":0.2582385736075495,"score_spread":0.24497223482219252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122230257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069747806,0.000400325,0.92715484,0.0019409675,0.00046522677,0.00018441469,0.0000027344024,0.000058999933,0.000044686374],"genre_scores_gemma":[0.97601724,0.000012063683,0.023406483,0.00037887503,0.00013137511,0.000013547488,0.0000020147236,0.000008080191,0.000030323743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844265,0.00011336935,0.000327577,0.00047515336,0.00038473096,0.00025653478],"domain_scores_gemma":[0.9988817,0.00032306486,0.00018941874,0.0003063445,0.00021617569,0.00008332031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032153857,0.00011903029,0.00022475951,0.000065779444,0.00023310306,0.000098400145,0.00039194807,0.00003742919,0.00000592568],"category_scores_gemma":[0.000106624924,0.00010603326,0.00015483581,0.0006648862,0.00010951396,0.00014375229,0.000543314,0.00022444234,3.6814623e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109936125,0.0006395298,0.043398615,0.00027699594,0.0015747504,0.00006648044,0.0035526752,0.3541917,0.009493604,0.015251522,0.009556685,0.5618875],"study_design_scores_gemma":[0.00034083202,0.00006210975,0.022473317,0.000012393781,0.00004745165,0.000020676494,0.000058842135,0.97528726,0.0010119521,0.00019638958,0.0003937345,0.000095050884],"about_ca_topic_score_codex":0.000010898432,"about_ca_topic_score_gemma":0.00003343013,"teacher_disagreement_score":0.90626943,"about_ca_system_score_codex":0.00005026007,"about_ca_system_score_gemma":0.000112145164,"threshold_uncertainty_score":0.43239108},"labels":[],"label_agreement":null},{"id":"W3122731100","doi":"10.2196/24394","title":"Artificial Intelligence-based Segmentation of Nuclei in Multi-organ Histopathology Images: Model Development and Validation (Preprint)","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Segmentation; Histopathology; Artificial intelligence; Pathology; Medicine; World Wide Web","score_opus":0.05925210455671731,"score_gpt":0.3093555204203834,"score_spread":0.2501034158636661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122731100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20119302,0.0000043507225,0.7978373,0.00060742226,0.000057056375,0.00020244421,7.030357e-7,0.000047963713,0.000049752623],"genre_scores_gemma":[0.67900574,0.00000484858,0.32038188,0.0005602422,0.000009122557,0.000029449717,0.0000040903005,0.0000034309926,0.0000012097111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986248,0.000035508907,0.000704729,0.00012314736,0.0003871292,0.00012466351],"domain_scores_gemma":[0.99944854,0.00004783363,0.00019706081,0.0001368667,0.00005513576,0.00011457023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003816868,0.00008617958,0.00013998148,0.00010298156,0.000033851604,0.000025936062,0.00027513652,0.000096377735,0.000015948704],"category_scores_gemma":[0.00011563126,0.00008542859,0.000016618927,0.00025822714,0.00008075357,0.0003768627,0.00014735271,0.00017307006,0.000015710546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040839575,0.0001641295,0.0009513373,0.00041408872,0.000005844421,0.0000066840626,0.09070269,0.024580333,0.0024908236,0.0018710751,0.00008007473,0.8786921],"study_design_scores_gemma":[0.0001427357,0.00005108584,0.00032335956,0.000033651188,0.0000013879139,0.0000023850075,0.0005799645,0.905106,0.09329794,0.0003448061,0.000037759455,0.0000789201],"about_ca_topic_score_codex":0.0000039160554,"about_ca_topic_score_gemma":0.000005552756,"teacher_disagreement_score":0.88052565,"about_ca_system_score_codex":0.000116972056,"about_ca_system_score_gemma":0.0002536244,"threshold_uncertainty_score":0.34836766},"labels":[],"label_agreement":null},{"id":"W3123409890","doi":"10.4132/jptm.2020.12.22","title":"Deep learning for computer-assisted diagnosis of hereditary diffuse gastric cancer","year":2021,"lang":"en","type":"article","venue":"Journal of Pathology and Translational Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Queen Elizabeth II Health Sciences Centre; Dalhousie University","funders":"Nova Scotia Health Authority","keywords":"Medicine; Cancer; Receiver operating characteristic; H&E stain; Gastrectomy; Artificial intelligence; Radiology; Pathology; Internal medicine; Computer science; Staining","score_opus":0.024747341568381036,"score_gpt":0.28460516186310186,"score_spread":0.2598578202947208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123409890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12647916,0.0076549193,0.8584407,0.006402091,0.0009495215,0.000048496742,0.0000020961559,0.000006738891,0.000016249083],"genre_scores_gemma":[0.93285733,0.0010316088,0.06523001,0.0002059459,0.0006495806,0.000008743963,0.0000031299792,0.000004963333,0.000008659899],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991097,0.00009966123,0.0003762743,0.00012768428,0.00019207959,0.000094602095],"domain_scores_gemma":[0.99867296,0.00058721914,0.00027468425,0.00006375352,0.0003454386,0.000055948472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032172044,0.00007219848,0.00025210116,0.0001327198,0.000066719476,0.00000453101,0.00010976464,0.000062147126,0.00002175497],"category_scores_gemma":[0.00006893007,0.000058891266,0.00005927632,0.00021479106,0.00009274635,0.00015257522,0.000013675716,0.00018575229,1.0034027e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019339267,0.0002755947,0.09617766,0.00019550955,0.00023320956,0.0009016929,0.00277063,0.00843061,0.0038710895,0.001698302,0.00044860478,0.8848037],"study_design_scores_gemma":[0.009465788,0.0030841092,0.8756249,0.0006299184,0.00031240983,0.010960844,0.00017818535,0.08536113,0.0021788802,0.009434732,0.0025359127,0.0002331747],"about_ca_topic_score_codex":0.00000338553,"about_ca_topic_score_gemma":0.000013590543,"teacher_disagreement_score":0.88457054,"about_ca_system_score_codex":0.000012924756,"about_ca_system_score_gemma":0.00008557344,"threshold_uncertainty_score":0.24015161},"labels":[],"label_agreement":null},{"id":"W3124660917","doi":"10.1109/isbi48211.2021.9433978","title":"Magnification Generalization For Histopathology Image Embedding","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Magnification; Generalization; Embedding; Computer science; Artificial intelligence; Histopathology; Domain (mathematical analysis); Pattern recognition (psychology); Mathematics; Pathology; Medicine","score_opus":0.027014116218558596,"score_gpt":0.30853442789000485,"score_spread":0.28152031167144626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124660917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002285314,0.00017428657,0.99052,0.0014853338,0.0034320483,0.00042862754,0.000003834959,0.00035615911,0.0013143889],"genre_scores_gemma":[0.06438253,0.000119064265,0.93281156,0.00036415833,0.0003638783,0.00044587522,0.00013512469,0.00002376117,0.001354065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849313,0.00010808441,0.000283673,0.000784293,0.00014987159,0.0001809711],"domain_scores_gemma":[0.9984638,0.000058699392,0.00022464822,0.000861264,0.00035477176,0.000036801615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039553462,0.00016095104,0.00018453486,0.00013390231,0.00009668587,0.00030417254,0.00059984176,0.00023690396,0.00003542091],"category_scores_gemma":[0.000095144766,0.0001828134,0.00010856454,0.0001452951,0.000023502433,0.00031264732,0.0006071862,0.0001734827,0.000009563601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069157715,0.00036121154,0.0003992265,0.0032762345,0.000105605875,0.000062336374,0.007464514,0.08935986,0.28629267,0.21504849,0.05345365,0.34410703],"study_design_scores_gemma":[0.00017267257,0.00003687893,0.00075970544,0.000033540917,0.000021795087,0.000023900779,0.000027571936,0.9499686,0.030102376,0.014520845,0.0039840955,0.0003480595],"about_ca_topic_score_codex":0.000039823484,"about_ca_topic_score_gemma":0.000021928807,"teacher_disagreement_score":0.8606087,"about_ca_system_score_codex":0.000366104,"about_ca_system_score_gemma":0.0001860139,"threshold_uncertainty_score":0.74549145},"labels":[],"label_agreement":null},{"id":"W3125776321","doi":"10.1038/s41598-021-81506-y","title":"Deep learning predicts postsurgical recurrence of hepatocellular carcinoma from digital histopathologic images","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Concordance; Hepatocellular carcinoma; Risk stratification; H&E stain; Metastasis; Carcinoma; Radiology; Surgery; Oncology; Internal medicine; Cancer; Immunohistochemistry","score_opus":0.014021945342383019,"score_gpt":0.2178518142205556,"score_spread":0.2038298688781726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125776321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8415531,0.0018151675,0.14614633,0.000089348476,0.008178596,0.00012035407,0.000003551804,0.00017277675,0.0019207622],"genre_scores_gemma":[0.99328566,0.000008865405,0.0055621606,0.000008423307,0.0000617131,0.000009722753,0.000042635405,0.000008649391,0.0010121712],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997054,0.000116023984,0.0005512292,0.00121502,0.00076072745,0.00030302576],"domain_scores_gemma":[0.99771315,0.000090117246,0.0004384466,0.0012137969,0.0004188875,0.00012560833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072922464,0.00015176398,0.00024269558,0.00011554048,0.00024160903,0.00052858226,0.0004162119,0.00008516403,0.00006135347],"category_scores_gemma":[0.0005295262,0.00014908137,0.00013156417,0.00084133295,0.00029411906,0.00077886926,0.00048737664,0.00023293954,0.000021289095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149091,0.00025948332,0.7404024,0.00006647796,0.000024340852,0.018489776,0.0021810743,0.00089804176,0.11458483,0.00028099018,0.002172479,0.12062521],"study_design_scores_gemma":[0.00050976814,0.00032336958,0.10265273,0.00023449985,0.00004942882,0.0054128855,0.00029224515,0.12985253,0.67080235,0.04438398,0.04441894,0.001067266],"about_ca_topic_score_codex":0.000026265623,"about_ca_topic_score_gemma":0.0000026821685,"teacher_disagreement_score":0.6377497,"about_ca_system_score_codex":0.0001146827,"about_ca_system_score_gemma":0.00026762104,"threshold_uncertainty_score":0.6079362},"labels":[],"label_agreement":null},{"id":"W3126484252","doi":"10.3390/electronics10050562","title":"Machine Learning Methods for Histopathological Image Analysis: A Review","year":2021,"lang":"en","type":"review","venue":"Electronics","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; École de technologie supérieure","keywords":"Computer science; Artificial intelligence; CAD; Segmentation; Cover (algebra); Image (mathematics); Feature extraction; Pattern recognition (psychology); Machine learning; Computer vision; Engineering drawing; Engineering","score_opus":0.05460810512104624,"score_gpt":0.42655720905667105,"score_spread":0.3719491039356248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126484252","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.7588306e-10,0.50958586,0.48959228,0.00006848131,0.00013236194,0.00038645958,0.0000023837538,0.00012434552,0.000107825224],"genre_scores_gemma":[3.2313363e-9,0.7015088,0.29703385,0.00014784026,0.00007385666,0.00043706404,0.00008893058,0.000028423967,0.0006811906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957194,0.001634203,0.0007470321,0.0010859789,0.0002221326,0.00059129734],"domain_scores_gemma":[0.99744475,0.0005919888,0.00066288724,0.0010429382,0.00017298316,0.0000844318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028494173,0.00044448194,0.0027253763,0.0002672948,0.00017753313,0.00012671752,0.0012382598,0.0002750239,0.0000480966],"category_scores_gemma":[0.00067051215,0.0003725935,0.0018786009,0.002848255,0.000029653156,0.00015066311,0.00033689258,0.0012116445,0.000017521217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.7713784e-7,0.000013516193,4.7697522e-8,0.0076015284,0.00030295033,0.000007327444,0.000005181396,0.0000026263708,6.4018946e-7,0.001671187,0.00035067156,0.99004394],"study_design_scores_gemma":[0.000046313,0.00015101838,3.0416594e-8,0.0038680988,0.0043192315,0.0001170006,2.1400471e-7,0.004079154,0.0000028921495,0.0002584145,0.9867876,0.00037003102],"about_ca_topic_score_codex":0.0000014087365,"about_ca_topic_score_gemma":0.000005356018,"teacher_disagreement_score":0.9896739,"about_ca_system_score_codex":0.0009676418,"about_ca_system_score_gemma":0.0007728254,"threshold_uncertainty_score":0.9998726},"labels":[],"label_agreement":null},{"id":"W3128158496","doi":"10.1016/j.media.2021.102256","title":"Self-supervised driven consistency training for annotation efficient histopathology image analysis","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Canadian Cancer Society; Compute Canada","keywords":"Consistency (knowledge bases); Benchmark (surveying); Bootstrapping (finance); Annotation; Feature (linguistics); Pattern recognition (psychology); Feature learning; Representation (politics); Transfer of learning","score_opus":0.017349676241491793,"score_gpt":0.28616298130608026,"score_spread":0.26881330506458845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128158496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021987954,0.00023211553,0.97288036,0.003387124,0.00025739503,0.00014688507,0.000014998495,0.00025865034,0.0008345001],"genre_scores_gemma":[0.5414662,0.000046432993,0.45694587,0.0009581598,0.0001501845,0.00010997578,0.00013018819,0.000017510603,0.00017551078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965624,0.00037737927,0.0006717983,0.0010039515,0.0009083592,0.00047606748],"domain_scores_gemma":[0.99738824,0.00046547662,0.00023075264,0.0009137262,0.00070121296,0.00030056445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010968349,0.00022425587,0.0007713737,0.00087623345,0.00029247694,0.00018206977,0.00068373163,0.00017621969,0.00044917158],"category_scores_gemma":[0.0010373819,0.00022464861,0.0009733014,0.006676189,0.00017951815,0.00028501634,0.00020223334,0.00024206005,0.000029699462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018793036,0.0038623514,0.019044697,0.00082847633,0.047507927,0.007143521,0.061768014,0.034654126,0.073391035,0.0104719065,0.005948152,0.7351919],"study_design_scores_gemma":[0.00054689747,0.00005245281,0.0033687425,0.000006632326,0.005118866,0.000023498882,0.00030210864,0.9881503,0.0011816015,0.00019590829,0.0008030544,0.00024996808],"about_ca_topic_score_codex":0.0000444483,"about_ca_topic_score_gemma":0.00023168224,"teacher_disagreement_score":0.95349616,"about_ca_system_score_codex":0.0002516183,"about_ca_system_score_gemma":0.00043988437,"threshold_uncertainty_score":0.9160905},"labels":[],"label_agreement":null},{"id":"W3128287206","doi":"10.7939/r3-h1kz-gs07","title":"MODELLING EARLY DETECTION OF PROSTATE CANCER","year":2019,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Prostate; Cancer; Medicine; Internal medicine","score_opus":0.006921831213527686,"score_gpt":0.16432764161215596,"score_spread":0.15740581039862828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128287206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92577446,0.000056469882,0.06871019,0.00020787172,0.00020927827,0.00011885828,0.0000011436362,0.00004199939,0.00487972],"genre_scores_gemma":[0.99023134,0.00007353659,0.0049395533,0.000014460934,0.000010738712,1.1256073e-7,6.3228725e-7,0.0000055756923,0.0047240844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995078,0.000022195842,0.00007770775,0.00018264244,0.000114348535,0.000095302166],"domain_scores_gemma":[0.9995281,0.000046522833,0.00011803994,0.00024902148,0.000026645852,0.000031635518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000023741984,0.000057792226,0.00010326949,0.00010205349,0.00003473771,0.000010655779,0.0003717959,0.000045457273,0.000079838515],"category_scores_gemma":[8.843725e-7,0.00006949297,0.00004953793,0.00027191118,0.000031880143,0.001680942,0.00015426011,0.00006818689,0.000019524932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012289328,0.00029227498,0.20676519,0.00083838706,0.00042154777,0.000015450341,0.08637329,0.52235276,0.04011392,0.026092518,0.0012843757,0.11422136],"study_design_scores_gemma":[0.0009367278,0.00038323255,0.0062185144,0.00014966873,0.000021395816,0.0000025133108,0.0003272664,0.8445903,0.1340787,0.001818734,0.011171529,0.00030140945],"about_ca_topic_score_codex":0.005096508,"about_ca_topic_score_gemma":0.000068151196,"teacher_disagreement_score":0.32223755,"about_ca_system_score_codex":0.000021280895,"about_ca_system_score_gemma":0.00006804942,"threshold_uncertainty_score":0.77044296},"labels":[],"label_agreement":null},{"id":"W3132213428","doi":"10.1016/j.ajpath.2021.01.015","title":"Searching Images for Consensus","year":2021,"lang":"en","type":"review","venue":"American Journal Of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto; University of Waterloo","funders":"Government of Ontario","keywords":"Medical diagnosis; Artificial intelligence; Computer science; Set (abstract data type); Data science; Scale (ratio); Medical imaging; Medical physics; Machine learning; Medicine; Pathology","score_opus":0.05363432350215195,"score_gpt":0.391137439606553,"score_spread":0.33750311610440104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132213428","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035877522,0.7147362,0.28406394,0.00017878912,0.00081778667,0.00010653302,0.0000063551124,0.000013131692,0.00007366229],"genre_scores_gemma":[0.000015155327,0.8507355,0.1486945,0.00009574894,0.0003866801,0.000012839979,0.0000011045204,0.000022452876,0.000036034497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773335,0.0007615512,0.00071780843,0.00030489435,0.00018994226,0.0002924647],"domain_scores_gemma":[0.9963433,0.0011034856,0.0017409761,0.000398179,0.00031352098,0.000100530386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095962064,0.00020887873,0.001709636,0.00033376794,0.000070028065,0.000063571904,0.0008854706,0.00008083905,0.0000041592484],"category_scores_gemma":[0.00031943273,0.00017133294,0.0006232771,0.0004750942,0.00027828405,0.00007513868,0.00017579301,0.00059194077,0.0000053835734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021074575,0.000010390794,3.1662404e-7,0.00034795076,0.000068921334,0.00074014906,0.00006161932,0.000003974646,0.0000040155637,0.00051145256,0.00068286195,0.9975662],"study_design_scores_gemma":[0.000115634495,0.0008540093,9.212205e-7,0.0016763482,0.00016144002,0.0246245,0.00004835338,0.00002515273,0.00000895973,0.00042566593,0.9718798,0.00017926084],"about_ca_topic_score_codex":0.0000037537238,"about_ca_topic_score_gemma":4.9664817e-7,"teacher_disagreement_score":0.997387,"about_ca_system_score_codex":0.00015399182,"about_ca_system_score_gemma":0.0009353531,"threshold_uncertainty_score":0.69867545},"labels":[],"label_agreement":null},{"id":"W3132659672","doi":"","title":"Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part V (biological, optical, microscopic imaging; cell segmentation and stain normalization; histopathology image analysis; opthalmology)","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; Canada Research Chairs; University of Toronto","funders":"","keywords":"Normalization (sociology); Computer science; Histopathology; Stain; Segmentation; Artificial intelligence; Computer vision; Pathology; Medicine; Staining","score_opus":0.014406831528575154,"score_gpt":0.2623743718655274,"score_spread":0.24796754033695226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132659672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17605706,0.000489359,0.80867445,0.011120675,0.00061511307,0.0004934825,0.000046566627,0.00028136032,0.0022219566],"genre_scores_gemma":[0.6523946,0.000844319,0.34508443,0.0003778646,0.00010798624,0.00006433979,0.0008425704,0.00003394765,0.00024995048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99415785,0.0020140174,0.0010530475,0.0017317828,0.0005974177,0.00044587045],"domain_scores_gemma":[0.99518365,0.0005049413,0.0010096423,0.00074125914,0.0022261706,0.00033433363],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0034398497,0.0004975147,0.00067175395,0.00035214704,0.00041134868,0.0014251283,0.0015842394,0.00040912587,0.00021033997],"category_scores_gemma":[0.00060517667,0.0005352044,0.00022683092,0.0007116181,0.0007577189,0.000565076,0.0040909625,0.0009437812,0.000014023654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038698525,0.0068288334,0.25644016,0.004179238,0.0027900496,0.00086384796,0.05939436,0.0003159613,0.19332437,0.115737185,0.027564486,0.3321745],"study_design_scores_gemma":[0.0018916839,0.0000134692355,0.0512225,0.0009683847,0.00030742292,0.00030387525,0.0004376567,0.9272656,0.012733345,0.0019872147,0.0018532668,0.0010156268],"about_ca_topic_score_codex":0.00018554882,"about_ca_topic_score_gemma":0.00012550311,"teacher_disagreement_score":0.9269496,"about_ca_system_score_codex":0.00027394653,"about_ca_system_score_gemma":0.00022128267,"threshold_uncertainty_score":0.99970996},"labels":[],"label_agreement":null},{"id":"W3132678645","doi":"10.1117/12.2581789","title":"A distributed system improves inter-observer and AI concordance in annotating interstitial fibrosis and tubular atrophy","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Concordance; Annotation; Computer science; Artificial intelligence; Medicine; Set (abstract data type); Atrophy; Observer (physics); Pathology; Internal medicine","score_opus":0.0067253279970733715,"score_gpt":0.22079878458787996,"score_spread":0.2140734565908066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132678645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4641478,0.00037208793,0.53436923,0.0005033436,0.0003367325,0.00008347597,0.000007633217,0.0000974354,0.00008227338],"genre_scores_gemma":[0.9877424,0.000011479421,0.011958203,0.00017503464,0.000045682435,0.00001652485,0.000002854397,0.000006573044,0.00004121417],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897516,0.00007085797,0.00023021395,0.00043582224,0.00010517933,0.00018274019],"domain_scores_gemma":[0.99949527,0.000070807684,0.000060021724,0.00023505643,0.000078734374,0.00006009257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011517669,0.000118047785,0.00017303105,0.000047231133,0.00006598499,0.00024824234,0.00015727486,0.000048684666,0.0000031900022],"category_scores_gemma":[0.000034440054,0.000116074836,0.000025673111,0.00031328836,0.000054449076,0.0005420652,0.00039595104,0.00013694356,0.0000017712639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034522533,0.00019110435,0.06425191,0.002999589,0.00024978307,0.0011392555,0.0075689857,0.00031058892,0.4886115,0.0692859,0.002130718,0.36291546],"study_design_scores_gemma":[0.0026357654,0.0007938112,0.03695407,0.001178436,0.000025123642,0.0004920337,0.002102233,0.8006721,0.15205942,0.0008965621,0.0013553759,0.0008350631],"about_ca_topic_score_codex":0.00029998826,"about_ca_topic_score_gemma":0.00023038077,"teacher_disagreement_score":0.8003615,"about_ca_system_score_codex":0.00013526177,"about_ca_system_score_gemma":0.00004348067,"threshold_uncertainty_score":0.47333944},"labels":[],"label_agreement":null},{"id":"W3133146641","doi":"10.1111/his.14353","title":"Development and initial validation of a deep learning algorithm to quantify histological features in colorectal carcinoma including tumour budding/poorly differentiated clusters","year":2021,"lang":"en","type":"article","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of British Columbia","funders":"","keywords":"Tumor budding; Perineural invasion; Colorectal cancer; Medicine; Algorithm; Carcinoma; Pathology; Lymph node; Metastasis; Lymphovascular invasion; Oncology; Cancer; Internal medicine; Lymph node metastasis; Computer science","score_opus":0.028521582491644545,"score_gpt":0.2786131738773993,"score_spread":0.25009159138575476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133146641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7844632,0.00023025468,0.2143777,0.00014410519,0.0005242661,0.000092710645,7.3236515e-7,0.00005502068,0.00011197435],"genre_scores_gemma":[0.9129242,0.000004144974,0.086905666,0.00006824514,0.000025916297,0.00002994685,0.000009991595,0.000008968097,0.000022958988],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99838877,0.0002952789,0.00035415724,0.00051612407,0.00018190629,0.00026375332],"domain_scores_gemma":[0.9994415,0.00010379952,0.00015557765,0.00012530576,0.000106116924,0.00006770687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003140525,0.00014840673,0.00030140628,0.00030765816,0.00014913072,0.000030396945,0.00021682985,0.0001463604,0.000007971237],"category_scores_gemma":[0.00018456964,0.00016224169,0.000032446533,0.00043344742,0.00007000472,0.00012843676,0.00043359862,0.00029499613,0.000003366863],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023015436,0.00028205532,0.06250204,0.00012822807,0.00001521877,0.002189818,0.044180434,0.00085550133,0.5454623,0.0026120967,0.000066002525,0.3414761],"study_design_scores_gemma":[0.00091539836,0.00036713496,0.79843825,0.000043291697,0.000013875757,0.0009508828,0.00045041245,0.017183924,0.18058811,0.00021169388,0.00048112049,0.00035591837],"about_ca_topic_score_codex":0.000044472097,"about_ca_topic_score_gemma":0.00018265605,"teacher_disagreement_score":0.73593616,"about_ca_system_score_codex":0.0004366853,"about_ca_system_score_gemma":0.000105657724,"threshold_uncertainty_score":0.66160244},"labels":[],"label_agreement":null},{"id":"W3133183798","doi":"10.5858/arpa.2020-0579-oa","title":"Pathologist Concordance for Ovarian Carcinoma Subtype Classification and Identification of Relevant Histologic Features Using Microscope and Whole Slide Imaging","year":2021,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Concordance; Identification (biology); Ovarian carcinoma; Carcinoma; Microscope; Ovarian cancer","score_opus":0.02004562284301263,"score_gpt":0.28480566281005576,"score_spread":0.2647600399670431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133183798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71481395,0.009935258,0.27271315,0.0018035594,0.00042682135,0.00019810541,0.000039992567,0.000028438797,0.000040704454],"genre_scores_gemma":[0.94627154,0.00027838064,0.05315447,0.00017649737,0.000056406476,0.000016220318,0.000014832965,0.000009528831,0.00002210785],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9985406,0.00025252404,0.00044439887,0.0004979938,0.000100951846,0.0001635438],"domain_scores_gemma":[0.99837935,0.00036526922,0.00051225926,0.00045568516,0.00023847519,0.000048979156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004872443,0.00012906057,0.0003227782,0.0001470055,0.00011688666,0.000011677095,0.00020776772,0.000060576698,9.4253284e-7],"category_scores_gemma":[0.0005169787,0.00012076326,0.000023035524,0.00025831672,0.0010963497,0.00016716478,0.000113961265,0.00012762155,1.749656e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037413236,0.000018500266,0.02963313,0.00012242682,0.000006711589,0.00004445571,0.0013793265,0.0000050543476,0.95664704,0.0037873823,0.00006171192,0.008256826],"study_design_scores_gemma":[0.0012938614,0.00032369673,0.7828741,0.00015871644,0.00007797035,0.0003880772,0.00091637863,0.009013734,0.19658999,0.0076160054,0.00055486907,0.00019257033],"about_ca_topic_score_codex":0.0000228646,"about_ca_topic_score_gemma":0.00001993994,"teacher_disagreement_score":0.7600571,"about_ca_system_score_codex":0.00003165034,"about_ca_system_score_gemma":0.0001829696,"threshold_uncertainty_score":0.49245828},"labels":[],"label_agreement":null},{"id":"W3133227625","doi":"10.48550/arxiv.2102.11385","title":"Lightweight Combinational Machine Learning Algorithm for Sorting Canine Torso Radiographs","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Torso; Sorting; Automation; Computer science; Field (mathematics); Process (computing); Artificial intelligence; Algorithm; Computer vision; Engineering; Mathematics; Mechanical engineering; Medicine; Anatomy","score_opus":0.039311479058367106,"score_gpt":0.18626669771651105,"score_spread":0.14695521865814395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133227625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017581131,0.00025436343,0.9786649,0.0001613602,0.0019610452,0.00036059308,0.000023651532,0.00038045415,0.0006125041],"genre_scores_gemma":[0.9625022,0.00022370179,0.034968868,0.000074035124,0.00026991472,0.000007640989,0.00015057786,0.000036442667,0.0017666477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977542,0.00015359884,0.00027765977,0.0012541862,0.00016365871,0.00039665744],"domain_scores_gemma":[0.9981607,0.00017909655,0.00044572068,0.0006619143,0.0004039485,0.00014858737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036288387,0.00033322012,0.00037044918,0.00041779425,0.00043321098,0.00023187281,0.0011584612,0.00028345623,0.000049172755],"category_scores_gemma":[0.00004770471,0.0004217245,0.0003650588,0.0009181074,0.000069998525,0.00047758233,0.0012174702,0.00077199243,0.000006370294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056183493,0.0006044476,0.021736566,0.00056527497,0.0014670689,0.0008884346,0.0018727647,0.6830045,0.0004176241,0.15613073,0.0016852387,0.13157117],"study_design_scores_gemma":[0.00067881704,0.00009408293,0.00061361055,0.00008274639,0.00006811448,0.000012884712,0.000041635943,0.98639894,0.00058400206,0.009033592,0.0019238599,0.00046774565],"about_ca_topic_score_codex":0.00036391016,"about_ca_topic_score_gemma":0.0000952161,"teacher_disagreement_score":0.944921,"about_ca_system_score_codex":0.00046769853,"about_ca_system_score_gemma":0.00029880778,"threshold_uncertainty_score":0.99982345},"labels":[],"label_agreement":null},{"id":"W3133988528","doi":"10.1177/0037549721996031","title":"Evolving convolutional neural network parameters through the genetic algorithm for the breast cancer classification problem","year":2021,"lang":"en","type":"article","venue":"SIMULATION","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Genetic algorithm; CAD; Maxima and minima; Convolution (computer science); Feature (linguistics); Deep learning; Pattern recognition (psychology); Process (computing); Artificial neural network; Machine learning; Algorithm; Mathematics","score_opus":0.0413754468144936,"score_gpt":0.2960581943761255,"score_spread":0.2546827475616319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133988528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096138736,0.0010487478,0.9902568,0.005885446,0.001193314,0.00051471754,0.000011898753,0.00008091764,0.000046770463],"genre_scores_gemma":[0.8680664,0.00004114916,0.13017926,0.0006351488,0.0007023008,0.00027415057,0.000010084556,0.000012863414,0.00007867101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988435,0.00011076382,0.0002175914,0.00032554846,0.0002711897,0.00023140988],"domain_scores_gemma":[0.998392,0.000686866,0.00015619028,0.00040005406,0.00034359377,0.000021313102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019817652,0.000105708,0.00007848721,0.000012833819,0.00058870413,0.00020364978,0.00032165975,0.000054646778,0.000018362904],"category_scores_gemma":[0.000022645992,0.000072462484,0.00007407343,0.00043682905,0.00006134454,0.00044227674,0.00007349264,0.00011882681,0.000004265606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034374925,0.000005744815,0.0003664868,0.0000036643662,0.000017693364,1.6545918e-7,0.00016666613,0.7656235,0.000032506214,0.0010866425,0.0004591975,0.23223428],"study_design_scores_gemma":[0.0001848071,0.000013974091,0.05464426,0.000013202282,0.000023204913,0.000012904093,0.000034783603,0.93439305,0.00003971205,0.00836787,0.0021818946,0.000090332454],"about_ca_topic_score_codex":0.0000844671,"about_ca_topic_score_gemma":0.00003903105,"teacher_disagreement_score":0.867105,"about_ca_system_score_codex":0.00019772322,"about_ca_system_score_gemma":0.00014136336,"threshold_uncertainty_score":0.45278957},"labels":[],"label_agreement":null},{"id":"W3134114476","doi":"10.3390/electronics10050562","title":"Machine Learning Methods for Histopathological Image Analysis: A Review","year":2021,"lang":"en","type":"review","venue":"MDPI (MDPI AG)","topic":"AI in cancer detection","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Artificial intelligence; Computer science; CAD; Segmentation; Feature extraction; Machine learning; Computer-aided diagnosis; Pattern recognition (psychology); Cover (algebra); Image segmentation; Computer vision; Engineering drawing; Engineering","score_opus":0.10026702834612677,"score_gpt":0.4582943368382742,"score_spread":0.3580273084921474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134114476","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4375611e-9,0.52001506,0.4781598,0.00012361385,0.00043845372,0.00059846253,0.000010832815,0.00019967394,0.00045413885],"genre_scores_gemma":[3.9904638e-8,0.6609438,0.3364548,0.00027840736,0.00017567842,0.0006972739,0.00011854447,0.000039712188,0.0012917266],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935777,0.0025694899,0.0012214065,0.0016735288,0.00038082295,0.0005770137],"domain_scores_gemma":[0.99589527,0.000982685,0.0010185811,0.0016581559,0.0002736789,0.00017163051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00394294,0.0006837905,0.0039802897,0.0004714284,0.00028086302,0.0002485355,0.0018224972,0.00039766083,0.00020917169],"category_scores_gemma":[0.0012116065,0.0005486856,0.0027671836,0.0031994244,0.00007873675,0.00027399333,0.0007793552,0.0011286456,0.0000763183],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1387643e-7,0.000025499567,4.5929767e-7,0.014824891,0.00031987665,0.00004134495,0.00002300405,0.0000040582026,8.361429e-7,0.0004925424,0.00109932,0.98316747],"study_design_scores_gemma":[0.00008403241,0.000101880396,7.4309344e-7,0.010377078,0.0049137855,0.00014498379,0.0000012272272,0.0034296254,0.0000020074176,0.00018836658,0.98018366,0.0005725907],"about_ca_topic_score_codex":0.00001786733,"about_ca_topic_score_gemma":0.000006325545,"teacher_disagreement_score":0.98259485,"about_ca_system_score_codex":0.00059680926,"about_ca_system_score_gemma":0.00035504802,"threshold_uncertainty_score":0.9996965},"labels":[],"label_agreement":null},{"id":"W3134537817","doi":"","title":"The Comprehensive Review of Neural Network: An Intelligent Medical Image Compression for Data Sharing","year":2020,"lang":"en","type":"article","venue":"International Journal of Integrated Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Image compression; Artificial neural network; Artificial intelligence; Image processing; Information sharing; Medical information; Image (mathematics); Data mining; Knowledge management; World Wide Web","score_opus":0.06956250996372296,"score_gpt":0.34142503886527076,"score_spread":0.27186252890154783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134537817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016513669,0.007209464,0.98108584,0.007467013,0.0024102512,0.00011649207,0.000010494055,0.000035942365,0.000013149541],"genre_scores_gemma":[0.5620087,0.05093742,0.37306303,0.007644706,0.006020497,0.000031760996,0.00015867405,0.00011920905,0.000016033817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833876,0.000036263315,0.0006305885,0.00019356523,0.00065479946,0.00014603758],"domain_scores_gemma":[0.99785465,0.00027671934,0.00038079027,0.00031897737,0.0010304756,0.00013841222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065789325,0.00011561151,0.00021594274,0.000051968313,0.000039923692,0.00010309962,0.004024645,0.00004022503,0.000014584206],"category_scores_gemma":[0.0007618668,0.00007897891,0.000090646,0.00019653603,0.000028506882,0.00066755037,0.0005490853,0.0003748617,9.1062117e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043465762,0.000109871326,0.000171565,0.0014534432,0.0010111647,0.00017291999,0.0006182489,0.23055817,0.018099004,0.0077992207,0.03826087,0.7013109],"study_design_scores_gemma":[0.00019069503,0.000118111544,0.00004311884,0.0023535434,0.000011179367,0.00011720574,0.000023805347,0.95502096,0.0019517229,0.000074968186,0.040022463,0.00007219991],"about_ca_topic_score_codex":0.000010027741,"about_ca_topic_score_gemma":0.0000017667232,"teacher_disagreement_score":0.7244628,"about_ca_system_score_codex":0.00008481437,"about_ca_system_score_gemma":0.00010910174,"threshold_uncertainty_score":0.7478858},"labels":[],"label_agreement":null},{"id":"W3134562253","doi":"10.1158/1557-3265.adi21-ia-03","title":"Abstract IA-03: Unsupervised resolution of intra- and inter-tumoral heterogeneity using deep learning","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Context (archaeology); Machine learning; Artificial neural network; Deep neural networks; Cancer; Scalability; Medicine; Biology; Database","score_opus":0.28727151812221824,"score_gpt":0.514604831551338,"score_spread":0.22733331342911972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134562253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95780236,0.0021017906,0.03834326,0.00068693265,0.0005896027,0.00015513328,0.000002580432,0.000054050142,0.00026429462],"genre_scores_gemma":[0.99289715,0.0008936897,0.00577796,0.000066911525,0.0002949302,0.000017771972,0.0000015923285,0.000015582615,0.000034415938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996654,0.0009018504,0.00063644047,0.00070390385,0.0006389527,0.00046490805],"domain_scores_gemma":[0.99767876,0.0007673501,0.00013989404,0.0005394762,0.0006735239,0.00020098954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003379399,0.00012048594,0.00032105745,0.00013670992,0.00024106569,0.00014221406,0.00051200285,0.0001630698,0.0000849962],"category_scores_gemma":[0.0009549195,0.00012280059,0.000114208175,0.00078605424,0.00043224441,0.00038266793,0.00079357345,0.0011960405,0.000011440651],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004686489,0.0003420403,0.120972075,0.00042528435,0.00015220378,0.00014212505,0.0007960654,0.003359383,0.048736528,0.00079216954,0.00031247118,0.823501],"study_design_scores_gemma":[0.0030378588,0.001258501,0.35731158,0.00075302174,0.00003581352,0.000077561876,0.00048387374,0.5314614,0.09471969,0.0040321243,0.006123623,0.0007049485],"about_ca_topic_score_codex":0.0006018647,"about_ca_topic_score_gemma":0.0005512738,"teacher_disagreement_score":0.82279605,"about_ca_system_score_codex":0.00026521378,"about_ca_system_score_gemma":0.00047745925,"threshold_uncertainty_score":0.51962674},"labels":[],"label_agreement":null},{"id":"W3138440048","doi":"10.1109/ichi48887.2020.9374352","title":"An Efficient Confidence Measure-Based Evaluation Metric for Breast Cancer Screening Using Bayesian Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Hyperparameter; Metric (unit); Artificial neural network; Bayesian network; Artificial intelligence; Machine learning; Measure (data warehouse); Bayesian probability; Feature (linguistics); Transfer of learning; Data mining; Pattern recognition (psychology)","score_opus":0.07122003278809984,"score_gpt":0.3407494340689796,"score_spread":0.26952940128087977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138440048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044681593,0.00020373547,0.9921166,0.0016793672,0.00053885556,0.00070839975,0.0000059726335,0.00025241563,0.000026512449],"genre_scores_gemma":[0.91613823,7.948458e-7,0.082023,0.0014047934,0.0003388712,0.00007447647,0.0000020652913,0.000016833035,9.2718886e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789685,0.00017816585,0.00026437402,0.00061791315,0.0007051586,0.0003375122],"domain_scores_gemma":[0.99863815,0.0001184131,0.00016206295,0.00035070762,0.0005256191,0.0002050625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008637104,0.0001679501,0.00016887161,0.00014464861,0.000255505,0.00025245643,0.0005651328,0.00007194181,0.000054163967],"category_scores_gemma":[0.00006447533,0.00016277931,0.00008279647,0.0014250535,0.00003096828,0.00046444993,0.000051948537,0.00013559482,6.9377404e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043008822,0.000010144744,0.00020456754,0.000007066688,0.0000074676873,3.8290912e-7,0.000052727475,0.798513,0.00053157896,0.00013871817,0.000019579998,0.20047176],"study_design_scores_gemma":[0.0006212437,0.00014318482,0.0014407869,0.000024157916,0.000040444636,0.0000058898017,0.000022158863,0.99557126,0.0018843025,0.00002940419,0.000009019249,0.0002081587],"about_ca_topic_score_codex":0.0003446985,"about_ca_topic_score_gemma":0.000054936023,"teacher_disagreement_score":0.9116701,"about_ca_system_score_codex":0.0002559535,"about_ca_system_score_gemma":0.0002333439,"threshold_uncertainty_score":0.66379476},"labels":[],"label_agreement":null},{"id":"W3138973186","doi":"10.1016/j.media.2021.102032","title":"Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Ontario Research Foundation","keywords":"Representation (politics); Artificial intelligence; Computer science; Training (meteorology); Image (mathematics); Computer vision; Pattern recognition (psychology); Geography","score_opus":0.038616818534811165,"score_gpt":0.3334691023019692,"score_spread":0.294852283767158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138973186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16939162,0.00033855648,0.8293721,0.00065457716,0.000099202916,0.00005796645,0.0000027174522,0.000028369168,0.000054904118],"genre_scores_gemma":[0.74883974,0.00005882743,0.2508065,0.00013510059,0.00008654246,0.000017195107,0.00001237707,0.0000079741285,0.000035730704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984846,0.0002126831,0.00035844417,0.00042101252,0.00033345137,0.00018981933],"domain_scores_gemma":[0.9975164,0.001658096,0.00016755692,0.0003311851,0.00022329594,0.00010346837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067379506,0.000091994225,0.0003505855,0.0002201322,0.00009916785,0.000057999678,0.00019878458,0.000072376766,0.00007112986],"category_scores_gemma":[0.0061414232,0.00009499403,0.00014182596,0.0010297283,0.00015722564,0.0002837449,0.00015294056,0.000101920195,7.4205417e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005335182,0.00019801252,0.03594834,0.00049816555,0.0010576765,0.0020050462,0.01006636,0.0024740046,0.4242588,0.00074634416,0.0007269772,0.52196693],"study_design_scores_gemma":[0.0005281849,0.000059689828,0.01104992,0.00011768893,0.0008519896,0.00012646479,0.00034508706,0.94747657,0.037826836,0.0013697861,0.000052441817,0.00019533068],"about_ca_topic_score_codex":0.00009722673,"about_ca_topic_score_gemma":0.00020278916,"teacher_disagreement_score":0.94500256,"about_ca_system_score_codex":0.00004713805,"about_ca_system_score_gemma":0.00012590515,"threshold_uncertainty_score":0.7352301},"labels":[],"label_agreement":null},{"id":"W3143953780","doi":"10.1088/1742-6596/1821/1/012014","title":"Comparison of Colorectal Cancer Classification between K-Nearest Neighbors (K-NN) and Neural Network","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial neural network; Artificial intelligence; k-nearest neighbors algorithm; Machine learning; Computer science; Field (mathematics); Colorectal cancer; Cancer; Value (mathematics); Pattern recognition (psychology); Mathematics; Medicine","score_opus":0.06615008404378488,"score_gpt":0.32529209779335333,"score_spread":0.25914201374956847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143953780","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7482914,0.0005577537,0.24867564,0.001326147,0.0008772387,0.00006369227,0.000007002627,0.000018987179,0.00018212617],"genre_scores_gemma":[0.9936448,0.0001619974,0.005703476,0.000022341772,0.00044032108,0.0000026792693,0.0000015596751,0.00000675775,0.00001607142],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988357,0.000098384335,0.0004313296,0.00016486908,0.0003096235,0.00016011985],"domain_scores_gemma":[0.9982537,0.000110420086,0.00069544883,0.00016365721,0.0007025394,0.00007425467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014570473,0.000114999784,0.00036580977,0.00003136922,0.00009817843,0.00013332984,0.00030597358,0.000056060762,0.000009262609],"category_scores_gemma":[0.000028326864,0.000108659486,0.00006445149,0.00036849538,0.00013864247,0.0009945801,0.00011488427,0.00026438036,4.978209e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009565441,0.000092482835,0.34025455,0.00009450574,0.00016976414,0.0000098125965,0.0034834926,0.0051730275,0.040428612,0.051584672,0.0005444196,0.558069],"study_design_scores_gemma":[0.00051290594,0.0007556435,0.46644354,0.00022208983,0.00008669212,0.000043981032,0.0007926346,0.038433794,0.4704991,0.021173948,0.0007361538,0.00029953624],"about_ca_topic_score_codex":0.000018283565,"about_ca_topic_score_gemma":0.000052780357,"teacher_disagreement_score":0.5577695,"about_ca_system_score_codex":0.00005532061,"about_ca_system_score_gemma":0.00038481288,"threshold_uncertainty_score":0.4431005},"labels":[],"label_agreement":null},{"id":"W3151903848","doi":"10.1093/jnci/djab055","title":"RE: Advanced Breast Cancer Definitions by Staging System Examined in the Breast Cancer Surveillance Consortium","year":2021,"lang":"en","type":"letter","venue":"JNCI Journal of the National Cancer Institute","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; ECOG-ACRIN Cancer Research Group","keywords":"Breast cancer; Medicine; Cancer; Oncology; Medical physics; Radiology; Internal medicine","score_opus":0.0496172421570683,"score_gpt":0.29133862469914096,"score_spread":0.24172138254207265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151903848","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032491726,0.0073590213,0.0048997016,0.95136917,0.025129782,0.00077582814,0.0060566654,0.00008900247,0.0010716562],"genre_scores_gemma":[0.52967834,0.006715306,0.0010033221,0.43745872,0.022711001,0.0011886936,0.0001042526,0.00015802884,0.0009823468],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935037,0.0007036924,0.0013563968,0.00070628745,0.0030848375,0.0006451049],"domain_scores_gemma":[0.99404436,0.0004940877,0.0022606326,0.00068326684,0.0024219558,0.00009572131],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013383304,0.00056394126,0.00077274186,0.0003864778,0.0005528459,0.00044530988,0.00325262,0.00042402672,0.00009177406],"category_scores_gemma":[0.00011708475,0.0003918023,0.00041954013,0.0019111608,0.00028689485,0.0014094368,0.00030308016,0.003113775,0.000004055655],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009148399,0.000062839834,0.0031260115,0.00035234325,0.0003719425,0.00018367918,0.0003931407,0.027009636,0.0003089321,0.0005146425,0.9633348,0.00425055],"study_design_scores_gemma":[0.0043051695,0.00007669357,0.050956875,0.007454987,0.00031910365,0.0059346706,0.0003751952,0.0053148195,0.0006947524,0.00088439375,0.92168427,0.0019990932],"about_ca_topic_score_codex":0.0018821056,"about_ca_topic_score_gemma":0.0039187837,"teacher_disagreement_score":0.5264292,"about_ca_system_score_codex":0.005772266,"about_ca_system_score_gemma":0.004830299,"threshold_uncertainty_score":0.9998534},"labels":[],"label_agreement":null},{"id":"W3152390953","doi":"","title":"Computerized cancer malignancy grading of fine needle aspirates","year":2009,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Malignancy; Grading (engineering); Breast cancer; Medicine; Radiology; Cancer; Stage (stratigraphy); Biopsy; Oncology; Internal medicine","score_opus":0.031150592232637792,"score_gpt":0.2919112792150696,"score_spread":0.2607606869824318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152390953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8920692,0.0015253868,0.0070493533,0.0006195665,0.004861548,0.0011389317,0.000019509778,0.00048521027,0.09223128],"genre_scores_gemma":[0.96762145,0.00043613883,0.00072001514,0.000010665306,0.0005395014,0.000009495969,0.000035699566,0.000048717888,0.030578295],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99610883,0.0005125065,0.00045148018,0.0010314644,0.0010875838,0.0008081223],"domain_scores_gemma":[0.99746734,0.00021408682,0.0005033287,0.0010419511,0.00052011147,0.00025317317],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046372926,0.00038444335,0.00063844887,0.0018423429,0.00060046866,0.00022553615,0.002316813,0.00039320544,0.000030331455],"category_scores_gemma":[0.000027484026,0.0004551237,0.00028861323,0.0023711661,0.00016842275,0.0007592967,0.00028798063,0.0010649478,0.000013935222],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038831865,0.0013647143,0.02947938,0.0038090637,0.0023313924,0.0062794834,0.0065696277,0.0012782519,0.45810816,0.0707076,0.020329336,0.3958598],"study_design_scores_gemma":[0.0019365409,0.0018823616,0.09974718,0.0014535524,0.00011798422,0.000046335008,0.0006377266,0.0050571943,0.85868305,0.0042108446,0.024910245,0.0013169871],"about_ca_topic_score_codex":0.01608514,"about_ca_topic_score_gemma":0.012454089,"teacher_disagreement_score":0.4005749,"about_ca_system_score_codex":0.0011523163,"about_ca_system_score_gemma":0.0014969263,"threshold_uncertainty_score":0.9997901},"labels":[],"label_agreement":null},{"id":"W3152579480","doi":"","title":"PathologyGAN: Learning Deep Representations of Cancer Tissue","year":2020,"lang":"en","type":"article","venue":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cancer; Artificial intelligence; Computer science; Breast cancer; Colorectal cancer; Deep learning; Feature (linguistics); Feature vector; Stromal cell; Pattern recognition (psychology); Medicine; Machine learning; Pathology; Internal medicine","score_opus":0.01898930245484571,"score_gpt":0.28565628189055436,"score_spread":0.26666697943570866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152579480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42828318,0.0015173253,0.55958754,0.0074531324,0.0010872633,0.0002756085,0.000005407882,0.0005417944,0.0012487721],"genre_scores_gemma":[0.97567916,0.00027732123,0.022861887,0.00055009726,0.00042536907,0.000028574132,0.000003925818,0.000034491783,0.00013918027],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99771595,0.0002690438,0.0005737123,0.0006510908,0.00039499908,0.000395183],"domain_scores_gemma":[0.9985166,0.00022000798,0.00042117163,0.00044408467,0.00022229893,0.00017579852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038495223,0.00022865042,0.0003399794,0.00018265915,0.00034875862,0.00011809637,0.0009109025,0.00012350477,0.000034098266],"category_scores_gemma":[0.0003024351,0.00023294288,0.00012475354,0.0009610406,0.000100438934,0.00042879736,0.00027709818,0.0006331303,0.000042750784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013185153,0.00015420426,0.023808187,0.00019524638,0.00031136593,0.00032800768,0.06587427,0.048501175,0.6188828,0.008902719,0.0018388167,0.23107138],"study_design_scores_gemma":[0.001991909,0.0016199754,0.008428311,0.0003542165,0.00018685988,0.00025297343,0.0022784774,0.21904567,0.73112035,0.0041657384,0.029133067,0.0014224774],"about_ca_topic_score_codex":0.000108068845,"about_ca_topic_score_gemma":0.000036202462,"teacher_disagreement_score":0.547396,"about_ca_system_score_codex":0.00008474285,"about_ca_system_score_gemma":0.0001504506,"threshold_uncertainty_score":0.94991356},"labels":[],"label_agreement":null},{"id":"W3153404381","doi":"10.1038/s41379-021-00756-3","title":"Abstracts from USCAP 2021: Education (271-295)","year":2021,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Pathology; Medicine","score_opus":0.013491939813853222,"score_gpt":0.25140401754040453,"score_spread":0.23791207772655132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153404381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31086034,0.0010318245,0.6743595,0.0021217954,0.003254463,0.00007337876,0.0000062021927,0.00011596168,0.008176528],"genre_scores_gemma":[0.95153064,0.00005924722,0.04563547,0.0011147788,0.00039375154,0.000032784028,0.000021020407,0.000012617266,0.0011997123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987491,0.00010959138,0.00020082279,0.00056907197,0.00014923904,0.00022222179],"domain_scores_gemma":[0.99888986,0.000063583095,0.00009283276,0.00076491013,0.0001218852,0.00006694787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012160605,0.00010899892,0.00013778004,0.000057320984,0.000080339836,0.00007415005,0.00036679523,0.000135494,0.00013367628],"category_scores_gemma":[0.000054968303,0.00012294321,0.00004807207,0.00017723259,0.00003223826,0.00029403082,0.0001881662,0.00017800018,0.0003464514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072072116,0.00020534851,0.00080187194,0.00000937935,0.000017319204,0.00025772225,0.0020504368,0.0010152449,0.09828373,0.0033903813,0.0034498312,0.8905115],"study_design_scores_gemma":[0.001066015,0.00019759023,0.14103973,0.00007106242,0.00004689286,0.0009597181,0.00021921528,0.085650615,0.2057199,0.4965888,0.067389786,0.0010506612],"about_ca_topic_score_codex":0.00009127279,"about_ca_topic_score_gemma":0.000110610126,"teacher_disagreement_score":0.88946086,"about_ca_system_score_codex":0.000098451696,"about_ca_system_score_gemma":0.00036919428,"threshold_uncertainty_score":0.5013479},"labels":[],"label_agreement":null},{"id":"W3153781230","doi":"10.4103/jpi.jpi_56_20","title":"Selection of Representative Histologic Slides in Interobserver Reproducibility Studies: Insights from Expert Review for Ovarian Carcinoma Subtype Classification","year":2021,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Concordance; Medicine; Context (archaeology); Medical diagnosis; Medical physics; Pathology; Cohort; Internal medicine","score_opus":0.11011704561470036,"score_gpt":0.36802382974583114,"score_spread":0.2579067841311308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153781230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6867027,0.014440208,0.29480004,0.0017453925,0.0018013647,0.00038553492,0.0000038262633,0.00001938352,0.000101549704],"genre_scores_gemma":[0.83890736,0.0041423426,0.15620379,0.0006127135,0.0000897588,0.00002333223,0.0000041871604,0.0000049274513,0.000011577479],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.997681,0.0003344651,0.0014541079,0.00023206073,0.00018512746,0.00011320739],"domain_scores_gemma":[0.9961047,0.00036101518,0.0016458719,0.0006677869,0.0011904897,0.0000300922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014759833,0.00010607648,0.0004925939,0.00014651705,0.00004485919,0.000013476733,0.00032761839,0.00009687656,0.0000048727047],"category_scores_gemma":[0.0029831424,0.00008828249,0.00011278321,0.00046815112,0.00007780156,0.00072659296,0.00011123375,0.00023775532,0.0000011638734],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014562927,0.0021353553,0.19769888,0.010308415,0.0014420642,0.000774089,0.42219904,0.0015410217,0.123653226,0.01527829,0.04713626,0.17637706],"study_design_scores_gemma":[0.0068847467,0.0050290697,0.52184516,0.0062206998,0.00043720333,0.0039041543,0.033562556,0.065456696,0.2723749,0.07513233,0.00790666,0.0012458093],"about_ca_topic_score_codex":0.000010345144,"about_ca_topic_score_gemma":0.0000487187,"teacher_disagreement_score":0.3886365,"about_ca_system_score_codex":0.00037752837,"about_ca_system_score_gemma":0.0002309076,"threshold_uncertainty_score":0.36000553},"labels":[],"label_agreement":null},{"id":"W3154477696","doi":"10.48550/arxiv.2107.12978","title":"Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Lesion; Scanner; Entropy (arrow of time); Computer vision; Medicine; Pathology","score_opus":0.08694388454999236,"score_gpt":0.21932174791650813,"score_spread":0.13237786336651577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154477696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50612485,0.00003751654,0.49289298,0.000016440634,0.0005474832,0.00026146733,0.0000011171024,0.00009836297,0.00001976018],"genre_scores_gemma":[0.87268037,0.0001665868,0.12689662,0.000038269052,0.00012966525,0.000003606001,0.0000068577147,0.000025326286,0.000052689447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979602,0.00015104577,0.00028084556,0.0011815031,0.000120465476,0.00030592285],"domain_scores_gemma":[0.99856615,0.00018675433,0.00040711262,0.0005096682,0.00024610982,0.00008419632],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045414895,0.00029359257,0.00027722324,0.0001922949,0.0007557887,0.0003562745,0.0004111013,0.00027667911,0.000004657577],"category_scores_gemma":[0.00007174623,0.0003673861,0.000087998334,0.00043549057,0.000043781023,0.0011865337,0.0010853537,0.00040839092,0.0000012681958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007370527,0.000038587823,0.001592028,0.00051684596,0.000057215977,0.000032310225,0.0011245956,0.8770491,0.09232239,0.00071714795,0.0000025011748,0.026473558],"study_design_scores_gemma":[0.000573851,0.00009577612,0.0010410333,0.000364037,0.000060376413,0.000015199208,0.0002975851,0.91905195,0.07746315,0.0006662297,0.000004121398,0.00036671365],"about_ca_topic_score_codex":0.00018826022,"about_ca_topic_score_gemma":0.000040947096,"teacher_disagreement_score":0.3665555,"about_ca_system_score_codex":0.0007489835,"about_ca_system_score_gemma":0.00014379509,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W3154595990","doi":"10.1038/s41598-021-87496-1","title":"A review and comparison of breast tumor cell nuclei segmentation performances using deep convolutional neural networks","year":2021,"lang":"en","type":"review","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Hospital; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Terry Fox Research Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Convolutional neural network; Segmentation; Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology); Computational biology; Biology","score_opus":0.04585159507461648,"score_gpt":0.3297263900041229,"score_spread":0.2838747949295064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154595990","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054337783,0.9627625,0.030382983,0.000009885583,0.006053137,0.00065442553,0.000003962844,0.000043232245,0.000035537643],"genre_scores_gemma":[0.00060644775,0.9927941,0.0062469435,0.000031365773,0.000116395415,0.000042976702,0.0000861822,0.000021197906,0.0000543822],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964974,0.00020873753,0.0013518314,0.0010760983,0.0005677343,0.00029817715],"domain_scores_gemma":[0.9964928,0.000058016358,0.002138425,0.00088395504,0.0003195392,0.00010728957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012529136,0.00030335074,0.0012799273,0.00020281994,0.0003508364,0.0003637699,0.00036226737,0.000097326454,0.000038162627],"category_scores_gemma":[0.000021748452,0.00027097814,0.00026376068,0.0013142974,0.0002540271,0.0005905185,0.00035904802,0.00028475316,0.000002023083],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.0951785e-7,0.00006975131,0.0001340523,0.032196682,0.000049636274,0.000056647008,0.0001164616,0.0010298797,0.000012388728,0.000019560022,0.002695819,0.9636184],"study_design_scores_gemma":[0.00012849428,0.00006599689,0.000023448343,0.038928583,0.0013741768,0.010613744,0.00004708164,0.45765263,0.000053264743,0.00009335331,0.4900991,0.0009201261],"about_ca_topic_score_codex":0.000015192634,"about_ca_topic_score_gemma":0.0000058445967,"teacher_disagreement_score":0.9626983,"about_ca_system_score_codex":0.00020430196,"about_ca_system_score_gemma":0.00045440285,"threshold_uncertainty_score":0.99997425},"labels":[],"label_agreement":null},{"id":"W3154729114","doi":"10.3389/fonc.2021.642945","title":"Prediction of Target-Drug Therapy by Identifying Gene Mutations in Lung Cancer With Histopathological Stained Image and Deep Learning Techniques","year":2021,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Hainan Normal University; National Natural Science Foundation of China","keywords":"Lung cancer; H&E stain; Medicine; Deep learning; Pathology; Gene mutation; Gene; Mutation; Immunohistochemistry; Biology; Artificial intelligence; Computer science; Genetics","score_opus":0.011425041889966401,"score_gpt":0.2780695524019389,"score_spread":0.2666445105119725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154729114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13673267,0.005496258,0.85653955,0.0004276322,0.00039988593,0.00019172567,0.0000036223205,0.00007243723,0.00013620577],"genre_scores_gemma":[0.4164858,0.0026043677,0.5804256,0.000096888194,0.00003554919,0.00022387496,0.000010926803,0.000011880079,0.00010513634],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883294,0.00028641228,0.00024096227,0.0003430931,0.0001179227,0.00017864887],"domain_scores_gemma":[0.9995622,0.000054093063,0.00013803317,0.0001303489,0.00008717428,0.00002811692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034448341,0.000091447175,0.00022748129,0.00018547986,0.000064004824,0.000021038117,0.00014732721,0.00009930324,0.000008776322],"category_scores_gemma":[0.000041008432,0.00008928329,0.00001757002,0.00044871468,0.00012657075,0.00029957338,0.0000717396,0.00027319815,6.9210245e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020548496,0.0002872834,0.5263782,0.00008460553,0.000047352467,0.0003342987,0.011052852,0.0017125439,0.14556389,0.00015034861,0.0024797402,0.31170338],"study_design_scores_gemma":[0.0061689354,0.0019792502,0.21211123,0.00025084807,0.000050352628,0.00027697007,0.0048065335,0.34390068,0.39903724,0.00860458,0.021945205,0.0008681766],"about_ca_topic_score_codex":0.000110742,"about_ca_topic_score_gemma":0.00012907088,"teacher_disagreement_score":0.34218815,"about_ca_system_score_codex":0.00069672585,"about_ca_system_score_gemma":0.00015997334,"threshold_uncertainty_score":0.3640867},"labels":[],"label_agreement":null},{"id":"W3157093734","doi":"10.1038/s41598-021-88494-z","title":"Overcoming the limitations of patch-based learning to detect cancer in whole slide images","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of British Columbia; Sunnybrook Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; False positive paradox; Artificial intelligence; Workflow; Context (archaeology); Task (project management); False positives and false negatives; Binary classification; True positive rate; Deep learning; Machine learning; Pattern recognition (psychology); Image (mathematics); Sensitivity (control systems); Support vector machine","score_opus":0.030994109111311646,"score_gpt":0.27550369146245823,"score_spread":0.2445095823511466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157093734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6527306,0.0006572519,0.33039755,0.0055096294,0.009295699,0.00039391752,0.0000026766384,0.00013610705,0.0008765738],"genre_scores_gemma":[0.9847414,0.000005484034,0.013864021,0.00008607265,0.000028921433,0.000059619873,0.000001542418,0.000007651962,0.0012053187],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982355,0.0001169949,0.00037509372,0.0005854691,0.00045799394,0.00022889825],"domain_scores_gemma":[0.9984209,0.0001964979,0.00022247623,0.0008324714,0.00027413917,0.00005355019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012887287,0.00008527609,0.0001239574,0.00017220064,0.00027708296,0.000303544,0.0002761902,0.000030526633,0.000015116843],"category_scores_gemma":[0.0006833008,0.00007330605,0.000065692984,0.0018066604,0.00008240604,0.0002851484,0.0001701909,0.00015944915,0.0000067857636],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000495941,0.000037292386,0.014799654,0.000026247424,0.000012488779,0.00029602714,0.0032800997,0.20605108,0.48762593,0.00005956712,0.0042741112,0.28353253],"study_design_scores_gemma":[0.0001272583,0.000034220368,0.016592737,0.00014639187,0.000009006078,0.000049582213,0.00028205535,0.022328557,0.8672065,0.003830911,0.08919426,0.00019852631],"about_ca_topic_score_codex":0.00027127986,"about_ca_topic_score_gemma":0.0015433709,"teacher_disagreement_score":0.37958056,"about_ca_system_score_codex":0.00013864113,"about_ca_system_score_gemma":0.0005195108,"threshold_uncertainty_score":0.2989334},"labels":[],"label_agreement":null},{"id":"W3157377277","doi":"10.1002/cjp2.227","title":"Reliable computational quantification of liver fibrosis is compromised by inherent staining variation","year":2021,"lang":"en","type":"article","venue":"The Journal of Pathology Clinical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Nottingham Biomedical Research Centre; Nottingham University Hospitals NHS Trust; University of Nottingham; Medical Research Council; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Medical Research Council Canada","keywords":"Biopsy; Medicine; Stain; Liver biopsy; Gold standard (test); Clinical trial; Liver fibrosis; Pathology; Liver disease; Thresholding; Staining; Fibrosis; Artificial intelligence; Medical physics; Radiology; Computer science; Internal medicine","score_opus":0.22871690089455587,"score_gpt":0.4688093677811549,"score_spread":0.24009246688659902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157377277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2856113,0.00069777,0.70768243,0.0053152684,0.00043057295,0.00013669109,0.000007853003,0.000010025042,0.00010807035],"genre_scores_gemma":[0.972062,0.0006367697,0.026880326,0.00019495857,0.00010318359,0.0000031368859,0.000003266171,0.0000059917847,0.000110372835],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951322,0.0025116312,0.0010169169,0.00021999932,0.0008994078,0.00021981102],"domain_scores_gemma":[0.99213547,0.004366708,0.00066478545,0.0004279245,0.0023227462,0.00008239274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012864116,0.00007089288,0.00026471488,0.00012710183,0.00018579382,0.000048469912,0.00075842196,0.00013693928,0.00007057157],"category_scores_gemma":[0.0016950174,0.000053732896,0.0001080903,0.0006362408,0.00029593307,0.00023958336,0.0002720402,0.00089695904,0.000025776797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033990864,0.004329617,0.023705028,0.00037267024,0.0007821414,0.000496804,0.020333733,0.03886554,0.3747263,0.025409997,0.2232843,0.28429478],"study_design_scores_gemma":[0.006558084,0.0068769255,0.30541137,0.0004574546,0.00014220964,0.0010481984,0.0010402421,0.49138734,0.08003149,0.09743075,0.0091047,0.0005112496],"about_ca_topic_score_codex":0.000021695047,"about_ca_topic_score_gemma":0.0000030767717,"teacher_disagreement_score":0.6864507,"about_ca_system_score_codex":0.00009997409,"about_ca_system_score_gemma":0.00061830744,"threshold_uncertainty_score":0.44584715},"labels":[],"label_agreement":null},{"id":"W3158042586","doi":"10.21203/rs.3.rs-225323/v1","title":"Deep learning-based tumor segmentation on digital images of histopathology slides for microdosimetry applications","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canada First Research Excellence Fund; University of Toronto; Government of Ontario; Canada Research Chairs; McGill University","keywords":"Computer science; Digital pathology; Artificial intelligence; Deep learning; Segmentation; Convolutional neural network; Pattern recognition (psychology); Artificial neural network; Process (computing); Overfitting","score_opus":0.036807723507012745,"score_gpt":0.3720991712101173,"score_spread":0.3352914477031046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158042586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012735783,0.00081997924,0.9837476,0.00041265265,0.00022208171,0.0015838486,0.00006326467,0.00013431693,0.00028045793],"genre_scores_gemma":[0.96025246,0.00004312891,0.03673108,0.000038794693,0.00016378476,0.0022165533,0.00025751806,0.00003814306,0.00025852892],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99733704,0.0003496238,0.00035005473,0.0008878916,0.00068673614,0.00038863556],"domain_scores_gemma":[0.99662286,0.0010399175,0.00025279878,0.00092264544,0.0010750972,0.00008667326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087659614,0.00019082891,0.00029057902,0.00059580634,0.0002483544,0.000357108,0.00090795505,0.00016574931,0.00001649143],"category_scores_gemma":[0.0005249833,0.00020951986,0.00019090441,0.0005873549,0.00018428327,0.00020521537,0.0007254341,0.00090004056,0.000017317549],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046523797,0.0018212515,0.009987382,0.011507734,0.00016006132,0.000096963,0.0029577343,0.17091908,0.09806818,0.002453587,0.002741281,0.69882154],"study_design_scores_gemma":[0.0019711023,0.0034011626,0.013959411,0.0014567742,0.00004875502,0.000034857585,0.0018836613,0.21242987,0.7456816,0.0077980855,0.010062675,0.0012720412],"about_ca_topic_score_codex":0.000044275628,"about_ca_topic_score_gemma":0.000013615608,"teacher_disagreement_score":0.9475167,"about_ca_system_score_codex":0.0006922147,"about_ca_system_score_gemma":0.00057746447,"threshold_uncertainty_score":0.8543972},"labels":[],"label_agreement":null},{"id":"W3158436118","doi":"10.1016/j.compbiomed.2021.104418","title":"Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"Australian Research Council","keywords":"Deep learning; Artificial intelligence; Computer science; Dropout (neural networks); Machine learning; Uncertainty quantification; Bayesian probability; Ensemble learning; Contextual image classification; Monte Carlo method; Pattern recognition (psychology); Image (mathematics); Statistics; Mathematics","score_opus":0.04164302445152511,"score_gpt":0.3488364629159524,"score_spread":0.30719343846442726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158436118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13112824,0.0014751498,0.8641731,0.0019390517,0.0010928662,0.00010571701,3.0912864e-7,0.00003689291,0.000048668135],"genre_scores_gemma":[0.95956755,0.00026453467,0.039566733,0.00043523833,0.00012596563,0.000018300729,0.000012579412,0.000005776098,0.0000033027416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985982,0.00021818146,0.00033675006,0.00053396163,0.00010052558,0.00021239277],"domain_scores_gemma":[0.9989443,0.00050193496,0.00012978679,0.00028365324,0.00008598278,0.000054349803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058925716,0.00012322392,0.00023404622,0.00027194768,0.00010627057,0.000017147813,0.00023265091,0.0001471615,0.0000105102745],"category_scores_gemma":[0.00013995645,0.00011117129,0.000019530728,0.00074560585,0.00016503406,0.00010382978,0.000074973235,0.0002776891,9.461491e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003216625,0.000030327845,0.0941974,0.000020009089,0.000007358648,0.000012963159,0.00048891443,0.034072816,0.0046160934,0.0047845095,0.000018052773,0.86171937],"study_design_scores_gemma":[0.00075661,0.00006698218,0.118149064,0.00022569227,0.0000041691355,0.00001033634,0.000066463654,0.8747353,0.0003211209,0.005096096,0.0004620886,0.00010608185],"about_ca_topic_score_codex":0.000359108,"about_ca_topic_score_gemma":0.0020975478,"teacher_disagreement_score":0.86161333,"about_ca_system_score_codex":0.00023758931,"about_ca_system_score_gemma":0.00011301498,"threshold_uncertainty_score":0.4533434},"labels":[],"label_agreement":null},{"id":"W3159603107","doi":"10.1007/s11548-021-02381-6","title":"Domain adaptation and self-supervised learning for surgical margin detection","year":2021,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Classifier (UML); Transfer of learning; Breast cancer; Breast-conserving surgery; Margin (machine learning); Modality (human–computer interaction); Surgical margin; Machine learning; Medicine; Pattern recognition (psychology); Surgery; Cancer; Mastectomy; Resection; Internal medicine","score_opus":0.019672105018974123,"score_gpt":0.24940626987707534,"score_spread":0.22973416485810122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159603107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28089428,0.00056337385,0.7151066,0.0012909584,0.0020678737,0.00003292129,5.1503804e-7,0.000026508995,0.000016966362],"genre_scores_gemma":[0.90181375,0.0005167029,0.09661297,0.00020790467,0.0008171703,0.0000051621178,0.0000043575874,0.000007313533,0.00001470262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873537,0.0003182999,0.000410751,0.00021180784,0.00019450435,0.00012929685],"domain_scores_gemma":[0.99782026,0.0012616072,0.0002759095,0.0000713105,0.00050006097,0.00007083358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007753732,0.00010081803,0.0002518893,0.00024524107,0.000107913285,0.00012109289,0.00015704398,0.00010791454,0.0000034213997],"category_scores_gemma":[0.000050022438,0.000096163734,0.00012346466,0.00011982145,0.00004222418,0.0003933857,0.00007027702,0.00021378824,4.3558825e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041953428,0.00014147398,0.013591535,0.000036076777,0.0007171827,0.0008388807,0.0010613239,0.00227209,0.0014895814,0.0026024613,0.0004109987,0.97641885],"study_design_scores_gemma":[0.00436237,0.0005621742,0.13765642,0.00017526676,0.000060183505,0.054136384,0.00015621795,0.7256901,0.001898903,0.0061996775,0.06864102,0.00046124475],"about_ca_topic_score_codex":0.0000020055493,"about_ca_topic_score_gemma":0.000003471505,"teacher_disagreement_score":0.97595763,"about_ca_system_score_codex":0.00007652699,"about_ca_system_score_gemma":0.00012309871,"threshold_uncertainty_score":0.39214432},"labels":[],"label_agreement":null},{"id":"W3160710436","doi":"10.4258/hir.2021.27.2.146","title":"Histoscope: A Web-Based Microscopy Tool for Oral Histology Education","year":2021,"lang":"en","type":"article","venue":"Healthcare Informatics Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Digital microscope; Virtual microscopy; Computer science; Histology; Microscope; Context (archaeology); Digital pathology; Multimedia; Microscopy; Telepathology; Artificial intelligence; World Wide Web; Pathology; Medicine; Biology","score_opus":0.0987787863363113,"score_gpt":0.4575919637239345,"score_spread":0.3588131773876232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160710436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035419002,0.001975804,0.9164421,0.036623515,0.004379847,0.0021154396,0.000050181527,0.00036350466,0.0026305823],"genre_scores_gemma":[0.27306488,0.0002014172,0.7161739,0.0069765463,0.00025833654,0.0013736006,0.00012686764,0.000040228304,0.001784265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745965,0.0003021045,0.00060584396,0.00026597496,0.00066981174,0.0006966118],"domain_scores_gemma":[0.9961254,0.00043137395,0.00014419683,0.00093179755,0.0021857654,0.00018145124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017051403,0.0001299301,0.00021617512,0.00041886256,0.00051649637,0.00022573776,0.00072211225,0.00017972905,0.000029272876],"category_scores_gemma":[0.0005074256,0.0001411653,0.00007013045,0.0010867416,0.00011347721,0.00056257745,0.00021979374,0.0005225173,0.00010612273],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014031121,0.0002935426,0.00086598576,0.0038630052,0.000021881093,0.000009695145,0.0042692292,0.00013207298,0.0023583088,0.047908325,0.1768804,0.76325727],"study_design_scores_gemma":[0.0010200997,0.0005993753,0.00023345024,0.00016207974,0.0000037199497,0.000081935985,0.000464936,0.15275238,0.018206084,0.0044425847,0.8217311,0.0003022722],"about_ca_topic_score_codex":0.0002098049,"about_ca_topic_score_gemma":0.0002840039,"teacher_disagreement_score":0.76295495,"about_ca_system_score_codex":0.0016418208,"about_ca_system_score_gemma":0.011688335,"threshold_uncertainty_score":0.9939145},"labels":[],"label_agreement":null},{"id":"W3160847342","doi":"10.5858/arpa.2020-0723-cp","title":"Validating Whole Slide Imaging Systems for Diagnostic Purposes in Pathology","year":2021,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York Central Hospital","funders":"","keywords":"Guideline; Medicine; Grading (engineering); Concordance; Medical physics; Telepathology; Context (archaeology); Medical diagnosis; MEDLINE; Pathology; Health care","score_opus":0.013545898990770425,"score_gpt":0.2739924397818307,"score_spread":0.2604465407910603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160847342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33187866,0.017830888,0.64095336,0.0044008465,0.003363744,0.00060416263,0.000060381866,0.00015678263,0.00075118773],"genre_scores_gemma":[0.9759844,0.00034440117,0.022305906,0.0007104878,0.00035287475,0.00020714781,0.000023310266,0.000025471578,0.00004597784],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976515,0.0005955874,0.0005959239,0.0006021414,0.00016918303,0.00038565695],"domain_scores_gemma":[0.9955012,0.0033006552,0.00029347534,0.0006460231,0.00017958644,0.000079022044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076680095,0.00018181828,0.0004970708,0.00030524458,0.00008628587,0.000013869853,0.00048865017,0.000066905,0.000004427426],"category_scores_gemma":[0.0028275251,0.00017481155,0.000046320278,0.00049218495,0.0005232284,0.00022081226,0.00022210476,0.00022853077,0.0000035618348],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055359968,0.00022186038,0.06435674,0.0006972696,0.000051804243,0.00640405,0.017413523,0.0014676076,0.8197655,0.034323,0.0012811589,0.053962104],"study_design_scores_gemma":[0.023905644,0.0049716495,0.3027838,0.007720549,0.00045257685,0.006436891,0.020742316,0.13310125,0.31478438,0.119666606,0.06215411,0.0032802385],"about_ca_topic_score_codex":0.000020892106,"about_ca_topic_score_gemma":0.00003268121,"teacher_disagreement_score":0.64410573,"about_ca_system_score_codex":0.000045867284,"about_ca_system_score_gemma":0.0002676016,"threshold_uncertainty_score":0.71286076},"labels":[],"label_agreement":null},{"id":"W3162760820","doi":"10.1002/cncy.22443","title":"A deep learning system to diagnose the malignant potential of urothelial carcinoma cells in cytology specimens","year":2021,"lang":"en","type":"article","venue":"Cancer Cytopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"Japan Society for the Promotion of Science","keywords":"Medicine; Cytopathology; Cytology; Urine cytology; Papanicolaou stain; Medical diagnosis; High-power field; Pathology; Artificial intelligence; Radiology; Cancer; Internal medicine; Bladder cancer; Computer science; Cervical cancer; Immunohistochemistry","score_opus":0.009160045762441239,"score_gpt":0.23469621897155132,"score_spread":0.2255361732091101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162760820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7952157,0.0010335088,0.19866712,0.0013057431,0.0030094034,0.00029082852,0.000008598717,0.000070476504,0.0003985995],"genre_scores_gemma":[0.9968324,0.00007801287,0.002159582,0.00034121363,0.00028079544,0.00017631002,9.247926e-7,0.000017120714,0.0001136601],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99781466,0.00057027955,0.00039319904,0.0005976844,0.0001889727,0.00043518384],"domain_scores_gemma":[0.9988881,0.00012996454,0.00016480466,0.0005976527,0.00014781413,0.00007171411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035949898,0.00016343035,0.00036236327,0.00014896873,0.00009977091,0.000029418272,0.0006448864,0.0001286907,0.00003663323],"category_scores_gemma":[0.000049282884,0.00014149897,0.0000850112,0.0006165177,0.00010473531,0.000089970876,0.00044179813,0.00030480942,0.000031829408],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002356061,0.00039388533,0.039649602,0.0002681643,0.00004994053,0.008904321,0.011782858,0.061722104,0.79672533,0.020140342,0.00036214612,0.0597657],"study_design_scores_gemma":[0.0054859095,0.0011668204,0.120816,0.00026780143,0.00009087696,0.0038272683,0.0027724644,0.07629815,0.7763604,0.00066468806,0.01126697,0.0009826771],"about_ca_topic_score_codex":0.00027672277,"about_ca_topic_score_gemma":0.00064512633,"teacher_disagreement_score":0.20161666,"about_ca_system_score_codex":0.0003406308,"about_ca_system_score_gemma":0.00025071908,"threshold_uncertainty_score":0.57701606},"labels":[],"label_agreement":null},{"id":"W3162818615","doi":"10.1109/icpr48806.2021.9412478","title":"Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Embedding; Computer science; Prior probability; Bayesian probability; MNIST database; Sampling (signal processing); Bayesian network; Artificial intelligence; Gibbs sampling; Data mining; Subspace topology; Machine learning; Pattern recognition (psychology); Deep learning; Detector","score_opus":0.19555856327727475,"score_gpt":0.2394912117054368,"score_spread":0.04393264842816205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162818615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022487871,0.000048175363,0.9732084,0.00017334173,0.0019465839,0.0008452106,0.000037264064,0.0005004973,0.00075262657],"genre_scores_gemma":[0.9252206,0.00003428319,0.073589906,0.00025699122,0.00074339664,0.0000047633116,0.000045497494,0.00006021326,0.000044364755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966552,0.00022015584,0.0004665476,0.0017832028,0.00016498481,0.00070987607],"domain_scores_gemma":[0.99764156,0.00034254644,0.00066286244,0.00095364527,0.00014106034,0.00025830866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007693864,0.00051259366,0.0006033479,0.00027401577,0.00056416745,0.00033696074,0.001946924,0.0004104401,0.000026456572],"category_scores_gemma":[0.00009689478,0.000660091,0.0004285579,0.0008588209,0.000103520746,0.0005958272,0.0017454976,0.00093624275,0.000004713112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015538388,0.000029193852,0.00034072198,0.00012641757,0.00020959777,0.00006236277,0.00092281116,0.9172787,0.0004505646,0.072420985,0.00013527497,0.007867968],"study_design_scores_gemma":[0.0009666268,0.00009391796,0.00004558266,0.00018544016,0.00012117802,0.000009916725,0.00058514165,0.96481794,0.00025499787,0.03183054,0.00044559297,0.00064314983],"about_ca_topic_score_codex":0.00013897312,"about_ca_topic_score_gemma":0.000037009544,"teacher_disagreement_score":0.90273273,"about_ca_system_score_codex":0.0008907592,"about_ca_system_score_gemma":0.00046970605,"threshold_uncertainty_score":0.99958503},"labels":[],"label_agreement":null},{"id":"W3163210332","doi":"10.18280/ts.380215","title":"Comparative Analysis of Texture Patterns on Mammograms for Classification","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quadratic classifier; Artificial intelligence; Pattern recognition (psychology); Support vector machine; Classifier (UML); Naive Bayes classifier; Linear discriminant analysis; Bayes classifier; Local binary patterns; Computer science; Random forest; AdaBoost; Linear classifier; Mathematics; Histogram","score_opus":0.05635913491711911,"score_gpt":0.308214551600478,"score_spread":0.25185541668335887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163210332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0744452,0.000023638451,0.92423564,0.00051039853,0.00012370259,0.00019513785,0.00004192077,0.000040858078,0.00038350586],"genre_scores_gemma":[0.9944344,0.0000041966873,0.005124235,0.00018788365,0.00005621108,0.000074140604,0.00006061312,0.0000034230557,0.000054905817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895823,0.00006130355,0.00024410801,0.0003252293,0.00027803428,0.00013307792],"domain_scores_gemma":[0.9992242,0.000117159754,0.0001537508,0.0002821404,0.00018420133,0.000038546492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015635522,0.00009679115,0.00022049111,0.00015387175,0.0000625367,0.000052072628,0.0002469213,0.000040342802,0.00010265827],"category_scores_gemma":[0.0000045156735,0.00009217539,0.00016163553,0.000780479,0.00001982671,0.00012676293,0.000029163719,0.000061371284,0.0000036055078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043054714,0.0026498148,0.03728538,0.00028958241,0.0072548334,0.000019399427,0.015641565,0.05726472,0.19199763,0.17588876,0.006800216,0.50447756],"study_design_scores_gemma":[0.0006574443,0.00044938273,0.17092437,0.000030876945,0.00034932315,0.0000013520356,0.00037438053,0.75643665,0.06672211,0.00056545093,0.003278387,0.00021029676],"about_ca_topic_score_codex":0.000009432453,"about_ca_topic_score_gemma":0.00007783563,"teacher_disagreement_score":0.91998917,"about_ca_system_score_codex":0.00008085861,"about_ca_system_score_gemma":0.000041354142,"threshold_uncertainty_score":0.3758803},"labels":[],"label_agreement":null},{"id":"W3163753640","doi":"10.1038/s41598-024-52183-4","title":"DiagSet: a dataset for prostate cancer histopathological image classification","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"European Regional Development Fund; National Center for Research and Development","keywords":"Medical diagnosis; Thresholding; Computer science; Artificial intelligence; Pattern recognition (psychology); Prostate cancer; Cancer detection; Cancer; Image (mathematics); Machine learning; Radiology; Medicine","score_opus":0.03572578786713289,"score_gpt":0.3208717744251828,"score_spread":0.2851459865580499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163753640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018892862,0.0017260923,0.9062753,0.0060628527,0.062986806,0.0017514272,0.00061443134,0.0010363623,0.0006538767],"genre_scores_gemma":[0.92924476,0.000069198286,0.05625924,0.00027530725,0.0006187819,0.0025118338,0.0017883906,0.00005050977,0.009181952],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976693,0.00003504812,0.0003578402,0.0012707436,0.0003768076,0.000290257],"domain_scores_gemma":[0.99848753,0.000052507345,0.00013951596,0.0011045638,0.00013233344,0.000083558385],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015285665,0.00012091587,0.000113437265,0.00016596928,0.0002964909,0.00122038,0.00033843526,0.000055857556,0.000023536324],"category_scores_gemma":[0.000103007435,0.0001012699,0.00006960367,0.000681548,0.00019232278,0.00089519186,0.00013721331,0.00011019905,0.00006845087],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072340617,0.000044744385,0.00022914956,0.00013177769,0.000010072098,0.0004920969,0.0006690395,0.000038079095,0.08706926,0.0021346468,0.7596842,0.14948967],"study_design_scores_gemma":[0.000046192006,0.000036829864,0.00054627267,0.000040448216,0.0000117768905,0.00023407994,0.000011485121,0.0409531,0.010008979,0.023764506,0.924174,0.00017231642],"about_ca_topic_score_codex":0.000022319842,"about_ca_topic_score_gemma":0.000022533379,"teacher_disagreement_score":0.91035193,"about_ca_system_score_codex":0.00025657512,"about_ca_system_score_gemma":0.00029773763,"threshold_uncertainty_score":0.9998165},"labels":[],"label_agreement":null},{"id":"W3164879340","doi":"10.1109/isbi48211.2021.9433836","title":"Deep Fisher Vector Coding For Whole Slide Image Classification","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Statistic; Pooling; Artificial intelligence; Pattern recognition (psychology); Population; Task (project management); Coding (social sciences); Machine learning; Data mining; Mathematics; Statistics","score_opus":0.03242260540169281,"score_gpt":0.27480580372853497,"score_spread":0.24238319832684216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164879340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006567419,0.000031633754,0.98568785,0.004636256,0.00067756657,0.00011012536,9.634649e-7,0.00017628711,0.008022562],"genre_scores_gemma":[0.46726507,0.000010456024,0.5254895,0.0010043642,0.00028935997,0.000119668366,0.000008952276,0.000016803584,0.0057958146],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992864,0.00002369172,0.00012195914,0.0002998673,0.00011900795,0.00014906551],"domain_scores_gemma":[0.9993132,0.00008791341,0.000044511693,0.00036325178,0.0001529011,0.000038257618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011974894,0.000062504936,0.00006823763,0.000029619156,0.00010114974,0.00019323893,0.00023237511,0.00003942657,0.00006436111],"category_scores_gemma":[0.00006633181,0.00006341054,0.00004675319,0.00023143114,0.000012713239,0.0005043679,0.00007037231,0.00005266293,0.000073810625],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000130333765,0.00008079053,0.00037701998,0.00007621199,0.00003428393,0.0000097536295,0.0006754381,0.00010880812,0.5965133,0.10277946,0.053527668,0.24580425],"study_design_scores_gemma":[0.00036573454,0.00004935677,0.0055199517,0.000012063151,0.0000071409363,0.000014528034,0.00012215783,0.68434227,0.22202656,0.0045083095,0.08283015,0.00020177076],"about_ca_topic_score_codex":0.0000067726537,"about_ca_topic_score_gemma":0.0000473419,"teacher_disagreement_score":0.6842335,"about_ca_system_score_codex":0.00010861114,"about_ca_system_score_gemma":0.000057716763,"threshold_uncertainty_score":0.25858065},"labels":[],"label_agreement":null},{"id":"W3164919620","doi":"10.48550/arxiv.2105.09983","title":"Optimizing Neural Network Weights using Nature-Inspired Algorithms","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Machine learning; Optimization algorithm; Feedforward neural network; Algorithm; Data mining; Mathematical optimization; Mathematics","score_opus":0.0625879317427007,"score_gpt":0.20471185054159433,"score_spread":0.14212391879889363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164919620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22164404,0.0006153674,0.7711776,0.000056771227,0.0052349423,0.00022264363,0.0000030909196,0.00042046572,0.000625097],"genre_scores_gemma":[0.9202908,0.00015624275,0.0784069,0.00019317839,0.00068168197,8.7123055e-7,0.000011274568,0.000034981807,0.00022405111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970179,0.00023505441,0.00025945564,0.0017012488,0.00017980419,0.00060651504],"domain_scores_gemma":[0.9975113,0.00008927771,0.0003734605,0.0015778103,0.0002511074,0.00019699479],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002327081,0.0004403156,0.0004466293,0.0002326782,0.00040560076,0.00039653917,0.0019513426,0.000749393,0.000020760026],"category_scores_gemma":[0.00001552697,0.0005509328,0.00034315028,0.0012422822,0.000091715796,0.00081495097,0.0031936858,0.0017131458,0.000010311855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001208447,0.000025352894,0.0004386989,0.00003772251,0.00009575731,0.00065617985,0.00016636166,0.9918741,0.00003649096,0.0054043815,0.00006268431,0.0011901773],"study_design_scores_gemma":[0.00029090364,0.000028869288,0.0003472846,0.0001765261,0.000075771546,0.0000294741,0.00004021457,0.9918268,0.0003725344,0.005951679,0.00028434937,0.00057560793],"about_ca_topic_score_codex":0.00022548388,"about_ca_topic_score_gemma":0.000059465263,"teacher_disagreement_score":0.6986468,"about_ca_system_score_codex":0.00077449623,"about_ca_system_score_gemma":0.0003676482,"threshold_uncertainty_score":0.9996942},"labels":[],"label_agreement":null},{"id":"W3165215947","doi":"10.1109/tmi.2021.3085712","title":"MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Alberta","funders":"Österreichische Forschungsförderungsgesellschaft; UK Research and Innovation","keywords":"Segmentation; Event (particle physics); Concordance; Class (philosophy); Pattern recognition (psychology); Key (lock); Ground truth","score_opus":0.029618269351456603,"score_gpt":0.2912371521399943,"score_spread":0.2616188827885377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165215947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029573084,0.00019303408,0.9841336,0.011131097,0.0009568573,0.00010809416,0.0000021536848,0.00025372,0.00026411016],"genre_scores_gemma":[0.9670498,0.0005380841,0.031181226,0.00096831785,0.00007038542,0.000046846544,0.0000016157481,0.000017895172,0.00012587165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984578,0.00011053072,0.00023153023,0.000483508,0.0005110873,0.00020553419],"domain_scores_gemma":[0.9992241,0.00010161251,0.000056975496,0.00032772255,0.00009057723,0.00019897791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002259983,0.00012841685,0.00011886633,0.000112428716,0.00024207942,0.00012233046,0.00021318879,0.0000743671,0.00013421179],"category_scores_gemma":[0.000021597838,0.00013712235,0.00004756689,0.0003764547,0.00008523231,0.0005367899,0.00000533539,0.00035614992,0.000059679176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051091474,0.0001828426,0.000032122072,0.000023754503,0.000019771756,0.000048522517,0.0010022444,0.000113412636,0.014213112,0.00022184536,0.00010429405,0.984033],"study_design_scores_gemma":[0.0011622548,0.00004252839,0.0008683565,0.00009879109,0.000026135021,0.00018883072,0.00055915344,0.934789,0.06036101,0.00033759399,0.0013025667,0.00026378623],"about_ca_topic_score_codex":0.000020645944,"about_ca_topic_score_gemma":0.000051143717,"teacher_disagreement_score":0.9837692,"about_ca_system_score_codex":0.00013673029,"about_ca_system_score_gemma":0.0001267421,"threshold_uncertainty_score":0.5591687},"labels":[],"label_agreement":null},{"id":"W3165855571","doi":"10.1109/isbi48211.2021.9434036","title":"Colorectal Cancer Tissue Classification Using Semi-Supervised Hypergraph Convolutional Network","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Terry Fox Foundation","keywords":"Hypergraph; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Deep learning; Artificial neural network; Mathematics","score_opus":0.03826354965499948,"score_gpt":0.28639436638565324,"score_spread":0.24813081673065376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165855571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10708757,0.00092046865,0.88487345,0.0013709072,0.0022313367,0.00014050343,0.000004051532,0.0002668768,0.0031048304],"genre_scores_gemma":[0.92116225,0.00009538856,0.07702287,0.00053634326,0.00060585263,0.000045200977,0.000008025698,0.0000129057835,0.000511166],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986996,0.000085884014,0.00020189903,0.00044507763,0.00028924993,0.00027831306],"domain_scores_gemma":[0.9992438,0.00006218311,0.000069215836,0.00029475673,0.00025142837,0.00007859595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013705847,0.00011782954,0.00012748486,0.00004535456,0.00023326966,0.00011075352,0.00029084645,0.000093374656,0.00029957373],"category_scores_gemma":[0.000013828121,0.0001242609,0.00005077457,0.00089571154,0.000050126415,0.00040784944,0.00013353556,0.00012441805,0.00003054055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049099417,0.0001463368,0.023022205,0.000045879002,0.00016253437,0.000038486156,0.0004514906,0.053832576,0.6750508,0.120006435,0.018142855,0.10905128],"study_design_scores_gemma":[0.00032012493,0.0000395549,0.017681954,0.000028058867,0.000014775,0.00007228898,0.000038311133,0.91652304,0.051245715,0.0024369694,0.011330904,0.00026830478],"about_ca_topic_score_codex":0.00017482127,"about_ca_topic_score_gemma":0.00022268025,"teacher_disagreement_score":0.86269045,"about_ca_system_score_codex":0.00028790816,"about_ca_system_score_gemma":0.00042208604,"threshold_uncertainty_score":0.50672126},"labels":[],"label_agreement":null},{"id":"W3168214987","doi":"10.1017/cjn.2021.91","title":"Synthesis of glioma histopathology images using generative adversarial networks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Discriminator; Artificial intelligence; Deep learning; Generative grammar; Generator (circuit theory); Set (abstract data type); Pattern recognition (psychology); Machine learning","score_opus":0.03291810227836283,"score_gpt":0.2611222735288195,"score_spread":0.22820417125045667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168214987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96223044,0.0020068611,0.029181989,0.002414883,0.0030567965,0.00008539066,0.000007822976,0.00002049787,0.0009953063],"genre_scores_gemma":[0.9580325,0.00023472824,0.040204916,0.0010906666,0.0004176146,0.0000017910694,8.07812e-8,0.000009390352,0.000008318172],"study_design_codex":"observational","study_design_gemma":"case_report","domain_scores_codex":[0.99428105,0.0019350053,0.0010772678,0.0007029683,0.00079650804,0.0012071938],"domain_scores_gemma":[0.9952876,0.0009502279,0.0012912091,0.00028074087,0.0010304819,0.0011597214],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0039650993,0.0003237862,0.0006566037,0.0009848595,0.0021744894,0.00063411274,0.0031256229,0.00024317432,0.00008241612],"category_scores_gemma":[0.0030417966,0.00024878065,0.00031716257,0.0025098894,0.0057813344,0.0017588797,0.00020642541,0.0010010992,9.571129e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002900819,0.00021004438,0.47626296,0.000041648247,0.00010110445,0.08469379,0.0019783145,0.3553123,0.014790784,0.018889343,0.0023300108,0.045099635],"study_design_scores_gemma":[0.001527642,0.1011994,0.09325689,0.00028908334,0.0003189641,0.4197808,0.00079089135,0.19784902,0.078617565,0.100588776,0.0035055017,0.0022754597],"about_ca_topic_score_codex":0.0008253346,"about_ca_topic_score_gemma":0.014674891,"teacher_disagreement_score":0.38300607,"about_ca_system_score_codex":0.00042551427,"about_ca_system_score_gemma":0.0061867028,"threshold_uncertainty_score":0.9999964},"labels":[],"label_agreement":null},{"id":"W3169323730","doi":"10.1007/s11042-021-11114-5","title":"Predicting breast cancer biopsy outcomes from BI-RADS findings using random forests with chi-square and MI features","year":2021,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ontario Institute of Technology","funders":"","keywords":"Random forest; Breast cancer; Computer science; Mammography; Classifier (UML); Biopsy; BI-RADS; Feature selection; Artificial intelligence; Estimator; Medicine; Machine learning; Breast cancer screening; Cancer; Radiology; Pattern recognition (psychology); Statistics; Internal medicine; Mathematics","score_opus":0.01907542134954093,"score_gpt":0.2658236636203795,"score_spread":0.24674824227083858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169323730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62438893,0.0011668279,0.37147367,0.0017591555,0.00014764133,0.00049014686,0.00035202695,0.00015387646,0.000067692985],"genre_scores_gemma":[0.9438483,0.000118024815,0.055239256,0.00012580625,0.00022191428,0.0003646723,0.000026198406,0.000017016206,0.000038781378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99898386,0.000022762146,0.00015684176,0.0004741751,0.00017202081,0.00019036775],"domain_scores_gemma":[0.99923766,0.00017736659,0.000082400926,0.00031023036,0.0000854344,0.00010693055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006189051,0.0001511017,0.00018362266,0.00004839192,0.0003360877,0.00029973596,0.0001655404,0.000073227064,0.000013536855],"category_scores_gemma":[0.000016750686,0.00012483998,0.0000308832,0.00031240922,0.00008206158,0.00036964964,0.00013244005,0.00013828582,0.000001302431],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003137254,0.000051075036,0.7156472,0.00004039261,0.00010359415,0.0000066627194,0.0012093206,0.00033251886,0.004984799,0.00022707607,0.000077535275,0.27728844],"study_design_scores_gemma":[0.0014295898,0.00001121627,0.9382469,0.000091782655,0.000049248345,0.00009859809,0.00011061768,0.056623492,0.0024524473,0.00026174175,0.00040603548,0.00021830911],"about_ca_topic_score_codex":0.00071851636,"about_ca_topic_score_gemma":0.00056605134,"teacher_disagreement_score":0.31945938,"about_ca_system_score_codex":0.000042722153,"about_ca_system_score_gemma":0.00007779293,"threshold_uncertainty_score":0.5090827},"labels":[],"label_agreement":null},{"id":"W3170559994","doi":"10.1096/fasebj.27.1_supplement.959.3","title":"Online Histology modules for first‐year medical students: a student to student approach","year":2013,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"American Anthropological Association","keywords":"Medical education; Perspective (graphical); Histology; Computer science; Multimedia; Medicine; Mathematics education; Psychology; Pathology; Artificial intelligence","score_opus":0.022946055735803016,"score_gpt":0.3092161760693227,"score_spread":0.28627012033351973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170559994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38658503,0.00013080087,0.6026377,0.008764759,0.0011713819,0.0005839876,0.0000024095648,0.000054068474,0.00006983932],"genre_scores_gemma":[0.9443041,0.000080738035,0.05137945,0.0024531274,0.0010893664,0.00024888144,0.0000016189693,0.000023780094,0.00041894923],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970554,0.00016217615,0.0004315315,0.0003363686,0.0015821899,0.00043233114],"domain_scores_gemma":[0.9985592,0.000170785,0.00017547069,0.00054270827,0.00021547484,0.00033637256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013345949,0.00017606084,0.00024529122,0.0001299538,0.00044567828,0.0004197362,0.004155927,0.00008574058,0.00009755187],"category_scores_gemma":[0.00009823515,0.00011470987,0.00012246986,0.0002246046,0.00007555824,0.0002754337,0.0008739784,0.00045158123,0.00008934264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063209067,0.017699597,0.077603415,0.00023174504,0.0031539858,0.0002567672,0.08144303,0.025695955,0.0047108266,0.0430679,0.32105893,0.42444575],"study_design_scores_gemma":[0.020686634,0.010025861,0.6147007,0.0005794406,0.0004373238,0.0066650664,0.020921169,0.21937297,0.004279074,0.028996564,0.0700129,0.0033223056],"about_ca_topic_score_codex":0.00002984319,"about_ca_topic_score_gemma":0.00006035787,"teacher_disagreement_score":0.55771905,"about_ca_system_score_codex":0.00039281833,"about_ca_system_score_gemma":0.000101670536,"threshold_uncertainty_score":0.7722815},"labels":[],"label_agreement":null},{"id":"W3174333731","doi":"10.1109/icaibd51990.2021.9459074","title":"Deep Learning Approach for Breast Ultrasound Image Segmentation","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Breast ultrasound; Artificial intelligence; Preprocessor; Segmentation; Deep learning; Residual; CAD; Feature extraction; Breast cancer; Pattern recognition (psychology); Image segmentation; Mammography; Cancer; Engineering; Engineering drawing; Algorithm","score_opus":0.01194038351076997,"score_gpt":0.24826015591898953,"score_spread":0.23631977240821955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174333731","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009006847,0.00003404412,0.9905724,0.00015335888,0.00017194265,0.00011179101,7.4806167e-7,0.00017012253,0.007884893],"genre_scores_gemma":[0.20798494,0.000008305995,0.7903325,0.00012912229,0.000094262345,0.000048792037,0.000013741561,0.000007789878,0.0013805644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931157,0.000038456976,0.00009680692,0.00028334948,0.00012887742,0.00014095736],"domain_scores_gemma":[0.99955577,0.0000781133,0.00004001787,0.00017789639,0.000115057665,0.000033169817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013351692,0.000063088504,0.00006038637,0.000028049064,0.00013504396,0.0001930618,0.0001579512,0.000029167531,0.000050560513],"category_scores_gemma":[0.00002703134,0.000063717765,0.00004086615,0.00022851002,0.000013203713,0.00049481273,0.000049435665,0.000069447844,0.000013754774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017022798,0.00012320944,0.00097332534,0.00009992495,0.000055025746,0.000004974545,0.0016594144,0.01413963,0.23613158,0.013240388,0.0011458064,0.7324097],"study_design_scores_gemma":[0.00060250564,0.00007100073,0.0024811823,0.0000049407286,0.000011086848,0.00040804394,0.00074828876,0.8476581,0.14499936,0.0017183878,0.0010460977,0.00025104062],"about_ca_topic_score_codex":0.000009087574,"about_ca_topic_score_gemma":0.0000065110976,"teacher_disagreement_score":0.83351845,"about_ca_system_score_codex":0.000076508564,"about_ca_system_score_gemma":0.00003300266,"threshold_uncertainty_score":0.25983348},"labels":[],"label_agreement":null},{"id":"W3175685598","doi":"10.1096/fasebj.2019.33.1_supplement.444.21","title":"Creation and Use of Medical Histology‐Pathology Electronic Flashcards","year":2019,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Virtual microscopy; Curriculum; Recall; Medical education; Reading (process); Histology; Computer science; Pathology; Medicine; Psychology; Multimedia; Pedagogy","score_opus":0.013174197763966389,"score_gpt":0.2569825853789594,"score_spread":0.24380838761499302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175685598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84314543,0.00035646054,0.15309222,0.0026303078,0.00054235966,0.000048930226,2.8399197e-7,0.000015506233,0.00016847183],"genre_scores_gemma":[0.9982884,0.00032578115,0.00090936077,0.00022248439,0.00008133385,0.0000012103259,1.6042858e-7,0.0000035901683,0.00016768245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906164,0.0001819413,0.00015970146,0.000110492336,0.00032067267,0.00016556436],"domain_scores_gemma":[0.9994066,0.00013451558,0.00013581198,0.00021931178,0.000054687538,0.00004909587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008501027,0.000053615666,0.00010708271,0.000066403896,0.0000736285,0.000037655424,0.0004009806,0.000076100885,0.00006770096],"category_scores_gemma":[0.00006995652,0.000036346355,0.000033058415,0.000103357735,0.000097178,0.0002437435,0.000100079866,0.0003622888,0.000014876266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027667888,0.00013977912,0.057704046,0.000053750227,0.00025496958,0.00017264212,0.0054714866,0.0010719625,0.22093216,0.18166316,0.0055499235,0.52670944],"study_design_scores_gemma":[0.006645577,0.0055275555,0.15100448,0.0002997038,0.00020623987,0.07085071,0.00034929364,0.4201431,0.19527304,0.085779615,0.062832944,0.0010877353],"about_ca_topic_score_codex":0.000017078066,"about_ca_topic_score_gemma":0.0000147578385,"teacher_disagreement_score":0.5256217,"about_ca_system_score_codex":0.00009304008,"about_ca_system_score_gemma":0.00019353302,"threshold_uncertainty_score":0.15739848},"labels":[],"label_agreement":null},{"id":"W317587060","doi":"10.1007/0-306-47015-2_46","title":"High-Performance Computing for Computer-Aided Diagnosis of Breast Cancer","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Contrast (vision); Computer science; Mammography; Artificial intelligence; Identification (biology); Contrast enhancement; Image quality; Pattern recognition (psychology); Image processing; Computer-aided diagnosis; Computer vision; Image (mathematics); Cancer; Medicine; Radiology; Internal medicine; Magnetic resonance imaging","score_opus":0.020552573305157366,"score_gpt":0.24843128783577342,"score_spread":0.22787871453061606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W317587060","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011143952,0.004200523,0.6173668,0.008997917,0.03131765,0.007916974,0.0011811696,0.0035972463,0.3142778],"genre_scores_gemma":[0.3425592,0.0014611314,0.18225428,0.009542592,0.028153561,0.0019066763,0.00019875684,0.001263,0.43266082],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99536675,0.000041257907,0.0013768243,0.0014084989,0.0009451466,0.000861524],"domain_scores_gemma":[0.9960632,0.00039668163,0.0015042014,0.0011288258,0.00063415203,0.00027299073],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00078136945,0.000816502,0.0010917071,0.0006455793,0.00025080395,0.00035184008,0.0031497283,0.0013516744,0.000088234585],"category_scores_gemma":[0.000019568184,0.0008639398,0.00036825074,0.00012381496,0.00030080453,0.0017704605,0.0009236784,0.0018494383,0.000017954302],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006018992,0.000018465384,0.00046495703,0.00042608692,0.0003449615,0.0000029337634,0.00046963373,0.0020817237,0.000056815923,0.027102621,0.095207796,0.8737638],"study_design_scores_gemma":[0.0047874516,0.00074398314,0.003262377,0.005283389,0.00053326733,0.00023590724,0.000017585731,0.12308373,0.0057071857,0.019428225,0.83237416,0.0045427587],"about_ca_topic_score_codex":0.000116762625,"about_ca_topic_score_gemma":0.000014839404,"teacher_disagreement_score":0.86922103,"about_ca_system_score_codex":0.00087203045,"about_ca_system_score_gemma":0.00056204305,"threshold_uncertainty_score":0.9999448},"labels":[],"label_agreement":null},{"id":"W3177773712","doi":"10.48550/arxiv.2107.02345","title":"Domain Adaptation via CycleGAN for Retina Segmentation in Optical Coherence Tomography","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Optical coherence tomography; Artificial intelligence; Segmentation; Domain adaptation; Adaptation (eye); Medical diagnosis; Domain (mathematical analysis); Machine learning; Set (abstract data type); Pipeline (software); Generalizability theory; Data set; Medicine","score_opus":0.05144249903892197,"score_gpt":0.19949770303519843,"score_spread":0.14805520399627645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177773712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31891045,0.000022831848,0.6796864,0.00006894909,0.00050058874,0.00044551553,0.000003910228,0.00009807556,0.00026325736],"genre_scores_gemma":[0.9243179,0.000035997095,0.075422466,0.00004849145,0.000053964697,0.000014249113,0.000033571287,0.000013826923,0.00005954906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981416,0.00014733203,0.00023793516,0.0010689241,0.00011905321,0.00028516277],"domain_scores_gemma":[0.9987475,0.00013481954,0.00022694685,0.00065143773,0.00014729078,0.000091962036],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031221684,0.00022769994,0.00024044991,0.0003382387,0.000103229024,0.0001500049,0.00075537304,0.00026563392,0.000008433107],"category_scores_gemma":[0.000014820362,0.00030559118,0.00016863308,0.00093649625,0.000075217846,0.00057071453,0.0005127079,0.00038271004,0.000004654853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032626704,0.000375387,0.015272749,0.00050287833,0.0001813096,0.00043160035,0.0045799343,0.8494902,0.0050587915,0.100939155,0.000096597425,0.0227451],"study_design_scores_gemma":[0.0012014864,0.00019699833,0.01111598,0.0002304555,0.00005153693,0.000008551031,0.0010459338,0.91098094,0.004360981,0.0700432,0.00010433931,0.0006596012],"about_ca_topic_score_codex":0.00017412132,"about_ca_topic_score_gemma":0.000409019,"teacher_disagreement_score":0.6054074,"about_ca_system_score_codex":0.00048077395,"about_ca_system_score_gemma":0.00019246679,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null},{"id":"W3183458014","doi":"10.1016/j.compbiomed.2021.104699","title":"Sharp U-Net: Depthwise convolutional network for biomedical image segmentation","year":2021,"lang":"en","type":"preprint","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Encoder; Convolutional neural network; Pattern recognition (psychology); Sharpening; Feature (linguistics); Network architecture; Image segmentation; Computer vision","score_opus":0.023522919402699648,"score_gpt":0.3336563153983283,"score_spread":0.31013339599562867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183458014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055511254,0.003985221,0.9760009,0.005275089,0.008542139,0.00048238705,0.000012654426,0.00008266218,0.00006783396],"genre_scores_gemma":[0.16264072,0.0015960931,0.82637167,0.003684694,0.004050965,0.00035487278,0.001245159,0.000023157072,0.00003265644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981467,0.00016129721,0.00043075494,0.00080207747,0.00012766948,0.00033148832],"domain_scores_gemma":[0.99879164,0.00045145434,0.0001930021,0.00034419767,0.00010547641,0.00011422112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006591375,0.00022961895,0.00045156665,0.000184898,0.000104372244,0.000030853622,0.00048344056,0.0004060982,0.000014611269],"category_scores_gemma":[0.000076222146,0.00020742195,0.00005628305,0.00022571786,0.0005014286,0.00009084242,0.00078881666,0.0004426688,0.0000011225985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036445216,0.00036891882,0.013960312,0.0015394012,0.00066271273,0.0001913634,0.005438297,0.002301705,0.008138364,0.0722365,0.12093786,0.7738601],"study_design_scores_gemma":[0.008613349,0.0018134799,0.03176067,0.002687358,0.0001232209,0.00029732857,0.00019638336,0.72054166,0.0004029039,0.21126896,0.021051921,0.0012427667],"about_ca_topic_score_codex":0.000061024315,"about_ca_topic_score_gemma":0.000034608216,"teacher_disagreement_score":0.77261734,"about_ca_system_score_codex":0.00016130025,"about_ca_system_score_gemma":0.00018586102,"threshold_uncertainty_score":0.8458422},"labels":[],"label_agreement":null},{"id":"W3183988414","doi":"10.1080/10408363.2021.1943302","title":"Disruptive innovations in the clinical laboratory: catching the wave of precision diagnostics","year":2021,"lang":"en","type":"review","venue":"Critical Reviews in Clinical Laboratory Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Disruptive technology; Disruptive innovation; Point-of-care testing; Medical laboratory; Scope (computer science); Service (business); Emerging technologies; Health care; Computer science; Medicine; Risk analysis (engineering); Engineering; Business; Marketing; Pathology; Artificial intelligence; Manufacturing engineering; Economics","score_opus":0.3469002162019703,"score_gpt":0.548654556726918,"score_spread":0.20175434052494767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183988414","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047502323,0.9869924,0.005363035,0.0021146238,0.003507803,0.0016234299,0.000083576895,0.000028631028,0.000238956],"genre_scores_gemma":[0.00023684843,0.98807216,0.008894438,0.0018276022,0.000561461,0.00037633927,0.000005914197,0.000020689115,0.0000045490588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9746167,0.015151438,0.006520951,0.0017051938,0.0013242175,0.00068149634],"domain_scores_gemma":[0.8674517,0.12524039,0.0022042678,0.0034832698,0.0013453718,0.0002749932],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055546228,0.0005541176,0.003279348,0.00030529496,0.00039291944,0.0004425459,0.0048319767,0.00067683065,0.000022417],"category_scores_gemma":[0.14538072,0.00029462058,0.0007442627,0.0125623485,0.00364185,0.0007862361,0.0010452026,0.0034544123,0.0000431656],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001426712,0.00035705225,0.0005072912,0.0012040584,0.000013031441,0.00004222704,0.00019422514,0.000001609168,3.8965617e-8,0.07466436,0.0021748769,0.9208398],"study_design_scores_gemma":[0.00011465573,0.0002733048,0.00049595564,0.016392332,0.00012002894,0.000007551894,0.00014650985,0.00020102749,4.2181418e-7,0.0033561946,0.97852445,0.00036755714],"about_ca_topic_score_codex":0.000011697436,"about_ca_topic_score_gemma":0.00010645619,"teacher_disagreement_score":0.9763496,"about_ca_system_score_codex":0.00017492569,"about_ca_system_score_gemma":0.0040178173,"threshold_uncertainty_score":0.9999506},"labels":[],"label_agreement":null},{"id":"W3184319394","doi":"10.18280/ts.380312","title":"Efficient Multi-Organ Multi-Center Cell Nuclei Segmentation Method Based on Deep Learnable Aggregation Network","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Jaccard index; Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology); Software; Image segmentation","score_opus":0.02026579987946393,"score_gpt":0.26308410703799673,"score_spread":0.2428183071585328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184319394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013640141,0.00006679035,0.9842343,0.0003916157,0.0007495917,0.0004232724,0.000004315894,0.00020579365,0.0002841993],"genre_scores_gemma":[0.5001787,0.00000463939,0.49832484,0.0010385046,0.00018304054,0.00005722819,0.000026297253,0.00002596196,0.00016080083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748725,0.00039374657,0.00039045,0.000691415,0.00059905567,0.00043806667],"domain_scores_gemma":[0.998951,0.00013255583,0.00021563892,0.00040548886,0.00017147766,0.0001238282],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006413015,0.00024068292,0.0001882544,0.000111462636,0.00030849603,0.00021886766,0.00034505615,0.0000854966,0.00030495966],"category_scores_gemma":[0.000015034871,0.0002519075,0.000118073745,0.0006012164,0.000023294408,0.00018825867,0.00009878196,0.00020941472,0.00011169936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004002535,0.0009976655,0.00052020326,0.000035255987,0.000021030211,0.000021544667,0.0006055747,0.93199295,0.01517491,0.00013718756,0.00034061336,0.050113045],"study_design_scores_gemma":[0.0034009414,0.00018344152,0.0012775994,0.000051027117,0.000017777285,0.000004827206,0.000068443725,0.9067514,0.08701729,0.0000240709,0.00096559717,0.00023759271],"about_ca_topic_score_codex":0.000020202253,"about_ca_topic_score_gemma":0.000030139656,"teacher_disagreement_score":0.48653853,"about_ca_system_score_codex":0.00040350112,"about_ca_system_score_gemma":0.00010306368,"threshold_uncertainty_score":0.9999933},"labels":[],"label_agreement":null},{"id":"W3185576150","doi":"10.1109/embc46164.2021.9630818","title":"A Similarity Measure of Histopathology Images by Deep Embeddings","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Similarity (geometry); Pattern recognition (psychology); Pixel; Measure (data warehouse); Computer science; Similarity measure; Magnification; Pooling; Feature extraction; Embedding; Computer vision; Image (mathematics); Mathematics; Data mining","score_opus":0.025934904238595034,"score_gpt":0.2864590160768847,"score_spread":0.26052411183828966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185576150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119383484,0.001327264,0.86137354,0.011268531,0.0054029264,0.00018374616,0.00009400049,0.000072035466,0.0008944501],"genre_scores_gemma":[0.97745883,0.0005264883,0.020786764,0.0003713798,0.00023313411,0.00002103414,0.000029023446,0.000014077948,0.00055926683],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998377,0.00012522032,0.00050627434,0.00043025828,0.0003118127,0.00024942623],"domain_scores_gemma":[0.9981966,0.00023837668,0.00026331976,0.00046725522,0.00078388065,0.00005055166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006632696,0.00020104853,0.0004147129,0.00010748431,0.00004148351,0.000011995682,0.0011885049,0.00022533484,0.00012012142],"category_scores_gemma":[0.00063282414,0.00016797485,0.00016996308,0.00055041484,0.00035615245,0.00018408505,0.000307312,0.0005229853,0.0000024745714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031939806,0.00018161126,0.0076290146,0.00014210073,0.00025521833,0.000007054769,0.0077514155,0.00521332,0.9263357,0.0074804453,0.040846452,0.0041257157],"study_design_scores_gemma":[0.009098165,0.0012798599,0.042641874,0.0030881066,0.00029528214,0.0006720668,0.004048611,0.41609767,0.34048235,0.017181994,0.1622412,0.0028727925],"about_ca_topic_score_codex":0.0001667582,"about_ca_topic_score_gemma":0.00007965644,"teacher_disagreement_score":0.8580753,"about_ca_system_score_codex":0.0001552012,"about_ca_system_score_gemma":0.00014146196,"threshold_uncertainty_score":0.6849816},"labels":[],"label_agreement":null},{"id":"W3188083976","doi":"10.1117/12.2593939","title":"Fast filters for preprocessing and mass segmentation in mammography images","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Preprocessor; Mammography; Artificial intelligence; Computer science; Segmentation; Digital mammography; Wiener filter; Pattern recognition (psychology); Computer vision; Median filter; Gaussian filter; Noise (video); Gaussian; Filter (signal processing); Gaussian noise; Breast cancer; Image processing; Image (mathematics); Cancer; Medicine","score_opus":0.01148776139177863,"score_gpt":0.2596198107493863,"score_spread":0.24813204935760766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188083976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022973754,0.00014455299,0.97538084,0.0005599905,0.00012429552,0.00008948312,9.2865963e-7,0.000049330178,0.00067680643],"genre_scores_gemma":[0.43942702,0.000027580722,0.5599476,0.00024393336,0.00002383644,0.00005346964,0.0000018995657,0.0000046589034,0.00027000412],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99951583,0.000014084443,0.000080875245,0.00023455541,0.000066005996,0.00008864125],"domain_scores_gemma":[0.99977416,0.00003512328,0.000025741318,0.0001103876,0.000036821122,0.000017743258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008782036,0.00004272478,0.000045351302,0.000063936204,0.00004091834,0.00013555014,0.00007166157,0.000017427408,0.000004662403],"category_scores_gemma":[0.000008809763,0.000043619504,0.000015387239,0.00026108781,0.00001305274,0.00045983223,0.0000371237,0.000026742464,5.534228e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016382804,0.0000343461,0.02907668,0.0001947456,0.00001649142,0.0000091240745,0.0019919842,0.0006660857,0.18627788,0.0007441808,0.00082871254,0.7801434],"study_design_scores_gemma":[0.00083403534,0.000071173476,0.016158849,0.00005395436,0.000005369978,0.000018190412,0.0009757969,0.10829085,0.86190236,0.011032653,0.00043894467,0.0002178035],"about_ca_topic_score_codex":0.0000072886983,"about_ca_topic_score_gemma":0.000028463106,"teacher_disagreement_score":0.7799256,"about_ca_system_score_codex":0.000023977133,"about_ca_system_score_gemma":0.000022126173,"threshold_uncertainty_score":0.17787518},"labels":[],"label_agreement":null},{"id":"W3188212740","doi":"10.3389/fgene.2021.661109","title":"Prediction of BRCA Gene Mutation in Breast Cancer Based on Deep Learning and Histopathology Images","year":2021,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"AI in cancer detection","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; University of Toronto; Government of Jiangsu Province","keywords":"Breast cancer; Mutation; Cancer; BRCA mutation; Magnification; Convolutional neural network; Deep learning; Oncology; Medicine; Artificial intelligence; Gene; Computer science; Internal medicine; Biology; Genetics","score_opus":0.006865642418595037,"score_gpt":0.21809952307615413,"score_spread":0.2112338806575591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188212740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1869973,0.0025789568,0.80866313,0.00035968248,0.0011774021,0.00008391013,0.000009038322,0.000024511346,0.00010608082],"genre_scores_gemma":[0.8771866,0.00082193856,0.12182105,0.00007070525,0.000039274895,0.000019243034,0.000004509208,0.000008377417,0.000028276245],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991517,0.00012793942,0.00018422806,0.00027559808,0.00013309867,0.00012741519],"domain_scores_gemma":[0.9996582,0.000021915619,0.000081705104,0.00014952217,0.00006506223,0.000023590268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001452788,0.00007358879,0.0001229524,0.00019250675,0.000028260474,0.000014577804,0.00009615029,0.00007283774,0.000004314648],"category_scores_gemma":[0.00001975444,0.00008923583,0.0000156558,0.00033794684,0.000048191894,0.0000701532,0.00004247628,0.00014165894,2.420792e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029922625,0.00004629004,0.57466674,0.000037665588,0.0000034831412,0.000044822656,0.0006247545,0.1448771,0.012252672,0.000012310167,0.00017794922,0.2672263],"study_design_scores_gemma":[0.00045763812,0.00007399498,0.40982506,0.000030107389,0.0000048087213,0.000022474216,0.000061714745,0.5710141,0.017955273,0.00030073483,0.00018501875,0.00006908253],"about_ca_topic_score_codex":0.00002741682,"about_ca_topic_score_gemma":0.00004190443,"teacher_disagreement_score":0.69018936,"about_ca_system_score_codex":0.0002295031,"about_ca_system_score_gemma":0.0000821248,"threshold_uncertainty_score":0.36389315},"labels":[],"label_agreement":null},{"id":"W3188542522","doi":"10.3389/froh.2021.703874","title":"Visual Analytics: A Method to Explore Natural Histories of Oral Epithelial Dysplasia","year":2021,"lang":"en","type":"article","venue":"Frontiers in Oral Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Visual analytics; Analytics; Computer science; Data science; Perspective (graphical); Exploratory research; Formative assessment; Visualization; Psychology; Artificial intelligence","score_opus":0.04290555220695904,"score_gpt":0.36339047355815957,"score_spread":0.32048492135120055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188542522","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008851258,0.0009627254,0.9791009,0.0046423743,0.0060958513,0.00019877288,0.0000065703703,0.000079200014,0.000062338426],"genre_scores_gemma":[0.212226,0.000031565338,0.7863787,0.0009599171,0.000082576895,0.000017038945,0.000004351704,0.000014473019,0.0002853718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977916,0.00036382428,0.0004749926,0.00051624444,0.00040466423,0.00044869047],"domain_scores_gemma":[0.99903977,0.000045050696,0.00017338258,0.0004108593,0.00015191163,0.000179046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072246656,0.00016737581,0.0004962919,0.00030383817,0.00009074784,0.0000420052,0.0004606563,0.00007791486,0.0000074191103],"category_scores_gemma":[0.00008243997,0.00017503714,0.00008130811,0.0013121992,0.00004878404,0.00037580117,0.00021177658,0.00028909577,0.0000038711464],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002528681,0.0001933937,0.0103795985,0.00023668264,0.00006799387,0.00006968675,0.011411211,0.0012776005,0.0005371589,0.0035338379,0.07193759,0.9001024],"study_design_scores_gemma":[0.005205085,0.0046141096,0.028927324,0.0004895573,0.00006138011,0.00017681139,0.009209587,0.5204767,0.05885753,0.025821274,0.34398544,0.00217517],"about_ca_topic_score_codex":0.00048019117,"about_ca_topic_score_gemma":0.00054300454,"teacher_disagreement_score":0.8979272,"about_ca_system_score_codex":0.0012796303,"about_ca_system_score_gemma":0.0008394743,"threshold_uncertainty_score":0.71378076},"labels":[],"label_agreement":null},{"id":"W3189794101","doi":"10.1007/978-3-030-87722-4_10","title":"Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Generalizability theory; Pooling; Cohort; Artificial intelligence; Normalization (sociology); Computer science; Machine learning; Segmentation; Statistics; Mathematics","score_opus":0.055550809972475176,"score_gpt":0.3125225474226076,"score_spread":0.2569717374501324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189794101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057723247,0.00025045508,0.93607837,0.0006247017,0.0038939253,0.0012591347,0.000026900518,0.00014059643,0.0000026734774],"genre_scores_gemma":[0.5202173,0.000055616085,0.47896853,0.00033424393,0.00013312753,0.00009228917,0.00018634358,0.000012283589,2.654061e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99565524,0.00021192491,0.00065135886,0.0020210487,0.000888264,0.0005721383],"domain_scores_gemma":[0.9972639,0.00052732293,0.00043002635,0.001382153,0.00029833155,0.00009827249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018919825,0.00038033663,0.0004214589,0.0009032589,0.00019217274,0.0009940473,0.002158131,0.00030361992,0.00000296164],"category_scores_gemma":[0.00036540997,0.00040013425,0.00008951361,0.0025243592,0.00018167408,0.0012022605,0.0019564105,0.0006820964,0.0000029701212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008459454,0.000039111408,0.0010475173,0.000063171894,0.0000045303773,0.000014301706,0.0010660643,0.52641994,0.00088729203,0.000017384333,0.00000998032,0.47042224],"study_design_scores_gemma":[0.00043066454,0.0000911766,0.00530107,0.00046713682,0.0000066570497,0.000017620967,0.0000031824995,0.9549582,0.03207142,0.006231496,0.000020359144,0.00040100556],"about_ca_topic_score_codex":0.0005779295,"about_ca_topic_score_gemma":0.001288679,"teacher_disagreement_score":0.47002125,"about_ca_system_score_codex":0.0011018339,"about_ca_system_score_gemma":0.001100669,"threshold_uncertainty_score":0.999845},"labels":[],"label_agreement":null},{"id":"W3189996993","doi":"10.1002/path.5773","title":"Weakly supervised learning on unannotated H&amp;E‐stained slides predicts <scp><i>BRAF</i></scp> mutation in thyroid cancer with high accuracy","year":2021,"lang":"en","type":"article","venue":"The Journal of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Nvidia","keywords":"Malignancy; Cancer; Computational biology; Artificial intelligence; Mutation; Biology; Pathology; Oncology; Computer science; Medicine; Bioinformatics; Internal medicine; Gene; Genetics","score_opus":0.015523136684348647,"score_gpt":0.2590707925333516,"score_spread":0.24354765584900293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189996993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9418987,0.00059023284,0.05431894,0.0023159063,0.00056489656,0.00011479229,0.0000019397478,0.00004701372,0.00014760216],"genre_scores_gemma":[0.99435204,0.00043000156,0.0042340187,0.0005641162,0.00018015044,0.000009763768,0.0000025557324,0.000020060563,0.0002073081],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997573,0.0009822425,0.00046212383,0.0002407463,0.00040686727,0.0003349954],"domain_scores_gemma":[0.9974768,0.0010894572,0.0005733595,0.00032903178,0.00045926156,0.00007207505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010886624,0.00017287508,0.00029776915,0.00023327883,0.00015201824,0.00007046427,0.0005606257,0.00009907645,0.000012821463],"category_scores_gemma":[0.0007883054,0.000118423646,0.000052288124,0.00085109106,0.00008658417,0.0004954061,0.00010916373,0.0007765451,0.000010409518],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060292415,0.00034894323,0.007979348,0.00008064035,0.00020268386,0.0056886594,0.03781499,0.515638,0.37906438,0.0013327191,0.0015934621,0.04965328],"study_design_scores_gemma":[0.019755665,0.014634614,0.32352304,0.0017835385,0.0004457042,0.03292738,0.009923108,0.052856106,0.5119335,0.0212641,0.009995285,0.00095791894],"about_ca_topic_score_codex":0.000068860696,"about_ca_topic_score_gemma":0.00028866343,"teacher_disagreement_score":0.46278185,"about_ca_system_score_codex":0.0002142533,"about_ca_system_score_gemma":0.00043821678,"threshold_uncertainty_score":0.4829176},"labels":[],"label_agreement":null},{"id":"W3192443502","doi":"10.1017/cjn.2021.171","title":"Cortical Dysplasia Teaching Pathology to a Machine","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Cortical dysplasia; Dimensionality reduction; Segmentation; Computer science; Feature (linguistics); Artificial intelligence; Cluster analysis; Dysplasia; Pattern recognition (psychology); Pathology; Medicine; Radiology; Magnetic resonance imaging","score_opus":0.026951291043510232,"score_gpt":0.27274044964212363,"score_spread":0.2457891585986134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192443502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610935,0.0008976488,0.013792242,0.01786971,0.0026216032,0.00011747132,0.000006202027,0.00004681655,0.0035548252],"genre_scores_gemma":[0.9497552,0.00010538186,0.03947921,0.010274981,0.00032955466,0.0000031874254,1.3900359e-7,0.000011324708,0.000041030413],"study_design_codex":"observational","study_design_gemma":"case_report","domain_scores_codex":[0.99307925,0.0022761577,0.0010296913,0.0009031452,0.0010106672,0.001701112],"domain_scores_gemma":[0.99468535,0.0008905823,0.00059313094,0.0003398761,0.0006472845,0.0028437453],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.006335084,0.0003626757,0.0005687713,0.0010760516,0.003989309,0.0015266032,0.004121149,0.00021991842,0.000125831],"category_scores_gemma":[0.0055946964,0.00027014816,0.00026056656,0.0021886397,0.0029644382,0.0016465579,0.0003025524,0.002304172,0.000014504303],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015730345,0.00018639122,0.69961196,0.000022070475,0.0000532291,0.13202235,0.0033203557,0.018626885,0.0025009613,0.061393376,0.005859581,0.07624554],"study_design_scores_gemma":[0.0010169835,0.14836274,0.16221203,0.00013704889,0.00008525722,0.52482104,0.0005321485,0.021138987,0.002980751,0.097510695,0.039610345,0.0015919956],"about_ca_topic_score_codex":0.0004735429,"about_ca_topic_score_gemma":0.046273433,"teacher_disagreement_score":0.53739995,"about_ca_system_score_codex":0.00040330543,"about_ca_system_score_gemma":0.0053241216,"threshold_uncertainty_score":0.99999756},"labels":[],"label_agreement":null},{"id":"W3193216832","doi":"10.1007/978-3-030-87592-3_5","title":"Synth-by-Reg (SbR): Contrastive Learning for Synthesis-Based Registration of Paired Images","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Institute of Mental Health; National Institute on Aging","keywords":"Overfitting; Artificial intelligence; Computer science; Image registration; Translation (biology); Reduction (mathematics); Complement (music); Pattern recognition (psychology); Modality (human–computer interaction); Computer vision; Natural language processing; Image (mathematics); Artificial neural network; Mathematics","score_opus":0.015152389055290798,"score_gpt":0.2593618590153644,"score_spread":0.24420946996007362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193216832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063015083,0.0005399754,0.9886278,0.0015333504,0.0020151779,0.00075353106,0.000014719472,0.00020013517,0.000013793911],"genre_scores_gemma":[0.6536185,0.00001368086,0.34591568,0.00016291461,0.00013109217,0.00013248256,0.0000080683285,0.00001625724,0.0000012992488],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99553823,0.0003430291,0.0007142213,0.0018545263,0.00093840674,0.00061157387],"domain_scores_gemma":[0.993905,0.0032093972,0.0008205717,0.0011993895,0.0007522706,0.00011333664],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002266915,0.00044878782,0.0006730263,0.00046098605,0.00028108744,0.0007336567,0.002431647,0.00034407314,0.0000043145924],"category_scores_gemma":[0.0023334802,0.00046213844,0.00021958169,0.0013128233,0.00063763786,0.0005783132,0.0009636924,0.00082510797,7.8837235e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027385915,0.00007793499,0.00029315334,0.00025907037,0.000019170908,0.000009175722,0.0005107163,0.54919654,0.016161378,0.000043084085,0.00003898762,0.4333634],"study_design_scores_gemma":[0.00018567973,0.00013272229,0.00039429622,0.00058369176,0.000012387216,0.000006085965,0.0000018741055,0.6495067,0.34699023,0.001850169,0.00002080616,0.00031537868],"about_ca_topic_score_codex":0.00019252664,"about_ca_topic_score_gemma":0.000084420775,"teacher_disagreement_score":0.647317,"about_ca_system_score_codex":0.0005246678,"about_ca_system_score_gemma":0.0015525259,"threshold_uncertainty_score":0.99978304},"labels":[],"label_agreement":null},{"id":"W3193532867","doi":"10.1016/j.compmedimag.2021.101974","title":"An unsupervised method for histological image segmentation based on tissue cluster level graph cut","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Jaccard index; Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Voronoi diagram; Cut; Cluster analysis; Image segmentation; Adjacency list; Graph partition; Graph; Computer vision; Mathematics","score_opus":0.03159187053559112,"score_gpt":0.33819063203238725,"score_spread":0.3065987614967961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193532867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015850094,0.00016078143,0.9852048,0.01137837,0.001081964,0.0002579302,0.000011836133,0.0002720598,0.000047261863],"genre_scores_gemma":[0.042289555,0.00006687134,0.94212615,0.015097219,0.00023579119,0.00007766536,0.00006606937,0.00002376141,0.000016889433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974975,0.00043463966,0.0003431952,0.0008111197,0.00056534156,0.0003482041],"domain_scores_gemma":[0.99813205,0.0006532734,0.000097625336,0.0005346847,0.00022700614,0.00035537308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089441915,0.00023303425,0.0003164871,0.00020558975,0.00028028197,0.00025499146,0.0004965821,0.00014241524,0.000020741683],"category_scores_gemma":[0.00016865216,0.00021480588,0.00010861377,0.000495353,0.00018569757,0.0003572134,0.00014374303,0.00031923642,0.0000019097852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013671095,0.0003979317,0.00021744832,0.00017742834,0.000041964766,0.00017992819,0.00043844152,0.00017042333,0.020357028,0.007278151,0.0041376203,0.9664669],"study_design_scores_gemma":[0.0025265093,0.00021018255,0.00060771214,0.00007408397,0.000023572296,0.00011626023,0.000019999728,0.978437,0.0068151946,0.006715902,0.0041776067,0.0002759714],"about_ca_topic_score_codex":0.000017925177,"about_ca_topic_score_gemma":0.000008758407,"teacher_disagreement_score":0.9782666,"about_ca_system_score_codex":0.000047540634,"about_ca_system_score_gemma":0.00018353066,"threshold_uncertainty_score":0.87595296},"labels":[],"label_agreement":null},{"id":"W3193837241","doi":"10.3390/jimaging7080154","title":"Design of an Ultrasound-Navigated Prostate Cancer Biopsy System for Nationwide Implementation in Senegal","year":2021,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of British Columbia; Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; National Cancer Institute; Canarie","keywords":"Prostate cancer; Medicine; Medical physics; Prostate biopsy; Biopsy; Prostate; Psychological intervention; Cancer; Computer science; Radiology; Nursing; Internal medicine","score_opus":0.015557312312328334,"score_gpt":0.3189761754709657,"score_spread":0.30341886315863736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193837241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23446289,0.00024466251,0.7641264,0.00040299658,0.0005877384,0.00014944782,0.0000049547098,0.000014366883,0.0000065205872],"genre_scores_gemma":[0.89786094,0.00002017131,0.10197894,0.000035124736,0.000079460304,0.000012280852,0.0000015623656,0.000007637506,0.0000039057068],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988668,0.00012036259,0.000493079,0.00013321299,0.00024697438,0.00013954793],"domain_scores_gemma":[0.998546,0.000113914706,0.0005339251,0.00011424143,0.0006532557,0.000038676342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007561515,0.00006919815,0.00014640584,0.00016825632,0.00004864226,0.00009631862,0.00018733779,0.000015589536,0.0000030253464],"category_scores_gemma":[0.00003828752,0.0000680102,0.00004105467,0.00042764493,0.000012700193,0.0011132322,0.000019515286,0.00008983916,1.7573433e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009419461,0.00005918426,0.025255708,0.00018037832,0.00005490182,0.00008262923,0.003082572,0.039384454,0.83787256,0.00028527612,0.00010072428,0.093547426],"study_design_scores_gemma":[0.002193153,0.00012974358,0.013610019,0.00044759753,0.00002976976,0.0012221835,0.002571534,0.1867079,0.7920602,0.0007779761,0.00007554582,0.00017436847],"about_ca_topic_score_codex":0.0001002422,"about_ca_topic_score_gemma":0.000034432738,"teacher_disagreement_score":0.663398,"about_ca_system_score_codex":0.00034027387,"about_ca_system_score_gemma":0.00042302278,"threshold_uncertainty_score":0.27733758},"labels":[],"label_agreement":null},{"id":"W3194353469","doi":"10.1038/s41597-022-01389-0","title":"Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Annotation; Computer science; Pipeline (software); Artificial intelligence; Cytology; Hemosiderin; Pathology; Medicine","score_opus":0.053244949372914664,"score_gpt":0.2823903223557649,"score_spread":0.22914537298285023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194353469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70844316,0.0030786917,0.18668878,0.006669588,0.040855113,0.003284295,0.036958624,0.0016212243,0.0124005275],"genre_scores_gemma":[0.99446476,0.000008903713,0.0012546098,0.00012081279,0.000106790925,0.000025249828,0.0020316849,0.000012514732,0.0019746996],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974256,0.00014486689,0.0002808035,0.0013152629,0.0005322017,0.00030123157],"domain_scores_gemma":[0.9970292,0.00005877118,0.000117464464,0.0027030369,0.000021930964,0.000069621216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013623106,0.00014759979,0.00013271083,0.000402799,0.000797966,0.00053238403,0.002378546,0.000025833764,0.00017750802],"category_scores_gemma":[0.000031807995,0.00015738214,0.000017555674,0.0009858831,0.000160427,0.0010774321,0.005451539,0.00031850836,0.000037334692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007210075,0.00076897757,0.00040117142,0.00008375135,0.0000158288,0.00031426697,0.0008174731,0.0006213453,0.57039607,0.00087679864,0.2686821,0.15695012],"study_design_scores_gemma":[0.0011007442,0.0008238401,0.007872279,0.000054287644,0.000017000793,0.00017649993,0.000703547,0.13393003,0.11331375,0.0029842302,0.73818606,0.0008377355],"about_ca_topic_score_codex":0.000086609434,"about_ca_topic_score_gemma":0.00034284368,"teacher_disagreement_score":0.46950394,"about_ca_system_score_codex":0.00019183467,"about_ca_system_score_gemma":0.000040736988,"threshold_uncertainty_score":0.67949533},"labels":[],"label_agreement":null},{"id":"W3195661002","doi":"10.22215/etd/2019-13731","title":"On Forecasting Lung Cancer Patients’ Survival Rates Using 3D Feature Engineering","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); Feature (linguistics); Computer science; Dimensionality reduction; Artificial intelligence; Data set; Pattern recognition (psychology); Curse of dimensionality; Data mining; Feature selection; Regression; Feature engineering; Statistics; Mathematics; Deep learning","score_opus":0.01680788696498753,"score_gpt":0.26940386230928703,"score_spread":0.2525959753442995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195661002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6734692,0.00079938036,0.27156958,0.00006224166,0.04293689,0.0013449898,0.000025364569,0.000765654,0.009026742],"genre_scores_gemma":[0.9323424,0.00007106671,0.048753403,0.00020622811,0.0011967245,0.00015402352,0.00035127145,0.0002694692,0.0166554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.000026421672,0.00022801092,0.000616459,0.00047578858,0.00035494135],"domain_scores_gemma":[0.9989499,0.00013865036,0.00025050252,0.0003767746,0.00022686877,0.000057308152],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011709721,0.0003514034,0.0002945426,0.00023600152,0.00012147332,0.00020968137,0.0005052692,0.000305356,0.00003775089],"category_scores_gemma":[0.000056435074,0.0003387411,0.000095192205,0.00041138756,0.0000039515767,0.00041170852,0.00006458911,0.0004944735,0.000009164763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003689039,0.00028947214,0.022940334,0.0053001526,0.0009933223,0.000030403256,0.0076523907,0.69453216,0.0062649795,0.0091373855,0.009277428,0.24321307],"study_design_scores_gemma":[0.00025270315,0.000063069485,0.0021181405,0.0006064062,0.000027869859,8.580428e-7,0.000028479453,0.9925955,0.0036052389,0.000019976975,0.00021360017,0.0004681484],"about_ca_topic_score_codex":0.00025625952,"about_ca_topic_score_gemma":0.00015135366,"teacher_disagreement_score":0.29806334,"about_ca_system_score_codex":0.00056309946,"about_ca_system_score_gemma":0.00017258938,"threshold_uncertainty_score":0.9999065},"labels":[],"label_agreement":null},{"id":"W3196024289","doi":"10.1093/biostatistics/kxab032","title":"Predicting the onset of breast cancer using mammogram imaging data with irregular boundary","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Computer science; Artificial intelligence; Mammography; Pattern recognition (psychology); Benchmark (surveying); Breast cancer screening; Boundary (topology); Machine learning; Medicine; Cancer; Mathematics","score_opus":0.02508658907445413,"score_gpt":0.2886221632118421,"score_spread":0.26353557413738793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196024289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01358042,0.00077074027,0.9825446,0.001035996,0.00060906424,0.00009860457,0.0012553745,0.00006187687,0.000043329328],"genre_scores_gemma":[0.6590741,0.00006463503,0.34036687,0.00023544591,0.00016315767,0.000005001659,0.000045754085,0.000020736175,0.00002427871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885726,0.0000744207,0.00019036484,0.00034828074,0.00032930315,0.00020038696],"domain_scores_gemma":[0.99835736,0.00013141555,0.00016675114,0.0010796146,0.0002235714,0.00004127465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022019842,0.000104076695,0.00011333945,0.000032526834,0.0002174131,0.00017907062,0.00071202166,0.000021670106,0.0000131296465],"category_scores_gemma":[0.000046867455,0.00007951217,0.000014178997,0.00045540684,0.00017832279,0.00030303624,0.00053725817,0.0001231888,8.6602597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007553364,0.00015752648,0.2306684,0.00036431092,0.00031006554,0.0005152583,0.0019505817,0.002785411,0.005217794,0.0045512673,0.008768682,0.74463516],"study_design_scores_gemma":[0.00033201033,0.000030089557,0.0489377,0.00025529112,0.000102180784,0.0013754449,0.00034184198,0.9400447,0.0025038568,0.00079958234,0.0050229058,0.00025441076],"about_ca_topic_score_codex":0.0006501518,"about_ca_topic_score_gemma":0.00030089886,"teacher_disagreement_score":0.93725926,"about_ca_system_score_codex":0.00008553967,"about_ca_system_score_gemma":0.0006232313,"threshold_uncertainty_score":0.32424122},"labels":[],"label_agreement":null},{"id":"W3196522557","doi":"10.1609/aaai.v36i11.21459","title":"Fair Conformal Predictors for Applications in Medical Imaging","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretability; Deep learning; Transparency (behavior); Artificial intelligence; Machine learning; Computer science; Data science; Field (mathematics); Mathematics; Computer security","score_opus":0.039484529412755605,"score_gpt":0.2989227623119308,"score_spread":0.2594382328991752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196522557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09118279,0.00006706037,0.87436676,0.016139504,0.0017987489,0.0029355981,0.000039013343,0.00033555212,0.013134948],"genre_scores_gemma":[0.99763805,0.000009114529,0.0011941885,0.00028750158,0.000065528235,0.0007256949,9.927369e-7,0.00001004278,0.00006889565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980137,0.000015555424,0.000509928,0.00041180805,0.0007392053,0.00030984456],"domain_scores_gemma":[0.9989833,0.00013802297,0.00028767737,0.0002390803,0.0002742512,0.00007766683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008425867,0.0001446105,0.00017475382,0.00017927906,0.00035884202,0.00009833176,0.002395978,0.00004332085,0.000104361796],"category_scores_gemma":[0.00021488732,0.00012436173,0.0000923739,0.0008257541,0.0001825759,0.00036510592,0.0006826195,0.00038667963,0.0000065038867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004618282,0.0001156987,0.0012412795,0.000029544646,0.000006179307,2.1782103e-7,0.0012232065,0.00023849275,0.0019535476,0.87881273,0.00021707383,0.11611582],"study_design_scores_gemma":[0.000099209916,0.0002499757,0.00064136414,0.0000857117,0.000009951834,0.00001596478,0.0027980208,0.62349486,0.13854991,0.22951609,0.004214745,0.00032419796],"about_ca_topic_score_codex":0.000046084093,"about_ca_topic_score_gemma":0.000015382599,"teacher_disagreement_score":0.9064553,"about_ca_system_score_codex":0.00016034268,"about_ca_system_score_gemma":0.00024356927,"threshold_uncertainty_score":0.5071324},"labels":[],"label_agreement":null},{"id":"W3197765800","doi":"10.1016/j.ajpath.2021.08.013","title":"Selection, Visualization, and Interpretation of Deep Features in Lung Adenocarcinoma and Squamous Cell Carcinoma","year":2021,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo; McMaster University; Ontario Tech University","funders":"Government of Ontario","keywords":"Interpretability; Distributed File System; Visualization; Adenocarcinoma; Lung cancer; Basal cell; Squamous carcinoma; Computer science; Deep learning; Cancer; Pathology; Artificial intelligence; Medicine; Oncology; Carcinoma; Internal medicine","score_opus":0.0038061430254757262,"score_gpt":0.24316120418393672,"score_spread":0.239355061158461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197765800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7011843,0.0016603195,0.296859,0.0001163283,0.00011103705,0.000025728226,2.893459e-7,0.0000043912664,0.000038642982],"genre_scores_gemma":[0.9903705,0.00006857509,0.009376603,0.00013589748,0.000034248184,0.000001424652,3.324591e-7,0.0000060679195,0.000006340292],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901587,0.00027377997,0.00031690949,0.00017414596,0.000109504545,0.0001097688],"domain_scores_gemma":[0.9990546,0.000115387586,0.00042213284,0.000095183255,0.0002667099,0.000045967656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022187989,0.00007587264,0.00023088379,0.00023726048,0.000030668885,0.00002193097,0.00011492595,0.00003671883,0.000002828208],"category_scores_gemma":[0.000084857464,0.00007634299,0.000025849791,0.0005150427,0.00013378398,0.00021781835,0.000061414765,0.0001441437,1.233742e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001468135,0.00011847324,0.8016752,0.0001048562,0.000018513685,0.0005567185,0.021872452,0.0008046615,0.028789649,0.0021924798,0.000100870515,0.14361933],"study_design_scores_gemma":[0.0008537304,0.0016849114,0.9035283,0.000023046256,0.000031934345,0.008148005,0.0017387111,0.056510385,0.026178462,0.0011318614,0.000014934699,0.0001557408],"about_ca_topic_score_codex":0.000025319161,"about_ca_topic_score_gemma":0.00005460687,"teacher_disagreement_score":0.28918624,"about_ca_system_score_codex":0.000055697015,"about_ca_system_score_gemma":0.00008866969,"threshold_uncertainty_score":0.31131768},"labels":[],"label_agreement":null},{"id":"W3197974008","doi":"10.3138/jvme-2021-0068","title":"Implementing Digital Pathology into Veterinary Academics and Research","year":2021,"lang":"en","type":"review","venue":"Journal of Veterinary Medical Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workflow; Multitude; Software; Computer science; Engineering management; Knowledge management; Engineering","score_opus":0.2759660038129125,"score_gpt":0.5318791395594188,"score_spread":0.2559131357465063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197974008","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001105529,0.9875734,0.007308513,0.0008277983,0.0028968086,0.00017225437,0.0000015153884,0.000016849588,0.000097325],"genre_scores_gemma":[0.0003904691,0.991022,0.0068431804,0.000102995116,0.0015294633,0.000031413812,0.000010468396,0.000026157699,0.000043856795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99584,0.000906732,0.0012038111,0.0004307287,0.0011791479,0.0004395946],"domain_scores_gemma":[0.9972329,0.00066513865,0.0008358517,0.00040060494,0.00046376037,0.0004017259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043298793,0.0002399319,0.0009018677,0.00062460883,0.00020984483,0.0002673244,0.0012004292,0.00051194313,0.000047337147],"category_scores_gemma":[0.0019387376,0.00020688058,0.00023047555,0.0007142585,0.00017601407,0.0009054563,0.0015034366,0.0022189964,0.00000823316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048927545,0.0000819706,0.0000026311575,0.002153646,0.00003835874,0.00039655753,0.0003612762,2.9204609e-8,0.0000050584767,0.00018593315,0.0016252318,0.9951444],"study_design_scores_gemma":[0.000102912156,0.0012158675,0.000006039923,0.009944718,0.000038293078,0.036377937,0.00013041527,0.00003477637,6.58245e-7,0.00054705486,0.95144284,0.00015850035],"about_ca_topic_score_codex":0.0000042568404,"about_ca_topic_score_gemma":3.3025088e-7,"teacher_disagreement_score":0.99498594,"about_ca_system_score_codex":0.0005091556,"about_ca_system_score_gemma":0.0056612124,"threshold_uncertainty_score":0.99997574},"labels":[],"label_agreement":null},{"id":"W3198972874","doi":"10.7554/elife.70119.sa2","title":"Author response: The BigBrainWarp toolbox for integration of BigBrain 3D histology with multimodal neuroimaging","year":2021,"lang":"en","type":"peer-review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Neuroimaging; Toolbox; Neuroscience; Multimodal therapy; Computer science; Psychology; Psychotherapist","score_opus":0.0572338534894595,"score_gpt":0.34251292165190006,"score_spread":0.28527906816244053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198972874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021340204,0.0048779347,0.72570133,0.2642772,0.0032689185,0.0010042272,0.000049542043,0.00014029135,0.000659235],"genre_scores_gemma":[0.0018928928,0.0004382756,0.5330994,0.020136923,0.00085700763,0.0014954782,0.00025518183,0.00016794521,0.44165686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965745,0.00079814804,0.00068320276,0.0009810305,0.0005812222,0.0003818906],"domain_scores_gemma":[0.99501896,0.0017993867,0.00066813343,0.0015958508,0.00085282774,0.0000648195],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020735117,0.00040788163,0.00072827504,0.00027785482,0.00019593693,0.0001172432,0.0015019365,0.00022750316,0.00007604138],"category_scores_gemma":[0.0013964986,0.00026411744,0.00024253335,0.0008718812,0.00020944579,0.00028101887,0.00026548974,0.0006156273,0.0000059279137],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016616088,0.00003393066,0.0000015558466,0.0008221913,0.00005981132,0.000011290819,0.00036714194,0.00007524688,0.0008471485,0.0015141111,0.7250469,0.2710545],"study_design_scores_gemma":[0.00033662116,0.00040777837,0.00006767079,0.0011234313,0.00008979759,0.00013343444,0.000034698176,0.042340834,0.0009802204,0.00015891937,0.9539936,0.00033300562],"about_ca_topic_score_codex":0.00030639808,"about_ca_topic_score_gemma":0.00054180674,"teacher_disagreement_score":0.44099763,"about_ca_system_score_codex":0.00029007508,"about_ca_system_score_gemma":0.0011727002,"threshold_uncertainty_score":0.9999811},"labels":[],"label_agreement":null},{"id":"W3199429500","doi":"10.1101/2021.09.13.460002","title":"Stable breast cancer prognosis","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; Cancer Research UK","keywords":"Breast cancer; Inference; Computer science; Artificial intelligence; Cancer; Machine learning; Data mining; Oncology; Medicine; Internal medicine","score_opus":0.01472785976463534,"score_gpt":0.22375646630978663,"score_spread":0.2090286065451513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199429500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63713604,0.008685219,0.32442978,0.0049511427,0.017637156,0.002258926,0.0006141905,0.004235284,0.00005227026],"genre_scores_gemma":[0.9655687,0.0007290849,0.03139197,0.0003954821,0.0008372979,0.0009503351,1.0623275e-7,0.000116963514,0.0000100602965],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959116,0.00017601684,0.00053646544,0.0018454411,0.0007324757,0.0007979733],"domain_scores_gemma":[0.9957397,0.000047119855,0.0004861549,0.002365556,0.0010339849,0.00032746643],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005115518,0.000619863,0.00060114556,0.00027581496,0.00025034838,0.0012225369,0.0018724976,0.0005574602,0.00012568926],"category_scores_gemma":[0.00004788568,0.0007084116,0.00021296486,0.0012828835,0.00008955391,0.00079797965,0.0020323186,0.0010198675,0.00005209782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060148363,0.0009936405,0.07112813,0.002874262,0.001411147,0.0005263346,0.00015221641,0.0029044393,0.90823746,0.003815056,0.007504889,0.00039227383],"study_design_scores_gemma":[0.0006931795,0.00006051073,0.2695178,0.001690396,0.00018507687,1.8042839e-7,0.0000052196538,0.016447607,0.6980107,0.0000079344545,0.010856206,0.0025252209],"about_ca_topic_score_codex":0.000531557,"about_ca_topic_score_gemma":0.000021283853,"teacher_disagreement_score":0.32843265,"about_ca_system_score_codex":0.0010545399,"about_ca_system_score_gemma":0.0020854876,"threshold_uncertainty_score":0.9998143},"labels":[],"label_agreement":null},{"id":"W3200175406","doi":"10.1109/cisp-bmei53629.2021.9624252","title":"A Medical Pre-Diagnosis System for Histopathological Image of Breast Cancer","year":2021,"lang":"en","type":"article","venue":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Chatbot; Computer science; Artificial intelligence; Artificial neural network; Classifier (UML); Machine learning; Pattern recognition (psychology)","score_opus":0.006857863487869831,"score_gpt":0.24940617809604082,"score_spread":0.242548314608171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200175406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016881773,0.000786577,0.97733706,0.002011871,0.0019848982,0.0002182072,0.00021502611,0.00013627492,0.00042830122],"genre_scores_gemma":[0.95374703,0.0005553275,0.0440801,0.0004226672,0.0006044113,0.00026727002,0.00005709084,0.000028470584,0.0002376184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789286,0.000024149524,0.00067226,0.00029435253,0.00084396236,0.0002724432],"domain_scores_gemma":[0.99861103,0.00020723412,0.000247044,0.00016124493,0.0005054559,0.0002679651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000470305,0.00022097235,0.00033863587,0.00019984359,0.00010847012,0.00027574186,0.0004401476,0.00018692353,0.00011205632],"category_scores_gemma":[0.00024134974,0.00018779421,0.00007802205,0.0002564453,0.00021537876,0.0006836253,0.0002552467,0.00029648398,0.000002394294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002900034,0.0005722762,0.00047498159,0.0070713772,0.00033959284,0.00034262383,0.002829893,0.00065524084,0.0064786854,0.008356742,0.008972341,0.96361625],"study_design_scores_gemma":[0.0011036681,0.00019218997,0.00044588855,0.0013795746,0.000028752287,0.00045353099,0.00016971315,0.9795237,0.0056558014,0.00007867433,0.010681909,0.00028660527],"about_ca_topic_score_codex":0.000010252068,"about_ca_topic_score_gemma":0.0000012361431,"teacher_disagreement_score":0.9788684,"about_ca_system_score_codex":0.00011521415,"about_ca_system_score_gemma":0.00023207131,"threshold_uncertainty_score":0.76580256},"labels":[],"label_agreement":null},{"id":"W3200175561","doi":"10.48550/arxiv.2109.05587","title":"On the Efficiency of Subclass Knowledge Distillation in Classification Tasks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Distillation; Class (philosophy); Machine learning; Task (project management); Artificial intelligence; Binary number; Process (computing); Binary classification; Subclass; Limiting; Annotation; Measure (data warehouse); Data mining; Mathematics; Engineering; Support vector machine","score_opus":0.09450960542890219,"score_gpt":0.20865508905513774,"score_spread":0.11414548362623556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200175561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55563956,0.000042551063,0.4398216,0.00012135153,0.0005166338,0.00020306089,0.0000026987186,0.000048902966,0.0036036265],"genre_scores_gemma":[0.9995329,0.00007006743,0.00013165208,0.000015785443,0.000029935667,0.0000021496126,0.0000070981732,0.000008802266,0.00020164665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984587,0.00027572826,0.00022292863,0.00076204777,0.00010538156,0.00017520193],"domain_scores_gemma":[0.9979714,0.0003243201,0.00031265605,0.0011663699,0.00018552056,0.00003974563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038177206,0.00017611445,0.00020072747,0.00025508527,0.00008643424,0.00006134566,0.0011065749,0.00020543637,0.000015632311],"category_scores_gemma":[0.00009000462,0.0001703302,0.00011747453,0.0011763171,0.00010622137,0.0001815567,0.00065773964,0.00047651012,0.000019280465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051918178,0.00038615335,0.0068702167,0.00016341583,0.000046205623,0.00003705057,0.0017955204,0.26575774,0.0008874323,0.71977156,0.0001951523,0.004037623],"study_design_scores_gemma":[0.00021741484,0.00005501219,0.024815155,0.00017151744,0.000016911006,9.678089e-7,0.00017178063,0.9546441,0.0014846066,0.018121846,0.000080829355,0.00021989192],"about_ca_topic_score_codex":0.000099459954,"about_ca_topic_score_gemma":0.0001949197,"teacher_disagreement_score":0.7016497,"about_ca_system_score_codex":0.00053692004,"about_ca_system_score_gemma":0.00027027747,"threshold_uncertainty_score":0.6945864},"labels":[],"label_agreement":null},{"id":"W3200356700","doi":"10.1002/path.5797","title":"The utility of color normalization for <scp>AI</scp>‐based diagnosis of hematoxylin and eosin‐stained pathology images","year":2021,"lang":"en","type":"article","venue":"The Journal of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; BC Cancer Agency; Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Normalization (sociology); Digital pathology; Artificial intelligence; Computer science; H&E stain; Pattern recognition (psychology); Color normalization; Benchmarking; Pathology; Medicine; Image processing; Color image; Staining","score_opus":0.015448240296665972,"score_gpt":0.2742874523250281,"score_spread":0.25883921202836213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200356700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46632627,0.0014616997,0.529326,0.002290368,0.00039167996,0.00014755361,0.00001213231,0.000007502377,0.000036769274],"genre_scores_gemma":[0.98900676,0.00053579843,0.01006542,0.00029654076,0.000053897846,0.000015024649,8.213086e-7,0.000007631747,0.00001808708],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818856,0.00072025787,0.0005831715,0.00013898664,0.00017923414,0.00018977292],"domain_scores_gemma":[0.9952834,0.002604118,0.00086773996,0.00037137093,0.00083619554,0.00003716245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022942007,0.00009971763,0.00031474882,0.00007998499,0.00015218508,0.000020523155,0.00046110043,0.00009637994,0.0000034363236],"category_scores_gemma":[0.001341843,0.00006318782,0.000098074735,0.00027670508,0.000350156,0.0001607605,0.00014346282,0.0001712287,2.8133e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017203601,0.0020542261,0.12323409,0.0016757892,0.000623758,0.0012812852,0.023250932,0.005745535,0.6097644,0.03463292,0.03213931,0.1638774],"study_design_scores_gemma":[0.0019136198,0.0017850943,0.050838735,0.00007452038,0.00015877724,0.002480214,0.0008408916,0.032953177,0.8846998,0.022563817,0.001605121,0.00008619964],"about_ca_topic_score_codex":0.0000041400403,"about_ca_topic_score_gemma":0.000023762552,"teacher_disagreement_score":0.5226805,"about_ca_system_score_codex":0.000025792251,"about_ca_system_score_gemma":0.00020887316,"threshold_uncertainty_score":0.25767246},"labels":[],"label_agreement":null},{"id":"W3200666261","doi":"10.1145/3459930.3471169","title":"Prostate biomedical images segmentation and classification by using U-NET CNN model","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Sørensen–Dice coefficient; Prostate cancer; Grading (engineering); Ground truth; Prostate; Pixel; Pattern recognition (psychology); Image segmentation; Deep learning; Computer vision; Medicine; Cancer; Internal medicine","score_opus":0.031621619678015855,"score_gpt":0.2912144474627683,"score_spread":0.25959282778475246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200666261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035372563,0.00009780728,0.9623935,0.001484724,0.00012232889,0.00007580434,0.000003835616,0.00008717812,0.0003622231],"genre_scores_gemma":[0.60650855,0.00009960972,0.39202055,0.0003610604,0.0000330287,0.000015044216,0.000019946914,0.000007702771,0.0009345133],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992678,0.000032503023,0.00012419884,0.00028236976,0.00018518567,0.00010792365],"domain_scores_gemma":[0.99965334,0.000017119657,0.0000465768,0.00016757393,0.000063849984,0.000051562398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010804626,0.000059883143,0.00005429216,0.000037479305,0.000080987505,0.00014044896,0.000086055596,0.00003652569,0.000009593279],"category_scores_gemma":[0.000009977597,0.000057873112,0.000010909719,0.00022329867,0.00004161736,0.0005302142,0.00007931523,0.00005219009,0.000005598169],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002759145,0.00003106328,0.00015939263,0.000015282048,0.0000065959844,0.0000020373755,0.0003399178,0.00037366975,0.8611881,0.0007152167,0.005354163,0.13181181],"study_design_scores_gemma":[0.00015040001,0.000016176667,0.00017093819,0.000005197181,0.0000033399788,0.000014036841,0.00006593031,0.894033,0.104146324,0.0010240214,0.00030201208,0.00006861028],"about_ca_topic_score_codex":0.000016030528,"about_ca_topic_score_gemma":0.0000022609543,"teacher_disagreement_score":0.89365935,"about_ca_system_score_codex":0.00007982941,"about_ca_system_score_gemma":0.000084110354,"threshold_uncertainty_score":0.2359997},"labels":[],"label_agreement":null},{"id":"W3200847902","doi":"10.3390/curroncol28050307","title":"Detection of Cervical Cancer Cells in Whole Slide Images Using Deformable and Global Context Aware Faster RCNN-FPN","year":2021,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Key Research and Development Program of Zhejiang Province","keywords":"Medicine; Context (archaeology); Cervical cancer; Cancer; Artificial intelligence; Computer vision; Computer science; Internal medicine; Biology","score_opus":0.06204921615106501,"score_gpt":0.36368009550130453,"score_spread":0.3016308793502395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200847902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6897754,0.0032804767,0.3026604,0.00042366932,0.0035066844,0.00015052885,0.000023354834,0.00003655725,0.00014290455],"genre_scores_gemma":[0.9980743,0.00013638551,0.0015584691,0.000085655636,0.000100696445,0.000019594381,0.0000012121701,0.000005378467,0.000018343557],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988398,0.00013741727,0.0002838905,0.0003471855,0.0001377757,0.00025391058],"domain_scores_gemma":[0.9993897,0.000050847255,0.00013751224,0.00020569633,0.0001534237,0.000062835265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014543014,0.00011469838,0.00024687496,0.00006413231,0.000056285528,0.000035330286,0.00017728782,0.00010686702,0.000015436024],"category_scores_gemma":[0.000014730998,0.00011743345,0.000041249597,0.00040286026,0.00007513886,0.00034979157,0.0002817566,0.0001854677,0.0000054789157],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044494736,0.00016037172,0.019042164,0.0001660424,0.000017871787,0.0000226598,0.0005593722,0.0011766597,0.059580605,0.00012733888,0.0001927483,0.91890967],"study_design_scores_gemma":[0.0034335642,0.00055488606,0.038272172,0.00035041248,0.000060363393,0.00028051142,0.0007486458,0.36120632,0.52507347,0.0017009537,0.06773329,0.0005854176],"about_ca_topic_score_codex":0.00038794617,"about_ca_topic_score_gemma":0.0027508964,"teacher_disagreement_score":0.91832423,"about_ca_system_score_codex":0.0007282772,"about_ca_system_score_gemma":0.00032054132,"threshold_uncertainty_score":0.4788797},"labels":[],"label_agreement":null},{"id":"W3202001413","doi":"10.4103/jpi.jpi_100_20","title":"Browser-based Data Annotation, Active Learning, and Real-Time Distribution of Artificial Intelligence Models: From Tumor Tissue Microarrays to COVID-19 Radiology","year":2021,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Cloud computing; DICOM; Workflow; Artificial intelligence; Machine learning; Scalability; Digital pathology; Big data; Data science; Data mining; Database","score_opus":0.044562526803212356,"score_gpt":0.31967228722538604,"score_spread":0.27510976042217367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202001413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18639553,0.000051483297,0.8123304,0.0007225434,0.0002554508,0.0000761681,0.000119196084,0.000016915777,0.00003228036],"genre_scores_gemma":[0.61211014,0.00018122274,0.38649148,0.0008043226,0.0001571405,0.0000042836728,0.00022980946,0.000010716689,0.000010873137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982915,0.00024968616,0.0009214267,0.00015498303,0.00021249829,0.00016993526],"domain_scores_gemma":[0.99753875,0.00040529476,0.0010209419,0.0003878237,0.0004970978,0.00015012054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007824636,0.000116949406,0.0003291611,0.00014401082,0.000103385115,0.000047220794,0.000579451,0.000108138425,0.000016743377],"category_scores_gemma":[0.0010895008,0.000115344534,0.000033191016,0.00034047506,0.0001300068,0.0008675834,0.00026403266,0.00028980963,0.000008530498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010199688,0.0004236925,0.0013239356,0.00036183817,0.00028159775,0.001179297,0.053663433,0.44206026,0.18185285,0.0084483,0.0067628557,0.30262196],"study_design_scores_gemma":[0.00053337857,0.0012971503,0.0007872068,0.000082966886,0.000084913285,0.002837703,0.0028848595,0.8846011,0.08748648,0.015328107,0.0037570375,0.0003190784],"about_ca_topic_score_codex":0.000025517309,"about_ca_topic_score_gemma":0.000015890208,"teacher_disagreement_score":0.44254085,"about_ca_system_score_codex":0.00013232557,"about_ca_system_score_gemma":0.0006617617,"threshold_uncertainty_score":0.47036135},"labels":[],"label_agreement":null},{"id":"W3202436968","doi":"10.1007/978-3-030-87237-3_65","title":"Training Deep Networks for Prostate Cancer Diagnosis Using Coarse Histopathological Labels","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Queen's University; University of British Columbia","funders":"","keywords":"Computer science; Prostate cancer; Artificial intelligence; Constraint (computer-aided design); Artificial neural network; Histopathology; Pattern recognition (psychology); Deep learning; Biopsy; Cancer; Radiology; Medicine; Pathology; Mathematics","score_opus":0.05455803568230379,"score_gpt":0.29117450365872205,"score_spread":0.23661646797641828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202436968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020650205,0.0036222185,0.9891076,0.0005367327,0.005336716,0.00079186866,0.0000150711085,0.000198749,0.00018455755],"genre_scores_gemma":[0.07056958,0.0006105726,0.9232849,0.002961721,0.0017443598,0.00046461498,0.000009839868,0.000092532464,0.00026190354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954126,0.00006240847,0.00062527414,0.0021586064,0.0007502035,0.0009908993],"domain_scores_gemma":[0.9970871,0.00075815705,0.0004476814,0.0010701581,0.00043944662,0.00019743507],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009906107,0.0006079841,0.0007391524,0.00046247247,0.0004967731,0.00059469364,0.0021048645,0.0004962779,0.00003430104],"category_scores_gemma":[0.00013834791,0.0005899709,0.00021642192,0.00077544566,0.0006712373,0.00060102163,0.001062018,0.00092025707,0.0000022533634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006912328,0.000013258726,0.00006923729,0.000029710947,0.000008421494,0.0000839395,0.0007912287,0.27786887,0.00005521965,0.0013058587,0.000011817714,0.71975553],"study_design_scores_gemma":[0.00031917414,0.00018971028,0.000037626203,0.00056878256,0.000023988681,0.00010991501,5.796356e-7,0.9730152,0.0006077351,0.020905899,0.003487086,0.0007342882],"about_ca_topic_score_codex":0.000043982687,"about_ca_topic_score_gemma":0.00027739725,"teacher_disagreement_score":0.71902126,"about_ca_system_score_codex":0.0012900269,"about_ca_system_score_gemma":0.0009279944,"threshold_uncertainty_score":0.9996552},"labels":[],"label_agreement":null},{"id":"W3202718475","doi":"10.1007/978-3-030-87592-3_5","title":"Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Institute of Mental Health; National Institute on Aging","keywords":"Computer science; Image registration; Artificial intelligence; Overfitting; Reduction (mathematics); Code (set theory); Translation (biology); Complement (music); Pattern recognition (psychology); Modality (human–computer interaction); Computer vision; Natural language processing; Image (mathematics); Artificial neural network","score_opus":0.041171073039473344,"score_gpt":0.1775797305565094,"score_spread":0.13640865751703607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202718475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044385903,0.00005314532,0.95415723,0.00023319438,0.00013783331,0.00014356917,0.000009920258,0.0001203094,0.0007588646],"genre_scores_gemma":[0.99625945,0.000020632788,0.0026922254,0.000037407488,0.000023012331,0.0000026861742,0.0000049056694,0.000009397988,0.0009502916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892217,0.0001673111,0.00014890601,0.00049096334,0.00007916109,0.00019148359],"domain_scores_gemma":[0.99832654,0.00075711263,0.00022174802,0.0003402703,0.00029470358,0.000059642847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027368226,0.00011857473,0.00017773065,0.00007743967,0.00015343001,0.00004131863,0.0003244906,0.00007730316,0.00001552781],"category_scores_gemma":[0.00039022442,0.00014673482,0.00011321941,0.00048735325,0.000091006026,0.00040668822,0.000055554257,0.0001031312,0.0000047589288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010884934,0.00087465235,0.0151820425,0.0006668782,0.00059893506,0.00047400853,0.0006593137,0.4845745,0.2730217,0.15182155,0.010122002,0.06091592],"study_design_scores_gemma":[0.00068575336,0.00016987375,0.000894625,0.00008636615,0.0000621705,0.0000037772613,0.00018456615,0.548763,0.4456223,0.0020831716,0.00119867,0.0002457226],"about_ca_topic_score_codex":0.000045671954,"about_ca_topic_score_gemma":0.000026298867,"teacher_disagreement_score":0.95187354,"about_ca_system_score_codex":0.00014254668,"about_ca_system_score_gemma":0.00018679533,"threshold_uncertainty_score":0.5983672},"labels":[],"label_agreement":null},{"id":"W3202770052","doi":"10.1007/978-3-030-87234-2_16","title":"Culprit-Prune-Net: Efficient Continual Sequential Multi-domain Learning with Application to Skin Lesion Classification","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer science; Pruning; Artificial intelligence; Deep learning; Machine learning; Domain knowledge; Artificial neural network; Oracle; Inference; Domain (mathematical analysis); Contextual image classification; Forgetting; Image (mathematics); Pattern recognition (psychology)","score_opus":0.019323937570082828,"score_gpt":0.2634131805385865,"score_spread":0.24408924296850365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202770052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001107932,0.00020065664,0.99486524,0.0008040668,0.0011515503,0.0009900506,0.0000031892657,0.00036706543,0.0005102403],"genre_scores_gemma":[0.42505443,0.00002273604,0.57325244,0.00054464577,0.000552284,0.000087304616,0.000021225456,0.000065769,0.00039915615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99461734,0.00011542793,0.00062279654,0.0024809726,0.0014698256,0.00069362833],"domain_scores_gemma":[0.9971706,0.00022626306,0.0004888842,0.0013075987,0.00056560396,0.00024101492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010920337,0.000592921,0.0005218357,0.0008216263,0.00050161954,0.0006805807,0.0019251335,0.00038277556,0.000011791205],"category_scores_gemma":[0.000064490356,0.00056543265,0.000121324476,0.0013104122,0.00042506,0.00037329152,0.0010437706,0.0010733842,0.00007170806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026131827,0.000058439615,0.00008292468,0.000047180827,0.000013786725,0.00003514309,0.001390053,0.35579962,0.00600956,0.0051114783,0.000010551515,0.6314151],"study_design_scores_gemma":[0.00056222494,0.00034086042,0.0007780363,0.0005441308,0.000012734415,0.00009591692,0.0000028010847,0.98347956,0.007351211,0.0018323194,0.0041441577,0.00085605175],"about_ca_topic_score_codex":0.000052484687,"about_ca_topic_score_gemma":0.00028809966,"teacher_disagreement_score":0.6305591,"about_ca_system_score_codex":0.0011211577,"about_ca_system_score_gemma":0.0006869913,"threshold_uncertainty_score":0.9996797},"labels":[],"label_agreement":null},{"id":"W3202780099","doi":"10.30683/1929-2279.2019.08.03","title":"A Detail Process for CAD Based Breast Cancer Detection","year":2019,"lang":"en","type":"article","venue":"Journal of cancer research updates","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; CAD; Medicine; Disease; Biopsy; Cancer; Mammography; Yield (engineering); Radiology; Computer science; Oncology; Internal medicine; Engineering drawing; Engineering","score_opus":0.04864816383186417,"score_gpt":0.41130045473668764,"score_spread":0.3626522909048235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202780099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7667781,0.003988518,0.20654857,0.017157182,0.0036649385,0.0014417318,0.00007793823,0.00010381305,0.00023921033],"genre_scores_gemma":[0.99725014,0.00030071277,0.0011330368,0.00019813636,0.0006956966,0.00020682535,4.1644932e-7,0.000026170563,0.00018888651],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972808,0.000154356,0.00042642822,0.00033469038,0.0012545725,0.0005491815],"domain_scores_gemma":[0.99630517,0.0002557853,0.00037406778,0.00034700884,0.0025302507,0.00018770261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018448738,0.0001480918,0.0002744986,0.00053355115,0.0002031823,0.00024373639,0.0011004148,0.00009737627,0.0001768756],"category_scores_gemma":[0.0000822216,0.000121128476,0.00014453752,0.0010239441,0.00007577954,0.0012886459,0.00008479689,0.00061341445,0.000017345898],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030993733,0.00028429643,0.031684905,0.0011158421,0.00041431974,0.00002499317,0.00093455316,0.029318687,0.15934204,0.00048068786,0.007106202,0.7661941],"study_design_scores_gemma":[0.0046915514,0.0018618219,0.01639272,0.00089873496,0.000055718247,0.00018235743,0.0002628648,0.19879428,0.7203451,0.0065162363,0.04938673,0.0006118991],"about_ca_topic_score_codex":0.00036552755,"about_ca_topic_score_gemma":0.00056550454,"teacher_disagreement_score":0.7655822,"about_ca_system_score_codex":0.00083322835,"about_ca_system_score_gemma":0.0015458537,"threshold_uncertainty_score":0.4939476},"labels":[],"label_agreement":null},{"id":"W3204961702","doi":"10.1016/j.tice.2021.101659","title":"Detection of malignant melanoma in H&amp;E-stained images using deep learning techniques","year":2021,"lang":"en","type":"article","venue":"Tissue and Cell","topic":"AI in cancer detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Melanoma; Artificial intelligence; Convolutional neural network; Deep learning; H&E stain; Pixel; Sørensen–Dice coefficient; Pattern recognition (psychology); Digital pathology; Computer science; Biology; Segmentation; Computer vision; Image segmentation; Staining; Cancer research","score_opus":0.01294673546246477,"score_gpt":0.2521314785744314,"score_spread":0.23918474311196664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204961702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4108177,0.0011049457,0.5873297,0.00003370249,0.00006798072,0.000058713544,2.1123562e-7,0.00005835804,0.00052867434],"genre_scores_gemma":[0.9601455,0.00016970118,0.039313555,0.000011890435,0.000027445534,0.0000045473275,5.028572e-7,0.000006196176,0.0003206865],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993788,0.00006805663,0.00014010312,0.00020394054,0.000089254565,0.00011984273],"domain_scores_gemma":[0.99967664,0.000027346361,0.000070196016,0.00015171271,0.000051736595,0.000022345917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014791549,0.00006633342,0.00010627106,0.000081800004,0.000052186922,0.000033247343,0.00008553643,0.00004970142,0.000009794106],"category_scores_gemma":[0.000012665777,0.00007055146,0.000015176295,0.00027907235,0.000019931209,0.00017741065,0.00009430384,0.00009493052,0.00000214789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033529705,0.000010972597,0.0004162299,0.0000340395,0.0000015043706,0.000015216782,0.00037614285,0.00004860411,0.84510565,0.00003232287,0.0000014153532,0.15395455],"study_design_scores_gemma":[0.000088694374,0.00007406323,0.0007712298,0.000026820395,0.000003772984,0.00003347454,0.000078319055,0.003325907,0.9924031,0.0004582312,0.002655569,0.000080812984],"about_ca_topic_score_codex":0.00020602367,"about_ca_topic_score_gemma":0.0000946624,"teacher_disagreement_score":0.54932773,"about_ca_system_score_codex":0.000041234012,"about_ca_system_score_gemma":0.000023027753,"threshold_uncertainty_score":0.2877005},"labels":[],"label_agreement":null},{"id":"W3204967528","doi":"","title":"A facial animation driven by X-ray microbeam data.","year":2000,"lang":"en","type":"dissertation","venue":"oURspace (University of Regina)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microbeam; Computer graphics (images); Animation; Computer science; X-ray; Computer facial animation; Computer animation; Physics; Optics","score_opus":0.0112636097658191,"score_gpt":0.21985574444631126,"score_spread":0.20859213468049215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204967528","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12262534,0.0014201246,0.37069538,0.4908039,0.0031689205,0.0013608553,0.000654896,0.00089540164,0.008375173],"genre_scores_gemma":[0.016009616,0.0029234733,0.099566065,0.00009009808,0.00032266488,0.0000021106928,0.0057212054,0.00010372788,0.87526107],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859643,0.00006555222,0.000021728305,0.00068769016,0.00039430038,0.0002343056],"domain_scores_gemma":[0.99829143,0.0000238045,0.00040821204,0.0010702988,0.00012631495,0.000079941354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011837931,0.0002160356,0.00029644184,0.0002449105,0.0002376204,0.00006169073,0.0021237598,0.00030855913,0.000017592527],"category_scores_gemma":[0.000008817858,0.0003111945,0.00009166026,0.00043880596,0.00006315964,0.001169648,0.00016702605,0.00028622244,0.00009386229],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007673374,0.000021992684,0.0000144269125,0.00007912251,0.00006125441,0.000012119473,0.0011275251,0.00008785894,0.0035294504,0.00018884447,0.9503365,0.044464163],"study_design_scores_gemma":[0.00034680255,0.00009527413,0.00035458227,0.00011366508,0.000048354428,0.0000037694638,0.0012503247,0.0062399306,0.00034667467,0.000010520649,0.9908925,0.00029757363],"about_ca_topic_score_codex":0.00005959562,"about_ca_topic_score_gemma":0.0010477427,"teacher_disagreement_score":0.86688584,"about_ca_system_score_codex":0.00021988209,"about_ca_system_score_gemma":0.00026083246,"threshold_uncertainty_score":0.999934},"labels":[],"label_agreement":null},{"id":"W3207981182","doi":"10.3389/fvets.2021.758295","title":"Quantitative and Semi-quantitative Methods for Assessing the Degree of Methylene Blue Staining in Sentinel Lymph Nodes in Dogs","year":2021,"lang":"en","type":"article","venue":"Frontiers in Veterinary Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Methylene blue; Staining; Lymph; Degree (music); Pathology; Biology; Medicine; Physics; Biochemistry","score_opus":0.11726323902925335,"score_gpt":0.4169982456526629,"score_spread":0.29973500662340957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207981182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45751655,0.0010206363,0.54059905,0.00017073164,0.0004665309,0.000118071024,0.0000012865811,0.000009777564,0.000097385986],"genre_scores_gemma":[0.44433594,0.000054665972,0.5555208,0.00004153317,0.000004633501,0.000027400456,2.9265132e-7,0.000005157308,0.000009600956],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974859,0.000658737,0.00043808873,0.00070462027,0.00028784946,0.00042481167],"domain_scores_gemma":[0.9980859,0.0010700586,0.00021686936,0.0003947076,0.00018567112,0.000046786972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004977179,0.00015947057,0.00033286295,0.00069961353,0.00017427962,0.00018180741,0.0008025294,0.000056876077,6.9271624e-7],"category_scores_gemma":[0.0011443335,0.00014273476,0.000041224102,0.003569371,0.0006991934,0.0017387684,0.0005326643,0.00018745499,1.351479e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023500426,0.00021224191,0.13441631,0.00032737834,0.000037414822,0.000172135,0.042454857,0.010366712,0.42630887,0.019646784,0.000027675425,0.3657946],"study_design_scores_gemma":[0.0006670973,0.00020219944,0.1783976,0.00025650547,0.0000044849407,0.000041742813,0.010995952,0.78987485,0.010817945,0.008443757,0.000071357565,0.00022651994],"about_ca_topic_score_codex":0.00011038713,"about_ca_topic_score_gemma":0.000011658737,"teacher_disagreement_score":0.7795081,"about_ca_system_score_codex":0.00030275626,"about_ca_system_score_gemma":0.0005775843,"threshold_uncertainty_score":0.58205545},"labels":[],"label_agreement":null},{"id":"W3208020934","doi":"10.1109/access.2021.3123472","title":"IoMT Cloud-Based Intelligent Prediction of Breast Cancer Stages Empowered With Deep Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Breast cancer; Deep learning; Artificial intelligence; Computer science; Machine learning; Cancer; Cloud computing; Medicine; Oncology; Internal medicine","score_opus":0.02328900358500442,"score_gpt":0.2904040540122134,"score_spread":0.267115050427209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208020934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20540914,0.00023896547,0.792087,0.00036188302,0.0014444281,0.00011039471,0.000014497903,0.0001541932,0.000179494],"genre_scores_gemma":[0.997776,0.000085189284,0.0016802483,0.00010793013,0.00019431803,0.00004164075,0.0000034747502,0.000015442158,0.00009579305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987111,0.0000916164,0.00022286043,0.0003934998,0.0003785629,0.00020233207],"domain_scores_gemma":[0.9989243,0.000060940827,0.00019223116,0.0004035319,0.0003547149,0.00006427281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001399734,0.00012708381,0.00016036945,0.000097787684,0.00010126197,0.00016261621,0.00056019454,0.000059562226,0.00009290344],"category_scores_gemma":[0.000012040049,0.00011600576,0.000045803085,0.00075396337,0.000051420222,0.000618987,0.000102168946,0.00019209387,0.0000038948624],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002682303,0.0002857656,0.22423463,0.00033409297,0.00023010753,0.00008245041,0.0017223854,0.43567544,0.02463113,0.00026488234,0.0008259659,0.31144494],"study_design_scores_gemma":[0.00085016206,0.000257632,0.096626,0.0003052428,0.000043652504,0.000056984853,0.00011929745,0.1782266,0.7208144,0.00020106442,0.0021652232,0.0003337114],"about_ca_topic_score_codex":0.00033927464,"about_ca_topic_score_gemma":0.0003119515,"teacher_disagreement_score":0.7923668,"about_ca_system_score_codex":0.00016860776,"about_ca_system_score_gemma":0.00024617297,"threshold_uncertainty_score":0.47305775},"labels":[],"label_agreement":null},{"id":"W3209404053","doi":"10.1109/irce53649.2021.9570898","title":"Breast Ultrasound Image Segmentation Model Based Residual Encoder","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Feature extraction; Deep learning; Pattern recognition (psychology); Breast ultrasound; Concatenation (mathematics); CAD; Residual; Convolution (computer science); Image segmentation; Upsampling; Convolutional neural network; Preprocessor; Path (computing); Feature (linguistics); Artificial neural network; Mammography; Algorithm; Image (mathematics); Mathematics","score_opus":0.01243794524017024,"score_gpt":0.2531243563837875,"score_spread":0.24068641114361725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209404053","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005088805,0.0000138130945,0.98513097,0.0012902934,0.00019281212,0.000059438044,0.0000057262064,0.00019211283,0.008026036],"genre_scores_gemma":[0.40685552,0.0000043179148,0.5906762,0.00083577953,0.00006625119,0.000015532782,0.000009052728,0.000008494839,0.0015288272],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905217,0.000049092876,0.00013047674,0.0003342279,0.0002759286,0.00015813552],"domain_scores_gemma":[0.9993081,0.0000694006,0.00003775097,0.000391908,0.000141798,0.000051009287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000125473,0.00008359594,0.00006621756,0.00004340468,0.000091783404,0.0001912373,0.000222392,0.000038275884,0.00016569383],"category_scores_gemma":[0.000012560619,0.00008381979,0.000033604276,0.0002789709,0.000022185608,0.0006875024,0.000060775357,0.00007528007,0.00006234583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030034658,0.00022184839,0.00059934065,0.000048681763,0.0000407219,0.000056416633,0.0010777849,0.078198135,0.7977849,0.014583116,0.025212878,0.08214612],"study_design_scores_gemma":[0.00026861954,0.0000134564125,0.0005233457,0.0000052449764,0.0000041874737,0.00010906306,0.00004641165,0.69527715,0.3007334,0.0028504878,0.000046091005,0.00012254636],"about_ca_topic_score_codex":0.000030049318,"about_ca_topic_score_gemma":0.00005511007,"teacher_disagreement_score":0.617079,"about_ca_system_score_codex":0.00011117568,"about_ca_system_score_gemma":0.00022926409,"threshold_uncertainty_score":0.3418072},"labels":[],"label_agreement":null},{"id":"W3209533960","doi":"10.1002/ima.22666","title":"Whole slide cervical image classification based on convolutional neural network and random forest","year":2021,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"National Natural Science Foundation of China","keywords":"Random forest; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Principal component analysis; Feature (linguistics); Classifier (UML)","score_opus":0.009071956171855461,"score_gpt":0.2482158553917342,"score_spread":0.23914389921987875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209533960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059422698,0.0023691468,0.8869222,0.047199447,0.0035702381,0.000102481325,0.000006075863,0.00008771867,0.00032001038],"genre_scores_gemma":[0.9923138,0.000038017257,0.0069783665,0.00026305128,0.0003653734,0.000006140226,0.0000022193926,0.000006629107,0.00002639933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889255,0.000069523085,0.00036645244,0.00020779195,0.0003279388,0.00013575827],"domain_scores_gemma":[0.99862105,0.00015203004,0.00031385207,0.00015202364,0.0007126944,0.000048368063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033732175,0.000094670075,0.00017313178,0.00027097462,0.00008014737,0.0002249168,0.00033782583,0.00006382212,0.0000027483948],"category_scores_gemma":[0.00011916552,0.00008586659,0.000040510702,0.00021004572,0.00011426297,0.0003363599,0.000107739106,0.00025140564,0.0000020644927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005556237,0.00035674716,0.32638305,0.00012386964,0.00048351128,0.0020276823,0.0001876957,0.026573708,0.04260228,0.3936989,0.012085594,0.19492133],"study_design_scores_gemma":[0.002072066,0.00008850791,0.022564493,0.00019286436,0.000012391995,0.0034462493,0.00007856832,0.9548892,0.00039595112,0.006786965,0.009348482,0.00012426365],"about_ca_topic_score_codex":0.000009947385,"about_ca_topic_score_gemma":0.000005707524,"teacher_disagreement_score":0.93289113,"about_ca_system_score_codex":0.00010273626,"about_ca_system_score_gemma":0.00010581607,"threshold_uncertainty_score":0.3501538},"labels":[],"label_agreement":null},{"id":"W3210056014","doi":"10.21528/cbic2021-135","title":"Data-augmentation de dados de radiografia de torax no contexto de aprendizagem profunda","year":2021,"lang":"pt","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Humanities; Philosophy","score_opus":0.11996697494864875,"score_gpt":0.3858904450724848,"score_spread":0.2659234701238361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210056014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012324412,0.0010685235,0.97983396,0.0018922801,0.001777602,0.00045159392,0.00009864166,0.0003206563,0.0022323455],"genre_scores_gemma":[0.72634304,0.00052418455,0.2433742,0.0051913722,0.0010537927,0.0001471428,0.00018563625,0.000092227834,0.023088375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959751,0.00072748587,0.00052264903,0.0011771327,0.0005182365,0.0010793919],"domain_scores_gemma":[0.99694675,0.0002525157,0.00024944573,0.0018740577,0.0002558659,0.00042134113],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015488047,0.00035173298,0.00032966098,0.00014936976,0.00036659633,0.0009398197,0.0016883167,0.00025862298,0.0007938062],"category_scores_gemma":[0.00026505018,0.00040742455,0.00013122857,0.00091924524,0.00010351816,0.0013977803,0.00094120024,0.0004484896,0.0002968677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034376627,0.0010164598,0.02962562,0.00080567756,0.0008586033,0.0009295767,0.015476992,0.0040875636,0.073203824,0.0051479978,0.24313386,0.6253701],"study_design_scores_gemma":[0.0017922008,0.00029704848,0.0045462004,0.00017180757,0.00019497763,0.0005385995,0.0010005615,0.8638231,0.06693,0.0008002931,0.059188507,0.00071666826],"about_ca_topic_score_codex":0.0015244767,"about_ca_topic_score_gemma":0.0012089203,"teacher_disagreement_score":0.85973555,"about_ca_system_score_codex":0.002135665,"about_ca_system_score_gemma":0.002483049,"threshold_uncertainty_score":0.99983776},"labels":[],"label_agreement":null},{"id":"W3210154426","doi":"10.1016/j.compbiomed.2021.104985","title":"Machine learning-based statistical analysis for early stage detection of cervical cancer","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Random forest; Artificial intelligence; Computer science; Feature selection; Machine learning; Cervical cancer; Transformation (genetics); Pattern recognition (psychology); Decision tree; Tree (set theory); Feature (linguistics); Cancer; Mathematics; Medicine","score_opus":0.019432094280282055,"score_gpt":0.3247012478427908,"score_spread":0.3052691535625088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210154426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05241785,0.00083543157,0.9452629,0.0008684809,0.00048210513,0.00007974744,0.000010562195,0.000026900794,0.000015993459],"genre_scores_gemma":[0.9779279,0.00011251351,0.021540094,0.0002862696,0.00007098293,0.000019339455,0.000019495059,0.00000340472,0.000019969031],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999097,0.00014154668,0.00022510665,0.0003212055,0.00006757663,0.00014758059],"domain_scores_gemma":[0.9991221,0.00049724017,0.000085691245,0.00015460589,0.0000876717,0.000052731568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002782386,0.000084799474,0.00029558863,0.00016408457,0.000051116047,0.0000052110686,0.0001271681,0.00008794125,0.000020019985],"category_scores_gemma":[0.00009045619,0.000072048,0.00003373031,0.0005806318,0.00016374364,0.000035640856,0.000060271865,0.00015192026,1.8195139e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029351775,0.00011297527,0.6605971,0.00022367302,0.0004494516,0.000029918527,0.0008293387,0.011873049,0.007628541,0.016734906,0.00004372036,0.30118382],"study_design_scores_gemma":[0.0013119329,0.0007187338,0.19089699,0.000032854237,0.000073392235,0.0000029986572,0.000012468015,0.8008443,0.0025910179,0.0018534391,0.0015651191,0.000096730204],"about_ca_topic_score_codex":0.0005100215,"about_ca_topic_score_gemma":0.0006767437,"teacher_disagreement_score":0.9255101,"about_ca_system_score_codex":0.00004490373,"about_ca_system_score_gemma":0.00004940754,"threshold_uncertainty_score":0.29380322},"labels":[],"label_agreement":null},{"id":"W3210191307","doi":"10.3390/curroncol28060366","title":"Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade","year":2021,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; York University; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Association Canadienne des Technologues en Radiation Médicale; Terry Fox Research Institute","keywords":"Medicine; Grading (engineering); Receiver operating characteristic; Breast cancer; Convolutional neural network; Biopsy; Digital pathology; Radiology; Breast imaging; Pathology; Artificial intelligence; Mammography; Cancer; Computer science; Internal medicine","score_opus":0.05426329752397563,"score_gpt":0.37104350113017126,"score_spread":0.31678020360619563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210191307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44164565,0.0069797076,0.5212229,0.011832822,0.011896192,0.00052315276,0.00020982593,0.00052653084,0.0051632496],"genre_scores_gemma":[0.99767196,0.00013969527,0.0019484332,0.00007827083,0.000056402012,0.000055201584,0.00001850923,0.0000100522175,0.000021472637],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99848014,0.00020577181,0.00028188503,0.0004910666,0.00021965685,0.00032147975],"domain_scores_gemma":[0.9987785,0.00017106386,0.0003328181,0.00033704934,0.00030970946,0.00007084168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019621657,0.00015050248,0.0003220713,0.00011255577,0.00007281212,0.000037920538,0.00037561348,0.000079026926,0.00003810027],"category_scores_gemma":[0.00004762116,0.00013304237,0.0000689271,0.00055676245,0.00021846313,0.00031123048,0.000246508,0.00023379241,0.0000023621722],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016595264,0.00078042556,0.4794577,0.00003644759,0.00012951785,0.0003035867,0.00021669023,0.00009942107,0.0018541674,0.0017885123,0.0015210367,0.51379585],"study_design_scores_gemma":[0.0027522848,0.00054937135,0.9429308,0.00022539131,0.00011522483,0.0016654029,0.00018692554,0.032010805,0.0009960027,0.0024017824,0.015566942,0.0005990629],"about_ca_topic_score_codex":0.000010675432,"about_ca_topic_score_gemma":0.00006356602,"teacher_disagreement_score":0.55602634,"about_ca_system_score_codex":0.0011157182,"about_ca_system_score_gemma":0.0008630741,"threshold_uncertainty_score":0.542531},"labels":[],"label_agreement":null},{"id":"W3211758690","doi":"10.1109/ius52206.2021.9593568","title":"Shift-Invariant Segmentation in Breast Ultrasound Images","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Image segmentation; Pixel; Convolutional neural network; Code (set theory); Pattern recognition (psychology); Variance (accounting); Consistency (knowledge bases); Invariant (physics); Computer vision; Mathematics","score_opus":0.009124318620724034,"score_gpt":0.24022498976378318,"score_spread":0.23110067114305916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211758690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017677719,0.000051995117,0.9704538,0.0033103903,0.0004146721,0.000064454915,0.000002132806,0.000124554,0.007900263],"genre_scores_gemma":[0.9366754,0.000024673614,0.062363796,0.00047736563,0.000053161875,0.000012402274,0.0000027907295,0.0000045861107,0.00038581272],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992862,0.00005282848,0.00012250087,0.0002566338,0.0001497495,0.00013211751],"domain_scores_gemma":[0.99958664,0.000068140434,0.00002764939,0.00025245192,0.00003439676,0.000030714433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013275252,0.000059767044,0.000060282324,0.000051308678,0.000036773705,0.0001434375,0.00017740004,0.000027612923,0.0001475479],"category_scores_gemma":[0.000012578262,0.000059470836,0.00002033696,0.00042995167,0.000012335907,0.00055380515,0.00006817935,0.000067874535,0.000059469607],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026023861,0.0004161151,0.06881512,0.000073057614,0.000056350855,0.00042835507,0.0044213645,0.001583589,0.61985636,0.110558815,0.0091388635,0.18462598],"study_design_scores_gemma":[0.000855821,0.000043425156,0.4421182,0.000034800203,0.0000053843514,0.00064299325,0.0003568756,0.0064306143,0.5310799,0.017550014,0.0005100635,0.00037193456],"about_ca_topic_score_codex":0.0001432398,"about_ca_topic_score_gemma":0.00028307093,"teacher_disagreement_score":0.9189977,"about_ca_system_score_codex":0.0001152657,"about_ca_system_score_gemma":0.00007964222,"threshold_uncertainty_score":0.24251503},"labels":[],"label_agreement":null},{"id":"W3214259318","doi":"10.1117/12.2611212","title":"Preserving dense features for Ki67 nuclei detection","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Margin (machine learning); Computer science; Artificial intelligence; Deep learning; Feature (linguistics); Key (lock); Computation; Pattern recognition (psychology); Feature extraction; Task (project management); Machine learning; Algorithm; Engineering","score_opus":0.024907146862218635,"score_gpt":0.28005723867825255,"score_spread":0.25515009181603393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214259318","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033367188,0.0002958495,0.9816816,0.0008908453,0.0065157926,0.0009748544,0.000013569675,0.00094991043,0.0053408733],"genre_scores_gemma":[0.7020006,0.00008924362,0.280614,0.00090058305,0.0012868493,0.0026549206,0.000025504462,0.00010773426,0.012320546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802655,0.00009656258,0.00024889398,0.0009219015,0.0003991015,0.00030699756],"domain_scores_gemma":[0.9981371,0.00015910743,0.00021045867,0.001301263,0.00012236129,0.00006968898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042111825,0.00024275262,0.00021963796,0.00020179129,0.00036701025,0.0003914859,0.0017193862,0.00023068316,0.00014759068],"category_scores_gemma":[0.00008760162,0.00025738653,0.00021430141,0.00023382637,0.000018203047,0.00027850727,0.0039039375,0.00070618326,0.000008667557],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031741356,0.00016165889,0.00007656686,0.0012566673,0.00035741532,0.000021451317,0.0031411238,0.050885316,0.02092927,0.009648996,0.06481588,0.84838825],"study_design_scores_gemma":[0.0007780991,0.00043826998,0.0021969127,0.00008159001,0.000077872224,0.000076787124,0.00018622733,0.54869074,0.14966002,0.08990192,0.2064339,0.0014776863],"about_ca_topic_score_codex":0.0004352538,"about_ca_topic_score_gemma":0.00024330123,"teacher_disagreement_score":0.84691054,"about_ca_system_score_codex":0.0005223644,"about_ca_system_score_gemma":0.00013837984,"threshold_uncertainty_score":0.99998784},"labels":[],"label_agreement":null},{"id":"W3215499360","doi":"10.32920/ryerson.14663766.v1","title":"Towards Improved Medical Image Segmentation Using Deep Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Medical imaging; Generalizability theory; Convolutional neural network; Deep learning; Modalities; Modular design; Machine learning; Image segmentation; Benchmark (surveying); Pattern recognition (psychology); Contouring; Modality (human–computer interaction); Market segmentation","score_opus":0.021547472727859014,"score_gpt":0.30546415616715733,"score_spread":0.2839166834392983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215499360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018257508,0.00017993039,0.9759597,0.0004987267,0.0024934271,0.00019178458,3.2116586e-7,0.00041907237,0.0019995288],"genre_scores_gemma":[0.19617733,0.00013015886,0.80263764,0.00035266852,0.00043240315,0.000043695072,0.000019861756,0.000029345034,0.00017690181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976435,0.00019342253,0.0003515656,0.000789538,0.0007520957,0.00026992758],"domain_scores_gemma":[0.9988313,0.000044932392,0.0002194324,0.0005553956,0.00020988466,0.00013908655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057148555,0.00022254737,0.0002478712,0.000118246055,0.00013707526,0.0006253886,0.000835096,0.0003533329,0.00043449254],"category_scores_gemma":[0.00016717942,0.00022964906,0.0001301799,0.0002514117,0.000043076772,0.00047219085,0.0025654144,0.0010366291,0.000011984289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006369682,0.000046925947,0.00012807093,0.00022453985,0.00010103955,0.000080176826,0.0021214336,0.006461604,0.0323292,0.00025563512,0.00005301341,0.958192],"study_design_scores_gemma":[0.00017511091,0.000027193022,0.00018006368,0.000081751736,0.000014450755,0.00004255132,0.00020373863,0.9767369,0.021751352,0.00043221726,0.000092524046,0.00026216207],"about_ca_topic_score_codex":0.0008223862,"about_ca_topic_score_gemma":0.000110674555,"teacher_disagreement_score":0.9702753,"about_ca_system_score_codex":0.0005273765,"about_ca_system_score_gemma":0.00075053563,"threshold_uncertainty_score":0.9364817},"labels":[],"label_agreement":null},{"id":"W3216069892","doi":"10.1111/biom.13611","title":"Supervised Two-Dimensional Functional Principal Component Analysis with Time-to-Event Outcomes and Mammogram Imaging Data","year":2021,"lang":"en","type":"article","venue":"Biometrics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; Simon Fraser University","funders":"National Cancer Institute; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Principal component analysis; Breast cancer; Mammography; Censoring (clinical trials); Computer science; Artificial intelligence; Population; Data set; Medicine; Event (particle physics); Pattern recognition (psychology); Data mining; Machine learning; Statistics; Cancer; Mathematics; Pathology; Internal medicine","score_opus":0.03557363428132682,"score_gpt":0.27811177480463467,"score_spread":0.24253814052330785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216069892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16315198,0.00045843917,0.83300024,0.0024252161,0.0004204194,0.00017927038,0.00007531931,0.00017583664,0.000113272676],"genre_scores_gemma":[0.7658154,0.000008147907,0.232133,0.0009894454,0.00010917882,0.000018184752,0.0003118591,0.000022354592,0.0005924305],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772227,0.00007061693,0.0002525212,0.00082787813,0.00084933377,0.00027737982],"domain_scores_gemma":[0.9981346,0.00022039415,0.00008471104,0.0011021062,0.00025234974,0.00020583764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046956737,0.00017339105,0.00026453807,0.0016486287,0.0001623638,0.00026044346,0.000560251,0.00003167456,0.0001105021],"category_scores_gemma":[0.00009266285,0.00014965437,0.00006680948,0.010906326,0.00004669391,0.00038087356,0.0013482091,0.00010664241,0.00007008226],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001120782,0.0008526732,0.548186,0.000056888253,0.0024498971,0.0003337135,0.00016998984,0.028425694,0.007391555,0.0005748289,0.005397693,0.40604898],"study_design_scores_gemma":[0.00088779774,0.00006873774,0.40755278,0.000009785799,0.00022493087,0.00007804562,0.000010516468,0.58039784,0.0006979465,0.000033208216,0.009690989,0.00034743696],"about_ca_topic_score_codex":0.00005876692,"about_ca_topic_score_gemma":0.00002345131,"teacher_disagreement_score":0.6026634,"about_ca_system_score_codex":0.00014624723,"about_ca_system_score_gemma":0.0001506672,"threshold_uncertainty_score":0.6102728},"labels":[],"label_agreement":null},{"id":"W3216211209","doi":"10.1016/j.cjca.2021.11.008","title":"The Role of Machine Learning in Cardiovascular Pathology","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Medicine; Induced pluripotent stem cell; Artificial intelligence; Medical diagnosis; Machine learning; Quality (philosophy); Pathology; Clinical Practice; Bioinformatics; Computer science; Data science; Medical physics","score_opus":0.018054438285811266,"score_gpt":0.24761108578734692,"score_spread":0.22955664750153565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216211209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022198753,0.9825005,0.014692903,0.00004990924,0.0015678572,0.00010309889,0.000004844925,0.0000038721446,0.0010748048],"genre_scores_gemma":[0.0012399002,0.997901,0.00029054613,0.000008706634,0.0005098929,0.0000085260435,0.000002051576,0.00001845717,0.000020897898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99645084,0.001931612,0.00080415927,0.00025343383,0.00017126628,0.00038866594],"domain_scores_gemma":[0.99800164,0.00036971644,0.00058432604,0.0006143099,0.00023590653,0.00019411992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021222525,0.00020163512,0.0022459575,0.0005098875,0.00010583743,0.000037516733,0.0012342659,0.00033500273,0.000002031329],"category_scores_gemma":[0.0003419294,0.0001495004,0.0013623921,0.0005523225,0.00016169746,0.00007751271,0.000087531946,0.0012150208,0.0000029918824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.3163615e-7,2.4170583e-7,0.000094572555,0.0001106798,0.00040256805,0.0005290649,0.000043619173,0.0014196247,1.7020052e-7,0.0004739522,0.000075265336,0.9968497],"study_design_scores_gemma":[0.000084358006,0.000078722034,0.000022501798,0.0006734041,0.00017950776,0.0051740087,0.000022306967,0.00005435987,0.0000012199993,0.000283819,0.99331117,0.00011461724],"about_ca_topic_score_codex":0.000738123,"about_ca_topic_score_gemma":0.002002781,"teacher_disagreement_score":0.9967351,"about_ca_system_score_codex":0.00043574304,"about_ca_system_score_gemma":0.0042823837,"threshold_uncertainty_score":0.75967646},"labels":[],"label_agreement":null},{"id":"W3216232448","doi":"10.1117/12.2622893","title":"Breast cancer diagnosis using SE-DNI model","year":2021,"lang":"en","type":"article","venue":"Second IYSF Academic Symposium on Artificial Intelligence and Computer Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Breast cancer; Cancer; Computer science; Oncology; Medicine; Internal medicine","score_opus":0.04557477430238857,"score_gpt":0.2837361799734323,"score_spread":0.23816140567104374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216232448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10280264,0.00054521154,0.8934191,0.0010749074,0.0016869042,0.00012790257,0.000022234708,0.00025432452,0.00006678801],"genre_scores_gemma":[0.96755326,0.0018680849,0.027535649,0.0014880325,0.001309057,0.000120573495,0.0000029525074,0.00005703161,0.00006534446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785995,0.000037200578,0.00049217674,0.0008121416,0.00029356102,0.0005049455],"domain_scores_gemma":[0.9990252,0.00012477649,0.00010356056,0.0004244093,0.00012529988,0.00019671743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019864648,0.00032090087,0.000290582,0.0003046574,0.0001678033,0.00022877593,0.0005442108,0.00023561843,0.000075625896],"category_scores_gemma":[0.000006402588,0.0003541864,0.000095383555,0.00079551217,0.000042034422,0.0006979898,0.00035357242,0.00066968903,0.000023374618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008922537,0.000033505636,0.00012403175,0.000056541772,0.00004194818,0.000019343317,0.00074811355,0.8557893,0.01485702,0.014772086,0.0002495623,0.11329959],"study_design_scores_gemma":[0.000032598724,0.00003085632,0.00006405569,0.00015585053,0.000012176053,0.00014909355,0.000019911455,0.86443007,0.13252178,0.0017219558,0.00050867914,0.00035298849],"about_ca_topic_score_codex":0.000031665822,"about_ca_topic_score_gemma":0.000010661311,"teacher_disagreement_score":0.86588347,"about_ca_system_score_codex":0.00015913734,"about_ca_system_score_gemma":0.000114737406,"threshold_uncertainty_score":0.999891},"labels":[],"label_agreement":null},{"id":"W3217733771","doi":"10.1142/9789811239014_0002","title":"Intensive Survey on Peripheral Blood Smear Analysis Using Deep Learning","year":2021,"lang":"en","type":"book-chapter","venue":"Series on language processing, pattern recognition, and intelligent systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Peripheral blood; Medicine; Peripheral; Internal medicine","score_opus":0.042900420511525934,"score_gpt":0.26307256702431625,"score_spread":0.22017214651279032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217733771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04793669,0.035725422,0.8852695,0.00009412317,0.004357624,0.0015320673,0.0004670109,0.0010104418,0.023607114],"genre_scores_gemma":[0.86377734,0.0042302343,0.0014533227,0.0015034139,0.002040939,0.00012446698,0.002502493,0.00040132715,0.12396645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666727,0.0002735972,0.00075781025,0.0012512569,0.00064100727,0.00040908996],"domain_scores_gemma":[0.9970316,0.00011923053,0.00084187917,0.0005304155,0.001312723,0.00016412916],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004952592,0.000655217,0.000886813,0.00061635143,0.00043256787,0.0009978823,0.00039298253,0.00040745363,0.00026589105],"category_scores_gemma":[0.00011706748,0.0006423811,0.00025236426,0.0003437925,0.00013200208,0.00044029314,0.00015313338,0.0007808667,0.00006097558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023339293,0.0001764268,0.0028432542,0.0023634322,0.004370836,0.0007219064,0.029352613,0.002980549,0.00018955569,0.00029710264,0.00015849943,0.9563124],"study_design_scores_gemma":[0.0062051155,0.01803691,0.0055546216,0.06871333,0.016925143,0.005693002,0.08515386,0.6758814,0.03486828,0.003290614,0.05009315,0.029584588],"about_ca_topic_score_codex":0.00090388657,"about_ca_topic_score_gemma":0.0009969657,"teacher_disagreement_score":0.92672783,"about_ca_system_score_codex":0.00023759395,"about_ca_system_score_gemma":0.000117062475,"threshold_uncertainty_score":0.99960274},"labels":[],"label_agreement":null},{"id":"W32350786","doi":"10.1007/s11548-020-02158-3","title":"Training: Institute of Diplomacy and Foreign Relations","year":2009,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Diplomacy; Political science; International relations; Foreign relations; Foreign policy; Law; Politics","score_opus":0.036621040750004545,"score_gpt":0.28347898575816194,"score_spread":0.2468579450081574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32350786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22920431,0.0005401676,0.76538426,0.0025394948,0.0017343662,0.000030486004,0.0000011040139,0.000018247281,0.0005475479],"genre_scores_gemma":[0.96873325,0.00016571664,0.030355493,0.00040655813,0.0003249731,4.9359056e-7,0.0000012000137,0.0000024357544,0.000009864068],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990287,0.00008231667,0.00047964888,0.00013076983,0.00018183264,0.0000967438],"domain_scores_gemma":[0.9987964,0.00039276708,0.00040602518,0.00009208165,0.00024947387,0.00006326035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045463254,0.00008382166,0.0002623298,0.00036841174,0.000049805767,0.000040346105,0.0002736319,0.00007318889,0.0000028002614],"category_scores_gemma":[0.000057487778,0.0000737442,0.00009190471,0.000114873954,0.000117307645,0.0006111364,0.000043158772,0.00016473011,3.2524068e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112213784,0.00008094528,0.019380009,0.0000058757287,0.00034570324,0.00020014703,0.000902079,0.0007225862,0.00057291327,0.056294132,0.0022424953,0.9191409],"study_design_scores_gemma":[0.0011365375,0.00051890017,0.87245756,0.00022512874,0.00003943836,0.015832227,0.000033949396,0.030813571,0.0003307082,0.067334734,0.01100419,0.00027302201],"about_ca_topic_score_codex":0.0000013756227,"about_ca_topic_score_gemma":5.021457e-7,"teacher_disagreement_score":0.9188679,"about_ca_system_score_codex":0.00003351405,"about_ca_system_score_gemma":0.00011812301,"threshold_uncertainty_score":0.30072013},"labels":[],"label_agreement":null},{"id":"W325298687","doi":"","title":"Image Analysis in Support of Computer-Assisted Cervical Cancer Screening","year":2013,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cervical cancer; Medicine; Population; Quarter (Canadian coin); Cancer; Disease; Environmental health; Geography; Pathology; Internal medicine","score_opus":0.02223391184587433,"score_gpt":0.2804927783751217,"score_spread":0.2582588665292474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W325298687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057500843,0.00007997003,0.9281806,0.011786777,0.00037360346,0.0005286233,0.000202262,0.00046925136,0.00087809254],"genre_scores_gemma":[0.5682344,0.000029123645,0.43076548,0.00027201188,0.000041519383,0.00026507818,0.0003135212,0.000013317292,0.00006553832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974512,0.000047309408,0.0009066686,0.000750269,0.0004544548,0.00039013737],"domain_scores_gemma":[0.99662185,0.000036180707,0.00066163257,0.0017500751,0.0008209622,0.00010931462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041000056,0.0002324727,0.0005117656,0.0024383331,0.000089021436,0.000095426854,0.001987878,0.0002400106,0.00027510457],"category_scores_gemma":[0.000162272,0.00023851525,0.00013433944,0.006348919,0.00040226863,0.0020267433,0.0010960974,0.00036599213,0.000026030455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005419786,0.0015445946,0.17273083,0.00047247123,0.00130352,0.000029962517,0.00026501593,0.0061220317,0.013920147,0.048538577,0.050984822,0.70403385],"study_design_scores_gemma":[0.0016686177,0.0002395558,0.21192147,0.0001335603,0.00023449182,0.0000148911295,0.00005106994,0.71551764,0.023672327,0.00040808096,0.0453797,0.0007586069],"about_ca_topic_score_codex":0.0032097565,"about_ca_topic_score_gemma":0.0006604889,"teacher_disagreement_score":0.7093956,"about_ca_system_score_codex":0.00015409423,"about_ca_system_score_gemma":0.00020924654,"threshold_uncertainty_score":0.97263694},"labels":[],"label_agreement":null},{"id":"W4200049440","doi":"10.3233/jifs-219221","title":"Ensemble-based deep meta learning for medical image segmentation","year":2021,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Segmentation; Image segmentation; Domain (mathematical analysis); Machine learning; Image (mathematics); Noise (video); Ensemble learning; Set (abstract data type); Pattern recognition (psychology)","score_opus":0.03363647031325565,"score_gpt":0.3024143267836178,"score_spread":0.2687778564703621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200049440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017084866,0.003320802,0.9899797,0.0011134746,0.0032309992,0.00020576689,7.6406195e-7,0.000038512593,0.00040152686],"genre_scores_gemma":[0.91924447,0.00026724188,0.078344874,0.00039588514,0.0012123348,0.00006489432,0.0000052141477,0.000035125868,0.00042997254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972298,0.0003550698,0.00090786105,0.00023944839,0.0010298842,0.00023791041],"domain_scores_gemma":[0.99724746,0.00052452635,0.00074469455,0.00024560967,0.0010445645,0.00019313206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019534053,0.00015231398,0.00041681656,0.00018729325,0.00012503957,0.00029797174,0.0005250352,0.0001048015,0.000055550394],"category_scores_gemma":[0.0005067533,0.0001251158,0.0003873844,0.0003504428,0.000025581647,0.00046240512,0.000061123355,0.0003398335,0.000019510755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006697473,0.0011585468,0.0012925934,0.0024361843,0.0071554007,0.0018871299,0.0055813296,0.23335907,0.16169252,0.013073723,0.020612238,0.55108154],"study_design_scores_gemma":[0.0012856536,0.0011343008,0.0000407091,0.00041689235,0.0004931333,0.0016958722,0.0013780498,0.61831427,0.34011114,0.0010613106,0.033663787,0.00040485428],"about_ca_topic_score_codex":0.000016625158,"about_ca_topic_score_gemma":0.000014767617,"teacher_disagreement_score":0.91753596,"about_ca_system_score_codex":0.00030446626,"about_ca_system_score_gemma":0.00048601642,"threshold_uncertainty_score":0.5102074},"labels":[],"label_agreement":null},{"id":"W4200051340","doi":"10.3390/biology10121347","title":"BreastNet18: A High Accuracy Fine-Tuned VGG16 Model Evaluated Using Ablation Study for Diagnosing Breast Cancer from Enhanced Mammography Images","year":2021,"lang":"en","type":"article","venue":"Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Mammography; Artificial intelligence; Breast cancer; Overfitting; Robustness (evolution); Computer science; Pattern recognition (psychology); Image processing; Cancer; Biology; Image (mathematics); Artificial neural network","score_opus":0.04126206466087099,"score_gpt":0.3446213915415939,"score_spread":0.30335932688072287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200051340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48543337,0.00027939497,0.51251066,0.00047869957,0.0006787738,0.00037048451,0.00013630539,0.00010667192,0.000005649634],"genre_scores_gemma":[0.967154,0.000043843833,0.03195749,0.00017213795,0.0003024725,0.0002832311,0.00005165213,0.000021389254,0.000013738356],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980259,0.0002428329,0.00035231956,0.00084132235,0.00016032849,0.00037727828],"domain_scores_gemma":[0.9982563,0.0004261586,0.00024724664,0.0005377764,0.000465861,0.00006665892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023484668,0.00022310567,0.00031942292,0.0001413032,0.00022725621,0.00011100807,0.00039492254,0.00014057159,0.000037566744],"category_scores_gemma":[0.00009905041,0.00022030831,0.00010288064,0.00058998825,0.00005379406,0.00036385283,0.00021515257,0.0001228737,0.0000030767467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025920288,0.00044185054,0.012094938,0.00002439086,0.0003351231,0.000009268518,0.0011717097,0.044990174,0.6604637,0.00029266602,0.00025350254,0.2796635],"study_design_scores_gemma":[0.0020806286,0.000187176,0.046055112,0.000059721355,0.00011562146,0.000017209159,0.000076982724,0.8597745,0.0831654,0.007987356,0.000043096494,0.00043722318],"about_ca_topic_score_codex":0.0027508007,"about_ca_topic_score_gemma":0.00080680824,"teacher_disagreement_score":0.8147843,"about_ca_system_score_codex":0.00019235564,"about_ca_system_score_gemma":0.00030265984,"threshold_uncertainty_score":0.8983912},"labels":[],"label_agreement":null},{"id":"W4200059501","doi":"10.34067/kid.0005102021","title":"Explainable Biomarkers for Automated Glomerular and Patient-Level Disease Classification","year":2021,"lang":"en","type":"article","venue":"Kidney360","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto General Hospital; University of Toronto; University Health Network; Toronto Metropolitan University","funders":"Canadian Institutes of Health Research; Alport Syndrome Foundation; Faculty of Arts, Ryerson University","keywords":"Biomarker; Renal pathology; Glomerular basement membrane; Tuft; Pathology; Artificial intelligence; Medicine; Pattern recognition (psychology); Computer science; Internal medicine; Glomerulonephritis; Kidney; Biology; Materials science","score_opus":0.03143347048122483,"score_gpt":0.26478248263542425,"score_spread":0.23334901215419943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200059501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041024573,0.0013824451,0.9406331,0.012345729,0.0016268872,0.0007236781,0.00012067934,0.0013339659,0.0008089078],"genre_scores_gemma":[0.9132324,0.00005790017,0.084863566,0.0011256444,0.00006016549,0.00024854598,0.00005115256,0.000021782615,0.00033883387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989843,0.000046488447,0.00015912134,0.00042546968,0.00017253542,0.00021208692],"domain_scores_gemma":[0.9990528,0.00005487855,0.00007450878,0.00043222698,0.00015890987,0.00022664855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009830444,0.00010160161,0.00009137279,0.00006573756,0.00017909575,0.00013987668,0.00016911316,0.00004759014,0.000009444],"category_scores_gemma":[0.0002108564,0.00010828151,0.000042492815,0.00036398036,0.000034024433,0.00041646833,0.000102938066,0.000040783227,0.00001068278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022076831,0.00042785672,0.0043123593,0.00065551593,0.0002787373,0.0001301977,0.0022632407,0.00019651318,0.07240077,0.0390795,0.23694457,0.64308995],"study_design_scores_gemma":[0.0009981238,0.00010835141,0.028078329,0.000064254324,0.00003249002,0.000021315034,0.00023814126,0.8067406,0.019598002,0.00519641,0.13853148,0.00039253038],"about_ca_topic_score_codex":0.000010475885,"about_ca_topic_score_gemma":0.0000023547773,"teacher_disagreement_score":0.8722078,"about_ca_system_score_codex":0.00010648487,"about_ca_system_score_gemma":0.00023588668,"threshold_uncertainty_score":0.44155917},"labels":[],"label_agreement":null},{"id":"W4200069325","doi":"10.21203/rs.3.rs-1120682/v1","title":"Transferability of Deep Learning Models for Focus Quality Assessment in Digital Pathology","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Waterloo; University of Toronto","funders":"","keywords":"Computer science; Deep learning; Convolutional neural network; Focus (optics); Artificial intelligence; Scalability; Transfer of learning; Machine learning; Generalizability theory; Transferability; Workflow; Digital pathology; False positive paradox; Data mining; Pattern recognition (psychology)","score_opus":0.1592189136475648,"score_gpt":0.44613665489825993,"score_spread":0.28691774125069514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200069325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17849846,0.00045682208,0.81860465,0.00046648394,0.00019037451,0.0010826179,0.000038352046,0.00006282612,0.0005994129],"genre_scores_gemma":[0.9829169,0.00014005374,0.016103573,0.0000037584866,0.000053936063,0.00070459844,0.00003803838,0.000020052308,0.00001909669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99505144,0.0013110328,0.00070096814,0.0011863582,0.0011321554,0.00061803247],"domain_scores_gemma":[0.9959425,0.0014222774,0.00013050427,0.0011848876,0.00121378,0.00010610616],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005736684,0.00020611114,0.0005928796,0.0003710284,0.00012221218,0.00031898223,0.0011217172,0.00039160065,0.000011645097],"category_scores_gemma":[0.000695208,0.000222216,0.0002712189,0.0005970636,0.00016917556,0.0005490669,0.0014950921,0.0023042106,8.4651936e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016132994,0.00078372285,0.012506606,0.0047863177,0.00007569422,0.00006105173,0.008698768,0.19234084,0.0009874898,0.02156683,0.000008974885,0.75802237],"study_design_scores_gemma":[0.000793392,0.00069330476,0.021295376,0.0004730566,0.0000044043386,0.000005912101,0.0011733965,0.7329648,0.002337972,0.23982696,0.000048265512,0.0003831465],"about_ca_topic_score_codex":0.00046743063,"about_ca_topic_score_gemma":0.000611533,"teacher_disagreement_score":0.80441844,"about_ca_system_score_codex":0.00094999466,"about_ca_system_score_gemma":0.0010191584,"threshold_uncertainty_score":0.9999975},"labels":[],"label_agreement":null},{"id":"W4200109783","doi":"10.1097/md.0000000000028289","title":"Accuracy of ultrasonic artificial intelligence in diagnosing benign and malignant breast diseases","year":2021,"lang":"en","type":"article","venue":"Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Liaoning Province","keywords":"Mammography; MEDLINE; Ultrasonography; Ultrasonic sensor; Breast disease; Diagnostic accuracy","score_opus":0.022744288866064867,"score_gpt":0.2865051182610912,"score_spread":0.2637608293950263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200109783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40106475,0.008935062,0.5751206,0.013335111,0.0010574701,0.00020915516,0.000008681395,0.000078625024,0.00019050289],"genre_scores_gemma":[0.9977113,0.00056458794,0.0014427522,0.00013147337,0.00013023755,0.000007727993,0.0000016149384,0.0000043071163,0.0000060075954],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99904174,0.000058450216,0.0002631621,0.00028191897,0.000208479,0.00014627396],"domain_scores_gemma":[0.9990599,0.00044492938,0.00008463981,0.0002807892,0.000066556655,0.00006314631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018501302,0.000078639845,0.00017268173,0.000090545436,0.000033405624,0.000017377595,0.0001837476,0.000026716714,0.000040175983],"category_scores_gemma":[0.00039638457,0.00006697737,0.000016901675,0.00054292486,0.00011241367,0.00019315955,0.00008830628,0.00008302009,0.0000019498077],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014119487,0.00007926036,0.011324199,0.000066640096,0.000007648761,0.000101531885,0.0013047328,0.00012263293,0.010655426,0.009054405,0.00008861353,0.9671808],"study_design_scores_gemma":[0.0011005228,0.0009005933,0.4723341,0.0041794917,0.00010518023,0.0012439504,0.0030530393,0.108407706,0.31007987,0.09639625,0.001322448,0.0008768543],"about_ca_topic_score_codex":0.00015746772,"about_ca_topic_score_gemma":0.000117311014,"teacher_disagreement_score":0.96630394,"about_ca_system_score_codex":0.000044099797,"about_ca_system_score_gemma":0.000086912594,"threshold_uncertainty_score":0.2731258},"labels":[],"label_agreement":null},{"id":"W4200124817","doi":"10.1109/bibe52308.2021.9635177","title":"Learning Similarity via Subjective Evaluations and Deep Features of Histopathology Images","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Artificial intelligence; Computer science; Pattern recognition (psychology); Inference; Euclidean distance; Fuzzy logic; Image (mathematics); Computer vision; Machine learning; Data mining","score_opus":0.018908460354306086,"score_gpt":0.2698948960763391,"score_spread":0.250986435722033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200124817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037703972,0.00029148004,0.951584,0.0013399501,0.0013095202,0.00014422373,0.00002764966,0.00007444733,0.0075247996],"genre_scores_gemma":[0.9623469,0.0007816371,0.03654562,0.0000766751,0.000053490137,0.000010477743,0.000015493386,0.0000063548064,0.0001633216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990992,0.000031942884,0.00026531972,0.0001994845,0.00026747893,0.00013657912],"domain_scores_gemma":[0.9991465,0.00008774636,0.00013577242,0.00016448849,0.00040971072,0.00005576101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020879348,0.00013690576,0.00016410941,0.00019568109,0.0000888678,0.00014272287,0.00020680563,0.00007630763,0.000032239237],"category_scores_gemma":[0.000108183245,0.00013563942,0.000038079022,0.00019388406,0.0000698391,0.00034703687,0.00013313873,0.00024154394,0.0000034849816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061709456,0.00019527545,0.0025412582,0.00040023003,0.0002785338,0.00004689232,0.00869137,0.0131811565,0.10938953,0.15847515,0.00026044942,0.7064785],"study_design_scores_gemma":[0.00036537444,0.00022974142,0.014537185,0.00010200162,0.000017100794,0.0001679545,0.00044945203,0.95042104,0.031233687,0.0017995613,0.00042666827,0.00025024274],"about_ca_topic_score_codex":0.000017190328,"about_ca_topic_score_gemma":0.000015510755,"teacher_disagreement_score":0.9372399,"about_ca_system_score_codex":0.00006892518,"about_ca_system_score_gemma":0.000072467505,"threshold_uncertainty_score":0.5531215},"labels":[],"label_agreement":null},{"id":"W4200332329","doi":"10.1109/embc46164.2021.9630248","title":"Semi-Supervised Segmentation of Renal Pathology: An Alternative to Manual Segmentation and Input to Deep Learning Training","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Computer science; Artificial intelligence; Biopsy; Pathognomonic; Image segmentation; Kidney; Kidney disease; Pathology; Pattern recognition (psychology); Renal biopsy; Radiology; Medicine; Disease; Internal medicine","score_opus":0.043333057059385734,"score_gpt":0.32222756053787466,"score_spread":0.27889450347848893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200332329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5302782,0.000038452014,0.4671071,0.001507984,0.000859466,0.00012771296,0.000012710237,0.000019357787,0.00004904648],"genre_scores_gemma":[0.93591887,0.00014271557,0.06308437,0.00039370806,0.00024094863,0.00003909117,0.00004581588,0.000011944504,0.00012254503],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845034,0.00017476654,0.00044729942,0.00043897072,0.000278011,0.00021061295],"domain_scores_gemma":[0.9988477,0.000188974,0.00018017081,0.0002294341,0.00047035803,0.00008333755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062669016,0.0001765888,0.00029804665,0.00019200878,0.000054486074,0.000021414537,0.0005471219,0.00011523221,0.000046858844],"category_scores_gemma":[0.00031024014,0.00015771076,0.000064198204,0.0005449128,0.00011248054,0.00027960504,0.0002350149,0.00033321694,0.0000017794829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003655974,0.000045544082,0.002997624,0.000039218252,0.00014055813,0.000003650956,0.06705869,0.10059994,0.8042197,0.0012810358,0.00021478657,0.02336266],"study_design_scores_gemma":[0.004033567,0.0018007117,0.028454354,0.0013086795,0.000086089494,0.00017188051,0.02530993,0.7350921,0.19826104,0.0021764222,0.0023051093,0.0010001251],"about_ca_topic_score_codex":0.00011069217,"about_ca_topic_score_gemma":0.00015010082,"teacher_disagreement_score":0.63449216,"about_ca_system_score_codex":0.0001292785,"about_ca_system_score_gemma":0.000077992634,"threshold_uncertainty_score":0.64312583},"labels":[],"label_agreement":null},{"id":"W4200369541","doi":"10.1109/embc46164.2021.9630347","title":"Analysis of Language Embeddings for Classification of Unstructured Pathology Reports","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Focus (optics); Digital pathology; Embedding; Word (group theory); Word embedding; Term (time)","score_opus":0.031281516883284906,"score_gpt":0.32062431225204574,"score_spread":0.28934279536876084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200369541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5101629,0.00014465756,0.48608238,0.001492373,0.0018291521,0.000117245334,0.000058018064,0.000017488488,0.0000957818],"genre_scores_gemma":[0.9798226,0.0001004153,0.019661084,0.00006119498,0.0001070705,0.000018811645,0.00007491278,0.000006545246,0.00014736809],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862903,0.000061881445,0.0006221142,0.00033942176,0.00020185154,0.00014571779],"domain_scores_gemma":[0.9979775,0.0002531782,0.0005093334,0.0004710386,0.0007628599,0.000026110201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005649693,0.00012795634,0.00043564045,0.00023357163,0.000020420943,0.000005649411,0.0005710499,0.00016466291,0.00005499567],"category_scores_gemma":[0.00058135163,0.000104185325,0.0002374476,0.001041621,0.00019840924,0.000097019845,0.00012144253,0.00019255836,1.7323123e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020116298,0.000058338093,0.01123938,0.000100272744,0.00097006914,0.00000297355,0.009215806,0.014308495,0.95230126,0.007978613,0.0012650319,0.002539623],"study_design_scores_gemma":[0.0017532511,0.00031831613,0.11642268,0.00055096566,0.0006061296,0.000117247466,0.0036506264,0.7436747,0.12388639,0.003968509,0.0044752117,0.00057600765],"about_ca_topic_score_codex":0.00010089427,"about_ca_topic_score_gemma":0.00010742621,"teacher_disagreement_score":0.8284149,"about_ca_system_score_codex":0.00007130135,"about_ca_system_score_gemma":0.00010900783,"threshold_uncertainty_score":0.42485544},"labels":[],"label_agreement":null},{"id":"W4200501894","doi":"10.21203/rs.3.rs-943804/v1","title":"Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; McMaster University; University of Waterloo","funders":"","keywords":"Digital pathology; Computer science; Demographics; Artificial intelligence; Deep learning; Scope (computer science); Machine learning; Data science; Pattern recognition (psychology); Demography","score_opus":0.07956605645229957,"score_gpt":0.3862819758299171,"score_spread":0.3067159193776175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200501894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011134947,0.004315793,0.9778125,0.0031441494,0.0012287083,0.0014276978,0.00031975846,0.00024631634,0.00037008643],"genre_scores_gemma":[0.9918871,0.0011832217,0.0044605667,0.0001674144,0.0009418799,0.00024307136,0.0009819929,0.00004637518,0.00008838312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927662,0.0020275994,0.00056517794,0.0015051692,0.0023436076,0.0007922595],"domain_scores_gemma":[0.99061775,0.0013774098,0.00028604767,0.006024673,0.001512894,0.00018121889],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0047114915,0.000315307,0.0004304491,0.00044132356,0.00043105514,0.0010144336,0.00453562,0.00042800925,0.00014002925],"category_scores_gemma":[0.00057501,0.00025919446,0.00019671817,0.0016889722,0.00038293694,0.0007569661,0.010202779,0.0025486508,0.000026468862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050284085,0.0009760747,0.011977533,0.0050739716,0.00089157466,0.0006006107,0.005372237,0.52588487,0.005694402,0.0008120914,0.11034514,0.33186862],"study_design_scores_gemma":[0.00037550653,0.00021146252,0.018858464,0.0011342753,0.000025817335,0.000011211294,0.00021327157,0.97367555,0.003360288,0.00078483316,0.0010458435,0.00030348415],"about_ca_topic_score_codex":0.0009533852,"about_ca_topic_score_gemma":0.00023790632,"teacher_disagreement_score":0.98075217,"about_ca_system_score_codex":0.00038539202,"about_ca_system_score_gemma":0.00096241006,"threshold_uncertainty_score":0.99998605},"labels":[],"label_agreement":null},{"id":"W4205389262","doi":"10.2196/27394","title":"Convolutional Neural Network–Based Automatic Classification of Colorectal and Prostate Tumor Biopsies Using Multispectral Imagery: System Development Study","year":2021,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Convolutional neural network; Multispectral image; Computer science; Artificial intelligence; Prostate; Medicine; Internal medicine","score_opus":0.015918019955075857,"score_gpt":0.24666524225967407,"score_spread":0.2307472223045982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205389262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94374853,0.00008657584,0.055080906,0.00018638528,0.00016485548,0.0005122965,0.0000054145867,0.00020398507,0.00001103835],"genre_scores_gemma":[0.8354312,0.000003115776,0.16448982,0.000018218392,0.000008544251,0.00003870802,0.0000041675194,0.000004565678,0.0000016602156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988698,0.00003848093,0.00048244357,0.00021111885,0.0001695086,0.00022864237],"domain_scores_gemma":[0.999291,0.000041516058,0.00030837845,0.00021296206,0.00010703041,0.000039081355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021472722,0.0001400605,0.00022945223,0.0001636517,0.0001903012,0.000083739986,0.00015902687,0.00011060866,8.549729e-7],"category_scores_gemma":[0.000016551076,0.00012663551,0.00002127706,0.000472369,0.00018939601,0.00023310307,0.00022382184,0.00013567823,0.0000010245884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030978874,0.0018208277,0.12934697,0.00742872,0.0008192907,0.0002763612,0.020659871,0.006486621,0.26191038,0.04466527,0.0002928378,0.5259831],"study_design_scores_gemma":[0.00053228595,0.0001990293,0.037255503,0.00006274844,0.000009814182,0.00019874121,0.0013696854,0.94433993,0.015841236,0.000029523044,0.000024512548,0.00013699151],"about_ca_topic_score_codex":0.00000597286,"about_ca_topic_score_gemma":0.00001507955,"teacher_disagreement_score":0.93785334,"about_ca_system_score_codex":0.00012083167,"about_ca_system_score_gemma":0.00019639374,"threshold_uncertainty_score":0.5164046},"labels":[],"label_agreement":null},{"id":"W4205428558","doi":"10.1016/j.ijmedinf.2021.104669","title":"Deep transfer learning based model for colorectal cancer histopathology segmentation: A comparative study of deep pre-trained models","year":2021,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Deep learning; Segmentation; Artificial intelligence; Computer science; Convolutional neural network; Encoder; Transfer of learning; Pattern recognition (psychology); Colorectal cancer; Histopathology; Machine learning; Cancer; Medicine; Pathology; Internal medicine","score_opus":0.043802240543229364,"score_gpt":0.3525245725941451,"score_spread":0.30872233205091576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205428558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19898476,0.00006495508,0.7994159,0.00061304437,0.0006988874,0.00014941643,0.0000037082675,0.000012147587,0.000057184523],"genre_scores_gemma":[0.944091,0.000034916826,0.055362333,0.0003508853,0.000104376595,0.000034608034,0.000004761377,0.0000054604434,0.000011650446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971176,0.00009937622,0.001017607,0.00009097299,0.00154155,0.0001328937],"domain_scores_gemma":[0.9976427,0.00028012533,0.00044573363,0.00008535225,0.0014343262,0.0001117562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000695053,0.0001108842,0.0002982263,0.0001747427,0.00005540575,0.00005270986,0.00078390376,0.000091611444,0.00004620403],"category_scores_gemma":[0.000118847696,0.00009951143,0.00011538051,0.00015550351,0.000062080464,0.00073276315,0.000076983764,0.0003396327,4.3546734e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001778603,0.00028845284,0.00010080178,0.000027911401,0.0001301455,0.000020103911,0.043054294,0.94115376,0.0001966965,0.00073994964,0.00004783311,0.0140621755],"study_design_scores_gemma":[0.0029990335,0.0005474066,0.00009073861,0.00006460923,0.000033640776,0.00011844479,0.0029859967,0.99035263,0.0018961739,0.00078919675,0.000034572622,0.00008757211],"about_ca_topic_score_codex":0.000008055838,"about_ca_topic_score_gemma":0.0001782068,"teacher_disagreement_score":0.7451062,"about_ca_system_score_codex":0.00026885446,"about_ca_system_score_gemma":0.0006607552,"threshold_uncertainty_score":0.40579584},"labels":[],"label_agreement":null},{"id":"W4205819613","doi":"10.1136/jclinpath-2021-207961","title":"Faster than light (microscopy): superiority of digital pathology over microscopy for assessment of immunohistochemistry","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University","funders":"Engineering and Physical Sciences Research Council; University of Leeds; National Institute for Health and Care Research","keywords":"Digital pathology; Microscope; Microscopy; Digital microscope; Pathology; Biopsy; Computer science; Medicine","score_opus":0.03779732526025994,"score_gpt":0.41588564804515904,"score_spread":0.3780883227848991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205819613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8677521,0.00029421705,0.12715498,0.00088113797,0.0034818659,0.00015662868,0.00006697039,0.000010565015,0.00020158177],"genre_scores_gemma":[0.9691684,0.000048661303,0.030256758,0.00018436275,0.00022959115,0.000014031421,0.0000027709757,0.000015292575,0.00008007923],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9965003,0.00034957443,0.0021513985,0.00036356112,0.0003639211,0.0002712586],"domain_scores_gemma":[0.99613166,0.00069789955,0.0021393613,0.0005843797,0.0003557498,0.00009095102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023771883,0.00016340605,0.00094615924,0.00013166621,0.00009611337,0.000025788047,0.0011129366,0.00020422631,0.00004663731],"category_scores_gemma":[0.0003727258,0.00015258873,0.0005910463,0.00019198247,0.00029799397,0.00030124706,0.00060066645,0.0008099863,7.05824e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072243763,0.0010431221,0.09240438,0.00011303738,0.000119449025,0.00020710398,0.00045008262,0.000088440465,0.89391184,0.0004876017,0.0010417931,0.009410709],"study_design_scores_gemma":[0.022220613,0.045455724,0.4597614,0.00030161545,0.00046515482,0.010648644,0.0008125399,0.0036858602,0.3901681,0.025723858,0.039110813,0.0016456678],"about_ca_topic_score_codex":0.0000016495961,"about_ca_topic_score_gemma":6.577475e-7,"teacher_disagreement_score":0.50374377,"about_ca_system_score_codex":0.00014274985,"about_ca_system_score_gemma":0.00056847057,"threshold_uncertainty_score":0.62223876},"labels":[],"label_agreement":null},{"id":"W4205944574","doi":"10.2196/33440","title":"The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Brier score; Medicine; Proportional hazards model; Machine learning; Retrospective cohort study; Artificial intelligence; Discriminative model; Random forest; Breast cancer; Cancer; Hazard ratio; Statistics; Computer science; Internal medicine; Confidence interval; Mathematics","score_opus":0.020452681424711835,"score_gpt":0.30229686392885496,"score_spread":0.2818441825041431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205944574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13185374,0.0002595625,0.8632802,0.00094263715,0.00028289485,0.0031555132,0.0000583772,0.00007656845,0.00009053053],"genre_scores_gemma":[0.9966593,0.00007077133,0.00046413572,0.00003205854,0.000033445813,0.0027242657,0.000003476275,0.000004556542,0.000008031069],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833435,0.00006313529,0.0004997942,0.000093019014,0.0008989013,0.00011080515],"domain_scores_gemma":[0.99888444,0.0002351876,0.00045297277,0.00023484186,0.00015525155,0.000037305424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011111351,0.00007011555,0.00016428856,0.000036267178,0.00047068542,0.000026190262,0.00047156357,0.000032321997,0.000004364554],"category_scores_gemma":[0.000032056796,0.000043410462,0.00003075536,0.00030511664,0.00011112621,0.00022936454,0.00029828143,0.00032316212,1.0069495e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012244558,0.0004080791,0.6697646,0.0001559981,0.00024395848,6.589909e-8,0.038258925,0.0274058,0.000015189244,0.005282656,0.0009059928,0.25743634],"study_design_scores_gemma":[0.00031629048,0.00032496094,0.07557182,0.00001048525,0.000023726598,0.0000044997278,0.0032392622,0.9195955,0.000031252763,0.00036412626,0.00048281648,0.0000352731],"about_ca_topic_score_codex":0.00011544532,"about_ca_topic_score_gemma":0.00004072266,"teacher_disagreement_score":0.8921897,"about_ca_system_score_codex":0.00012380267,"about_ca_system_score_gemma":0.00008750707,"threshold_uncertainty_score":0.36201793},"labels":[],"label_agreement":null},{"id":"W4206461547","doi":"10.1093/noajnl/vdac001","title":"Integrating morphologic and molecular histopathological features through whole slide image registration and deep learning","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Princess Margaret Cancer Foundation","keywords":"Workflow; Digital pathology; Scale-invariant feature transform; Computer science; Artificial intelligence; ATRX; Pathology; Pipeline (software); Deep learning; Pattern recognition (psychology); Feature extraction; Biology; Medicine; Database","score_opus":0.0101506632032242,"score_gpt":0.2726875042782666,"score_spread":0.2625368410750424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206461547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33537152,0.016001927,0.6301371,0.007949248,0.0015573339,0.0005073406,0.000003645501,0.00062327675,0.007848611],"genre_scores_gemma":[0.86102366,0.0006914884,0.13526206,0.0026680005,0.00007178493,0.00016903334,0.000004861967,0.000015308395,0.00009378254],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981361,0.00056966516,0.00020888499,0.0006527274,0.0001910393,0.00024156955],"domain_scores_gemma":[0.99913013,0.00034593488,0.00022987531,0.00021303068,0.00003762654,0.000043376116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003498854,0.00015844752,0.00020939202,0.00006104439,0.00064616714,0.00007348446,0.00031297174,0.00007639472,0.00001020194],"category_scores_gemma":[0.00036162132,0.00014993495,0.000031761116,0.0002322976,0.00025422583,0.0006651554,0.00047456118,0.00075924664,0.0000017440893],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008996793,0.000074171054,0.0019070721,0.000027932365,0.000008039276,0.0014241367,0.0023009104,0.0030629388,0.6225389,0.016387329,0.0004472136,0.3517314],"study_design_scores_gemma":[0.0023694115,0.011406215,0.00921246,0.000025657395,0.000068545945,0.013580517,0.0038833297,0.039313085,0.036720518,0.12342323,0.75866336,0.0013336668],"about_ca_topic_score_codex":0.000009749081,"about_ca_topic_score_gemma":0.00001696363,"teacher_disagreement_score":0.75821614,"about_ca_system_score_codex":0.0001355795,"about_ca_system_score_gemma":0.00003433256,"threshold_uncertainty_score":0.611417},"labels":[],"label_agreement":null},{"id":"W4206948011","doi":"10.3389/fmed.2021.749146","title":"Establishment and Verification of Neural Network for Rapid and Accurate Cytological Examination of Four Types of Cerebrospinal Fluid Cells","year":2022,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Cerebrospinal fluid; Cytology; Pathology; Artificial neural network; Peripheral blood; Computer science; Giemsa stain; Clinical Practice; Medicine; Artificial intelligence; Immunology","score_opus":0.02404164877762521,"score_gpt":0.24998586624849467,"score_spread":0.22594421747086946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206948011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4275048,0.002323251,0.5677483,0.00054728246,0.0013955915,0.00039996495,0.0000068401005,0.000011462014,0.000062462525],"genre_scores_gemma":[0.96317965,0.00019313315,0.036506508,0.000030352181,0.000043438715,0.000029048697,0.0000038288695,0.0000029712437,0.000011083881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918205,0.00009819736,0.00026724488,0.00017412665,0.0001874496,0.00009096239],"domain_scores_gemma":[0.99948967,0.00007763844,0.00021647391,0.0001379705,0.00005762558,0.000020644164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007172647,0.000057770518,0.00022456642,0.00010557286,0.000039182138,0.0000029699927,0.00015834442,0.000026911759,0.0000055098253],"category_scores_gemma":[0.00004996293,0.000051892057,0.000012238005,0.00028360533,0.00012294317,0.00010362163,0.00007723132,0.00006573118,8.945735e-9],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010124337,0.00018294743,0.032669198,0.0007956692,0.000088393936,0.0000043527384,0.006106035,0.024847358,0.05323947,0.004103466,0.022457343,0.8544933],"study_design_scores_gemma":[0.0026002866,0.004621606,0.21872179,0.00010022386,0.00005158513,0.0000133584745,0.0011160156,0.7513712,0.01579818,0.0036476296,0.001790526,0.00016757795],"about_ca_topic_score_codex":0.000018156952,"about_ca_topic_score_gemma":0.000001340165,"teacher_disagreement_score":0.8543258,"about_ca_system_score_codex":0.00004191078,"about_ca_system_score_gemma":0.000017290276,"threshold_uncertainty_score":0.21160966},"labels":[],"label_agreement":null},{"id":"W4207020292","doi":"10.5858/arpa.2021-0461-le","title":"In Reply","year":2022,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre; University of Toronto","funders":"","keywords":"","score_opus":0.010222435846509883,"score_gpt":0.2600738846170785,"score_spread":0.24985144877056858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207020292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8084796,0.0043098005,0.12539564,0.040612765,0.005551255,0.000577521,0.000037426216,0.00029202827,0.014743935],"genre_scores_gemma":[0.98737675,0.00005293714,0.007575568,0.0046879197,0.000107162756,0.00006415189,0.0000020568116,0.000008993593,0.00012446223],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986361,0.00039624015,0.0002806405,0.00031561218,0.00019833785,0.00017303656],"domain_scores_gemma":[0.99900895,0.00024734784,0.00014087031,0.00054077007,0.000021500016,0.00004058251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005539043,0.00008084403,0.00020518797,0.00032671393,0.0000735666,0.0000014421478,0.0006178251,0.000015806434,0.00008426683],"category_scores_gemma":[0.000114865055,0.00007831568,0.000019698617,0.00068358285,0.0003095059,0.000119542296,0.00034961634,0.00027838966,0.0000029538114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031248012,0.0004938172,0.032737218,0.0001332259,0.000056675355,0.0053391345,0.06273817,0.0015030595,0.6522988,0.14236397,0.020934232,0.081089236],"study_design_scores_gemma":[0.010466755,0.010139947,0.2358145,0.00021224217,0.00005423286,0.0014620668,0.004683918,0.015034951,0.051315613,0.18182819,0.48777562,0.0012119717],"about_ca_topic_score_codex":0.000031719934,"about_ca_topic_score_gemma":0.000012159227,"teacher_disagreement_score":0.60098314,"about_ca_system_score_codex":0.000039455266,"about_ca_system_score_gemma":0.00013474189,"threshold_uncertainty_score":0.31936207},"labels":[],"label_agreement":null},{"id":"W4210276975","doi":"10.1101/2022.01.31.478433","title":"Neural network for the prediction of treatment response in Triple Negative Breast Cancer <sup>*</sup>","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Response Biomedical (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Workflow; Triple-negative breast cancer; Deep learning; Breast cancer; Computer science; Machine learning; Artificial intelligence; Variety (cybernetics); Artificial neural network; Selection (genetic algorithm); Predictive modelling; Deep neural networks; Triple negative; Cancer; Medicine; Internal medicine","score_opus":0.020584800437717564,"score_gpt":0.2424014588536214,"score_spread":0.22181665841590384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210276975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92274356,0.0020604585,0.058083367,0.0025441612,0.00604133,0.005052763,0.0029216514,0.00055002776,0.000002699371],"genre_scores_gemma":[0.9899702,0.00038781593,0.004656955,0.000118653865,0.00068750733,0.0041000927,2.8014603e-7,0.00006820007,0.000010284193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689215,0.00054400647,0.0006225078,0.0010182121,0.00039304275,0.0005300989],"domain_scores_gemma":[0.9968619,0.00061738864,0.0005765759,0.0015248802,0.00031512088,0.00010413906],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001144334,0.0004405616,0.0005038745,0.00025262908,0.00031783665,0.00014107315,0.0011603778,0.00024158724,0.000036008307],"category_scores_gemma":[0.000109265224,0.00038761573,0.00022022722,0.0012109886,0.00010806188,0.00027939348,0.0006587398,0.000561467,0.0000015296504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003226602,0.00029376475,0.018104207,0.00022531752,0.00052094675,0.000019169585,0.00051775936,0.9629667,0.011916694,0.00059845846,0.0013612491,0.00024912698],"study_design_scores_gemma":[0.0019525827,0.0007067414,0.29687312,0.00022128406,0.00013808421,9.76426e-8,0.000021830516,0.68544865,0.0101402,0.000019802783,0.003947661,0.00052993634],"about_ca_topic_score_codex":0.0009565363,"about_ca_topic_score_gemma":0.000027017682,"teacher_disagreement_score":0.27876893,"about_ca_system_score_codex":0.002637731,"about_ca_system_score_gemma":0.0014201358,"threshold_uncertainty_score":0.9998576},"labels":[],"label_agreement":null},{"id":"W4210340693","doi":"10.2196/preprints.12660","title":"Computer-Aided Detection for Breast Cancer Screening in Clinical Settings: Scoping Review (Preprint)","year":2018,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Breast cancer; CAD; Medicine; MEDLINE; Medical physics; Breast cancer screening; Cancer; Computer science; Mammography; Internal medicine; Engineering drawing","score_opus":0.06425589824964406,"score_gpt":0.3920401945511958,"score_spread":0.32778429630155176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210340693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012816531,0.0030728923,0.9835474,0.002381601,0.0050208312,0.0039660684,0.000017554865,0.00058371836,0.00012830013],"genre_scores_gemma":[0.07067648,0.020570865,0.889145,0.008910154,0.0064458717,0.003982137,0.000017178852,0.00014949788,0.000102792226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99478364,0.00039079296,0.0017894951,0.0020474375,0.00043223216,0.0005563966],"domain_scores_gemma":[0.9962708,0.00046477217,0.0010250469,0.0015753389,0.00051142543,0.0001526147],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004040718,0.0004550433,0.0009924417,0.00025588513,0.00016585732,0.00028712684,0.001620117,0.00048748832,0.00007031673],"category_scores_gemma":[0.0001766794,0.0004694684,0.00044977883,0.00048251366,0.00009594436,0.00046004774,0.00286958,0.0010253076,0.00002572862],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000343349,0.00004314141,0.0011209291,0.009450524,0.000061568644,0.0000024590388,0.00006359387,0.0018356636,0.0000147335295,0.00003657717,0.0012733325,0.9860631],"study_design_scores_gemma":[0.0011092708,0.00022868565,0.015742699,0.26256338,0.00007214086,0.00007785571,0.000007240461,0.7156297,0.0011077581,0.0016948129,0.00059346796,0.0011730113],"about_ca_topic_score_codex":0.00051446573,"about_ca_topic_score_gemma":0.0010308424,"teacher_disagreement_score":0.9848901,"about_ca_system_score_codex":0.00038112045,"about_ca_system_score_gemma":0.00054726534,"threshold_uncertainty_score":0.9997757},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4210603886","doi":"10.1007/s00521-021-06873-z","title":"A configurable deep learning framework for medical image analysis","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Computer science; Component (thermodynamics); Artificial intelligence; Task (project management); Personalized medicine; Deep learning; Machine learning; Computation; Universality (dynamical systems); Pattern recognition (psychology); Data mining; Bioinformatics; Algorithm","score_opus":0.011037408823150617,"score_gpt":0.29550659353673636,"score_spread":0.28446918471358573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210603886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067558596,0.00013371947,0.9905246,0.0017965443,0.00007611367,0.00021397034,0.0000020599402,0.00023870985,0.000258419],"genre_scores_gemma":[0.93425167,0.000006046064,0.06489179,0.00041597002,0.00012379118,0.0002537931,0.000008315757,0.0000068368226,0.000041804702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989806,0.0000710326,0.00016616628,0.0003594239,0.00024214978,0.00018067117],"domain_scores_gemma":[0.9990374,0.0004981801,0.00009803802,0.0002377845,0.000047358128,0.00008123238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000344662,0.000074215284,0.00012528744,0.0000993128,0.0011980331,0.000111398986,0.00041509036,0.00003239324,0.00003325473],"category_scores_gemma":[0.000056182816,0.000080858306,0.000071841714,0.0009786407,0.00003674389,0.00006533975,0.0002650158,0.000355481,0.000002368145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008412084,0.00007059815,0.0013137474,0.000029074055,0.00013201762,0.0000022974586,0.00077969406,0.0664381,0.00034245846,0.17840718,0.0002566052,0.7522198],"study_design_scores_gemma":[0.00010326128,0.000053468913,0.0005426928,0.0000018588694,0.000034003635,0.000015623342,0.000085463784,0.9761896,0.000066700886,0.0076108784,0.015202114,0.0000943408],"about_ca_topic_score_codex":0.000020637139,"about_ca_topic_score_gemma":0.0000029203081,"teacher_disagreement_score":0.9274958,"about_ca_system_score_codex":0.00003674135,"about_ca_system_score_gemma":0.000023992496,"threshold_uncertainty_score":0.9214423},"labels":[],"label_agreement":null},{"id":"W4211179311","doi":"10.1038/s41598-022-06100-2","title":"Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Breast cancer; Chemotherapy; Ultrasound; Parametric statistics; Computer science; Medicine; Radiology; Cancer; Oncology; Artificial intelligence; Medical physics; Internal medicine; Statistics; Mathematics","score_opus":0.016490636260684595,"score_gpt":0.2994004918979116,"score_spread":0.28290985563722704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211179311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8615616,0.00024808734,0.1319748,0.00059888564,0.0045210775,0.0008674689,0.000020789903,0.00016181552,0.000045462435],"genre_scores_gemma":[0.9677067,0.000010902476,0.02479932,0.00006273223,0.00002586073,0.0004528485,0.00000547695,0.000023028051,0.0069131544],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965286,0.00033510945,0.00050751347,0.0012408684,0.0009892159,0.00039865304],"domain_scores_gemma":[0.99769866,0.0002920479,0.00043877805,0.0010933602,0.00027282417,0.00020432798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021751465,0.00019905211,0.00026448964,0.00072064606,0.0008079621,0.00021726458,0.00048818224,0.000031770243,0.00021189205],"category_scores_gemma":[0.00032047997,0.00019084448,0.000113751084,0.0035111029,0.000114674374,0.00028391439,0.0004200641,0.00012874705,0.000015378233],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013228469,0.0005402749,0.053816363,0.000026925169,0.00013798797,0.00022555696,0.022312295,0.36260822,0.49587432,0.000020827356,0.0054110317,0.057703342],"study_design_scores_gemma":[0.0014132491,0.0035407105,0.40492702,0.000095958254,0.00005810449,0.0020979764,0.0012762957,0.057666097,0.44627458,0.00039508485,0.0811237,0.0011312396],"about_ca_topic_score_codex":0.0004405254,"about_ca_topic_score_gemma":0.00009602387,"teacher_disagreement_score":0.35111064,"about_ca_system_score_codex":0.0016714167,"about_ca_system_score_gemma":0.00031238692,"threshold_uncertainty_score":0.7782412},"labels":[],"label_agreement":null},{"id":"W4212847259","doi":"10.1136/jclinpath-2021-208020","title":"Compound computer vision workflow for efficient and automated immunohistochemical analysis of whole slide images","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Princess Margaret Cancer Foundation; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Workflow; Computer science; Computer graphics (images); Artificial intelligence; Computer vision; Pathology; Medicine; Database","score_opus":0.025998894832815974,"score_gpt":0.37875321083543817,"score_spread":0.3527543160026222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212847259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54453427,0.00026481214,0.45302978,0.0008223955,0.0012082561,0.00008698066,0.000010241965,0.000030461584,0.00001277619],"genre_scores_gemma":[0.894263,0.000015975695,0.105293475,0.00027563985,0.0001260314,0.0000051995426,0.0000027455626,0.000006827382,0.0000110513165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730855,0.00047942536,0.001427567,0.00028632098,0.00032535847,0.0001727737],"domain_scores_gemma":[0.99657696,0.0015340468,0.0012191035,0.000315727,0.0002667068,0.00008745563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029938798,0.00010387159,0.00078893517,0.00035553798,0.00012578681,0.00002813905,0.00057287194,0.0000932608,0.000010752458],"category_scores_gemma":[0.0002203779,0.00009208973,0.00044499038,0.0006048522,0.000195129,0.00009524044,0.0004386347,0.00043825048,6.5703716e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036055283,0.003611234,0.015187632,0.00012372536,0.003055902,0.00092175737,0.0015144782,0.3802588,0.111655205,0.0010681424,0.032687217,0.44631037],"study_design_scores_gemma":[0.0018172889,0.0032545594,0.058471404,0.000018738241,0.00037084447,0.0004650934,0.000020966,0.9315168,0.00049074594,0.00074016635,0.0026901707,0.00014321151],"about_ca_topic_score_codex":0.0000018974545,"about_ca_topic_score_gemma":5.6894703e-7,"teacher_disagreement_score":0.551258,"about_ca_system_score_codex":0.0000776834,"about_ca_system_score_gemma":0.0000905608,"threshold_uncertainty_score":0.37553102},"labels":[],"label_agreement":null},{"id":"W4212986460","doi":"10.1109/access.2022.3151830","title":"Design Guidelines for Mammogram-Based Computer-Aided Systems Using Deep Learning Techniques","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Convolutional neural network; Feature extraction; Machine learning; Computer-aided diagnosis; Mammography; CAD; Feature (linguistics); Artificial neural network; Breast cancer; Cancer; Medicine","score_opus":0.1936062150228185,"score_gpt":0.3889147563378393,"score_spread":0.1953085413150208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212986460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025902137,0.00020005138,0.9925385,0.0002822108,0.0026004799,0.0008938698,0.000002137122,0.00087969843,0.000012850111],"genre_scores_gemma":[0.3607837,0.0000044420103,0.63722706,0.0006018333,0.00057691825,0.00073284755,0.0000033560116,0.000039545805,0.000030322708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799454,0.0003018535,0.0004203765,0.000522005,0.00041872123,0.00034249626],"domain_scores_gemma":[0.9984973,0.00026272394,0.00031356397,0.00045963263,0.00040712173,0.000059656435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010997634,0.00018203398,0.00023022546,0.0002602654,0.00072497537,0.00062584854,0.001634141,0.00005606196,0.0000052712126],"category_scores_gemma":[0.000040945462,0.00019630977,0.000087599525,0.0006956134,0.000025959556,0.00066932157,0.00034206867,0.00021904807,0.0000012938103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025183203,0.000024758312,0.00012045177,0.000054653123,0.000016138481,0.000007856406,0.00006274919,0.9250592,0.0046637678,0.00012351856,0.0013232741,0.068518445],"study_design_scores_gemma":[0.00024328669,0.00026400387,0.000009807526,0.000033756623,0.000011168192,0.000030548614,0.00001595123,0.9569691,0.034733772,0.00047087634,0.0069794967,0.00023825276],"about_ca_topic_score_codex":0.00028622718,"about_ca_topic_score_gemma":0.0000035652931,"teacher_disagreement_score":0.3581935,"about_ca_system_score_codex":0.00036066415,"about_ca_system_score_gemma":0.00013744149,"threshold_uncertainty_score":0.80052805},"labels":[],"label_agreement":null},{"id":"W4213056095","doi":"10.4018/978-1-7998-8929-8.ch002","title":"Optimized Breast Cancer Premature Detection Method With Computational Segmentation","year":2022,"lang":"en","type":"book-chapter","venue":"Advances in healthcare information systems and administration book series","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mohawk College","funders":"","keywords":"Breast cancer; Mammography; Medicine; Breast tissue; Breast cancer screening; Cancer; Radiology; Segmentation; Oncology; Internal medicine; Artificial intelligence; Computer science","score_opus":0.011325864025008962,"score_gpt":0.2905149505712467,"score_spread":0.27918908654623775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213056095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021411292,0.014366722,0.9438912,0.006721541,0.0028875985,0.0039020923,0.00084210763,0.0005624921,0.02680483],"genre_scores_gemma":[0.24965689,0.14115295,0.4854459,0.010612102,0.0028230806,0.016649656,0.006178507,0.0005858401,0.08689508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745667,0.00011839521,0.0010065553,0.00043455834,0.0007553188,0.00022849326],"domain_scores_gemma":[0.9978399,0.00011204321,0.0012323289,0.00029244472,0.00041174213,0.00011149844],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003929556,0.0003802009,0.00043743828,0.0003790001,0.00042737206,0.0003710862,0.00021564066,0.00023776277,0.00005025937],"category_scores_gemma":[0.0000063597217,0.00036939053,0.000048492388,0.0001781313,0.000069768335,0.012943804,0.000073886564,0.000501629,0.000004283034],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009802609,0.00001844729,0.000095556126,0.0026270447,0.00007818613,0.000014060134,0.0018750954,0.17104265,0.0000044456533,0.6405763,0.00011059905,0.18257737],"study_design_scores_gemma":[0.0023782316,0.00178615,0.00052223104,0.001508233,0.000056570854,0.0029387127,0.0010563127,0.058042493,0.00015971364,0.008304726,0.92161447,0.0016321781],"about_ca_topic_score_codex":0.00016670588,"about_ca_topic_score_gemma":0.0003493439,"teacher_disagreement_score":0.92150384,"about_ca_system_score_codex":0.00065423554,"about_ca_system_score_gemma":0.0005799718,"threshold_uncertainty_score":0.9998758},"labels":[],"label_agreement":null},{"id":"W4213457699","doi":"10.2147/rmhp.s332109","title":"Implementing Epic Beaker Laboratory Information System for Diagnostics in Anatomic Pathology","year":2022,"lang":"en","type":"article","venue":"Risk Management and Healthcare Policy","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Alberta; University of Ottawa","funders":"","keywords":"EPIC; Desk; Radiological weapon; Information system; Beaker; Software; Surgical pathology","score_opus":0.01076205341111987,"score_gpt":0.28494025503666853,"score_spread":0.2741782016255487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213457699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49728093,0.004147434,0.46414882,0.020838382,0.0031753357,0.0065979133,0.0007380033,0.0009320375,0.002141151],"genre_scores_gemma":[0.99231887,0.0007895118,0.004954573,0.0011657815,0.000100452184,0.0006333935,0.000017149865,0.000008024068,0.000012270435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875736,0.00015514668,0.00032402115,0.00021268177,0.00015573943,0.0003950533],"domain_scores_gemma":[0.9993848,0.000065586006,0.00020884132,0.00024648083,0.000043426033,0.000050874187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093052717,0.00009250863,0.000125872,0.00052465906,0.0005017854,0.000062690706,0.00023394241,0.000028731938,0.0000018502828],"category_scores_gemma":[0.000023920664,0.00010814034,0.000022200176,0.00060679973,0.000011740344,0.00034548636,0.0005368675,0.00014695583,0.0000031159427],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020099355,0.000015817868,0.044086974,0.0009127628,0.00001954634,0.000012687276,0.0040485705,0.00028836817,7.2870733e-7,0.51184434,0.0013110195,0.43743908],"study_design_scores_gemma":[0.0049292333,0.0009576469,0.20846196,0.000121919824,0.00005843631,0.000039619772,0.01899634,0.10702166,0.00007598918,0.025343014,0.63309145,0.0009027109],"about_ca_topic_score_codex":0.0015046931,"about_ca_topic_score_gemma":0.0003855984,"teacher_disagreement_score":0.63178045,"about_ca_system_score_codex":0.0006033353,"about_ca_system_score_gemma":0.00008108827,"threshold_uncertainty_score":0.4409835},"labels":[],"label_agreement":null},{"id":"W4214887223","doi":"10.1007/978-981-16-6963-7_73","title":"Pathologist-Level Classification of Melanoma Disease Pathologies Using a Convolutional Neural Network: A Retrospective Study of Chinese","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SKiN Health","funders":"","keywords":"Melanoma; Convolutional neural network; Medicine; Histopathology; Pathological; Dermatology; Disease; Radiology; Artificial intelligence; Pathology; Computer science","score_opus":0.02915566171090668,"score_gpt":0.2513770119689366,"score_spread":0.22222135025802991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214887223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07198439,0.0022221296,0.9237084,0.000059759273,0.00071285665,0.0008485535,0.00004314152,0.000202259,0.0002185256],"genre_scores_gemma":[0.99193674,0.00003364016,0.0077166357,0.00001472076,0.00015918241,0.000054884473,0.000012154153,0.000043200947,0.000028849425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976427,0.00007662657,0.0006312161,0.00068784953,0.0005963765,0.0003652096],"domain_scores_gemma":[0.99838775,0.0003750846,0.0004480881,0.0005921751,0.00013361273,0.00006330059],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002918894,0.0003931204,0.0006455454,0.0004603031,0.00007367118,0.00001962773,0.00063733594,0.00023340523,0.000017882157],"category_scores_gemma":[0.00054905674,0.00038526303,0.00015895137,0.0007171925,0.00006135226,0.00014857361,0.0003295901,0.0010705579,3.346995e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094234834,0.00012359748,0.012142144,0.000056829882,0.000061528204,0.00009404217,0.00030387027,0.96921253,0.0010684768,0.010624842,0.0000021677192,0.006215744],"study_design_scores_gemma":[0.00041043287,0.00065138686,0.1440833,0.000045650922,0.00004067053,0.00003284032,0.0000012270029,0.83979344,0.000026444784,0.014515456,0.000021052312,0.00037809755],"about_ca_topic_score_codex":0.00003999447,"about_ca_topic_score_gemma":0.000021064441,"teacher_disagreement_score":0.91995233,"about_ca_system_score_codex":0.00086739106,"about_ca_system_score_gemma":0.0001555376,"threshold_uncertainty_score":0.9998599},"labels":[],"label_agreement":null},{"id":"W4220659516","doi":"10.1016/j.jtho.2022.02.013","title":"NSCLC Subtyping in Conventional Cytology: Results of the International Association for the Study of Lung Cancer Cytology Working Group Survey to Determine Specific Cytomorphologic Criteria for Adenocarcinoma and Squamous Cell Carcinoma","year":2022,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Université Laval; Princess Margaret Cancer Centre","funders":"Merck Sharp and Dohme; Daiichi-Sankyo; Takeda Pharmaceutical Company; AbbVie; Chugai Pharmaceutical; Roche; Novartis; GlaxoSmithKline; Amgen; Pfizer; Bayer; AstraZeneca; Eli Lilly and Company; University of Missouri; U.S. Department of Defense","keywords":"Subtyping; Adenocarcinoma; Cytology; Medicine; Lung cancer; Gold standard (test); Oncology; Carcinoma; Algorithm; Internal medicine; Cancer; Pathology; Computer science","score_opus":0.06734476077710362,"score_gpt":0.3816303051502155,"score_spread":0.3142855443731119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220659516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97672474,0.000641036,0.014546254,0.0027589789,0.0043014693,0.0009293573,0.000073121926,0.0000045493075,0.000020490497],"genre_scores_gemma":[0.9972971,0.000012922124,0.0021299245,0.0001562915,0.00019214512,0.00016093813,0.0000030782185,0.000009942825,0.00003765569],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99708223,0.001067993,0.00096387975,0.00029399924,0.00035658112,0.00023533666],"domain_scores_gemma":[0.99405944,0.0033670075,0.0018750064,0.00023284426,0.0004310396,0.000034662044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052036135,0.00012167008,0.00043953006,0.00030018846,0.00020435001,0.000025010275,0.0010911121,0.000098160046,0.000011400154],"category_scores_gemma":[0.00048147436,0.000093349205,0.000115423674,0.00042468778,0.000059103553,0.000115308365,0.0004846003,0.00035181214,6.471878e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009869779,0.00084592134,0.94894034,0.000059991013,0.00013727063,0.000035335685,0.0043189283,0.003094066,0.009147441,0.0001328157,0.0032908882,0.020127216],"study_design_scores_gemma":[0.0037550132,0.0038295616,0.9739899,0.00002184375,0.000084192754,0.00020608796,0.000847794,0.013853655,0.0015282776,0.00028032408,0.0014826411,0.00012072969],"about_ca_topic_score_codex":0.0002183605,"about_ca_topic_score_gemma":0.0016546812,"teacher_disagreement_score":0.025049532,"about_ca_system_score_codex":0.001210099,"about_ca_system_score_gemma":0.00026401237,"threshold_uncertainty_score":0.380667},"labels":[],"label_agreement":null},{"id":"W4220680613","doi":"10.1101/2022.03.10.22272226","title":"A Pilot Validation Study Comparing FIBI, a Slide-Free Imaging Method, with Standard FFPE H&amp;E Tissue Section Histology for Primary Surgical Pathology Diagnosis","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Digital pathology; Surgical pathology; Medical diagnosis; Medicine; Pathology; Nuclear medicine; Fixation (population genetics); Histology; Biomedical engineering","score_opus":0.05287156703864924,"score_gpt":0.33594363643133446,"score_spread":0.2830720693926852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220680613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27121946,0.0003149913,0.72075397,0.00096191803,0.0039742575,0.001991051,0.000035898538,0.0004834531,0.00026501348],"genre_scores_gemma":[0.6890341,0.000049108738,0.3032561,0.00013526891,0.0006063025,0.0065201554,0.000108865956,0.00010671051,0.00018336062],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99427646,0.0016153348,0.0007832007,0.0019605695,0.0008032205,0.0005612321],"domain_scores_gemma":[0.99564964,0.0010502321,0.00076162873,0.0020905416,0.00032187608,0.00012611049],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032120808,0.0005256936,0.0010292742,0.0005647458,0.0005218429,0.00023139814,0.0018349387,0.0001432082,0.00006829469],"category_scores_gemma":[0.00025557447,0.0005398697,0.0001501654,0.0005640876,0.00011728618,0.00033908035,0.0032012146,0.0012205399,0.000004259813],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028211721,0.0015352473,0.837439,0.001037295,0.0005519809,0.0010294578,0.009058277,0.047122847,0.0010224062,0.0015710252,0.0041771177,0.09263416],"study_design_scores_gemma":[0.04067758,0.033986717,0.2921468,0.0011303423,0.0028837598,0.0074913846,0.0018918647,0.07071448,0.016239822,0.06440117,0.4575702,0.010865881],"about_ca_topic_score_codex":0.0005811647,"about_ca_topic_score_gemma":0.00056795526,"teacher_disagreement_score":0.5452922,"about_ca_system_score_codex":0.00213949,"about_ca_system_score_gemma":0.00042612661,"threshold_uncertainty_score":0.99970526},"labels":[],"label_agreement":null},{"id":"W4220687271","doi":"10.1007/s11548-022-02606-2","title":"Coarse label refinement for improving prostate cancer detection in ultrasound imaging","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Prostate cancer; Leverage (statistics); Pattern recognition (psychology); Histopathology; Cancer detection; Machine learning; Ultrasound; Cancer; Radiology; Medicine; Pathology","score_opus":0.015974225868757994,"score_gpt":0.2693842301608495,"score_spread":0.2534100042920915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220687271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36728522,0.0010114239,0.6201868,0.0028314302,0.008514302,0.0001277542,0.000009511551,0.000024848316,0.00000867284],"genre_scores_gemma":[0.9880646,0.00011757826,0.0105411615,0.0007814663,0.0004143147,0.00005463958,0.0000031104598,0.000008001069,0.000015112511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986626,0.00018566058,0.00051407365,0.00021345228,0.0002513532,0.00017284552],"domain_scores_gemma":[0.99845946,0.00069049094,0.0004779797,0.0000907985,0.00023934842,0.00004195189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011289679,0.00010059517,0.00021978628,0.00050197204,0.00013816562,0.000074404576,0.00035096737,0.000029407394,0.000007883676],"category_scores_gemma":[0.000047374346,0.000100066354,0.000086283166,0.00016764353,0.00004017175,0.0003611348,0.00013501823,0.00027002062,1.3736765e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033320166,0.00009341302,0.023700869,0.000014843201,0.00012517662,0.00013190786,0.00044512414,0.0037382916,0.0064491625,0.00016171538,0.0011574732,0.9636488],"study_design_scores_gemma":[0.0063279555,0.00082221575,0.19048525,0.00017428983,0.00006380686,0.019182509,0.00023930064,0.7421516,0.0044825827,0.0041675903,0.031088764,0.0008141096],"about_ca_topic_score_codex":0.000047676756,"about_ca_topic_score_gemma":0.000025530908,"teacher_disagreement_score":0.9628347,"about_ca_system_score_codex":0.0003980694,"about_ca_system_score_gemma":0.00017182791,"threshold_uncertainty_score":0.40805873},"labels":[],"label_agreement":null},{"id":"W4220752318","doi":"10.1016/j.jmsacl.2022.03.001","title":"Clinical Pathology and the Data Science revolution","year":2022,"lang":"en","type":"editorial","venue":"Journal of Mass Spectrometry and Advances in the Clinical Lab","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital","funders":"","keywords":"Pathology; Medicine; Data science; Computer science","score_opus":0.03578892904482415,"score_gpt":0.4016668275040151,"score_spread":0.36587789845919094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220752318","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082967215,0.04412901,0.036898337,0.0056167617,0.91135645,0.0003084828,0.000042645144,0.00001949283,0.00079913944],"genre_scores_gemma":[0.011661412,0.34527382,0.043904852,0.0007105533,0.5983265,0.000011289029,0.000007159641,0.000023442595,0.000080960206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926265,0.0027134856,0.0019361795,0.00085503364,0.0015140936,0.00035470232],"domain_scores_gemma":[0.97450536,0.021052433,0.0023402094,0.0017347587,0.00024383924,0.00012341294],"candidate_categories":["metaresearch","sts","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051689114,0.00021883364,0.0008879357,0.0002916081,0.00042187466,0.00023329267,0.0062367534,0.00030602273,0.000014616492],"category_scores_gemma":[0.018431246,0.00012005022,0.00016584973,0.0012502495,0.0028193379,0.0018645825,0.0022112413,0.0048885704,0.0000012082473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003158301,0.00079031364,0.003845504,0.0002369973,0.00021500689,0.0011570068,0.00049312186,0.00009249812,0.000023998986,0.05013021,0.53343534,0.4064217],"study_design_scores_gemma":[0.002354582,0.0015281809,0.0011095472,0.00009084283,0.00008245185,0.00040735505,0.00012941708,0.0009786243,0.0000011917089,0.062005993,0.93111944,0.00019236583],"about_ca_topic_score_codex":0.0000033395017,"about_ca_topic_score_gemma":0.000010047351,"teacher_disagreement_score":0.40622935,"about_ca_system_score_codex":0.00013835127,"about_ca_system_score_gemma":0.0006747766,"threshold_uncertainty_score":0.99989444},"labels":[],"label_agreement":null},{"id":"W4220860114","doi":"10.1038/s41585-022-00583-4","title":"AI for prostate cancer diagnosis — hype or today’s reality?","year":2022,"lang":"en","type":"review","venue":"Nature Reviews Urology","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Prostate cancer; Workload; Grading (engineering); Medical physics; Cancer; Computer science; Internal medicine","score_opus":0.0895248973238381,"score_gpt":0.41598028795736297,"score_spread":0.32645539063352486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220860114","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.8617996e-9,0.9779302,0.0048339088,0.004844984,0.0060631298,0.005687395,0.0002456607,0.00020712226,0.00018760627],"genre_scores_gemma":[1.0490409e-7,0.9439776,0.0023204922,0.007757553,0.0008929507,0.044131964,0.00009729099,0.000088598674,0.00073345844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944874,0.0013812509,0.0013230519,0.0016857889,0.00037080352,0.0007517038],"domain_scores_gemma":[0.9953009,0.001318594,0.0013397053,0.0017691313,0.0001245089,0.00014719115],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017872924,0.00076382223,0.0033035276,0.00034173668,0.00028935872,0.000096633936,0.0025402168,0.0012909214,0.00066477124],"category_scores_gemma":[0.00077989895,0.0005357815,0.0010705802,0.0016452619,0.000072503164,0.00027748873,0.00076003914,0.0030240044,0.000060943657],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013041764,0.000027116852,0.0000012531266,0.011185029,0.0000786914,0.000014052255,0.000026508953,0.0000013360846,1.132474e-8,0.00088997587,0.13064069,0.8571223],"study_design_scores_gemma":[0.00017179258,0.0004080323,4.7154856e-7,0.0013273638,0.0006509208,0.0001848823,3.464457e-7,0.000051905667,3.4472964e-7,0.00064456,0.9960233,0.00053607894],"about_ca_topic_score_codex":0.000043421074,"about_ca_topic_score_gemma":0.00019952528,"teacher_disagreement_score":0.8653826,"about_ca_system_score_codex":0.0007471129,"about_ca_system_score_gemma":0.0011269449,"threshold_uncertainty_score":0.99970937},"labels":[],"label_agreement":null},{"id":"W4221019523","doi":"10.1080/21681163.2022.2058415","title":"Automatic characterization of breast lesions using multi-scale attention-guided deep learning of digital histology images","year":2022,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Magnification; Artificial intelligence; Computer science; Pooling; Pattern recognition (psychology); Convolutional neural network; Deep learning; Perceptron; Artificial neural network; Sample (material)","score_opus":0.020863076023730505,"score_gpt":0.32592759043157665,"score_spread":0.30506451440784615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221019523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0778254,0.00007883958,0.92098516,0.00006169012,0.0007954077,0.00013484806,0.000010851559,0.00010733482,4.6069425e-7],"genre_scores_gemma":[0.45671624,0.000016817265,0.5431456,0.000013654779,0.000031631607,0.000011868301,0.000042461368,0.00001937239,0.0000023485736],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983006,0.00022880011,0.0006125045,0.00036376153,0.00028258844,0.00021175074],"domain_scores_gemma":[0.99920195,0.00011281025,0.00032727612,0.00019244026,0.000099203666,0.00006629203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008438406,0.00015780545,0.00030136094,0.00081619725,0.00011268343,0.000052654876,0.00030279078,0.000057313104,0.0000074620975],"category_scores_gemma":[0.000053347037,0.00017720579,0.000057188896,0.0012672074,0.00006135318,0.00028468962,0.0005562503,0.00016703217,1.3616678e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021632966,0.000112749156,0.00055812974,0.00014469506,0.000013322394,0.000002754209,0.00035200117,0.001878256,0.71799034,0.00056824816,9.5137824e-7,0.27837637],"study_design_scores_gemma":[0.0003675359,0.00007322378,0.0027015689,0.00007957504,0.000011953866,0.00013887297,0.000025022362,0.99181587,0.0044061886,0.00010396811,0.00011417766,0.00016201839],"about_ca_topic_score_codex":0.00001700294,"about_ca_topic_score_gemma":8.546582e-8,"teacher_disagreement_score":0.98993766,"about_ca_system_score_codex":0.00015844178,"about_ca_system_score_gemma":0.000040405383,"threshold_uncertainty_score":0.72262424},"labels":[],"label_agreement":null},{"id":"W4221087148","doi":"10.1117/12.2611584","title":"Sparse capsule networks for informative representation learning in digital pathology","year":2022,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Digital pathology; Computer science; Artificial intelligence; Representation (politics); Digitization; Deep learning; Pattern recognition (psychology); Feature learning; Computer vision; Machine learning","score_opus":0.019397365843109547,"score_gpt":0.26205735468811764,"score_spread":0.24265998884500808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221087148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036888983,0.000015387897,0.9588632,0.00022154558,0.0003802727,0.00020548776,0.000001067134,0.00011765533,0.0033064303],"genre_scores_gemma":[0.9943144,0.0000029836608,0.004724246,0.00017691695,0.000030943098,0.0001945518,0.000010318746,0.000004004339,0.0005416883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939173,0.000034615638,0.00015341573,0.00016673176,0.000103521794,0.00014999874],"domain_scores_gemma":[0.9996666,0.00007429573,0.00007601619,0.00013742261,0.000028300119,0.000017368578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021579985,0.000048288075,0.00006730785,0.0000905611,0.00014264983,0.00006782585,0.0002119402,0.000019846922,0.000019227307],"category_scores_gemma":[0.000045917488,0.000052324653,0.00002533325,0.00035269486,0.000013016394,0.000847193,0.00027030238,0.00016922092,0.0000044928943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020715064,0.000021946304,0.0024682325,0.0000032402597,0.0000045774514,0.000008360381,0.0036286742,0.7893689,0.000043727996,0.0066653136,0.0012962082,0.19647008],"study_design_scores_gemma":[0.000344075,0.00019546499,0.0016803761,0.0000014373263,6.55404e-7,0.0000271529,0.0007441108,0.9907804,0.00023426463,0.0026092022,0.0033019918,0.0000808779],"about_ca_topic_score_codex":0.000024974248,"about_ca_topic_score_gemma":0.000013102288,"teacher_disagreement_score":0.95742536,"about_ca_system_score_codex":0.00013037036,"about_ca_system_score_gemma":0.000029515813,"threshold_uncertainty_score":0.21337375},"labels":[],"label_agreement":null},{"id":"W4221101816","doi":"10.18280/ts.390123","title":"A Novel Ensemble Bagging Classification Method for Breast Cancer Classification Using Machine Learning Techniques","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Overfitting; Machine learning; Artificial intelligence; Ensemble learning; Computer science; Breast cancer; Contextual image classification; Statistical classification; Weighted voting; Pattern recognition (psychology); Cancer; Voting; Image (mathematics); Artificial neural network; Medicine","score_opus":0.06985194399396133,"score_gpt":0.3282756140508642,"score_spread":0.25842367005690287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221101816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027103182,0.00007355808,0.9939865,0.0017730523,0.00025862726,0.0006480895,0.000059526265,0.00039790035,0.00009243682],"genre_scores_gemma":[0.59102696,0.0000096670565,0.4074917,0.0002578329,0.00020152466,0.0009034425,0.000018656425,0.000027023098,0.0000631559],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814063,0.00017894374,0.0003608909,0.0005599506,0.0004556209,0.00030398276],"domain_scores_gemma":[0.9990859,0.00012047485,0.00034608314,0.00025131268,0.00013745436,0.00005875316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012040992,0.00017418132,0.00016718933,0.00022565547,0.0008394711,0.0001293795,0.00048625158,0.00004530762,0.00013560943],"category_scores_gemma":[0.00000952764,0.00019477574,0.00009197186,0.0005178349,0.000021042562,0.00044246175,0.00016127033,0.00027292114,0.0000010485053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049167033,0.000081002836,0.00034653363,0.000024572852,0.000025306212,3.912822e-7,0.000395317,0.0076281964,0.7157377,0.004168296,0.000071127695,0.2714724],"study_design_scores_gemma":[0.00041517816,0.00012745862,0.0019773666,0.000019553481,0.000028815093,0.000059663755,0.00013873843,0.9581991,0.030217338,0.0003613515,0.008230114,0.00022533874],"about_ca_topic_score_codex":0.0003622054,"about_ca_topic_score_gemma":0.000031544212,"teacher_disagreement_score":0.9505709,"about_ca_system_score_codex":0.00095717993,"about_ca_system_score_gemma":0.00015816302,"threshold_uncertainty_score":0.7942724},"labels":[],"label_agreement":null},{"id":"W4224988658","doi":"10.1109/isbi52829.2022.9761550","title":"Semi-Supervised Tumor Response Grade Classification from Histology Images of Colorectal Liver Metastases","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Colorectal cancer; Pattern recognition (psychology); Segmentation; Contextual image classification; Medicine; Cancer; Internal medicine; Image (mathematics)","score_opus":0.017962215900082883,"score_gpt":0.2672617231353203,"score_spread":0.24929950723523744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224988658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72747153,0.00076922384,0.18294904,0.061231986,0.022452015,0.00089105044,0.002183764,0.00066160376,0.001389762],"genre_scores_gemma":[0.9917447,0.000038098693,0.0057619666,0.0014820808,0.00026615284,0.00023121442,0.0001634946,0.000031366035,0.00028095674],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957377,0.00078714854,0.00066389586,0.0008716947,0.0015915215,0.00034804677],"domain_scores_gemma":[0.99783564,0.0008367229,0.00044744636,0.00054244266,0.00016560928,0.00017213821],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010358862,0.00026145295,0.00032114756,0.0005120833,0.00029481886,0.000088061504,0.0018580357,0.00005218682,0.0009690504],"category_scores_gemma":[0.00019135291,0.00027436254,0.00018567136,0.000690069,0.00039570828,0.00033312335,0.00056056865,0.00053848536,0.000055833498],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011005237,0.0007703072,0.0010731564,0.000014651781,0.00016801956,0.00025754672,0.0007611697,0.00032449132,0.9487538,0.0012046288,0.035659086,0.0099126715],"study_design_scores_gemma":[0.0031283337,0.0012388404,0.014808988,0.00007277019,0.00009593323,0.00051153137,0.00039597528,0.6415787,0.1710226,0.0013981168,0.16487356,0.00087469385],"about_ca_topic_score_codex":0.00043350263,"about_ca_topic_score_gemma":0.0000054537945,"teacher_disagreement_score":0.7777312,"about_ca_system_score_codex":0.0010993344,"about_ca_system_score_gemma":0.0002189682,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W4224999590","doi":"10.1109/isbi52829.2022.9761413","title":"Automated Dcis Identification From Multiplex Immunohistochemistry Using Generative Adversarial Networks","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"Breast Cancer Now","keywords":"Ductal carcinoma; Artificial intelligence; Breast cancer; Computer science; Convolutional neural network; Multiplex; Deep learning; Pattern recognition (psychology); Segmentation; Immunohistochemistry; Pathology; Cancer; Medicine; Biology; Internal medicine; Bioinformatics","score_opus":0.012214064952695405,"score_gpt":0.28123459685206426,"score_spread":0.26902053189936886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224999590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043927655,0.00017711351,0.91926163,0.0056954552,0.02866522,0.00038226024,0.0002464747,0.0010042642,0.0006399377],"genre_scores_gemma":[0.98830104,0.000021104095,0.0074246633,0.0012334107,0.0018190928,0.00018291925,0.0005369052,0.000041556945,0.00043932052],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960488,0.00023453627,0.0006992438,0.0010023145,0.0016160142,0.00039907778],"domain_scores_gemma":[0.9983458,0.00018423489,0.00048686133,0.00063970353,0.00017233987,0.0001710439],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005702568,0.00029549832,0.00023733797,0.00024341398,0.0007148361,0.00031969286,0.0018525529,0.00009391055,0.0006426349],"category_scores_gemma":[0.000067336376,0.00033884073,0.00016641343,0.00069448614,0.00019282801,0.00052746263,0.00066626596,0.00069302414,0.000047927468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001493052,0.00034903325,0.00025450217,0.000006109149,0.00021860246,0.00008426829,0.000661629,0.064228706,0.89913243,0.00022920036,0.023869086,0.010817108],"study_design_scores_gemma":[0.0009346203,0.00005155438,0.00025685862,0.000024315603,0.000021335407,0.00005475482,0.00006063423,0.96863407,0.018126175,0.00018136163,0.011317785,0.00033654028],"about_ca_topic_score_codex":0.00075595547,"about_ca_topic_score_gemma":0.000002390935,"teacher_disagreement_score":0.94437337,"about_ca_system_score_codex":0.0022453156,"about_ca_system_score_gemma":0.00016491457,"threshold_uncertainty_score":0.99990636},"labels":[],"label_agreement":null},{"id":"W4225086334","doi":"10.1007/s12539-022-00515-1","title":"Feature Generalization for Breast Cancer Detection in Histopathological Images","year":2022,"lang":"en","type":"article","venue":"Interdisciplinary Sciences Computational Life Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Overfitting; Feature learning; Feature extraction; Transfer of learning; Feature (linguistics); Histogram; Deep learning; Local binary patterns; Histogram of oriented gradients; Machine learning; Artificial neural network; Image (mathematics)","score_opus":0.02589910239017413,"score_gpt":0.32568874294969935,"score_spread":0.29978964055952523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225086334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11801723,0.00056529813,0.8393148,0.036966868,0.0035641976,0.0006267319,0.000138122,0.00023274132,0.0005739915],"genre_scores_gemma":[0.96284336,0.0000074008335,0.035633273,0.000779012,0.00018649998,0.00041589068,0.0000058810847,0.000006967946,0.00012169177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686414,0.0002530421,0.00033695175,0.0010612435,0.001035807,0.00044883476],"domain_scores_gemma":[0.99904937,0.0002929555,0.00025958705,0.00016532947,0.0001361731,0.000096617216],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0018541652,0.0001958366,0.00020142952,0.00065658556,0.0029054217,0.00024892518,0.0017266131,0.000048587168,0.00005985918],"category_scores_gemma":[0.000045886707,0.0001768226,0.000104759536,0.0028315443,0.0007101358,0.0015126995,0.0013469934,0.00023081875,0.000004122637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003830976,0.0000829646,0.0033978643,0.000010515476,0.0000038227754,0.000005857992,0.00067891,0.9583373,0.00068245275,0.0069717597,0.0022034787,0.027586782],"study_design_scores_gemma":[0.000319138,0.00064593146,0.05693105,0.000017566936,0.0000036853546,0.00020610804,0.0005443374,0.8906999,0.00019251034,0.04963081,0.00051187695,0.00029706498],"about_ca_topic_score_codex":0.000034162873,"about_ca_topic_score_gemma":0.00005968859,"teacher_disagreement_score":0.84482616,"about_ca_system_score_codex":0.00049564446,"about_ca_system_score_gemma":0.00054942287,"threshold_uncertainty_score":0.99839264},"labels":[],"label_agreement":null},{"id":"W4225463219","doi":"10.22215/etd/2022-14880","title":"Automated Segmentation of Complex Biological Structures in Histopathology Images","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Histopathology; Computer science; Segmentation; Artificial intelligence; Image segmentation; Pattern recognition (psychology); Pathology; Medicine","score_opus":0.02833472268173314,"score_gpt":0.32609211949508926,"score_spread":0.2977573968133561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225463219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9147375,0.00089158595,0.049773537,0.00026147722,0.006507158,0.0013656975,0.000066490655,0.002266597,0.024129942],"genre_scores_gemma":[0.9552703,0.00006066663,0.04270373,0.000101509315,0.000027924218,0.00010879948,0.0008002646,0.00001537966,0.0009114632],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986672,0.00018553481,0.00037881,0.00040723357,0.00021407525,0.00014719102],"domain_scores_gemma":[0.9992906,0.00006107935,0.00030522433,0.00026756932,0.000056835226,0.000018700463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015862519,0.00015316356,0.00027194674,0.0003335182,0.00005436029,0.000018413622,0.000537405,0.00015633587,0.00066072243],"category_scores_gemma":[0.000024773297,0.00014304556,0.000053754746,0.00040181406,0.000033329336,0.00011766916,0.00008921649,0.00021850309,0.0000033057984],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032410372,0.00029520516,0.0059157056,0.0004789788,0.000055631466,0.00012759597,0.008200985,0.0032283962,0.7563547,0.033492185,0.016067222,0.17545931],"study_design_scores_gemma":[0.00082373316,0.00068436045,0.890185,0.00002524342,0.000015531354,0.00004768542,0.0015177688,0.028680885,0.06455597,0.011646841,0.0011961131,0.00062088144],"about_ca_topic_score_codex":0.00023433508,"about_ca_topic_score_gemma":0.0002598093,"teacher_disagreement_score":0.8842693,"about_ca_system_score_codex":0.00026181736,"about_ca_system_score_gemma":0.00008589842,"threshold_uncertainty_score":0.7234447},"labels":[],"label_agreement":null},{"id":"W4226054404","doi":"10.1016/j.jpi.2022.100002","title":"MiNuGAN: Dual Segmentation of Mitoses and Nuclei Using Conditional GANs on Multi-center Breast H&amp;E Images","year":2022,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Mitosis; Grading (engineering); Biology","score_opus":0.028834968179859557,"score_gpt":0.28713162013982657,"score_spread":0.25829665195996704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226054404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72208244,0.000023227678,0.27702546,0.00017369346,0.0005268821,0.000056332272,0.00006357001,0.000007513978,0.000040870986],"genre_scores_gemma":[0.84248525,0.000013231241,0.15705623,0.00036311115,0.0000597358,0.0000018603977,0.0000057226653,0.000005004633,0.000009855399],"study_design_codex":"bench_or_experimental","study_design_gemma":"case_report","domain_scores_codex":[0.99889314,0.00008528848,0.00054841524,0.00005188878,0.00031318312,0.00010805585],"domain_scores_gemma":[0.9988221,0.000072833376,0.00081399037,0.00011069811,0.000141387,0.000039016246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003666251,0.00007988302,0.00015701354,0.00023605229,0.00013794821,0.00002933992,0.00018044021,0.000033748936,0.000018648172],"category_scores_gemma":[0.00002198811,0.00007494698,0.000050412065,0.00012450083,0.00008533112,0.0006465118,0.00013284635,0.00022798861,0.0000018835636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014186503,0.005819843,0.07714529,0.0011636092,0.0011035575,0.0015064476,0.1841322,0.18680793,0.34391466,0.0054945,0.021581808,0.16991152],"study_design_scores_gemma":[0.03186654,0.009202335,0.1635467,0.0005162847,0.0004357187,0.33659434,0.029824637,0.3278269,0.08656441,0.0055042296,0.006217863,0.0019000436],"about_ca_topic_score_codex":0.0000011624376,"about_ca_topic_score_gemma":0.000001035468,"teacher_disagreement_score":0.3350879,"about_ca_system_score_codex":0.00011271945,"about_ca_system_score_gemma":0.0000717099,"threshold_uncertainty_score":0.3056249},"labels":[],"label_agreement":null},{"id":"W4226072173","doi":"10.3389/fonc.2022.772403","title":"Automatic Prostate Gleason Grading Using Pyramid Semantic Parsing Network in Digital Histopathology","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Histopathology; Parsing; Computer science; Grading (engineering); Prostate; Artificial intelligence; Medicine; Prostate cancer; Natural language processing; Pathology; Internal medicine; Cancer; Biology","score_opus":0.014215524939486893,"score_gpt":0.25678313221977866,"score_spread":0.24256760728029178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226072173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5941968,0.0011000681,0.3933255,0.000604456,0.009684837,0.00045232155,0.0000019413856,0.00018137367,0.0004527181],"genre_scores_gemma":[0.91196674,0.000015595777,0.087514274,0.00025470322,0.00009691579,0.00008691685,0.00000299325,0.000021178246,0.000040660674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978139,0.00032960193,0.00045630184,0.0005403314,0.00021146743,0.0006484135],"domain_scores_gemma":[0.99924695,0.000104115905,0.00023698468,0.00033982866,0.000018607016,0.000053524098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007793856,0.00016321769,0.00041572686,0.00045275586,0.00024264406,0.000060731054,0.00061110663,0.00009914551,0.0000096693175],"category_scores_gemma":[0.00006364867,0.00020438641,0.000051576855,0.0012045982,0.00012305233,0.0004988183,0.0005247784,0.00055068283,0.0000027387714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009044889,0.0002403053,0.24504888,0.00005859888,0.000016562,0.0013115488,0.006813075,0.19579294,0.00021774031,0.0010229774,0.006122556,0.5432644],"study_design_scores_gemma":[0.0007023091,0.00039352302,0.0056219194,0.000037940415,0.0000065614854,0.00039196844,0.00042578287,0.9630101,0.000013048141,0.020241529,0.0089139305,0.00024143272],"about_ca_topic_score_codex":0.00007369728,"about_ca_topic_score_gemma":0.00004626284,"teacher_disagreement_score":0.7672171,"about_ca_system_score_codex":0.004565408,"about_ca_system_score_gemma":0.0003089531,"threshold_uncertainty_score":0.9992559},"labels":[],"label_agreement":null},{"id":"W4226188536","doi":"10.1109/embc48229.2022.9871198","title":"Hospital-Agnostic Image Representation Learning in Digital Pathology","year":2022,"lang":"en","type":"article","venue":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Generalization; Representation (politics); Digital pathology; Computer vision; Machine learning; Pattern recognition (psychology); Domain (mathematical analysis); Image (mathematics); Visualization; Deep learning; Mathematics","score_opus":0.02068158496392965,"score_gpt":0.28571979908957706,"score_spread":0.26503821412564743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226188536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8078366,0.00019429486,0.1776359,0.0070834015,0.006077259,0.00034925767,0.000048495618,0.00013434018,0.00064044667],"genre_scores_gemma":[0.9966812,0.00014335666,0.0023222256,0.00016545813,0.00015183412,0.00009255908,0.000049905335,0.000012476551,0.0003809415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984157,0.00011468014,0.00044899827,0.00042766807,0.00032581371,0.00026714517],"domain_scores_gemma":[0.9988714,0.00035445948,0.0002302753,0.0003218381,0.00018442523,0.00003759581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006308032,0.00016583332,0.0002614623,0.00024384719,0.000084122796,0.000022494567,0.0012306416,0.00008777834,0.00011120379],"category_scores_gemma":[0.0008177598,0.00015007977,0.000104267434,0.00079792924,0.00019268424,0.00034680695,0.00056807604,0.0008653257,0.0000043438263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015836395,0.00065496133,0.1886308,0.00015581223,0.00041064376,0.00006459666,0.057144735,0.5556776,0.1260339,0.024201939,0.03045269,0.016413968],"study_design_scores_gemma":[0.0048829187,0.0017684816,0.092758164,0.0004090948,0.00003725862,0.0002535064,0.005739074,0.8514661,0.0020290297,0.013231406,0.02619682,0.0012281102],"about_ca_topic_score_codex":0.00020771683,"about_ca_topic_score_gemma":0.000033519165,"teacher_disagreement_score":0.29578856,"about_ca_system_score_codex":0.00026532562,"about_ca_system_score_gemma":0.00008947168,"threshold_uncertainty_score":0.61200756},"labels":[],"label_agreement":null},{"id":"W4226516420","doi":"","title":"Implementing Epic Beaker Laboratory Information System for Diagnostics in Anatomic Pathology","year":2022,"lang":"en","type":"review","venue":"Dove Medical Press (Taylor and Francis Group)","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Alberta; University of Ottawa","funders":"","keywords":"EPIC; Desk; Radiological weapon; Medicine; Beaker; Pathology; Medical physics; Computer science; Radiology; History","score_opus":0.025485637479713663,"score_gpt":0.29609280022329965,"score_spread":0.270607162743586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226516420","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015385688,0.5049174,0.4926768,0.00001465074,0.0014084292,0.00069811096,0.00013185067,0.00007413473,0.00007709746],"genre_scores_gemma":[0.0087566,0.98003596,0.0030253201,0.0007468809,0.000979432,0.005863943,0.0004994305,0.0000915711,8.3699484e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968219,0.00034791563,0.0011076934,0.0005427266,0.0005996522,0.00058011105],"domain_scores_gemma":[0.9975137,0.0012138336,0.0005217658,0.00050989346,0.00005865841,0.00018212893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022689204,0.0003411149,0.0010524015,0.00029308247,0.00021553638,0.00012758373,0.0008846435,0.00040958554,0.00005255381],"category_scores_gemma":[0.00071448076,0.00030664954,0.00016825156,0.0004908782,0.000079341546,0.0005451507,0.00078942504,0.0007587016,0.0000069999983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037929497,0.000015080247,0.000015462385,0.008052518,0.000027667316,0.00003347406,0.00030262445,0.0000011465833,3.389974e-8,0.0031892206,0.000031041927,0.9883279],"study_design_scores_gemma":[0.00065611454,0.000097540105,0.00000847557,0.00014645545,0.00010118047,0.0000656024,0.00009571605,0.083325945,8.666338e-7,0.00010790614,0.91506076,0.00033343007],"about_ca_topic_score_codex":0.000070681184,"about_ca_topic_score_gemma":0.000044145574,"teacher_disagreement_score":0.9879945,"about_ca_system_score_codex":0.00032983941,"about_ca_system_score_gemma":0.000021411664,"threshold_uncertainty_score":0.99993855},"labels":[],"label_agreement":null},{"id":"W4229003695","doi":"10.1186/s12885-022-09613-1","title":"Cost-effectiveness of using artificial intelligence versus polygenic risk score to guide breast cancer screening","year":2022,"lang":"en","type":"article","venue":"BMC Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Medicine; Breast cancer screening; Mammography; Breast cancer; Family history; Risk assessment; Cancer screening; Gynecology; Cancer; Internal medicine; Computer science","score_opus":0.16633481193913788,"score_gpt":0.3833364305709453,"score_spread":0.21700161863180742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229003695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17883497,0.00054003915,0.816318,0.000088743654,0.0032471768,0.00062784046,0.0001944512,0.00009265223,0.000056157874],"genre_scores_gemma":[0.9798802,0.000043297907,0.018870365,0.00007524493,0.00034440603,0.0007277771,0.0000015948638,0.000032583135,0.00002450568],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975268,0.0003730166,0.00039050868,0.0006662697,0.000622409,0.0004209761],"domain_scores_gemma":[0.9985098,0.0002705004,0.0002887485,0.00060698495,0.0001977751,0.00012613961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008200491,0.0002046239,0.00027342406,0.00023517721,0.00043230024,0.00006412577,0.00092823314,0.000047157697,0.00026609047],"category_scores_gemma":[0.000051285777,0.00023330454,0.00012981216,0.0015601085,0.0000658403,0.00031484704,0.00078578887,0.00028736165,0.0000054687903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011011979,0.000036825833,0.010931325,0.000046781923,0.000060892333,0.0000028486934,0.00039325014,0.6810718,0.004125743,0.0011134539,0.00007727905,0.3010386],"study_design_scores_gemma":[0.0014272762,0.00066482055,0.085997455,0.00060563156,0.00023084597,0.00007737326,0.0010242811,0.78966373,0.11244152,0.0022018852,0.0040977164,0.0015674538],"about_ca_topic_score_codex":0.018466169,"about_ca_topic_score_gemma":0.0029650258,"teacher_disagreement_score":0.80104524,"about_ca_system_score_codex":0.0017790078,"about_ca_system_score_gemma":0.0008219484,"threshold_uncertainty_score":0.98806995},"labels":[],"label_agreement":null},{"id":"W4229443674","doi":"10.18280/ts.390214","title":"A New Hybrid Breast Cancer Diagnosis Model Using Deep Learning Model and ReliefF","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Support vector machine; Computer science; Machine learning; Convolutional neural network; Naive Bayes classifier; Deep learning; Breast cancer; Pattern recognition (psychology); Transfer of learning; Classifier (UML); Artificial neural network; Cancer; Medicine","score_opus":0.02322270039703138,"score_gpt":0.2461706726459423,"score_spread":0.22294797224891094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229443674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13405408,0.0003487652,0.86436385,0.000728764,0.00010566549,0.00017195586,0.00001766523,0.0001383819,0.00007087972],"genre_scores_gemma":[0.96067125,0.00008120279,0.038280036,0.0004370203,0.0001215437,0.00025512115,0.0000019378772,0.000022541595,0.0001293297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984064,0.000070901726,0.00022497734,0.0004868587,0.0004962492,0.00031462207],"domain_scores_gemma":[0.9994906,0.000036131725,0.000118927186,0.00018291459,0.000038799688,0.00013263786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002567764,0.0001664517,0.00015191507,0.00011919308,0.000542969,0.00012349569,0.00038930614,0.000020701282,0.0002709741],"category_scores_gemma":[0.0000026397906,0.0001880399,0.000057732137,0.00024535353,0.000021925609,0.0004651475,0.00042494238,0.0002807095,0.0000016483383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021900074,0.000029462948,0.0007560157,0.000008733235,0.000019472542,0.000005016075,0.00078293966,0.9058656,0.0009906988,0.0003433287,0.00079221575,0.09038463],"study_design_scores_gemma":[0.0005211077,0.00008230062,0.00033628687,0.000015309006,0.000023814222,0.000063841464,0.000031599666,0.9958691,0.00042518668,0.0020189818,0.00039147504,0.00022099742],"about_ca_topic_score_codex":0.00040859834,"about_ca_topic_score_gemma":0.00002443305,"teacher_disagreement_score":0.8266172,"about_ca_system_score_codex":0.0004372918,"about_ca_system_score_gemma":0.00019863709,"threshold_uncertainty_score":0.76680446},"labels":[],"label_agreement":null},{"id":"W4229568859","doi":"10.1053/j.semdp.2009.09.006","title":"Primary frozen section diagnosis by robotic microscopy and virtual slide telepathology: the University Health Network experience","year":2009,"lang":"en","type":"article","venue":"Seminars in Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Telepathology; Frozen section procedure; Medicine; Medical diagnosis; Medical laboratory; Nuclear medicine; Pathology; Health care; Telemedicine","score_opus":0.006747183872741627,"score_gpt":0.23822620694807345,"score_spread":0.23147902307533183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229568859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.787732,0.0075864154,0.19509861,0.0066771586,0.0019594964,0.00058885297,0.000008364571,0.0001906747,0.00015843878],"genre_scores_gemma":[0.9684995,0.010595824,0.014411454,0.0061497004,0.00018273863,0.000052283624,0.000008955052,0.0000142168265,0.00008536675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997573,0.00060882827,0.0003226487,0.00073263905,0.00016396576,0.0005988852],"domain_scores_gemma":[0.9970602,0.0020339086,0.00020555318,0.00056062045,0.00003098513,0.000108777145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073081057,0.00022235051,0.00034102518,0.00011845579,0.00040064863,0.000043936714,0.00070553884,0.00019787339,0.0000054845978],"category_scores_gemma":[0.0005229949,0.00021306475,0.000041772808,0.00067109213,0.0003284109,0.00033249366,0.00028841986,0.00044439433,0.000008118535],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013312526,0.00057616225,0.2763946,0.000041726456,0.000022359192,0.0017281348,0.02190178,0.008625328,0.006334209,0.00310129,0.117852494,0.56328875],"study_design_scores_gemma":[0.00235416,0.0054317107,0.94168377,0.000694215,0.00004771978,0.0025417903,0.0016941588,0.005166668,0.0037444704,0.00778301,0.027493753,0.0013645884],"about_ca_topic_score_codex":0.00008347786,"about_ca_topic_score_gemma":0.00007093985,"teacher_disagreement_score":0.66528916,"about_ca_system_score_codex":0.00043905448,"about_ca_system_score_gemma":0.00010641728,"threshold_uncertainty_score":0.8688528},"labels":[],"label_agreement":null},{"id":"W4230205729","doi":"10.1155/2011/564210","title":"Abstracts of the 1st Congress of the International Academy of Digital Pathology August 3–5, 2011 Quebec city, Canada","year":2011,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Centres Intégré Universitaires de Santé et de Services Sociaux; University Health Network","funders":"Massachusetts General Hospital","keywords":"Digital pathology; Library science; Medicine; Pathology; Political science; Computer science","score_opus":0.033618945133769666,"score_gpt":0.23762981294289884,"score_spread":0.20401086780912916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230205729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832795,0.00006897756,0.0063656927,0.0016379394,0.0015077834,0.00015519875,0.000048579408,0.000013817214,0.006922473],"genre_scores_gemma":[0.9988694,0.000005359111,0.00021320651,0.00020170094,0.00003811799,0.0000031773147,0.0000012839703,0.0000071460045,0.00066060404],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984117,0.000120217075,0.0005513733,0.0002993623,0.00039422256,0.00022313236],"domain_scores_gemma":[0.9987993,0.000119537326,0.0003711394,0.00051229313,0.00014446647,0.000053249118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030270318,0.00012661073,0.00027197553,0.00006218907,0.00004074445,0.0000094470815,0.0018531431,0.00016985858,0.00013168684],"category_scores_gemma":[0.00014569837,0.00008403377,0.00014372861,0.00021013957,0.00069229637,0.00014999496,0.0007792376,0.00031460563,0.000004246717],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024643782,0.0015000212,0.47818965,0.00028107956,0.00079982716,0.0006649009,0.0029874984,0.00077882904,0.15173937,0.31824854,0.027047914,0.017515907],"study_design_scores_gemma":[0.00063557096,0.00015961513,0.42845482,0.000049470975,0.00009796808,0.00027185533,0.00009803613,0.003844827,0.5533393,0.010279687,0.0024672875,0.00030154843],"about_ca_topic_score_codex":0.049944356,"about_ca_topic_score_gemma":0.05511968,"teacher_disagreement_score":0.40159994,"about_ca_system_score_codex":0.00008897739,"about_ca_system_score_gemma":0.00037249815,"threshold_uncertainty_score":0.9621219},"labels":[],"label_agreement":null},{"id":"W4230628205","doi":"10.32768/abc.20207118-24","title":"Accurate Detection of Breast Cancer Metastasis Using a Hybrid Model of Artificial Intelligence Algorithm","year":2020,"lang":"en","type":"article","venue":"Archives of Breast Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Algorithm; Breast cancer; Support vector machine; Computer science; Artificial intelligence; Classifier (UML); Logistic regression; Perceptron; Machine learning; Cross-validation; Cancer; Artificial neural network; Medicine; Internal medicine","score_opus":0.05170118406221385,"score_gpt":0.2915836875612417,"score_spread":0.23988250349902784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230628205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042926956,0.00028854917,0.954423,0.0007234738,0.0002819203,0.00020427775,0.0010689383,0.000050604092,0.00003224705],"genre_scores_gemma":[0.9492762,0.00024678293,0.050170437,0.00008040837,0.00016594256,0.000032602507,0.0000013470543,0.000023331986,0.0000029653527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979644,0.000094907715,0.0006773168,0.0005262815,0.00043016172,0.00030696017],"domain_scores_gemma":[0.99849737,0.000088687346,0.00065823284,0.00041064815,0.00020755826,0.00013749834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012310798,0.00023031901,0.00045599043,0.00020331563,0.000076212564,0.000024134348,0.0007284369,0.000040008224,0.000033727945],"category_scores_gemma":[0.000013105245,0.00023325568,0.0002059476,0.00067102164,0.00028215756,0.0005512117,0.00031134515,0.00019321273,0.000001130154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017342543,0.00004150232,0.00004467131,0.00010765391,0.00009522368,9.437909e-7,0.00090973824,0.1355874,0.18573585,0.00016948087,0.0000029878736,0.6771311],"study_design_scores_gemma":[0.0000913697,0.000049953367,0.00074124866,0.00010461226,0.00005174805,0.000027356127,0.00005280937,0.688767,0.30805206,0.001912316,0.000004756768,0.00014473315],"about_ca_topic_score_codex":0.0024294748,"about_ca_topic_score_gemma":0.00011774607,"teacher_disagreement_score":0.90634924,"about_ca_system_score_codex":0.00008414436,"about_ca_system_score_gemma":0.00040322889,"threshold_uncertainty_score":0.95118904},"labels":[],"label_agreement":null},{"id":"W4231340752","doi":"10.1179/014788805794775334","title":"Issues About Tissues, Part I: The Objectives of Histopathology","year":2005,"lang":"en","type":"article","venue":"Journal of Histotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histopathology; Medicine; Pathology; Autopsy; Biopsy; Demise; Medical physics; General surgery; Political science","score_opus":0.009135932362235073,"score_gpt":0.25400001797935384,"score_spread":0.24486408561711878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231340752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17183757,0.11633773,0.57511646,0.12200634,0.008128401,0.00039576352,0.0000037537015,0.00042120658,0.005752788],"genre_scores_gemma":[0.95632845,0.0012325026,0.040790778,0.00029602903,0.0004641601,0.0000056549416,8.5269264e-8,0.000013124045,0.0008692106],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987622,0.00010699599,0.00054205366,0.00016710968,0.00022690518,0.00019475236],"domain_scores_gemma":[0.9983554,0.00007840366,0.0007788675,0.00053844426,0.00021944309,0.000029438846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054057885,0.00010888001,0.00031162243,0.00031830225,0.00008953809,0.000010376525,0.001260718,0.00018666098,0.000030243073],"category_scores_gemma":[0.00014879499,0.000078716585,0.000103901926,0.00032172346,0.00040531965,0.00028528375,0.0001540105,0.0004851262,0.000018298872],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000846527,0.00022911848,0.0005687282,0.000027215752,0.00007381112,0.00012298542,0.0036472967,0.0007007954,0.030136934,0.08986776,0.038845267,0.83569545],"study_design_scores_gemma":[0.00029890682,0.00070212694,0.000989584,0.000028540984,0.000019288564,0.0017789622,0.000095302086,0.00046159833,0.037344553,0.008620117,0.94955426,0.00010673576],"about_ca_topic_score_codex":0.000018106453,"about_ca_topic_score_gemma":0.000035568355,"teacher_disagreement_score":0.910709,"about_ca_system_score_codex":0.00029385602,"about_ca_system_score_gemma":0.00010607321,"threshold_uncertainty_score":0.3209969},"labels":[],"label_agreement":null},{"id":"W4231340977","doi":"10.1155/2011/769680","title":"Welcome to the 1st Congress of the International Academy of Digital Pathology","year":2011,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Digital pathology; Library science; Pathology; Political science; Medicine; Computer science","score_opus":0.04453798976563801,"score_gpt":0.2671184635165611,"score_spread":0.2225804737509231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231340977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59776247,0.00014472741,0.36898383,0.014905931,0.0042185294,0.0004278177,0.000039931867,0.00006984538,0.01344694],"genre_scores_gemma":[0.997992,0.000006001753,0.000984254,0.00057661254,0.00010076485,0.0000088994275,7.711348e-7,0.0000068029317,0.00032390928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987343,0.00012421828,0.00035683616,0.00031147595,0.000262305,0.00021089695],"domain_scores_gemma":[0.9991053,0.00010085712,0.00016776657,0.00048625033,0.00008696749,0.000052889434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039461546,0.00010521461,0.0002030292,0.00009041115,0.000047130616,0.00001652062,0.0019084617,0.00012710186,0.00006553403],"category_scores_gemma":[0.00015422862,0.000064500564,0.00013064484,0.00034988535,0.00039085004,0.00012906297,0.0008456959,0.00024521037,0.000053692886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017139134,0.0006910995,0.06278777,0.00005467689,0.00032577268,0.0003531857,0.0054703373,0.0003413777,0.060584415,0.8264721,0.008710712,0.034037128],"study_design_scores_gemma":[0.0020201886,0.0017338357,0.18697232,0.00010430796,0.00023836673,0.0015688166,0.00042933878,0.05972155,0.57812876,0.11003566,0.057929356,0.0011175295],"about_ca_topic_score_codex":0.000008335135,"about_ca_topic_score_gemma":0.0000044773105,"teacher_disagreement_score":0.71643645,"about_ca_system_score_codex":0.000029258594,"about_ca_system_score_gemma":0.0000326986,"threshold_uncertainty_score":0.35464284},"labels":[],"label_agreement":null},{"id":"W4233531354","doi":"10.1007/978-3-030-50402-1","title":"Artificial Intelligence and Machine Learning for Digital Pathology","year":2020,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Biobank; Computer science; Digital pathology; Artificial intelligence; Block (permutation group theory); Data science; Deep learning; Bioinformatics","score_opus":0.030907480100315403,"score_gpt":0.2575827554205666,"score_spread":0.22667527532025117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233531354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028788767,0.00054891186,0.9955358,0.0013889449,0.0016210568,0.0004334961,0.000008587105,0.00020925356,0.00022516989],"genre_scores_gemma":[0.29731598,0.00012811934,0.6979866,0.0020439702,0.0020179816,0.000071265364,0.000028114371,0.000080635764,0.00032730988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968777,0.00004200258,0.00045371384,0.0016042149,0.00047426962,0.0005481337],"domain_scores_gemma":[0.9981158,0.00080071384,0.00024412325,0.00053968217,0.00014588222,0.00015379439],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005397566,0.0003848287,0.0004350263,0.0004339081,0.0002956078,0.0008592995,0.0018447562,0.0002665963,0.000002866656],"category_scores_gemma":[0.00039488994,0.00037763422,0.000086918764,0.0007963408,0.00065227045,0.0006877048,0.0013339642,0.00091026456,0.000015660115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010109484,0.000009796701,0.000027282404,0.00004406549,0.000004181855,0.00003453516,0.0006223479,0.0200147,0.000060008046,0.001955294,0.000016114554,0.9772016],"study_design_scores_gemma":[0.000043236665,0.00045054607,0.000010280526,0.00008717984,0.0000041609774,0.00010273879,2.0363656e-7,0.7678774,0.0017232187,0.22691579,0.0024299196,0.0003553391],"about_ca_topic_score_codex":0.0000043223367,"about_ca_topic_score_gemma":0.000026146543,"teacher_disagreement_score":0.9768462,"about_ca_system_score_codex":0.0003110453,"about_ca_system_score_gemma":0.00061441277,"threshold_uncertainty_score":0.99986756},"labels":[],"label_agreement":null},{"id":"W4233928497","doi":"10.1093/jicru_ndp021","title":"5. Technical Aspects of Image Quality in Mammography","year":2009,"lang":"en","type":"article","venue":"Journal of the ICRU","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mammography; Quality (philosophy); Image quality; Computer science; Psychology; Artificial intelligence; Image (mathematics); Medicine; Epistemology; Philosophy; Breast cancer","score_opus":0.014453786419871986,"score_gpt":0.29620436411376805,"score_spread":0.28175057769389605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233928497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6024201,0.0007247862,0.35843495,0.022816597,0.0019032499,0.00023588043,0.0000014300527,0.000050354418,0.0134126395],"genre_scores_gemma":[0.981404,0.000015177283,0.018321026,0.00018260763,0.00006721257,2.2096661e-7,5.691279e-9,0.0000017944134,0.000007968765],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989956,0.00010766676,0.0003907499,0.00007420642,0.00033358127,0.00009816688],"domain_scores_gemma":[0.9990929,0.00005508197,0.00041917094,0.0003182353,0.00008448326,0.000030163637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085429393,0.000051430525,0.00014895896,0.0001320712,0.000022356293,0.000022461765,0.0008606957,0.00003756975,0.0000030117305],"category_scores_gemma":[0.000085100815,0.000033807857,0.00015651986,0.00056354277,0.00004093861,0.00027434394,0.000067278015,0.00026947126,8.9558193e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021289282,0.0007110011,0.00920636,0.000043320913,0.000040924035,0.00008291114,0.0007562993,0.00053830043,0.7550809,0.051604778,0.0059586684,0.17576367],"study_design_scores_gemma":[0.0007196979,0.00049329194,0.69752634,0.00015240909,0.000010381486,0.00031626187,0.000022363003,0.0003204435,0.13719098,0.1620408,0.0010749487,0.00013210521],"about_ca_topic_score_codex":0.000011897923,"about_ca_topic_score_gemma":0.000020628728,"teacher_disagreement_score":0.68832,"about_ca_system_score_codex":0.000076287295,"about_ca_system_score_gemma":0.00006573841,"threshold_uncertainty_score":0.15994012},"labels":[],"label_agreement":null},{"id":"W4235038263","doi":"10.35940/ijeat.b4916.129219","title":"Skin Cancer Diagnostic using Machine Learning Techniques - Shearlet Transform and Naïve Bayes Classifier","year":2019,"lang":"en","type":"article","venue":"International Journal of Engineering and Advanced Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Shearlet; Naive Bayes classifier; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Bayes classifier; Computer science; Bayes' theorem; Melanoma diagnosis; Contextual image classification; Mathematics; Melanoma; Support vector machine; Medicine; Image (mathematics); Bayesian probability","score_opus":0.004429185020775231,"score_gpt":0.24287392209326328,"score_spread":0.23844473707248803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235038263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53046745,0.002513732,0.46437117,0.0016324476,0.0007883118,0.00007518251,0.0000022288598,0.00012447739,0.000025022797],"genre_scores_gemma":[0.92631525,0.0016045704,0.07194441,0.00002563301,0.000075609685,0.0000050824765,2.3083032e-7,0.00001087004,0.000018345358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993538,0.0000067151877,0.00021253519,0.0001463045,0.00015645678,0.00012418223],"domain_scores_gemma":[0.99953175,0.000107737666,0.00012546533,0.00007219837,0.00012889899,0.00003394312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010348255,0.00010155289,0.00015323995,0.0004233107,0.000027042757,0.000042123305,0.0002742077,0.000083074854,0.000005420845],"category_scores_gemma":[0.00009285733,0.000094734656,0.000028924173,0.00015115828,0.000030293864,0.0004203903,0.000078407895,0.0003637589,3.7587142e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029775456,0.000022530092,0.0067430567,0.00003809179,0.00013165295,0.00005341457,0.00017241779,0.027134433,0.17013794,0.0045633637,0.0000035911885,0.7909697],"study_design_scores_gemma":[0.0018224742,0.00074138,0.0026052122,0.001216597,0.000034997945,0.0028488003,0.00011232652,0.57384837,0.36793151,0.0068606776,0.041365635,0.0006120185],"about_ca_topic_score_codex":0.000013359347,"about_ca_topic_score_gemma":0.0000037447792,"teacher_disagreement_score":0.7903577,"about_ca_system_score_codex":0.00010162508,"about_ca_system_score_gemma":0.000024518886,"threshold_uncertainty_score":0.38631672},"labels":[],"label_agreement":null},{"id":"W4235505678","doi":"10.32920/ryerson.14663766","title":"Towards Improved Medical Image Segmentation Using Deep Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Medical imaging; Generalizability theory; Convolutional neural network; Deep learning; Modalities; Modular design; Machine learning; Benchmark (surveying); Image segmentation; Pattern recognition (psychology); Modality (human–computer interaction); Market segmentation; Contouring","score_opus":0.021547472727859014,"score_gpt":0.30546415616715733,"score_spread":0.2839166834392983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235505678","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018257508,0.00017993039,0.9759597,0.0004987267,0.0024934271,0.00019178458,3.2116586e-7,0.00041907237,0.0019995288],"genre_scores_gemma":[0.19617733,0.00013015886,0.80263764,0.00035266852,0.00043240315,0.000043695072,0.000019861756,0.000029345034,0.00017690181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976435,0.00019342253,0.0003515656,0.000789538,0.0007520957,0.00026992758],"domain_scores_gemma":[0.9988313,0.000044932392,0.0002194324,0.0005553956,0.00020988466,0.00013908655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057148555,0.00022254737,0.0002478712,0.000118246055,0.00013707526,0.0006253886,0.000835096,0.0003533329,0.00043449254],"category_scores_gemma":[0.00016717942,0.00022964906,0.0001301799,0.0002514117,0.000043076772,0.00047219085,0.0025654144,0.0010366291,0.000011984289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006369682,0.000046925947,0.00012807093,0.00022453985,0.00010103955,0.000080176826,0.0021214336,0.006461604,0.0323292,0.00025563512,0.00005301341,0.958192],"study_design_scores_gemma":[0.00017511091,0.000027193022,0.00018006368,0.000081751736,0.000014450755,0.00004255132,0.00020373863,0.9767369,0.021751352,0.00043221726,0.000092524046,0.00026216207],"about_ca_topic_score_codex":0.0008223862,"about_ca_topic_score_gemma":0.000110674555,"teacher_disagreement_score":0.9702753,"about_ca_system_score_codex":0.0005273765,"about_ca_system_score_gemma":0.00075053563,"threshold_uncertainty_score":0.9364817},"labels":[],"label_agreement":null},{"id":"W4236531604","doi":"10.1117/1.2178271","title":"Classification of breast masses in mammograms using neural networks with shape, edge sharpness, and texture features","year":2006,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Mysore; Fundação de Amparo à Pesquisa do Estado de São Paulo; University of Alberta","keywords":"Artificial intelligence; Pattern recognition (psychology); Pixel; Perceptron; Artificial neural network; Computer science; Multilayer perceptron; Texture (cosmology); Feature extraction; Feature (linguistics); Computer vision; Image (mathematics)","score_opus":0.005502419003245388,"score_gpt":0.22510395462243976,"score_spread":0.21960153561919438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236531604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5973887,0.006780109,0.39389884,0.0014782603,0.00020296733,0.000118518015,5.429484e-7,0.00002398756,0.00010806905],"genre_scores_gemma":[0.99594796,0.000039370305,0.0037544512,0.00003931372,0.00020001126,0.000001060612,5.242706e-7,0.000011379207,0.0000059551026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989149,0.000053820924,0.00031481363,0.00017090917,0.00022993951,0.00031561605],"domain_scores_gemma":[0.9991667,0.000039022307,0.00047333812,0.00013983899,0.00015038159,0.000030682797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003074098,0.00011983008,0.00018876302,0.00020824365,0.000059860125,0.00012502736,0.00027398817,0.00003940332,0.000002132644],"category_scores_gemma":[0.0000044787616,0.00009746994,0.00003980837,0.0005253277,0.000057890837,0.0008420735,0.000038521663,0.0004597069,4.225481e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037015651,0.00021827653,0.32972515,0.0001031372,0.00007905178,0.00010981999,0.00029798163,0.17208621,0.03018915,0.005136448,0.0004771126,0.4612075],"study_design_scores_gemma":[0.00047282962,0.000086275846,0.19100638,0.000106587446,0.000018343799,0.002817331,0.000034719233,0.8043825,0.0002831209,0.0006004273,0.000080019556,0.00011146714],"about_ca_topic_score_codex":0.000099625075,"about_ca_topic_score_gemma":0.00012173754,"teacher_disagreement_score":0.63229626,"about_ca_system_score_codex":0.00023372611,"about_ca_system_score_gemma":0.00015278909,"threshold_uncertainty_score":0.3974709},"labels":[],"label_agreement":null},{"id":"W4243371481","doi":"10.1016/j.imu.2019.100227","title":"CBIR system using Capsule Networks and 3D CNN for Alzheimer's disease diagnosis","year":2019,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Johnson and Johnson Pharmaceutical Research and Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; Takeda Pharmaceutical Company; Janssen Alzheimer Immunotherapy Research And Development; AbbVie; Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation; Merck; Fujirebio Europe; Alzheimer's Association; Foundation for the National Institutes of Health; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative","keywords":"Autoencoder; Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Pattern recognition (psychology); Image retrieval; Feature extraction; Content-based image retrieval; Image (mathematics)","score_opus":0.02578148744340237,"score_gpt":0.2769107994368082,"score_spread":0.2511293119934058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243371481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13395232,0.0013802724,0.8594888,0.00043413986,0.0023455485,0.0014031674,0.0000043198843,0.00018855587,0.00080289104],"genre_scores_gemma":[0.97056246,0.0000814819,0.02844142,0.000536304,0.0002301127,0.00011694776,0.000005558123,0.000014905409,0.000010803448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855745,0.00003334607,0.0006082515,0.00017696698,0.00030747137,0.00031652872],"domain_scores_gemma":[0.99874777,0.00024321828,0.00024833065,0.0005043689,0.0000960966,0.00016024588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063046237,0.00017295161,0.00030941036,0.00021644916,0.000091766546,0.000054405464,0.00039850918,0.0000819925,0.0000053602616],"category_scores_gemma":[0.00008254005,0.0001479528,0.000031693202,0.00039505484,0.00007509764,0.0006012506,0.00016224103,0.00016574826,0.000007937238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029219672,0.00018950082,0.07057117,0.005695441,0.00048759894,0.00005391934,0.035504647,0.45713916,0.00011351059,0.038756136,0.011900762,0.37929597],"study_design_scores_gemma":[0.0011378922,0.00011897376,0.0010744145,0.00061333604,0.000047928177,0.000011194717,0.0005983924,0.9942638,0.00005841245,0.00019782796,0.0017058311,0.00017194777],"about_ca_topic_score_codex":0.000077142904,"about_ca_topic_score_gemma":0.0000057854086,"teacher_disagreement_score":0.83661014,"about_ca_system_score_codex":0.00017515208,"about_ca_system_score_gemma":0.00007634323,"threshold_uncertainty_score":0.603334},"labels":[],"label_agreement":null},{"id":"W4244558909","doi":"10.22215/etd/2010-09391","title":"The development of a semi-automated testing method for medical imaging systems","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Computer science","score_opus":0.018444389400195656,"score_gpt":0.33983321062073646,"score_spread":0.3213888212205408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244558909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060537056,0.00021418725,0.99069786,0.000086844484,0.0040268404,0.00048499604,9.033027e-7,0.00059719343,0.003285801],"genre_scores_gemma":[0.022335535,0.00000449453,0.9748185,0.000035137473,0.00022148207,0.0005599826,0.000032830438,0.000041162224,0.001950876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801236,0.00006914206,0.00065704336,0.00036355018,0.00065297744,0.00024495067],"domain_scores_gemma":[0.9971054,0.0014428948,0.00048126106,0.00038139094,0.00052129885,0.000067764115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002115977,0.00017399825,0.00023589307,0.0000993438,0.00033135532,0.00016031276,0.0010395001,0.00021512332,0.0000030344463],"category_scores_gemma":[0.0008169757,0.00012011804,0.00005396782,0.00032296532,0.000017140857,0.00011324735,0.00007860736,0.00030296136,0.0000030660447],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013561269,0.000017491637,0.00003388768,0.0005664988,0.00007204597,0.0000013017413,0.0018797605,0.00008255441,0.0073240637,0.0026094948,0.0014539193,0.9859454],"study_design_scores_gemma":[0.0001268474,0.00001048842,0.00020123935,0.00028479533,0.000010387537,0.000015502274,0.000384537,0.97870886,0.015416424,0.0001929041,0.004489783,0.00015821657],"about_ca_topic_score_codex":0.00012065889,"about_ca_topic_score_gemma":0.00058641616,"teacher_disagreement_score":0.9857872,"about_ca_system_score_codex":0.00009797704,"about_ca_system_score_gemma":0.0011931524,"threshold_uncertainty_score":0.48982716},"labels":[],"label_agreement":null},{"id":"W4245064891","doi":"10.1002/9780471420194.tnmm06","title":"Cancer Informatics","year":2017,"lang":"en","type":"other","venue":"TNM Online","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Informatics; Health informatics; Computer science; Best practice; Data science; Health informatics tools; Knowledge management; Health Administration Informatics; Process (computing); Translational research informatics; Cancer; Frontier; Health care; Medicine; Engineering; Political science","score_opus":0.022899434167475252,"score_gpt":0.31453127435953165,"score_spread":0.2916318401920564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245064891","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017647271,0.001028516,0.14956228,0.00047541223,0.0033745768,0.00020373918,0.00083559257,0.0008262248,0.8436919],"genre_scores_gemma":[0.000010549358,0.0009251723,0.053496487,0.00036039075,0.0013411234,0.000025592848,0.00006137837,0.00011600714,0.9436633],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993287,0.000008333176,0.00013093666,0.00014942967,0.00021413706,0.00016849313],"domain_scores_gemma":[0.9984909,0.000010482533,0.00037790183,0.0010424311,0.000028183196,0.000050087336],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000043544034,0.00015626132,0.00018281564,0.00012792218,0.000052875108,0.000083987354,0.0011764762,0.00017773645,0.0014554375],"category_scores_gemma":[0.000016448535,0.00014289352,0.00004355473,0.00007174178,0.0000383793,0.00014745278,0.0002467897,0.0001953306,0.0002522517],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.7390248e-7,0.000007319453,0.0000035647706,0.000033268745,0.000012087526,0.0000014613225,0.000044071883,0.0000032761457,9.213988e-7,0.00008395918,0.81967664,0.18013309],"study_design_scores_gemma":[0.00010133663,0.000015985896,0.00002646131,0.00024671762,0.000006682625,0.0000035038952,0.0000016448449,0.005551517,0.000016497432,0.00008944544,0.9937712,0.00016903125],"about_ca_topic_score_codex":0.00039476968,"about_ca_topic_score_gemma":0.0014618065,"teacher_disagreement_score":0.17996405,"about_ca_system_score_codex":0.000083964755,"about_ca_system_score_gemma":0.00016518695,"threshold_uncertainty_score":0.99945736},"labels":[],"label_agreement":null},{"id":"W4247277608","doi":"10.1080/21681163.2018.1514280","title":"Automatic pathology of prostate cancer in whole mount slides incorporating individual gland classification","year":2018,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia","funders":"Prostate Cancer Canada","keywords":"Magnification; Prostate cancer; Cancer; Prostate; Histopathology; Stage (stratigraphy); Adenocarcinoma; Pathology; Digital pathology; Histology; Prostate gland; Cancer detection; Computer science; Medicine; Artificial intelligence; Biology; Internal medicine","score_opus":0.020685092915240226,"score_gpt":0.3434349296715566,"score_spread":0.32274983675631636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247277608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07913172,0.00022885164,0.91910994,0.0002711902,0.00094528316,0.0001894766,0.000005761502,0.000116529984,0.0000012408104],"genre_scores_gemma":[0.5121028,0.00003508793,0.48763177,0.000060986422,0.00010977391,0.000032134576,0.000011889635,0.000014739449,8.357786e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823314,0.00020377187,0.0005987927,0.00045088155,0.00025338304,0.00026000544],"domain_scores_gemma":[0.99921775,0.00014377439,0.00023719268,0.00022562337,0.00010573677,0.0000699027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018025313,0.00017359365,0.00026950106,0.0008351839,0.000047106467,0.00009245571,0.00031877158,0.000111040696,0.0000025117322],"category_scores_gemma":[0.000099978075,0.00017160235,0.00002290598,0.0015369996,0.00010342575,0.0003188678,0.00029501782,0.0001462878,5.38286e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037393615,0.0000623926,0.0013453529,0.00017492469,0.00001032318,0.0000064091523,0.0014226887,0.00022847262,0.1788345,0.0062872316,0.0000119449005,0.811612],"study_design_scores_gemma":[0.0004227527,0.000119126904,0.009219067,0.00027588615,0.000005728843,0.000016307273,0.000023269948,0.9789013,0.00840893,0.0020990227,0.00033228644,0.00017627006],"about_ca_topic_score_codex":0.000054736323,"about_ca_topic_score_gemma":0.000005940608,"teacher_disagreement_score":0.97867286,"about_ca_system_score_codex":0.00016852924,"about_ca_system_score_gemma":0.000071028284,"threshold_uncertainty_score":0.6997741},"labels":[],"label_agreement":null},{"id":"W4248718073","doi":"10.1155/2012/724801","title":"The Challenges of Implementing a “Patient-Oriented” Telepathology Network; the Eastern Québec Telepathology Project Experience","year":2012,"lang":"en","type":"article","venue":"Analytical Cellular Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cégep de Baie-Comeau; Université Laval","funders":"","keywords":"Telepathology; Videoconferencing; Computer science; Telemedicine; Teleradiology; Second opinion; Population; Multimedia; Medical physics; Medicine; Pathology; Health care","score_opus":0.0313169042326975,"score_gpt":0.2831704549666816,"score_spread":0.2518535507339841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248718073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69410366,0.017303064,0.269253,0.005655579,0.0029252367,0.0010206721,0.000004850126,0.00023698091,0.009496963],"genre_scores_gemma":[0.9959954,0.0002822176,0.0025978247,0.00036281015,0.00050240953,0.00010943446,0.0000014903696,0.000019935631,0.00012844648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587876,0.0010209996,0.00073691265,0.0006099716,0.0003703691,0.0013830056],"domain_scores_gemma":[0.99723023,0.0007423798,0.00042777671,0.0013202085,0.00016737719,0.000112033296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017475409,0.0002879207,0.00040645033,0.00010333828,0.0005692702,0.00003832078,0.001262112,0.00020014154,0.000024957373],"category_scores_gemma":[0.00027926825,0.00017986048,0.00019614324,0.00056415267,0.0008489773,0.00028266545,0.0008799363,0.00045350438,0.000058595928],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013692725,0.0004091857,0.16710807,0.00006996704,0.00020108932,0.00039088304,0.035078894,0.00014100665,0.002322555,0.30438536,0.0018063281,0.48794973],"study_design_scores_gemma":[0.0023716989,0.005063092,0.049814563,0.00010400977,0.00045739496,0.005795819,0.01748248,0.20816104,0.014761815,0.010222082,0.68325657,0.0025094526],"about_ca_topic_score_codex":0.00058279,"about_ca_topic_score_gemma":0.0011017825,"teacher_disagreement_score":0.6814502,"about_ca_system_score_codex":0.00007757164,"about_ca_system_score_gemma":0.00015348283,"threshold_uncertainty_score":0.73344976},"labels":[],"label_agreement":null},{"id":"W4249058857","doi":"10.1117/3.651880.ch3","title":"An Indexed Atlas of Digital Mammograms for Computer-Aided Diagnosis of Breast Cancer","year":2010,"lang":"en","type":"book-chapter","venue":"SPIE eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Mammography; Breast cancer; Radiology; Malignancy; Context (archaeology); Digital mammography; Abnormality; Breast cancer screening; Asymptomatic; Magnetic resonance imaging; Medical physics; Cancer; Pathology; Internal medicine","score_opus":0.01851873255895706,"score_gpt":0.253137432404925,"score_spread":0.23461869984596792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249058857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05146362,0.0006142403,0.73191774,0.00078929716,0.01766216,0.007918152,0.0058267643,0.0014666673,0.18234138],"genre_scores_gemma":[0.8404268,0.00009330995,0.09696141,0.0002995808,0.0041801278,0.0010695873,0.00012939321,0.0004636338,0.056376167],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979403,0.0000064509136,0.00060394127,0.000689915,0.0004549286,0.00030443587],"domain_scores_gemma":[0.99744767,0.000121245546,0.00076524564,0.0011132747,0.00040590134,0.00014667421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013838148,0.00039913665,0.000630533,0.00024051717,0.00007317417,0.00012058848,0.0012402787,0.00049504964,0.000035631954],"category_scores_gemma":[0.0000047260546,0.00040097977,0.0003277991,0.000037065125,0.0002909518,0.00026312127,0.00028805254,0.00039008993,0.0000053086796],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084582345,0.00006798543,0.0006774462,0.00029291707,0.00022010575,0.0000059618974,0.00030175396,0.00003491404,0.0012722652,0.04098719,0.0003866302,0.9556683],"study_design_scores_gemma":[0.009155319,0.0102056125,0.008772519,0.0056979633,0.0010431323,0.00033645905,0.000036737893,0.018892946,0.18573435,0.3997025,0.35261282,0.007809659],"about_ca_topic_score_codex":0.00016310712,"about_ca_topic_score_gemma":0.00026024375,"teacher_disagreement_score":0.9478586,"about_ca_system_score_codex":0.000107468826,"about_ca_system_score_gemma":0.0002507172,"threshold_uncertainty_score":0.9998442},"labels":[],"label_agreement":null},{"id":"W4249532821","doi":"10.4018/978-1-60960-553-7.ch014","title":"Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Radial basis function; Pattern recognition (psychology); Simulated annealing; Artificial intelligence; Classifier (UML); Artificial neural network; Computer science; Multilayer perceptron; Algorithm","score_opus":0.04331279114824958,"score_gpt":0.25691155286323486,"score_spread":0.21359876171498526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249532821","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019043146,0.0005811839,0.15546219,0.000069154106,0.0020284778,0.00087564206,0.00021255597,0.00037730412,0.82135034],"genre_scores_gemma":[0.99546826,0.000007471898,0.0031797006,0.000025219591,0.00012412127,0.0000043230225,0.000002891348,0.000023989194,0.0011640412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854445,0.0000312367,0.00043273883,0.0005234582,0.00024726626,0.00022085443],"domain_scores_gemma":[0.998912,0.000035138077,0.00034773507,0.00047890967,0.0001394347,0.00008680652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014022307,0.0002605494,0.00031681015,0.0001909303,0.000081653634,0.00007468016,0.000306695,0.0003466267,0.000010083666],"category_scores_gemma":[0.000007404139,0.00029134357,0.00009044277,0.00008413529,0.00012028427,0.00016629073,0.00014746985,0.00021449558,0.0000060543284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012036916,0.000027811588,0.0020222343,0.000113513364,0.00013451095,0.000025128133,0.00028686324,0.0010693868,0.0006529681,0.76121247,0.000063144995,0.2342716],"study_design_scores_gemma":[0.0035749779,0.00081164046,0.029655198,0.0027160242,0.0005929389,0.0011853315,0.00014175242,0.26630288,0.00083011895,0.68244594,0.008323814,0.0034193685],"about_ca_topic_score_codex":0.0009652375,"about_ca_topic_score_gemma":0.00031450152,"teacher_disagreement_score":0.9764251,"about_ca_system_score_codex":0.00036439687,"about_ca_system_score_gemma":0.00017400953,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W4249732865","doi":"10.1007/978-0-387-39940-9_2431","title":"Databases for Biomedical Images","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Database; Computer science; Information retrieval","score_opus":0.025512572805538404,"score_gpt":0.27076214544631266,"score_spread":0.24524957264077427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249732865","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011490533,0.004899051,0.62551004,0.00017681143,0.0050064404,0.0012948595,0.0064311894,0.00028507848,0.3563954],"genre_scores_gemma":[0.00036223122,0.011160136,0.17498182,0.0002191027,0.007928166,0.00042819604,0.006396037,0.00027145233,0.7982529],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966457,0.000045294728,0.0009791448,0.0010302666,0.0008897015,0.00040988976],"domain_scores_gemma":[0.9961275,0.00042797328,0.0007925909,0.002185781,0.00024610056,0.00022009098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066084013,0.00050146173,0.00079568505,0.00043887686,0.000106049214,0.000064512125,0.0014535858,0.00024204183,0.000046853394],"category_scores_gemma":[0.00014684549,0.00048043777,0.0002226854,0.00011571285,0.0001624784,0.0007593898,0.00044289284,0.0003431316,0.00008763828],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043829794,0.000103764076,0.0000055129067,0.0017485464,0.00019082314,0.00008612942,0.00009701462,0.000013546094,0.00026618977,0.32730478,0.5361291,0.13401075],"study_design_scores_gemma":[0.00038076725,0.00023578675,0.000003371732,0.00090639666,0.00007008027,0.00005372277,0.000007365325,0.0008499089,0.000145531,0.0010907853,0.9957593,0.0004969532],"about_ca_topic_score_codex":0.00013726788,"about_ca_topic_score_gemma":0.000013739937,"teacher_disagreement_score":0.4596302,"about_ca_system_score_codex":0.00014215831,"about_ca_system_score_gemma":0.00040856932,"threshold_uncertainty_score":0.99976474},"labels":[],"label_agreement":null},{"id":"W4249899331","doi":"10.7287/peerj-cs.154v0.2/reviews/2","title":"Peer Review #2 of \"Supervised deep learning embeddings for the prediction of cervical cancer diagnosis (v0.2)\"","year":2018,"lang":"en","type":"peer-review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Cervical cancer; Artificial intelligence; Deep learning; Computer science; Machine learning; Medicine; Cancer; Internal medicine","score_opus":0.05171172823766321,"score_gpt":0.3369723321350403,"score_spread":0.28526060389737706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249899331","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024994117,0.45992148,0.35590467,0.17158389,0.0065030055,0.002920212,0.00029149043,0.00019578212,0.0026769827],"genre_scores_gemma":[0.00012967426,0.8680932,0.012720291,0.007962449,0.0017137215,0.006055483,0.00017816505,0.000085945685,0.10306107],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99586415,0.00019262603,0.0010976802,0.00073511247,0.0017648377,0.0003455857],"domain_scores_gemma":[0.99233776,0.0008506256,0.0010146799,0.0010954862,0.0046204687,0.0000809917],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024637822,0.00037473885,0.0010310824,0.000115879724,0.0001664526,0.000043138727,0.0017774346,0.00029077168,0.0019519428],"category_scores_gemma":[0.0016926684,0.00025744265,0.0005739464,0.00078962854,0.00014461242,0.0002792617,0.00044777367,0.00052059744,0.000013910384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053651374,0.000020806196,0.000047885904,0.033337448,0.00010810294,1.1042983e-7,0.000091998576,0.000017237287,0.000002754336,0.000065809465,0.810835,0.15546751],"study_design_scores_gemma":[0.00019012262,0.00026349648,0.00009543149,0.03520299,0.000483821,0.000004256257,0.000007936771,0.019226344,0.00036116262,0.000068416884,0.94388324,0.00021277013],"about_ca_topic_score_codex":0.00068780035,"about_ca_topic_score_gemma":0.00017158817,"teacher_disagreement_score":0.4081717,"about_ca_system_score_codex":0.00023783642,"about_ca_system_score_gemma":0.0002892709,"threshold_uncertainty_score":0.9999878},"labels":[],"label_agreement":null},{"id":"W4251629148","doi":"10.3410/f.727121335.793537532","title":"Faculty Opinions recommendation of An updated histological classification system for multiple sclerosis lesions.","year":2017,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Microglia; Multiple sclerosis; Myelin; Pathology; Luxol fast blue stain; Lesion; Proteolipid protein 1; Medicine; Immunohistochemistry; Myelin basic protein; Pathogenesis; Demyelinating disease; Central nervous system; Immunology; Inflammation; Internal medicine","score_opus":0.10858915248995327,"score_gpt":0.37098678449772116,"score_spread":0.2623976320077679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251629148","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.6587106e-7,0.00033611857,0.007495623,0.0963436,0.0025390186,0.0022914212,0.89081407,0.00015103024,0.000028547345],"genre_scores_gemma":[0.00012104633,0.000104008555,0.00974692,0.0010515343,0.00032995755,0.00085855636,0.9875122,0.000027897358,0.0002479341],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942803,0.0007206156,0.0019002984,0.0012249596,0.0014454034,0.0004284533],"domain_scores_gemma":[0.9845602,0.0002268135,0.003665132,0.003669611,0.007535729,0.00034251262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022428427,0.00058055285,0.0010755442,0.00043851012,0.00082270295,0.0003865,0.005024509,0.0010739777,0.000050559975],"category_scores_gemma":[0.005610362,0.0004009656,0.0006708475,0.0014257774,0.00041024826,0.0011644576,0.0007530523,0.00089064654,0.00003347158],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020346673,0.00030384646,0.0000021731678,0.0036140527,0.00007747753,9.323232e-8,0.000051677638,3.3464062e-7,0.000011434999,0.00084334123,0.9833445,0.011730732],"study_design_scores_gemma":[0.0008355472,0.00024006107,0.0017863878,0.0063176393,0.00014890253,0.00003319964,0.000027646032,0.0011904137,0.00008050581,0.00003333761,0.988911,0.00039539268],"about_ca_topic_score_codex":0.000085908774,"about_ca_topic_score_gemma":0.000016836368,"teacher_disagreement_score":0.09669807,"about_ca_system_score_codex":0.00051446265,"about_ca_system_score_gemma":0.0007153338,"threshold_uncertainty_score":0.9998442},"labels":[],"label_agreement":null},{"id":"W4251805236","doi":"10.1093/jicru_ndp026","title":"Appendix B: Examples of Phantom and Test Tools for Mammography QC","year":2009,"lang":"en","type":"article","venue":"Journal of the ICRU","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Imaging phantom; Mammography; Medical physics; Test (biology); Computer science; Nuclear medicine; Medicine; Geology; Internal medicine; Breast cancer","score_opus":0.023582856743732634,"score_gpt":0.2590851511433036,"score_spread":0.23550229439957096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251805236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60080194,0.0022520954,0.38476786,0.009761766,0.0016140739,0.00038079158,0.000015011232,0.000029802255,0.00037667635],"genre_scores_gemma":[0.97542137,0.00007664976,0.024113897,0.00019944822,0.000157903,7.5855746e-7,5.8518413e-8,0.0000030224885,0.000026864329],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99941003,0.000021899305,0.00023164539,0.00007391062,0.0001652507,0.00009725114],"domain_scores_gemma":[0.9990194,0.00030193603,0.00036046226,0.00018949817,0.00009395111,0.0000347804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034960848,0.000056913184,0.0001269946,0.00008317938,0.000060604212,0.00007621664,0.00051653,0.000026037647,0.000002001364],"category_scores_gemma":[0.00012954838,0.000036575457,0.00011227841,0.00019271811,0.00003156582,0.00041724188,0.000043848173,0.00008417018,4.1358658e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009846617,0.00016932977,0.009165413,0.000048892107,0.000078836085,0.0000045823067,0.0007194673,0.00013784746,0.1152836,0.0050547975,0.013240178,0.8559986],"study_design_scores_gemma":[0.0035461949,0.0046774787,0.38357395,0.00061071117,0.00015200114,0.0014337441,0.00017394651,0.0032074668,0.3711595,0.12678047,0.10417323,0.00051130867],"about_ca_topic_score_codex":0.0000033186766,"about_ca_topic_score_gemma":0.0000037569962,"teacher_disagreement_score":0.8554873,"about_ca_system_score_codex":0.000019615674,"about_ca_system_score_gemma":0.000035027948,"threshold_uncertainty_score":0.14915039},"labels":[],"label_agreement":null},{"id":"W4254790362","doi":"10.1007/s11517-006-0109-2","title":"Gabor filters and phase portraits for the detection of architectural distortion in mammograms","year":2006,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Phase portrait; Portrait; Human physiology; Distortion (music); Artificial intelligence; Computer vision; Phase distortion; Gabor filter; Phase (matter); Computer science; Pattern recognition (psychology); Optics; Filter (signal processing); Medicine; Image (mathematics); Physics; Art; Internal medicine; Telecommunications; Visual arts","score_opus":0.010927639814719468,"score_gpt":0.24537964296831338,"score_spread":0.2344520031535939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254790362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41782194,0.00023622424,0.5813742,0.00014921486,0.00023157492,0.000119219505,7.2777675e-7,0.00006294451,0.0000039413776],"genre_scores_gemma":[0.9928562,0.0000064220385,0.006900702,0.000038048514,0.00017259117,0.000017454404,0.0000021060353,0.0000050363487,0.0000014248684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989781,0.000029662675,0.00031355783,0.00025689183,0.0001821735,0.0002396457],"domain_scores_gemma":[0.9992032,0.0005217471,0.00007779852,0.00011963371,0.000022016808,0.000055573015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052793394,0.00011040159,0.00015797377,0.00006473501,0.000061929735,0.000021834334,0.00025199185,0.000097300144,0.0000025255772],"category_scores_gemma":[0.00025018657,0.000073239185,0.000053638225,0.00027132191,0.000077844146,0.000044268825,0.000097786404,0.0002099546,3.2402056e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024114917,0.000053141248,0.0014362074,0.00003547072,0.0000075532907,0.0000042520624,0.00007907206,0.020549772,0.007884469,0.0004811223,0.0000044026124,0.9694404],"study_design_scores_gemma":[0.0005778412,0.00025198955,0.08431719,0.00004948072,0.0000030718252,0.00003687481,0.000005491383,0.9124239,0.0016475035,0.00018034237,0.00039976166,0.000106511194],"about_ca_topic_score_codex":0.00009894826,"about_ca_topic_score_gemma":0.000018894178,"teacher_disagreement_score":0.9693339,"about_ca_system_score_codex":0.000047449357,"about_ca_system_score_gemma":0.0000128926795,"threshold_uncertainty_score":0.29866073},"labels":[],"label_agreement":null},{"id":"W4255283714","doi":"10.22215/etd/2021-14596","title":"Image Separation using Multi-layer Image Segmentation for Translucent Partially Overlapped Objects","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Image segmentation; Scale-space segmentation; Segmentation-based object categorization; Pattern recognition (psychology); Convolutional neural network; Computer vision; Region growing","score_opus":0.043599628740655254,"score_gpt":0.3661325495298943,"score_spread":0.32253292078923906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255283714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020559661,0.00016954544,0.97299093,0.000065884924,0.0035700754,0.0014280407,0.000021219541,0.00026879282,0.0009258471],"genre_scores_gemma":[0.056969907,0.00007220923,0.93676156,0.00019020382,0.00035816783,0.00046477816,0.0013988527,0.00009520386,0.0036891382],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973999,0.00011129096,0.0006021122,0.0009559896,0.0005209154,0.00040977937],"domain_scores_gemma":[0.99830645,0.000074943935,0.00040975798,0.00052133837,0.00059027504,0.00009724028],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026826136,0.00040707045,0.0003718776,0.00020182849,0.00028530514,0.00061389967,0.00039758865,0.0003142589,0.0000902018],"category_scores_gemma":[0.000040281247,0.0004490711,0.0002666711,0.00042601008,0.000017686272,0.001479683,0.000030944688,0.0002199493,0.000023494164],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008857594,0.00012374177,0.0000057457573,0.00037884017,0.00008677865,0.000009612765,0.003410286,0.00039484847,0.97781706,0.00022051483,0.00037740025,0.017086597],"study_design_scores_gemma":[0.0011099075,0.000098381955,0.00032550658,0.00010630247,0.00009425443,0.000005976263,0.00072914804,0.4150773,0.5816184,0.00015667432,0.00018317129,0.00049496227],"about_ca_topic_score_codex":0.00013229989,"about_ca_topic_score_gemma":0.0018465902,"teacher_disagreement_score":0.41468245,"about_ca_system_score_codex":0.0004922715,"about_ca_system_score_gemma":0.00060004706,"threshold_uncertainty_score":0.9997961},"labels":[],"label_agreement":null},{"id":"W4280598218","doi":"10.18280/ria.360212","title":"Semantics Convolutional Neural Network for Medical Images Analysis","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Semantics (computer science); Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); False positive paradox; Layer (electronics); Data mining; Deep learning; Semantic feature; Artificial neural network; Noise (video)","score_opus":0.030539923167676692,"score_gpt":0.2858623798987183,"score_spread":0.25532245673104165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280598218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002669938,0.00041259057,0.99031204,0.00449899,0.0013880347,0.00023653105,0.000018276101,0.00015184087,0.00031173075],"genre_scores_gemma":[0.9790316,0.00003120694,0.018469423,0.00065228564,0.00038766043,0.00020486845,0.00002337315,0.000013764214,0.0011858105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794745,0.00012118103,0.0004357272,0.0005284511,0.0005469768,0.0004202262],"domain_scores_gemma":[0.9985968,0.00043390304,0.00014864483,0.0005755471,0.0001235681,0.000121555706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010571013,0.00013337043,0.00022830942,0.00016748242,0.000697805,0.00008665552,0.0011302824,0.00005144641,0.0006970703],"category_scores_gemma":[0.00012301955,0.00014836037,0.00025836183,0.0019348362,0.0000900902,0.00018498399,0.00048622346,0.00027530515,0.000039041624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015220606,0.00006302533,0.0007775401,0.000013604405,0.00009791686,0.000011422769,0.00022463471,0.94374174,0.00007936659,0.025426459,0.007293029,0.022256054],"study_design_scores_gemma":[0.000034433473,0.00012692438,0.00013773302,0.000004627471,0.000052978787,0.00004002898,0.00010855818,0.97306323,0.0014507921,0.005484973,0.019326659,0.00016905478],"about_ca_topic_score_codex":0.00003318371,"about_ca_topic_score_gemma":0.00002427629,"teacher_disagreement_score":0.9763617,"about_ca_system_score_codex":0.00014778173,"about_ca_system_score_gemma":0.000117581745,"threshold_uncertainty_score":0.76324314},"labels":[],"label_agreement":null},{"id":"W4281386887","doi":"10.1016/j.cmpb.2022.106903","title":"YOLO-LOGO: A transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms","year":2022,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Mitacs; CancerCare Manitoba Foundation; Manitoba Medical Service Foundation; Research Manitoba","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Mammography; Object detection; Digital mammography; Computer vision; Image segmentation; Pattern recognition (psychology); Transformer; Breast cancer; Cancer; Medicine; Engineering","score_opus":0.04076577112486669,"score_gpt":0.33207232641954865,"score_spread":0.29130655529468197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281386887","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04758731,0.00021470856,0.94974047,0.00065703905,0.000512896,0.0011661403,0.00001654665,0.000099138175,0.000005751752],"genre_scores_gemma":[0.41228545,0.000017498069,0.58688974,0.00015833379,0.000051817595,0.00054294534,0.00003648805,0.000011857261,0.000005865777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982664,0.00017352296,0.00041630774,0.0005846981,0.00024745543,0.0003116029],"domain_scores_gemma":[0.9994018,0.00015793201,0.00012570589,0.00018392426,0.00004488982,0.00008575961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014063579,0.0001967836,0.0002592769,0.0004632913,0.00017162312,0.00015922467,0.00020826187,0.000070949085,0.0000017844646],"category_scores_gemma":[0.000006186213,0.00019085403,0.000044797736,0.0009490426,0.00011263042,0.00046212718,0.00007816048,0.00020444387,1.0543641e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117600335,0.000094641124,0.001408721,0.00008362977,0.00001054808,0.0000030534259,0.0012986965,0.0016679582,0.006056394,0.00005971439,0.0000031154495,0.98919594],"study_design_scores_gemma":[0.0027038425,0.001386019,0.0014311512,0.000038878217,0.000012390166,0.00007370474,0.00024392724,0.98689544,0.0011456679,0.0056050178,0.00025490674,0.00020907573],"about_ca_topic_score_codex":0.000052940224,"about_ca_topic_score_gemma":0.00003381878,"teacher_disagreement_score":0.98898685,"about_ca_system_score_codex":0.0002165115,"about_ca_system_score_gemma":0.000043411463,"threshold_uncertainty_score":0.77828014},"labels":[],"label_agreement":null},{"id":"W4281621439","doi":"10.21802/gmj.2022.2.5","title":"Artificial Intelligence Approach in Prostate Cancer Diagnosis: Bibliometric Analysis","year":2022,"lang":"en","type":"article","venue":"Galician Medical Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Ministry of Education and Science of Ukraine","keywords":"Medicine; Prostate cancer; MEDLINE; Gynecology; Cancer; Internal medicine","score_opus":0.037144825830759585,"score_gpt":0.31729258864048066,"score_spread":0.2801477628097211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281621439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101914436,0.0030935495,0.8797502,0.012102098,0.0022604286,0.00026110103,0.000012404763,0.00011051552,0.0004952558],"genre_scores_gemma":[0.99213284,0.0012401041,0.0038456304,0.0017993235,0.0004336481,0.0005094672,0.0000020138898,0.000012664649,0.000024316047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953618,0.0004878654,0.00073773455,0.0004512772,0.0024306236,0.0005307069],"domain_scores_gemma":[0.9987543,0.00014452748,0.00027896982,0.00032597667,0.00009792781,0.0003982744],"candidate_categories":["bibliometrics","insufficient_payload"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.003200392,0.00015308907,0.00031515257,0.041029457,0.0004121923,0.00025781067,0.0016748179,0.000063538915,0.0013360106],"category_scores_gemma":[0.00024999768,0.00014368942,0.00018438761,0.19318768,0.00007666771,0.0003877659,0.00047748984,0.001406018,0.000010514778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020142963,0.0002538944,0.044329036,0.000007607587,0.00013301664,0.00023900736,0.0009031879,0.013869018,0.0000053664326,0.0008553925,0.0014478997,0.9379364],"study_design_scores_gemma":[0.00039409788,0.0005074243,0.15137053,0.00006914079,0.00022266406,0.0009485185,0.0011693006,0.8103971,0.0005854338,0.019706856,0.0137757,0.0008532555],"about_ca_topic_score_codex":0.00031264147,"about_ca_topic_score_gemma":0.00013798679,"teacher_disagreement_score":0.9370832,"about_ca_system_score_codex":0.00064603746,"about_ca_system_score_gemma":0.00054789847,"threshold_uncertainty_score":0.9995769},"labels":[],"label_agreement":null},{"id":"W4281631055","doi":"10.1016/j.mlwa.2022.100347","title":"A semi-supervised learning approach for bladder cancer grading","year":2022,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Toronto General Hospital; Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Regularization (linguistics); Labeled data; Machine learning; Pattern recognition (psychology); Consistency (knowledge bases); Semi-supervised learning; Deep learning; Data mining","score_opus":0.014855339333511302,"score_gpt":0.25355052705762005,"score_spread":0.23869518772410875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281631055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022667968,0.00040701145,0.9931449,0.0010500306,0.00005894761,0.00095644937,0.000008021451,0.0006590609,0.0014487653],"genre_scores_gemma":[0.8482366,0.000029284673,0.13147706,0.0002887178,0.00017477234,0.017042678,0.00009018672,0.000062222025,0.002598492],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983354,0.00013474454,0.00019576277,0.0006457341,0.00033998495,0.00034834733],"domain_scores_gemma":[0.9991048,0.00013044139,0.0001836391,0.0004117044,0.0000836613,0.00008574226],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00038896213,0.00018057307,0.0001717044,0.00016409812,0.001955096,0.00012610755,0.0007166838,0.000034640598,0.00006316131],"category_scores_gemma":[0.000018927532,0.00017965428,0.00006846526,0.0010578091,0.000036446832,0.0001960617,0.00028360717,0.00077009405,0.000005399615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040314077,0.00008529466,0.012532245,0.00003747516,0.00007152711,7.839278e-7,0.0012548205,0.9018883,0.0009956042,0.0060461042,0.0002885298,0.07675898],"study_design_scores_gemma":[0.00045582253,0.00017088908,0.00029889532,0.000003441433,0.0000231749,0.000031705385,0.0001439752,0.7966265,0.000086802815,0.0002286434,0.20170692,0.00022322952],"about_ca_topic_score_codex":0.00020166021,"about_ca_topic_score_gemma":0.000015683561,"teacher_disagreement_score":0.8616679,"about_ca_system_score_codex":0.00024324734,"about_ca_system_score_gemma":0.000110165805,"threshold_uncertainty_score":0.9993442},"labels":[],"label_agreement":null},{"id":"W4281665821","doi":"10.3390/cancers14112663","title":"Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging","year":2022,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Moncton","funders":"","keywords":"Breast cancer; Dual (grammatical number); Breast imaging; Deep learning; Medicine; Ultrasound; Medical physics; Ultrasound imaging; Radiology; Artificial intelligence; Computer science; Mammography; Cancer; Internal medicine; Art","score_opus":0.01513061884163048,"score_gpt":0.2618334693633993,"score_spread":0.24670285052176882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281665821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03420194,0.0016847239,0.95711815,0.0028715073,0.0024477202,0.0006673441,0.00012470846,0.00037002668,0.000513896],"genre_scores_gemma":[0.99102485,0.00019180667,0.0035860285,0.00071477704,0.00011869998,0.0041027116,0.0000033745562,0.000027969962,0.00022980831],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850774,0.00006245615,0.00020685165,0.0005251999,0.00027091493,0.00042683264],"domain_scores_gemma":[0.99931526,0.00015271766,0.00012013157,0.000270038,0.00007087488,0.00007096994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002947434,0.0001465703,0.00016278311,0.00016870504,0.00037491616,0.000080647216,0.00047276134,0.000023777045,0.00013026375],"category_scores_gemma":[0.000033572942,0.00017624303,0.00007822817,0.0005707357,0.000042520518,0.00042953953,0.00019628867,0.00033330295,0.000001796677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029607494,0.0000071193363,0.007776906,0.000014739794,0.000012157276,0.0000047142157,0.0018973999,0.8754941,0.0002885283,0.0004238515,0.0015523292,0.1124985],"study_design_scores_gemma":[0.00055058394,0.000027746666,0.0016741483,0.000017915434,0.000007722901,0.000035587807,0.00043216694,0.99212927,0.00034033987,0.0015960622,0.0029573871,0.00023106112],"about_ca_topic_score_codex":0.0014513626,"about_ca_topic_score_gemma":0.0008580781,"teacher_disagreement_score":0.9568229,"about_ca_system_score_codex":0.0060263337,"about_ca_system_score_gemma":0.0005275239,"threshold_uncertainty_score":0.9977894},"labels":[],"label_agreement":null},{"id":"W4282926808","doi":"10.1038/s41598-022-13917-4","title":"Quantitative digital histopathology and machine learning to predict pathological complete response to chemotherapy in breast cancer patients using pre-treatment tumor biopsies","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; York University; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities; Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Histopathology; Pathological; Breast cancer; Chemotherapy; Medicine; Pathology; Cancer; Oncology; Biopsy; Internal medicine","score_opus":0.025617155649519146,"score_gpt":0.27971823153129954,"score_spread":0.2541010758817804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282926808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99121594,0.00007636636,0.0049614646,0.00062722166,0.0023339735,0.000604687,0.00006806551,0.000099406265,0.000012882812],"genre_scores_gemma":[0.9954677,0.0000015843439,0.0038969684,0.00014141912,0.000014778205,0.0001788715,0.000010846344,0.000014066659,0.00027371862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99731076,0.0002948203,0.0004161167,0.0011351451,0.00048323028,0.0003599475],"domain_scores_gemma":[0.9989752,0.00008083142,0.00023730398,0.00045514083,0.00010870201,0.00014277826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001120006,0.00018431999,0.00025004166,0.0004404424,0.00057044515,0.00029028123,0.00024286554,0.00002516775,0.000029554545],"category_scores_gemma":[0.00012379668,0.00016861415,0.00004459608,0.0010350492,0.00014406213,0.00031964653,0.00055459666,0.00014989318,0.000002590866],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021805335,0.0006788315,0.7554153,0.000017065911,0.000019398032,0.001973702,0.028095463,0.04092268,0.14006837,0.000029577559,0.00038371966,0.030215358],"study_design_scores_gemma":[0.001082829,0.0035624895,0.91064817,0.00006360741,0.000011886689,0.002704634,0.00054556364,0.060509335,0.0018021608,0.0007098176,0.017672366,0.0006871515],"about_ca_topic_score_codex":0.00017244442,"about_ca_topic_score_gemma":0.000030534953,"teacher_disagreement_score":0.15523285,"about_ca_system_score_codex":0.0010322548,"about_ca_system_score_gemma":0.00016636988,"threshold_uncertainty_score":0.6875886},"labels":[],"label_agreement":null},{"id":"W4283074804","doi":"10.1089/ipm.09.03.04","title":"Pathology is Poised for the Digital Revolution","year":2022,"lang":"en","type":"article","venue":"Inside Precision Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Federation of Science Journalists","funders":"","keywords":"Digital pathology; Digital Revolution; Medicine; Computer science; Pathology; Telecommunications","score_opus":0.03084144528261226,"score_gpt":0.2869741492550537,"score_spread":0.2561327039724415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283074804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066264286,0.0014877863,0.95486313,0.032083355,0.0032419343,0.00056351186,0.000012373984,0.0001447491,0.0009767374],"genre_scores_gemma":[0.9906576,0.00006947696,0.00357058,0.0044643627,0.00040020983,0.00027030535,0.0000053901786,0.000012393058,0.000549652],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862576,0.00007511382,0.000270291,0.0003544956,0.0004936436,0.00018069855],"domain_scores_gemma":[0.99819404,0.0008860776,0.00013110161,0.0006521629,0.000091440175,0.000045205114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081838586,0.00009460678,0.00013969556,0.00008007831,0.0004434168,0.000030351783,0.00073543,0.00003240478,0.00014032832],"category_scores_gemma":[0.00046579013,0.00006329783,0.000054484437,0.00042943834,0.00007891113,0.00022291155,0.0004497321,0.00019937754,0.000015161391],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007678386,0.000020957212,0.000100043464,0.000004959304,0.000010803146,0.000009992704,0.0016878804,0.00038654794,0.0012531781,0.0017106077,0.09370206,0.9010362],"study_design_scores_gemma":[0.0018957227,0.0015437728,0.0036078524,0.000032950375,0.00002312222,0.0003671319,0.00043242224,0.11319602,0.0010695813,0.06317777,0.81444794,0.00020569182],"about_ca_topic_score_codex":0.00002303598,"about_ca_topic_score_gemma":0.000003516793,"teacher_disagreement_score":0.9840312,"about_ca_system_score_codex":0.00015625102,"about_ca_system_score_gemma":0.000045804278,"threshold_uncertainty_score":0.34104484},"labels":[],"label_agreement":null},{"id":"W4283079279","doi":"10.1089/ipm.09.03.03","title":"How Digital Pathology is Advancing Biomarker Identification &amp; Drug Discovery","year":2022,"lang":"en","type":"article","venue":"Inside Precision Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada","funders":"","keywords":"Digital pathology; Virtual microscopy; Identification (biology); Medicine; Medical physics; Medical education; Pathology","score_opus":0.02410013385189814,"score_gpt":0.28050518822770537,"score_spread":0.25640505437580724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283079279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16731738,0.0009449999,0.8039889,0.022979794,0.0038367005,0.0002782724,0.000015780357,0.00021154144,0.000426678],"genre_scores_gemma":[0.9918275,0.00007914546,0.0029033944,0.0013072495,0.00020375899,0.0000830028,0.000024412268,0.00001978782,0.0035517712],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749815,0.00017093154,0.0004197266,0.0007100343,0.00091816863,0.00028295827],"domain_scores_gemma":[0.9980782,0.00038111323,0.000292656,0.0010370257,0.00011587801,0.000095128446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010097997,0.00017115979,0.00023394937,0.0002559569,0.00034368475,0.0002614396,0.0008360924,0.000040505045,0.00009250111],"category_scores_gemma":[0.00058790715,0.00015051302,0.00006638913,0.0008350047,0.00010164203,0.0021340786,0.0008725854,0.0002855941,0.0000372309],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063290296,0.00006281366,0.0010017253,0.0000166353,0.000020383222,0.00006515479,0.0037452648,0.00021553275,0.047536816,0.0003974384,0.064583324,0.8822916],"study_design_scores_gemma":[0.003016475,0.0006150392,0.020769138,0.00024607082,0.000054255728,0.0014600307,0.0022093419,0.027730705,0.018026052,0.08040697,0.84436846,0.001097432],"about_ca_topic_score_codex":0.000033456996,"about_ca_topic_score_gemma":0.000021989685,"teacher_disagreement_score":0.8811942,"about_ca_system_score_codex":0.00028886663,"about_ca_system_score_gemma":0.000058081587,"threshold_uncertainty_score":0.61377424},"labels":[],"label_agreement":null},{"id":"W4283316793","doi":"10.1016/j.media.2022.102520","title":"MVFStain: Multiple virtual functional stain histopathology images generation based on specific domain mapping","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Stain; Staining; Artificial intelligence; Computer science; H&E stain; Pathology; Pattern recognition (psychology); Medicine","score_opus":0.01887046352473579,"score_gpt":0.2305144341979102,"score_spread":0.21164397067317442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283316793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012659219,0.00007613448,0.9791698,0.006721579,0.0006957604,0.000115910494,0.00001662704,0.00016989316,0.0003750769],"genre_scores_gemma":[0.9508546,0.000012527902,0.043758012,0.0036318721,0.0006256318,0.00021233431,0.00018963212,0.00002101486,0.0006943644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996011,0.0007670769,0.00042172772,0.00080250786,0.0016448752,0.00035279646],"domain_scores_gemma":[0.9984723,0.00034982618,0.0001680504,0.00071364484,0.00011496741,0.00018121676],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018228445,0.00018638375,0.0003077962,0.00089636736,0.0006606553,0.00011196779,0.00067716365,0.000075674034,0.0031308269],"category_scores_gemma":[0.0002934958,0.00019238354,0.00027846682,0.0023715952,0.00015210592,0.00026559096,0.00033081634,0.00050240423,0.00004980657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033655178,0.0018094569,0.0071462756,0.000035744604,0.0008095164,0.003336215,0.0026234654,0.3253776,0.12286087,0.006852138,0.19297525,0.3358369],"study_design_scores_gemma":[0.000709347,0.0001841579,0.0031707047,0.0000023355133,0.000053816828,0.000022924729,0.00027084662,0.96391904,0.000829943,0.00028143259,0.03030817,0.00024729536],"about_ca_topic_score_codex":0.000046410612,"about_ca_topic_score_gemma":0.00003836367,"teacher_disagreement_score":0.9381954,"about_ca_system_score_codex":0.0007818217,"about_ca_system_score_gemma":0.00021124748,"threshold_uncertainty_score":0.99778044},"labels":[],"label_agreement":null},{"id":"W4283319497","doi":"10.2196/34753","title":"A Clinical Decision Support System for Assessing the Risk of Cervical Cancer: Development and Evaluation Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Iran University of Medical Sciences","keywords":"Cervical cancer; Medicine; Clinical decision support system; Decision support system; Risk assessment; Cancer; Disease; Health care; Gynecology; Intensive care medicine; Internal medicine; Data mining; Computer science","score_opus":0.059994612783788745,"score_gpt":0.4234037059758423,"score_spread":0.36340909319205356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283319497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6624866,0.000033143006,0.33521798,0.00012625486,0.0009152879,0.0010862404,0.0000036789666,0.00004531975,0.00008549653],"genre_scores_gemma":[0.9691535,0.000009853104,0.029549424,0.00016843913,0.00007319375,0.0010337953,0.0000026949676,0.000005317026,0.0000037444274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621695,0.0003278083,0.0011542498,0.00014374268,0.0019927556,0.00016450706],"domain_scores_gemma":[0.9978547,0.00095280964,0.0005519434,0.00034200386,0.00018593774,0.00011258965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009643883,0.000093192335,0.00022501031,0.00006974715,0.00044920066,0.00007605535,0.0006493461,0.00006441618,0.000031800973],"category_scores_gemma":[0.00026218887,0.000063321706,0.000052374704,0.00030332286,0.00006089131,0.00030767656,0.00066634605,0.0003537184,0.0000016338503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019935384,0.0001192371,0.01582532,0.00009245772,0.00004521199,7.595565e-7,0.010610547,0.00027718226,1.8643861e-7,0.00013332553,0.0006499617,0.9722259],"study_design_scores_gemma":[0.0016048371,0.00040832424,0.046134785,0.000060981125,0.00005132716,0.000022214703,0.01101469,0.93404734,0.00002025578,0.00013908366,0.006391796,0.00010433508],"about_ca_topic_score_codex":0.000015666297,"about_ca_topic_score_gemma":0.000021966438,"teacher_disagreement_score":0.97212154,"about_ca_system_score_codex":0.00029702362,"about_ca_system_score_gemma":0.0010366549,"threshold_uncertainty_score":0.34549338},"labels":[],"label_agreement":null},{"id":"W4283321234","doi":"10.1097/01.gox.0000842404.08151.7e","title":"19. Breastgan: Artificial Intelligence-enabled Breast Augmentation Simulation","year":2022,"lang":"en","type":"article","venue":"Plastic & Reconstructive Surgery Global Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canmore Museum and Geoscience Centre; McGill University Health Centre; McGill University","funders":"","keywords":"Computer science; Artificial neural network; Context (archaeology); Artificial intelligence; Chart; Surgical planning; Medical physics; Machine learning; Medicine; Surgery","score_opus":0.042029962631398424,"score_gpt":0.2981065623613233,"score_spread":0.2560765997299249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283321234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08167122,0.000031826483,0.9050924,0.00042062017,0.007900186,0.00084547093,0.0002928133,0.00024386916,0.0035015407],"genre_scores_gemma":[0.99430317,0.0000025839984,0.005111679,0.00015013537,0.00017855401,0.0001757997,0.000036553414,0.0000136767685,0.000027880651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705344,0.0004343503,0.0006347388,0.00081151485,0.00062531343,0.00044066578],"domain_scores_gemma":[0.997313,0.001448669,0.00043571662,0.00043361099,0.00019003342,0.00017893151],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008449695,0.0002528488,0.00036145822,0.00020106247,0.00076213287,0.0005246853,0.0010804033,0.00005916951,0.0007726794],"category_scores_gemma":[0.00027469386,0.00028985483,0.00012683964,0.0016143331,0.000114679984,0.0016908013,0.0011710365,0.00023952978,0.00010544996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044173465,0.00011566264,0.015780076,0.000011708188,0.00008962354,0.000037264745,0.00015532323,0.14041537,0.000027843178,0.016613401,0.0005957284,0.82571626],"study_design_scores_gemma":[0.0004332682,0.00025310964,0.030087028,0.00006435309,0.000067573994,0.0024182796,0.0015485848,0.78877074,0.00060317543,0.17324325,0.0013436661,0.0011669699],"about_ca_topic_score_codex":0.000662076,"about_ca_topic_score_gemma":0.00005648271,"teacher_disagreement_score":0.9126319,"about_ca_system_score_codex":0.0015582565,"about_ca_system_score_gemma":0.0006829575,"threshold_uncertainty_score":0.99995536},"labels":[],"label_agreement":null},{"id":"W4283652538","doi":"10.1142/9789811257452_0007","title":"Peripheral Blood Smear Analysis Using Deep Learning: Current Challenges and Future Directions","year":2022,"lang":"en","type":"book-chapter","venue":"Series in computer vision","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Peripheral blood; Current (fluid); Peripheral; Medicine; Computer science; Internal medicine; Engineering; Electrical engineering","score_opus":0.019888009327195484,"score_gpt":0.2631684633860333,"score_spread":0.2432804540588378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283652538","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030250677,0.32839414,0.5991275,0.0030045551,0.028085947,0.0016042509,0.000029745564,0.0019945826,0.034734245],"genre_scores_gemma":[0.021429623,0.6677545,0.2804098,0.00027658592,0.014202561,0.0001673785,0.00018215844,0.0005194379,0.015057975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746364,0.00015177907,0.00043104382,0.0011214938,0.0005249962,0.0003070313],"domain_scores_gemma":[0.99874985,0.000065189226,0.00029643285,0.0006985946,0.00009285231,0.00009709711],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028773802,0.00044130284,0.00058325223,0.0008337757,0.00044540374,0.00021376707,0.0005773556,0.0002377787,0.0001482263],"category_scores_gemma":[0.0000032729668,0.00048019603,0.00023673482,0.00037318232,0.00009963604,0.00071067066,0.001312975,0.0011238384,0.0000026746943],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001898155,0.000037622933,0.000026879194,0.00007227062,0.00025159438,0.000038693495,0.0026312675,0.005817683,0.0000036684796,0.018885165,0.000012474355,0.9722037],"study_design_scores_gemma":[0.0002971156,0.00068978115,0.00069741043,0.00011778867,0.0002698642,0.00013944485,0.000048947804,0.1879946,0.000004446433,0.004121465,0.80493397,0.0006851969],"about_ca_topic_score_codex":0.000018138166,"about_ca_topic_score_gemma":0.00015998879,"teacher_disagreement_score":0.9715185,"about_ca_system_score_codex":0.00032893452,"about_ca_system_score_gemma":0.000058097175,"threshold_uncertainty_score":0.999765},"labels":[],"label_agreement":null},{"id":"W4283722125","doi":"10.1109/i2mtc48687.2022.9806556","title":"An Automated Tool to Assess Air Space Size in Histopathology Images of Lung Tissue","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Intersection (aeronautics); Standard deviation; Computer vision; Image segmentation; Pattern recognition (psychology); Automated method; Mathematics; Statistics; Cartography","score_opus":0.04234032207718045,"score_gpt":0.3287013346268449,"score_spread":0.28636101254966445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283722125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8637828,0.000043635686,0.12186012,0.010422899,0.0021478087,0.000597189,0.000028477898,0.0005731111,0.0005439262],"genre_scores_gemma":[0.98799825,0.000021337399,0.011132434,0.00035216662,0.000017108685,0.00035249518,0.000007817246,0.000009889841,0.000108490196],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99797815,0.00014965322,0.0004214783,0.0005239718,0.000715136,0.00021162935],"domain_scores_gemma":[0.99902946,0.000030157118,0.00024279613,0.0003397551,0.00031037687,0.00004746232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069452554,0.00015748372,0.00020548272,0.0007446437,0.00013162557,0.000045215416,0.0008753347,0.00008136707,0.00016384078],"category_scores_gemma":[0.00010255367,0.000190378,0.000022925287,0.00066692027,0.00009331676,0.0004713113,0.0002762093,0.00027413518,0.0000043236873],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074749674,0.00026497626,0.0153462095,0.000022106044,0.00003790795,0.000030092238,0.0009975779,0.0012951668,0.8825346,0.02992045,0.001101248,0.06837492],"study_design_scores_gemma":[0.0033947837,0.001621224,0.11105101,0.000099853685,0.000034051278,0.0002614108,0.0027599318,0.12661423,0.73716295,0.007558372,0.008546533,0.00089562795],"about_ca_topic_score_codex":0.00011294217,"about_ca_topic_score_gemma":0.00017572491,"teacher_disagreement_score":0.14537163,"about_ca_system_score_codex":0.00082937215,"about_ca_system_score_gemma":0.00019509294,"threshold_uncertainty_score":0.776339},"labels":[],"label_agreement":null},{"id":"W4284895461","doi":"10.1155/2022/8517706","title":"Breast Cancer Detection on Histopathological Images Using a Composite Dilated Backbone Network","year":2022,"lang":"en","type":"article","venue":"Computational Intelligence and Neuroscience","topic":"AI in cancer detection","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Backbone network; Computer science; Artificial intelligence; Detector; Deep learning; Convolution (computer science); Segmentation; Feature (linguistics); Pattern recognition (psychology); Artificial neural network; Telecommunications","score_opus":0.05077951029351844,"score_gpt":0.2974821849732336,"score_spread":0.24670267467971516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284895461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086969316,0.00013192896,0.9104854,0.0006630842,0.0013989698,0.00015420048,0.000016721371,0.00014069783,0.00003967852],"genre_scores_gemma":[0.9933605,0.00003911372,0.005025439,0.0014031662,0.00008527647,0.000038524802,0.0000011179897,0.000008499961,0.000038372033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980293,0.0001757389,0.0002451187,0.00071445806,0.0005303051,0.00030511207],"domain_scores_gemma":[0.9993155,0.00014805025,0.0001491777,0.00020069086,0.00009112395,0.00009545386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028701194,0.00015975826,0.00013893968,0.0001384857,0.0012212762,0.00016034947,0.00056454743,0.000028629147,0.000024419733],"category_scores_gemma":[0.000013931835,0.0001610493,0.000044487344,0.0011576937,0.00022403723,0.0004135432,0.00048952317,0.00031975482,0.0000047801473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031528096,0.000047418656,0.00037104127,0.0000031456689,0.0000011548109,0.00002346982,0.000076875665,0.9535046,0.006894119,0.0014607883,0.000044582965,0.037541233],"study_design_scores_gemma":[0.00006229302,0.00021886146,0.019152509,0.000013494941,0.0000044443796,0.0010300215,0.000011532641,0.96754515,0.0038803213,0.007616538,0.00025532892,0.00020948985],"about_ca_topic_score_codex":0.000036899026,"about_ca_topic_score_gemma":0.000002212516,"teacher_disagreement_score":0.90639114,"about_ca_system_score_codex":0.00022365178,"about_ca_system_score_gemma":0.000066956,"threshold_uncertainty_score":0.93931925},"labels":[],"label_agreement":null},{"id":"W4284978235","doi":"10.1016/j.cmpb.2022.107012","title":"Constrained multiple instance learning for ulcerative colitis prediction using histological images","year":2022,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"European Regional Development Fund; Generalitat Valenciana; Ministerio de Economía y Competitividad; European Commission","keywords":"Ulcerative colitis; Artificial intelligence; Inflammatory bowel disease; Colitis; Rectum; Computer science; Focus (optics); Relevance (law); Medicine; Machine learning; Pattern recognition (psychology); Disease; Pathology; Gastroenterology","score_opus":0.08131422063713314,"score_gpt":0.361383803857829,"score_spread":0.28006958322069586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284978235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0143341785,0.0005999131,0.9823517,0.00045154185,0.0013411674,0.00070670445,0.0000065832346,0.00017697594,0.00003119727],"genre_scores_gemma":[0.23006535,0.000022059754,0.7693059,0.00017846916,0.00017276785,0.00021741203,0.000014216613,0.000008324485,0.00001549032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795896,0.00068520143,0.00034056904,0.0005344665,0.00018736228,0.0002934563],"domain_scores_gemma":[0.9990281,0.0004850806,0.00015870787,0.00017601682,0.00007575188,0.000076380355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018810683,0.00015319721,0.0002921586,0.00020257561,0.00040798794,0.00006562546,0.00026295337,0.000057951394,0.0000057467714],"category_scores_gemma":[0.00007301631,0.00014357692,0.000043550033,0.00066060957,0.00025297943,0.00017909697,0.00032199014,0.0003225132,8.282348e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007886549,0.000060302707,0.0025323844,0.000038015616,0.000016787624,0.000011935874,0.0011067978,0.0005880207,0.0012927776,0.0007587083,0.000066453424,0.993449],"study_design_scores_gemma":[0.0018363416,0.0020696411,0.0048775454,0.000050710056,0.000011335679,0.00018379556,0.00023067018,0.9533797,0.00029489858,0.0027658504,0.034114495,0.0001849991],"about_ca_topic_score_codex":0.0000448811,"about_ca_topic_score_gemma":0.000005298901,"teacher_disagreement_score":0.99326396,"about_ca_system_score_codex":0.00024074707,"about_ca_system_score_gemma":0.000057536814,"threshold_uncertainty_score":0.5854897},"labels":[],"label_agreement":null},{"id":"W4285019244","doi":"10.1007/s11063-022-10928-0","title":"Classification and Detection of Cancer in Histopathologic Scans of Lymph Node Sections Using Convolutional Neural Network","year":2022,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Convolutional neural network; Feature extraction; Pattern recognition (psychology); Medical diagnosis; Image processing; Deep learning; Machine learning; Cancer detection; Artificial neural network; Cancer; Radiology; Medicine; Image (mathematics)","score_opus":0.03440520410655615,"score_gpt":0.2697299902752155,"score_spread":0.23532478616865934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285019244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93088955,0.00055221806,0.06665844,0.0010296395,0.0007045565,0.00010237973,0.0000047144504,0.00004921601,0.000009262987],"genre_scores_gemma":[0.997774,0.000005801602,0.0016710511,0.0004115917,0.00007829718,0.000045980974,9.881741e-7,0.000008614594,0.0000036561496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988106,0.00013546657,0.0002946936,0.0003129384,0.00025349855,0.00019281176],"domain_scores_gemma":[0.99941564,0.00003596224,0.0003259677,0.00014325144,0.000054667504,0.000024525563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020897016,0.00009899656,0.00014822287,0.00017959804,0.00031029782,0.0000238368,0.0002051869,0.000033017044,0.0000036160357],"category_scores_gemma":[0.000011939978,0.00011179223,0.00003364722,0.0008190729,0.00013201646,0.0003722415,0.0001137352,0.00019950236,5.8292915e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027104295,0.000018068456,0.038321152,0.000060643237,0.0000029087566,0.0000021682624,0.00040099313,0.54282033,0.39302096,0.000030738753,0.000009156845,0.025285803],"study_design_scores_gemma":[0.00021220262,0.000030118063,0.18085812,0.000023267916,0.00000910786,0.000058353216,0.00005489349,0.81682783,0.0016994976,0.000117167954,0.000015155279,0.00009426584],"about_ca_topic_score_codex":0.00039346443,"about_ca_topic_score_gemma":0.000057690293,"teacher_disagreement_score":0.39132145,"about_ca_system_score_codex":0.00046263917,"about_ca_system_score_gemma":0.000095504045,"threshold_uncertainty_score":0.4558755},"labels":[],"label_agreement":null},{"id":"W4285109585","doi":"10.1109/tevc.2022.3178299","title":"Evolutionary Computation in Action: Hyperdimensional Deep Embedding Spaces of Gigapixel Pathology Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University; Ontario Tech University","funders":"","keywords":"Artificial intelligence; Interpretability; Computer science; Digital pathology; Deep learning; Pattern recognition (psychology); Feature vector; Evolutionary algorithm; Evolutionary computation; Feature (linguistics); Feature selection; Visualization; Representation (politics)","score_opus":0.02046694541035996,"score_gpt":0.27993150332622446,"score_spread":0.2594645579158645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285109585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07498771,0.0002785812,0.92023605,0.0008798657,0.0027157122,0.0004316084,0.000050627194,0.0002811813,0.00013867626],"genre_scores_gemma":[0.9189112,0.000033435892,0.080496766,0.00013493007,0.00006952274,0.00020262763,0.000041713567,0.00002742984,0.000082346734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965011,0.0006480507,0.00072747114,0.0007862875,0.0009527831,0.00038430624],"domain_scores_gemma":[0.9984673,0.00046846084,0.0003881104,0.00032207047,0.00026584466,0.00008818891],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046408345,0.0002932719,0.0003397648,0.0011751046,0.00086196634,0.00003782679,0.0004212449,0.00012199218,0.000087104],"category_scores_gemma":[0.000010704208,0.0003717894,0.00018332333,0.0017299168,0.00015752194,0.0011029876,0.000030473322,0.0006338931,0.000028248769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014074997,0.00048472182,0.0001344096,0.000026570828,0.000031188083,0.000024505487,0.00045606296,0.9607597,0.0038770272,0.00039208127,0.0004110517,0.033261932],"study_design_scores_gemma":[0.0010718348,0.0005961367,0.012474285,0.000030674983,0.00002207925,0.00048468358,0.00040810858,0.9767647,0.0013000673,0.0063420613,0.00015617149,0.0003491995],"about_ca_topic_score_codex":0.00012786136,"about_ca_topic_score_gemma":0.00003159931,"teacher_disagreement_score":0.8439235,"about_ca_system_score_codex":0.0013140977,"about_ca_system_score_gemma":0.00030840447,"threshold_uncertainty_score":0.9998734},"labels":[],"label_agreement":null},{"id":"W4285176390","doi":"10.1016/b978-0-32-385845-8.00011-3","title":"The use of deep learning in image analysis for the study of oncology","year":2022,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Machine learning; Popularity; Field (mathematics); Process (computing); Big data; Deep belief network; Artificial neural network; Data science; Data mining; Psychology; Mathematics","score_opus":0.04198398377511795,"score_gpt":0.289117765711507,"score_spread":0.24713378193638905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285176390","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013830693,0.003055465,0.07537284,0.000645419,0.0022995493,0.007813426,0.000027248478,0.00016235969,0.9092406],"genre_scores_gemma":[0.0874799,0.0004902829,0.0070707756,0.0001803395,0.00019410062,0.0011695656,0.0000054672573,0.00010476912,0.9033048],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830705,0.00020344701,0.00057187123,0.0003705351,0.00037191185,0.00017521322],"domain_scores_gemma":[0.9964472,0.0017587191,0.000731467,0.0008997612,0.00014241676,0.000020447835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010361169,0.00017483353,0.0004878991,0.0002798823,0.00024919942,0.000044046064,0.0010707928,0.000089531764,0.000027894685],"category_scores_gemma":[0.00006828268,0.00011719936,0.00027821722,0.00012868707,0.0001327806,0.00007574998,0.00056731334,0.0005405232,9.937751e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028470591,0.000018354503,0.00006748044,0.000011269983,0.00050673337,0.0000031897732,0.0021603573,0.0024885843,0.0000070829587,0.0015797607,0.000006168937,0.9931225],"study_design_scores_gemma":[0.0003410933,0.00087917864,0.0003330703,0.000012347883,0.00046706392,0.000002011326,0.00020285565,0.01633008,0.000016236254,0.0012614661,0.9800119,0.00014271117],"about_ca_topic_score_codex":0.000024991858,"about_ca_topic_score_gemma":0.0021772648,"teacher_disagreement_score":0.9929798,"about_ca_system_score_codex":0.0002203456,"about_ca_system_score_gemma":0.00010675729,"threshold_uncertainty_score":0.47792512},"labels":[],"label_agreement":null},{"id":"W4286517374","doi":"10.18280/ria.360313","title":"Investigations on Deep Learning Techniques for Analysing Mammograms","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Convolutional neural network; Mammography; Pattern recognition (psychology); Residual; Residual neural network; Machine learning; Abstraction; Breast cancer; Class (philosophy); Cancer; Medicine; Algorithm","score_opus":0.046899225563322613,"score_gpt":0.29061476187625906,"score_spread":0.24371553631293646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286517374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032294858,0.000089151115,0.9927459,0.0011717608,0.00036139635,0.0003546919,0.0000018389544,0.00042359717,0.0016222185],"genre_scores_gemma":[0.9099302,0.000018200937,0.0877944,0.00037990676,0.0001171475,0.0005519314,0.000010173686,0.000022344644,0.0011756517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856603,0.00011400105,0.0003162368,0.00048498617,0.00023270526,0.00028606158],"domain_scores_gemma":[0.9989366,0.00024401525,0.00015868754,0.00050729775,0.00008487903,0.00006852501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063395087,0.00012584962,0.00013927535,0.00024156722,0.0010184324,0.00013331784,0.0006866093,0.000036151443,0.00007189318],"category_scores_gemma":[0.00013583379,0.0001460117,0.0001225073,0.0011410034,0.000054902375,0.00021178754,0.00022445573,0.00033252002,0.000039528102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011291494,0.000078175064,0.00016456566,0.000020775315,0.000016247044,0.0000038264275,0.0016004224,0.41951382,0.0052348454,0.038805857,0.00025933216,0.53429085],"study_design_scores_gemma":[0.000014320807,0.00038103783,0.0000068396653,0.000016542683,0.000007465806,0.000014361824,0.0004980004,0.79582834,0.1313506,0.011681027,0.06003463,0.00016682946],"about_ca_topic_score_codex":0.000026604943,"about_ca_topic_score_gemma":0.000010397018,"teacher_disagreement_score":0.90670073,"about_ca_system_score_codex":0.00023544492,"about_ca_system_score_gemma":0.00003936781,"threshold_uncertainty_score":0.7833062},"labels":[],"label_agreement":null},{"id":"W4286707749","doi":"10.32768/abc.202293364-376","title":"Detection of Metastatic Breast Cancer from Whole-Slide Pathology Images Using an Ensemble Deep-Learning Method","year":2022,"lang":"en","type":"article","venue":"Archives of Breast Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome Canada","funders":"","keywords":"Breast cancer; Medicine; Convolutional neural network; Deep learning; Lymph node; Lymph; Metastasis; Metastatic breast cancer; Diagnostic accuracy; Cancer; Artificial intelligence; Radiology; Pathology; Oncology; Computer science; Internal medicine","score_opus":0.01784394135487419,"score_gpt":0.2920982579915649,"score_spread":0.2742543166366907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286707749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20716467,0.00082760124,0.7903478,0.00032985,0.0005799008,0.00017594807,0.00042515542,0.00008540898,0.00006367224],"genre_scores_gemma":[0.902358,0.00009042708,0.097116925,0.00008968452,0.00013446716,0.00013493138,0.000008420361,0.000036627647,0.000030512416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997026,0.0009938848,0.0004739883,0.0006834392,0.00043611755,0.0003865307],"domain_scores_gemma":[0.9982857,0.00033100366,0.0006202676,0.0005542479,0.00010092189,0.00010785679],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003758464,0.00023504838,0.00045258264,0.00033266045,0.00032806152,0.000034756697,0.00074411917,0.00003436502,0.00015623067],"category_scores_gemma":[0.000014416581,0.0002547599,0.0001539011,0.00056582125,0.0001579859,0.00058387645,0.00054844475,0.00042844718,0.0000010065492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013440453,0.00006533569,0.0011855363,0.000030144218,0.000080421836,0.000008488737,0.0018679859,0.071111076,0.44300687,0.000039106246,0.0000022065724,0.48246843],"study_design_scores_gemma":[0.0014914987,0.0003976175,0.16540621,0.0001432517,0.00026062728,0.001029931,0.0011783489,0.6540436,0.16700494,0.007982057,0.00041404078,0.0006478562],"about_ca_topic_score_codex":0.012839366,"about_ca_topic_score_gemma":0.0007021703,"teacher_disagreement_score":0.69519335,"about_ca_system_score_codex":0.00020766519,"about_ca_system_score_gemma":0.00021800007,"threshold_uncertainty_score":0.99999046},"labels":[],"label_agreement":null},{"id":"W4286856866","doi":"10.3791/50341-v","title":"Detection of Architectural Distortion in Prior Mammograms &lt;em&gt;via&lt;/em&gt; Analysis of Oriented Patterns","year":2013,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.015538371501576805,"score_gpt":0.3355714869614179,"score_spread":0.3200331154598411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286856866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6527521,0.0002072151,0.34629285,0.000017121934,0.00050075457,0.00020061278,0.0000021682479,0.000018612529,0.000008582982],"genre_scores_gemma":[0.99444586,0.000033614106,0.0053491453,0.000027369224,0.00007280124,0.000029013008,0.0000030664673,0.000018237875,0.000020883877],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99657214,0.00029905708,0.0014396629,0.0003246996,0.0010468143,0.00031761278],"domain_scores_gemma":[0.9971791,0.00007430513,0.0017478248,0.00039393708,0.0004589089,0.00014592602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005548397,0.00023965062,0.00071179756,0.0013636636,0.000064331696,0.000068841095,0.00057167304,0.00012030207,0.0000757062],"category_scores_gemma":[0.00006507405,0.0002128499,0.0004248126,0.0018367259,0.000055368993,0.00079741527,0.00014248717,0.00023425603,0.0000040259633],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003451149,0.00057215506,0.0072939578,0.000041639123,0.00067603233,0.000008961223,0.0057284245,0.0008022436,0.86408097,0.000023712613,0.000011700351,0.12041512],"study_design_scores_gemma":[0.0027850964,0.0011958808,0.19206326,0.00015585848,0.00024279175,0.00004161916,0.00040454278,0.04306032,0.7594974,0.00014396792,0.000108860026,0.0003004052],"about_ca_topic_score_codex":0.00031109306,"about_ca_topic_score_gemma":0.00018203311,"teacher_disagreement_score":0.3416938,"about_ca_system_score_codex":0.00047854154,"about_ca_system_score_gemma":0.000056199257,"threshold_uncertainty_score":0.8679767},"labels":[],"label_agreement":null},{"id":"W4287185803","doi":"10.48550/arxiv.2105.01824","title":"Deep learning-based tumor segmentation on digital images of histopathology slides for microdosimetry applications","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Digital pathology; Artificial intelligence; Computer science; Segmentation; Deep learning; Workflow; Pattern recognition (psychology)","score_opus":0.03185344098017691,"score_gpt":0.19711853568369173,"score_spread":0.1652650947035148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287185803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08835142,0.00007643285,0.91042656,0.000040163253,0.00026227537,0.00045294856,0.000020917249,0.00013435338,0.00023494773],"genre_scores_gemma":[0.9896568,0.000018164308,0.009784855,0.000060399652,0.000045120545,0.000018291552,0.00006997163,0.000017701535,0.00032870396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986175,0.00008314358,0.0001961831,0.0008502431,0.000070372684,0.00018259788],"domain_scores_gemma":[0.99837273,0.0002447223,0.00041345906,0.00065784896,0.00025503855,0.00005619826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012382235,0.00019647891,0.0002503173,0.0002849132,0.0001298755,0.000092454386,0.00069802377,0.00013267419,0.000008460527],"category_scores_gemma":[0.000051196785,0.00025514036,0.00019700814,0.00040774592,0.00010957868,0.0002624989,0.00037576945,0.00030389812,0.000009492636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009587843,0.00026347014,0.0049102106,0.0003782994,0.0000567977,0.00005225695,0.00022050898,0.9747685,0.00533574,0.0036759202,0.000085401014,0.010156997],"study_design_scores_gemma":[0.0017069808,0.0007260428,0.0047775353,0.00020185023,0.00020590256,0.000015690786,0.000531173,0.85557836,0.12465656,0.009267738,0.0012938776,0.0010383115],"about_ca_topic_score_codex":0.000024534113,"about_ca_topic_score_gemma":0.000011000547,"teacher_disagreement_score":0.9013054,"about_ca_system_score_codex":0.00042073178,"about_ca_system_score_gemma":0.00018916337,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W4287844213","doi":"10.1016/j.artmed.2022.102368","title":"Evolutionary deep feature selection for compact representation of gigapixel images in digital pathology","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University; Brock University; Ontario Tech University","funders":"Ontario Research Foundation","keywords":"Computer science; Digital pathology; Artificial intelligence; Pattern recognition (psychology); Deep learning; Salient; Feature selection; Representation (politics); Feature (linguistics); Visualization; Set (abstract data type); Feature vector; Evolutionary algorithm; Feature extraction; Data mining","score_opus":0.043917067507823856,"score_gpt":0.342908389920368,"score_spread":0.2989913224125441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287844213","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10571737,0.00036362367,0.8872766,0.004762118,0.0010367425,0.0005345966,0.000008658712,0.000058641326,0.00024168105],"genre_scores_gemma":[0.99587613,0.000026060292,0.0037236304,0.00010116776,0.0001268104,0.00008603507,0.00001688627,0.000007879975,0.00003540871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851763,0.000101202015,0.0004671904,0.0003790619,0.00031412227,0.0002208019],"domain_scores_gemma":[0.99908257,0.00036822495,0.00017682786,0.00022195687,0.00011881304,0.000031632648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005262939,0.0001033835,0.00023121898,0.0004434097,0.00010284965,0.000014969437,0.0003715114,0.00005122338,0.000039388888],"category_scores_gemma":[0.00041966114,0.00010641378,0.00004187608,0.001538128,0.00013973752,0.00043145148,0.00008787424,0.00027997087,0.0000025632253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069715927,0.00057427475,0.04134505,0.000070950184,0.00002105171,0.000050136718,0.010005664,0.1521959,0.054101806,0.035018828,0.0035656726,0.7023535],"study_design_scores_gemma":[0.00024230585,0.001538515,0.013584102,0.00006547886,0.000008427174,0.00012641601,0.0036927108,0.71137655,0.037207197,0.2314419,0.000480642,0.00023575588],"about_ca_topic_score_codex":0.00032693538,"about_ca_topic_score_gemma":0.00024137436,"teacher_disagreement_score":0.8901588,"about_ca_system_score_codex":0.00029583115,"about_ca_system_score_gemma":0.00006336286,"threshold_uncertainty_score":0.43394282},"labels":[],"label_agreement":null},{"id":"W4287958519","doi":"10.1007/s11548-022-02707-y","title":"Training deep neural networks with noisy clinical labels: toward accurate detection of prostate cancer in US data","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Generalizability theory; Prostate cancer; Machine learning; Artificial neural network; Pattern recognition (psychology); Cancer; Medicine; Mathematics; Statistics","score_opus":0.08352760268747464,"score_gpt":0.33551231751081056,"score_spread":0.25198471482333595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287958519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5045863,0.0008964627,0.48810238,0.0010463863,0.0052786833,0.00006163269,0.000008707292,0.000014597032,0.000004881341],"genre_scores_gemma":[0.9954149,0.0003414279,0.003282862,0.00043230446,0.0005044924,0.000007740819,0.000006262367,0.000008011838,0.0000019841807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977017,0.0006122774,0.00087520207,0.00029787523,0.00033018008,0.000182752],"domain_scores_gemma":[0.9976967,0.00091929256,0.00087288884,0.00021105207,0.00023758513,0.0000624655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018511065,0.00011999338,0.00041696912,0.00036900895,0.00007112904,0.00004915826,0.00088317704,0.000066583794,0.000007979258],"category_scores_gemma":[0.000046512796,0.00010359901,0.000082691455,0.00030233816,0.00011340509,0.0005903164,0.0003936752,0.0006200151,6.991431e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006814574,0.00007115898,0.11657347,0.0000062233676,0.00030271077,0.00033183207,0.00048401204,0.14850526,0.00004483199,0.000020657952,0.000107334374,0.73287106],"study_design_scores_gemma":[0.00071394234,0.00029297787,0.22822078,0.00003923489,0.000015606927,0.00302679,0.00003951215,0.7667934,0.000016265227,0.000059695227,0.0006706936,0.000111125715],"about_ca_topic_score_codex":0.0000332249,"about_ca_topic_score_gemma":0.000063403444,"teacher_disagreement_score":0.73275995,"about_ca_system_score_codex":0.000112651294,"about_ca_system_score_gemma":0.00019565866,"threshold_uncertainty_score":0.42246452},"labels":[],"label_agreement":null},{"id":"W4288463778","doi":"10.18280/ts.390317","title":"A Hybrid Model Particle Swarm Optimization Based Mammogram Classification Using Kernel Support Vector Machine","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Particle swarm optimization; Support vector machine; Artificial intelligence; Computer science; Mammography; Classifier (UML); Machine learning; Digital mammography; Kernel (algebra); Computation; Breast cancer; Pattern recognition (psychology); Feature extraction; Cancer; Algorithm; Mathematics; Medicine","score_opus":0.04243668920910821,"score_gpt":0.2592386474227966,"score_spread":0.21680195821368842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288463778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037614018,0.000018440836,0.9605351,0.00081917876,0.0002334887,0.0003601506,0.000029517665,0.00026262188,0.00012747112],"genre_scores_gemma":[0.93205035,0.0000016655032,0.06711473,0.0004853115,0.000059776317,0.00017455863,0.00004541543,0.00002086691,0.00004735406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814,0.0001299342,0.00033996298,0.00046102077,0.0006262615,0.0003028453],"domain_scores_gemma":[0.99928033,0.000026141752,0.00018131569,0.00034736184,0.000068462505,0.000096384385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005008525,0.00015503034,0.00012721732,0.00010835009,0.0004120406,0.00012446466,0.0004683729,0.00002131714,0.00047314222],"category_scores_gemma":[0.000005257887,0.00017745647,0.00007705187,0.000381356,0.000028852648,0.0004212016,0.00014499045,0.00015689743,0.00000955084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045022007,0.00018951774,0.00021257452,0.000008825197,0.000012286255,0.000005885769,0.00015796549,0.986148,0.0063557983,0.0012038029,0.0001588765,0.005501472],"study_design_scores_gemma":[0.0007273944,0.00022808072,0.0001755743,0.0000034818243,0.00002062884,0.00001553997,0.00001724723,0.9922237,0.0059017325,0.00026353076,0.00022629353,0.00019679528],"about_ca_topic_score_codex":0.000037629587,"about_ca_topic_score_gemma":0.0000025885158,"teacher_disagreement_score":0.8944363,"about_ca_system_score_codex":0.0005156202,"about_ca_system_score_gemma":0.000198817,"threshold_uncertainty_score":0.72364646},"labels":[],"label_agreement":null},{"id":"W4289937451","doi":"10.21203/rs.3.rs-1882716/v1","title":"Bias Reduction in Representation of Histopathology Images Using Deep Feature Selection","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Generalization; Pattern recognition (psychology); Selection bias; Feature extraction; Feature selection; Feature (linguistics); Representation (politics); Data mining; Statistics; Mathematics","score_opus":0.1385631995075036,"score_gpt":0.437929365569947,"score_spread":0.2993661660624434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289937451","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6319841,0.002806456,0.35414135,0.0021579494,0.00426651,0.0026546563,0.000029015704,0.0003597429,0.0016001875],"genre_scores_gemma":[0.962948,0.00039336825,0.035412345,0.000006636471,0.0003350606,0.0003328127,0.000043797325,0.000037427417,0.0004905083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99466646,0.002194647,0.00040920544,0.0010399988,0.0012407879,0.00044892853],"domain_scores_gemma":[0.997842,0.00019609994,0.000334254,0.0009295085,0.00063817546,0.000059965227],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024172321,0.00018635203,0.00033800298,0.0017894694,0.0002598661,0.000111783724,0.000858359,0.00033820365,0.00006855454],"category_scores_gemma":[0.00045742063,0.00022073781,0.00012664194,0.002750933,0.00014191886,0.00040682865,0.0018516098,0.0024143755,0.0000035071444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006392167,0.0008067007,0.054932646,0.0035137734,0.000093229435,0.0002763899,0.017307285,0.48846307,0.23136504,0.004122098,0.0064547267,0.19202583],"study_design_scores_gemma":[0.0015430071,0.0016069064,0.1641444,0.0011682087,0.000045042016,0.00071765005,0.0036538248,0.6238353,0.1428175,0.05602321,0.0030557753,0.0013891456],"about_ca_topic_score_codex":0.0021821265,"about_ca_topic_score_gemma":0.00016099006,"teacher_disagreement_score":0.3309639,"about_ca_system_score_codex":0.0028221624,"about_ca_system_score_gemma":0.0006097941,"threshold_uncertainty_score":0.9998871},"labels":[],"label_agreement":null},{"id":"W4289985685","doi":"10.3390/curroncol29080435","title":"Reducing Unnecessary Biopsies Using Digital Breast Tomosynthesis and Ultrasound in Dense and Nondense Breasts","year":2022,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Ultrasound; Digital Breast Tomosynthesis; Breast ultrasound; Radiology; Tomosynthesis; Breast cancer; Mammography; Medical physics; Internal medicine; Cancer","score_opus":0.049629862006088356,"score_gpt":0.32293039101625565,"score_spread":0.27330052901016727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289985685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99339366,0.0013327341,0.0035100623,0.00040532995,0.0010425441,0.00012498302,0.000024992234,0.00005888835,0.00010682088],"genre_scores_gemma":[0.99866533,0.000088599256,0.0010917842,0.000031160143,0.00007929103,0.000023529283,0.0000022487645,0.000009578114,0.000008488098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987452,0.00015687723,0.00020982452,0.00046284628,0.0001627357,0.00026248663],"domain_scores_gemma":[0.99914247,0.00043304326,0.00010747742,0.00021021572,0.000030287143,0.000076483295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030012277,0.00013026054,0.00019590293,0.00021452767,0.000230798,0.0001206431,0.00022980232,0.000045249886,0.000016108654],"category_scores_gemma":[0.00006215298,0.00014377233,0.000023071303,0.00038799644,0.0001301972,0.00049234135,0.00056843564,0.00025786128,0.0000013834829],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074371135,0.00022879263,0.048547693,0.000048143625,0.00001792936,0.0000778972,0.0028325627,0.0005551912,0.003291173,0.0002367958,0.00016378787,0.9439257],"study_design_scores_gemma":[0.0076801283,0.002516037,0.38180286,0.00058148295,0.00018390291,0.10579735,0.007943848,0.40988368,0.004053386,0.014827999,0.061131846,0.0035974574],"about_ca_topic_score_codex":0.00007720825,"about_ca_topic_score_gemma":0.000032347434,"teacher_disagreement_score":0.9403282,"about_ca_system_score_codex":0.00045649902,"about_ca_system_score_gemma":0.00014323501,"threshold_uncertainty_score":0.58628654},"labels":[],"label_agreement":null},{"id":"W4292874285","doi":"10.1109/memea54994.2022.9856496","title":"Classification of Ultrasound Breast Images Using Fused Ensemble of Deep Learning Classifiers","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Artificial intelligence; Autoencoder; Deep learning; Transfer of learning; Computer science; Ensemble learning; Machine learning; Pattern recognition (psychology); Convolutional neural network; Contextual image classification; Source code; Image (mathematics)","score_opus":0.038277995129390244,"score_gpt":0.2945394759490936,"score_spread":0.25626148081970335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292874285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07546049,0.000113235175,0.9158898,0.0025787447,0.0010636249,0.00060124364,0.00005133388,0.000094077826,0.0041474267],"genre_scores_gemma":[0.9969744,0.000066110566,0.0023006801,0.00013576842,0.00014191092,0.00027344833,0.00002209465,0.000015333178,0.00007025056],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966338,0.0001790434,0.0005228998,0.000459676,0.0020288317,0.00017570388],"domain_scores_gemma":[0.99862623,0.00018090598,0.00046004055,0.00033867126,0.00027291814,0.00012120721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009808848,0.00014295547,0.00018859192,0.00019576485,0.00033564205,0.000040655228,0.0008477359,0.00006410436,0.00020762095],"category_scores_gemma":[0.00007303046,0.00015211046,0.00007825023,0.0004979837,0.00013666652,0.00019021181,0.00015679329,0.00034930903,0.0000032203793],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070155416,0.0005602145,0.010701119,0.000046826284,0.00017565052,0.0000013149538,0.0002960792,0.006337899,0.8820859,0.0086647235,0.00032315278,0.090736926],"study_design_scores_gemma":[0.0060099373,0.0013241849,0.05776763,0.00028065196,0.0002540606,0.0005806806,0.0017829242,0.6651246,0.20954429,0.006710951,0.048990406,0.0016297012],"about_ca_topic_score_codex":0.000063556625,"about_ca_topic_score_gemma":0.000006868729,"teacher_disagreement_score":0.9215139,"about_ca_system_score_codex":0.00034417445,"about_ca_system_score_gemma":0.000090911,"threshold_uncertainty_score":0.62028843},"labels":[],"label_agreement":null},{"id":"W4293205487","doi":"10.2139/ssrn.4060776","title":"Validation of the BOADICEA&amp;nbsp; Multifactorial Breast Cancer Risk Prediction Model in a Large Prospective Study","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Breast cancer; Medicine; Cancer; Prospective cohort study; Risk assessment; Environmental health; Internal medicine; Computer science","score_opus":0.009584734804327042,"score_gpt":0.25793486162663853,"score_spread":0.2483501268223115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293205487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84124684,0.00016147555,0.1561508,0.00020232986,0.001532864,0.0005869917,0.00005602109,0.0000378301,0.000024842271],"genre_scores_gemma":[0.99915427,0.00016774936,0.0001126868,0.000012127584,0.00028817382,0.0001384624,8.709581e-7,0.000014660654,0.00011100962],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971019,0.00048294518,0.00038802467,0.00032922742,0.00077114487,0.0009267319],"domain_scores_gemma":[0.9989564,0.00003130223,0.00048995606,0.00035206045,0.00013586413,0.000034418703],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026066096,0.00013486142,0.00016298646,0.00017132648,0.00058762805,0.000048855607,0.00075697916,0.00004004861,0.000018063636],"category_scores_gemma":[0.000035322653,0.00011170418,0.00009584639,0.00081805914,0.000020819525,0.0005032967,0.00028506687,0.0023137582,0.00000103414],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044166206,0.0012137808,0.6528015,0.0000057269485,0.0002749016,9.996676e-7,0.011668909,0.31097355,0.0014222978,0.0065796706,0.00006965508,0.0145473275],"study_design_scores_gemma":[0.0087244,0.0015482341,0.33136317,0.000034389544,0.00015775468,0.00042617234,0.0046129017,0.48368147,0.001055559,0.16774979,0.00015522834,0.0004909199],"about_ca_topic_score_codex":0.001015864,"about_ca_topic_score_gemma":0.0046566124,"teacher_disagreement_score":0.32143834,"about_ca_system_score_codex":0.0051119803,"about_ca_system_score_gemma":0.0024493793,"threshold_uncertainty_score":0.99998796},"labels":[],"label_agreement":null},{"id":"W4293523360","doi":"10.1109/cibcb55180.2022.9863023","title":"Accurate Nuclei Segmentation in Breast Cancer Tumour Biopsies","year":2022,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Breast cancer; Haematoxylin; Pattern recognition (psychology); Feature extraction; Image segmentation; Deep learning; Process (computing); Computer vision; Cancer; Medicine; Pathology; Internal medicine; Staining","score_opus":0.016157253972484898,"score_gpt":0.2677869805176422,"score_spread":0.2516297265451573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293523360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7387109,0.00020912508,0.22294432,0.027556475,0.0038422353,0.00059769285,0.000048516653,0.00077314803,0.0053176186],"genre_scores_gemma":[0.99597174,0.000019787145,0.002755887,0.00070771045,0.000040721123,0.00015126847,0.0000010741483,0.0000060386083,0.0003457703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992188,0.000057676232,0.00012622413,0.00023283457,0.00021612326,0.00014832687],"domain_scores_gemma":[0.99972343,0.000017075028,0.000054386193,0.00015955101,0.000021235577,0.00002433694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014759695,0.00006418175,0.000060707564,0.000116142204,0.00013562215,0.000065930835,0.00035853637,0.000011441076,0.00057797774],"category_scores_gemma":[0.0000014651874,0.00006539738,0.000018969211,0.0006223048,0.000011426159,0.0005028026,0.00027460235,0.00010780375,0.000019528272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016768272,0.00039743973,0.05838854,0.00006708413,0.000064375665,0.00009578066,0.010893988,0.18745425,0.16611779,0.023968844,0.035942346,0.5164419],"study_design_scores_gemma":[0.0014949184,0.00015786181,0.3226522,0.000020027677,0.000007560988,0.00021380896,0.0020967957,0.631613,0.031366456,0.0032703879,0.0064273668,0.0006796199],"about_ca_topic_score_codex":0.0012237796,"about_ca_topic_score_gemma":0.00021891744,"teacher_disagreement_score":0.51576227,"about_ca_system_score_codex":0.00041294104,"about_ca_system_score_gemma":0.000067916924,"threshold_uncertainty_score":0.6328451},"labels":[],"label_agreement":null},{"id":"W4293578078","doi":"10.1016/j.jpi.2022.100133","title":"A self-supervised contrastive learning approach for whole slide image representation in digital pathology","year":2022,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; McMaster University; University of Waterloo","funders":"Government of Ontario","keywords":"Computer science; Digital pathology; Artificial intelligence; Machine learning; Robustness (evolution); Supervised learning; Pattern recognition (psychology); Natural language processing; Artificial neural network","score_opus":0.013974875699225928,"score_gpt":0.25804156085375457,"score_spread":0.24406668515452865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293578078","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16544595,0.000039449995,0.833008,0.00017944178,0.0003838927,0.0002473547,0.000009510994,0.00003687391,0.0006495125],"genre_scores_gemma":[0.58190346,0.000016214906,0.41764024,0.00024484552,0.00007801501,0.000064962755,0.000013033728,0.000010793682,0.000028430903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832016,0.00015320575,0.0008779872,0.00011262389,0.00027913757,0.00025690894],"domain_scores_gemma":[0.99840176,0.00023851027,0.0008872778,0.00018136551,0.0002400355,0.000051061936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012181588,0.00011524346,0.00030382597,0.00038370263,0.00017764013,0.00009755965,0.00052236364,0.00007211009,0.0000033953586],"category_scores_gemma":[0.0003310529,0.00011450967,0.000111365516,0.0003862153,0.0000502565,0.0017024487,0.00024957472,0.0006553431,0.0000028667982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012222992,0.0016737878,0.024967935,0.0006272295,0.00034574317,0.0027174419,0.3039921,0.3826123,0.010702701,0.005671941,0.0036264223,0.26184013],"study_design_scores_gemma":[0.0033999893,0.0019611176,0.0011866011,0.000012529418,0.000026897676,0.008043659,0.011421559,0.9684747,0.00043742362,0.0029257834,0.0018782039,0.00023156492],"about_ca_topic_score_codex":5.5729043e-7,"about_ca_topic_score_gemma":3.2932766e-7,"teacher_disagreement_score":0.5858624,"about_ca_system_score_codex":0.00025513864,"about_ca_system_score_gemma":0.0001510255,"threshold_uncertainty_score":0.46695685},"labels":[],"label_agreement":null},{"id":"W4294612686","doi":"10.1038/s41379-022-01146-z","title":"Deep learning-based histotype diagnosis of ovarian carcinoma whole-slide pathology images","year":2022,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; BC Cancer Agency; Vancouver General Hospital; University of British Columbia","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Government of Canada","keywords":"Pathology; Hematopathology; Medicine; Cytopathology; Anatomical pathology; Ovarian carcinoma; Ovarian cancer; Biology; Immunohistochemistry; Cancer; Internal medicine","score_opus":0.01287668340762892,"score_gpt":0.22502375351454887,"score_spread":0.21214707010691994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294612686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18309999,0.0009305914,0.8125256,0.0016855561,0.00096689555,0.00018292731,0.000011309822,0.00021300031,0.0003841533],"genre_scores_gemma":[0.98674184,0.000010215668,0.011975542,0.0006296575,0.000051702606,0.00035949028,0.000013556415,0.000030770203,0.00018720445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973119,0.0008328469,0.00036918803,0.0007549558,0.00030032007,0.00043079292],"domain_scores_gemma":[0.99848396,0.0002100931,0.00029301672,0.0008389214,0.00010337148,0.000070654125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058447383,0.00020097329,0.00035915177,0.00031027445,0.00033875782,0.000019626383,0.0009577618,0.00012233113,0.00012590282],"category_scores_gemma":[0.00010077372,0.00023412891,0.00012612317,0.0004030298,0.00017700957,0.00014546518,0.0006133539,0.00054805033,0.000025770118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029585126,0.00077805197,0.18784475,0.00012716767,0.00005331389,0.004468171,0.009412893,0.41355574,0.047720734,0.002986646,0.0017966818,0.33096],"study_design_scores_gemma":[0.00258551,0.0038200587,0.11476866,0.0000115193425,0.00007355456,0.0013513146,0.00015475562,0.8181119,0.023362624,0.015892202,0.018925993,0.00094193115],"about_ca_topic_score_codex":0.00009133633,"about_ca_topic_score_gemma":0.00003686927,"teacher_disagreement_score":0.80364186,"about_ca_system_score_codex":0.0002801544,"about_ca_system_score_gemma":0.00013512805,"threshold_uncertainty_score":0.95475},"labels":[],"label_agreement":null},{"id":"W4294845321","doi":"10.1101/2022.09.06.22279630","title":"Inference of core needle biopsy whole slide images requiring definitive therapy for prostate cancer","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Overdiagnosis; Medicine; Prostate cancer; Guideline; Prostate; Biopsy; Radiology; Cancer; Workflow; Medical physics; Oncology; Internal medicine; Pathology; Computer science","score_opus":0.06928177082321467,"score_gpt":0.33786955425091636,"score_spread":0.2685877834277017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294845321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6212922,0.0031011375,0.3664825,0.0012058925,0.0041480917,0.0019614508,0.00057687855,0.00035736524,0.0008745045],"genre_scores_gemma":[0.97481245,0.0012195857,0.020797363,0.00016074003,0.00016187895,0.0023458644,0.000025950478,0.000049124425,0.00042701687],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99784356,0.000088853296,0.0004478019,0.0008400597,0.0004159271,0.00036377503],"domain_scores_gemma":[0.99777824,0.00028431215,0.00060255924,0.0009422565,0.00032672257,0.00006592256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005542142,0.00030319035,0.0004160953,0.00021881961,0.0001744214,0.00011273188,0.0013972359,0.00012459129,0.000051999064],"category_scores_gemma":[0.00011251901,0.00030164904,0.00017555579,0.00041043363,0.00012382897,0.00025671202,0.0014058457,0.00052876986,0.0000038007263],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073636783,0.00045194462,0.2633965,0.0022838956,0.00077047886,0.000065217755,0.029900964,0.036126487,0.13943031,0.008956846,0.0026699477,0.51521105],"study_design_scores_gemma":[0.004848555,0.0023659926,0.133998,0.002156297,0.0001513944,0.000036893238,0.0012462056,0.061518304,0.5915671,0.15530537,0.04295435,0.0038515287],"about_ca_topic_score_codex":0.00054220646,"about_ca_topic_score_gemma":0.000030796276,"teacher_disagreement_score":0.5113595,"about_ca_system_score_codex":0.00025297666,"about_ca_system_score_gemma":0.000537292,"threshold_uncertainty_score":0.99994355},"labels":[],"label_agreement":null},{"id":"W4294974890","doi":"10.1109/ichi54592.2022.00049","title":"Quality Control of Whole Slide Images using the YOLO Concept","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Computer vision; Artificial intelligence; Digitization; Digital pathology; Intersection (aeronautics); Jaccard index; Focus (optics); Computer graphics (images); Pattern recognition (psychology); Optics; Database","score_opus":0.08719580780154045,"score_gpt":0.36553790024706495,"score_spread":0.2783420924455245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294974890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046450082,0.000144773,0.91258,0.024003724,0.008611281,0.0010397701,0.0011231534,0.0002040911,0.005843091],"genre_scores_gemma":[0.9918503,0.00002593913,0.003606238,0.0040584016,0.00013650784,0.00010114055,0.00002517192,0.000011896034,0.0001843995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635965,0.00043795523,0.0011311098,0.00025033567,0.0014859634,0.0003349831],"domain_scores_gemma":[0.9971891,0.00036377492,0.0010470147,0.0007203974,0.0005784473,0.00010124622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013429441,0.00021257771,0.00031150426,0.00022670296,0.0005333374,0.00016216194,0.0020175523,0.00006151783,0.0002349736],"category_scores_gemma":[0.000121743826,0.00018619587,0.00013112313,0.00041019745,0.00013801166,0.00064077665,0.00039169437,0.00074762746,0.000018387607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043006046,0.00030553868,0.0033393467,0.00032678506,0.00038322623,0.000014418295,0.026571434,0.075228155,0.0048424685,0.77045566,0.00728944,0.1108135],"study_design_scores_gemma":[0.0012871829,0.0006517569,0.0012698025,0.00008660297,0.000012590422,0.00006892834,0.0056553283,0.9678987,0.0034190712,0.010472234,0.008759307,0.00041847094],"about_ca_topic_score_codex":0.0006048077,"about_ca_topic_score_gemma":0.000053571697,"teacher_disagreement_score":0.94540024,"about_ca_system_score_codex":0.00057699735,"about_ca_system_score_gemma":0.0006263581,"threshold_uncertainty_score":0.75928473},"labels":[],"label_agreement":null},{"id":"W4294975187","doi":"10.1109/embc48229.2022.9871809","title":"Vision Transformers for Classification of Breast Ultrasound Images","year":2022,"lang":"en","type":"article","venue":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"AI in cancer detection","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Breast ultrasound; Computer science; Convolutional neural network; Pattern recognition (psychology); Breast cancer; Deep learning; Contextual image classification; Medical imaging; Ultrasound; Artificial neural network; Machine learning; Mammography; Medicine; Image (mathematics); Radiology","score_opus":0.030434717523500132,"score_gpt":0.306323042800441,"score_spread":0.27588832527694085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294975187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10373904,0.0001367048,0.8847216,0.006459763,0.0038571742,0.00042439616,0.00033985384,0.00005975727,0.0002617533],"genre_scores_gemma":[0.9940585,0.00014744163,0.005152442,0.000116806215,0.00013107993,0.00010583442,0.0000587384,0.000010843414,0.00021829903],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986601,0.00007090313,0.00043951906,0.00030831865,0.00032523816,0.0001959186],"domain_scores_gemma":[0.9988483,0.0003276933,0.00024579276,0.0002471912,0.00029520073,0.00003577663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082361535,0.0001450308,0.00024104303,0.00016952415,0.00009107567,0.000008773391,0.0010745563,0.00008094936,0.00008958554],"category_scores_gemma":[0.00012681568,0.000120624965,0.00015472698,0.0005224942,0.00020767823,0.00019367457,0.00011620563,0.0003606874,5.6517837e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001133515,0.00015100354,0.003053388,0.00012361226,0.00020872327,2.0115479e-7,0.0052505913,0.0148171745,0.9414265,0.009288576,0.019110125,0.0064567407],"study_design_scores_gemma":[0.007391404,0.0024676172,0.11161414,0.0006113948,0.00014097577,0.00027539165,0.006784388,0.7649709,0.030293167,0.008876983,0.0651913,0.0013823594],"about_ca_topic_score_codex":0.0001506847,"about_ca_topic_score_gemma":0.000028076412,"teacher_disagreement_score":0.91113335,"about_ca_system_score_codex":0.00018856932,"about_ca_system_score_gemma":0.00010217872,"threshold_uncertainty_score":0.49189433},"labels":[],"label_agreement":null},{"id":"W4296886862","doi":"10.1177/117693510600200030","title":"Applications of Machine Learning in Cancer Prediction and Prognosis","year":2006,"lang":"en","type":"article","venue":"Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1099,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Genome Prairie; Genome Canada","keywords":"Machine learning; Artificial intelligence; Computer science; Artificial neural network; Probabilistic logic","score_opus":0.010822964316296065,"score_gpt":0.25227877826539813,"score_spread":0.24145581394910207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296886862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07662637,0.0025790546,0.91623783,0.0004443813,0.00028963987,0.00070342014,0.000042024076,0.00022209017,0.00285522],"genre_scores_gemma":[0.98780435,0.00079737086,0.010503446,0.000065187836,0.00007731935,0.0006392016,0.0000055583027,0.000006487872,0.00010106503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928737,0.000011134713,0.00034568942,0.00008281726,0.00015107577,0.00012189174],"domain_scores_gemma":[0.99955523,0.000024717612,0.0001939731,0.00013343866,0.00006945142,0.000023172806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012332057,0.00007225642,0.00010280265,0.00013111581,0.0000566414,0.000033279306,0.00016337619,0.000045397526,0.000006826502],"category_scores_gemma":[0.000004764096,0.000071914445,0.000015567279,0.00048594503,0.00003920787,0.0005121018,0.00006904041,0.00012921641,0.0000012191093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071839218,0.000043731117,0.31208068,0.0003883774,0.000012575013,1.7854873e-7,0.002482955,0.0386447,0.00025060985,0.0034775187,0.0004937222,0.6421178],"study_design_scores_gemma":[0.0005552227,0.000073746094,0.040761393,0.0001256636,0.000014925525,0.0000045671877,0.00011811899,0.9054284,0.0058989567,0.0012264766,0.04561457,0.00017794892],"about_ca_topic_score_codex":0.0011179831,"about_ca_topic_score_gemma":0.0004702451,"teacher_disagreement_score":0.911178,"about_ca_system_score_codex":0.00014396962,"about_ca_system_score_gemma":0.00007757059,"threshold_uncertainty_score":0.2932586},"labels":[],"label_agreement":null},{"id":"W4296887690","doi":"10.18280/isi.270408","title":"Effect of Microscopy Magnification Towards Grading of Breast Invasive Carcinoma: An Experimental Analysis on Deep Learning and Traditional Machine Learning Methods","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Sponsored Research and Industrial Consultancy","keywords":"Magnification; Artificial intelligence; Grading (engineering); Transfer of learning; Computer science; Deep learning; Pattern recognition (psychology); Machine learning; Support vector machine; Naive Bayes classifier","score_opus":0.01586505765901695,"score_gpt":0.2868139259147462,"score_spread":0.2709488682557292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296887690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78124404,0.00012908659,0.21794225,0.0000093182025,0.00012571987,0.00019355769,0.000017043592,0.000062585845,0.00027642839],"genre_scores_gemma":[0.9835098,0.00001119412,0.016190678,0.000011950506,0.000017109445,0.0000938292,0.0001535737,0.000008093302,0.000003808194],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99786586,0.00087328104,0.0004997644,0.00020882132,0.0003949498,0.00015731907],"domain_scores_gemma":[0.99875754,0.00026598893,0.0006352313,0.00018500375,0.00010038754,0.000055832163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504929,0.00015775519,0.00029774744,0.0007063478,0.00046463005,0.00009325144,0.00025553207,0.000048413654,0.00003535039],"category_scores_gemma":[0.00010067772,0.00016674204,0.00010122675,0.0009050886,0.00009678841,0.0018001158,0.00013063417,0.00025742946,8.116309e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066890946,0.0001612841,0.038892306,0.0009392853,0.00037830346,0.0000027585088,0.047908515,0.09433883,0.17679709,0.0038922033,0.0000056373538,0.6360149],"study_design_scores_gemma":[0.0006738203,0.003022938,0.03057974,0.000029699946,0.000115175506,0.00009770533,0.0016962339,0.43913263,0.5241866,0.00019727973,0.00003848571,0.00022965319],"about_ca_topic_score_codex":0.00021616858,"about_ca_topic_score_gemma":0.000003464379,"teacher_disagreement_score":0.6357852,"about_ca_system_score_codex":0.00044785347,"about_ca_system_score_gemma":0.00005208013,"threshold_uncertainty_score":0.67995435},"labels":[],"label_agreement":null},{"id":"W4296959973","doi":"10.1007/978-3-031-17027-0_11","title":"Efficient Medical Image Assessment via Self-supervised Learning","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Embedding; Autoencoder; Machine learning; Image (mathematics); Pattern recognition (psychology); Data mining; Deep learning","score_opus":0.008906780855070427,"score_gpt":0.2545659366843183,"score_spread":0.24565915582924788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296959973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011293649,0.00021314272,0.98594594,0.0018818596,0.0038620175,0.0004907618,0.0000019371043,0.00067575666,0.0068156696],"genre_scores_gemma":[0.08923832,0.000090257316,0.90658015,0.0026653802,0.0009747686,0.00007371672,0.000008716539,0.00010198903,0.0002667211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919471,0.0001691981,0.000719985,0.0022741763,0.0039666053,0.0009229106],"domain_scores_gemma":[0.9967926,0.0006764177,0.00038086178,0.0015435371,0.00024536185,0.00036121713],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026681025,0.00064615457,0.0006192144,0.0009725971,0.0008082678,0.0005547148,0.005023886,0.00038070788,0.00068473263],"category_scores_gemma":[0.000114758295,0.00064234115,0.00021175809,0.00110846,0.0005534555,0.00039474384,0.004196377,0.0030381286,0.00006648852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053029116,0.00008148606,0.000035892735,0.00005720254,0.00002426243,0.00033463043,0.0010180568,0.19766067,0.00019244512,0.0056166076,0.000027960232,0.7949455],"study_design_scores_gemma":[0.00035587492,0.00033457807,0.00006732547,0.00013190307,0.000010280718,0.00020866327,2.476479e-7,0.98213965,0.00022392863,0.009638271,0.006202611,0.0006866747],"about_ca_topic_score_codex":0.00006121854,"about_ca_topic_score_gemma":0.000026621503,"teacher_disagreement_score":0.79425883,"about_ca_system_score_codex":0.0020762305,"about_ca_system_score_gemma":0.0019614443,"threshold_uncertainty_score":0.9996028},"labels":[],"label_agreement":null},{"id":"W4298009673","doi":"10.18280/ts.390421","title":"Morphological and Otsu’s Technique Based Mammography Mass Detection and Deep Neural Network Classifier Based Prediction","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Thresholding; Mammography; Computer science; Segmentation; Otsu's method; Artificial neural network; Pattern recognition (psychology); Breast cancer; Perceptron; Feature extraction; Deep learning; Classifier (UML); Feature selection; Image segmentation; Cancer; Image (mathematics); Medicine","score_opus":0.013029600308924876,"score_gpt":0.20313872472610797,"score_spread":0.19010912441718308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298009673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06474328,0.00011183425,0.9332734,0.00047145225,0.00038074542,0.0005876539,0.000010537832,0.0003423833,0.000078717625],"genre_scores_gemma":[0.9774042,0.000004543475,0.021002889,0.00070897816,0.00013296522,0.00072046305,0.0000075225785,0.000013864384,0.000004591009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981054,0.00030861353,0.00027009725,0.0005681067,0.00043094557,0.00031681624],"domain_scores_gemma":[0.999412,0.00009790288,0.00012245402,0.00022203034,0.000036535253,0.00010909116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069142197,0.00018880231,0.00015181664,0.00020022651,0.0005731093,0.00011706614,0.000241049,0.0000806888,0.00014689444],"category_scores_gemma":[0.000004965921,0.00019162589,0.000068532965,0.00059343915,0.000092970135,0.00025623266,0.00012545883,0.0003444193,6.20513e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011411668,0.00048748244,0.06685978,0.00011884916,0.00012373582,0.00021085446,0.000297885,0.2504239,0.23719348,0.0011982076,0.0013187532,0.4406259],"study_design_scores_gemma":[0.0008533306,0.0012116869,0.031475745,0.0000070075466,0.000022162078,0.00007159358,0.000019885956,0.9587207,0.0043012705,0.0008103101,0.002292076,0.0002142227],"about_ca_topic_score_codex":0.00001644415,"about_ca_topic_score_gemma":0.000009497497,"teacher_disagreement_score":0.9126609,"about_ca_system_score_codex":0.00014196016,"about_ca_system_score_gemma":0.000026248894,"threshold_uncertainty_score":0.7814277},"labels":[],"label_agreement":null},{"id":"W4298307599","doi":"10.1007/978-3-031-01664-6_7","title":"Integrated CADe/CADx of Mammographic Lesions","year":2017,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Mammography; Radiology; Cancer; Breast cancer; Internal medicine","score_opus":0.01422364321398969,"score_gpt":0.21872253511362738,"score_spread":0.20449889189963769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298307599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013567507,0.0029659101,0.88993746,0.0022032557,0.0054537267,0.00078307046,0.00018012241,0.001562813,0.09677797],"genre_scores_gemma":[0.87461853,0.0033037385,0.061255362,0.00058822555,0.0029685039,0.0003371091,0.00008340099,0.00079606066,0.056049053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99763894,0.000020378802,0.0004801404,0.0006697564,0.0008093924,0.00038136274],"domain_scores_gemma":[0.99751335,0.00054632983,0.00031760253,0.0012973261,0.00008362751,0.00024176102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028446916,0.0005078453,0.0006459925,0.0010088403,0.00013233745,0.000080785576,0.0017135696,0.00081172044,0.00013430703],"category_scores_gemma":[0.0005610128,0.0004334529,0.00033772935,0.00012288679,0.0002446519,0.000104570674,0.00021809677,0.0009812576,0.00003752529],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045636734,0.000080783044,0.00000202976,0.0005822748,0.0007386519,0.0001506387,0.0001706673,0.0012790419,0.00948195,0.1087339,0.0054054447,0.873329],"study_design_scores_gemma":[0.00036496416,0.0005068472,0.00015993368,0.0054366225,0.00018411012,0.00009201759,0.0000028829852,0.033485975,0.029992186,0.009292243,0.91875196,0.001730267],"about_ca_topic_score_codex":0.000038972026,"about_ca_topic_score_gemma":0.000009729033,"teacher_disagreement_score":0.9133465,"about_ca_system_score_codex":0.00017304457,"about_ca_system_score_gemma":0.00016953521,"threshold_uncertainty_score":0.9998117},"labels":[],"label_agreement":null},{"id":"W4298442302","doi":"10.1007/978-3-031-01654-7_1","title":"Computer-Aided Diagnosis of Breast Cancer","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Medicine; Computer science; Cancer; Internal medicine","score_opus":0.010124070865723443,"score_gpt":0.21159894643741467,"score_spread":0.20147487557169122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298442302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022973122,0.008738302,0.96390957,0.0041977162,0.009810989,0.00088461896,0.0004809536,0.0015686412,0.010179496],"genre_scores_gemma":[0.8720725,0.011304749,0.08603618,0.002006118,0.018500393,0.0015033328,0.00005160453,0.0010977691,0.007427335],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753904,0.000021216778,0.0005000936,0.0006061359,0.00085862115,0.0004748753],"domain_scores_gemma":[0.997846,0.0007694285,0.00025842653,0.0007532444,0.000076267446,0.00029660485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002286164,0.00052208576,0.0006763862,0.0005743851,0.000054843524,0.000044636126,0.0010183573,0.000582986,0.00054610946],"category_scores_gemma":[0.00006112786,0.00046809626,0.00028369945,0.00017193827,0.00011905609,0.00013125305,0.00025266552,0.0005904638,0.000046828674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002017169,0.00007734965,0.000013224587,0.00046064518,0.00043093637,0.00002094295,0.000104729974,0.0027050392,0.0008315518,0.017447028,0.0039971415,0.97389126],"study_design_scores_gemma":[0.00090429786,0.00067313045,0.0033166448,0.010536085,0.00055846485,0.00031010064,0.0000020053017,0.10579239,0.052072916,0.0031372372,0.8184189,0.0042777876],"about_ca_topic_score_codex":0.000043584,"about_ca_topic_score_gemma":0.0000032924697,"teacher_disagreement_score":0.96961343,"about_ca_system_score_codex":0.00035736136,"about_ca_system_score_gemma":0.00010396277,"threshold_uncertainty_score":0.9997771},"labels":[],"label_agreement":null},{"id":"W4299419913","doi":"10.1007/978-3-031-01654-7_7","title":"Concluding Remarks","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics; Mathematical analysis","score_opus":0.012113657254733668,"score_gpt":0.21216868460228805,"score_spread":0.20005502734755437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299419913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005893831,0.0035015221,0.84774315,0.0012795639,0.004434313,0.0003180805,0.000017269042,0.0013282964,0.14137189],"genre_scores_gemma":[0.61367184,0.004883898,0.20832998,0.0053318506,0.030442566,0.00078071497,0.00009602988,0.0021394743,0.13432366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975178,0.000018413833,0.0003959511,0.0006573606,0.0008476154,0.0005628524],"domain_scores_gemma":[0.9978261,0.0008122712,0.00015951971,0.0008214413,0.00003892362,0.0003417414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003819224,0.00052705774,0.00050959305,0.00054308097,0.000100805744,0.00009260725,0.0009894811,0.0007460091,0.0004026522],"category_scores_gemma":[0.00034699996,0.00048307597,0.00023541966,0.00012188778,0.00008623489,0.0001430678,0.00025894472,0.0009182541,0.0002403339],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019059144,0.00003250298,5.257781e-7,0.00030268793,0.00037042008,0.00008651128,0.00015550823,0.000785076,0.00394451,0.16316865,0.009329007,0.82180554],"study_design_scores_gemma":[0.00011816988,0.00009867092,0.000013436267,0.0009741715,0.000057241978,0.00007362403,6.5247616e-7,0.013579428,0.00774954,0.0021902965,0.97424895,0.0008957966],"about_ca_topic_score_codex":0.0000041048315,"about_ca_topic_score_gemma":7.858852e-7,"teacher_disagreement_score":0.96492,"about_ca_system_score_codex":0.0004567167,"about_ca_system_score_gemma":0.00007914102,"threshold_uncertainty_score":0.9997621},"labels":[],"label_agreement":null},{"id":"W4300217162","doi":"10.1007/978-3-031-01654-7_2","title":"Detection and Analysis of Breast Masses","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Sign (mathematics); Abnormality; Medicine; Mammography; Radiology; Cancer; Internal medicine; Mathematics","score_opus":0.007176013851671199,"score_gpt":0.19684547789353848,"score_spread":0.1896694640418673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300217162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027880122,0.0020106717,0.99004304,0.00025270312,0.0009111914,0.00018248141,0.0000688274,0.00039162772,0.00586066],"genre_scores_gemma":[0.9908723,0.0005018875,0.006897269,0.000064240645,0.0005033673,0.0000354827,0.0000090797075,0.000082740386,0.0010336066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845153,0.0000149906955,0.0003212706,0.00043198545,0.00052751746,0.0002527196],"domain_scores_gemma":[0.99866194,0.00048262556,0.00016863403,0.00047166756,0.00004103448,0.0001741065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022598582,0.00031365964,0.0005383222,0.0013486476,0.00004443866,0.00003814427,0.00035034685,0.00041571088,0.000111107154],"category_scores_gemma":[0.000099153534,0.00028177327,0.00021574947,0.00036353187,0.00008384749,0.000100301295,0.00011460134,0.00034019598,0.00000715904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021926538,0.000029785559,0.000008233071,0.00023098904,0.0023014226,0.000008391347,0.00009333898,0.0015192492,0.011500107,0.010271775,0.000052531555,0.97396225],"study_design_scores_gemma":[0.0006377273,0.00079933833,0.012736965,0.0021801237,0.007982913,0.00040421376,0.0000081769085,0.58557266,0.09387359,0.0038291132,0.2877448,0.0042303493],"about_ca_topic_score_codex":0.000013788072,"about_ca_topic_score_gemma":0.000005944256,"teacher_disagreement_score":0.99059355,"about_ca_system_score_codex":0.0001439077,"about_ca_system_score_gemma":0.000026956948,"threshold_uncertainty_score":0.99996346},"labels":[],"label_agreement":null},{"id":"W4300407363","doi":"10.1007/978-3-031-01654-7_3","title":"Datasets of Images of Breast Masses","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Mammography; Standard deviation; Radiology; Scanner; Breast cancer; Pixel; Nuclear medicine; Biopsy; Cancer; Artificial intelligence; Computer science; Mathematics","score_opus":0.008027803054816525,"score_gpt":0.20719908238297627,"score_spread":0.19917127932815976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300407363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000069314985,0.0069767674,0.9588555,0.0009297904,0.0033499543,0.00059977884,0.0030297835,0.0007042595,0.025484871],"genre_scores_gemma":[0.89435464,0.0019162081,0.09661718,0.00022651869,0.0028275554,0.00010633258,0.00026057524,0.00045650057,0.003234506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816394,0.000015240296,0.0004410599,0.00038187817,0.0007117978,0.0002861016],"domain_scores_gemma":[0.9981493,0.0005852595,0.00026037468,0.00080243306,0.000045844943,0.00015680245],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002490092,0.00033891495,0.0005293835,0.00049346796,0.000023381208,0.000017898932,0.00090032053,0.00036016954,0.00018564546],"category_scores_gemma":[0.00016583488,0.00029625857,0.00016628453,0.00011631574,0.00014371925,0.00012434884,0.00021951566,0.00035534572,0.000018454553],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000699581,0.00015201981,0.000005423423,0.0024040653,0.0008720385,0.000046751808,0.00012697585,0.0017164211,0.063113116,0.051817596,0.012719436,0.8669562],"study_design_scores_gemma":[0.00046121576,0.000489539,0.0006060073,0.004994486,0.00034296696,0.00033973294,0.0000034118589,0.00983193,0.43274844,0.0033320242,0.5448157,0.002034552],"about_ca_topic_score_codex":0.000015143602,"about_ca_topic_score_gemma":8.206154e-7,"teacher_disagreement_score":0.8942853,"about_ca_system_score_codex":0.0001237325,"about_ca_system_score_gemma":0.00008618711,"threshold_uncertainty_score":0.999949},"labels":[],"label_agreement":null},{"id":"W4300637832","doi":"10.1007/978-3-031-01656-1","title":"Computer-Aided Detection of Architectural Distortion in Prior Mammograms of Interval Cancer","year":2013,"lang":"en","type":"book","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Interval (graph theory); Distortion (music); Cancer; Computer science; Artificial intelligence; Medicine; Mathematics; Internal medicine; Telecommunications; Combinatorics","score_opus":0.006962751491088176,"score_gpt":0.21127357688756998,"score_spread":0.2043108253964818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300637832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019478923,0.00080940436,0.975125,0.00019752467,0.0030712865,0.000662719,0.000027420761,0.0002886107,0.00033908064],"genre_scores_gemma":[0.9903564,0.00008414108,0.007995048,0.00003650631,0.0005994693,0.00021271528,0.000009071578,0.0000773468,0.0006293234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974503,0.000068175475,0.0007942562,0.0005857731,0.0007334544,0.00036802382],"domain_scores_gemma":[0.99832517,0.00051154266,0.00041974714,0.0005403146,0.00007405272,0.00012919586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026247127,0.00041337076,0.00074420404,0.0009965955,0.000027512539,0.000031212396,0.0007996579,0.000479696,0.000034100114],"category_scores_gemma":[0.00017167372,0.0003728846,0.0002580004,0.0004458324,0.00014269615,0.000112105095,0.00017942418,0.00069546286,0.0000049729088],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004201143,0.00006355479,0.000004766812,0.00073752605,0.00011435585,0.000006495857,0.00021562836,0.009962305,0.015395503,0.00011558705,0.0001443591,0.9731979],"study_design_scores_gemma":[0.0012342049,0.002073878,0.0070147784,0.010707515,0.00015782038,0.000082521066,0.00000666983,0.64225465,0.31528765,0.0015220738,0.017647173,0.0020110542],"about_ca_topic_score_codex":0.00028426386,"about_ca_topic_score_gemma":0.000080261045,"teacher_disagreement_score":0.9711869,"about_ca_system_score_codex":0.0008307536,"about_ca_system_score_gemma":0.0001745803,"threshold_uncertainty_score":0.9998723},"labels":[],"label_agreement":null},{"id":"W4300756618","doi":"10.1007/978-3-031-01647-9_4","title":"Detection of Sites of Architectural Distortion in Mammograms","year":2011,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Distortion (music); Sign (mathematics); Breast cancer; Radiology; Mammography; Medicine; Biopsy; Cancer; Computer science; Internal medicine; Mathematics","score_opus":0.011660165795021075,"score_gpt":0.19379842828216431,"score_spread":0.18213826248714324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300756618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070706955,0.0013035178,0.9798178,0.000107757995,0.0015867163,0.00050150586,0.000027120275,0.00037352802,0.009211336],"genre_scores_gemma":[0.9971241,0.000055877652,0.0023302066,0.00000979512,0.00012153216,0.00002532493,0.0000037216491,0.000036554044,0.00029293387],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818903,0.000021653746,0.00054840377,0.0004235196,0.0005765304,0.00024086461],"domain_scores_gemma":[0.99879956,0.00030875215,0.00027907162,0.0004781627,0.000045267705,0.00008917791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023974541,0.00031197735,0.00048634756,0.0009198921,0.000019171366,0.0000105172385,0.00051340327,0.00045416103,0.000042834607],"category_scores_gemma":[0.00021813481,0.00028562782,0.0001983686,0.00020130366,0.00012038881,0.000064529195,0.000093175055,0.00051725726,0.000005265969],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007821173,0.000058067297,0.00000788688,0.0005069378,0.000114418945,0.0000145863105,0.0003069034,0.0017804386,0.054172788,0.006237492,0.00001195635,0.9367103],"study_design_scores_gemma":[0.00071367354,0.0019928368,0.003411569,0.0043116813,0.00015018838,0.00010975316,0.000004818725,0.037017304,0.9118427,0.018440727,0.02007912,0.0019256356],"about_ca_topic_score_codex":0.00006979208,"about_ca_topic_score_gemma":0.000042375093,"teacher_disagreement_score":0.99005336,"about_ca_system_score_codex":0.00020940186,"about_ca_system_score_gemma":0.000041979263,"threshold_uncertainty_score":0.9999596},"labels":[],"label_agreement":null},{"id":"W4301387036","doi":"10.48550/arxiv.1701.03779","title":"Tumour Ellipsification in Ultrasound Images for Treatment Prediction in\\n Breast Cancer","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Contouring; Computer science; Artificial intelligence; Region of interest; Segmentation; Pattern recognition (psychology); Support vector machine; Ultrasound; Computer vision; Feature (linguistics); Feature extraction; Breast cancer; Cancer; Radiology; Medicine","score_opus":0.07290549991499964,"score_gpt":0.2232271426290522,"score_spread":0.15032164271405254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301387036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4153702,0.00015652842,0.5791911,0.0005923093,0.0019596678,0.0013802656,0.00035191787,0.0002193138,0.0007787242],"genre_scores_gemma":[0.99693966,0.0014128301,0.00059472217,0.000012875035,0.00016309148,0.00004042477,0.000025273488,0.000016741775,0.0007943564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830705,0.00007520159,0.00020871444,0.0010511846,0.00007129028,0.00028658842],"domain_scores_gemma":[0.99840987,0.00009467979,0.00033495255,0.00096486346,0.00012699075,0.00006865699],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021657822,0.00025525488,0.00027288188,0.0003639597,0.00014636376,0.00014557427,0.0009450696,0.00024144622,0.000010098589],"category_scores_gemma":[0.000016083743,0.00030032778,0.00012087112,0.0002586137,0.00006854006,0.0006141801,0.00023064559,0.00021302543,0.000011709309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003397622,0.0005359596,0.22098358,0.0002589765,0.00013985949,0.00009670191,0.0010419637,0.74744874,0.0032423849,0.00916626,0.0008320593,0.015913729],"study_design_scores_gemma":[0.002405646,0.00014904974,0.4287652,0.00038467094,0.00009460752,0.000017939947,0.00009420032,0.52649266,0.0036377471,0.0366088,0.00064499205,0.0007045103],"about_ca_topic_score_codex":0.0026995305,"about_ca_topic_score_gemma":0.001207174,"teacher_disagreement_score":0.5815695,"about_ca_system_score_codex":0.0023336434,"about_ca_system_score_gemma":0.00032879433,"threshold_uncertainty_score":0.99994487},"labels":[],"label_agreement":null},{"id":"W4301489718","doi":"10.1007/978-3-031-01651-6_3","title":"Segmentation and Land marking of Mammograms","year":2013,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Segmentation; Computer vision; Artificial intelligence; Cartography; Geography","score_opus":0.006843207094334703,"score_gpt":0.18955367888736405,"score_spread":0.18271047179302935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301489718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005720333,0.0020438028,0.966084,0.00075460284,0.0016956731,0.0006199292,0.000022359469,0.00053925026,0.027668318],"genre_scores_gemma":[0.7049156,0.0032354218,0.26540396,0.0007845851,0.0028606798,0.00043795607,0.000059309616,0.0005863425,0.021716177],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870336,0.000010727894,0.0002728144,0.00037391356,0.0004467409,0.0001924303],"domain_scores_gemma":[0.9990575,0.00036175112,0.00013510966,0.0003040599,0.000028316525,0.00011331322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014774119,0.0002580374,0.00030401204,0.00033641284,0.00003463016,0.000057397257,0.00030211313,0.00029897364,0.00011524678],"category_scores_gemma":[0.000080268,0.00022742039,0.0000751911,0.000069961745,0.00006735456,0.00008156853,0.00010300085,0.00027952698,0.000015491305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010796428,0.00001489818,0.0000053555605,0.00039378097,0.00017561961,0.0000132388095,0.00010365674,0.0005771331,0.004777991,0.01041779,0.000650605,0.98285913],"study_design_scores_gemma":[0.0014223036,0.0015429714,0.001275763,0.008177319,0.0003827969,0.00027618266,0.000013082978,0.3770557,0.09234742,0.020321775,0.4930895,0.004095199],"about_ca_topic_score_codex":0.000017604512,"about_ca_topic_score_gemma":0.0000016452879,"teacher_disagreement_score":0.97876394,"about_ca_system_score_codex":0.00009389911,"about_ca_system_score_gemma":0.000025372616,"threshold_uncertainty_score":0.92739344},"labels":[],"label_agreement":null},{"id":"W4302161581","doi":"10.1007/978-3-031-01654-7_5","title":"Pattern Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":429,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Classification scheme; Machine learning","score_opus":0.017690986081031892,"score_gpt":0.21232853123531117,"score_spread":0.19463754515427928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302161581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000069572297,0.001005432,0.9576766,0.0015283999,0.0023493466,0.00022376483,0.000016074935,0.0008492254,0.03634418],"genre_scores_gemma":[0.93358713,0.001432428,0.022040823,0.002048768,0.009799925,0.0004681342,0.00007641749,0.0006950599,0.029851321],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978439,0.000016428576,0.00034713946,0.0005876518,0.00078773755,0.00041712966],"domain_scores_gemma":[0.9982739,0.00044487088,0.00015530373,0.00083071727,0.000036430876,0.0002587519],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025650882,0.0004299622,0.0003541912,0.00046813887,0.00006950142,0.00008159594,0.0008597429,0.0006280147,0.0003060829],"category_scores_gemma":[0.00014911823,0.00039256105,0.00017662926,0.00009836588,0.00006114056,0.00012696467,0.0001328762,0.00067994924,0.00042471447],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003567223,0.00002020822,7.056194e-7,0.00009362021,0.00009091713,0.000010865131,0.00004930704,0.000119905235,0.0014696006,0.027725147,0.0021056065,0.96831053],"study_design_scores_gemma":[0.0001206413,0.00011395841,0.0002084729,0.0006393842,0.000061296996,0.000043688324,8.3020126e-7,0.043675993,0.005003893,0.0019838647,0.9471651,0.0009829284],"about_ca_topic_score_codex":0.00000434065,"about_ca_topic_score_gemma":9.86066e-7,"teacher_disagreement_score":0.9673276,"about_ca_system_score_codex":0.00036240584,"about_ca_system_score_gemma":0.000057698344,"threshold_uncertainty_score":0.99985266},"labels":[],"label_agreement":null},{"id":"W4302362316","doi":"10.32920/21287928","title":"Assessing the Impact of Color Normalization in Convolutional Neural Network-Based Nuclei Segmentation Frameworks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto Metropolitan University","funders":"Mitacs","keywords":"Convolutional neural network; Segmentation; Normalization (sociology); Preprocessor; Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Data pre-processing; Image segmentation","score_opus":0.028948166286554302,"score_gpt":0.3453888592991942,"score_spread":0.31644069301263994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362316","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20780674,0.0000781386,0.7895436,0.00040848236,0.0012590203,0.00048216316,0.0000062024787,0.000092271206,0.00032338765],"genre_scores_gemma":[0.97296226,0.00000763478,0.026375853,0.00027974666,0.00014150809,0.00013450615,0.00007062049,0.000014436641,0.00001340581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979504,0.00042762776,0.00046709203,0.00041700192,0.00049025274,0.0002476642],"domain_scores_gemma":[0.99845654,0.0003123879,0.0005370969,0.00052700244,0.00013401797,0.0000329584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075986015,0.00019364222,0.0002174397,0.00015598931,0.00018922304,0.00029780477,0.00080504885,0.0002703601,0.0002969424],"category_scores_gemma":[0.00003703881,0.00015643006,0.00016157038,0.0007241274,0.00006599026,0.0005283794,0.0007453694,0.0011260597,0.0000013111711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011258929,0.000036125402,0.025543885,0.000018754006,0.000019032856,0.000001151451,0.000164654,0.9692486,0.000082212486,0.0009794707,0.00047061138,0.0034242314],"study_design_scores_gemma":[0.00019926016,0.0000616171,0.1354414,0.00004032972,0.0000071726026,0.000001981341,0.000038614045,0.86173767,0.00011113949,0.002217163,0.000010643798,0.00013301293],"about_ca_topic_score_codex":0.001056849,"about_ca_topic_score_gemma":0.000068167894,"teacher_disagreement_score":0.76515555,"about_ca_system_score_codex":0.0011089958,"about_ca_system_score_gemma":0.00065490167,"threshold_uncertainty_score":0.6379033},"labels":[],"label_agreement":null},{"id":"W4302362361","doi":"10.32920/21287940","title":"piNET–An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Guelph; Toronto Metropolitan University","funders":"","keywords":"False positive paradox; Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); True positive rate; Proliferation index; Calculator; Medicine; Pathology","score_opus":0.020596076553230928,"score_gpt":0.33892212992473747,"score_spread":0.31832605337150655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044332664,0.00012354624,0.9822074,0.003405814,0.004522843,0.0016156957,0.00023010149,0.0032942228,0.00016706793],"genre_scores_gemma":[0.70762724,0.000058742567,0.28216866,0.0014953029,0.0016638675,0.0060891057,0.00012993635,0.000105329855,0.00066183484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713165,0.00013981665,0.00045475495,0.0012577227,0.0005947093,0.00042133278],"domain_scores_gemma":[0.99772716,0.0000809326,0.00035818145,0.001353415,0.00032758585,0.00015274106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037929427,0.00038736765,0.0003662438,0.00022345528,0.00034257444,0.0005945284,0.001443133,0.00043837976,0.0004484474],"category_scores_gemma":[0.00003676784,0.00038845296,0.00016034485,0.00040926324,0.00004187899,0.0005836924,0.0013833626,0.0008531318,0.000007884152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004453533,0.00078525476,0.018668402,0.0016992174,0.0008045209,0.000024073906,0.0034736388,0.615446,0.0012415347,0.08921851,0.05603202,0.21216153],"study_design_scores_gemma":[0.00026146008,0.000092607785,0.0184588,0.000080112695,0.000025451953,0.000019055267,0.000022522574,0.9592029,0.0011194781,0.018571053,0.0015906881,0.00055591157],"about_ca_topic_score_codex":0.0008012643,"about_ca_topic_score_gemma":0.00015008735,"teacher_disagreement_score":0.70319396,"about_ca_system_score_codex":0.0009102104,"about_ca_system_score_gemma":0.00082763797,"threshold_uncertainty_score":0.9998567},"labels":[],"label_agreement":null},{"id":"W4302362414","doi":"10.32920/21287940.v1","title":"piNET–An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Guelph; Toronto Metropolitan University","funders":"","keywords":"False positive paradox; Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Proliferation index; True positive rate; Breast cancer; Cancer; Medicine; Pathology","score_opus":0.020596076553230928,"score_gpt":0.33892212992473747,"score_spread":0.31832605337150655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044332664,0.00012354624,0.9822074,0.003405814,0.004522843,0.0016156957,0.00023010149,0.0032942228,0.00016706793],"genre_scores_gemma":[0.70762724,0.000058742567,0.28216866,0.0014953029,0.0016638675,0.0060891057,0.00012993635,0.000105329855,0.00066183484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713165,0.00013981665,0.00045475495,0.0012577227,0.0005947093,0.00042133278],"domain_scores_gemma":[0.99772716,0.0000809326,0.00035818145,0.001353415,0.00032758585,0.00015274106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037929427,0.00038736765,0.0003662438,0.00022345528,0.00034257444,0.0005945284,0.001443133,0.00043837976,0.0004484474],"category_scores_gemma":[0.00003676784,0.00038845296,0.00016034485,0.00040926324,0.00004187899,0.0005836924,0.0013833626,0.0008531318,0.000007884152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004453533,0.00078525476,0.018668402,0.0016992174,0.0008045209,0.000024073906,0.0034736388,0.615446,0.0012415347,0.08921851,0.05603202,0.21216153],"study_design_scores_gemma":[0.00026146008,0.000092607785,0.0184588,0.000080112695,0.000025451953,0.000019055267,0.000022522574,0.9592029,0.0011194781,0.018571053,0.0015906881,0.00055591157],"about_ca_topic_score_codex":0.0008012643,"about_ca_topic_score_gemma":0.00015008735,"teacher_disagreement_score":0.70319396,"about_ca_system_score_codex":0.0009102104,"about_ca_system_score_gemma":0.00082763797,"threshold_uncertainty_score":0.9998567},"labels":[],"label_agreement":null},{"id":"W4302362817","doi":"10.32920/21287937.v1","title":"IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Digital pathology; Artificial intelligence; Histogram; Ground truth; Computer science; Histogram equalization; Proliferation index; Pattern recognition (psychology); Workload; Computer vision; Pathology; Image (mathematics); Medicine; Immunohistochemistry","score_opus":0.031872007941474226,"score_gpt":0.2869350455357409,"score_spread":0.2550630375942667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004970177,0.00008091477,0.98508304,0.0015420121,0.0037049411,0.0024997185,0.000018282666,0.0006665042,0.0014343999],"genre_scores_gemma":[0.8604239,0.000016526099,0.1287747,0.0008717798,0.00059931877,0.0056334375,0.00035754178,0.000056090557,0.003266668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977752,0.00011066771,0.00042197428,0.0009063577,0.0005159234,0.00026985406],"domain_scores_gemma":[0.99843854,0.00008244024,0.00026095487,0.000908262,0.00023508062,0.000074752854],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004791123,0.00025658886,0.00026146547,0.00021623126,0.00031275366,0.000301229,0.0009157276,0.0002762501,0.00013299442],"category_scores_gemma":[0.000045625435,0.00027488905,0.00018172362,0.00031177886,0.000026398111,0.00032400634,0.0010070676,0.0004400867,0.000008973997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042877946,0.00053257693,0.0074787755,0.0012017258,0.00037138467,0.000009013031,0.0044402974,0.4812413,0.0013711445,0.08079063,0.03590245,0.38623193],"study_design_scores_gemma":[0.00047149727,0.00017504371,0.0016361669,0.000015127045,0.000021789985,0.0000032876108,0.000014590253,0.94374907,0.00062267965,0.008214504,0.044717122,0.0003591206],"about_ca_topic_score_codex":0.00025732713,"about_ca_topic_score_gemma":0.00015679013,"teacher_disagreement_score":0.85630834,"about_ca_system_score_codex":0.0011945415,"about_ca_system_score_gemma":0.00043639776,"threshold_uncertainty_score":0.9999703},"labels":[],"label_agreement":null},{"id":"W4302362904","doi":"10.32920/21287928.v1","title":"Assessing the Impact of Color Normalization in Convolutional Neural Network-Based Nuclei Segmentation Frameworks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto Metropolitan University","funders":"Mitacs","keywords":"Convolutional neural network; Segmentation; Normalization (sociology); Preprocessor; Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Data pre-processing; Image segmentation","score_opus":0.028948166286554302,"score_gpt":0.3453888592991942,"score_spread":0.31644069301263994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20780674,0.0000781386,0.7895436,0.00040848236,0.0012590203,0.00048216316,0.0000062024787,0.000092271206,0.00032338765],"genre_scores_gemma":[0.97296226,0.00000763478,0.026375853,0.00027974666,0.00014150809,0.00013450615,0.00007062049,0.000014436641,0.00001340581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979504,0.00042762776,0.00046709203,0.00041700192,0.00049025274,0.0002476642],"domain_scores_gemma":[0.99845654,0.0003123879,0.0005370969,0.00052700244,0.00013401797,0.0000329584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075986015,0.00019364222,0.0002174397,0.00015598931,0.00018922304,0.00029780477,0.00080504885,0.0002703601,0.0002969424],"category_scores_gemma":[0.00003703881,0.00015643006,0.00016157038,0.0007241274,0.00006599026,0.0005283794,0.0007453694,0.0011260597,0.0000013111711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011258929,0.000036125402,0.025543885,0.000018754006,0.000019032856,0.000001151451,0.000164654,0.9692486,0.000082212486,0.0009794707,0.00047061138,0.0034242314],"study_design_scores_gemma":[0.00019926016,0.0000616171,0.1354414,0.00004032972,0.0000071726026,0.000001981341,0.000038614045,0.86173767,0.00011113949,0.002217163,0.000010643798,0.00013301293],"about_ca_topic_score_codex":0.001056849,"about_ca_topic_score_gemma":0.000068167894,"teacher_disagreement_score":0.76515555,"about_ca_system_score_codex":0.0011089958,"about_ca_system_score_gemma":0.00065490167,"threshold_uncertainty_score":0.6379033},"labels":[],"label_agreement":null},{"id":"W4302362914","doi":"10.32920/21287937","title":"IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Digital pathology; Artificial intelligence; Histogram; Ground truth; Computer science; Histogram equalization; Workload; Proliferation index; Pattern recognition (psychology); Contrast (vision); Computer vision; Pathology; Image (mathematics); Medicine; Immunohistochemistry","score_opus":0.031872007941474226,"score_gpt":0.2869350455357409,"score_spread":0.2550630375942667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004970177,0.00008091477,0.98508304,0.0015420121,0.0037049411,0.0024997185,0.000018282666,0.0006665042,0.0014343999],"genre_scores_gemma":[0.8604239,0.000016526099,0.1287747,0.0008717798,0.00059931877,0.0056334375,0.00035754178,0.000056090557,0.003266668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977752,0.00011066771,0.00042197428,0.0009063577,0.0005159234,0.00026985406],"domain_scores_gemma":[0.99843854,0.00008244024,0.00026095487,0.000908262,0.00023508062,0.000074752854],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004791123,0.00025658886,0.00026146547,0.00021623126,0.00031275366,0.000301229,0.0009157276,0.0002762501,0.00013299442],"category_scores_gemma":[0.000045625435,0.00027488905,0.00018172362,0.00031177886,0.000026398111,0.00032400634,0.0010070676,0.0004400867,0.000008973997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042877946,0.00053257693,0.0074787755,0.0012017258,0.00037138467,0.000009013031,0.0044402974,0.4812413,0.0013711445,0.08079063,0.03590245,0.38623193],"study_design_scores_gemma":[0.00047149727,0.00017504371,0.0016361669,0.000015127045,0.000021789985,0.0000032876108,0.000014590253,0.94374907,0.00062267965,0.008214504,0.044717122,0.0003591206],"about_ca_topic_score_codex":0.00025732713,"about_ca_topic_score_gemma":0.00015679013,"teacher_disagreement_score":0.85630834,"about_ca_system_score_codex":0.0011945415,"about_ca_system_score_gemma":0.00043639776,"threshold_uncertainty_score":0.9999703},"labels":[],"label_agreement":null},{"id":"W4302412485","doi":"10.1007/978-3-031-01654-7","title":"Fractal Analysis of Breast Masses in Mammograms","year":2012,"lang":"en","type":"book","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Fractal; Fractal analysis; Fractal dimension; Mathematics; Mathematical analysis","score_opus":0.006105087330226674,"score_gpt":0.20920491674753203,"score_spread":0.20309982941730537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302412485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011023368,0.0026804237,0.96897846,0.0008211671,0.0031351855,0.00059267227,0.00022816983,0.000886802,0.021574764],"genre_scores_gemma":[0.9782942,0.00019628176,0.016324244,0.00015739842,0.0011612247,0.00016088043,0.00008555819,0.00016658462,0.0034536188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974927,0.000044568787,0.0005351063,0.0005508322,0.00088462135,0.00049217744],"domain_scores_gemma":[0.997917,0.00090314075,0.00021510212,0.0007212995,0.00003775284,0.00020570104],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039899544,0.00040727053,0.0008516828,0.002451152,0.000025348849,0.000046707068,0.00096488796,0.00060884183,0.00020050953],"category_scores_gemma":[0.00020539932,0.00037055204,0.00038464277,0.0016313518,0.00008612055,0.00013475594,0.00016539186,0.00066094537,0.000016072627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076821816,0.00052642566,0.00023334639,0.0010073108,0.0056191557,0.00013462176,0.00056899514,0.034369726,0.003798904,0.005714189,0.0042752447,0.9436753],"study_design_scores_gemma":[0.0008871594,0.0005752995,0.031113695,0.004304806,0.0037640145,0.00018976704,0.000016617634,0.58669674,0.012927203,0.001360436,0.3533987,0.0047655064],"about_ca_topic_score_codex":0.00004218761,"about_ca_topic_score_gemma":0.000017323766,"teacher_disagreement_score":0.97719187,"about_ca_system_score_codex":0.0005223351,"about_ca_system_score_gemma":0.00016153004,"threshold_uncertainty_score":0.99987465},"labels":[],"label_agreement":null},{"id":"W4302421535","doi":"10.1007/978-3-031-01656-1_8","title":"Detection of Architectural Distortion in Prior Mammograms","year":2013,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Distortion (music); Artificial intelligence; Entropy (arrow of time); Breast cancer; Cancer detection; Pattern recognition (psychology); Mathematics; Computer science; Computer vision; Medicine; Cancer; Physics; Bandwidth (computing); Internal medicine","score_opus":0.0066084423627181,"score_gpt":0.1893625451340683,"score_spread":0.1827541027713502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302421535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044108476,0.00093538594,0.9812097,0.00049082807,0.0028965867,0.00089699996,0.00001606565,0.00072514935,0.00841846],"genre_scores_gemma":[0.99333054,0.00006107368,0.0044845864,0.00003918212,0.00033783691,0.00010976525,0.0000049864398,0.000077599296,0.0015544586],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978629,0.000023900908,0.0005338509,0.000568991,0.0006706463,0.0003397559],"domain_scores_gemma":[0.9986778,0.00037193444,0.00021826061,0.00055411947,0.000038760798,0.00013914212],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000209408,0.00039479672,0.00047498572,0.00089240563,0.000037509137,0.00004219846,0.000589888,0.00051001157,0.000082233186],"category_scores_gemma":[0.00023615178,0.00035681456,0.00019693558,0.00020385625,0.000093555485,0.00010152388,0.00010925845,0.00070482446,0.00003986524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020125475,0.000023170816,7.5599905e-7,0.00018013339,0.00005131557,0.000011592103,0.000075824595,0.0019075898,0.010157606,0.0019802386,0.000028071741,0.9855636],"study_design_scores_gemma":[0.001959238,0.0030894796,0.0054529235,0.009171058,0.00024653063,0.0004007208,0.00001070747,0.33778766,0.39590603,0.021936936,0.21832009,0.0057186447],"about_ca_topic_score_codex":0.000062349696,"about_ca_topic_score_gemma":0.000027909678,"teacher_disagreement_score":0.9889197,"about_ca_system_score_codex":0.00046410284,"about_ca_system_score_gemma":0.000050873976,"threshold_uncertainty_score":0.99988836},"labels":[],"label_agreement":null},{"id":"W4302757635","doi":"10.21203/rs.3.rs-2093909/v1","title":"Semi-supervised learning to automate tumor bud detection in cytokeratin-stained whole-slide images of colorectal cancer","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Swiss Cancer Research Foundation; KWF Kankerbestrijding; European Commission","keywords":"Tumor budding; Artificial intelligence; Colorectal cancer; Computer science; Convolutional neural network; Machine learning; Cytokeratin; Deep learning; Pathology; Cancer; Medicine; Immunohistochemistry; Metastasis; Internal medicine","score_opus":0.032719080200603205,"score_gpt":0.3659890491056398,"score_spread":0.3332699689050366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302757635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9644126,0.0005121577,0.028801594,0.0014004356,0.0010884332,0.0024446077,0.000113338654,0.000554084,0.0006726895],"genre_scores_gemma":[0.9933138,0.00010684839,0.00312243,0.000036295583,0.00018004417,0.0027233898,0.000021959726,0.00006565588,0.00042961363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99314076,0.0018079665,0.0006873151,0.0013412309,0.002044378,0.000978368],"domain_scores_gemma":[0.9973028,0.0005022281,0.00025673886,0.0009017165,0.0008067342,0.00022983304],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0033372084,0.0003636849,0.00057171955,0.0015937316,0.0004915497,0.00038367207,0.0017706254,0.00020783565,0.00020945599],"category_scores_gemma":[0.00060191454,0.00041083177,0.0001757314,0.0025900712,0.000114001385,0.00037629585,0.005004008,0.003267196,0.000030005684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063990185,0.00025281572,0.011135894,0.0027609805,0.00011293703,0.00032241223,0.012260668,0.52151597,0.34360918,0.00012605642,0.0011139328,0.10614928],"study_design_scores_gemma":[0.0010864112,0.00162606,0.041587196,0.0012340248,0.00001123984,0.00002004865,0.0023521564,0.5922032,0.3541293,0.0006408238,0.004246276,0.0008632441],"about_ca_topic_score_codex":0.005409492,"about_ca_topic_score_gemma":0.0016258978,"teacher_disagreement_score":0.10528603,"about_ca_system_score_codex":0.0031049768,"about_ca_system_score_gemma":0.0014048894,"threshold_uncertainty_score":0.99983436},"labels":[],"label_agreement":null},{"id":"W4302893119","doi":"10.1007/978-3-031-01651-6_4","title":"Feature Extraction and Indexing of Mammograms","year":2013,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on biomedical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Search engine indexing; Feature extraction; Computer science; Feature (linguistics); Artificial intelligence; Database index; Pattern recognition (psychology); Information retrieval; Linguistics","score_opus":0.006978836515250166,"score_gpt":0.2014697145824254,"score_spread":0.19449087806717524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302893119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018824753,0.0029770911,0.9568793,0.002566221,0.0025929543,0.0006014994,0.000019803396,0.00079298555,0.03338187],"genre_scores_gemma":[0.58786607,0.0037957204,0.31044897,0.0010414193,0.0056795185,0.0004879397,0.000051116014,0.0009190683,0.08971016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984383,0.000011858295,0.00024045282,0.0004962977,0.00056097406,0.00025208973],"domain_scores_gemma":[0.9987373,0.00044022698,0.00017791108,0.00044073546,0.0000438918,0.00015994401],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016440963,0.00034956544,0.00039514888,0.00046621004,0.00004864603,0.000071407354,0.00040401614,0.0006744263,0.000083032],"category_scores_gemma":[0.0001582212,0.00030898352,0.00011682357,0.00010510515,0.00008877787,0.00013261852,0.0001168232,0.0007128556,0.000018242858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001483482,0.000021900183,0.000001010315,0.00043158495,0.0002090259,0.000025967185,0.00009274832,0.0006885954,0.008563537,0.031935114,0.0030337367,0.9549819],"study_design_scores_gemma":[0.00033284278,0.00048730557,0.00026052046,0.0031338562,0.00012231973,0.00022637697,0.000004679122,0.089134306,0.031573333,0.0064778817,0.8667299,0.0015166574],"about_ca_topic_score_codex":0.0000105100235,"about_ca_topic_score_gemma":0.0000013316617,"teacher_disagreement_score":0.9534653,"about_ca_system_score_codex":0.00013253908,"about_ca_system_score_gemma":0.000039703413,"threshold_uncertainty_score":0.9999362},"labels":[],"label_agreement":null},{"id":"W4306642500","doi":"10.1097/pai.0000000000001079","title":"Using Deep Learning to Predict Final HER2 Status in Invasive Breast Cancers That are Equivocal (2+) by Immunohistochemistry","year":2022,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dr. Georges-L.-Dumont University Hospital Centre; Queen Elizabeth II Health Sciences Centre; Dalhousie University","funders":"","keywords":"Immunohistochemistry; Receiver operating characteristic; Medicine; Convolutional neural network; Artificial intelligence; Computer science; Pathology; Internal medicine","score_opus":0.012921959815790368,"score_gpt":0.25405644327391347,"score_spread":0.2411344834581231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306642500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8977024,0.0024064472,0.09685115,0.00020288599,0.000542105,0.00056818646,0.000062241495,0.0002455692,0.001419043],"genre_scores_gemma":[0.9927702,0.000028052762,0.005108374,0.00076541054,0.000048250316,0.0009021334,0.00012218488,0.00008759408,0.0001678272],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995619,0.00017641694,0.00063432317,0.0015286485,0.000768485,0.0012731389],"domain_scores_gemma":[0.99770296,0.000091374335,0.00053743285,0.0013116946,0.00009528783,0.00026127335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039343955,0.00057060097,0.0005984551,0.00020363704,0.0006044166,0.00008982547,0.0018604365,0.00027076437,0.00025471847],"category_scores_gemma":[0.00006119214,0.0007968111,0.0001684216,0.001027869,0.00026290753,0.00015344543,0.0017850987,0.0016243581,0.000016903185],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023206323,0.00008535639,0.00030569496,0.000045691926,0.00006268094,0.00030687024,0.00054975884,0.029510649,0.96582323,0.000037018443,0.00059360004,0.0024474077],"study_design_scores_gemma":[0.0031890234,0.00033080718,0.0007096596,0.00008582294,0.00006833529,0.0030343602,0.002958973,0.0062031467,0.9796961,0.00031885624,0.0015817373,0.0018231851],"about_ca_topic_score_codex":0.0012510445,"about_ca_topic_score_gemma":0.0000022385916,"teacher_disagreement_score":0.0950678,"about_ca_system_score_codex":0.007094695,"about_ca_system_score_gemma":0.0007737945,"threshold_uncertainty_score":0.9994483},"labels":[],"label_agreement":null},{"id":"W4307233259","doi":"10.1007/s00330-022-09165-9","title":"Algorithmic transparency and interpretability measures improve radiologists’ performance in BI-RADS 4 classification","year":2022,"lang":"en","type":"article","venue":"European Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Deutschen Konsortium für Translationale Krebsforschung; Technische Universität München; Deutsche Forschungsgemeinschaft","keywords":"Interpretability; Certainty; Neuroticism; Artificial intelligence; Pearson product-moment correlation coefficient; Medicine; Correlation; Machine learning; Neuroradiology; Personality; Transparency (behavior); Big Five personality traits; Radiology; Computer science; Psychology; Mathematics; Statistics; Social psychology; Neurology; Psychiatry","score_opus":0.024408638103329935,"score_gpt":0.23119211170579437,"score_spread":0.20678347360246443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307233259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7470968,0.0012863702,0.24481106,0.0008291682,0.0017056523,0.00039636865,0.000008158964,0.00025949656,0.0036069779],"genre_scores_gemma":[0.99746984,0.0001786709,0.0019897784,0.00015896997,0.00008453603,0.000065688255,0.0000035274004,0.000013603074,0.00003540155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971796,0.0013812196,0.00035952174,0.0006626357,0.00013667271,0.00028033915],"domain_scores_gemma":[0.99917597,0.00007520805,0.00012163419,0.00055126357,0.000024047054,0.00005187375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016154592,0.00014605938,0.00020261657,0.00016393539,0.00018547007,0.000026379206,0.00078988704,0.000035417543,0.000014012247],"category_scores_gemma":[0.000050725244,0.00014820368,0.000037703754,0.00032457974,0.0001805189,0.00023018499,0.0002411419,0.00044945488,0.000009566165],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015034521,0.00011692722,0.102615476,0.000057955094,0.000032801418,0.00005549119,0.0060244645,0.0020860888,0.023504853,0.002874461,0.00023889609,0.8622422],"study_design_scores_gemma":[0.0008446583,0.0011404038,0.7989748,0.000009680665,0.000007097634,0.00040723072,0.0001315888,0.18715477,0.00047906573,0.0005814457,0.009907002,0.0003622387],"about_ca_topic_score_codex":0.00001868346,"about_ca_topic_score_gemma":0.000008024335,"teacher_disagreement_score":0.86188,"about_ca_system_score_codex":0.00028107135,"about_ca_system_score_gemma":0.00005187226,"threshold_uncertainty_score":0.60435706},"labels":[],"label_agreement":null},{"id":"W4307396299","doi":"10.1016/j.fertnstert.2022.08.837","title":"HUMAN BLASTOCYST EUPLOID PREDICTION BASED ON 3D MORPHOLOGICAL EVALUATION","year":2022,"lang":"en","type":"article","venue":"Fertility and Sterility","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CReATe Fertility Centre; University of Toronto","funders":"","keywords":"Blastocyst; Ploidy; Andrology; Computer science; Biology; Embryo; Cell biology; Medicine; Embryogenesis; Genetics","score_opus":0.04550975125344064,"score_gpt":0.2808706017715013,"score_spread":0.23536085051806066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307396299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9283325,0.000024302075,0.0692997,0.00032580088,0.00050594,0.00043925116,0.000038534577,0.00020856212,0.00082537736],"genre_scores_gemma":[0.99874794,3.0667906e-7,0.0006097797,0.00033745036,0.00002831457,0.00022789597,0.000016420108,0.000003972886,0.000027911994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976405,0.0006914926,0.00024337346,0.000609626,0.00063777965,0.00017722856],"domain_scores_gemma":[0.99910253,0.00006184145,0.00007636979,0.00062080525,0.00007069437,0.000067753994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018859382,0.00011820797,0.00013254612,0.00004831298,0.00068831426,0.00006729905,0.00028338804,0.00005400654,0.0003500046],"category_scores_gemma":[0.000070949645,0.00011775407,0.000046888606,0.00022396978,0.00007800052,0.0002246699,0.00026538337,0.00026372855,0.000005082979],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022338804,0.0040753093,0.0439623,0.00030858326,0.000082602164,0.000045020475,0.0030637044,0.098830886,0.022245113,0.00028217235,0.0020395862,0.8027259],"study_design_scores_gemma":[0.00028781654,0.0005285061,0.52983683,0.0000022202319,0.0000048652983,0.000002880503,0.000011194996,0.46783647,0.00016246077,0.0008184827,0.0004476245,0.000060611485],"about_ca_topic_score_codex":0.000063359905,"about_ca_topic_score_gemma":0.000016260807,"teacher_disagreement_score":0.8026653,"about_ca_system_score_codex":0.00039415972,"about_ca_system_score_gemma":0.000060142564,"threshold_uncertainty_score":0.5294026},"labels":[],"label_agreement":null},{"id":"W4307703018","doi":"10.3390/su142113998","title":"Optimized Stacking Ensemble Learning Model for Breast Cancer Detection and Classification Using Machine Learning","year":2022,"lang":"en","type":"article","venue":"Sustainability","topic":"AI in cancer detection","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Machine learning; Artificial intelligence; Breast cancer; Categorization; Computer science; Boosting (machine learning); Ensemble learning; Classifier (UML); Overfitting; Gradient boosting; Health care; Random forest; Medicine; Cancer; Internal medicine; Artificial neural network","score_opus":0.02880260261634244,"score_gpt":0.2964242684119681,"score_spread":0.2676216657956257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307703018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19760194,0.00010849672,0.8008216,0.0005697616,0.0001596283,0.00051222125,0.000006914834,0.00020861224,0.0000108260165],"genre_scores_gemma":[0.9819046,0.00001275774,0.017438587,0.000028832654,0.00004580466,0.00035381038,0.0000025608854,0.00002133841,0.00019169299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982135,0.000326104,0.00024719545,0.000608124,0.00026203852,0.0003430229],"domain_scores_gemma":[0.99884266,0.00012659303,0.00021789315,0.0002791762,0.00047069933,0.0000630098],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012474831,0.00014647859,0.00017239364,0.00013741964,0.0015465671,0.00012984926,0.00022386108,0.00005141521,0.00001038844],"category_scores_gemma":[0.00022004436,0.00017053631,0.00006483384,0.00043136734,0.000049057464,0.0005542798,0.00036184373,0.000469734,1.13378285e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014835224,0.000022068207,0.0033577534,0.00008502101,0.000009620597,5.151439e-7,0.0011337305,0.8619848,0.004521859,0.00039492606,0.0000013044876,0.12834007],"study_design_scores_gemma":[0.00054146454,0.000087334076,0.0022500132,0.0000038830653,0.00001581493,0.000022086384,0.00062827405,0.9899152,0.00050974055,0.0055837343,0.000261505,0.00018094326],"about_ca_topic_score_codex":0.00055819174,"about_ca_topic_score_gemma":0.000056887075,"teacher_disagreement_score":0.78430265,"about_ca_system_score_codex":0.0032757183,"about_ca_system_score_gemma":0.0004114972,"threshold_uncertainty_score":0.9997533},"labels":[],"label_agreement":null},{"id":"W4307830882","doi":"10.32920/21428604.v1","title":"piNET: An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Digital pathology; Artificial intelligence; Histogram; Pipeline (software); Robustness (evolution); Ground truth; Proliferation index; Pattern recognition (psychology); Data mining; Computer vision; Pathology; Medicine; Image (mathematics)","score_opus":0.020813745057121438,"score_gpt":0.3394433286053347,"score_spread":0.3186295835482133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307830882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005517248,0.00012458459,0.98218834,0.003143574,0.0040160622,0.0015524082,0.000248987,0.0030664892,0.00014227345],"genre_scores_gemma":[0.7281613,0.00005410105,0.26258022,0.0014399822,0.0015689097,0.00543621,0.0001298321,0.0001005642,0.00052890036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972843,0.00013307252,0.00042498866,0.0012105214,0.00054911803,0.00039798018],"domain_scores_gemma":[0.99784404,0.000070072245,0.00033808805,0.0012968783,0.00030619308,0.0001447173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003577538,0.00036746883,0.00034731015,0.00021517463,0.00032536074,0.0005654321,0.0013508053,0.00041639197,0.00042340657],"category_scores_gemma":[0.00003073267,0.00036868447,0.000145244,0.00039558636,0.00003980269,0.00058785465,0.0012283645,0.0007857222,0.0000065923737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046184848,0.0008254103,0.023399996,0.0016634818,0.0007824132,0.000024899078,0.003928304,0.6029389,0.001414085,0.07605133,0.049486697,0.23902266],"study_design_scores_gemma":[0.0002495974,0.00009569588,0.023121266,0.000073311116,0.000022414673,0.000018341902,0.000022249318,0.9567229,0.0010745861,0.016658287,0.0014124205,0.0005289236],"about_ca_topic_score_codex":0.00079717214,"about_ca_topic_score_gemma":0.00016585123,"teacher_disagreement_score":0.72264403,"about_ca_system_score_codex":0.00083458656,"about_ca_system_score_gemma":0.00076316035,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4307830910","doi":"10.32920/21428604","title":"piNET: An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Digital pathology; Artificial intelligence; Pipeline (software); Histogram; Proliferation index; Ground truth; Robustness (evolution); Pattern recognition (psychology); Data mining; Computer vision; Pathology; Medicine","score_opus":0.020813745057121438,"score_gpt":0.3394433286053347,"score_spread":0.3186295835482133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307830910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005517248,0.00012458459,0.98218834,0.003143574,0.0040160622,0.0015524082,0.000248987,0.0030664892,0.00014227345],"genre_scores_gemma":[0.7281613,0.00005410105,0.26258022,0.0014399822,0.0015689097,0.00543621,0.0001298321,0.0001005642,0.00052890036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972843,0.00013307252,0.00042498866,0.0012105214,0.00054911803,0.00039798018],"domain_scores_gemma":[0.99784404,0.000070072245,0.00033808805,0.0012968783,0.00030619308,0.0001447173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003577538,0.00036746883,0.00034731015,0.00021517463,0.00032536074,0.0005654321,0.0013508053,0.00041639197,0.00042340657],"category_scores_gemma":[0.00003073267,0.00036868447,0.000145244,0.00039558636,0.00003980269,0.00058785465,0.0012283645,0.0007857222,0.0000065923737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046184848,0.0008254103,0.023399996,0.0016634818,0.0007824132,0.000024899078,0.003928304,0.6029389,0.001414085,0.07605133,0.049486697,0.23902266],"study_design_scores_gemma":[0.0002495974,0.00009569588,0.023121266,0.000073311116,0.000022414673,0.000018341902,0.000022249318,0.9567229,0.0010745861,0.016658287,0.0014124205,0.0005289236],"about_ca_topic_score_codex":0.00079717214,"about_ca_topic_score_gemma":0.00016585123,"teacher_disagreement_score":0.72264403,"about_ca_system_score_codex":0.00083458656,"about_ca_system_score_gemma":0.00076316035,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4307918986","doi":"10.1002/cpe.7348","title":"Breast lesion identification and categorization using mammography screening based on combined convolutional recursive neural network framework with parameters optimized using multi‐objective seagull optimization algorithm","year":2022,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Mammography; Convolutional neural network; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Algorithm; Identification (biology); Machine learning; Breast cancer; Cancer; Medicine","score_opus":0.033870215734192376,"score_gpt":0.30506608446506084,"score_spread":0.2711958687308685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307918986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057633024,0.00030013247,0.94079274,0.00024320478,0.00047797096,0.0004582752,0.000011439138,0.00007921656,0.0000040123437],"genre_scores_gemma":[0.55404353,0.000030215915,0.44563198,0.00017807329,0.000025387164,0.00005138357,0.000029187444,0.00000946676,7.5673654e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977802,0.00051702344,0.00032885454,0.0007003983,0.00043559476,0.00023791133],"domain_scores_gemma":[0.9982602,0.0005880434,0.0005612193,0.00017099018,0.00031628113,0.000103247025],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004188662,0.00022051219,0.00019317158,0.00020287604,0.0014651577,0.0003559387,0.00014398951,0.000069112284,0.000003732336],"category_scores_gemma":[0.00007763497,0.00023782827,0.000027722248,0.00095550355,0.00019865221,0.0018734294,0.00013121223,0.0003153025,1.2122536e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031237476,0.00006307165,0.00077474216,0.000010008163,0.000018402436,0.0000045486754,0.0023393715,0.9687722,0.000035647656,0.0005896642,0.000002446419,0.027077531],"study_design_scores_gemma":[0.0012462233,0.00037109,0.0014469066,0.00006917188,0.000049210335,0.00021015145,0.002306103,0.99359435,0.000044063185,0.00037194067,0.000006171007,0.00028464393],"about_ca_topic_score_codex":0.00009995328,"about_ca_topic_score_gemma":4.7882355e-7,"teacher_disagreement_score":0.49641052,"about_ca_system_score_codex":0.00010910147,"about_ca_system_score_gemma":0.00010000172,"threshold_uncertainty_score":0.9998348},"labels":[],"label_agreement":null},{"id":"W4308448228","doi":"10.1016/j.media.2022.102670","title":"Segmentation with mixed supervision: Confidence maximization helps knowledge distillation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Distillation; Maximization; Artificial intelligence; Segmentation; Machine learning; Mathematics; Mathematical optimization; Chemistry; Chromatography","score_opus":0.008958241496845029,"score_gpt":0.2593132697323961,"score_spread":0.25035502823555106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308448228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015336315,0.0001302202,0.9818976,0.0016019472,0.00022517933,0.00012372725,0.000004012265,0.00014902747,0.00053199806],"genre_scores_gemma":[0.98094124,0.000031948286,0.018256178,0.00022777653,0.00007754772,0.00009001894,0.00009237469,0.000009882645,0.00027304568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975041,0.00031707386,0.00029300692,0.00048083364,0.0012159462,0.00018904172],"domain_scores_gemma":[0.9989586,0.0001284777,0.0001360615,0.00045524279,0.00017863959,0.00014299763],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070347014,0.00012273614,0.00020706777,0.00034792078,0.00040063867,0.00012827652,0.0005595926,0.00003989204,0.001656116],"category_scores_gemma":[0.00010590068,0.000109643384,0.000097535274,0.0035974253,0.00007560121,0.0005776998,0.00029839962,0.00020043127,0.000034069268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018797704,0.00083810376,0.027621737,0.00011943213,0.0020471876,0.00033780455,0.0077723972,0.054022368,0.004372633,0.006447685,0.008667822,0.88756484],"study_design_scores_gemma":[0.00044314674,0.00015504012,0.0073619173,0.000008478581,0.00027422016,0.000026531621,0.00029773611,0.987621,0.0016938602,0.0003683492,0.0015480301,0.00020169896],"about_ca_topic_score_codex":0.00012993824,"about_ca_topic_score_gemma":0.00021123301,"teacher_disagreement_score":0.9656049,"about_ca_system_score_codex":0.0002410326,"about_ca_system_score_gemma":0.00014445369,"threshold_uncertainty_score":0.9992565},"labels":[],"label_agreement":null},{"id":"W4308569225","doi":"10.1038/s41523-022-00488-w","title":"Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer","year":2022,"lang":"en","type":"article","venue":"npj Breast Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Innovative Medicines Initiative; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission; Puma Biotechnology; AstraZeneca; Myriad Genetics; European Federation of Pharmaceutical Industries and Associations; Daiichi Sankyo Europe; Horizon 2020 Framework Programme; Knut och Alice Wallenbergs Stiftelse; Bristol-Myers Squibb","keywords":"Pleomorphism (cytology); Grading (engineering); Breast cancer; Limiting; Artificial intelligence; Pathology; Radiology; Medicine; Computer science; Cancer; Biology; Internal medicine","score_opus":0.011400631360581837,"score_gpt":0.2521539765656102,"score_spread":0.2407533452050284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308569225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7197241,0.0060831127,0.16722219,0.0605809,0.025225688,0.0051918095,0.0010504315,0.011671448,0.0032503128],"genre_scores_gemma":[0.9955524,0.000106526895,0.001568302,0.00080910523,0.0004559624,0.0012747358,0.0000058260844,0.00007509015,0.0001520437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747944,0.00013767587,0.00036181742,0.00079682015,0.0005379091,0.0006863139],"domain_scores_gemma":[0.99898434,0.000066457906,0.0002413469,0.00043334486,0.00014587419,0.00012861802],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039349968,0.00026445067,0.00030473826,0.00027751166,0.00064029894,0.00014475631,0.00091863086,0.0000807274,0.0012988144],"category_scores_gemma":[0.000008550864,0.0003062592,0.000111329,0.0010110902,0.000054106848,0.00062314566,0.0005458546,0.0005777587,0.000018319293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000499545,0.00016041486,0.034224834,0.0001361543,0.00011367424,0.000045252753,0.0025974778,0.40574035,0.0047973194,0.0013920218,0.0037017332,0.5465912],"study_design_scores_gemma":[0.0014460909,0.00007563707,0.13436475,0.000091073685,0.00001886122,0.000379961,0.00018444168,0.8485293,0.00012737888,0.0001787062,0.014113575,0.00049025257],"about_ca_topic_score_codex":0.004707742,"about_ca_topic_score_gemma":0.00060472783,"teacher_disagreement_score":0.546101,"about_ca_system_score_codex":0.002060749,"about_ca_system_score_gemma":0.00027994084,"threshold_uncertainty_score":0.99993896},"labels":[],"label_agreement":null},{"id":"W4309361044","doi":"10.1093/nar/gkac988","title":"ViLoN—a multi-layer network approach to data integration demonstrated for patient stratification","year":2022,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Marshallplan-Jubiläumsstiftung","keywords":"Biology; Stratification (seeds); Computational biology; Layer (electronics); Nanotechnology","score_opus":0.22377380687520274,"score_gpt":0.3910254467603152,"score_spread":0.16725163988511246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309361044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008684484,0.0000532099,0.98559284,0.0010938226,0.00046869135,0.0017894979,0.00006964336,0.00017327374,0.0020745343],"genre_scores_gemma":[0.74387956,0.0000041957087,0.2545313,0.00013311884,0.00013332641,0.00095477904,0.00018231753,0.000021756732,0.0001596795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99646795,0.00055751,0.00033705778,0.0009709037,0.0010880535,0.000578505],"domain_scores_gemma":[0.99742556,0.00018227345,0.00008355098,0.001751693,0.00040907724,0.00014786204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028484233,0.00013502248,0.00013748772,0.00024389036,0.001162244,0.00032738823,0.0024974132,0.000069783455,0.000041583495],"category_scores_gemma":[0.00020051429,0.0001382626,0.000035808203,0.0020218145,0.000060339902,0.00063405046,0.0016763462,0.0006003664,0.000030776042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023215474,0.00055830233,0.00020619178,0.000036629077,0.000047109283,0.0000026295427,0.0028673038,0.021958614,0.019383768,0.02675763,0.13181773,0.7961319],"study_design_scores_gemma":[0.00028602744,0.00055645825,0.000845245,0.0000072840035,0.00000320129,0.000007785227,0.0006274019,0.9774321,0.001591443,0.0014458694,0.017030038,0.00016718502],"about_ca_topic_score_codex":0.000110027104,"about_ca_topic_score_gemma":0.000046808134,"teacher_disagreement_score":0.9554734,"about_ca_system_score_codex":0.0005105477,"about_ca_system_score_gemma":0.00029248575,"threshold_uncertainty_score":0.8939159},"labels":[],"label_agreement":null},{"id":"W4309668563","doi":"10.1038/s41598-022-24317-z","title":"Bias reduction in representation of histopathology images using deep feature selection","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University; Laurentian University; Brock University; Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Generalization; Pattern recognition (psychology); Feature selection; Feature (linguistics); Selection bias; Set (abstract data type); Machine learning; Data mining; Statistics; Mathematics","score_opus":0.03312228736148102,"score_gpt":0.2889676040453901,"score_spread":0.2558453166839091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309668563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85281897,0.00017826006,0.12871602,0.00023769466,0.017353464,0.00028212427,5.25215e-7,0.00010338298,0.00030958414],"genre_scores_gemma":[0.97982705,0.0000016094676,0.019170262,0.00000707805,0.00004895355,0.00003375191,0.0000069831285,0.000007227435,0.00089705933],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99794537,0.00024316329,0.0003796772,0.0007407053,0.0005106107,0.00018050146],"domain_scores_gemma":[0.9986843,0.000017100945,0.00053239113,0.0005955545,0.00014352883,0.000027135728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015678675,0.00007903215,0.00013612064,0.00058062474,0.0003737676,0.00008283474,0.00019681442,0.000040633822,0.000030196254],"category_scores_gemma":[0.000096777985,0.000091811096,0.000055226403,0.0025992512,0.00009988255,0.00055721443,0.00019607955,0.0001971046,7.809216e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018241859,0.000098080964,0.015029136,0.00001944529,0.000004446717,0.00018359498,0.0025092533,0.06677569,0.8899231,0.00019965132,0.0040548425,0.021184549],"study_design_scores_gemma":[0.00038324992,0.00024225924,0.02455026,0.000030792835,0.000026102496,0.0142099485,0.00083617656,0.16183266,0.7458876,0.042650126,0.008863097,0.00048773777],"about_ca_topic_score_codex":0.00018312484,"about_ca_topic_score_gemma":0.000032743745,"teacher_disagreement_score":0.14403549,"about_ca_system_score_codex":0.0005689425,"about_ca_system_score_gemma":0.00016842871,"threshold_uncertainty_score":0.3743948},"labels":[],"label_agreement":null},{"id":"W4309763239","doi":"10.1016/j.media.2022.102690","title":"Symmetry-based regularization in deep breast cancer screening","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Canadian Mennonite University; Nvidia","keywords":"Regularization (linguistics); Computer science; Artificial intelligence; Machine learning; Breast cancer; Generalization; Artificial neural network; Theoretical computer science; Mathematics; Medicine; Cancer","score_opus":0.006943077669812815,"score_gpt":0.2585088927304301,"score_spread":0.25156581506061726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309763239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025523535,0.00011454287,0.98894453,0.007890587,0.00013119893,0.000059906586,0.0000066719413,0.000096383985,0.00020383773],"genre_scores_gemma":[0.9705975,0.00001298667,0.02675932,0.0021786105,0.00009972266,0.00013668221,0.000028155637,0.0000122205165,0.00017476626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754155,0.00027054123,0.000282898,0.00044297762,0.00121459,0.00024742502],"domain_scores_gemma":[0.99917364,0.000080651174,0.00010927075,0.00043676794,0.00007000206,0.00012968056],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089704484,0.000100794714,0.00022001339,0.0007445584,0.00019746872,0.00007591946,0.00075433584,0.000048733204,0.0020704502],"category_scores_gemma":[0.00008858701,0.00010466231,0.00014447005,0.0066941413,0.00005243006,0.000284707,0.0003081738,0.0003295595,0.000005416482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042871856,0.00025859018,0.06514946,0.000025874037,0.00057544763,0.00031003612,0.00046166262,0.11204834,0.00043767708,0.0010072497,0.0009136977,0.8187691],"study_design_scores_gemma":[0.00031033735,0.000015362586,0.016920509,0.0000070855376,0.00010869631,0.000007013395,0.000034917288,0.9815536,0.00023305761,0.0002736894,0.0004141483,0.000121583114],"about_ca_topic_score_codex":0.00095610425,"about_ca_topic_score_gemma":0.0005205259,"teacher_disagreement_score":0.9680452,"about_ca_system_score_codex":0.00030414193,"about_ca_system_score_gemma":0.00014999836,"threshold_uncertainty_score":0.9988418},"labels":[],"label_agreement":null},{"id":"W4309915768","doi":"10.1016/j.media.2022.102699","title":"Mitosis domain generalization in histopathology images — The MIDOG challenge","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Amazon Web Services; Siemens Healthineers; Nvidia","keywords":"Artificial intelligence; Computer science; Grading (engineering); Limiting; Generalization; Pattern recognition (psychology); Set (abstract data type); Domain (mathematical analysis); Machine learning; Mathematics; Biology","score_opus":0.007711893702026811,"score_gpt":0.2507850560881752,"score_spread":0.24307316238614837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309915768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018573213,0.0009481893,0.9437399,0.035113946,0.00037084497,0.000104196886,0.0000035619403,0.00009253272,0.0010536093],"genre_scores_gemma":[0.98440343,0.00027963615,0.011514169,0.0029573068,0.00018495932,0.00027054732,0.000017576733,0.000013420955,0.00035898198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973788,0.0007587958,0.00031432265,0.0004478654,0.0008464811,0.00025373217],"domain_scores_gemma":[0.99901366,0.00012335757,0.00011137479,0.0006314246,0.000042487212,0.00007772178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014348128,0.000107905966,0.00023259669,0.00042414875,0.0002842215,0.00005011583,0.0011616687,0.000052306605,0.0009837124],"category_scores_gemma":[0.00013147184,0.00008670972,0.00016741369,0.002839566,0.0001311105,0.00019587477,0.0005876417,0.00034809692,0.000015959105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010482003,0.0022048727,0.045214698,0.000098496756,0.001591746,0.0044005895,0.030503992,0.022015592,0.018851278,0.02045388,0.0808661,0.7736939],"study_design_scores_gemma":[0.0015578754,0.00036185302,0.049040437,0.000011974692,0.00065705925,0.00015765523,0.00109554,0.84223366,0.0017964508,0.015528003,0.08666648,0.00089299167],"about_ca_topic_score_codex":0.00039815734,"about_ca_topic_score_gemma":0.0004807097,"teacher_disagreement_score":0.9658302,"about_ca_system_score_codex":0.0002766319,"about_ca_system_score_gemma":0.00007293571,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W4309927410","doi":"10.1101/2022.11.21.517353","title":"HAPPY: A deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Common Fund; NIH Office of the Director; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Human Genome Research Institute; Wellcome Trust; NIHR Oxford Biomedical Research Centre; European Regional Development Fund; National Institutes of Health; National Cancer Institute; Eesti Teadusagentuur; National Institute on Drug Abuse; Engineering and Physical Sciences Research Council; Bill and Melinda Gates Foundation; Li Ka Shing Foundation; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research","keywords":"Histology; Placenta; Segmentation; Biology; Artificial intelligence; Pipeline (software); Computer science; Pathology; Pattern recognition (psychology); Anatomy; Medicine; Pregnancy; Fetus; Genetics","score_opus":0.014185406962969837,"score_gpt":0.24778842528202094,"score_spread":0.23360301831905111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309927410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051084913,0.0021648463,0.93600345,0.0013091482,0.0057749096,0.0019127892,0.00022955115,0.0014996224,0.00002077879],"genre_scores_gemma":[0.8560155,0.000146495,0.14023338,0.00062491023,0.00056891993,0.0020344995,0.0000014577697,0.00023391514,0.00014091868],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943363,0.0003475376,0.0008957131,0.0024483583,0.0006375023,0.0013345884],"domain_scores_gemma":[0.9957178,0.0003019541,0.0008676658,0.002155224,0.00055342866,0.00040389062],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015625529,0.0008092844,0.0008885609,0.0006155584,0.0010271096,0.000606993,0.0027318737,0.0005171123,0.000050754643],"category_scores_gemma":[0.0004104793,0.0010383187,0.00028036087,0.0013706718,0.00012760954,0.00040534162,0.00362705,0.0017074625,0.00008200608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119892655,0.0002495704,0.0026108448,0.0012285926,0.00016690216,0.00016126585,0.0005757801,0.015793668,0.9717102,0.0008220275,0.0061122323,0.00044903732],"study_design_scores_gemma":[0.0015110552,0.00040647748,0.00609676,0.0003634099,0.00010227819,3.3351543e-7,0.00008830959,0.04294612,0.34592542,0.000039293718,0.59981287,0.0027077],"about_ca_topic_score_codex":0.00018359131,"about_ca_topic_score_gemma":0.000017004957,"teacher_disagreement_score":0.80493057,"about_ca_system_score_codex":0.0013092625,"about_ca_system_score_gemma":0.0005152849,"threshold_uncertainty_score":0.9992067},"labels":[],"label_agreement":null},{"id":"W4310170610","doi":"10.18280/isi.270517","title":"Predicting Cancer Survival Using Multilayer Perceptron and High-Dimensional SVM Kernel Space","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Machine learning; Artificial intelligence; Computer science; Breast cancer; Multilayer perceptron; Perceptron; Workflow; Data mining; Medicine; Cancer; Artificial neural network; Internal medicine; Database","score_opus":0.024295106685446568,"score_gpt":0.2551163620625447,"score_spread":0.2308212553770981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310170610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8212546,0.00015233348,0.17600052,0.00012023583,0.0016739822,0.0002420133,0.00002484216,0.0002303693,0.00030106984],"genre_scores_gemma":[0.9875385,0.000011203623,0.011979946,0.00019967981,0.000118646356,0.00008712173,0.000012116113,0.000012375604,0.000040370156],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839896,0.00011730363,0.00038462106,0.0002306759,0.0005625915,0.00030586193],"domain_scores_gemma":[0.99914706,0.00006204691,0.00030488562,0.00025710493,0.00015105867,0.00007782694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005318439,0.0001696209,0.00017056103,0.00021277861,0.0009506677,0.00024830244,0.00028807207,0.000057141835,0.00008427397],"category_scores_gemma":[0.000049758477,0.00018494145,0.00004076202,0.0004335067,0.00007318422,0.003473434,0.0005404498,0.00024803134,0.000009206265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018983505,0.00006804391,0.05202976,0.00043098096,0.0001480909,0.000010539289,0.04234769,0.5718796,0.00995664,0.0070923083,0.00092369947,0.3149228],"study_design_scores_gemma":[0.00052411814,0.00010036339,0.02706925,0.000050200866,0.000014111727,0.000090768604,0.0009618412,0.96803564,0.00089607865,0.00070376677,0.001282386,0.0002714478],"about_ca_topic_score_codex":0.002178789,"about_ca_topic_score_gemma":0.000049387912,"teacher_disagreement_score":0.39615607,"about_ca_system_score_codex":0.0010616498,"about_ca_system_score_gemma":0.00016832442,"threshold_uncertainty_score":0.7541694},"labels":[],"label_agreement":null},{"id":"W4310209114","doi":"10.3389/fneph.2022.1007002","title":"Machine learning in renal pathology","year":2022,"lang":"en","type":"article","venue":"Frontiers in Nephrology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto General Hospital; University of Toronto; University Health Network; Toronto Metropolitan University","funders":"Canadian Institutes of Health Research; Government of Canada; University of Toronto; Alport Syndrome Foundation; Nephcure Foundation","keywords":"Artificial intelligence; Renal pathology; Interpretability; Linear discriminant analysis; Glomerular basement membrane; Pathology; Digital pathology; Computer science; Deep learning; Classifier (UML); Nephropathy; Medicine; Machine learning; Pattern recognition (psychology); Kidney; Glomerulonephritis; Diabetes mellitus; Internal medicine","score_opus":0.006872204105003736,"score_gpt":0.21017026492976845,"score_spread":0.2032980608247647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310209114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13566707,0.0022135887,0.8493698,0.005156837,0.0052033053,0.00026682104,0.0000029373125,0.00023589695,0.0018837134],"genre_scores_gemma":[0.93698126,0.000080245954,0.059411656,0.0028546173,0.000078276906,0.00018952283,0.000006262316,0.000015725478,0.0003824061],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983037,0.0005799735,0.00022046667,0.00041070356,0.00013261187,0.00035255536],"domain_scores_gemma":[0.9995732,0.00004312362,0.0000795602,0.00026839093,0.000008560985,0.000027189137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005985222,0.000094052906,0.00019721017,0.000491929,0.000115239396,0.000010308009,0.0006304233,0.0000730083,0.00006026662],"category_scores_gemma":[0.000028514361,0.00011374654,0.000029531435,0.00068267697,0.00006250366,0.00013160557,0.00052846887,0.0007967817,0.0000056159297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045008562,0.00022864252,0.4319488,0.000013994935,0.000034607914,0.0021028628,0.005530009,0.17258547,0.002832746,0.00969057,0.03329759,0.34128463],"study_design_scores_gemma":[0.0016332713,0.00078239175,0.02894813,0.0000026412422,0.0000030715225,0.00040235682,0.00013806605,0.55725884,0.00011668738,0.027162166,0.38327047,0.00028192546],"about_ca_topic_score_codex":0.0001003828,"about_ca_topic_score_gemma":0.00012745358,"teacher_disagreement_score":0.80131423,"about_ca_system_score_codex":0.00033568655,"about_ca_system_score_gemma":0.00006719784,"threshold_uncertainty_score":0.46384493},"labels":[],"label_agreement":null},{"id":"W4310608228","doi":"","title":"Unsupervised Malignant Mammographic Breast Mass Segmentation Algorithm Based On Pickard Markov Random Field","year":2016,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Markov random field; Artificial intelligence; Segmentation; Random field; Markov process; Pattern recognition (psychology); Algorithm; Image segmentation; Mathematics; Statistics","score_opus":0.006610380100650399,"score_gpt":0.2016156965948969,"score_spread":0.1950053164942465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310608228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004286538,0.00007548755,0.9683392,0.017963719,0.00031891893,0.00037270857,0.000025486383,0.00035474895,0.00826317],"genre_scores_gemma":[0.703433,0.00017016003,0.29330516,0.00071277574,0.000042324446,0.00014166556,0.00003113854,0.000037543705,0.00212623],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99517334,0.0027182642,0.00039860368,0.0007332331,0.00059115887,0.00038538344],"domain_scores_gemma":[0.9950387,0.0019670315,0.00024625272,0.0017471093,0.0008238912,0.00017702933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002966751,0.00025439952,0.00022560316,0.00029502402,0.00032675496,0.00029045163,0.0012023536,0.00013330224,0.00018629774],"category_scores_gemma":[0.00027255545,0.00020812375,0.00017307566,0.0007633748,0.00011035636,0.00047282872,0.00019033597,0.00017668492,0.000069054855],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007176818,0.00025182555,0.0022250707,0.000027772983,0.000036128702,0.000008678763,0.0006794344,0.000028153103,0.026028285,0.012029474,0.0010721636,0.9575412],"study_design_scores_gemma":[0.008181085,0.000011328143,0.0077657895,0.0018863676,0.00004642152,0.000054271033,0.00008126202,0.31493247,0.6504224,0.008137499,0.007446999,0.001034137],"about_ca_topic_score_codex":0.00022730957,"about_ca_topic_score_gemma":0.00012937776,"teacher_disagreement_score":0.9565071,"about_ca_system_score_codex":0.00016028748,"about_ca_system_score_gemma":0.00013418462,"threshold_uncertainty_score":0.848704},"labels":[],"label_agreement":null},{"id":"W4311162621","doi":"10.18280/ts.390539","title":"MRI and CT Image Based Breast Tumor Detection Framework with Boundary Detection Technique","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Segmentation; Transfer of learning; Deep learning; Computer vision; Image segmentation; Image processing; Image (mathematics)","score_opus":0.004894150588017146,"score_gpt":0.20307245246267955,"score_spread":0.1981783018746624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311162621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0457586,0.000034778845,0.95236224,0.00039070804,0.00026215782,0.00063471,0.000013926287,0.00043308365,0.00010977046],"genre_scores_gemma":[0.95456123,0.0000015588462,0.04409243,0.0003783558,0.00012286776,0.00080539053,0.000002442496,0.00002570114,0.000010022006],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981053,0.00018989957,0.00024085416,0.0005771362,0.00058374205,0.00030309107],"domain_scores_gemma":[0.99926364,0.00007665227,0.00016470831,0.00033512776,0.00006507318,0.00009478354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005777082,0.00021269546,0.0001554453,0.00023717702,0.00084071275,0.00023656196,0.0003480957,0.000028707023,0.00021030496],"category_scores_gemma":[0.000005272191,0.0002135586,0.000053768126,0.0006941684,0.000096234915,0.0005373548,0.00016397098,0.00047796115,0.000004833224],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012786427,0.000578576,0.0013122187,0.00020126255,0.00013632844,0.00034431284,0.0008537998,0.007280808,0.45841193,0.0008883076,0.0003166532,0.52839714],"study_design_scores_gemma":[0.002759605,0.005082455,0.0138866,0.00012922568,0.000086951324,0.0051435647,0.00028768665,0.35264876,0.5980812,0.0064759683,0.014099722,0.0013182578],"about_ca_topic_score_codex":0.00008849057,"about_ca_topic_score_gemma":0.00004713615,"teacher_disagreement_score":0.9088026,"about_ca_system_score_codex":0.00045042983,"about_ca_system_score_gemma":0.00011829255,"threshold_uncertainty_score":0.8708667},"labels":[],"label_agreement":null},{"id":"W4312074741","doi":"10.1101/2022.12.06.519385","title":"General stain deconvolution of histopathology images with physics-guided deep learning","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"Sunnybrook Research Institute","keywords":"Deconvolution; Stain; Artificial intelligence; Computer science; Deep learning; Interpretability; Machine learning; Pattern recognition (psychology); Algorithm; Pathology","score_opus":0.012418860235511725,"score_gpt":0.22326180149195043,"score_spread":0.2108429412564387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312074741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37752292,0.0008299455,0.6191889,0.00010533119,0.0013164026,0.00043375065,0.00002287754,0.00055576663,0.000024136358],"genre_scores_gemma":[0.9121521,0.00011856006,0.08695289,0.00007549818,0.00032067133,0.0002760281,3.1462164e-7,0.00008653908,0.000017416163],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966976,0.00045201168,0.00053677865,0.0012391014,0.00055036554,0.0005241216],"domain_scores_gemma":[0.9968188,0.00006416948,0.0009310128,0.001520753,0.00053481886,0.00013045996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079075195,0.00045881522,0.00057761715,0.00029721524,0.00028264208,0.0001244581,0.001253726,0.0002551538,0.000038370155],"category_scores_gemma":[0.00008980713,0.0005181018,0.0001370505,0.0007624989,0.00018532295,0.00036611277,0.0013505301,0.0011394747,0.000009607817],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085749794,0.00026086642,0.028610473,0.0007293297,0.00020435527,0.00021784518,0.00016312255,0.07707551,0.88196725,0.0101275295,0.00038141364,0.00017657374],"study_design_scores_gemma":[0.0019522529,0.0010594053,0.22222571,0.00033236283,0.00025142485,6.1564435e-7,0.000018112245,0.11494104,0.6469742,0.00012358678,0.009284922,0.00283637],"about_ca_topic_score_codex":0.00014692538,"about_ca_topic_score_gemma":0.0000033144133,"teacher_disagreement_score":0.53462917,"about_ca_system_score_codex":0.0011525714,"about_ca_system_score_gemma":0.00075435766,"threshold_uncertainty_score":0.9997271},"labels":[],"label_agreement":null},{"id":"W4312074763","doi":"10.1101/2022.12.06.519318","title":"Whole slide image representation in bone marrow cytology","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Hospital; McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Bone marrow; Classifier (UML); Cytology; Computer science; Digital pathology; Representation (politics); Pathology; Medicine","score_opus":0.01596219263868156,"score_gpt":0.24753606194891356,"score_spread":0.231573869310232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312074763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7334406,0.0019277163,0.24672052,0.004051557,0.009610244,0.001990347,0.000149491,0.0019534226,0.00015613037],"genre_scores_gemma":[0.9491406,0.00013619568,0.049202334,0.00032847884,0.00032152515,0.0007580998,4.5786106e-7,0.000092580936,0.000019694417],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958077,0.0004740459,0.0007229609,0.0017447614,0.0006074208,0.0006431092],"domain_scores_gemma":[0.9963396,0.0001165295,0.00058443815,0.0025452941,0.00024887294,0.00016523841],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010131763,0.00046306703,0.0005846068,0.0007169239,0.00019640118,0.000349281,0.0016407478,0.00039860304,0.000100913945],"category_scores_gemma":[0.00023657142,0.0006002398,0.00015221923,0.0014710957,0.00010457524,0.00064141315,0.0024407269,0.001395137,0.00010735628],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048559905,0.00020122244,0.010646665,0.00027040107,0.00007614483,0.0006921734,0.00008035227,0.0016529849,0.98141,0.0025975355,0.0022802686,0.000043650845],"study_design_scores_gemma":[0.002390434,0.00029618185,0.38255996,0.00039954847,0.00009549324,4.976442e-7,0.00002446652,0.038779784,0.52902085,0.0002783437,0.042995,0.0031594865],"about_ca_topic_score_codex":0.00029523193,"about_ca_topic_score_gemma":0.000022743212,"teacher_disagreement_score":0.4523892,"about_ca_system_score_codex":0.0011924423,"about_ca_system_score_gemma":0.0006662253,"threshold_uncertainty_score":0.9996449},"labels":[],"label_agreement":null},{"id":"W4312113263","doi":"10.1245/s10434-022-12967-2","title":"ASO Author Reflections: Development of Natural Language Processing-Based Machine-Learning Algorithms to Identify Pathologic Complete Response from Surgical Pathology Reports","year":2022,"lang":"en","type":"letter","venue":"Annals of Surgical Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Surgical oncology; Medicine; Surgical pathology; Pathology; Algorithm; Radiology; Artificial intelligence; Natural language processing; Computer science; Surgery","score_opus":0.09974196263666248,"score_gpt":0.41232079815739037,"score_spread":0.3125788355207279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312113263","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077933,0.009285049,0.03770141,0.8632913,0.0075517325,0.0018314634,0.00031407396,0.0010116996,0.0010802659],"genre_scores_gemma":[0.4024403,0.00055594597,0.32666504,0.25582644,0.0043514376,0.0021771821,0.0031254762,0.00043535154,0.0044228304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990651,0.0038638536,0.0019602054,0.0015659005,0.0011401867,0.0008188601],"domain_scores_gemma":[0.99389166,0.0025393243,0.001945262,0.00091541716,0.0005401356,0.00016823127],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0041450486,0.00054255064,0.0015679535,0.0008768347,0.00039163764,0.0000632497,0.001253306,0.0011132661,0.00035002947],"category_scores_gemma":[0.000352783,0.00051402685,0.00041459818,0.0012492893,0.00030560166,0.0001857267,0.0010546474,0.003403709,0.000019946303],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059979996,0.00096913206,0.00021255155,0.00043957494,0.00040774007,0.29129297,0.0077225366,0.0017163726,0.006611352,0.000028338985,0.1565587,0.52804273],"study_design_scores_gemma":[0.0005976082,0.00167268,0.00041166556,0.00009445729,0.000030344816,0.0025032845,0.00006688443,0.0023743012,0.0018505391,0.00015634469,0.98971933,0.0005225556],"about_ca_topic_score_codex":0.000147264,"about_ca_topic_score_gemma":0.000039508108,"teacher_disagreement_score":0.83316064,"about_ca_system_score_codex":0.00043039361,"about_ca_system_score_gemma":0.0013450901,"threshold_uncertainty_score":0.9997311},"labels":[],"label_agreement":null},{"id":"W4312120085","doi":"10.58506/ajstss.v1i2.17","title":"Development and validation of digital medical laboratory educational platform","year":2022,"lang":"en","type":"article","venue":"African Journal of Science Technology and Social Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Digital pathology; Telepathology; Virtual microscopy; Virtual Laboratory; Multimedia; Computer science; Resource (disambiguation); Medical education; Medical physics; Medicine; Pathology; Telemedicine; Artificial intelligence; Health care","score_opus":0.01942582558003912,"score_gpt":0.2805344839137773,"score_spread":0.26110865833373814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312120085","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9873914,0.00012781918,0.0026238146,0.009119394,0.00026494035,0.000029609766,0.0000010970772,0.000012097699,0.000429839],"genre_scores_gemma":[0.9935486,0.0000067735436,0.0063622883,0.00004858775,0.000023283645,0.0000028991142,4.9769145e-8,9.1516796e-7,0.000006613423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843276,0.000016388844,0.00024818358,0.00016970214,0.0009777509,0.00015520866],"domain_scores_gemma":[0.99936306,0.000065514505,0.00031449835,0.000049206246,0.0001571453,0.000050546863],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.002205748,0.0000491679,0.0001054677,0.0008697186,0.0014327591,0.000076024204,0.0009736073,0.000034093096,0.000011840807],"category_scores_gemma":[0.0001687806,0.000042148215,0.000012238667,0.0033378568,0.0043650945,0.0011230266,0.0004156568,0.00017893642,2.088669e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013647263,0.000140471,0.027859269,0.0000109657485,0.000017318831,0.0000083545065,0.018882189,0.000029439043,0.004690253,0.6897355,0.00013286667,0.25847974],"study_design_scores_gemma":[0.0021106275,0.0046538957,0.04925526,0.00010769922,0.000038627997,0.0026398366,0.16507688,0.0039396537,0.12947786,0.5962281,0.04515314,0.0013184013],"about_ca_topic_score_codex":0.0000011235433,"about_ca_topic_score_gemma":8.000579e-7,"teacher_disagreement_score":0.25716135,"about_ca_system_score_codex":0.000099760124,"about_ca_system_score_gemma":0.0020687769,"threshold_uncertainty_score":0.99986726},"labels":[],"label_agreement":null},{"id":"W4312839084","doi":"10.2139/ssrn.4231806","title":"A Deep Neural Network for Cervical Cell Detection Based on Cytology Images","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial intelligence; Artificial neural network; Computer science; Cytology; Deep neural networks; Pattern recognition (psychology); Computer vision; Medicine; Pathology","score_opus":0.006437612693196812,"score_gpt":0.22374353533566962,"score_spread":0.2173059226424728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312839084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006662421,0.00053649774,0.98873514,0.0019099563,0.0016292876,0.00021976003,0.0000012006938,0.00011066714,0.00019505442],"genre_scores_gemma":[0.9949569,0.000039356994,0.0032988286,0.0007982965,0.0006510227,0.00011089234,0.000001592662,0.000023830542,0.00011925051],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968311,0.0002973956,0.00024785177,0.0003668452,0.00034662386,0.0019101527],"domain_scores_gemma":[0.99918926,0.00018143475,0.00020302918,0.00028730425,0.00006516421,0.000073807314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014114451,0.00015653293,0.0001613681,0.00015296122,0.000981421,0.000085960295,0.0007463454,0.00005733379,0.000026161855],"category_scores_gemma":[0.000021340142,0.00016022775,0.00016842084,0.00045018859,0.000024056464,0.00019869745,0.00011747758,0.0019995302,0.0000064599503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006626472,0.00016909905,0.00033556548,0.00001246331,0.000050457507,0.000013940982,0.0000915127,0.66764945,0.0015594778,0.016086336,0.0004952572,0.3128738],"study_design_scores_gemma":[0.0011347643,0.0037432166,0.00025875788,0.0000018365969,0.000018233655,0.00067950715,0.000086551794,0.89349574,0.0012792384,0.096123956,0.0029662875,0.00021191762],"about_ca_topic_score_codex":0.000019906573,"about_ca_topic_score_gemma":0.0002443259,"teacher_disagreement_score":0.9882945,"about_ca_system_score_codex":0.0019950527,"about_ca_system_score_gemma":0.0007393886,"threshold_uncertainty_score":0.8687075},"labels":[],"label_agreement":null},{"id":"W4312845627","doi":"10.1109/icdacai57211.2022.00075","title":"Breast Cancer Detection Using Convolutional Neural Networks Model","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Breast cancer; Artificial intelligence; Convolutional neural network; Workload; Machine learning; Deep learning; Residual neural network; Data set; Artificial neural network; Dependency (UML); Set (abstract data type); Field (mathematics); Cancer; Data mining; Medical physics; Medicine","score_opus":0.19017241743889626,"score_gpt":0.3606697299280047,"score_spread":0.17049731248910846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312845627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02252936,0.000083774554,0.9712604,0.0023066471,0.0029346643,0.00016015829,0.0003934623,0.00014678294,0.00018473089],"genre_scores_gemma":[0.9964603,0.00008546455,0.0021385264,0.00048550178,0.0006131446,0.000013205811,0.0001158985,0.000019904013,0.000068010995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967981,0.00016488311,0.0006209572,0.0011111881,0.000881079,0.00042382017],"domain_scores_gemma":[0.9982657,0.0001264779,0.00036955945,0.00074866187,0.00035156062,0.00013805935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080423907,0.0002808898,0.0002521167,0.00033880124,0.0010098631,0.00052065606,0.0022583166,0.00007350103,0.00024587708],"category_scores_gemma":[0.000050017872,0.00032102858,0.00007744128,0.0005549755,0.00016966986,0.0006108457,0.0024077606,0.000784358,0.000006506328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058687518,0.00009601883,0.00013684208,0.0000037302584,0.00005438656,0.000006493784,0.00011519645,0.7829926,0.00019477715,0.048060957,0.00008231145,0.16819797],"study_design_scores_gemma":[0.00007869468,0.00006774501,0.000093213355,0.000025373662,0.000023987892,0.000120772296,0.00032005954,0.9888362,0.00017172335,0.009848225,0.00007902724,0.00033492557],"about_ca_topic_score_codex":0.00063900434,"about_ca_topic_score_gemma":0.00020405733,"teacher_disagreement_score":0.97393095,"about_ca_system_score_codex":0.00048671168,"about_ca_system_score_gemma":0.0002273154,"threshold_uncertainty_score":0.9999242},"labels":[],"label_agreement":null},{"id":"W4312866229","doi":"10.1007/978-3-031-21517-9_6","title":"Mayfly-Algorithm Selected Features for Classification of Breast Histology Images into Benign/Malignant Class","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Concatenation (mathematics); Feature extraction; Feature (linguistics); Pattern recognition (psychology); Pixel; Feature selection; Algorithm; Mathematics","score_opus":0.012015002871406867,"score_gpt":0.2458053075751026,"score_spread":0.23379030470369574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312866229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003443918,0.00084852,0.9924845,0.0019515238,0.0030714315,0.0008094321,0.0000593849,0.00017853214,0.0005622533],"genre_scores_gemma":[0.101798736,0.00010445747,0.8960608,0.000573417,0.00066619646,0.00017580308,0.000050405048,0.000088790875,0.00048135448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99543,0.00009415948,0.00076104555,0.0019726013,0.0010715566,0.00067064306],"domain_scores_gemma":[0.9960632,0.0006670109,0.0008052487,0.001501693,0.00083052006,0.00013236579],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009201793,0.0005663939,0.0007307349,0.0012320488,0.00047217097,0.00019515712,0.0034702288,0.000431699,0.000033824846],"category_scores_gemma":[0.00010044471,0.00056602573,0.0001967292,0.0012585978,0.0008942414,0.00048945047,0.0010872307,0.00091588584,0.0000044643907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031530188,0.000045801113,0.000019769956,0.000097284945,0.000027593362,0.000015284553,0.0006894282,0.0039000225,0.007112208,0.01698767,0.00024459435,0.97082883],"study_design_scores_gemma":[0.0010370716,0.0013241905,0.002180325,0.00030586863,0.000060826686,0.0007997265,0.0000018795416,0.76556975,0.017191118,0.19469756,0.015182889,0.0016487829],"about_ca_topic_score_codex":0.00013385616,"about_ca_topic_score_gemma":0.00015245212,"teacher_disagreement_score":0.96918005,"about_ca_system_score_codex":0.0014222328,"about_ca_system_score_gemma":0.0011917197,"threshold_uncertainty_score":0.99967915},"labels":[],"label_agreement":null},{"id":"W4313490077","doi":"10.1186/s12885-022-10488-5","title":"Inference of core needle biopsy whole slide images requiring definitive therapy for prostate cancer","year":2023,"lang":"en","type":"article","venue":"BMC Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"New Energy and Industrial Technology Development Organization","keywords":"Medicine; Overdiagnosis; Prostate cancer; Guideline; Prostate; Biopsy; Cancer; Surgical oncology; Radiology; Medical physics; Oncology; Internal medicine; Pathology","score_opus":0.0935098420949048,"score_gpt":0.35763488195457277,"score_spread":0.26412503985966795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313490077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58235896,0.0048035737,0.40198925,0.0018520731,0.0040346095,0.0022009567,0.00070414616,0.0009924786,0.0010639537],"genre_scores_gemma":[0.98191476,0.0020165814,0.011710576,0.0002540089,0.0003018579,0.002156319,0.000009762924,0.000045076977,0.001591052],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985761,0.000028299379,0.00027668657,0.0004641786,0.00026281396,0.0003919122],"domain_scores_gemma":[0.9987616,0.00025120063,0.00022861735,0.00040208967,0.00029543674,0.00006109047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024461575,0.00017476955,0.00022919041,0.00016725404,0.00013308499,0.00007298731,0.0004890324,0.00006458865,0.000025640045],"category_scores_gemma":[0.00006333277,0.00016366312,0.00009455693,0.000957472,0.00010194481,0.00046568923,0.00015758345,0.00010495263,0.000018405202],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057452935,0.000095940355,0.0912974,0.0006261568,0.00018948977,0.000009291454,0.010828875,0.018253082,0.2121083,0.0053392253,0.01779427,0.6428834],"study_design_scores_gemma":[0.005769218,0.0010208978,0.17258534,0.001298878,0.000057197572,0.000011540353,0.0010882288,0.102358796,0.6486157,0.025714403,0.039790493,0.0016892909],"about_ca_topic_score_codex":0.0013055024,"about_ca_topic_score_gemma":0.0004608377,"teacher_disagreement_score":0.64119416,"about_ca_system_score_codex":0.00019256731,"about_ca_system_score_gemma":0.0004928082,"threshold_uncertainty_score":0.66739887},"labels":[],"label_agreement":null},{"id":"W4313495964","doi":"10.1109/acit57182.2022.9994181","title":"Pancreatic Tumor Detection by Convolutional Neural Networks","year":2022,"lang":"en","type":"article","venue":"2022 International Arab Conference on Information Technology (ACIT)","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pancreatic cancer; Convolutional neural network; Artificial intelligence; Computer science; Medical imaging; Cancer; Process (computing); Deep learning; Cancer detection; Computed tomography; Medicine; Radiology; Internal medicine","score_opus":0.007503623571780644,"score_gpt":0.21603050060808407,"score_spread":0.20852687703630343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313495964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023875799,0.00006299029,0.9589081,0.0070747216,0.003650638,0.00040276145,0.000093375624,0.00096928485,0.004962362],"genre_scores_gemma":[0.995831,0.000023444736,0.0011642312,0.0017447824,0.00006969097,0.0007110895,0.00014435276,0.000010123505,0.00030130125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977744,0.00008907467,0.00058757456,0.00037760215,0.00082856405,0.00034275957],"domain_scores_gemma":[0.9985845,0.00007029843,0.0004925395,0.00046351086,0.0003242812,0.00006488605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034181905,0.00023381771,0.0001937654,0.0008752311,0.0006163628,0.00020676396,0.0016317642,0.0001158581,0.00084904226],"category_scores_gemma":[0.000101033234,0.00026492262,0.00008316042,0.00095821224,0.0001383132,0.0018295671,0.0006300829,0.00090772205,0.00012000338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023226821,0.00018842767,0.0011086193,0.000016228983,0.0001818174,0.000013843557,0.00040901292,0.04860861,0.0024734442,0.61423004,0.01321826,0.31931943],"study_design_scores_gemma":[0.0005920126,0.00036710748,0.000369026,0.000007226989,0.000006307029,0.00020120273,0.00027631258,0.955548,0.0018045177,0.008532546,0.032017957,0.0002777913],"about_ca_topic_score_codex":0.000033749016,"about_ca_topic_score_gemma":0.0000062056874,"teacher_disagreement_score":0.9719552,"about_ca_system_score_codex":0.0009241226,"about_ca_system_score_gemma":0.00010480127,"threshold_uncertainty_score":0.9999803},"labels":[],"label_agreement":null},{"id":"W4313530895","doi":"10.1016/j.compmedimag.2022.102161","title":"Synchronous Medical Image Augmentation framework for deep learning-based image segmentation","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Focus (optics); Image (mathematics); Image segmentation; Sample (material); Transformation (genetics); Deep learning; Medical imaging; Pattern recognition (psychology); Computer vision","score_opus":0.008452284627012663,"score_gpt":0.28564876436989484,"score_spread":0.2771964797428822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313530895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037971379,0.00039572062,0.9831642,0.01016897,0.0016355414,0.00037025285,0.0000048675556,0.00044538316,0.000017907128],"genre_scores_gemma":[0.28497103,0.00024003412,0.7040425,0.00942856,0.0005484658,0.00056737685,0.00013011975,0.00005960197,0.000012336161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967778,0.000360588,0.0004227358,0.0006487841,0.0013813452,0.0004087706],"domain_scores_gemma":[0.998123,0.0008583075,0.00020956254,0.00031163034,0.00011971984,0.00037780518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014246193,0.00022018499,0.00026480982,0.0002510765,0.00088749087,0.00025303956,0.00072350714,0.000103154365,0.000147933],"category_scores_gemma":[0.00044305026,0.0002363714,0.00012025351,0.00058009726,0.00029872876,0.0003738104,0.0004712354,0.0008646993,0.0000031897323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017505656,0.00035420613,0.000781743,0.00030074953,0.00008912742,0.00021119871,0.0016601275,0.000506319,0.0015605476,0.014361526,0.0020019913,0.9779974],"study_design_scores_gemma":[0.0021834136,0.00023241906,0.00032605807,0.00006754388,0.000021722657,0.0001202527,0.00012157363,0.9814962,0.00044893057,0.010965739,0.003740606,0.00027550609],"about_ca_topic_score_codex":0.000026010277,"about_ca_topic_score_gemma":0.0000030662616,"teacher_disagreement_score":0.98098993,"about_ca_system_score_codex":0.00014294997,"about_ca_system_score_gemma":0.00028057184,"threshold_uncertainty_score":0.9638946},"labels":[],"label_agreement":null},{"id":"W4313547826","doi":"10.1016/j.jpi.2022.100177","title":"An update on computational pathology tools for genitourinary pathology practice: A review paper from the Genitourinary Pathology Society (GUPS)","year":2022,"lang":"en","type":"review","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute","keywords":"Genitourinary system; Standardization; Computer science; Digital pathology; Grading (engineering); Pathology; Surgical pathology; Deep learning; Anatomical pathology; Artificial intelligence; Data science; Medical physics; Bioinformatics; Medicine; Biology; Anatomy","score_opus":0.06624757497684777,"score_gpt":0.370564328847515,"score_spread":0.30431675387066726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313547826","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000079936144,0.8245178,0.16510814,0.002895182,0.004677748,0.0019082977,0.00052664033,0.00010982335,0.00017644974],"genre_scores_gemma":[0.000008717956,0.8087453,0.17001157,0.019041836,0.0012783553,0.0004219772,0.0003952647,0.00008395265,0.000012990394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885461,0.0040656105,0.0046116523,0.00073065725,0.0010826609,0.0009633521],"domain_scores_gemma":[0.98013914,0.008131785,0.008561202,0.002057791,0.0008479695,0.00026208718],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007284091,0.0010435111,0.0033347975,0.00040764766,0.00089317845,0.00026753405,0.0044190483,0.001121438,0.00018271057],"category_scores_gemma":[0.0017392925,0.000766049,0.0019365168,0.00079739734,0.00047595068,0.0030739517,0.0011466176,0.004012764,0.00010212464],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010480715,0.0004485178,0.0000020093826,0.0044293366,0.0004932441,0.005368502,0.0025655457,0.000677641,0.0000025900988,0.001243906,0.031615198,0.9530487],"study_design_scores_gemma":[0.00088303303,0.0034132435,0.000019046693,0.0019950792,0.0015186947,0.093976654,0.00052657153,0.00091588957,6.877803e-7,0.0030597025,0.8930117,0.00067971024],"about_ca_topic_score_codex":0.0000013828698,"about_ca_topic_score_gemma":0.000001234986,"teacher_disagreement_score":0.952369,"about_ca_system_score_codex":0.000730611,"about_ca_system_score_gemma":0.0018875789,"threshold_uncertainty_score":0.99947906},"labels":[],"label_agreement":null},{"id":"W4313886837","doi":"10.1109/jiot.2023.3235651","title":"FastNet: A Lightweight Convolutional Neural Network for Tumors Fast Identification in Mobile-Computer-Assisted Devices","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Southern Medical University; Technological University Dublin; University of Electronic Science and Technology of China; National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Identification (biology); Artificial intelligence","score_opus":0.02089264385230817,"score_gpt":0.2703384254907671,"score_spread":0.24944578163845893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313886837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37218273,0.00018644151,0.622143,0.0003610491,0.004711495,0.00025289456,0.000003022568,0.0001226591,0.00003677032],"genre_scores_gemma":[0.9802573,0.000018491226,0.018437989,0.00015904427,0.0008237789,0.000060533665,0.00000505788,0.000019328654,0.00021848921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977939,0.00011121144,0.0008518575,0.00037402124,0.0004580868,0.00041093913],"domain_scores_gemma":[0.9984361,0.00021905942,0.00073892536,0.00024054042,0.00026900566,0.00009636289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010842588,0.00018003547,0.0002762283,0.00042542137,0.000118586766,0.0003082613,0.0011411502,0.0000930604,0.000010864685],"category_scores_gemma":[0.000025991973,0.00017396142,0.00018272997,0.00075692136,0.00006232239,0.0012374029,0.000136509,0.0003699049,0.000023449047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005252034,0.00045208368,0.026916431,0.0003798129,0.00044320378,0.00020689165,0.016374966,0.22859386,0.021760942,0.004926152,0.055397157,0.6440233],"study_design_scores_gemma":[0.00062311196,0.0003472165,0.022659877,0.00032563266,0.000011186431,0.00040622836,0.00005898565,0.9636023,0.0061712395,0.0033850467,0.002190383,0.00021878771],"about_ca_topic_score_codex":0.000045210545,"about_ca_topic_score_gemma":0.000031388685,"teacher_disagreement_score":0.7350084,"about_ca_system_score_codex":0.00023822863,"about_ca_system_score_gemma":0.0000982377,"threshold_uncertainty_score":0.7093941},"labels":[],"label_agreement":null},{"id":"W4313893521","doi":"10.1002/ima.22846","title":"Histopathological carcinoma classification using parallel, cross‐concatenated and grouped convolutions deep neural network","year":2023,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Scheme for Promotion of Academic and Research Collaboration; Ministry of Education, India; Kasturba Medical College, Manipal","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Deep learning; Artificial neural network; Robustness (evolution); Liver cancer; Contextual image classification; Machine learning; Cancer; Medicine; Image (mathematics); Internal medicine; Biology","score_opus":0.029706730758619675,"score_gpt":0.2936547298234702,"score_spread":0.2639479990648505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313893521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72382337,0.002028459,0.26805118,0.0032438582,0.0025780068,0.000079894446,0.0000014662386,0.00016240563,0.000031347758],"genre_scores_gemma":[0.99653965,0.00007109032,0.003091468,0.00004314665,0.0002229224,0.000005968199,0.0000011782842,0.000006890528,0.000017661856],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891204,0.00005868986,0.00042049636,0.00021306585,0.00021192594,0.00018379328],"domain_scores_gemma":[0.9989118,0.000062280415,0.00039793426,0.00013271382,0.00044931102,0.00004599024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040964334,0.00009737613,0.00017104739,0.0004702708,0.00014447227,0.00019318782,0.00043887226,0.00008735976,9.047333e-7],"category_scores_gemma":[0.000076087716,0.00008634419,0.00003124335,0.00041162322,0.0002099032,0.0004255332,0.00019556658,0.00023143823,0.0000018617446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005564868,0.000042930453,0.7936634,0.000030165791,0.000121112294,0.00093974354,0.00032701943,0.010651472,0.017234089,0.12827319,0.0005762245,0.04808501],"study_design_scores_gemma":[0.00049528846,0.000054047887,0.09829677,0.00003643858,0.000009683701,0.005675168,0.000108714325,0.89035046,0.00003787325,0.0041018086,0.0007351965,0.00009854678],"about_ca_topic_score_codex":0.00004023891,"about_ca_topic_score_gemma":0.0000026437708,"teacher_disagreement_score":0.879699,"about_ca_system_score_codex":0.00016017625,"about_ca_system_score_gemma":0.00003446712,"threshold_uncertainty_score":0.3521014},"labels":[],"label_agreement":null},{"id":"W4315646835","doi":"10.18280/isi.270613","title":"Classification of Colon and Lung Cancer Through Analysis of Histopathology Images Using Deep Learning Models","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Histopathology; Lung cancer; Colorectal cancer; Artificial intelligence; Deep learning; Computer science; Visualization; Medical physics; Medicine; Cancer; Pathology; Internal medicine","score_opus":0.029387893905483978,"score_gpt":0.27336906932830346,"score_spread":0.2439811754228195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315646835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38448256,0.00041536667,0.6144299,0.000014446252,0.00012451588,0.00010299362,0.000010521311,0.000036020243,0.0003836797],"genre_scores_gemma":[0.98632276,0.00008105965,0.01347424,0.000025400499,0.000007545278,0.000059463593,0.000018805798,0.000004387932,0.0000063109946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884486,0.00014084169,0.000491938,0.00013645219,0.0002560078,0.00012988175],"domain_scores_gemma":[0.9987229,0.000052370946,0.0007812413,0.0002037504,0.00022129757,0.000018409719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003709377,0.00008737676,0.00023794395,0.00045952745,0.0002812614,0.000035250072,0.00021890443,0.000045527897,0.000014597786],"category_scores_gemma":[0.000033675577,0.00010035393,0.000057624307,0.0012952116,0.00010605767,0.0026484893,0.00018143651,0.00012390774,1.3740528e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037700585,0.00001518148,0.008006938,0.0002302725,0.00013822297,4.876032e-7,0.027790762,0.8666543,0.00837382,0.008193566,0.000013277917,0.080545515],"study_design_scores_gemma":[0.00012992222,0.00006462011,0.016117077,0.000016063153,0.00015060228,0.000009642933,0.0007975191,0.9794461,0.0016471759,0.0014584654,0.00007213211,0.00009069007],"about_ca_topic_score_codex":0.0005479834,"about_ca_topic_score_gemma":0.00002127247,"teacher_disagreement_score":0.60184026,"about_ca_system_score_codex":0.0006003255,"about_ca_system_score_gemma":0.00007571109,"threshold_uncertainty_score":0.40923145},"labels":[],"label_agreement":null},{"id":"W4316371389","doi":"10.18280/ts.390628","title":"Systematical Analysis and Pathological Classification of Breast Cancer from Mammographic Images with Using Specific Machine Learning Methods","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Learning vector quantization; Pattern recognition (psychology); Support vector machine; Computer science; Image processing; Segmentation; Artificial neural network; Mathematics; Image (mathematics)","score_opus":0.034879448155380424,"score_gpt":0.2915703319928246,"score_spread":0.2566908838374442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316371389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3283408,0.00032724958,0.670925,0.00014298595,0.000040443654,0.00012820629,0.000038874052,0.00004370392,0.000012706677],"genre_scores_gemma":[0.8847507,0.000022360431,0.1150901,0.000018011546,0.000034746,0.00006390152,0.000009045399,0.00000749152,0.0000035896644],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977929,0.00078539096,0.00035318822,0.0004436103,0.0004624825,0.00016244833],"domain_scores_gemma":[0.9991982,0.0001698986,0.00028699488,0.00022083292,0.000067271394,0.00005680865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091529684,0.00013594923,0.00031429573,0.00029657103,0.0002468295,0.00007315275,0.00027634567,0.000029459614,0.00034091272],"category_scores_gemma":[0.0000036278964,0.000110617126,0.00008263749,0.0012431822,0.00009378346,0.0001746676,0.00015424279,0.00022040603,2.585418e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038963856,0.00038973926,0.372268,0.00019298935,0.0014234824,0.000047588368,0.0020780952,0.082987115,0.4296424,0.002901397,0.00002135462,0.107658185],"study_design_scores_gemma":[0.00036754648,0.00015508062,0.3586869,0.000025418367,0.00029817517,0.000043932603,0.00022723917,0.6385188,0.0012915218,0.00018561058,0.00003953697,0.00016023433],"about_ca_topic_score_codex":0.0002618314,"about_ca_topic_score_gemma":0.00001695777,"teacher_disagreement_score":0.55640996,"about_ca_system_score_codex":0.0001245359,"about_ca_system_score_gemma":0.000027845608,"threshold_uncertainty_score":0.45108357},"labels":[],"label_agreement":null},{"id":"W4316467213","doi":"10.18280/ts.390620","title":"Collaborative Colorectal Cancer Classification on Highly Class Imbalanced Data Setting via Federated Neural Style Transfer Based Data Augmentation","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Dicle Üniversitesi","keywords":"Computer science; Class (philosophy); Transfer of learning; Style (visual arts); Artificial intelligence; Artificial neural network; Machine learning; Deep learning; Transfer (computing); Data mining; Parallel computing","score_opus":0.04207698531958367,"score_gpt":0.2952368259259382,"score_spread":0.25315984060635455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316467213","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18395418,0.00008738696,0.80125326,0.008013095,0.0015033191,0.0017170432,0.0027490407,0.00048353412,0.00023912871],"genre_scores_gemma":[0.9923035,0.0000066877487,0.002587919,0.0012323267,0.00018462042,0.00046877944,0.0031677217,0.000027678077,0.000020757458],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635935,0.00057644147,0.00048372112,0.0012089055,0.0009931601,0.00037842416],"domain_scores_gemma":[0.9984347,0.00019370754,0.00020517099,0.0009181583,0.00015346962,0.000094789786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092329667,0.00025985355,0.00021273727,0.0001509485,0.0008804025,0.00030454178,0.0019277489,0.00005178184,0.0003933144],"category_scores_gemma":[0.000015407019,0.00027911153,0.00003107258,0.0009722131,0.000055320445,0.0012950987,0.00042227388,0.0003377742,0.000009084698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024100477,0.0011551982,0.0018264009,0.00009252947,0.0003509953,0.000043575892,0.003069548,0.13398121,0.54750156,0.0015016657,0.034725185,0.27334207],"study_design_scores_gemma":[0.0019134356,0.0005609924,0.005276218,0.000014360232,0.000034794182,0.000003278585,0.0002840803,0.9718697,0.015246774,0.000022720971,0.004467366,0.0003062571],"about_ca_topic_score_codex":0.00013503851,"about_ca_topic_score_gemma":0.00023653288,"teacher_disagreement_score":0.8378885,"about_ca_system_score_codex":0.00078481744,"about_ca_system_score_gemma":0.00043868445,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W4317504313","doi":"10.1007/978-981-19-7742-8_12","title":"Medical-Network (Med-Net): A Neural Network for Breast Cancer Segmentation in Ultrasound Image","year":2023,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Computer science; Discriminative model; Segmentation; Feature (linguistics); Artificial neural network; Pattern recognition (psychology); Encoder; Breast ultrasound; Salient; Image segmentation; Deep learning; Breast cancer; Computer vision; Cancer; Medicine; Mammography","score_opus":0.020195050953061514,"score_gpt":0.26187201526667925,"score_spread":0.24167696431361774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317504313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045990148,0.01961003,0.8326358,0.03729085,0.04631715,0.015570188,0.0012951746,0.02037064,0.022311129],"genre_scores_gemma":[0.5214733,0.03465145,0.09117906,0.0031481362,0.021694586,0.02472931,0.0018901504,0.0017517029,0.2994823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972832,0.000025066518,0.00092543,0.00075644435,0.00052924134,0.00048058567],"domain_scores_gemma":[0.9979895,0.00031138482,0.000645211,0.0005684377,0.0004571564,0.000028341092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010300764,0.00038682812,0.0005126442,0.0005573377,0.00025849018,0.00027234596,0.00065959245,0.0007795419,0.000009055916],"category_scores_gemma":[0.00012314045,0.00036730047,0.000053771902,0.0012492564,0.00022193226,0.00041525174,0.00028863017,0.0005174209,0.000007734588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027045711,0.00001040052,0.003250952,0.0005648697,0.00015614326,0.00001971647,0.00009733977,0.0013611127,0.000058143894,0.77162766,0.059182692,0.16364394],"study_design_scores_gemma":[0.0031726025,0.00059517386,0.012817197,0.007891552,0.00013062717,0.0007645518,0.0007486135,0.06476906,0.00018693932,0.73138165,0.17398268,0.003559333],"about_ca_topic_score_codex":0.00027324463,"about_ca_topic_score_gemma":0.00081048155,"teacher_disagreement_score":0.74145675,"about_ca_system_score_codex":0.00028356456,"about_ca_system_score_gemma":0.00019400069,"threshold_uncertainty_score":0.99987787},"labels":[],"label_agreement":null},{"id":"W4317930395","doi":"10.1016/j.compbiomed.2023.106575","title":"Compatible-domain Transfer Learning for Breast Cancer Classification with Limited Annotated Data","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Transfer of learning; Deep learning; Machine learning; Task (project management); Data set; Set (abstract data type); Test set; Pattern recognition (psychology); Training set","score_opus":0.06814694937578723,"score_gpt":0.3460717671990667,"score_spread":0.27792481782327944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317930395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120407574,0.00020439534,0.8662837,0.011922718,0.00062290725,0.00029679964,0.000017409939,0.0002076082,0.000036880792],"genre_scores_gemma":[0.9908746,0.00039788164,0.007776243,0.0004896533,0.00018484774,0.000056447865,0.00019371213,0.000009357687,0.00001726535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989401,0.000100973346,0.00018738562,0.00048175085,0.00006732924,0.00022243518],"domain_scores_gemma":[0.99923563,0.00028494254,0.00004507088,0.00032419444,0.00005803764,0.00005209743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047247717,0.00011261555,0.0002063881,0.0002308879,0.00011650075,0.000010994499,0.00043460063,0.00007837183,0.0000031521135],"category_scores_gemma":[0.000014655819,0.000084003615,0.000008001374,0.0007424461,0.0002064047,0.00014972595,0.00009863157,0.00016445995,0.0000012465662],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005696467,0.00006216146,0.08346085,0.00017416208,0.00014165262,0.000019888545,0.0044014943,0.0026162723,0.011121856,0.017114744,0.0066638156,0.8736535],"study_design_scores_gemma":[0.002626193,0.00054594764,0.20631172,0.00023225925,0.000013748819,0.00004684582,0.0001767881,0.78197485,0.00005130204,0.001685531,0.006159471,0.00017535369],"about_ca_topic_score_codex":0.000072930874,"about_ca_topic_score_gemma":0.000103330654,"teacher_disagreement_score":0.8734781,"about_ca_system_score_codex":0.000039239272,"about_ca_system_score_gemma":0.00004228836,"threshold_uncertainty_score":0.3425568},"labels":[],"label_agreement":null},{"id":"W4318672081","doi":"10.1148/radiol.221785","title":"Supplemental Breast Cancer Screening in Women with Dense Breasts and Negative Mammography: A Systematic Review and Meta-Analysis","year":2023,"lang":"en","type":"review","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Sinai Health System; Princess Margaret Cancer Centre; McMaster University; Women's College Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Mammography; Meta-analysis; Breast cancer; Screening mammography; Cancer; Radiology; Gynecology; Medical physics; Internal medicine","score_opus":0.05284240375586524,"score_gpt":0.3292527069291568,"score_spread":0.27641030317329157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318672081","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000048140378,0.9940915,0.003364755,0.0003320823,0.000029544455,0.0018500253,0.00026114067,0.00006238261,0.0000037169514],"genre_scores_gemma":[0.00006296081,0.9946416,0.0015990527,0.00024164752,0.000020194264,0.003350934,0.00001208057,0.000029566558,0.000041943927],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9965153,0.0011255048,0.00079217745,0.000926592,0.000198858,0.00044158052],"domain_scores_gemma":[0.9980918,0.00046996368,0.0006752,0.0005828843,0.000053354142,0.00012676329],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010270335,0.0004720334,0.0061637494,0.00081263355,0.000074719006,0.00006703384,0.00046728292,0.00014801981,0.00004532206],"category_scores_gemma":[0.000020032176,0.00030704564,0.00040984876,0.0027359424,0.00014265957,0.00018115526,0.00025855057,0.0003173003,0.0000028657714],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014188594,0.000014522136,0.00006680416,0.7605129,0.20750187,0.00012626291,0.0004297246,0.000011738573,2.9123418e-8,0.00012961126,0.00014753896,0.031044839],"study_design_scores_gemma":[0.00049296074,0.00024703617,0.00048390194,0.05608557,0.9313168,0.006449623,0.00009504559,0.00036573235,5.5893178e-8,0.0001439179,0.003127809,0.0011915272],"about_ca_topic_score_codex":0.00050844636,"about_ca_topic_score_gemma":0.0010867909,"teacher_disagreement_score":0.72381496,"about_ca_system_score_codex":0.0002140535,"about_ca_system_score_gemma":0.000113891,"threshold_uncertainty_score":0.9999382},"labels":[],"label_agreement":null},{"id":"W4318695000","doi":"10.1117/1.jmi.10.1.017501","title":"Single patch super-resolution of histopathology whole slide images: a comparative study","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Magnification; Histopathology; Artificial intelligence; Digital pathology; Image resolution; Image quality; Computer science; Medicine; Pixel; Digital imaging; Computer vision; Digital image; Deep learning; Image processing; Pattern recognition (psychology); Medical physics; Image (mathematics); Pathology","score_opus":0.04251881914739823,"score_gpt":0.3364908861053369,"score_spread":0.29397206695793865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318695000","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41964945,0.00045344883,0.5670151,0.010581087,0.0018693848,0.00012302579,0.0000012270117,0.00007234822,0.00023494253],"genre_scores_gemma":[0.9966725,0.000021088985,0.0028621906,0.00015284836,0.00023692728,0.0000031918958,3.635372e-7,0.0000071039403,0.00004376203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973678,0.00030627617,0.0006443337,0.0001917563,0.001252198,0.00023763084],"domain_scores_gemma":[0.9986677,0.00025003828,0.0004066322,0.0002335156,0.0002914736,0.00015060304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022584067,0.000103236314,0.00034572842,0.0003306578,0.00007824339,0.000043678167,0.0008006891,0.000045566867,0.000021916747],"category_scores_gemma":[0.00037276413,0.00008817866,0.00009518886,0.00064697466,0.00014884584,0.00054751727,0.000265158,0.00044071893,0.00002110309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019923157,0.0028127085,0.06303422,0.00013894032,0.0001822641,0.0056661223,0.05692453,0.0014162019,0.13749655,0.00042923258,0.12535931,0.6063407],"study_design_scores_gemma":[0.007251776,0.0024937668,0.08740272,0.0008823142,0.00014894558,0.0037256302,0.019695507,0.83020586,0.019881632,0.004454527,0.02315994,0.00069740904],"about_ca_topic_score_codex":0.0000722398,"about_ca_topic_score_gemma":0.000017441744,"teacher_disagreement_score":0.82878965,"about_ca_system_score_codex":0.00019365603,"about_ca_system_score_gemma":0.00020001944,"threshold_uncertainty_score":0.35958216},"labels":[],"label_agreement":null},{"id":"W4319083729","doi":"10.3390/diagnostics13030558","title":"Virtual Versus Light Microscopy Usage among Students: A Systematic Review and Meta-Analytic Evidence in Medical Education","year":2023,"lang":"en","type":"review","venue":"Diagnostics","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Virtual microscopy; CINAHL; Medical education; MEDLINE; Systematic review; Disadvantage; Medicine; Medical physics; Psychology; Computer science; Artificial intelligence; Pathology; Nursing; Psychological intervention","score_opus":0.12722148226732424,"score_gpt":0.4406864187001275,"score_spread":0.31346493643280327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319083729","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015082281,0.99348617,0.0015511363,0.00035038646,0.0013843181,0.0030966254,0.0000074310074,0.00010587722,0.000016554228],"genre_scores_gemma":[0.0000065742115,0.996673,0.00025805223,0.0004542035,0.00008675536,0.002235997,0.000008924375,0.000046272187,0.00023026111],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9947852,0.0009918625,0.0016192041,0.0009303934,0.001319935,0.00035343232],"domain_scores_gemma":[0.9909463,0.006404721,0.000900867,0.0013505282,0.00014574944,0.00025182895],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002775222,0.0005298653,0.0038219339,0.00040705004,0.00007640955,0.00033083273,0.002327026,0.00033097886,0.000031160365],"category_scores_gemma":[0.020556662,0.00040536764,0.00043957846,0.001814891,0.0000862104,0.00045389868,0.00085022266,0.00064069027,0.00024243332],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.3919516e-7,0.000109486406,0.000010714072,0.97768515,0.0018470852,0.00008465436,0.0001209677,5.995448e-7,6.4583183e-9,0.00036237168,0.0036605787,0.01611742],"study_design_scores_gemma":[0.00016162505,0.00017104615,0.00001067888,0.90567946,0.076848336,0.000053075983,0.00001849147,0.00011527179,4.198636e-7,0.00006446287,0.016211398,0.00066573586],"about_ca_topic_score_codex":0.00006049832,"about_ca_topic_score_gemma":0.00016701318,"teacher_disagreement_score":0.075001255,"about_ca_system_score_codex":0.00057520444,"about_ca_system_score_gemma":0.0012669498,"threshold_uncertainty_score":0.99983984},"labels":[],"label_agreement":null},{"id":"W4319299947","doi":"10.1109/wacv56688.2023.00204","title":"A Morphology Focused Diffusion Probabilistic Model for Synthesis of Histopathology Images","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"AI in cancer detection","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Histopathology; Probabilistic logic; Pattern recognition (psychology); Machine learning; Pathology; Medicine","score_opus":0.03419935978624389,"score_gpt":0.2980842172225716,"score_spread":0.2638848574363277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319299947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01398912,0.00001495883,0.9814742,0.0020400065,0.00045708855,0.0012676845,0.0000998454,0.00030460663,0.00035247806],"genre_scores_gemma":[0.8934312,0.000044338107,0.104105905,0.00014397646,0.00010144218,0.0015781841,0.000018371073,0.000035497018,0.0005410925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735105,0.00013180227,0.0008126387,0.00095067016,0.00036637764,0.00038745845],"domain_scores_gemma":[0.9965809,0.0007002353,0.00051838474,0.0014919314,0.0006026198,0.000105953666],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049587403,0.0003013917,0.00058195513,0.00065716,0.00014371882,0.000055868753,0.0016269127,0.00019363224,0.000024818482],"category_scores_gemma":[0.000060472532,0.00029173712,0.00023080228,0.00084392243,0.00028328164,0.00022220828,0.00044359197,0.00019281702,0.0001075254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003324598,0.0010545099,0.00008407015,0.0005810591,0.00007912808,0.000009225509,0.0012427653,0.023638155,0.16312319,0.074211106,0.030881524,0.7047628],"study_design_scores_gemma":[0.0005120933,0.00061158894,0.0008121126,0.00015073299,0.00002860333,0.000011699813,0.000014104694,0.9544379,0.016062483,0.026439453,0.0006447627,0.00027447546],"about_ca_topic_score_codex":0.000018196783,"about_ca_topic_score_gemma":0.000009227619,"teacher_disagreement_score":0.9307997,"about_ca_system_score_codex":0.000110930414,"about_ca_system_score_gemma":0.00016865828,"threshold_uncertainty_score":0.99995345},"labels":[],"label_agreement":null},{"id":"W4320034240","doi":"10.15537/smj.2023.44.2.20220611","title":"The utilization of artificial intelligence applications to improve breast cancer detection and prognosis","year":2023,"lang":"en","type":"review","venue":"Saudi Medical Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Breast cancer; Breast imaging; Workflow; Medical physics; Breast cancer screening; Categorization; Mammography; Breast density; Artificial intelligence; Segmentation; Medical imaging; BI-RADS; Radiology; Cancer; Internal medicine; Computer science","score_opus":0.08669058911099724,"score_gpt":0.3900812840830881,"score_spread":0.30339069497209087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320034240","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.423228e-7,0.42744753,0.57022333,0.00078252424,0.0009885638,0.0004963464,0.000010503539,0.000042655884,0.000008002582],"genre_scores_gemma":[0.0000866956,0.9975221,0.00064029754,0.00003750584,0.0010616842,0.0006099814,7.378839e-7,0.000022384456,0.00001862627],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745,0.0001861685,0.0008642796,0.00036555,0.0008646462,0.0002693556],"domain_scores_gemma":[0.9981546,0.00038173512,0.000603448,0.00030017673,0.00026467824,0.00029536747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013357888,0.00019375996,0.00044831677,0.0002121351,0.0004230982,0.00019403444,0.0009260165,0.00023350772,0.00001672903],"category_scores_gemma":[0.00025645754,0.00012625814,0.00015351798,0.0013726592,0.00014541938,0.00014318617,0.00029532716,0.0007120047,0.000023133336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029695675,0.00001221302,6.55893e-7,0.00070084806,0.00004835828,0.0000015589546,0.000033288994,0.0000024594647,0.0000020843738,0.00046817728,0.00006296659,0.99866444],"study_design_scores_gemma":[0.000059929105,0.00020527585,0.000051748655,0.009867826,0.00033989598,0.0011523601,0.000061867075,0.010180531,0.00012496006,0.009224638,0.9682824,0.00044855083],"about_ca_topic_score_codex":0.000027476697,"about_ca_topic_score_gemma":0.00014518936,"teacher_disagreement_score":0.99821585,"about_ca_system_score_codex":0.00023739846,"about_ca_system_score_gemma":0.00077714934,"threshold_uncertainty_score":0.51486576},"labels":[],"label_agreement":null},{"id":"W4320036947","doi":"10.1007/978-3-031-25082-8_26","title":"CCRL: Contrastive Cell Representation Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Cluster analysis; Machine learning; Feature learning; Representation (politics); Context (archaeology); Identification (biology); Annotation; Unsupervised learning; Margin (machine learning); Supervised learning; Pattern recognition (psychology); Artificial neural network","score_opus":0.02115011942808011,"score_gpt":0.2596260242020277,"score_spread":0.23847590477394756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320036947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054060576,0.00014095737,0.986283,0.00046249662,0.003736078,0.00039508168,0.0000022363542,0.00060726877,0.008318788],"genre_scores_gemma":[0.5517881,0.0003677291,0.42995247,0.0016984058,0.0027176745,0.00008435832,0.000023139726,0.00024491976,0.01312322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958069,0.00006518185,0.0004923277,0.001824014,0.0011674032,0.00064422947],"domain_scores_gemma":[0.99723476,0.00088349753,0.00041264694,0.0010191391,0.00030474056,0.00014522148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008559774,0.00045560062,0.0004466424,0.00092764193,0.00035860503,0.0005581252,0.0022200823,0.0003291902,0.000016827402],"category_scores_gemma":[0.00016689951,0.0004681805,0.00013386793,0.0011277833,0.00047075909,0.00078013656,0.0011681585,0.0012710936,0.00024242775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010116136,0.000015357318,0.00011180357,0.00003976364,0.0000127098465,0.00012386219,0.0014305309,0.19589183,0.0006062008,0.005645021,0.000066986395,0.79604584],"study_design_scores_gemma":[0.00042808347,0.00031944746,0.00035938187,0.00031262042,0.000011870792,0.0000455712,8.872764e-7,0.8415986,0.009701907,0.14497308,0.0014187199,0.00082986796],"about_ca_topic_score_codex":0.00005656015,"about_ca_topic_score_gemma":0.000068933135,"teacher_disagreement_score":0.79521596,"about_ca_system_score_codex":0.00055095955,"about_ca_system_score_gemma":0.0004671556,"threshold_uncertainty_score":0.999777},"labels":[],"label_agreement":null},{"id":"W4321383330","doi":"10.2196/42704","title":"Acceptability of Automated Robotic Clinical Breast Examination: Survey Study","year":2023,"lang":"en","type":"article","venue":"Journal of Participatory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Cancer Research UK","keywords":"Mammography; Breast imaging; Breast cancer; Medicine; Artificial intelligence; Population; Modality (human–computer interaction); Medical physics; Medical education; Family medicine; Computer science; Cancer","score_opus":0.2580258221710583,"score_gpt":0.4671979663763273,"score_spread":0.20917214420526903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321383330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9811283,0.00005614072,0.015299745,0.00052941183,0.0026370175,0.0001640075,0.000001219358,0.00014681446,0.00003736157],"genre_scores_gemma":[0.999317,0.00001133177,0.000258941,0.00003663999,0.00034416525,0.0000045309425,5.65587e-7,0.000008516858,0.000018326946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953342,0.0018137152,0.001548169,0.0002214235,0.0008625914,0.00021989772],"domain_scores_gemma":[0.99668133,0.001085712,0.0007728183,0.0004954137,0.000766824,0.00019788602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016705705,0.00011742169,0.00057276624,0.0002755047,0.00005542402,0.000013131035,0.0006387117,0.000063541294,0.00011986855],"category_scores_gemma":[0.0018248201,0.00008769777,0.000083769024,0.0013837669,0.00020668063,0.00037320508,0.00012959521,0.00028355548,0.000018269226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007159935,0.0006221207,0.95143783,0.000038515496,0.00014194688,0.00008284778,0.003263017,0.002536574,0.0001725718,0.000024608407,0.0041642194,0.03744413],"study_design_scores_gemma":[0.0011236747,0.0016099084,0.93550926,0.000035391306,0.000051363175,0.000058872316,0.00043660085,0.060961008,0.00007786584,0.00005173275,0.000018254214,0.00006606115],"about_ca_topic_score_codex":0.000062396364,"about_ca_topic_score_gemma":0.00009157593,"teacher_disagreement_score":0.058424436,"about_ca_system_score_codex":0.00009831468,"about_ca_system_score_gemma":0.0002136108,"threshold_uncertainty_score":0.5789897},"labels":[],"label_agreement":null},{"id":"W4322739481","doi":"10.1117/12.2672689","title":"Colorectal cancer classification based on histology images: comparison between DNN and CNN","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Pattern recognition (psychology); Set (abstract data type); Moment (physics); Contextual image classification; Machine learning; Image (mathematics)","score_opus":0.05447225367849994,"score_gpt":0.32486645573156553,"score_spread":0.2703942020530656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322739481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34642428,0.000081135164,0.6273511,0.0145924175,0.0014105232,0.0004029107,0.00001118488,0.0011324905,0.00859395],"genre_scores_gemma":[0.99607676,0.000013419009,0.0031560664,0.00026046298,0.000095858784,0.00007412205,0.000005494997,0.000008434276,0.0003093965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897134,0.00006911693,0.00017372187,0.00039833944,0.00018659,0.00020086295],"domain_scores_gemma":[0.9992948,0.00026458595,0.000083178194,0.00024859863,0.000046854013,0.00006197225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019703554,0.000100664794,0.00015317193,0.00017481284,0.00012386595,0.000054374796,0.00027143874,0.00008006812,0.00002980328],"category_scores_gemma":[0.000026057447,0.0000954457,0.00002460956,0.0005067061,0.00007159625,0.00012146249,0.00007096973,0.00013015728,0.000115335264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007078041,0.00007962219,0.273515,0.000060081118,0.000043711247,0.000008488251,0.0007716053,0.0025138503,0.019210463,0.0072484533,0.08423044,0.6122475],"study_design_scores_gemma":[0.00028690323,0.00019123775,0.40322536,0.000009952529,0.0000074352033,8.1995586e-7,0.000027896222,0.57724196,0.011537151,0.0003864217,0.0069411937,0.00014364436],"about_ca_topic_score_codex":0.00018290692,"about_ca_topic_score_gemma":0.00009087822,"teacher_disagreement_score":0.6496525,"about_ca_system_score_codex":0.00024439025,"about_ca_system_score_gemma":0.00008159942,"threshold_uncertainty_score":0.38921624},"labels":[],"label_agreement":null},{"id":"W4323670147","doi":"10.1016/j.heliyon.2023.e14264","title":"Establishing an effective clinical data collecting tool for optimal evaluation of native and allograft renal biopsies","year":2023,"lang":"en","type":"article","venue":"Heliyon","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University; Health Canada; University Health Network","funders":"","keywords":"Medicine; Medical diagnosis; Health care; Kidney; Pathology; Medical physics; Internal medicine","score_opus":0.1691791353720834,"score_gpt":0.4341131860100545,"score_spread":0.2649340506379711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323670147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8217582,0.00023997395,0.17608497,0.00013954732,0.0006368967,0.0008959258,0.000034349032,0.00015236063,0.000057750673],"genre_scores_gemma":[0.94317013,0.00014428225,0.056031052,0.000044601667,0.00032065113,0.00019502507,0.000050805225,0.000016493874,0.000026974009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981734,0.0004016178,0.00029557594,0.0005462052,0.00040470972,0.00017848385],"domain_scores_gemma":[0.9973157,0.0015760342,0.00018406546,0.00049266004,0.00039182356,0.000039718198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006498923,0.00009203936,0.00017640207,0.00016152176,0.00017624436,0.00014015724,0.00046933666,0.00008106953,0.0000018963227],"category_scores_gemma":[0.002670277,0.000091048336,0.000031565494,0.00069152116,0.000067893074,0.0013647862,0.00044013988,0.00012413035,0.0000013750673],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021245539,0.000091248585,0.0055472166,0.00027059056,0.00013127601,0.000002577742,0.0052613714,0.0048387893,0.007264529,0.00042529005,0.0009653489,0.9749893],"study_design_scores_gemma":[0.000944116,0.0006718185,0.030526264,0.0001413767,0.000046373407,0.0000052584196,0.00022002649,0.9601409,0.0061298516,0.0006264932,0.0004101704,0.00013734077],"about_ca_topic_score_codex":0.000022150234,"about_ca_topic_score_gemma":0.00006548038,"teacher_disagreement_score":0.97485197,"about_ca_system_score_codex":0.00007353567,"about_ca_system_score_gemma":0.00012961624,"threshold_uncertainty_score":0.37128434},"labels":[],"label_agreement":null},{"id":"W4324056392","doi":"10.3390/curroncol30030251","title":"The Potential of Adding Mammography to Handheld Ultrasound or Automated Breast Ultrasound to Reduce Unnecessary Biopsies in BI-RADS Ultrasound Category 4a: A Multicenter Hospital-Based Study in China","year":2023,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"GE Healthcare","keywords":"Medicine; Mammography; Biopsy; Ultrasound; Radiology; Logistic regression; Breast ultrasound; BI-RADS; Breast cancer; Cancer; Internal medicine","score_opus":0.02767381926076122,"score_gpt":0.3432715318367426,"score_spread":0.31559771257598135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324056392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98817325,0.00018287307,0.0033199326,0.0011474706,0.004747479,0.0018502943,0.000051267594,0.0004947691,0.000032654287],"genre_scores_gemma":[0.9984662,0.00007746836,0.0006560706,0.00006229948,0.00013986962,0.0005275501,0.000018110328,0.00003561481,0.000016799944],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960662,0.00061150413,0.0008956757,0.0009903895,0.00054025685,0.00089598104],"domain_scores_gemma":[0.9969849,0.0015258134,0.00029703407,0.00081249117,0.00017240123,0.0002073836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013081506,0.00039616754,0.00055820623,0.001339439,0.00027345849,0.00019453792,0.0014495518,0.00016784383,0.000015429123],"category_scores_gemma":[0.0005836165,0.0003166211,0.00013179191,0.00527755,0.00018920942,0.00035305988,0.0003132773,0.0005048579,0.000040859995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031392362,0.009500212,0.7544639,0.00041425013,0.0003704328,0.00042678323,0.03730181,0.027466226,0.07423761,0.00018739927,0.011858048,0.08063409],"study_design_scores_gemma":[0.0029983264,0.0021514853,0.98011726,0.00022874847,0.00003630548,0.000065271124,0.003071789,0.0075710737,0.0022793573,0.00011563265,0.00082911574,0.0005356429],"about_ca_topic_score_codex":0.0005805196,"about_ca_topic_score_gemma":0.003094823,"teacher_disagreement_score":0.22565335,"about_ca_system_score_codex":0.0006210796,"about_ca_system_score_gemma":0.00038410365,"threshold_uncertainty_score":0.9999286},"labels":[],"label_agreement":null},{"id":"W4353080404","doi":"10.54097/hset.v34i.5388","title":"Breast Cancer Prediction Based on the CNN Models","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Breast cancer; Margin (machine learning); Medical diagnosis; Deep learning; Artificial intelligence; Computer science; Cancer; Residual neural network; Machine learning; Pattern recognition (psychology); Medicine; Internal medicine; Radiology","score_opus":0.010397495251094416,"score_gpt":0.21177538505510102,"score_spread":0.20137788980400662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353080404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4565897,0.00018054759,0.4133759,0.11745699,0.0045648892,0.00064128934,0.000024712459,0.005985981,0.0011799762],"genre_scores_gemma":[0.998556,0.000083818726,0.0011590476,0.000034129607,0.00003592598,0.00010231664,1.3485322e-7,0.000005819141,0.000022766464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989138,0.000007603107,0.00011285597,0.00039427239,0.0002607225,0.00031074331],"domain_scores_gemma":[0.99940234,0.00006731636,0.00002621304,0.0004249491,0.000044763394,0.000034442615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043758663,0.0000962317,0.000080190526,0.0009846383,0.00018432015,0.00006615718,0.0006943391,0.00007911425,0.0000013683937],"category_scores_gemma":[0.000024987961,0.00006749058,0.000010635812,0.0046131304,0.00020875534,0.00033063258,0.00014856832,0.00018299175,0.000023862782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002203917,0.000011323072,0.00021473496,0.000006906829,0.0000020620307,0.000007846632,0.0001078628,0.3983913,0.005899407,0.5842027,0.00024369055,0.010909908],"study_design_scores_gemma":[0.000085294756,0.000028556278,0.0020833656,0.000041803323,8.0344483e-7,0.000012784823,0.000011614632,0.98649204,0.006611052,0.003806407,0.0007486131,0.00007768566],"about_ca_topic_score_codex":0.000019428277,"about_ca_topic_score_gemma":0.0000051544835,"teacher_disagreement_score":0.58810073,"about_ca_system_score_codex":0.0001298244,"about_ca_system_score_gemma":0.00007425403,"threshold_uncertainty_score":0.2752186},"labels":[],"label_agreement":null},{"id":"W4360600249","doi":"10.1177/09622802231160551","title":"Identifying regions of interest in mammogram images","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Mammography; Computer science; Bivariate analysis; Lasso (programming language); Artificial intelligence; Breast cancer screening; Noise (video); Boundary (topology); Domain (mathematical analysis); Medicine; Triangulation; Region of interest; Segmentation; Data mining; Pattern recognition (psychology); Cancer; Machine learning; Mathematics; Image (mathematics); Internal medicine","score_opus":0.5030285996736024,"score_gpt":0.6263801075811303,"score_spread":0.12335150790752791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360600249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015858888,0.000079389734,0.99330866,0.0029864558,0.00037855151,0.00018970983,0.0000055874316,0.00007214262,0.0013936103],"genre_scores_gemma":[0.15329978,0.000281884,0.8460659,0.00004101368,0.000055271194,0.00010720881,0.0000023088865,0.000013448696,0.0001331864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99304634,0.0038782316,0.00058570254,0.0005283668,0.0012390334,0.00072229846],"domain_scores_gemma":[0.9824234,0.016584922,0.000042141135,0.00051524746,0.00015055898,0.00028370338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021356212,0.000092647024,0.00027806518,0.0011056,0.000059949398,0.00006391584,0.0012891163,0.00015823016,0.00023433295],"category_scores_gemma":[0.03914593,0.000085713415,0.000033963104,0.00449525,0.0007515411,0.0001536279,0.0011057463,0.0014781159,0.000061107006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014271106,0.000051341474,0.00042801048,0.0000944384,0.0000037346983,0.0003442916,0.00026376484,0.0000030795338,0.00067121297,0.20658253,0.0019348023,0.78960854],"study_design_scores_gemma":[0.00043875733,0.00018476126,0.02993028,0.00041814923,0.0000012837611,0.000013836659,0.00034267383,0.091228075,0.0029897694,0.87304884,0.0012740706,0.0001294837],"about_ca_topic_score_codex":0.0004991566,"about_ca_topic_score_gemma":0.00041260876,"teacher_disagreement_score":0.789479,"about_ca_system_score_codex":0.00017818245,"about_ca_system_score_gemma":0.0003127251,"threshold_uncertainty_score":0.96894777},"labels":[],"label_agreement":null},{"id":"W4360989162","doi":"10.18280/ria.370106","title":"Optimization of Breast Cancer Classification Using Faster R-CNN","year":2023,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Computer science; Artificial intelligence; Pattern recognition (psychology); Cancer; Medicine; Internal medicine","score_opus":0.12871134035839205,"score_gpt":0.32892071452358856,"score_spread":0.20020937416519652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010620038,0.001338368,0.97463685,0.006617105,0.0052563106,0.00038178705,0.000058609305,0.00018416128,0.00090673973],"genre_scores_gemma":[0.96530956,0.002960039,0.017463686,0.00013255206,0.00082858943,0.00006380389,0.000016001333,0.000071632734,0.013154154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973607,0.00016972693,0.0008379692,0.0007143519,0.0003746075,0.0005426675],"domain_scores_gemma":[0.99781126,0.00015348326,0.00049525284,0.00083698914,0.0005803025,0.00012274292],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063855195,0.0002542419,0.00030446152,0.00034912364,0.00023200676,0.00015539475,0.0006534943,0.00023049237,0.00083705044],"category_scores_gemma":[0.0000580466,0.00030347775,0.00015279124,0.0032667234,0.00027786163,0.000963957,0.00023705626,0.00025206225,0.00061111216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015431238,0.00006988135,0.000378775,0.00021898246,0.000024068475,0.0000048604265,0.0017527608,0.8421478,0.008855463,0.003546254,0.0005780199,0.1424077],"study_design_scores_gemma":[0.000039394778,0.00005685954,0.000556811,0.00059388427,0.00004050509,0.000055580305,0.0006501415,0.9617488,0.033022683,0.0006342958,0.002322965,0.00027808],"about_ca_topic_score_codex":0.00061244774,"about_ca_topic_score_gemma":0.0000348149,"teacher_disagreement_score":0.95717317,"about_ca_system_score_codex":0.0003765144,"about_ca_system_score_gemma":0.00026131183,"threshold_uncertainty_score":0.9999417},"labels":[],"label_agreement":null},{"id":"W4361288163","doi":"10.1016/j.eswa.2023.119972","title":"Multiresolution texture analysis of histopathologic images using ecological diversity measures","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Texture (cosmology); Artificial intelligence; Pattern recognition (psychology); Computer science; Fixation (population genetics); Wavelet; Image (mathematics); Computer vision; Wavelet transform; Biology","score_opus":0.048090713525796434,"score_gpt":0.28626409642895634,"score_spread":0.2381733829031599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361288163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01486108,0.000406694,0.9833285,0.00012834823,0.0001113675,0.0004573544,0.00001404646,0.00038845604,0.00030415523],"genre_scores_gemma":[0.9894137,0.000026694946,0.010038697,0.000023246776,0.00005491492,0.00030525622,0.00000900702,0.000005189335,0.0001233328],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879915,0.00010019327,0.00021007302,0.00039686335,0.00031733245,0.00017641128],"domain_scores_gemma":[0.99892396,0.0000812297,0.00019511368,0.0005723565,0.0001749566,0.000052381303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029555673,0.00010767817,0.00024006152,0.00036411316,0.0004511657,0.000034420085,0.000495212,0.00008586492,0.000004276054],"category_scores_gemma":[0.000016598984,0.0000856593,0.00008088938,0.0027317777,0.00009036523,0.00017303826,0.0002778742,0.00007684849,0.00001769156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013622701,0.0013373252,0.17288034,0.00030249887,0.0027561132,0.00009141281,0.02053486,0.48764512,0.20478126,0.03780482,0.019163843,0.052566182],"study_design_scores_gemma":[0.00039190566,0.0001449233,0.1695912,0.00003248594,0.00029922437,0.00003320493,0.00072127697,0.8169478,0.001352256,0.00023063025,0.009794886,0.00046016977],"about_ca_topic_score_codex":0.0006429604,"about_ca_topic_score_gemma":0.00005043658,"teacher_disagreement_score":0.9745526,"about_ca_system_score_codex":0.00025247078,"about_ca_system_score_gemma":0.000036250258,"threshold_uncertainty_score":0.34930852},"labels":[],"label_agreement":null},{"id":"W4361823676","doi":"10.1158/1055-9965.c.6514878.v1","title":"Data from Assessment of Automated Image Analysis of Breast Cancer Tissue Microarrays for Epidemiologic Studies","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Tissue microarray; Breast cancer; Medicine; Aromatase; Internal medicine; Categorical variable; Estrogen receptor; Oncology; Cancer; Immunohistochemistry; Pathology; Mathematics","score_opus":0.24230178507818634,"score_gpt":0.4906077444840348,"score_spread":0.2483059594058485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361823676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005694338,0.0008635652,0.97493756,0.0018789629,0.0015506466,0.0006237429,0.01367004,0.00072126207,0.00005991004],"genre_scores_gemma":[0.21128497,0.002182578,0.7841857,0.00011513534,0.00017443404,0.00043044044,0.0013665127,0.000035356203,0.0002248416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968103,0.00022645033,0.0010247625,0.0013558909,0.00031872487,0.00026383036],"domain_scores_gemma":[0.9938511,0.0012997495,0.0012107538,0.0029735728,0.0006181108,0.000046666908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015061751,0.0002990385,0.0014965838,0.00046744643,0.000054899392,0.000041086798,0.0030130667,0.00021686048,0.00006361041],"category_scores_gemma":[0.0001862856,0.0002484968,0.00023613786,0.0010630079,0.00014687731,0.00021964463,0.005648224,0.00022321973,0.0000027580402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012706206,0.0006608455,0.04318843,0.004727242,0.101515576,0.000019829813,0.0019881267,0.3790409,0.12065046,0.002476282,0.28624925,0.059356],"study_design_scores_gemma":[0.00014065635,0.000039001265,0.102289066,0.0001385346,0.0013174014,3.4169247e-7,0.00007973675,0.89096105,0.0027226463,0.0019682278,0.00011421328,0.00022910647],"about_ca_topic_score_codex":0.009701419,"about_ca_topic_score_gemma":0.0033189557,"teacher_disagreement_score":0.51192015,"about_ca_system_score_codex":0.00025106192,"about_ca_system_score_gemma":0.00034038667,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W4361824099","doi":"10.1158/1055-9965.c.6514878","title":"Data from Assessment of Automated Image Analysis of Breast Cancer Tissue Microarrays for Epidemiologic Studies","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Tissue microarray; Breast cancer; Medicine; Internal medicine; Aromatase; Categorical variable; Estrogen receptor; Cancer; Oncology; Immunohistochemistry; Pathology; Mathematics","score_opus":0.24230178507818634,"score_gpt":0.4906077444840348,"score_spread":0.2483059594058485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361824099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005694338,0.0008635652,0.97493756,0.0018789629,0.0015506466,0.0006237429,0.01367004,0.00072126207,0.00005991004],"genre_scores_gemma":[0.21128497,0.002182578,0.7841857,0.00011513534,0.00017443404,0.00043044044,0.0013665127,0.000035356203,0.0002248416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968103,0.00022645033,0.0010247625,0.0013558909,0.00031872487,0.00026383036],"domain_scores_gemma":[0.9938511,0.0012997495,0.0012107538,0.0029735728,0.0006181108,0.000046666908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015061751,0.0002990385,0.0014965838,0.00046744643,0.000054899392,0.000041086798,0.0030130667,0.00021686048,0.00006361041],"category_scores_gemma":[0.0001862856,0.0002484968,0.00023613786,0.0010630079,0.00014687731,0.00021964463,0.005648224,0.00022321973,0.0000027580402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012706206,0.0006608455,0.04318843,0.004727242,0.101515576,0.000019829813,0.0019881267,0.3790409,0.12065046,0.002476282,0.28624925,0.059356],"study_design_scores_gemma":[0.00014065635,0.000039001265,0.102289066,0.0001385346,0.0013174014,3.4169247e-7,0.00007973675,0.89096105,0.0027226463,0.0019682278,0.00011421328,0.00022910647],"about_ca_topic_score_codex":0.009701419,"about_ca_topic_score_gemma":0.0033189557,"teacher_disagreement_score":0.51192015,"about_ca_system_score_codex":0.00025106192,"about_ca_system_score_gemma":0.00034038667,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W4362456932","doi":"10.3390/cancers15072079","title":"Semi-Supervised Learning to Automate Tumor Bud Detection in Cytokeratin-Stained Whole-Slide Images of Colorectal Cancer","year":2023,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Swiss Cancer Research Foundation; KWF Kankerbestrijding","keywords":"Artificial intelligence; Computer science; Tumor budding; Convolutional neural network; Colorectal cancer; Machine learning; Deep learning; Cancer; Medicine; Metastasis","score_opus":0.011444058623971038,"score_gpt":0.26261467608165096,"score_spread":0.25117061745767993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362456932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97294223,0.000081617014,0.023824172,0.0005209709,0.0012119625,0.0004077569,0.000013601758,0.0006880427,0.00030965338],"genre_scores_gemma":[0.99766624,0.00004068288,0.0013382509,0.00016834411,0.00010602262,0.00036786663,0.0000026136024,0.00002917533,0.00028082498],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99820226,0.00011477911,0.00035626028,0.0005216765,0.00033708886,0.00046791128],"domain_scores_gemma":[0.99923617,0.00009695747,0.00015000424,0.00026657467,0.00013533221,0.00011497077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003894179,0.00019130092,0.00027262542,0.0004333964,0.00014391913,0.00008018149,0.0004518642,0.000064956104,0.000022309083],"category_scores_gemma":[0.00009178952,0.00021177808,0.00006776619,0.0023275476,0.00005347776,0.00043863655,0.00019143874,0.00025943498,0.000048617923],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009114972,0.0000054542625,0.0023908238,0.00008362164,0.000022385442,0.00003160607,0.00333295,0.40427378,0.53062046,0.000026729313,0.00090993673,0.05821115],"study_design_scores_gemma":[0.00058522704,0.00023677229,0.014984001,0.00012242918,0.000006135954,0.0000056432227,0.00050521863,0.4798679,0.5016049,0.000056805693,0.0017627734,0.00026218678],"about_ca_topic_score_codex":0.002399823,"about_ca_topic_score_gemma":0.001713732,"teacher_disagreement_score":0.07559414,"about_ca_system_score_codex":0.0024295999,"about_ca_system_score_gemma":0.00060517807,"threshold_uncertainty_score":0.8636059},"labels":[],"label_agreement":null},{"id":"W4362471337","doi":"10.1200/cci.22.00182","title":"Developing a Data and Analytics Platform to Enable a Breast Cancer Learning Health System at a Regional Cancer Center","year":2023,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group; University of Toronto; Hamilton Health Sciences; Institute for Work & Health; McMaster University; Population Health Research Institute","funders":"","keywords":"Center (category theory); Cancer; Breast cancer; Analytics; Data science; Medicine; Computer science; Internal medicine","score_opus":0.2451775432343702,"score_gpt":0.4387868475491681,"score_spread":0.1936093043147979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362471337","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19818991,0.0031004944,0.6372416,0.13231239,0.015812969,0.004380435,0.002883512,0.0043792343,0.0016994666],"genre_scores_gemma":[0.7103922,0.058995586,0.13403995,0.08004979,0.0076373373,0.002438683,0.00054559985,0.00038846122,0.0055123987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99612814,0.00008238204,0.001604781,0.0005730448,0.00078605703,0.0008256136],"domain_scores_gemma":[0.99713695,0.00035559834,0.0007712099,0.0009941533,0.00026244373,0.000479674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019487757,0.00030217608,0.0006139613,0.00025564528,0.00054165226,0.00027877322,0.0013693569,0.000176353,0.000023652019],"category_scores_gemma":[0.000098578574,0.00027467063,0.00008458526,0.0015018304,0.000092494716,0.0013346446,0.0025672961,0.0005742463,0.00009041807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030130817,0.00005648003,0.16415747,0.0030417466,0.00044554236,0.000017412127,0.010419272,0.029187651,0.0000031929703,0.003384,0.19413139,0.59485453],"study_design_scores_gemma":[0.0010685242,0.00011425716,0.011741479,0.0012629671,0.000029259578,0.00006673971,0.00087634666,0.7125806,0.000009592553,0.000087419474,0.27167925,0.00048354492],"about_ca_topic_score_codex":0.0016381833,"about_ca_topic_score_gemma":0.0033186395,"teacher_disagreement_score":0.68339294,"about_ca_system_score_codex":0.0021600958,"about_ca_system_score_gemma":0.0016923363,"threshold_uncertainty_score":0.99997056},"labels":[],"label_agreement":null},{"id":"W4362486869","doi":"10.1117/12.2654104","title":"Self-supervised learning and uncertainty estimation for surgical margin detection","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Margin (machine learning); Autoencoder; Supervised learning; Deep learning","score_opus":0.014312111477946041,"score_gpt":0.2674790710469064,"score_spread":0.25316695956896035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362486869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060882345,0.000017164442,0.9359356,0.00054378813,0.00031013542,0.00026608646,3.7670856e-7,0.0013973578,0.00064711744],"genre_scores_gemma":[0.9278535,0.000042980075,0.071279235,0.000026779298,0.00008625344,0.00010897395,0.0000040846307,0.00001047569,0.00058770966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992427,0.000045834935,0.00011892595,0.0002795876,0.00013640113,0.00017650981],"domain_scores_gemma":[0.9995374,0.00021680992,0.000034799403,0.00011318792,0.000051003033,0.000046773148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038754867,0.000076836084,0.00007990964,0.00011254887,0.00021024396,0.00010902645,0.000107802,0.000058122478,0.0000075281846],"category_scores_gemma":[0.000044744236,0.00007276393,0.00003142692,0.0004717662,0.000012492416,0.0003215046,0.000077560166,0.0000833765,0.000030748804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030314459,0.000011245966,0.00025683155,0.0000743677,0.000015057259,0.0000037263715,0.0004365574,0.013506137,0.0007080819,0.003833583,0.00018758547,0.9809365],"study_design_scores_gemma":[0.0005145638,0.00012038329,0.00034842087,0.000004680015,0.0000036506028,0.000016035656,0.00003587504,0.98297834,0.002044138,0.001856946,0.011982788,0.00009419715],"about_ca_topic_score_codex":0.00002744353,"about_ca_topic_score_gemma":0.000020235186,"teacher_disagreement_score":0.9808423,"about_ca_system_score_codex":0.00007790609,"about_ca_system_score_gemma":0.000021271702,"threshold_uncertainty_score":0.29672268},"labels":[],"label_agreement":null},{"id":"W4362594696","doi":"10.1158/1538-7445.am2023-5695","title":"Abstract 5695: Deep learning risk prediction model of distant recurrence from H&amp;E endometrial cancer slides","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Vancouver General Hospital","funders":"","keywords":"Medicine; Concordance; Artificial intelligence; Endometrial cancer; Risk stratification; Internal medicine; Cutoff; Oncology; Machine learning; Cancer; Computer science","score_opus":0.16388003217323344,"score_gpt":0.4123272824228798,"score_spread":0.24844725024964637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362594696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81560266,0.0025513691,0.17760451,0.00030190783,0.0022567164,0.0005244227,0.00034825006,0.00041633644,0.00039381842],"genre_scores_gemma":[0.98594123,0.0108638685,0.0017285505,0.0000066563634,0.000620955,0.00048388363,0.000018260967,0.000031031206,0.0003055732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960935,0.0003273251,0.00047545004,0.00082368887,0.0015792925,0.000700746],"domain_scores_gemma":[0.9973108,0.0010038716,0.0002551008,0.00069904374,0.0005548042,0.00017637094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022688431,0.00017968593,0.0002817239,0.00068848475,0.00044982735,0.00016692624,0.0011045777,0.00014376813,0.00016319806],"category_scores_gemma":[0.0009557746,0.00017663471,0.000106583,0.0032733763,0.00021066777,0.0006356071,0.00048192884,0.0011738032,0.00008562738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039157592,0.00005848033,0.010941951,0.00012716056,0.00013051971,0.0000066623516,0.004286874,0.33607593,0.102995835,0.00036273044,0.003596962,0.54102534],"study_design_scores_gemma":[0.0015203909,0.00023900159,0.019781182,0.0004421075,0.00002697823,8.256583e-7,0.00030096906,0.8855373,0.0691032,0.014058743,0.008555128,0.0004341503],"about_ca_topic_score_codex":0.009461012,"about_ca_topic_score_gemma":0.0015236543,"teacher_disagreement_score":0.5494614,"about_ca_system_score_codex":0.0008223379,"about_ca_system_score_gemma":0.00057743624,"threshold_uncertainty_score":0.99713504},"labels":[],"label_agreement":null},{"id":"W4362604473","doi":"10.1117/12.2654280","title":"Self-supervised learning enhanced ultrasound video thyroid nodule tracking","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Computer science; Nodule (geology); Ultrasound; Computer vision; Artificial intelligence; Thyroid; Tracking (education); Thyroid nodules; Radiology; Medicine; Internal medicine; Psychology; Biology","score_opus":0.014602150709377681,"score_gpt":0.24563211181222444,"score_spread":0.23102996110284676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362604473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17255294,0.000047033594,0.80304253,0.0004719513,0.00089632376,0.00018226873,3.3905562e-7,0.0044208155,0.018385803],"genre_scores_gemma":[0.96168256,0.00007141293,0.03592814,0.0002021572,0.00017651037,0.000031471645,0.0000022603003,0.000021725047,0.0018837572],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984196,0.00008324092,0.00021412503,0.00051649334,0.00035738584,0.0004091804],"domain_scores_gemma":[0.99901456,0.00030612102,0.000065616034,0.00044764974,0.00008421933,0.000081833496],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004278358,0.00014874211,0.00014163853,0.00015772495,0.0002950308,0.00027344943,0.0006341594,0.00007576194,0.00008317862],"category_scores_gemma":[0.000114550516,0.00014643208,0.000075212214,0.0012853123,0.00001966887,0.00084028987,0.00016345744,0.0002541516,0.0010519071],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017278817,0.00008211388,0.0018540461,0.00010147499,0.00009709565,0.000031505013,0.011617413,0.00989245,0.69351757,0.005307044,0.004631848,0.2728502],"study_design_scores_gemma":[0.0008621387,0.00030912907,0.006735416,0.00003601498,0.000012868874,0.000039392195,0.0005617373,0.48086804,0.49398702,0.002700552,0.01319353,0.0006941673],"about_ca_topic_score_codex":0.000032332933,"about_ca_topic_score_gemma":0.000022840628,"teacher_disagreement_score":0.7891296,"about_ca_system_score_codex":0.000118514676,"about_ca_system_score_gemma":0.00005463308,"threshold_uncertainty_score":0.9997259},"labels":[],"label_agreement":null},{"id":"W4362670222","doi":"10.54097/hset.v41i.6747","title":"ML Classification Methods Comparison for Breast Cancer Diagnosis in Clinical Application Field","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Field (mathematics); Deep learning; Artificial intelligence; Breast cancer; Machine learning; CAD; Cancer detection; Cancer; Pattern recognition (psychology); Medicine; Engineering","score_opus":0.03834364278375412,"score_gpt":0.3933924767144641,"score_spread":0.35504883393070996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362670222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13722573,0.00014657038,0.8433369,0.017319001,0.0009890129,0.00034775655,0.000003531246,0.00061056623,0.00002095565],"genre_scores_gemma":[0.9347594,0.0003407043,0.06369726,0.000023312497,0.000046825542,0.0011204677,4.1940785e-7,0.000005903892,0.0000057121565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869406,0.00001924512,0.0003351352,0.0005404753,0.00011889302,0.0002922095],"domain_scores_gemma":[0.9990751,0.00039297598,0.000073526586,0.00035888833,0.00005954412,0.00003993222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013216558,0.000090591755,0.00017679347,0.0010293142,0.000080536876,0.000043263557,0.00060194003,0.00016667105,6.5927986e-7],"category_scores_gemma":[0.00020528494,0.000086910935,0.000017049417,0.0039622984,0.00013314537,0.00026476494,0.00015083095,0.00019194603,0.0000064280925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004584122,0.000038506892,0.039699484,0.00002272264,0.0000028644204,0.0000010589972,0.00013684035,0.0022232581,0.007690983,0.19825628,0.0002447936,0.75167865],"study_design_scores_gemma":[0.00021125562,0.00005449584,0.10729371,0.000034761404,0.0000018135746,0.000003974098,0.000025494472,0.8641729,0.01628704,0.0032934274,0.008491953,0.0001291901],"about_ca_topic_score_codex":0.000047330104,"about_ca_topic_score_gemma":0.00006866063,"teacher_disagreement_score":0.8619496,"about_ca_system_score_codex":0.00012488791,"about_ca_system_score_gemma":0.00005592141,"threshold_uncertainty_score":0.3544125},"labels":[],"label_agreement":null},{"id":"W4362693492","doi":"10.1117/12.2654040","title":"A novel H and E color augmentation for domain invariance classification of unannotated histopathology prostate cancer images","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Normalization (sociology); Color space; Pattern recognition (psychology); Robustness (evolution); Random forest; Deep learning; Generalization; Artificial neural network; Mathematics; Image (mathematics)","score_opus":0.034616229861945756,"score_gpt":0.3047997518472347,"score_spread":0.27018352198528894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362693492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18766275,0.000047293754,0.8074235,0.0036177263,0.0003663866,0.0005565488,0.000028794826,0.00017224396,0.00012478502],"genre_scores_gemma":[0.87036103,0.000117805896,0.12713379,0.00020352702,0.000033546436,0.0008884754,0.000016898708,0.000013521764,0.0012314231],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992511,0.000026162686,0.00019661007,0.00029039828,0.000097234515,0.00013846786],"domain_scores_gemma":[0.9994304,0.00008734646,0.00015732464,0.00016575083,0.00013441389,0.000024744293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028539347,0.00007053751,0.00010337428,0.00011397508,0.00007379783,0.000026485768,0.00014431182,0.000040867148,0.0000031362335],"category_scores_gemma":[0.00002795262,0.00006788174,0.000016741218,0.000491587,0.0000700951,0.00030161443,0.00005568275,0.00003486641,0.000003119035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006647209,0.00002321969,0.000989835,0.000071419585,0.0000073703386,7.8420334e-7,0.0012675499,0.0002504909,0.94515395,0.022641731,0.0018581885,0.027668994],"study_design_scores_gemma":[0.0035578075,0.00061550626,0.44114357,0.00006516462,0.000025808697,0.00002384031,0.0004819621,0.36371544,0.16421938,0.02068774,0.0050531514,0.00041061043],"about_ca_topic_score_codex":0.00010202409,"about_ca_topic_score_gemma":0.000115824325,"teacher_disagreement_score":0.7809346,"about_ca_system_score_codex":0.00010918975,"about_ca_system_score_gemma":0.00007834008,"threshold_uncertainty_score":0.2768137},"labels":[],"label_agreement":null},{"id":"W4362693576","doi":"10.1117/12.2654599","title":"Ki67 proliferation index quantification using silver standard masks","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; University Health Network","funders":"","keywords":"Computer science; Deep learning; Consistency (knowledge bases); Artificial intelligence; Set (abstract data type); Gold standard (test); Software; Training set; Pattern recognition (psychology); Machine learning; Operating system; Mathematics; Statistics","score_opus":0.05397665118970082,"score_gpt":0.309109633334395,"score_spread":0.2551329821446942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362693576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06450922,0.0000075787248,0.93238723,0.00075618963,0.0006804298,0.00017926867,0.0000010471819,0.00065989944,0.00081915397],"genre_scores_gemma":[0.9838404,0.0000053192134,0.015346466,0.00011253279,0.000104271436,0.000017892535,0.0000032792761,0.000008689087,0.0005611442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901724,0.000038840913,0.00016341485,0.00029301288,0.000322295,0.0001652053],"domain_scores_gemma":[0.9994023,0.000025332114,0.00006232323,0.0003654733,0.00010819425,0.000036377864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033349948,0.000073718795,0.00006958192,0.00015716003,0.0001517887,0.00019157979,0.00023360265,0.000056966088,0.00002554952],"category_scores_gemma":[0.000023517903,0.000071010494,0.000026110478,0.0008633917,0.000016910568,0.00069660606,0.00008275269,0.00007357798,0.00015326336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014464218,0.000088769986,0.038105525,0.00014110713,0.000101568796,0.000022647624,0.0038030322,0.12685156,0.20749049,0.16719505,0.026387792,0.4296678],"study_design_scores_gemma":[0.00014212371,0.000036650195,0.0058436682,0.000008077234,0.0000027905996,0.0000046181267,0.000026765838,0.95000225,0.0375445,0.0034081447,0.0028631263,0.00011726372],"about_ca_topic_score_codex":0.00004207777,"about_ca_topic_score_gemma":0.000030273019,"teacher_disagreement_score":0.9193312,"about_ca_system_score_codex":0.00015808882,"about_ca_system_score_gemma":0.00009429607,"threshold_uncertainty_score":0.2895724},"labels":[],"label_agreement":null},{"id":"W4362694365","doi":"10.1117/12.2651349","title":"Deep modality association learning using histopathology images and immune cell sequencing data","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MaRS; University of Waterloo","funders":"","keywords":"Histopathology; Modality (human–computer interaction); Computer science; Pattern recognition (psychology); Discriminative model; Artificial intelligence; T-cell receptor; Modalities; Computational biology; Biology; Pathology; Immune system; T cell; Medicine; Immunology","score_opus":0.053266252589240184,"score_gpt":0.28539612965957006,"score_spread":0.2321298770703299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362694365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122149974,0.00018379815,0.8746717,0.0007173175,0.00045261273,0.00006429979,0.0000011330902,0.0004623434,0.0012968121],"genre_scores_gemma":[0.93069565,0.000067384986,0.06788759,0.000078455945,0.00006897741,0.0000027233687,0.000007761996,0.000009652863,0.0011818124],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889714,0.0001443107,0.00017258273,0.0003979731,0.00017419149,0.00021378402],"domain_scores_gemma":[0.9991615,0.00012127961,0.00014536601,0.00047578392,0.00006782969,0.00002825098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013124838,0.000073828254,0.00010856472,0.000086761815,0.00021592918,0.00010124827,0.00041318272,0.000064985164,0.0000065679965],"category_scores_gemma":[0.0002024672,0.00007867749,0.00001454098,0.0003637657,0.000018293958,0.000778846,0.0008285583,0.00017245596,0.000023539842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008986902,0.00002160876,0.04368408,0.00012848612,0.00002657651,0.00008166105,0.0034634024,0.051181234,0.78178084,0.0015401858,0.0010061702,0.11707678],"study_design_scores_gemma":[0.00010870883,0.00001738237,0.011448019,0.0000053496547,0.000006362247,0.000013786395,0.00009894329,0.978157,0.008603887,0.0012311883,0.00020575036,0.00010362771],"about_ca_topic_score_codex":0.00045228886,"about_ca_topic_score_gemma":0.00002338609,"teacher_disagreement_score":0.9269758,"about_ca_system_score_codex":0.00053092,"about_ca_system_score_gemma":0.000058355854,"threshold_uncertainty_score":0.3208375},"labels":[],"label_agreement":null},{"id":"W4362694529","doi":"10.1117/12.2654943","title":"Identification of molecular cell type of breast cancer on digital histopathology images using deep learning and multiplexed fluorescence imaging","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Breast cancer; Estrogen receptor; Cancer; Immunohistochemistry; Stain; Histopathology; Pathology; Progesterone receptor; Artificial intelligence; Computer science; Medicine; Staining; Internal medicine","score_opus":0.011526036211141052,"score_gpt":0.2681623755411702,"score_spread":0.2566363393300291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362694529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67973936,0.00022390365,0.31914142,0.00012211173,0.000320524,0.00010636844,0.0000041245303,0.00013043346,0.00021178964],"genre_scores_gemma":[0.99590045,0.000041522853,0.003953326,0.000009460084,0.000011723188,0.0000031202526,0.0000011138862,0.00000913336,0.00007014364],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999191,0.00003707634,0.00020688886,0.00027490576,0.00015786027,0.00013230818],"domain_scores_gemma":[0.999421,0.00004497149,0.00017728335,0.0001854131,0.00014564657,0.000025660043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001402243,0.00007788837,0.00010923888,0.00016242929,0.000051058305,0.00004060433,0.00017807829,0.000025827858,0.000004741313],"category_scores_gemma":[0.000035453322,0.00007994114,0.000024188894,0.0004529286,0.00008527269,0.00032354656,0.0001319637,0.000076476994,0.0000046817513],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000933079,0.000010203646,0.009423948,0.00003077263,0.000001929172,0.0000051178386,0.00022964168,0.0038321563,0.9265281,0.00006803583,0.0000048831507,0.059855912],"study_design_scores_gemma":[0.0001617641,0.000031500265,0.033414945,0.000027330134,0.0000064956675,0.000016698981,0.00008490142,0.53816855,0.42781362,0.00015861743,0.000011430673,0.000104135266],"about_ca_topic_score_codex":0.00008648635,"about_ca_topic_score_gemma":0.0000023200187,"teacher_disagreement_score":0.5343364,"about_ca_system_score_codex":0.0000628855,"about_ca_system_score_gemma":0.000026496826,"threshold_uncertainty_score":0.3259905},"labels":[],"label_agreement":null},{"id":"W4365447539","doi":"10.1038/s41598-023-33348-z","title":"Generalization of vision pre-trained models for histopathology","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Waterloo","funders":"Government of Ontario; Mayo Clinic","keywords":"Computer science; Artificial intelligence; Generalization; Machine learning; Histopathology; Convolutional neural network; Pattern recognition (psychology); Mathematics; Pathology; Medicine","score_opus":0.02463649158646424,"score_gpt":0.29035481381181694,"score_spread":0.2657183222253527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365447539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07862447,0.000036800495,0.90974826,0.00021630194,0.0104925595,0.00032708675,0.0000013494058,0.00026024724,0.00029290386],"genre_scores_gemma":[0.9659537,0.0000038743938,0.029641995,0.000022636286,0.000062829786,0.00007883902,0.000033778077,0.000011392727,0.004190936],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984189,0.000044122,0.00038274593,0.0006222082,0.00033333464,0.00019863709],"domain_scores_gemma":[0.99855006,0.000038079565,0.00029147704,0.0008305469,0.0002490831,0.00004075589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002026979,0.00007223559,0.00012006067,0.00028802524,0.00017981156,0.0000880706,0.00024558775,0.000056260633,0.0000042942643],"category_scores_gemma":[0.000106873726,0.0000703305,0.00006781482,0.0010394013,0.00009601264,0.00047346266,0.00012005173,0.000029544737,0.000004060182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030053558,0.000089939735,0.0003934889,0.00016498583,0.000010509382,0.00010432044,0.003832225,0.19703875,0.6148777,0.020430274,0.106692575,0.056335162],"study_design_scores_gemma":[0.000096393676,0.000075594224,0.0010243871,0.000015302281,0.0000045886572,0.00006321881,0.000006615996,0.7544427,0.038705435,0.19545355,0.010010693,0.00010150464],"about_ca_topic_score_codex":0.000009676262,"about_ca_topic_score_gemma":0.000008630813,"teacher_disagreement_score":0.8873292,"about_ca_system_score_codex":0.00006523897,"about_ca_system_score_gemma":0.00011570628,"threshold_uncertainty_score":0.28679946},"labels":[],"label_agreement":null},{"id":"W4365460709","doi":"10.48550/arxiv.2304.05482","title":"Computational Pathology: A Survey Review and The Way Forward","year":2023,"lang":"en","type":"review","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Viewpoints; Computer science; Data science; Multidisciplinary approach; Workflow; Digital pathology; Sketch; Field (mathematics); Cyberinfrastructure; Interoperability; Management science; Artificial intelligence; Engineering; World Wide Web","score_opus":0.160211525889562,"score_gpt":0.250540532994813,"score_spread":0.09032900710525099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365460709","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015496802,0.852209,0.1464416,0.00009064861,0.00026599405,0.00062844343,0.00002586123,0.00015651676,0.00018041936],"genre_scores_gemma":[0.00010100918,0.9985787,0.00018755758,0.00021570557,0.00003284457,0.0000059184476,0.000023621908,0.000020596905,0.00083404477],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976237,0.0010322322,0.00027864997,0.00075381063,0.000083628795,0.00022798825],"domain_scores_gemma":[0.99754214,0.0012396673,0.00034347657,0.0006834635,0.00011676889,0.00007446137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014808878,0.00026736528,0.00097012037,0.00015467482,0.000200065,0.00005885739,0.0011648843,0.00015347038,0.000008990733],"category_scores_gemma":[0.00013308508,0.0002013949,0.000269028,0.0016498565,0.00024836618,0.000213329,0.00067052926,0.00036259872,0.00023717682],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021383892,0.000040860403,0.000051834697,0.033669233,0.0007084675,0.00047972455,0.00011212458,0.0019027553,3.3088658e-9,0.22514991,0.01019766,0.727666],"study_design_scores_gemma":[0.0011118253,0.000089506415,0.00022521427,0.012177778,0.0019225654,0.00027185198,0.000007123737,0.0359932,2.4081318e-8,0.03405418,0.9131592,0.0009875193],"about_ca_topic_score_codex":0.000054553402,"about_ca_topic_score_gemma":0.00005028445,"teacher_disagreement_score":0.90296155,"about_ca_system_score_codex":0.00014664893,"about_ca_system_score_gemma":0.000189729,"threshold_uncertainty_score":0.82126456},"labels":[],"label_agreement":null},{"id":"W4365503179","doi":"10.1117/12.2673725","title":"Out of distribution detection for medical images","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Context (archaeology); Field (mathematics); Process (computing); Artificial intelligence; Popularity; Annotation; Class (philosophy); Machine learning; Set (abstract data type); Data mining; Medical imaging; Geography; Mathematics","score_opus":0.017787104274084316,"score_gpt":0.2938367698072183,"score_spread":0.276049665533134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365503179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041187485,0.000006114082,0.99310124,0.0010500659,0.0009816617,0.00010255867,0.000006198399,0.00032247597,0.000310924],"genre_scores_gemma":[0.996796,0.000013240194,0.0026512402,0.00003415222,0.00010001605,0.000042610478,0.0000068085697,0.0000034968546,0.0003524396],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993595,0.000015134041,0.00012799399,0.00014870893,0.0002367543,0.000111890746],"domain_scores_gemma":[0.9995844,0.000102658276,0.000040370778,0.00016478536,0.00007166461,0.00003613151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000353784,0.000039999464,0.00006013808,0.000041444753,0.000048089518,0.000016324784,0.00021569396,0.000051089348,0.000013183225],"category_scores_gemma":[0.00016742294,0.00003568882,0.00004089341,0.0002955654,0.000024392937,0.00017139963,0.00007315453,0.00003908948,0.000035636513],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018285049,0.0000262868,0.00016121297,0.000056820307,0.000016547036,0.0000015749421,0.00013784626,0.000070176604,0.019962147,0.009770253,0.020109486,0.94966936],"study_design_scores_gemma":[0.0003924049,0.00022837604,0.00498479,0.000015098635,0.0000046999685,0.000004600456,0.00002736046,0.32530957,0.64445466,0.009982033,0.0144821545,0.0001142287],"about_ca_topic_score_codex":0.0000151855875,"about_ca_topic_score_gemma":0.0000452775,"teacher_disagreement_score":0.9926773,"about_ca_system_score_codex":0.000042992444,"about_ca_system_score_gemma":0.00003545366,"threshold_uncertainty_score":0.14553477},"labels":[],"label_agreement":null},{"id":"W4365504611","doi":"10.1007/s10278-023-00797-x","title":"DeepBLS: Deep Feature-Based Broad Learning System for Tissue Phenotyping in Colorectal Cancer WSIs","year":2023,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Terry Fox Foundation","keywords":"Computer science; Grading (engineering); Colorectal cancer; Artificial intelligence; Stroma; Deep learning; Feature extraction; Digital pathology; Histology; Pattern recognition (psychology); Feature (linguistics); Pathology; Cancer; Medicine; Biology; Immunohistochemistry","score_opus":0.012211836045831035,"score_gpt":0.2756273847826754,"score_spread":0.26341554873684436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365504611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114058845,0.0010359724,0.88023514,0.0015353425,0.002152491,0.00023650969,0.000004337781,0.00023805366,0.00050334074],"genre_scores_gemma":[0.9946865,0.000009212496,0.004865572,0.000045851124,0.00030285737,0.00002118003,0.0000013550283,0.000024720743,0.00004274179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863833,0.00004136842,0.00039157222,0.00023158948,0.00033337026,0.00036376517],"domain_scores_gemma":[0.99888176,0.00028800897,0.00040715508,0.00010653369,0.00022810143,0.00008843997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047316102,0.00014647236,0.00026168203,0.00048176647,0.00012536864,0.0005799907,0.00046108032,0.000035775185,0.0000011999009],"category_scores_gemma":[0.00019406351,0.00014256565,0.00012472934,0.00089851866,0.000027292408,0.0017941999,0.00009118169,0.00032910754,0.000008176278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013876198,0.00003862948,0.035113174,0.0002698426,0.00006368237,0.0002051837,0.0013608437,0.10258507,0.012228936,0.00018665509,0.0007602811,0.84704894],"study_design_scores_gemma":[0.0015784141,0.00017022756,0.0050543565,0.00088388636,0.000023518518,0.00020196456,0.0005963623,0.9618823,0.025604008,0.0004626521,0.0032022323,0.0003400696],"about_ca_topic_score_codex":0.00002233578,"about_ca_topic_score_gemma":0.000023845103,"teacher_disagreement_score":0.8806277,"about_ca_system_score_codex":0.00064086384,"about_ca_system_score_gemma":0.0001816876,"threshold_uncertainty_score":0.5813658},"labels":[],"label_agreement":null},{"id":"W4365515993","doi":"10.21203/rs.3.rs-2618116/v1","title":"VOLTA: an Environment-Aware Contrastive Cell Representation Learning for Histopathology","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Histopathology; Computer science; Artificial intelligence; Representation (politics); Machine learning; Sample (material); Supervised learning; Pattern recognition (psychology); Pathology; Artificial neural network; Medicine","score_opus":0.13571809669137366,"score_gpt":0.41305341332614715,"score_spread":0.2773353166347735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365515993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011501692,0.00029003312,0.9831081,0.00088981236,0.0012007856,0.0020891896,0.00005060172,0.000550591,0.00031917324],"genre_scores_gemma":[0.9786691,0.000498321,0.010480851,0.000027921844,0.0008290414,0.0027748556,0.00035292207,0.000115144,0.0062518315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945689,0.0015626216,0.00037150856,0.0016613151,0.0010325547,0.0008030868],"domain_scores_gemma":[0.9965576,0.001311345,0.00023205884,0.0012458973,0.00045479764,0.00019833627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003031966,0.0002641664,0.00035147142,0.0005798523,0.00056761905,0.00028721464,0.0013337358,0.00045057797,0.000031135674],"category_scores_gemma":[0.00056968577,0.00029932553,0.00016254942,0.000373867,0.00020124728,0.00037689097,0.0020757988,0.0019166488,0.00021224476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016743924,0.0014540871,0.032189872,0.007062296,0.00027477878,0.0010626045,0.036162008,0.520444,0.044623926,0.0061869565,0.03963313,0.30923194],"study_design_scores_gemma":[0.0017977778,0.0031856468,0.049881026,0.00042964393,0.000038556416,0.000020815445,0.002547639,0.8649113,0.013783501,0.03909077,0.023102287,0.0012110427],"about_ca_topic_score_codex":0.0003679309,"about_ca_topic_score_gemma":0.000053425083,"teacher_disagreement_score":0.9726273,"about_ca_system_score_codex":0.0011451787,"about_ca_system_score_gemma":0.00037111578,"threshold_uncertainty_score":0.9999459},"labels":[],"label_agreement":null},{"id":"W4366245713","doi":"10.1016/j.jpi.2023.100315","title":"Removing non-nuclei information from histopathological images: A preprocessing step towards improving nuclei segmentation methods","year":2023,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Fundación CeiBA","keywords":"Computer science; Segmentation; Preprocessor; Artificial intelligence; Histogram; Pattern recognition (psychology); Digital pathology; Centroid; Watershed; Computer vision; Image (mathematics)","score_opus":0.022250201296386548,"score_gpt":0.315663489276448,"score_spread":0.29341328798006144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366245713","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14022161,0.000038427406,0.8569019,0.00027273566,0.0015303184,0.00014540042,0.0000059956446,0.00017089343,0.00071274757],"genre_scores_gemma":[0.09923957,0.00006450472,0.89995176,0.0005310167,0.00017017608,0.000008663992,0.000008452774,0.000011781974,0.0000140438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713534,0.0002193772,0.0016349944,0.00013713019,0.0005200461,0.00035310021],"domain_scores_gemma":[0.9965786,0.0002286758,0.002196666,0.00041764724,0.00046373214,0.000114716204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027294983,0.00021037787,0.0003991137,0.00062748755,0.00024927,0.0003469356,0.00083753205,0.00023396795,0.000011227618],"category_scores_gemma":[0.0007351134,0.0001840194,0.00014630625,0.000768165,0.00009205554,0.0067082415,0.00042408996,0.0005912993,0.0000744729],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031453746,0.000019053627,0.00033663306,0.00012050209,0.00002044423,0.00012642173,0.019647311,0.0012594438,0.015303467,0.0000517412,0.000746658,0.9623369],"study_design_scores_gemma":[0.0023138085,0.0010436948,0.021810116,0.00030056396,0.00013383784,0.0046426794,0.010429003,0.92243576,0.02716784,0.0056715403,0.0033299276,0.0007212354],"about_ca_topic_score_codex":0.000011376788,"about_ca_topic_score_gemma":8.7363446e-7,"teacher_disagreement_score":0.9616156,"about_ca_system_score_codex":0.00040638022,"about_ca_system_score_gemma":0.00025708863,"threshold_uncertainty_score":0.75040936},"labels":[],"label_agreement":null},{"id":"W4366371937","doi":"10.1016/j.patrec.2023.04.006","title":"Large-margin representation learning for texture classification","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Margin (machine learning); Pattern recognition (psychology); Artificial intelligence; Computer science; Representation (politics); Convolutional neural network; CLs upper limits; Backpropagation; Metric (unit); Similarity (geometry); Feature learning; Artificial neural network; Machine learning; Image (mathematics)","score_opus":0.06300581101001862,"score_gpt":0.30417756776002575,"score_spread":0.24117175675000713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366371937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05326971,0.000005873206,0.93254626,0.012039579,0.0008430793,0.00040214809,0.000012781279,0.00074468163,0.00013591522],"genre_scores_gemma":[0.9935586,0.000024343079,0.0018565923,0.0031035084,0.00040987515,0.0004811129,0.00040204378,0.000026541578,0.00013738555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862665,0.00011659905,0.00022614228,0.00048068792,0.0002454548,0.00030445898],"domain_scores_gemma":[0.99921876,0.00020138675,0.0001678798,0.0002626456,0.000100328165,0.00004902653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038514275,0.000121195364,0.00010461726,0.0002561153,0.0002460298,0.00015438121,0.0002483125,0.00007157434,0.000033898727],"category_scores_gemma":[0.0000981498,0.00013606054,0.00008674016,0.00064608955,0.000016894342,0.0005905044,0.000060188468,0.0001768084,0.0006392623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012562241,0.000019606234,0.004224201,0.000050681894,0.00002358795,0.0000048557768,0.0010053769,0.000513157,0.01903755,0.000041010022,0.020402255,0.9546652],"study_design_scores_gemma":[0.0012834747,0.00009692515,0.050973177,0.00008031273,0.000023247776,0.00001503107,0.0004440744,0.91590995,0.007177922,0.0022011697,0.021315463,0.00047925752],"about_ca_topic_score_codex":0.000011505072,"about_ca_topic_score_gemma":0.000009207673,"teacher_disagreement_score":0.9541859,"about_ca_system_score_codex":0.00009770348,"about_ca_system_score_gemma":0.000013748734,"threshold_uncertainty_score":0.8216637},"labels":[],"label_agreement":null},{"id":"W4366823058","doi":"10.1038/s43856-023-00282-0","title":"Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning","year":2023,"lang":"en","type":"article","venue":"Communications Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"Verily Life Sciences; Google","keywords":"Logistic regression; Colorectal cancer; Artificial intelligence; Medicine; Machine learning; Stage (stratigraphy); Test set; Deep learning; Lymph node; Metastasis; Oncology; Lymph node metastasis; Internal medicine; Cancer; Computer science","score_opus":0.0823631598769878,"score_gpt":0.34574269829738646,"score_spread":0.2633795384203987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366823058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97126794,0.0053230235,0.020211203,0.0019278191,0.0004933641,0.0001623812,0.000005077908,0.00032765826,0.0002815175],"genre_scores_gemma":[0.9827158,0.0018637988,0.015020029,0.00021700584,0.000058936697,0.00006561194,0.000033733613,0.0000148293,0.0000102670665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982503,0.00052860985,0.00043295173,0.00036638792,0.00017463502,0.0002471388],"domain_scores_gemma":[0.9974688,0.0013379458,0.0002585144,0.00079848233,0.00006719625,0.00006903942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008204536,0.00014302599,0.00033717885,0.000331591,0.00035415185,0.000020015817,0.0010186989,0.00007371141,0.000016016242],"category_scores_gemma":[0.0005766839,0.00013156961,0.000028311339,0.001039336,0.0003765324,0.00023419052,0.0009982199,0.0004194237,0.0000047243893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000121912135,0.000031282572,0.94377697,0.000021556993,0.00002719598,0.000014268637,0.005262035,0.0017991813,0.00884533,0.00012473896,0.000028727989,0.040056508],"study_design_scores_gemma":[0.0006152576,0.000064517524,0.6041069,0.00014283208,0.00004183971,0.000021531505,0.00096039416,0.39268485,0.00024180968,0.0005435238,0.00042900193,0.00014756396],"about_ca_topic_score_codex":0.0025852046,"about_ca_topic_score_gemma":0.0005891029,"teacher_disagreement_score":0.39088565,"about_ca_system_score_codex":0.00042671803,"about_ca_system_score_gemma":0.00010319386,"threshold_uncertainty_score":0.5365253},"labels":[],"label_agreement":null},{"id":"W4367055910","doi":"10.1038/s41746-023-00811-0","title":"Self-supervised learning for medical image classification: a systematic review and implementation guidelines","year":2023,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":412,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"U.S. National Library of Medicine; National Institute of Biomedical Imaging and Bioengineering; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Artificial intelligence; Computer science; Machine learning; Deep learning; Supervised learning; Medical imaging; Scopus; Data science; MEDLINE; Artificial neural network","score_opus":0.12664126699211417,"score_gpt":0.44221957864895156,"score_spread":0.31557831165683736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367055910","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6191307e-8,0.918204,0.07353895,0.00316268,0.00039112646,0.00391464,0.000011927407,0.00051324035,0.00026341612],"genre_scores_gemma":[8.849288e-7,0.9934216,0.003183914,0.00043551007,0.0004890722,0.0019504037,0.0001921918,0.000056282704,0.00027010273],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9961307,0.00015969883,0.0018879038,0.0006917369,0.00084136426,0.00028856867],"domain_scores_gemma":[0.9970051,0.00097008934,0.00082433695,0.00058284245,0.0004106158,0.00020703672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018140431,0.00039645657,0.0021884097,0.0002300912,0.00012641645,0.0001829233,0.000794368,0.00018164788,0.000023963556],"category_scores_gemma":[0.0036384726,0.00027397546,0.00020126632,0.0008512147,0.0000720553,0.00057203206,0.00023059893,0.00029425474,0.00007156216],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2567201e-7,0.00000390721,1.11659126e-7,0.58902353,0.000083551415,0.0000034584293,0.000040834107,7.696121e-9,3.3796667e-8,0.00035063727,0.0033882835,0.40710542],"study_design_scores_gemma":[0.00035328322,0.00022438649,3.1838036e-7,0.50075465,0.0017769297,0.00020164147,0.000082950566,0.0036493014,6.752172e-8,0.00017943291,0.4924712,0.00030586694],"about_ca_topic_score_codex":0.000004127589,"about_ca_topic_score_gemma":0.0000028330692,"teacher_disagreement_score":0.4890829,"about_ca_system_score_codex":0.00019722295,"about_ca_system_score_gemma":0.00035865942,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W4367147092","doi":"10.2139/ssrn.4423668","title":"Whole Slide Image Representation in Bone Marrow Cytology","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"William Osler Health System; McMaster University","funders":"","keywords":"Bone marrow; Representation (politics); Cytology; Image (mathematics); Computer science; Artificial intelligence; Pathology; Medicine; Political science","score_opus":0.02046210510179831,"score_gpt":0.29485134718438355,"score_spread":0.27438924208258525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367147092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04092871,0.0023369712,0.9400069,0.011668392,0.003790099,0.0003869044,0.000004045756,0.00033904891,0.00053892453],"genre_scores_gemma":[0.9718707,0.0090073375,0.012178958,0.00021023155,0.0014005541,0.00014572385,0.000025849813,0.00011442769,0.005046168],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953442,0.0003747246,0.00066804665,0.0008079882,0.00049628975,0.002308726],"domain_scores_gemma":[0.99828035,0.00010950998,0.00056157843,0.00082356844,0.0001418975,0.00008308664],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00279044,0.00028603122,0.0004165412,0.000694418,0.00014492017,0.0002879648,0.0013899456,0.00033555823,0.000008600038],"category_scores_gemma":[0.00016658995,0.0003127907,0.00019786657,0.0006460916,0.00005670684,0.0005317731,0.0009827558,0.0063472325,0.00019479624],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050282426,0.0005186444,0.012709547,0.00035529322,0.0012311611,0.0018114763,0.0053097233,0.039718404,0.037652913,0.2332557,0.013716001,0.6532183],"study_design_scores_gemma":[0.00065031165,0.00018732033,0.0030813352,0.00009634525,0.000019902627,0.0012336595,0.00030788104,0.015574241,0.000860855,0.9768746,0.0007197745,0.00039379107],"about_ca_topic_score_codex":0.0005844348,"about_ca_topic_score_gemma":0.005271249,"teacher_disagreement_score":0.93094206,"about_ca_system_score_codex":0.003787322,"about_ca_system_score_gemma":0.0036226863,"threshold_uncertainty_score":0.9999324},"labels":[],"label_agreement":null},{"id":"W4367396455","doi":"10.1016/j.eswa.2023.120282","title":"Automated breast cancer detection in mammography using ensemble classifier and feature weighting algorithms","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Department of Science and Technology of Jilin Province","keywords":"Computer science; Artificial intelligence; Mammography; Weighting; Classifier (UML); Breast cancer; Pattern recognition (psychology); False positive paradox; Ensemble learning; Feature (linguistics); Machine learning; Algorithm; Cancer; Medicine; Radiology","score_opus":0.017320838011506315,"score_gpt":0.2784307853574309,"score_spread":0.2611099473459246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367396455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030526694,0.0011248795,0.963252,0.00091922295,0.00051519193,0.0012412984,0.000016311675,0.0021985923,0.00020578738],"genre_scores_gemma":[0.98590976,0.00010310835,0.010987359,0.000048724618,0.00028319407,0.0025280751,0.000004068496,0.000031044496,0.00010464787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986784,0.000058912083,0.00020599054,0.0005214065,0.000240067,0.00029524945],"domain_scores_gemma":[0.9992237,0.00004661007,0.00013417819,0.00041204033,0.000098979035,0.00008451287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018185479,0.00016171177,0.00016905165,0.00038589962,0.00031430493,0.00017278672,0.00022574457,0.000118381184,9.4554076e-7],"category_scores_gemma":[0.000001873433,0.00014273581,0.000025234893,0.0026296158,0.00004398414,0.00037563196,0.00007107194,0.00015768243,0.000008737209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010096579,0.00023801495,0.0274698,0.00057948753,0.0003419756,0.000058328325,0.009801515,0.026719956,0.31394476,0.005294416,0.0067105647,0.6087402],"study_design_scores_gemma":[0.00031835536,0.000019632418,0.011008104,0.00013584418,0.0000057103834,0.00022122775,0.00039407794,0.97991395,0.0018784561,0.000054651675,0.0058015715,0.00024839301],"about_ca_topic_score_codex":0.001445438,"about_ca_topic_score_gemma":0.00031020964,"teacher_disagreement_score":0.95538306,"about_ca_system_score_codex":0.00021429927,"about_ca_system_score_gemma":0.00006416938,"threshold_uncertainty_score":0.58205974},"labels":[],"label_agreement":null},{"id":"W4367548959","doi":"10.1016/j.asoc.2023.110346","title":"Ranking loss and sequestering learning for reducing image search bias in histopathology","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Mayo Clinic","keywords":"Computer science; Artificial intelligence; Machine learning; Ranking (information retrieval); Learning to rank; Feature (linguistics); Image (mathematics); Generalization; Deep learning; Matching (statistics); Feature extraction; Feature learning; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.048551244677853524,"score_gpt":0.3041836823348007,"score_spread":0.25563243765694715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367548959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45139188,0.000030206042,0.5474182,0.00013333367,0.0002097885,0.0001834628,1.2196136e-7,0.0003993561,0.0002336583],"genre_scores_gemma":[0.9307892,0.000007593424,0.06893478,0.00006113146,0.0001262742,0.00002540912,0.0000021380047,0.000026040037,0.000027469467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983119,0.00008095147,0.00029964035,0.00061262056,0.00016633589,0.0005285499],"domain_scores_gemma":[0.99890304,0.00067539845,0.00010262409,0.00022882024,0.00004081011,0.000049294067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018857023,0.0001454352,0.00022144105,0.00032995438,0.00035882386,0.00016145145,0.00032829973,0.000077440294,6.5927657e-7],"category_scores_gemma":[0.00009735745,0.00017471735,0.000032036583,0.00070042675,0.0000640535,0.00018452863,0.00062470365,0.000355077,0.000012007688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036955804,0.000015882475,0.0065719476,0.00033760356,0.000010693708,0.00010125941,0.0178962,0.15820104,0.10284875,0.0063055507,0.000043422686,0.7076307],"study_design_scores_gemma":[0.0006293907,0.000052529183,0.0063790977,0.000103589686,0.0000029935075,0.00006429467,0.0002694906,0.98557365,0.004204192,0.0021609277,0.0003035077,0.0002563427],"about_ca_topic_score_codex":0.0000425338,"about_ca_topic_score_gemma":0.000005380013,"teacher_disagreement_score":0.8273726,"about_ca_system_score_codex":0.00017660372,"about_ca_system_score_gemma":0.000047664853,"threshold_uncertainty_score":0.7124767},"labels":[],"label_agreement":null},{"id":"W4367594351","doi":"10.21203/rs.3.rs-1474064/v1","title":"AI-powered pan-species computational pathology: bridging clinic and wildlife care","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"National Institutes of Health; Cancer Research UK; Rosetrees Trust; Children's Cancer and Leukaemia Group","keywords":"Bridging (networking); Wildlife; Computer science; Medicine; Geography; Pathology; Zoology; Biology; Ecology; Computer security","score_opus":0.07914614839443844,"score_gpt":0.40905526216263066,"score_spread":0.3299091137681922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367594351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21602008,0.026179384,0.6671785,0.056123283,0.010076919,0.0067464327,0.0011634213,0.0024745986,0.014037377],"genre_scores_gemma":[0.9873352,0.0008568015,0.00899515,0.0008342746,0.0005730237,0.00048527878,0.00020228242,0.000053234497,0.00066474424],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99429905,0.0012895488,0.0004489548,0.0014209282,0.0018513511,0.0006901436],"domain_scores_gemma":[0.9969646,0.00073538575,0.00017371478,0.0011590627,0.0007900444,0.00017719824],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002010619,0.00028396788,0.00040052048,0.0006757824,0.00086865184,0.0006339853,0.0015444318,0.0002767759,0.00024334106],"category_scores_gemma":[0.00026495053,0.00031803528,0.00015264502,0.0006982267,0.00036077967,0.00027353838,0.007859517,0.003121162,0.00006005401],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004609468,0.0006421334,0.071304046,0.008902409,0.0006124088,0.0027978073,0.074878775,0.046660837,0.00032287659,0.039503053,0.23042797,0.52348673],"study_design_scores_gemma":[0.003054471,0.002712296,0.3684722,0.0018220459,0.000049801856,0.00037257964,0.011786513,0.15925287,0.00031821962,0.11596017,0.33312294,0.0030758877],"about_ca_topic_score_codex":0.00011958659,"about_ca_topic_score_gemma":0.000039435545,"teacher_disagreement_score":0.77131516,"about_ca_system_score_codex":0.00091648765,"about_ca_system_score_gemma":0.0010973369,"threshold_uncertainty_score":0.99992716},"labels":[],"label_agreement":null},{"id":"W4367848900","doi":"10.32920/22734299","title":"Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Transfer of learning; Artificial intelligence; Segmentation; Machine learning; Rendering (computer graphics); Volume rendering; Class (philosophy); Limit (mathematics); Training set; Mathematics","score_opus":0.015427011110762206,"score_gpt":0.2705299063062502,"score_spread":0.25510289519548796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367848900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012425825,0.00038363648,0.9482493,0.0045881956,0.0041836645,0.00074435095,0.000017692098,0.0037231897,0.02568417],"genre_scores_gemma":[0.9568237,0.001744448,0.005575934,0.00043988155,0.00058545923,0.00019280173,0.00012626275,0.00016045563,0.034351047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953567,0.00063555414,0.0005810828,0.0018671216,0.00089796045,0.00066158525],"domain_scores_gemma":[0.9980593,0.00064191077,0.00024041784,0.0006197855,0.00015292813,0.0002856561],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00093453226,0.0006474192,0.00067543134,0.0006974294,0.00041365484,0.0005741621,0.0010897513,0.0005942359,0.00018025862],"category_scores_gemma":[0.000344179,0.000605361,0.00022940256,0.00056384446,0.00026051482,0.0003828895,0.0017387464,0.0065488326,0.00032431426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009861821,0.0010298807,0.030605089,0.0019435484,0.0022159303,0.001008098,0.023469197,0.19487359,0.008284177,0.013797803,0.027261212,0.6945253],"study_design_scores_gemma":[0.0014676269,0.0023287924,0.004018787,0.0005776291,0.00007355505,0.00008621631,0.00051061594,0.8037491,0.00249954,0.0033172239,0.17982543,0.0015455121],"about_ca_topic_score_codex":0.0003960842,"about_ca_topic_score_gemma":0.00005150917,"teacher_disagreement_score":0.94439787,"about_ca_system_score_codex":0.0003528621,"about_ca_system_score_gemma":0.0001847875,"threshold_uncertainty_score":0.99963975},"labels":[],"label_agreement":null},{"id":"W4367849022","doi":"10.32920/22734299.v1","title":"Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence; Segmentation; Machine learning; Rendering (computer graphics); Volume rendering; Class (philosophy); Limit (mathematics); Training set; Mathematics","score_opus":0.015427011110762206,"score_gpt":0.2705299063062502,"score_spread":0.25510289519548796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367849022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012425825,0.00038363648,0.9482493,0.0045881956,0.0041836645,0.00074435095,0.000017692098,0.0037231897,0.02568417],"genre_scores_gemma":[0.9568237,0.001744448,0.005575934,0.00043988155,0.00058545923,0.00019280173,0.00012626275,0.00016045563,0.034351047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953567,0.00063555414,0.0005810828,0.0018671216,0.00089796045,0.00066158525],"domain_scores_gemma":[0.9980593,0.00064191077,0.00024041784,0.0006197855,0.00015292813,0.0002856561],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00093453226,0.0006474192,0.00067543134,0.0006974294,0.00041365484,0.0005741621,0.0010897513,0.0005942359,0.00018025862],"category_scores_gemma":[0.000344179,0.000605361,0.00022940256,0.00056384446,0.00026051482,0.0003828895,0.0017387464,0.0065488326,0.00032431426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009861821,0.0010298807,0.030605089,0.0019435484,0.0022159303,0.001008098,0.023469197,0.19487359,0.008284177,0.013797803,0.027261212,0.6945253],"study_design_scores_gemma":[0.0014676269,0.0023287924,0.004018787,0.0005776291,0.00007355505,0.00008621631,0.00051061594,0.8037491,0.00249954,0.0033172239,0.17982543,0.0015455121],"about_ca_topic_score_codex":0.0003960842,"about_ca_topic_score_gemma":0.00005150917,"teacher_disagreement_score":0.94439787,"about_ca_system_score_codex":0.0003528621,"about_ca_system_score_gemma":0.0001847875,"threshold_uncertainty_score":0.99963975},"labels":[],"label_agreement":null},{"id":"W4372336638","doi":"10.1038/s41598-023-34341-2","title":"Denoising diffusion probabilistic models for 3D medical image generation","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":300,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; RWTH Aachen University; Eisai; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Probabilistic logic; Artificial intelligence; Correctness; Synthetic data; Medical imaging; Segmentation; Image quality; Computer vision; Magnetic resonance imaging; Pattern recognition (psychology); Consistency (knowledge bases); Noise (video); Statistical model; Noise reduction; Image (mathematics); Algorithm; Radiology; Medicine","score_opus":0.038571390029432474,"score_gpt":0.28589318687496723,"score_spread":0.24732179684553476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372336638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07151415,0.000027234233,0.91270447,0.00061858416,0.013880841,0.00047660616,7.7476534e-7,0.00048454155,0.00029281713],"genre_scores_gemma":[0.87083167,0.00000935689,0.12411936,0.00011665001,0.0007879137,0.0003494486,0.00009149745,0.000038184273,0.0036559405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971662,0.00004413936,0.00043472467,0.00096792163,0.00104786,0.00033914903],"domain_scores_gemma":[0.99840856,0.00006617771,0.00018977071,0.0009345534,0.00026271478,0.00013823029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028668114,0.000110978166,0.00012381107,0.000224891,0.00061272027,0.00067876827,0.00034347695,0.000085899075,0.000018894223],"category_scores_gemma":[0.00050786743,0.00010172427,0.0000708589,0.0010458641,0.00012787287,0.0008336259,0.00025694462,0.00008545629,0.00003130072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013278043,0.00020307314,0.00015501198,0.0002582251,0.00002976179,0.00087979354,0.0031810277,0.037863832,0.31621137,0.01046674,0.20370598,0.4270319],"study_design_scores_gemma":[0.00007646645,0.00002091759,0.000031768493,0.000024125959,0.0000042645047,0.00011647672,0.0000064887117,0.9093956,0.0073500015,0.0776927,0.0051643965,0.00011679571],"about_ca_topic_score_codex":0.00001446129,"about_ca_topic_score_gemma":0.00003771132,"teacher_disagreement_score":0.8715318,"about_ca_system_score_codex":0.00013818691,"about_ca_system_score_gemma":0.00033015164,"threshold_uncertainty_score":0.6545378},"labels":[],"label_agreement":null},{"id":"W4376140937","doi":"10.21203/rs.3.rs-2864977/v1","title":"ImageBox3: No-Server Tile Serving to Traverse Whole Slide Images on the Web","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Tree traversal; Server; Cloud computing; Code (set theory); World Wide Web; Operating system","score_opus":0.11088365497139976,"score_gpt":0.3901678607466917,"score_spread":0.2792842057752919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376140937","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33107778,0.0011169364,0.14077885,0.35519716,0.025440339,0.025050879,0.0018288863,0.009547677,0.109961465],"genre_scores_gemma":[0.9341812,0.0004575227,0.00901377,0.0013515276,0.0026831366,0.002762918,0.000052802952,0.00029105297,0.04920604],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938676,0.0009214256,0.00034975886,0.0014117797,0.0023989081,0.0010505494],"domain_scores_gemma":[0.9941914,0.0011649671,0.00010268421,0.0032867577,0.000968328,0.00028584455],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00413449,0.00034963485,0.00030881978,0.00066163996,0.00060642534,0.0012559148,0.004297904,0.00026410157,0.00024006852],"category_scores_gemma":[0.0010707787,0.0002790915,0.00023169721,0.001487102,0.0001225925,0.0003145506,0.007502345,0.0025868863,0.012205764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001388813,0.00019108945,0.000402955,0.0016179624,0.00015636893,0.00040084185,0.0034974704,0.010079253,0.014291257,0.0039394223,0.9307075,0.034576964],"study_design_scores_gemma":[0.001580043,0.0026027232,0.04380188,0.009811369,0.00004249755,0.000030061585,0.0029948426,0.29988745,0.07028866,0.05195663,0.51344913,0.0035547342],"about_ca_topic_score_codex":0.00083562545,"about_ca_topic_score_gemma":0.00030762536,"teacher_disagreement_score":0.60310346,"about_ca_system_score_codex":0.0008429532,"about_ca_system_score_gemma":0.00070445077,"threshold_uncertainty_score":0.99996614},"labels":[],"label_agreement":null},{"id":"W4377009397","doi":"10.53350/pjmhs2023172817","title":"Impact of Evaluation of Tumour Grade by Core Needle Biopsy on Clinical Risk Assessment and Patient Selection for Adjuvant Systemic Treatment in Breast Cancer","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Family Physicians of Canada","funders":"","keywords":"Medicine; Breast cancer; Biopsy; Stage (stratigraphy); Cancer; Lobular carcinoma; Retrospective cohort study; Cohort; Ductal carcinoma; Internal medicine; Oncology; Radiology","score_opus":0.07776050824662019,"score_gpt":0.4284020063465083,"score_spread":0.35064149809988815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377009397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98909783,0.00006761588,0.00930199,0.00011287692,0.00029184122,0.0009530355,0.000113438386,0.000045401066,0.00001597259],"genre_scores_gemma":[0.9988,0.00019741314,0.00064620253,0.0000060563666,0.000024786037,0.00030251764,0.0000074375494,0.00000822897,0.000007404199],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846613,0.00019270129,0.0004801739,0.00033066276,0.00037234748,0.00015795363],"domain_scores_gemma":[0.9990069,0.00017663921,0.00036350987,0.00017933967,0.0002247953,0.000048789563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084376516,0.000120382916,0.00025671968,0.0001763518,0.000039241186,0.000015173823,0.00007844471,0.000063827894,0.000006830221],"category_scores_gemma":[0.000019201318,0.00008965392,0.00009514138,0.00052292965,0.00002286813,0.00013160918,0.000030010482,0.00006613732,7.649406e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015747927,0.00050184655,0.6699585,0.000045177563,0.00013382525,3.5449577e-7,0.000583942,0.025319025,0.01408048,0.000091414746,0.0010657691,0.2880622],"study_design_scores_gemma":[0.0011224505,0.0019029903,0.49427375,0.00005713389,0.000033660945,0.0000088522265,0.00006979605,0.5008347,0.0014715139,0.00016109378,0.0000016251611,0.00006243877],"about_ca_topic_score_codex":0.004661497,"about_ca_topic_score_gemma":0.00020502233,"teacher_disagreement_score":0.47551566,"about_ca_system_score_codex":0.001195759,"about_ca_system_score_gemma":0.00036471308,"threshold_uncertainty_score":0.704682},"labels":[],"label_agreement":null},{"id":"W4377010966","doi":"10.1186/s13000-023-01355-3","title":"Biased data, biased AI: deep networks predict the acquisition site of TCGA images","year":2023,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Ontario Tech University; Brock University; William Osler Health System; Laurentian University; McMaster University; University Health Network","funders":"Ontario Research Foundation","keywords":"Artificial intelligence; Computer science; Pathology; Computational biology; Medicine; Biology","score_opus":0.023526141178360993,"score_gpt":0.2762786573897046,"score_spread":0.2527525162113436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377010966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0767277,0.00044957097,0.9176879,0.0024192384,0.0017407482,0.0003446212,0.00011819337,0.00040627157,0.00010574404],"genre_scores_gemma":[0.99644613,0.000326942,0.0014170967,0.0011661411,0.00029857125,0.000091702605,0.00021842722,0.000017100805,0.00001787153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811053,0.00036477172,0.00032497937,0.00056566874,0.00025007062,0.00038397536],"domain_scores_gemma":[0.9942196,0.0037963954,0.00018350067,0.0016388281,0.00010277857,0.00005891014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009090864,0.00015390397,0.00021933074,0.00016820275,0.00015308423,0.000052655043,0.0012266001,0.00013295721,0.000024110905],"category_scores_gemma":[0.0013359505,0.00012472183,0.000054639473,0.0010114923,0.00021868302,0.00036777093,0.00074203114,0.00022977174,0.00014185191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015731066,0.0005068739,0.1369058,0.00019551374,0.00021744649,0.0032561673,0.0042925803,0.2620103,0.014045443,0.004047996,0.18686429,0.38750026],"study_design_scores_gemma":[0.00055321533,0.0002516976,0.32479125,0.000052287014,0.000045714314,0.0000856695,0.000035101788,0.6696893,0.0017492973,0.0018484284,0.0007012191,0.00019681969],"about_ca_topic_score_codex":0.000046304503,"about_ca_topic_score_gemma":0.00003055304,"teacher_disagreement_score":0.91971844,"about_ca_system_score_codex":0.000035860743,"about_ca_system_score_gemma":0.000058811318,"threshold_uncertainty_score":0.5086009},"labels":[],"label_agreement":null},{"id":"W4377200874","doi":"10.34028/iajit/20/3a/9","title":"A Comparative Study of Different Pre-Trained Deep Learning Models and Custom CNN for Pancreatic Tumor Detection","year":2023,"lang":"en","type":"article","venue":"The International Arab Journal of Information Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning; Computer architecture","score_opus":0.021832431681603776,"score_gpt":0.275247938828781,"score_spread":0.25341550714717725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377200874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5580914,0.000012415665,0.44092554,0.00045158857,0.00020806593,0.0002066731,6.6753813e-7,0.00005441697,0.00004923252],"genre_scores_gemma":[0.99829507,0.000028090511,0.0015470355,0.000029226961,0.000031300006,0.000049957816,9.919373e-7,0.0000032310538,0.000015118533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887466,0.000040761228,0.0005782872,0.000074465,0.00032542515,0.00010640448],"domain_scores_gemma":[0.99832034,0.00017714218,0.0008675094,0.0001245143,0.00049267395,0.000017836268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048241208,0.00009163114,0.00020475384,0.00075276155,0.00012681745,0.00005954806,0.00061090424,0.000042299966,0.0000015603346],"category_scores_gemma":[0.00013919742,0.00006413472,0.000045657565,0.00041716162,0.000055696546,0.0010865174,0.00014850727,0.00024110625,0.0000026962819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012582652,0.00037451703,0.0021881233,0.00012460355,0.0011306365,0.0000060160146,0.062622435,0.31187767,0.0090892995,0.040755346,0.0002333373,0.57033974],"study_design_scores_gemma":[0.0011531444,0.0012849071,0.003319392,0.00003697914,0.000023010556,0.00013732797,0.005832133,0.9469295,0.0102805775,0.030769585,0.00015826727,0.000075177995],"about_ca_topic_score_codex":0.000008013163,"about_ca_topic_score_gemma":0.000015623735,"teacher_disagreement_score":0.63505185,"about_ca_system_score_codex":0.0001065877,"about_ca_system_score_gemma":0.000023171611,"threshold_uncertainty_score":0.2615338},"labels":[],"label_agreement":null},{"id":"W4377234480","doi":"10.18280/ts.400204","title":"Multiclass Classification of Cervical Pap Smear Images Using Deep Learning-Based Model","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Multiclass classification; Computer science; Pattern recognition (psychology); Support vector machine","score_opus":0.05169101083684824,"score_gpt":0.2852563848741612,"score_spread":0.23356537403731298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377234480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14137872,0.000013249029,0.85759866,0.00038197916,0.00009773687,0.00015708823,0.0000026081714,0.00027177818,0.00009820405],"genre_scores_gemma":[0.9733594,0.0000037141576,0.026436167,0.00006289422,0.00005908296,0.000025180636,0.000006328179,0.000015413534,0.000031805484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848324,0.00010820521,0.00031650942,0.00035101644,0.00048186295,0.000259141],"domain_scores_gemma":[0.99929184,0.00010233164,0.00016369851,0.00024879246,0.0001249957,0.000068321846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043527092,0.00012862844,0.00014416841,0.00018246366,0.00013542315,0.000060790873,0.0003928157,0.00006551134,0.000037528775],"category_scores_gemma":[0.000020370511,0.00013225432,0.00007911082,0.000577707,0.000062428815,0.0002852432,0.00008138247,0.00015202838,0.00003258148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023516353,0.00006619517,0.0013049685,0.000046365025,0.000015378157,0.0000027887702,0.00039377058,0.84857696,0.12617785,0.00074876426,0.0000738326,0.02256961],"study_design_scores_gemma":[0.00047639717,0.000099360586,0.010674381,0.00002045633,0.00001236723,0.0000010448902,0.000043104243,0.96849215,0.019520763,0.0004396518,0.0000885622,0.00013173504],"about_ca_topic_score_codex":0.000023285014,"about_ca_topic_score_gemma":0.000009518472,"teacher_disagreement_score":0.8319807,"about_ca_system_score_codex":0.00014462501,"about_ca_system_score_gemma":0.000084632404,"threshold_uncertainty_score":0.5393175},"labels":[],"label_agreement":null},{"id":"W4377564016","doi":"10.1148/radiol.230935","title":"Standalone AI in Breast Cancer Screening: Where We Are and What Is to Be Achieved","year":2023,"lang":"en","type":"letter","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Breast cancer; Mammography; MEDLINE; Breast imaging; Medical physics; Artificial intelligence; Gynecology; Cancer; Internal medicine; Computer science","score_opus":0.026618476745070986,"score_gpt":0.27865820095657085,"score_spread":0.25203972421149984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377564016","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075129274,0.0051660454,0.021515997,0.9696548,0.0023102444,0.00030115258,0.000103504244,0.00018687312,0.000010074895],"genre_scores_gemma":[0.0007153114,0.015605647,0.0021804585,0.9765793,0.0031343543,0.00024034535,0.000019229627,0.00008440399,0.0014409659],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975431,0.00022404466,0.0003066592,0.0010534739,0.00026525962,0.00060745224],"domain_scores_gemma":[0.9988005,0.00017579316,0.00017107508,0.0006831872,0.000078234596,0.000091168695],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002318482,0.00033554548,0.0005969689,0.0003943127,0.000086453845,0.00025153332,0.0008204563,0.0008135594,0.000048800433],"category_scores_gemma":[0.000009482497,0.00033681348,0.00006534693,0.00062628876,0.00009898232,0.0005748687,0.00041710705,0.0014230644,0.000029438674],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024871884,0.0000031103868,0.0008877122,0.00009240769,0.00004862594,0.00027238208,0.0006813752,0.0000630535,0.00003731501,0.000012378033,0.94510555,0.052771192],"study_design_scores_gemma":[0.000444415,0.00011983018,0.009195761,0.00061332213,0.000015127527,0.00040906973,0.000084718304,0.0019091833,0.000022355058,0.00033997034,0.9863542,0.0004920942],"about_ca_topic_score_codex":0.00057551457,"about_ca_topic_score_gemma":0.0012049825,"teacher_disagreement_score":0.0522791,"about_ca_system_score_codex":0.00037020154,"about_ca_system_score_gemma":0.00012930862,"threshold_uncertainty_score":0.9999084},"labels":[],"label_agreement":null},{"id":"W4377564079","doi":"10.1148/radiol.222639","title":"Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis","year":2023,"lang":"en","type":"review","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":173,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; Cancer Research UK; NYU Grossman School of Medicine; National Institute of Biomedical Imaging and Bioengineering; York University; Foundation for the National Institutes of Health","keywords":"Medicine; Mammography; Digital Breast Tomosynthesis; Meta-analysis; Digital mammography; Tomosynthesis; Receiver operating characteristic; Medical physics; Breast cancer; Breast imaging; Cohort study; Cohort; Radiology; Diagnostic accuracy; Artificial intelligence; Nuclear medicine; Internal medicine; Cancer","score_opus":0.056539810242278526,"score_gpt":0.3192466179773954,"score_spread":0.2627068077351169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377564079","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.741735e-7,0.87128764,0.1230898,0.00029662493,0.00010391004,0.00217182,0.0028438747,0.00020029099,0.0000052524147],"genre_scores_gemma":[0.00025512575,0.99639213,0.000279927,0.00012516648,0.00008636294,0.0025739914,0.000044173255,0.00006383458,0.00017925823],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99659306,0.00031181425,0.0011128702,0.001242601,0.00026538133,0.00047427684],"domain_scores_gemma":[0.99702096,0.000887731,0.00093620113,0.00082220073,0.00015870633,0.00017420916],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071525027,0.0006406057,0.0064561605,0.0007361295,0.00023707782,0.00045395194,0.00055478705,0.000318274,0.000013707593],"category_scores_gemma":[0.00009664118,0.0004636435,0.0019931037,0.0018872546,0.00014988241,0.00070073426,0.00036849518,0.00025411785,0.000007635585],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010740055,0.000011031036,0.00000745616,0.5266615,0.118468165,0.000010756251,0.000024400511,0.000005603129,9.979306e-8,0.000046627236,0.00010596417,0.35464764],"study_design_scores_gemma":[0.00022497644,0.00016058085,0.000023486327,0.024924703,0.9441285,0.008988103,0.000009568537,0.0012880247,3.7869756e-7,0.00016842545,0.018893367,0.0011898907],"about_ca_topic_score_codex":0.000026905505,"about_ca_topic_score_gemma":0.000090435875,"teacher_disagreement_score":0.82566035,"about_ca_system_score_codex":0.00025925337,"about_ca_system_score_gemma":0.00007665226,"threshold_uncertainty_score":0.99978155},"labels":[],"label_agreement":null},{"id":"W4377695098","doi":"10.1016/j.media.2023.102846","title":"Diffusion models in medical imaging: A comprehensive survey","year":2023,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":652,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Diffusion map; Noise (video); Noise reduction; Machine learning; Diffusion; Medical imaging; Data science; Image (mathematics); Nonlinear dimensionality reduction","score_opus":0.08373872611063253,"score_gpt":0.387150647904169,"score_spread":0.30341192179353643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377695098","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002155632,0.5724848,0.4262063,0.00035761824,0.00034608634,0.00021586641,0.00001631005,0.00023453822,0.00013631117],"genre_scores_gemma":[0.000027557382,0.9979584,0.0008449522,0.0003807022,0.00020444134,0.00013329496,0.0002245095,0.000057586283,0.0001685632],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9905379,0.0019104423,0.0016019455,0.0015217524,0.003715965,0.0007120034],"domain_scores_gemma":[0.9948472,0.0021744568,0.00047162955,0.001518241,0.0002511939,0.0007373176],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032972132,0.00059133174,0.0032286686,0.0022030526,0.0001080169,0.00022146177,0.003472345,0.0006632756,0.00049406284],"category_scores_gemma":[0.0016599966,0.00047635593,0.0012362617,0.011881974,0.00028662666,0.00045455093,0.0019425671,0.0016315434,0.00040282562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014801801,0.00007394154,0.00004538329,0.0011650841,0.0006461053,0.0011850991,0.000055228018,0.000015268402,3.1384605e-8,0.000036838468,0.0018795185,0.994896],"study_design_scores_gemma":[0.00030744937,0.000014582548,0.00021769055,0.004313667,0.0013768175,0.00006437815,0.000009971498,0.8360782,1.16102036e-7,0.0004814734,0.15648751,0.00064814306],"about_ca_topic_score_codex":0.003242386,"about_ca_topic_score_gemma":0.00295645,"teacher_disagreement_score":0.99424785,"about_ca_system_score_codex":0.00043257236,"about_ca_system_score_gemma":0.0012051977,"threshold_uncertainty_score":0.9997688},"labels":[],"label_agreement":null},{"id":"W4377966413","doi":"10.1056/nejmra2301725","title":"The Current and Future State of AI Interpretation of Medical Images","year":2023,"lang":"en","type":"review","venue":"New England Journal of Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":422,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Current (fluid); Interpretation (philosophy); Workflow; Foundation (evidence); Computer science; Generative grammar; State (computer science); Artificial intelligence; Data science; Engineering; Political science; Programming language","score_opus":0.027929898195808173,"score_gpt":0.3693324346798019,"score_spread":0.34140253648399377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377966413","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004505904,0.93449503,0.05639258,0.0052909995,0.0036808967,0.00010611618,0.0000022545207,0.0000072535504,0.000020353447],"genre_scores_gemma":[0.00008281838,0.99636096,0.00017354418,0.000022974864,0.0033241208,0.0000013540925,8.9698403e-7,0.000010104559,0.000023211951],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973241,0.00026861453,0.0010683293,0.00012585784,0.0011023132,0.000110797264],"domain_scores_gemma":[0.9972052,0.0008413183,0.0013650239,0.00021314852,0.00023099524,0.00014432766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027146882,0.00015173455,0.00092913787,0.0002318772,0.000031551022,0.000017269222,0.00074527983,0.000067186156,0.000006021523],"category_scores_gemma":[0.00039803857,0.000072461095,0.000118117925,0.0003656513,0.00015430704,0.000121748584,0.000116790696,0.00087195827,6.147467e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016566102,0.0000045999013,0.0000012711631,0.0020509488,0.00007846638,0.0000113312535,0.00047964547,0.0000014957258,2.5653318e-7,0.0001149923,0.0035724675,0.99366796],"study_design_scores_gemma":[0.0019315457,0.00048518257,0.00001762352,0.020654498,0.00019166063,0.00037240787,0.00001505876,0.00041589982,0.000002877032,0.0021096165,0.9737416,0.00006202841],"about_ca_topic_score_codex":0.000016003634,"about_ca_topic_score_gemma":0.000017848617,"teacher_disagreement_score":0.9936059,"about_ca_system_score_codex":0.000041254796,"about_ca_system_score_gemma":0.0006557394,"threshold_uncertainty_score":0.37882733},"labels":[],"label_agreement":null},{"id":"W4378172114","doi":"10.5858/arpa.2022-0432-oa","title":"A Pilot Validation Study Comparing Fluorescence-Imitating Brightfield Imaging, A Slide-Free Imaging Method, With Standard Formalin-Fixed, Paraffin-Embedded Hematoxylin-Eosin–Stained Tissue Section Histology for Primary Surgical Pathology Diagnosis","year":2023,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; National Institutes of Health","keywords":"H&E stain; Digital pathology; Surgical pathology; Gold standard (test); Medical diagnosis; Pathology; Medicine; Microtome; Concordance; Radiology; Nuclear medicine; Staining","score_opus":0.02146073886678078,"score_gpt":0.3114129432800192,"score_spread":0.28995220441323843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378172114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2782408,0.00046717716,0.71485835,0.0029485074,0.001278322,0.0013837441,0.000035839083,0.0005500681,0.00023719654],"genre_scores_gemma":[0.77545404,0.00007571196,0.22285555,0.00032948278,0.0003135531,0.00081752625,0.000064957625,0.00006305295,0.000026142414],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99502325,0.0013767836,0.0011097599,0.0011794585,0.00052653474,0.00078420853],"domain_scores_gemma":[0.99407583,0.0033511645,0.0008396176,0.0011224046,0.00043475314,0.00017622374],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002635093,0.0004598141,0.0011605987,0.00091527676,0.00042028594,0.000036131256,0.0009936555,0.00008746712,0.000010859771],"category_scores_gemma":[0.00090138277,0.0004035994,0.00008530293,0.0012097267,0.0008409136,0.00054733024,0.0005061556,0.00052889663,0.000002972905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009406053,0.0019524789,0.3293747,0.0021155186,0.0006774689,0.013796229,0.10029193,0.0047683385,0.2897692,0.028824428,0.009246435,0.2097772],"study_design_scores_gemma":[0.101436615,0.062403556,0.14704235,0.0034871828,0.002334628,0.01046268,0.032188106,0.23596738,0.3255823,0.064261004,0.008732667,0.006101529],"about_ca_topic_score_codex":0.00010055544,"about_ca_topic_score_gemma":0.00014901934,"teacher_disagreement_score":0.4972132,"about_ca_system_score_codex":0.00016870203,"about_ca_system_score_gemma":0.00035257457,"threshold_uncertainty_score":0.9998416},"labels":[],"label_agreement":null},{"id":"W4378771036","doi":"10.48550/arxiv.2305.18033","title":"The ACROBAT 2022 Challenge: Automatic Registration Of Breast Cancer Tissue","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Orionin Tutkimussäätiö; Turun Yliopisto; Vetenskapsrådet; Cancerfonden; VINNOVA; Karolinska Institutet; European Commission; Swedish e-Science Research Centre; Turun Yliopistosäätiö; Syöpäsäätiö; European Federation of Pharmaceutical Industries and Associations","keywords":"Computer science; Image registration; Artificial intelligence; Breast cancer; Cancer; Medicine; Image (mathematics)","score_opus":0.0761882580260853,"score_gpt":0.22232525955518045,"score_spread":0.14613700152909515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378771036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117048256,0.00064118404,0.85691696,0.00791062,0.008828288,0.0014883033,0.00011673411,0.00144689,0.005602761],"genre_scores_gemma":[0.9908906,0.0018329712,0.00020207897,0.000016790405,0.00013427898,0.000007136988,0.000004465593,0.000019305002,0.0068923794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984164,0.00014423009,0.00025580515,0.0007393378,0.00017496807,0.00026923933],"domain_scores_gemma":[0.997671,0.00015757108,0.00052847335,0.0013677065,0.00020525228,0.000069994574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041019576,0.00021555432,0.0002302374,0.00013409954,0.00025023622,0.00009641601,0.0017942889,0.00021533105,0.000050730345],"category_scores_gemma":[0.00002078132,0.00020981656,0.00011625688,0.00052033947,0.00014949465,0.00028942167,0.0012567866,0.00044033915,0.0001097998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013100868,0.0002192284,0.0012318075,0.0012978729,0.00075243914,0.0003266777,0.0019118101,0.53242815,0.0006659799,0.3259685,0.01417275,0.120893754],"study_design_scores_gemma":[0.0003656393,0.000105323175,0.0074621886,0.00033163794,0.00009318048,0.0000133348885,0.00018129295,0.9168465,0.0005323843,0.071324654,0.0022393763,0.0005044757],"about_ca_topic_score_codex":0.00097090105,"about_ca_topic_score_gemma":0.0015373718,"teacher_disagreement_score":0.87384236,"about_ca_system_score_codex":0.00045459913,"about_ca_system_score_gemma":0.0003391882,"threshold_uncertainty_score":0.8556071},"labels":[],"label_agreement":null},{"id":"W4378781122","doi":"10.2460/ajvr.23.03.0062","title":"Machine learning can appropriately classify the collimation of ventrodorsal and dorsoventral thoracic radiographic images of dogs and cats","year":2023,"lang":"en","type":"article","venue":"American Journal of Veterinary Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Radiography; CATS; Medicine; Nuclear medicine; Anatomy; Radiology; Internal medicine","score_opus":0.07559388755793749,"score_gpt":0.3808888446801116,"score_spread":0.3052949571221741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378781122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99488103,0.00067957013,0.0027844282,0.0013949091,0.0000932073,0.00012355438,0.0000044515236,0.000013099486,0.000025722802],"genre_scores_gemma":[0.9961218,0.0018488836,0.001938523,0.0000058885958,0.000052920703,0.000004926062,6.7034347e-7,0.000010169053,0.000016184413],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99771553,0.0008223864,0.00035287745,0.00017241255,0.00066579855,0.0002709866],"domain_scores_gemma":[0.9985282,0.0004685488,0.00043835334,0.00020210941,0.0002701408,0.00009267927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026799466,0.00008948798,0.0002619462,0.0005848216,0.00017486962,0.00006433767,0.00044615866,0.000025618641,0.0000023086823],"category_scores_gemma":[0.00011692135,0.000065563,0.0000621684,0.0017770093,0.0008315408,0.00024402785,0.00026578794,0.00051646645,4.2859472e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015517697,0.00012338767,0.0924571,0.00036904318,0.00026154137,0.00025294223,0.007827662,0.0009985338,0.1863834,0.00040680243,0.00017245758,0.7091954],"study_design_scores_gemma":[0.0018396685,0.04060251,0.8302442,0.0006111399,0.00007281149,0.0043473397,0.005061236,0.097815596,0.014718565,0.0027819101,0.0014349665,0.00047006522],"about_ca_topic_score_codex":0.0004059478,"about_ca_topic_score_gemma":0.0000061521446,"teacher_disagreement_score":0.73778707,"about_ca_system_score_codex":0.000047064696,"about_ca_system_score_gemma":0.00011124021,"threshold_uncertainty_score":0.30638465},"labels":[],"label_agreement":null},{"id":"W4378803851","doi":"10.20944/preprints202305.2209.v1","title":"Breast Cancer Detection in Mammography Images: A CNN-Based Approach with Feature Selection","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Radiological Society of North America","keywords":"Convolutional neural network; Mammography; Artificial intelligence; Computer science; Feature selection; Breast cancer; Pattern recognition (psychology); Classifier (UML); Feature extraction; Artificial neural network; Feature (linguistics); Machine learning; Cancer; Medicine","score_opus":0.05680739561498406,"score_gpt":0.30134257638351175,"score_spread":0.2445351807685277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378803851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24798457,0.00021275847,0.74168235,0.0018485151,0.0022923562,0.0023062143,0.00005833676,0.0027454474,0.00086945354],"genre_scores_gemma":[0.98972505,0.00008551993,0.006889825,0.00009669216,0.00032334888,0.0023232568,0.000019327299,0.000099564546,0.0004373941],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954006,0.0003066812,0.00045437078,0.0024014506,0.00078391074,0.00065299013],"domain_scores_gemma":[0.9972969,0.00006746427,0.0004963558,0.0016485788,0.0003338981,0.0001567854],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008472112,0.00061438594,0.0005245367,0.0011544543,0.00019554907,0.00016338979,0.0014018989,0.00065757846,0.000037204478],"category_scores_gemma":[0.000027075384,0.0006144417,0.00024217807,0.0026786018,0.00011610116,0.0004399375,0.0010857382,0.0022721165,0.00012446416],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035779137,0.00026497262,0.8079914,0.0006993979,0.00021181638,0.000024637993,0.0006445679,0.16643804,0.0039675375,0.00003686572,0.0001139056,0.01924906],"study_design_scores_gemma":[0.0008056076,0.000052877644,0.8491925,0.00048098626,0.00005798005,0.000084555395,0.000041453914,0.10255501,0.044997144,0.00070384314,0.00016861348,0.00085943966],"about_ca_topic_score_codex":0.0041226833,"about_ca_topic_score_gemma":0.0017337064,"teacher_disagreement_score":0.7417405,"about_ca_system_score_codex":0.0011695147,"about_ca_system_score_gemma":0.0005671179,"threshold_uncertainty_score":0.9996307},"labels":[],"label_agreement":null},{"id":"W4378904793","doi":"10.1155/2023/2662719","title":"Analysis of Histopathological Images for Early Diagnosis of Oral Squamous Cell Carcinoma by Hybrid Systems Based on CNN Fusion Features","year":2023,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Najran University","keywords":"Basal cell; Stage (stratigraphy); Computer science; Cancer; Medicine; Segmentation; Artificial intelligence; Pathology; Internal medicine","score_opus":0.022708683803372168,"score_gpt":0.2799947814244216,"score_spread":0.2572860976210494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378904793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5799267,0.00092108577,0.41319916,0.00025270024,0.005004136,0.0003288652,0.00020881309,0.000036851536,0.00012167414],"genre_scores_gemma":[0.99900275,0.00006226484,0.00044218785,0.000029378592,0.0001617777,0.000044991284,0.000018569253,0.0000141725295,0.0002239245],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689543,0.00021671863,0.0011533095,0.00030019536,0.001237331,0.00019700977],"domain_scores_gemma":[0.9959949,0.000790552,0.0014733238,0.00031324071,0.0013377608,0.00009021429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001169311,0.00018718667,0.00058302307,0.0013430761,0.000045948847,0.00011379513,0.0012631962,0.00008784637,0.000010462877],"category_scores_gemma":[0.00021126562,0.00015171534,0.00051889854,0.0006660739,0.000057029738,0.00021269552,0.0000939421,0.00017577814,0.000005458423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014162319,0.0014723853,0.18572865,0.00061430794,0.0013025125,0.0005040768,0.0014768214,0.6962149,0.028255984,0.0012336441,0.066680774,0.015099696],"study_design_scores_gemma":[0.001672338,0.0041483855,0.037109956,0.000495935,0.00059574534,0.00016464831,0.0003914664,0.653331,0.29649,0.00011619073,0.0049476074,0.00053673604],"about_ca_topic_score_codex":0.0004099389,"about_ca_topic_score_gemma":0.0000026588232,"teacher_disagreement_score":0.41907603,"about_ca_system_score_codex":0.00039244007,"about_ca_system_score_gemma":0.00007403755,"threshold_uncertainty_score":0.6186772},"labels":[],"label_agreement":null},{"id":"W4378952948","doi":"10.1016/j.modpat.2023.100233","title":"Fully Automated Tumor Bud Assessment in Hematoxylin and Eosin-Stained Whole Slide Images of Colorectal Cancer","year":2023,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"Swiss Cancer Foundation; Swiss Cancer Research Foundation; KWF Kankerbestrijding; European Commission","keywords":"Tumor budding; H&E stain; Digital pathology; Medicine; Colorectal cancer; Pathology; Histopathology; Immunohistochemistry; Metastasis; Cancer; Internal medicine","score_opus":0.01138601940535358,"score_gpt":0.29488468433259113,"score_spread":0.2834986649272376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378952948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91982216,0.0001489674,0.07750327,0.0012160006,0.00034816723,0.00022379983,0.000022012715,0.00055777753,0.00015787201],"genre_scores_gemma":[0.99106205,0.000031545005,0.008541578,0.00011022245,0.000019412591,0.00014321177,0.0000042473284,0.000015888445,0.000071820905],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998563,0.0001490418,0.00030751093,0.00047019342,0.0001782089,0.00033202991],"domain_scores_gemma":[0.99936825,0.000095058684,0.00014149005,0.00027254762,0.000074571035,0.000048100483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004290454,0.00014042637,0.0002923625,0.00026910182,0.000056119272,0.00003240919,0.0003009379,0.00008278525,0.0000055137916],"category_scores_gemma":[0.000025614752,0.00014240539,0.000031913787,0.00055224984,0.000107184125,0.00019947345,0.00031886448,0.00017168344,0.000009322609],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084931475,0.00016414035,0.04235104,0.00021765393,0.0000375399,0.0013139783,0.0044746376,0.014588791,0.8992989,0.001940022,0.001775172,0.0337532],"study_design_scores_gemma":[0.0006721503,0.00019076392,0.19274439,0.000035738853,0.0000055587157,0.0001118358,0.00006744457,0.7623449,0.04000978,0.0035917482,0.000057751942,0.00016795941],"about_ca_topic_score_codex":0.00014578956,"about_ca_topic_score_gemma":0.00023739225,"teacher_disagreement_score":0.8592891,"about_ca_system_score_codex":0.00015082068,"about_ca_system_score_gemma":0.00018042096,"threshold_uncertainty_score":0.5807123},"labels":[],"label_agreement":null},{"id":"W4379654529","doi":"10.1016/j.compbiomed.2023.107133","title":"A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Pipeline (software); Pattern recognition (psychology); Mammography; Deep learning; Region of interest; Machine learning; Breast cancer; Cancer","score_opus":0.028448656248558673,"score_gpt":0.3139208341662758,"score_spread":0.2854721779177171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379654529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013712271,0.000070604096,0.9744884,0.00845414,0.0025210625,0.00040057735,0.000010596223,0.0002933784,0.000049021924],"genre_scores_gemma":[0.99272823,0.000029699451,0.0059122415,0.00064126216,0.00041093762,0.00024698535,0.000013623909,0.00000861752,0.000008384377],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998961,0.00006342703,0.00020129026,0.00045606509,0.00008350591,0.00023476723],"domain_scores_gemma":[0.99923396,0.00030437452,0.00009542692,0.00025599066,0.000050035993,0.000060231087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041517938,0.00013375097,0.00020225224,0.000413396,0.000117088406,0.000010842971,0.00023526653,0.00014088704,9.727455e-7],"category_scores_gemma":[0.000024489675,0.000105552506,0.00002827537,0.00065687724,0.00012486348,0.000043508386,0.000047244543,0.00016360881,0.0000019505603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004798734,0.000048163387,0.0015183975,0.00025952916,0.000029743016,0.0000047477224,0.00051547884,0.0034750286,0.041628715,0.008996178,0.00051376695,0.9425304],"study_design_scores_gemma":[0.0023336872,0.0009659741,0.04545153,0.0004337625,0.000012259014,0.00006499509,0.00006247767,0.9467738,0.00074024824,0.0011355215,0.0018486475,0.00017704928],"about_ca_topic_score_codex":0.00009453927,"about_ca_topic_score_gemma":0.00006338696,"teacher_disagreement_score":0.979016,"about_ca_system_score_codex":0.00015526371,"about_ca_system_score_gemma":0.00003718606,"threshold_uncertainty_score":0.43043062},"labels":[],"label_agreement":null},{"id":"W4379919680","doi":"10.48550/arxiv.2306.03407","title":"LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Nvidia","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Task (project management); Inefficiency; Machine learning; Image (mathematics)","score_opus":0.18762219671951189,"score_gpt":0.2426375994714252,"score_spread":0.05501540275191333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379919680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111204274,0.000031523097,0.88588315,0.00020325553,0.00089819357,0.000510682,0.000018157094,0.0010548001,0.00019598214],"genre_scores_gemma":[0.8991966,0.000042367454,0.095970295,0.00004837437,0.00014641376,0.00001287103,0.000023325782,0.00004874249,0.00451097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711674,0.00019382112,0.00026952624,0.001675234,0.00014956496,0.0005951038],"domain_scores_gemma":[0.9980173,0.00030609732,0.00034089934,0.00091531186,0.0002479366,0.00017246019],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005583532,0.00036793243,0.00041302555,0.0003291569,0.00047477012,0.00022284138,0.0017584416,0.00040321404,0.000007168709],"category_scores_gemma":[0.00012483743,0.00043212765,0.00028087717,0.00072971237,0.00015190105,0.00026423504,0.002860664,0.001002739,0.0001161006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049434297,0.00009965491,0.0020729888,0.000101963,0.000064637694,0.00015459939,0.00028972098,0.9898741,0.0006891461,0.002125847,0.00029648154,0.0041814297],"study_design_scores_gemma":[0.0008576158,0.00010996668,0.0019460166,0.00012306694,0.00004847528,0.0000046028763,0.00039777055,0.99253225,0.0005798298,0.0019979328,0.000915813,0.00048663132],"about_ca_topic_score_codex":0.00015967019,"about_ca_topic_score_gemma":0.00009379477,"teacher_disagreement_score":0.7899128,"about_ca_system_score_codex":0.0003801526,"about_ca_system_score_gemma":0.00013013191,"threshold_uncertainty_score":0.9998131},"labels":[],"label_agreement":null},{"id":"W4380029579","doi":"10.1158/1538-7445.am2023-5393","title":"Abstract 5393: Comparison of deep learning approaches applied to hematoxylin and eosin-stained whole slide images from women with benign breast disease to predict risk of developing invasive breast cancer","year":2023,"lang":"en","type":"article","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Convolutional neural network; Artificial intelligence; H&E stain; Deep learning; Pooling; Receiver operating characteristic; Pattern recognition (psychology); Computer science; Hyperparameter; Breast cancer; Digital pathology; Set (abstract data type); Feature (linguistics); Medicine; Pathology; Machine learning; Cancer; Staining; Internal medicine","score_opus":0.056569257416390566,"score_gpt":0.3316191630211277,"score_spread":0.27504990560473713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380029579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9616633,0.00044441066,0.035032738,0.001314903,0.00006850079,0.0009027059,0.0003790649,0.0001264695,0.000067875444],"genre_scores_gemma":[0.9951016,0.00017395531,0.003352715,0.000026227413,0.00012172927,0.0011299858,0.000011443236,0.000042601896,0.000039789807],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99666864,0.00018859428,0.0004287337,0.0008633448,0.0011017141,0.0007489555],"domain_scores_gemma":[0.9977379,0.000514375,0.00022698891,0.0005528208,0.00047573601,0.00049218506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010419739,0.00023951248,0.00048101816,0.0005334798,0.0003085023,0.00015249867,0.0007998596,0.00007259764,0.000033141863],"category_scores_gemma":[0.00011594718,0.0002187386,0.000033299257,0.0021867286,0.00021749346,0.0003086929,0.00075147074,0.0005101039,0.000013929254],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035890334,0.00015907695,0.20607403,0.0013298852,0.00047562807,0.00002875571,0.03361658,0.2569956,0.054625086,0.00027569983,0.001164326,0.4416663],"study_design_scores_gemma":[0.0010168499,0.00025914714,0.90986013,0.0009305593,0.00002895498,0.0000037361206,0.007825186,0.016735073,0.061900645,0.00071602786,0.00021070924,0.00051300443],"about_ca_topic_score_codex":0.0032847743,"about_ca_topic_score_gemma":0.0013632381,"teacher_disagreement_score":0.7037861,"about_ca_system_score_codex":0.00072480185,"about_ca_system_score_gemma":0.0008713207,"threshold_uncertainty_score":0.8919901},"labels":[],"label_agreement":null},{"id":"W4380151099","doi":"10.1101/2023.06.06.23290887","title":"GestaltMatcher Database - A global reference for facial phenotypic variability in rare human diseases","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Health Research Foundation","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Benchmarking; Interoperability; Medicine; Computer science; Database; World Wide Web","score_opus":0.07835171933478706,"score_gpt":0.3369114019507723,"score_spread":0.2585596826159852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380151099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.208255,0.0001080797,0.78319263,0.0009725675,0.0026961975,0.0015694277,0.0015984066,0.0009935101,0.0006141932],"genre_scores_gemma":[0.98967963,0.000012534102,0.0085148355,0.00009053183,0.00034463426,0.0008978926,0.0002474364,0.00003058001,0.00018193078],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99692446,0.00031759223,0.00049105985,0.0014542157,0.00035870445,0.00045393826],"domain_scores_gemma":[0.99742234,0.0001992064,0.0002277654,0.001862919,0.0001415276,0.00014624889],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010280465,0.0003390916,0.00041370612,0.00011111517,0.00013919863,0.00020748672,0.0018630862,0.00026776976,0.000028746294],"category_scores_gemma":[0.00051882747,0.00035737755,0.00011104756,0.00046661816,0.000089547415,0.00032367805,0.0024348549,0.0004992141,0.000051397667],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031298102,0.0009408663,0.85019964,0.005266589,0.00020237797,0.00017215566,0.0016080907,0.0034695575,0.0007755428,0.058258045,0.008146041,0.07064813],"study_design_scores_gemma":[0.0007892702,0.00011323806,0.53349614,0.00036706877,0.00005575419,0.0000030038766,0.000024087854,0.03249662,0.0002183563,0.4265753,0.0049084486,0.000952704],"about_ca_topic_score_codex":0.0005890668,"about_ca_topic_score_gemma":0.0007613564,"teacher_disagreement_score":0.78142464,"about_ca_system_score_codex":0.0006467925,"about_ca_system_score_gemma":0.00042797494,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W4380355035","doi":"10.1016/j.neunet.2023.06.013","title":"A multi-modal deep neural network for multi-class liver cancer diagnosis","year":2023,"lang":"en","type":"article","venue":"Neural Networks","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Deep learning; Artificial neural network; Pattern recognition (psychology); Convolutional neural network; Benchmark (surveying); Convolution (computer science); Liver cancer; Contextual image classification; Radiology; Cancer; Image (mathematics); Medicine","score_opus":0.05427200641567054,"score_gpt":0.30213546146903353,"score_spread":0.247863455053363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380355035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031691022,0.002737335,0.9490789,0.0021282102,0.0112765655,0.0013376806,0.00002207963,0.0017096652,0.000018524792],"genre_scores_gemma":[0.9503558,0.0008633672,0.037990004,0.0027459166,0.0036711423,0.003797147,0.000024386129,0.0001035522,0.0004486528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970938,0.0001320489,0.0003897742,0.0009074282,0.00031519792,0.0011617375],"domain_scores_gemma":[0.9983314,0.0004703335,0.00019126688,0.0006427638,0.00014445418,0.00021978322],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029076202,0.00036026753,0.00033953437,0.00011277479,0.00048161042,0.0002410879,0.001064538,0.00024238758,0.000030492787],"category_scores_gemma":[0.00004723478,0.0003513736,0.00025827956,0.0013984625,0.000083265564,0.0006123194,0.00047058397,0.000462687,0.00003741124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003201133,0.000034501183,0.005178663,0.000017982587,0.00003011497,0.000027068274,0.00014876823,0.76381516,0.000016137456,0.000076583885,0.018836802,0.2117862],"study_design_scores_gemma":[0.0010380398,0.00013709,0.017553933,0.000027174967,0.000024770832,0.000010214762,0.000007786002,0.9744136,0.000055025997,0.00005045067,0.0062914174,0.0003905286],"about_ca_topic_score_codex":0.0002760246,"about_ca_topic_score_gemma":0.0016021256,"teacher_disagreement_score":0.9186648,"about_ca_system_score_codex":0.0001839457,"about_ca_system_score_gemma":0.0000320897,"threshold_uncertainty_score":0.99989384},"labels":[],"label_agreement":null},{"id":"W4380576977","doi":"10.1002/gcc.23177","title":"Machine learning in computational histopathology: Challenges and opportunities","year":2023,"lang":"en","type":"review","venue":"Genes Chromosomes and Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Canadian Institute for Advanced Research","keywords":"Workflow; Digital pathology; Histopathology; Artificial intelligence; Computer science; Machine learning; Context (archaeology); Digitization; Medical physics; Pathology; Computer vision; Medicine; Biology","score_opus":0.15577363301303981,"score_gpt":0.33501063061285596,"score_spread":0.17923699759981615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380576977","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001051292,0.99815774,0.00034261553,0.0005604132,0.00048319699,0.00018266376,0.000018922536,0.00014078461,0.000103178674],"genre_scores_gemma":[0.000016043121,0.99858344,0.00034531316,0.0000499995,0.00016265326,0.00022910692,0.000016787915,0.000031366777,0.0005653217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863094,0.00014348255,0.0003031403,0.00054538064,0.00015340402,0.00022363919],"domain_scores_gemma":[0.9994218,0.00013036447,0.00019112551,0.00016579636,0.000027667762,0.00006326906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022825373,0.00026495365,0.0007249298,0.00026405274,0.00010150458,0.000058317735,0.00023318818,0.00016456438,0.000010203218],"category_scores_gemma":[0.0000058272517,0.00023919428,0.000064735024,0.00015277963,0.00009311883,0.00015585373,0.0003182811,0.000270961,0.0000046625178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.810984e-7,0.000003772882,0.000006474807,0.0038176852,0.000018389646,0.00003943438,0.0002728502,0.00006567773,8.082164e-8,0.002024705,0.000018555837,0.9937318],"study_design_scores_gemma":[0.00011597426,0.00004977665,0.00008743874,0.0022467747,0.000040563984,0.00013313175,0.00003028768,0.0024325352,1.3368015e-7,0.0009548656,0.99363697,0.00027154465],"about_ca_topic_score_codex":0.000055242865,"about_ca_topic_score_gemma":0.00012893644,"teacher_disagreement_score":0.9936184,"about_ca_system_score_codex":0.00015365519,"about_ca_system_score_gemma":0.00023981219,"threshold_uncertainty_score":0.975406},"labels":[],"label_agreement":null},{"id":"W4380985881","doi":"10.3389/fradi.2023.1181190","title":"Impact of multi-source data augmentation on performance of convolutional neural networks for abnormality classification in mammography","year":2023,"lang":"en","type":"article","venue":"Frontiers in Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Digital mammography; Mammography; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Breast imaging; Breast cancer; Computer vision; Machine learning; Medicine; Cancer","score_opus":0.06025992123370529,"score_gpt":0.32569505438473684,"score_spread":0.26543513315103157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380985881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5307701,0.000075420925,0.4682176,0.000039935374,0.0006562688,0.0001947505,0.000020958543,0.000020918209,0.000004011869],"genre_scores_gemma":[0.9817341,0.00009821681,0.017918192,0.000015963571,0.000038263155,0.000030443602,0.0001528746,0.000005711337,0.0000062452004],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988502,0.00014128698,0.0003628039,0.00032740657,0.0001004181,0.00021783615],"domain_scores_gemma":[0.999115,0.00012625664,0.00022335218,0.000469333,0.000043258806,0.00002279088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067627995,0.00008848628,0.00021068193,0.00035994357,0.000030144247,0.0000050043213,0.0005909684,0.0001024455,9.460163e-7],"category_scores_gemma":[0.000037429254,0.00008908782,0.000053080254,0.00081398257,0.00012613015,0.00030644113,0.00008169782,0.00012780206,3.4807118e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021248817,0.000040475083,0.61594826,0.000021174288,0.000019403673,3.4324896e-7,0.00013374949,0.35753867,0.00014566432,0.000113722635,0.0015440227,0.024282023],"study_design_scores_gemma":[0.00046572532,0.00018438914,0.4578854,0.000006675337,0.0000017421318,0.0000019138702,0.00001692956,0.54130787,0.0000247463,0.000051951414,0.00001383393,0.000038813974],"about_ca_topic_score_codex":0.00008191015,"about_ca_topic_score_gemma":0.000020138004,"teacher_disagreement_score":0.45096394,"about_ca_system_score_codex":0.00018067526,"about_ca_system_score_gemma":0.000050341296,"threshold_uncertainty_score":0.3632896},"labels":[],"label_agreement":null},{"id":"W4381135038","doi":"10.32920/22734344.v1","title":"An Efficient Confidence Measure-Based Evaluation Metric for Breast Cancer Screening Using Bayesian Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperparameter; Computer science; Artificial neural network; Metric (unit); Transfer of learning; Machine learning; Artificial intelligence; Bayesian network; Feature (linguistics); Coverage probability; Confidence interval; Pattern recognition (psychology); Data mining; Statistics; Mathematics","score_opus":0.10654218833104377,"score_gpt":0.37683245118835923,"score_spread":0.27029026285731544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381135038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002199901,0.00036422088,0.9889952,0.0006409768,0.0049155788,0.0020412814,0.000043980708,0.00078045204,0.000018432338],"genre_scores_gemma":[0.8907208,0.0000056596637,0.10765121,0.00023140984,0.00068618194,0.00060811895,0.00002313441,0.00006322135,0.00001029558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995367,0.00041646586,0.0005877047,0.0015609297,0.0014416084,0.0006262739],"domain_scores_gemma":[0.9962624,0.0003184845,0.00055368175,0.0013465292,0.0013118716,0.0002070836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032018013,0.00044157455,0.00043022216,0.0007576346,0.0003862277,0.00072122965,0.0015162989,0.00036930168,0.000039248847],"category_scores_gemma":[0.00010755713,0.0004521623,0.00024757045,0.0015826239,0.000059547867,0.0003267435,0.00046862217,0.0005845103,0.0000013968705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003710466,0.00001905736,0.00015783522,0.000044465174,0.000032426342,0.000001028014,0.00003815061,0.8294241,0.000057604917,0.00010236992,0.000033265624,0.17005263],"study_design_scores_gemma":[0.0005078968,0.00007085184,0.0029143116,0.0002752228,0.00013503002,0.000008307288,0.00001793137,0.9946971,0.0004166147,0.00044224426,0.0000032250116,0.00051128515],"about_ca_topic_score_codex":0.0030228118,"about_ca_topic_score_gemma":0.0005133666,"teacher_disagreement_score":0.88852084,"about_ca_system_score_codex":0.0011289167,"about_ca_system_score_gemma":0.0009221033,"threshold_uncertainty_score":0.999793},"labels":[],"label_agreement":null},{"id":"W4381188165","doi":"10.1016/j.bspc.2023.105152","title":"Breast cancer diagnosis from histopathology images using deep neural network and XGBoost","year":2023,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Classifier (UML); Computer-aided diagnosis; Artificial neural network; CAD; Extractor; Deep learning; Magnification; Transfer of learning; Breast cancer; Machine learning; Cancer; Medicine","score_opus":0.01284097049723461,"score_gpt":0.25179288770446295,"score_spread":0.23895191720722833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381188165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14224632,0.012810514,0.8365882,0.007031572,0.0006918636,0.00016070786,0.0000528948,0.00040314673,0.000014748702],"genre_scores_gemma":[0.9967644,0.00013571099,0.0014936313,0.00068373175,0.00081687915,0.00008165762,0.0000027970043,0.000011646325,0.000009541201],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986546,0.00008579349,0.00019922694,0.00045693733,0.00023783052,0.00036561475],"domain_scores_gemma":[0.99938285,0.00018210041,0.00009943988,0.00010274466,0.000049872397,0.00018300963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023141432,0.00014579378,0.00022369849,0.000077479875,0.0003429814,0.00017607106,0.00020452899,0.00011111985,0.000025734593],"category_scores_gemma":[0.00001217033,0.00012390625,0.000027672606,0.0004295168,0.00029153549,0.00027290953,0.00012757772,0.00016308836,0.0000029550213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032426484,0.000014064914,0.010071226,0.000024884677,0.000010839832,0.000048471917,0.00014680924,0.00012450737,0.002846891,0.000011356689,0.0004083323,0.9862602],"study_design_scores_gemma":[0.0010002803,0.00007533886,0.053833533,0.0001013663,0.000048067195,0.00012443852,0.000019949262,0.94153666,0.00007394299,0.0019231954,0.001036644,0.00022659202],"about_ca_topic_score_codex":0.00035094563,"about_ca_topic_score_gemma":0.000014113665,"teacher_disagreement_score":0.9860336,"about_ca_system_score_codex":0.000055571887,"about_ca_system_score_gemma":0.000067813424,"threshold_uncertainty_score":0.505275},"labels":[],"label_agreement":null},{"id":"W4382072741","doi":"10.59934/jaiea.v1i3.97","title":"Knearst Algorithm Analysis – Neighbor Breast Cancer Prediction Coimbra","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Algorithm; Breast cancer; k-nearest neighbors algorithm; Regression analysis; Python (programming language); Linear regression; Computer science; Simple linear regression; Regression; Artificial intelligence; Mathematics; Statistics; Machine learning; Cancer; Medicine; Internal medicine","score_opus":0.015106945241228192,"score_gpt":0.2494985985237779,"score_spread":0.2343916532825497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382072741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031620697,0.00038156466,0.99493504,0.0009084565,0.0003649809,0.00011064069,0.00005228198,0.00006317921,0.000021793183],"genre_scores_gemma":[0.96337324,0.00030664811,0.035320785,0.000068111825,0.0006293888,0.00019930968,0.0000049932914,0.000018160008,0.00007933898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987691,0.000024647505,0.0004704659,0.00022072917,0.0003437282,0.00017134522],"domain_scores_gemma":[0.99916583,0.00006214566,0.00023887608,0.00024236692,0.00018797713,0.00010279135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003875499,0.00011234999,0.00018807776,0.0004924661,0.00028295603,0.0001247964,0.0004387795,0.00003691291,0.00014370994],"category_scores_gemma":[0.000007758408,0.00011881584,0.00011899748,0.0018798165,0.000029848561,0.00036252566,0.000118943935,0.00028777565,0.0000061156684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011319436,0.00007258483,0.0001153072,0.000008843864,0.00020511291,0.0000031374295,0.000236326,0.535774,0.0015852797,0.0035825947,0.0001944927,0.458211],"study_design_scores_gemma":[0.000026260543,0.0000998776,0.0017527447,0.0000072344537,0.00013812227,0.00013789622,0.00013681417,0.98397,0.0016039256,0.00077774277,0.0112136025,0.00013580735],"about_ca_topic_score_codex":0.00004524777,"about_ca_topic_score_gemma":0.0000053696954,"teacher_disagreement_score":0.9602112,"about_ca_system_score_codex":0.00021207191,"about_ca_system_score_gemma":0.00007851661,"threshold_uncertainty_score":0.48451692},"labels":[],"label_agreement":null},{"id":"W4382239691","doi":"10.1609/aaai.v37i4.25643","title":"Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Modal; Modalities; Graph; Medical diagnosis; Fuse (electrical); Artificial intelligence; Data mining; Machine learning; Theoretical computer science; Medicine","score_opus":0.21205819958701175,"score_gpt":0.37601068456775266,"score_spread":0.16395248498074091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056312937,0.00002489777,0.93759096,0.0037791482,0.0008374447,0.00056409184,0.000018212915,0.00044954938,0.000422745],"genre_scores_gemma":[0.99235755,0.000076834294,0.007084885,0.00011994457,0.000097298245,0.00006063432,0.000006033784,0.00001592146,0.00018089268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972558,0.000027517524,0.00055855437,0.00086557056,0.0008580949,0.000434435],"domain_scores_gemma":[0.99812764,0.00020622757,0.00036632136,0.00065633387,0.0005117935,0.00013168027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013959813,0.00020980342,0.00032222946,0.00040328273,0.00033615073,0.00023591374,0.0046220585,0.00014033008,0.000049055598],"category_scores_gemma":[0.0013925206,0.00016807932,0.00021436666,0.0029677178,0.00023225638,0.00042660173,0.0012669798,0.00035979686,0.00006959046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002185339,0.0003468643,0.0024912078,0.00018174562,0.0007271791,0.0000047386784,0.0027515418,0.013436509,0.017638206,0.3702981,0.00086268975,0.5910427],"study_design_scores_gemma":[0.000032395285,0.00013360534,0.0001926287,0.00005412369,0.00006438495,0.0000034328118,0.00016084364,0.8962643,0.08044985,0.022282733,0.00018456718,0.00017714678],"about_ca_topic_score_codex":0.000067695284,"about_ca_topic_score_gemma":0.00009094752,"teacher_disagreement_score":0.93604463,"about_ca_system_score_codex":0.000045667173,"about_ca_system_score_gemma":0.0001360656,"threshold_uncertainty_score":0.85890114},"labels":[],"label_agreement":null},{"id":"W4382394973","doi":"10.18280/ts.400337","title":"Diagnosis of Melanoma Using Differential Evolution Optimized Artificial Neural Network","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Differential evolution; Differential (mechanical device); Artificial intelligence; Computer science; Melanoma; Biology; Engineering; Cancer research","score_opus":0.038938670643691366,"score_gpt":0.25941864067606635,"score_spread":0.220479970032375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382394973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5282695,0.000026030319,0.47032312,0.00014367566,0.00086708023,0.00017542884,0.000004079211,0.0001688439,0.000022208278],"genre_scores_gemma":[0.9922505,0.0000070650512,0.0069916174,0.000026075173,0.0006412065,0.000055180946,0.000006488514,0.000012784274,0.000009057464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835205,0.00012475983,0.00039688614,0.00033066675,0.0004336761,0.00036196987],"domain_scores_gemma":[0.9993553,0.00010939023,0.00017700007,0.00023065168,0.00006314355,0.00006447529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028214778,0.00014725943,0.00020922339,0.00015054736,0.00017243631,0.00007109143,0.00038543428,0.00006185234,0.00015411951],"category_scores_gemma":[0.000009584611,0.0001489711,0.00012231442,0.00078368426,0.00005030104,0.00030599398,0.0001653087,0.00009868164,0.000017377764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022166767,0.000181452,0.0067545353,0.000051036044,0.0001251989,0.000020071942,0.00059217616,0.8898874,0.022936322,0.0073106093,0.0022820712,0.06963746],"study_design_scores_gemma":[0.0005019124,0.00015588485,0.016221501,0.00002956219,0.000029529736,0.0000037677692,0.000017107644,0.9741931,0.0067338385,0.0018933064,0.000059007558,0.0001614867],"about_ca_topic_score_codex":0.00007274494,"about_ca_topic_score_gemma":0.000011952821,"teacher_disagreement_score":0.463981,"about_ca_system_score_codex":0.00014118399,"about_ca_system_score_gemma":0.000048460475,"threshold_uncertainty_score":0.6074865},"labels":[],"label_agreement":null},{"id":"W4382806705","doi":"10.1016/j.annonc.2023.04.031","title":"PD-4 Deep learning of pancreatic cancer histopathology images predicts recurrence after surgery","year":2023,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"National Natural Science Foundation of China","keywords":"Medicine; Histopathology; Pancreatic cancer; Cancer; General surgery; Surgery; Radiology; Oncology; Internal medicine; Pathology","score_opus":0.06465485342694925,"score_gpt":0.3504452867392094,"score_spread":0.2857904333122601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382806705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9525207,0.0048695263,0.03263704,0.0046082777,0.002758444,0.00023030017,0.000013497449,0.00028552947,0.0020766417],"genre_scores_gemma":[0.99463725,0.0036083318,0.0010144002,0.00025657678,0.00009406694,0.00012083013,0.0000023077475,0.000010836263,0.00025541344],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99827975,0.0004088386,0.00042674696,0.0003423873,0.0001968109,0.000345476],"domain_scores_gemma":[0.9979954,0.00094652525,0.0003969354,0.00033134036,0.00027002406,0.000059782524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010542761,0.00011686286,0.0004440413,0.00031566934,0.000053126998,0.000006776963,0.0003727424,0.00013609223,0.000052900294],"category_scores_gemma":[0.00047473493,0.00011871226,0.00010549581,0.0007141794,0.0002158904,0.00023155588,0.00021835582,0.00023188909,0.000028614437],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015604825,0.00009611184,0.08897242,0.00022124604,0.00004664734,0.00015227265,0.0025253121,0.0010812811,0.003802477,0.00027615603,0.012063852,0.89060616],"study_design_scores_gemma":[0.000610195,0.0030295586,0.8495319,0.0003805361,0.00006413793,0.00011757519,0.00017426338,0.017456282,0.043580983,0.0052292063,0.07925684,0.00056852814],"about_ca_topic_score_codex":0.00014684409,"about_ca_topic_score_gemma":0.00004703032,"teacher_disagreement_score":0.89003766,"about_ca_system_score_codex":0.00006212174,"about_ca_system_score_gemma":0.00026061427,"threshold_uncertainty_score":0.48409456},"labels":[],"label_agreement":null},{"id":"W4382935262","doi":"10.1109/biosmart58455.2023.10162036","title":"Breast masses detection on mammograms using recent one-shot deep object detectors","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Health Research","keywords":"Breast cancer; Artificial intelligence; Mammography; Computer science; Object detection; Computer vision; Detector; Histogram; Pattern recognition (psychology); Adaptive histogram equalization; Filter (signal processing); Histogram equalization; Cancer; Medicine; Image (mathematics)","score_opus":0.08212860602618581,"score_gpt":0.2994586591583133,"score_spread":0.2173300531321275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382935262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28109246,0.00001635392,0.7123485,0.00039013004,0.0021661224,0.0003134087,0.0000019775466,0.002083721,0.0015873105],"genre_scores_gemma":[0.9876669,0.000055939563,0.011732898,0.0001436952,0.00022986873,0.00003316903,0.0000018182691,0.00003163569,0.00010406841],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99796027,0.00010391162,0.00026337247,0.00064335414,0.0005320161,0.0004970769],"domain_scores_gemma":[0.9988951,0.00010766643,0.00010810338,0.0006524749,0.00011174274,0.00012491984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003510369,0.00021683628,0.00017289066,0.00041432827,0.00030278374,0.00024855803,0.00049333327,0.00012160994,0.0000745313],"category_scores_gemma":[0.000031603297,0.00021273704,0.00009084802,0.0024998097,0.000037730446,0.000506935,0.00020321559,0.0002227416,0.00029341303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036477188,0.000050641967,0.0004914722,0.000018994511,0.000034693334,0.000013446371,0.00016369662,0.0043340116,0.030162161,0.00020599217,0.00008338021,0.96440506],"study_design_scores_gemma":[0.00057684403,0.00055910414,0.01156186,0.00007623665,0.000026951438,0.00033377227,0.00020919036,0.4830762,0.49731556,0.0018462735,0.0036365262,0.0007814623],"about_ca_topic_score_codex":0.00024371882,"about_ca_topic_score_gemma":0.0008423636,"teacher_disagreement_score":0.9636236,"about_ca_system_score_codex":0.0004934703,"about_ca_system_score_gemma":0.00006107647,"threshold_uncertainty_score":0.86751646},"labels":[],"label_agreement":null},{"id":"W4383186319","doi":"10.1002/mp.16574","title":"A hierarchical self‐attention‐guided deep learning framework to predict breast cancer response to chemotherapy using pre‑treatment tumor biopsies","year":2023,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; York University; Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Medicine; Chemotherapy; Oncology; Cancer; Medical physics; Radiology; Internal medicine","score_opus":0.018275465789735938,"score_gpt":0.3124292387929628,"score_spread":0.29415377300322687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383186319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48216867,0.000015239268,0.50861585,0.007652278,0.00058491714,0.00029899753,0.0000064055344,0.0006450879,0.000012517209],"genre_scores_gemma":[0.96440864,0.00005633178,0.030440366,0.0027953265,0.0016531072,0.00031764398,0.0000036227225,0.0000650103,0.0002599405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712604,0.00024634163,0.0003096783,0.0006646309,0.0010878517,0.00056542613],"domain_scores_gemma":[0.9983646,0.00038822167,0.00008218672,0.00051415985,0.000109274675,0.00054154306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059705845,0.00024953223,0.000289653,0.00014943894,0.00029770334,0.0001258485,0.0006462729,0.000120586505,0.0000619938],"category_scores_gemma":[0.00025886894,0.00022331462,0.00011674821,0.0019265338,0.00007284047,0.00019887743,0.00033060505,0.0004013277,0.00014094173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013619377,0.000684396,0.01411196,0.00010852849,0.00041364165,0.00022645177,0.024122184,0.03854198,0.012595652,0.0007313855,0.00243036,0.90467155],"study_design_scores_gemma":[0.002056649,0.0014652617,0.15355901,0.0010295028,0.00006932887,0.00017655597,0.0001542522,0.81623685,0.008915673,0.0070719332,0.0081528565,0.0011121413],"about_ca_topic_score_codex":0.00012362345,"about_ca_topic_score_gemma":0.000008016319,"teacher_disagreement_score":0.9035594,"about_ca_system_score_codex":0.0007266857,"about_ca_system_score_gemma":0.00039640625,"threshold_uncertainty_score":0.91065055},"labels":[],"label_agreement":null},{"id":"W4383199002","doi":"10.2214/ajr.23.29476","title":"Reply to: “Expanding Biopsy Options for Suspicious Breast Lesions: CT-Guided Biopsy Using a 3D-Printed Device”","year":2023,"lang":"en","type":"letter","venue":"American Journal of Roentgenology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Western University","funders":"","keywords":"Medicine; Biopsy; Radiology; Breast biopsy; 3d printed; Mammography; Breast cancer; Internal medicine; Cancer","score_opus":0.05169801580705817,"score_gpt":0.33367650833587265,"score_spread":0.28197849252881446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383199002","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023716625,0.00017593305,0.61425865,0.35659063,0.0044910535,0.00048792083,0.00006574647,0.0001980829,0.0000153569],"genre_scores_gemma":[0.024212161,0.00032804479,0.5932632,0.37250468,0.008539115,0.00016541313,0.00004108876,0.0003802823,0.000566023],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587977,0.00036669846,0.0013705661,0.0008253175,0.0005431604,0.0010144756],"domain_scores_gemma":[0.995071,0.00051212165,0.002330283,0.0009981686,0.00086520927,0.00022321093],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070048374,0.00048621988,0.0011323364,0.0018725878,0.00034218573,0.00016056391,0.002000692,0.00019610747,0.000016509717],"category_scores_gemma":[0.00030182797,0.0004758653,0.00045913775,0.001971423,0.00033089682,0.00029735797,0.00050986663,0.001468622,0.00004653161],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024857774,0.00017653908,0.0010211216,0.00026304807,0.0022915457,0.007131678,0.001622366,0.007773537,0.015212231,0.00027364574,0.7720714,0.19191429],"study_design_scores_gemma":[0.0030904417,0.0060511986,0.0015458378,0.002136277,0.001070689,0.24048233,0.0016658207,0.016384685,0.0016520801,0.002417188,0.7205724,0.0029310347],"about_ca_topic_score_codex":0.00065633835,"about_ca_topic_score_gemma":0.000012825867,"teacher_disagreement_score":0.23335065,"about_ca_system_score_codex":0.0010994276,"about_ca_system_score_gemma":0.00064897945,"threshold_uncertainty_score":0.99976933},"labels":[],"label_agreement":null},{"id":"W4383227235","doi":"10.3390/e25071021","title":"Fuzzy C-Means Clustering: A Review of Applications in Breast Cancer Detection","year":2023,"lang":"en","type":"review","venue":"Entropy","topic":"AI in cancer detection","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; Simon Fraser University; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Initialization; Centroid; Cluster analysis; Computer science; Mahalanobis distance; Artificial intelligence; Segmentation; Fuzzy logic; Python (programming language); Breast cancer; Image segmentation; Pattern recognition (psychology); Data mining; Cancer; Medicine","score_opus":0.039998064258600696,"score_gpt":0.34102148071982,"score_spread":0.30102341646121933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383227235","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.328363e-8,0.8967874,0.101039834,0.0001267332,0.00053550804,0.0011747701,0.00004409506,0.00016227645,0.00012931244],"genre_scores_gemma":[0.000002117837,0.9968176,0.00088364637,0.000047362857,0.00022402206,0.001883723,0.000009879803,0.00003868096,0.00009295805],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980049,0.0001553456,0.0007448991,0.00054378377,0.00029793882,0.0002531223],"domain_scores_gemma":[0.99838823,0.00010197821,0.0005623039,0.00080902816,0.0000797383,0.00005869495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031925697,0.00027049956,0.0009897928,0.0003206733,0.000049571856,0.000029589737,0.0008528658,0.00014960358,0.000018238117],"category_scores_gemma":[0.00001777068,0.0002421638,0.00030273615,0.0020967727,0.000030014231,0.00015516287,0.00025038913,0.00033612733,0.000095997144],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.0396536e-7,0.00001507964,0.0000019936056,0.07176087,0.0000302141,0.000001306971,0.00001768008,0.0000111391355,0.0000013571248,0.0004350827,0.00021287767,0.9275118],"study_design_scores_gemma":[0.00007666915,0.000016340551,0.000020443977,0.08790109,0.00013377881,0.000036977166,0.0000023114003,0.0004823756,0.0000036591002,0.00024405507,0.9108273,0.00025502895],"about_ca_topic_score_codex":0.00020274457,"about_ca_topic_score_gemma":0.00015120907,"teacher_disagreement_score":0.92725676,"about_ca_system_score_codex":0.0006311345,"about_ca_system_score_gemma":0.0002681443,"threshold_uncertainty_score":0.98751533},"labels":[],"label_agreement":null},{"id":"W4383710235","doi":"10.1186/s42492-023-00140-9","title":"Vision transformer architecture and applications in digital health: a tutorial and survey","year":2023,"lang":"en","type":"review","venue":"Visual Computing for Industry Biomedicine and Art","topic":"AI in cancer detection","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Architecture; Computer science; Digital health; Telehealth; Transformer; Artificial intelligence; Digital image processing; Digital image; Segmentation; Telemedicine; Digital imaging; Data science; Health care; Multimedia; Computer vision; Computer architecture; Image processing; Engineering; Image (mathematics); Electrical engineering","score_opus":0.06898679803051441,"score_gpt":0.4118624459068289,"score_spread":0.3428756478763145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383710235","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088752055,0.8489613,0.14525642,0.000554393,0.0010560118,0.002810739,0.00019074074,0.00024978034,0.00003309722],"genre_scores_gemma":[0.0018361827,0.9923433,0.0012816142,0.00019711953,0.0031638474,0.00018136261,0.0006572364,0.000103268365,0.0002360718],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982322,0.00006808731,0.0005532453,0.00064697757,0.00017971738,0.0003198122],"domain_scores_gemma":[0.99868244,0.00073740305,0.00020814192,0.00016622493,0.000034062734,0.00017171432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083448476,0.00029292225,0.00081540627,0.0004388377,0.00020504437,0.0001804576,0.0001863545,0.0004068413,3.2283623e-7],"category_scores_gemma":[0.000056099743,0.00023137564,0.000053005922,0.0009578324,0.00013910144,0.00012952351,0.00014174153,0.00068385585,0.0000013443531],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036478286,0.000018989345,0.00006400357,0.0028380791,0.000019727042,8.937828e-7,0.00013036482,6.64393e-7,2.6565232e-7,0.000053795997,0.00047231038,0.99639726],"study_design_scores_gemma":[0.0005973458,0.00080801017,0.0004252589,0.006046087,0.00003434022,0.000068953,0.000030460533,0.0014341904,4.057925e-7,0.0002836835,0.98995316,0.00031807585],"about_ca_topic_score_codex":0.000056620087,"about_ca_topic_score_gemma":0.000028544653,"teacher_disagreement_score":0.9960792,"about_ca_system_score_codex":0.00005429847,"about_ca_system_score_gemma":0.00020358869,"threshold_uncertainty_score":0.94352245},"labels":[],"label_agreement":null},{"id":"W4383814816","doi":"10.4018/ijirr.316131","title":"A New Scalable Deep Learning Model of Pattern Recognition for Medical Diagnosis Using Model Aggregation and Model Selection","year":2023,"lang":"en","type":"article","venue":"International Journal of Information Retrieval Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Machine learning; Selection (genetic algorithm); Model selection; Artificial neural network; Scalability; Feature selection; Pattern recognition (psychology)","score_opus":0.10088374289027614,"score_gpt":0.3890273448687375,"score_spread":0.2881436019784614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383814816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12187181,0.000024573426,0.8765923,0.00101656,0.00021210323,0.00018050004,0.000008123545,0.00003247148,0.00006159337],"genre_scores_gemma":[0.89906013,0.00080248597,0.09974907,0.00009162025,0.00019048767,0.000013614939,0.000018100627,0.000012855796,0.00006165219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620026,0.000088687266,0.00080414745,0.00013637161,0.0025291205,0.00024141344],"domain_scores_gemma":[0.99492925,0.00046110197,0.00056036474,0.0000871191,0.0037954473,0.00016670866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003621901,0.0000985353,0.00016260747,0.001394762,0.00016580058,0.00025237285,0.0005612857,0.00015331073,0.000013207993],"category_scores_gemma":[0.002721426,0.00009853572,0.00008806833,0.0008446536,0.00004661919,0.0036379867,0.00019878351,0.00049444014,0.0000070236597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001725171,0.000012385311,0.0002402933,0.000032455064,0.00003332292,5.823156e-7,0.0007469565,0.61943185,0.0005486453,0.0003010633,0.0003109672,0.37816894],"study_design_scores_gemma":[0.0008735928,0.0001676385,0.000062104074,0.00019607112,0.000007402579,0.000038929204,0.00008176707,0.96957684,0.009981911,0.018888962,0.000041089377,0.00008371561],"about_ca_topic_score_codex":0.00004533861,"about_ca_topic_score_gemma":0.000008476058,"teacher_disagreement_score":0.7771883,"about_ca_system_score_codex":0.00037659137,"about_ca_system_score_gemma":0.00091957324,"threshold_uncertainty_score":0.401817},"labels":[],"label_agreement":null},{"id":"W4384557826","doi":"10.3390/info14070410","title":"Breast Cancer Detection in Mammography Images: A CNN-Based Approach with Feature Selection","year":2023,"lang":"en","type":"article","venue":"Information","topic":"AI in cancer detection","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Random forest; Support vector machine; Convolutional neural network; Mammography; Feature selection; Pattern recognition (psychology); Classifier (UML); Breast cancer; Feature extraction; Artificial neural network; Machine learning; Cancer; Medicine","score_opus":0.005280063777756617,"score_gpt":0.2072418453120105,"score_spread":0.2019617815342539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384557826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025461446,0.000015222162,0.97140765,0.0007100553,0.0003116906,0.00041750574,0.000010540486,0.00085056416,0.00081531913],"genre_scores_gemma":[0.9937043,0.0000110627225,0.0056760376,0.00017044206,0.00006128056,0.00031877554,0.00002234191,0.000008278057,0.000027488597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900913,0.000037961843,0.00018625952,0.00018360924,0.00034089046,0.00024215724],"domain_scores_gemma":[0.9994489,0.000019272693,0.00014419248,0.00020124952,0.00014502135,0.000041351548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002502758,0.00013059497,0.000096143,0.00084299734,0.00012810876,0.00019719423,0.00020822103,0.00010310557,0.0000040197046],"category_scores_gemma":[0.0000053147655,0.00011735855,0.000037159378,0.003923422,0.000023261095,0.0031260964,0.000026980728,0.00022389951,0.000042421023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024095907,0.000046552563,0.01662505,0.00022262736,0.00002942217,0.0000020193347,0.0018409628,0.21086404,0.0007954225,0.00022617959,0.002278244,0.76682854],"study_design_scores_gemma":[0.00078187225,0.00009216834,0.15403636,0.000050384584,0.000006151697,0.000056998346,0.00012019085,0.8362744,0.007222065,0.00010010972,0.0010289268,0.00023040263],"about_ca_topic_score_codex":0.00036623533,"about_ca_topic_score_gemma":0.00021399402,"teacher_disagreement_score":0.9682428,"about_ca_system_score_codex":0.00028660425,"about_ca_system_score_gemma":0.00010060273,"threshold_uncertainty_score":0.47857428},"labels":[],"label_agreement":null},{"id":"W4385019662","doi":"10.48550/arxiv.2307.10507","title":"FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Public Safety Canada; Compute Canada","keywords":"Overfitting; Computer science; Generalization; Personalization; Code (set theory); Interpolation (computer graphics); Machine learning; Artificial intelligence; Maxima and minima; Distribution (mathematics); Data mining; Distributed computing; Image (mathematics); Artificial neural network; Mathematics","score_opus":0.05828039505646204,"score_gpt":0.19364854109333235,"score_spread":0.1353681460368703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385019662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18101473,0.000022062655,0.8179755,0.00003958051,0.00024310667,0.0002432862,0.0000015641176,0.00034597196,0.00011415246],"genre_scores_gemma":[0.9970793,0.000100364836,0.002058591,0.000030249092,0.000044538152,0.000003393557,0.00003902363,0.000029092422,0.00061541377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830425,0.00019155961,0.00019791597,0.0009801525,0.000093194074,0.00023291948],"domain_scores_gemma":[0.9991839,0.000048298494,0.00027741576,0.00023121788,0.0001982449,0.000060958228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027627728,0.00022885273,0.00019949846,0.0005134022,0.00023998544,0.00021330427,0.00030740848,0.00028187924,0.0000021546946],"category_scores_gemma":[0.000050269085,0.00030912377,0.00005185768,0.0009986471,0.000035504807,0.0007100896,0.0007176185,0.00053465454,0.000007361702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021858703,0.000012448252,0.007714753,0.00006633536,0.000019867548,0.000011789059,0.0010859359,0.9855913,0.0010615765,0.0031356437,0.000015345715,0.001263126],"study_design_scores_gemma":[0.00028722503,0.000039520528,0.001971242,0.000077131954,0.000018261087,0.00000232802,0.000086610555,0.9821439,0.00022488447,0.014861138,0.000002933754,0.00028485255],"about_ca_topic_score_codex":0.00083780824,"about_ca_topic_score_gemma":0.00071538414,"teacher_disagreement_score":0.8160646,"about_ca_system_score_codex":0.000694522,"about_ca_system_score_gemma":0.00016266701,"threshold_uncertainty_score":0.9999361},"labels":[],"label_agreement":null},{"id":"W4385059574","doi":"10.2196/45547","title":"Data-Efficient Computational Pathology Platform for Faster and Cheaper Breast Cancer Subtype Identifications: Development of a Deep Learning Model","year":2023,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Medical Research Council; Medical Research Council; Korea Health Industry Development Institute; National Research Foundation Singapore; National Research Foundation","keywords":"Breast cancer; Computer science; Deep learning; Artificial intelligence; Pathology; Medicine; Computational biology; Cancer; Internal medicine; Biology","score_opus":0.06940561362447524,"score_gpt":0.34248875872351375,"score_spread":0.2730831450990385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385059574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15421756,0.00029177434,0.8438057,0.0005724418,0.00036117889,0.00045334428,0.00014493753,0.00012585949,0.000027248268],"genre_scores_gemma":[0.9529306,0.00006947036,0.045065414,0.00013904173,0.00008970265,0.0013078322,0.000093057424,0.000023513123,0.00028131198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987003,0.000015443638,0.00030309212,0.0004932928,0.00025062505,0.00023722349],"domain_scores_gemma":[0.99918437,0.0000638709,0.00017536781,0.00031345183,0.00021181806,0.00005109651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030299943,0.0001181893,0.00015318542,0.00015274403,0.00020643411,0.000052398256,0.00041945637,0.00006397803,0.000020992422],"category_scores_gemma":[0.000010911503,0.00011601793,0.000024576793,0.00040028407,0.000060665217,0.00030138635,0.00033540398,0.00010401238,0.000010081199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004340213,0.000041021187,0.0011956824,0.00013343013,0.00004089265,9.439762e-7,0.0049702493,0.61299545,0.0015613221,0.0009866572,0.00074430776,0.37728664],"study_design_scores_gemma":[0.00033277457,0.000011887285,0.02817051,0.00003272551,0.000008327101,0.00000806008,0.000085670064,0.9683955,0.00019593752,0.0005101832,0.0021128342,0.00013563696],"about_ca_topic_score_codex":0.000018947303,"about_ca_topic_score_gemma":0.00017785282,"teacher_disagreement_score":0.79874027,"about_ca_system_score_codex":0.00017117006,"about_ca_system_score_gemma":0.00030648365,"threshold_uncertainty_score":0.47310737},"labels":[],"label_agreement":null},{"id":"W4385077980","doi":"10.1016/j.mpdhp.2023.07.001","title":"Benefits and challenges of digital pathology use for primary diagnosis in gynaecological practice: a real-life experience","year":2023,"lang":"en","type":"article","venue":"Diagnostic histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Digital pathology; Telepathology; Workflow; Service (business); Flexibility (engineering); Mainstream; Surgical pathology; Software deployment; Medicine; Pathology; Computer science; Telemedicine; Health care; Business; Marketing","score_opus":0.06320385500724199,"score_gpt":0.2925166338654656,"score_spread":0.22931277885822363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385077980","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98217016,0.004470974,0.0066915895,0.00444696,0.00096687255,0.0006476012,0.000043422002,0.00023098115,0.00033145494],"genre_scores_gemma":[0.9644012,0.02943958,0.004253701,0.00036303603,0.000045349414,0.0014601913,0.000009341093,0.000017926037,0.00000968179],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980172,0.00018697469,0.00044997144,0.00074395275,0.00017105018,0.0004308744],"domain_scores_gemma":[0.98608685,0.012989688,0.00022820312,0.0004604044,0.00012830329,0.00010653444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00052333367,0.00018453147,0.00041775886,0.00031612747,0.00008074255,0.000037980324,0.00041691252,0.000231588,0.0000045855777],"category_scores_gemma":[0.016267553,0.00019008134,0.000054654807,0.00043339253,0.00030423488,0.0008212419,0.00040433626,0.00015497579,0.000012727797],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015283126,0.0007736013,0.32567376,0.00028263027,0.000014676543,0.0018773586,0.01790986,0.00055102876,0.0002620711,0.084639974,0.0007845521,0.56707764],"study_design_scores_gemma":[0.00070160505,0.0009368745,0.99192494,0.000038075348,0.000013753542,0.00022843416,0.00041088788,0.00041638833,0.0000729942,0.0019180562,0.0030873502,0.00025062458],"about_ca_topic_score_codex":0.000023463936,"about_ca_topic_score_gemma":0.000044129312,"teacher_disagreement_score":0.6662512,"about_ca_system_score_codex":0.00012934465,"about_ca_system_score_gemma":0.000097796095,"threshold_uncertainty_score":0.9920188},"labels":[],"label_agreement":null},{"id":"W4385242208","doi":"10.1016/j.ucl.2023.06.001","title":"Artificial Intelligence and Pathomics","year":2023,"lang":"en","type":"review","venue":"Urologic Clinics of North America","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Medicine; Prostate cancer; Histopathology; Deep learning; Artificial intelligence; Cancer; Machine learning; Pathology; Internal medicine; Computer science","score_opus":0.16680836065029353,"score_gpt":0.3770602230364296,"score_spread":0.21025186238613608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385242208","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010517623,0.83493143,0.16336924,0.000067789726,0.0009496503,0.00037019272,0.000038141774,0.0002112268,0.000051782914],"genre_scores_gemma":[0.000021306323,0.9880192,0.011557627,0.00015141301,0.00014761389,0.000045553767,0.000014856705,0.000024867515,0.000017560444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734396,0.00018695733,0.0011735628,0.000759972,0.00024079475,0.0002947368],"domain_scores_gemma":[0.9963869,0.0014043674,0.0011682985,0.00087077526,0.00007562544,0.00009406778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044499544,0.00030964907,0.001302098,0.00021781622,0.00007255398,0.000047213223,0.0012628236,0.00023423214,0.000004433461],"category_scores_gemma":[0.0005270729,0.0002656829,0.0003063105,0.0011275631,0.00028303784,0.00009172651,0.0007772784,0.00056843477,0.00014519425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023308648,0.00002185924,0.000020340087,0.00078206736,0.000031526142,0.000012541187,0.000025324198,0.000057339214,1.9508015e-9,0.0002447817,0.00004943936,0.9987525],"study_design_scores_gemma":[0.000010496009,0.0005838318,0.000018244458,0.00033386977,0.0001352114,0.000018438821,0.000003856673,0.0050779223,1.0227286e-7,0.006344892,0.9871566,0.0003165071],"about_ca_topic_score_codex":0.00001490032,"about_ca_topic_score_gemma":0.000020867386,"teacher_disagreement_score":0.9984359,"about_ca_system_score_codex":0.00003590036,"about_ca_system_score_gemma":0.0002489124,"threshold_uncertainty_score":0.99997956},"labels":[],"label_agreement":null},{"id":"W4385260955","doi":"10.48550/arxiv.2307.11808","title":"Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Classifier (UML); Bilevel optimization; Affine transformation; Machine learning; Pattern recognition (psychology); Transformation (genetics); Deep learning; Optimization problem; Algorithm; Mathematics","score_opus":0.34530193554941285,"score_gpt":0.2655657906388144,"score_spread":0.07973614491059844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385260955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033578016,0.000019206174,0.96385664,0.000071416034,0.0011331453,0.00046310536,0.000035957128,0.0008038461,0.000038650895],"genre_scores_gemma":[0.7605241,0.00008347111,0.23846088,0.00002773266,0.000116733,0.000004476693,0.00021719132,0.00003262789,0.00053278025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801123,0.00017298752,0.00021999252,0.0012471343,0.00010079448,0.00024784345],"domain_scores_gemma":[0.9980895,0.0001817862,0.00038979054,0.0011333375,0.00014283627,0.00006275301],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052535965,0.0002150233,0.00022989673,0.0002858101,0.00029428102,0.00016339173,0.001622407,0.00022047173,0.000019003528],"category_scores_gemma":[0.00016267165,0.00026089587,0.00008546617,0.0004998877,0.00006617879,0.0007991348,0.0025606733,0.00034515816,0.0000178974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008575549,0.000017884844,0.00040054455,0.00009632658,0.000020048807,0.00003076111,0.000077716584,0.9952223,0.00007565689,0.0007607256,0.00016175608,0.0031277158],"study_design_scores_gemma":[0.00029774354,0.00004870168,0.0005223526,0.00008025116,0.00007629603,0.000005088366,0.000046242854,0.9919597,0.00007575195,0.0065651312,0.00005025255,0.00027251113],"about_ca_topic_score_codex":0.00008319988,"about_ca_topic_score_gemma":0.0000073133447,"teacher_disagreement_score":0.7269461,"about_ca_system_score_codex":0.00063989,"about_ca_system_score_gemma":0.00018813452,"threshold_uncertainty_score":0.9999843},"labels":[],"label_agreement":null},{"id":"W4385264945","doi":"10.1097/pai.0000000000001145","title":"Toward a Total Dataization of Anatomic Pathology: Are You Ready?","year":2023,"lang":"en","type":"editorial","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; McGill University","funders":"","keywords":"Library science; Medicine; Family medicine; Pathology; Gerontology; Computer science","score_opus":0.009035889730501701,"score_gpt":0.25513194629372316,"score_spread":0.24609605656322145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385264945","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0125747165,0.0015596503,0.15896747,0.00022022262,0.823221,0.00070855493,0.0005828701,0.0008595489,0.001305954],"genre_scores_gemma":[0.48504785,0.0015003799,0.03734451,0.000576368,0.44444796,0.003663004,0.022683395,0.001473109,0.0032634358],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995641,0.00011097172,0.0009604861,0.0017506953,0.00084190123,0.00069496996],"domain_scores_gemma":[0.9949037,0.0002916355,0.0013758137,0.0028973075,0.00042206587,0.000109464396],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005005346,0.0006756054,0.0010444913,0.00027819746,0.00012105038,0.00006296337,0.0025554793,0.002060522,0.000025896003],"category_scores_gemma":[0.0005353442,0.000840675,0.0002317515,0.00079247775,0.00042420442,0.00011860805,0.0013381365,0.0014288997,0.00014112306],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005033805,0.000040033952,4.376657e-7,0.00018556335,0.000099455945,0.00034284755,0.00008133082,0.00006703518,0.672836,0.0002638864,0.3251444,0.00088866305],"study_design_scores_gemma":[0.0035617203,0.0004445222,0.00005110276,0.00034367928,0.00049877027,0.0006424841,0.00023178532,0.0007489912,0.90421826,0.0037734776,0.082329914,0.0031553283],"about_ca_topic_score_codex":0.00010562914,"about_ca_topic_score_gemma":2.5672193e-7,"teacher_disagreement_score":0.4724731,"about_ca_system_score_codex":0.0007402077,"about_ca_system_score_gemma":0.00067953067,"threshold_uncertainty_score":0.99940443},"labels":[],"label_agreement":null},{"id":"W4385274786","doi":"10.1016/j.mpdhp.2023.07.002","title":"An overview of artificial intelligence applications for next-generation gynaecological pathology","year":2023,"lang":"en","type":"article","venue":"Diagnostic histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"UK Research and Innovation","keywords":"Digital pathology; Telepathology; Computer science; Pathology; Medicine; Artificial intelligence; Telemedicine","score_opus":0.19135884384001856,"score_gpt":0.3661635388011782,"score_spread":0.17480469496115963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385274786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028136266,0.00040311462,0.96877295,0.0004824809,0.0011705067,0.00067532173,0.000020287727,0.00027194398,0.0000671222],"genre_scores_gemma":[0.9535377,0.0003433858,0.04325297,0.00037525088,0.0003193941,0.0020556576,0.00007928392,0.00001631921,0.000020044656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841565,0.00019139588,0.00043368884,0.00055232854,0.00011946671,0.00028748382],"domain_scores_gemma":[0.9976704,0.0013155116,0.00017604114,0.00061109534,0.00016000554,0.00006692982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060992857,0.00012590222,0.00024812538,0.00021355774,0.00016709839,0.000025152423,0.0006244137,0.00017449842,0.00003922568],"category_scores_gemma":[0.0008847798,0.00013223111,0.000073326446,0.00064603804,0.00017587254,0.0002164574,0.00010320133,0.000105444175,0.000116337855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070162223,0.00019623195,0.0003670985,0.000046055447,0.0000029617229,0.000050051123,0.0006298893,0.0019486969,0.030582415,0.397711,0.0006320042,0.56782657],"study_design_scores_gemma":[0.00039216477,0.0042102607,0.041827846,0.00002438484,0.00009496836,0.0003262137,0.00027554677,0.559493,0.029346116,0.34472582,0.018267266,0.0010163939],"about_ca_topic_score_codex":0.00000597581,"about_ca_topic_score_gemma":0.000039022914,"teacher_disagreement_score":0.92552,"about_ca_system_score_codex":0.000083024555,"about_ca_system_score_gemma":0.0000864088,"threshold_uncertainty_score":0.53922284},"labels":[],"label_agreement":null},{"id":"W4385386780","doi":"10.18280/ria.370315","title":"Classification of Thyroid Nodules Using Follow the Regularized Leader Optimization Based Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thyroid nodules; Artificial neural network; Artificial intelligence; Deep neural networks; Computer science; Thyroid; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.07066258820118834,"score_gpt":0.2809815651429256,"score_spread":0.21031897694173726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385386780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063494146,0.0001412908,0.9904575,0.0015947485,0.00075853965,0.00031013603,0.0000010920173,0.00021842633,0.00016886953],"genre_scores_gemma":[0.9748034,0.00003253398,0.024763282,0.00010264691,0.00011380095,0.000031736738,0.000010623951,0.000020457912,0.00012150952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983605,0.00016872195,0.00047115164,0.00042438612,0.0002682211,0.00030701977],"domain_scores_gemma":[0.99829435,0.00028779262,0.00028203707,0.00089655956,0.00019305892,0.000046181278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068760256,0.0001486603,0.00017213378,0.0001669893,0.0002951023,0.000111993315,0.0007867304,0.000102378166,0.000026905596],"category_scores_gemma":[0.00011874559,0.00012699781,0.0001227507,0.0019907253,0.00013453607,0.00033765507,0.00011799527,0.00017857178,0.000029266865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012952392,0.000019342117,0.000095955664,0.000014738087,0.0000071420086,0.0000012925482,0.0003537781,0.97342014,0.0077038044,0.0014862933,0.000055506498,0.016829055],"study_design_scores_gemma":[0.00004990117,0.00005215106,0.00010680949,0.000029038536,0.000012416998,0.0000056699046,0.00029456877,0.9833693,0.0154684,0.0003970404,0.00008058402,0.00013410207],"about_ca_topic_score_codex":0.000027834703,"about_ca_topic_score_gemma":0.0000133595795,"teacher_disagreement_score":0.968454,"about_ca_system_score_codex":0.000084696214,"about_ca_system_score_gemma":0.00004030764,"threshold_uncertainty_score":0.51788205},"labels":[],"label_agreement":null},{"id":"W4385424183","doi":"10.1007/s11042-023-16279-9","title":"Combining frequency transformer and CNNs for medical image segmentation","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Computation; Image segmentation; Transformer; Scale-space segmentation; Segmentation-based object categorization; Pattern recognition (psychology); Computer vision; Algorithm","score_opus":0.024640237170712002,"score_gpt":0.30169650946548776,"score_spread":0.27705627229477575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385424183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006689115,0.00007094331,0.98867327,0.003129138,0.00008923427,0.00070514483,0.000039087034,0.00021873934,0.00038533652],"genre_scores_gemma":[0.51349884,0.0012548626,0.47497517,0.00078516157,0.0005116411,0.008418564,0.00025959764,0.00004284642,0.00025328324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992748,0.000011022481,0.0001543318,0.00025781695,0.00015199765,0.00015003174],"domain_scores_gemma":[0.9994119,0.00026899687,0.000035758265,0.00014226604,0.00003885108,0.0001022643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020775311,0.00007302009,0.00008095218,0.000056664052,0.0002189961,0.0001066729,0.00014875377,0.000056369718,0.000009924189],"category_scores_gemma":[0.000031575815,0.00007073953,0.000020668465,0.0002590068,0.000069958274,0.00035326433,0.000028470133,0.00006916381,0.000019386274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018641691,0.000018513261,0.0002516253,0.000035039426,0.000009771894,4.919176e-7,0.0008592229,0.0000029305418,0.01596954,0.009186648,0.0005134088,0.97315097],"study_design_scores_gemma":[0.004584926,0.00030216537,0.032112867,0.000083643914,0.00006513883,0.000046638685,0.0008914781,0.8219722,0.032003213,0.061389584,0.04567429,0.0008738882],"about_ca_topic_score_codex":0.000016719474,"about_ca_topic_score_gemma":0.000014426843,"teacher_disagreement_score":0.97227705,"about_ca_system_score_codex":0.000017465141,"about_ca_system_score_gemma":0.000036063433,"threshold_uncertainty_score":0.28846744},"labels":[],"label_agreement":null},{"id":"W4385431541","doi":"10.1016/j.compmedimag.2023.102276","title":"Invasion depth estimation of carcinoma cells using adaptive stain normalization to improve epidermis segmentation accuracy","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Epidermis (zoology); Stain; Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Pathology; Computer vision; Biology; Anatomy; Medicine; Staining","score_opus":0.02803492667397791,"score_gpt":0.3012182966454943,"score_spread":0.27318336997151643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385431541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25360528,0.000041803956,0.7447636,0.0005863728,0.0006088678,0.00023402418,0.0000026088878,0.00015153136,0.0000059136787],"genre_scores_gemma":[0.9099604,0.00008091152,0.0893191,0.0005190938,0.000075265234,0.000014908682,0.000014139161,0.000013416239,0.0000027881729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820745,0.00015378984,0.00039933817,0.0004123019,0.0005745484,0.00025256968],"domain_scores_gemma":[0.9988118,0.0003262364,0.00020733163,0.00028012277,0.00016237669,0.00021214782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007280762,0.00015323126,0.00021696054,0.00042112416,0.00016804949,0.000092629045,0.00030003715,0.000072014336,0.0000014907553],"category_scores_gemma":[0.00020785652,0.00015489511,0.00004862254,0.0012672124,0.00009259358,0.00061226956,0.00035294527,0.0001488226,0.0000029348234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048649123,0.000106909545,0.0011916093,0.0002211359,0.000027739256,0.000038365117,0.0025723302,0.006750562,0.03504993,0.002347808,0.0005064839,0.9511385],"study_design_scores_gemma":[0.0010560147,0.00007555385,0.00213173,0.00012972238,0.000012476286,0.000016859049,0.0000739346,0.97135615,0.023136698,0.0018221429,0.00003756377,0.0001511248],"about_ca_topic_score_codex":0.00016743176,"about_ca_topic_score_gemma":0.0000073172805,"teacher_disagreement_score":0.9646056,"about_ca_system_score_codex":0.000065270266,"about_ca_system_score_gemma":0.00014874696,"threshold_uncertainty_score":0.63164395},"labels":[],"label_agreement":null},{"id":"W4385716142","doi":"10.1002/jdd.13358","title":"Implementation and evaluation of a virtual microscope to teach oral histology","year":2023,"lang":"en","type":"article","venue":"Journal of Dental Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Library science; Medicine; Dentistry; Medical education; Family medicine","score_opus":0.03138056683053807,"score_gpt":0.40996976474280566,"score_spread":0.3785891979122676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385716142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849188,0.00010186753,0.011653889,0.0007995184,0.0022877716,0.00015381252,9.722855e-7,0.000009892782,0.00007348945],"genre_scores_gemma":[0.9947312,0.000014822278,0.004959155,0.0001060887,0.00009859547,0.000009903711,0.0000022614836,0.0000041024746,0.000073891],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999015,0.00011310029,0.00030596892,0.000106609215,0.00037804595,0.000081307284],"domain_scores_gemma":[0.9991838,0.000026672102,0.0003071815,0.00009697768,0.00033240765,0.000052997984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010392201,0.000050663537,0.0000962446,0.000363308,0.000042297277,0.00003087132,0.00016188761,0.000027006628,0.000029681301],"category_scores_gemma":[0.000055287976,0.000051061365,0.000026953016,0.00042290756,0.000016788885,0.00044288227,0.000050441115,0.00006375471,0.000016026757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033630433,0.000095221054,0.008782283,0.000012924839,0.000023497036,6.3331754e-7,0.0041959514,0.00023916402,0.109680966,0.00070445257,0.018382287,0.857849],"study_design_scores_gemma":[0.0033843713,0.003481723,0.74832344,0.00016525919,0.00023426351,0.00093963026,0.024478188,0.011587614,0.19091561,0.004992842,0.011072265,0.00042478167],"about_ca_topic_score_codex":0.00006738758,"about_ca_topic_score_gemma":0.00006222089,"teacher_disagreement_score":0.8574242,"about_ca_system_score_codex":0.00035066306,"about_ca_system_score_gemma":0.00048528082,"threshold_uncertainty_score":0.2082222},"labels":[],"label_agreement":null},{"id":"W4385768519","doi":"10.1101/2023.08.05.23293672","title":"Photon Absorption Remote Sensing Imaging of Breast Needle Core Biopsies is Diagnostically Equivalent to Gold Standard H&amp;E Histologic Assessment","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Illumisonics (Canada); University of Waterloo","funders":"","keywords":"Concordance; Gold standard (test); Histology; Breast cancer; Medicine; Kappa; Pathology; Nuclear medicine; Cancer; Radiology; Internal medicine; Mathematics","score_opus":0.06556382899463968,"score_gpt":0.3324432181345736,"score_spread":0.2668793891399339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385768519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25482067,0.000109792476,0.7359877,0.0041039567,0.0034473126,0.0005603594,0.00009891709,0.000492374,0.00037887835],"genre_scores_gemma":[0.7852496,0.00025674206,0.21335675,0.00043777403,0.00023130294,0.000015754647,0.00002242689,0.000067798625,0.00036187848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962976,0.00014554095,0.00076111406,0.001233329,0.0010318332,0.0005305655],"domain_scores_gemma":[0.9968602,0.00033921565,0.00054058485,0.0015774424,0.0004934686,0.00018909186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011247112,0.00043583132,0.00063392357,0.00049772573,0.00010979132,0.00019656369,0.0010625914,0.00021222731,0.000029312952],"category_scores_gemma":[0.00024268497,0.00044575657,0.0002269869,0.0006410238,0.00013541708,0.00016280025,0.0024433702,0.0006670702,0.00007363489],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003694073,0.00022944344,0.06567283,0.0031062046,0.00050123804,0.0005325254,0.008509503,0.017660592,0.09465696,0.0015809808,0.02714049,0.78003985],"study_design_scores_gemma":[0.0014165925,0.0007070506,0.24316657,0.0067773736,0.00036258475,0.0005460197,0.00035951575,0.63347185,0.03293054,0.06218468,0.014585405,0.0034918184],"about_ca_topic_score_codex":0.000855193,"about_ca_topic_score_gemma":0.00010774439,"teacher_disagreement_score":0.776548,"about_ca_system_score_codex":0.0012630101,"about_ca_system_score_gemma":0.00034036857,"threshold_uncertainty_score":0.99979943},"labels":[],"label_agreement":null},{"id":"W4385841175","doi":"10.1259/bjro.20230008","title":"The effect of spatial resolution on deep learning classification of lung cancer histopathology","year":2023,"lang":"en","type":"article","venue":"BJR|Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Okanagan University College; University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"BC Cancer Foundation","keywords":"Histopathology; Lung cancer; Adenocarcinoma; Pathology; Convolutional neural network; Cancer; Medicine; Artificial intelligence; Computer science; Internal medicine","score_opus":0.026259926496100986,"score_gpt":0.32959642790054444,"score_spread":0.30333650140444346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385841175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63779235,0.00085240806,0.32925677,0.0047789398,0.00511983,0.0034408371,0.000009469001,0.00040609672,0.01834326],"genre_scores_gemma":[0.99892163,0.00006358403,0.00025909225,0.000015200924,0.00005763524,0.000185948,0.0000030459248,0.000008520489,0.0004853392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878657,0.00040018596,0.0002125032,0.00025776448,0.0001916876,0.00015126585],"domain_scores_gemma":[0.9988553,0.00035467104,0.00028731336,0.00042147693,0.00006118732,0.000020028823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011483909,0.00007304993,0.00014773948,0.00007377973,0.00020628469,0.000057142915,0.0012123208,0.00005679612,0.00000916567],"category_scores_gemma":[0.000176615,0.00005559354,0.000033635803,0.0004051507,0.00006030202,0.00019616273,0.00041207412,0.00013730537,0.000016943493],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048743704,0.000022221748,0.027470006,0.00008781704,0.000025723584,0.0000037399186,0.0010161801,0.0105415005,0.036769357,0.008468331,0.0032419416,0.9118658],"study_design_scores_gemma":[0.0007919169,0.0011066701,0.41642672,0.00010358788,0.000021032874,0.000003354146,0.000022821108,0.53709775,0.03274807,0.00049713964,0.011036953,0.00014400609],"about_ca_topic_score_codex":0.0012482849,"about_ca_topic_score_gemma":0.0005109984,"teacher_disagreement_score":0.91172177,"about_ca_system_score_codex":0.00019169967,"about_ca_system_score_gemma":0.000058972906,"threshold_uncertainty_score":0.22670387},"labels":[],"label_agreement":null},{"id":"W4386084036","doi":"10.1002/path.6155","title":"Pitfalls in machine learning‐based assessment of tumor‐infiltrating lymphocytes in breast cancer: A report of the International Immuno‐Oncology Biomarker Working Group on Breast Cancer","year":2023,"lang":"en","type":"review","venue":"The Journal of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of British Columbia; University of Guelph; Sunnybrook Health Science Centre; Health Sciences Centre; BC Cancer Agency","funders":"DOD Prostate Cancer Research Program; National Institute of Biomedical Imaging and Bioengineering; National Institute of Diabetes and Digestive and Kidney Diseases; Gilead Sciences; National Cancer Institute; National Institutes of Health; KU Leuven; Agence Nationale de la Recherche; Irish Cancer Society; Engineering and Physical Sciences Research Council; Science Foundation Ireland; Peter MacCallum Cancer Centre; U.S. Department of Veterans Affairs; National Breast Cancer Foundation; Japan Society for the Promotion of Science; Cancer Research Institute; National Health and Medical Research Council; European Commission; Svenska Sällskapet för Medicinsk Forskning; Cancer Research UK; Breast Cancer Now; Higher Education Authority; U.S. Department of Defense; DOD Peer Reviewed Cancer Research Program; Breast Cancer Research Foundation; National Center for Advancing Translational Sciences; Medical Research Council; Mayo Clinic","keywords":"Breast cancer; Oncology; Medicine; Internal medicine; Tumor-infiltrating lymphocytes; Biomarker; Cancer; Biology; Immunotherapy","score_opus":0.053811492697129655,"score_gpt":0.3746130460595623,"score_spread":0.32080155336243266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386084036","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018264523,0.95504034,0.0069160364,0.005490171,0.012005517,0.0015158937,0.00016697338,0.00006385871,0.0005367088],"genre_scores_gemma":[0.100534536,0.8976166,0.0011506979,0.00016888797,0.000336959,0.000098595265,0.00000469063,0.00005954309,0.000029477835],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99476314,0.0018977445,0.0020843842,0.00032469677,0.00062267383,0.000307355],"domain_scores_gemma":[0.9926132,0.0010718083,0.005531398,0.0005210277,0.00022689602,0.000035668872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052802404,0.00030997442,0.0014108018,0.0007301849,0.00007001846,0.000024025827,0.0020176645,0.00020698964,0.000030031808],"category_scores_gemma":[0.00012332154,0.00018784785,0.00037000753,0.0012211235,0.00019494239,0.000119200355,0.00044782113,0.0012100146,6.211063e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022426048,0.00029117987,0.021710157,0.0012484917,0.0003715526,0.0016024978,0.00052620796,0.01089626,0.00086312107,0.00014754897,0.00006946825,0.96204925],"study_design_scores_gemma":[0.010316241,0.0023597286,0.41176316,0.16892846,0.0018022032,0.2153778,0.00054712995,0.098461494,0.00027320898,0.0010842688,0.08675276,0.0023335665],"about_ca_topic_score_codex":0.0013638021,"about_ca_topic_score_gemma":0.0013354224,"teacher_disagreement_score":0.95971566,"about_ca_system_score_codex":0.0023181327,"about_ca_system_score_gemma":0.0024639284,"threshold_uncertainty_score":0.7660213},"labels":[],"label_agreement":null},{"id":"W4386158194","doi":"10.1021/acs.analchem.3c00613","title":"Early Diagnosis: End-to-End CNN–LSTM Models for Mass Spectrometry Data Classification","year":2023,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de Recherche du Québec - Santé; Société d'Accélération du Transfert de Technologies; Ministère de l'Enseignement supérieur, de la Recherche et de l'Innovation; Institut National Du Cancer; Institut National de la Santé et de la Recherche Médicale; Agence Nationale de la Recherche; Université de Lille","keywords":"Artificial intelligence; Computer science; Preprocessor; Convolutional neural network; Benchmark (surveying); Pattern recognition (psychology); Deep learning; Curse of dimensionality; Data pre-processing; Feature selection; Machine learning","score_opus":0.0966839250659563,"score_gpt":0.3227062023904667,"score_spread":0.2260222773245104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386158194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016124524,0.00004476616,0.97303396,0.0047162003,0.00020090163,0.00021406842,0.00009411397,0.00047414648,0.005097298],"genre_scores_gemma":[0.9701869,0.000041902058,0.027166437,0.00022399348,0.00047590613,0.00018236774,0.00012993698,0.000026579897,0.0015660126],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782985,0.000016113243,0.00030002883,0.00093952665,0.0004632951,0.00045116176],"domain_scores_gemma":[0.9975231,0.00032752636,0.00007669274,0.0017454574,0.000098284174,0.00022889029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044203564,0.00017116238,0.00020110214,0.00009938024,0.00011350891,0.00020800965,0.0018023964,0.00014407568,0.00007611391],"category_scores_gemma":[0.00025671694,0.00018148858,0.00008546358,0.0013770424,0.000054748478,0.0005824312,0.00049104064,0.00020991426,0.00018573394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027180655,0.0008216576,0.007670308,0.0014296318,0.0011642651,0.00016208524,0.0009650288,0.009025067,0.2921442,0.07683145,0.41693798,0.1925765],"study_design_scores_gemma":[0.00021057551,0.000044431283,0.0017712663,0.000025543526,0.000040058407,0.0000034829627,0.000032757696,0.9447228,0.03317556,0.014946148,0.004755635,0.0002717959],"about_ca_topic_score_codex":0.000021571212,"about_ca_topic_score_gemma":0.0000017521102,"teacher_disagreement_score":0.95406234,"about_ca_system_score_codex":0.00020694137,"about_ca_system_score_gemma":0.00010130218,"threshold_uncertainty_score":0.74008894},"labels":[],"label_agreement":null},{"id":"W4386215890","doi":"10.32920/24043227","title":"Semi-Supervised Learning Approach for Bladder Cancer Diagnosis","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Leverage (statistics); Computer science; Artificial intelligence; Regularization (linguistics); Machine learning; Semi-supervised learning; Deep learning; Labeled data; Supervised learning; Consistency (knowledge bases); Pattern recognition (psychology); Artificial neural network","score_opus":0.07775395249087082,"score_gpt":0.308579458840713,"score_spread":0.23082550634984217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386215890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006758856,0.0003754241,0.9895758,0.0016124792,0.0027318445,0.0010007016,0.00002190693,0.0016700566,0.002335907],"genre_scores_gemma":[0.1558233,0.0033648445,0.7383998,0.0013723096,0.0033167403,0.06174864,0.00017727041,0.0003390813,0.03545798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997452,0.00008301056,0.0003313584,0.0012845418,0.00039138008,0.00045768093],"domain_scores_gemma":[0.99838424,0.00025556673,0.00018163078,0.000882568,0.0001925274,0.00010347517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044201355,0.00033278484,0.00036184033,0.00020411384,0.00021012417,0.0003615937,0.001463104,0.00038265125,0.00009625828],"category_scores_gemma":[0.000082580045,0.00032606593,0.00025358744,0.0003850077,0.000034176333,0.00021401362,0.0019350713,0.0007569965,0.000039290462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002010112,0.00011074046,0.0053126137,0.0010554774,0.00053500035,0.000004253439,0.0022562977,0.621927,0.0000985851,0.0021049087,0.12117506,0.24539992],"study_design_scores_gemma":[0.00027676325,0.000051447154,0.0004076467,0.00007475638,0.00003989393,0.000001204687,0.000058037665,0.97867715,0.0019769322,0.0027073824,0.015221441,0.00050736876],"about_ca_topic_score_codex":0.0010233689,"about_ca_topic_score_gemma":0.00008877668,"teacher_disagreement_score":0.3567501,"about_ca_system_score_codex":0.00033780388,"about_ca_system_score_gemma":0.00027478224,"threshold_uncertainty_score":0.9999191},"labels":[],"label_agreement":null},{"id":"W4386274114","doi":"10.1109/iri58017.2023.00054","title":"Cost Efficient Mammogram Segmentation and Classification with NeuroMem® Chip for Breast Cancer Detection","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Artificial neural network; Breast cancer; Pattern recognition (psychology); Mammography; Feature extraction; Image segmentation; Chip; Anomaly detection; Computer vision; Cancer; Medicine; Telecommunications","score_opus":0.038508518446706164,"score_gpt":0.292496976735301,"score_spread":0.25398845828859484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386274114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1750001,0.0000085826405,0.82195777,0.0013413526,0.00041025796,0.0007125749,0.000011869791,0.00047580956,0.00008171337],"genre_scores_gemma":[0.994523,0.000030309264,0.004393765,0.00011180907,0.00007677482,0.0006824687,0.0000050748963,0.00001374215,0.00016305762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909055,0.000024892537,0.00012203304,0.00038084193,0.00019164903,0.00019005645],"domain_scores_gemma":[0.9995127,0.00005565332,0.00007943397,0.0002008906,0.000094636845,0.00005672964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001631424,0.00009846687,0.000071784656,0.00015067526,0.000192604,0.00014253479,0.00012432625,0.000037999434,0.0000056106805],"category_scores_gemma":[0.0000049877353,0.000082981,0.000019348518,0.00076773996,0.00003170445,0.00024234233,0.000038474005,0.000057112076,0.000012697778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006321297,0.00002225012,0.0011305321,0.000036224603,0.000013064788,6.0301517e-7,0.0002626529,0.004986398,0.027728463,0.00048848416,0.00019181358,0.9650763],"study_design_scores_gemma":[0.0005436524,0.00015055492,0.22696088,0.000012788419,0.00001128396,0.000031790754,0.0001031686,0.75391793,0.017573858,0.000108125474,0.0004460674,0.0001398821],"about_ca_topic_score_codex":0.000054101693,"about_ca_topic_score_gemma":0.00022054878,"teacher_disagreement_score":0.96493644,"about_ca_system_score_codex":0.00012799747,"about_ca_system_score_gemma":0.000033503708,"threshold_uncertainty_score":0.3383867},"labels":[],"label_agreement":null},{"id":"W4386331794","doi":"10.18280/ts.400444","title":"Classification and Diagnosis of Mammary Tumors in Dogs Using Deep Learning Techniques","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Burdur Mehmet Akif Ersoy Üniversitesi","keywords":"Deep learning; Artificial intelligence; Computer science; Medicine","score_opus":0.03448578612135991,"score_gpt":0.2736170234912668,"score_spread":0.2391312373699069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386331794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6611827,0.00006388484,0.33787555,0.0002964462,0.0000493772,0.00019117347,4.968323e-7,0.00022803397,0.000112326685],"genre_scores_gemma":[0.98343307,0.00009668339,0.016329193,0.000027904909,0.000028839217,0.00006984213,0.000001618096,0.0000065745107,0.0000062583117],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991252,0.000074359144,0.00023000318,0.00023204078,0.00019405477,0.00014434106],"domain_scores_gemma":[0.99963343,0.0000811739,0.00010757614,0.000119438606,0.00003065074,0.000027736027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004343929,0.000076695134,0.00010365706,0.00026479494,0.000058548994,0.000043292006,0.00020064293,0.00003720339,0.000008295585],"category_scores_gemma":[0.00001307048,0.0000824033,0.00002203352,0.00061117724,0.00003082826,0.00037470364,0.00010384517,0.00009861921,0.0000018351939],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017985825,0.00008503711,0.26854405,0.0001333014,0.000019781184,0.000023226681,0.0027006706,0.002565851,0.08931388,0.005639211,0.000084452215,0.63087255],"study_design_scores_gemma":[0.00028029803,0.00020381887,0.3363826,0.00014094691,0.00000642984,0.000008546152,0.00013955966,0.6085332,0.051858064,0.0018480651,0.00041004657,0.00018845068],"about_ca_topic_score_codex":0.000077335135,"about_ca_topic_score_gemma":0.000015781616,"teacher_disagreement_score":0.63068414,"about_ca_system_score_codex":0.00009026067,"about_ca_system_score_gemma":0.000023478575,"threshold_uncertainty_score":0.3360309},"labels":[],"label_agreement":null},{"id":"W4386346473","doi":"10.1158/0008-5472.can-23-1856","title":"Using Machine Learning to Predict <i>TP53</i> Mutation Status and Aggressiveness of Prostate Cancer from Routine Histology Images","year":2023,"lang":"en","type":"letter","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval","funders":"","keywords":"Prostate cancer; Cancer; Biomarker; Mutation; Histology; Medicine; Oncology; Prostate; Internal medicine; Biology; Genetics; Gene","score_opus":0.07832069754635498,"score_gpt":0.39128608212138694,"score_spread":0.312965384575032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386346473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47771645,0.06991752,0.030417286,0.40296176,0.00919397,0.0049944855,0.0037276235,0.00090310146,0.00016783131],"genre_scores_gemma":[0.6724339,0.082823604,0.03567077,0.13078964,0.030761957,0.0129174,0.0020739185,0.002303829,0.030224942],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951214,0.00083586323,0.00048924,0.0012318571,0.0012744712,0.0010471713],"domain_scores_gemma":[0.9973869,0.0006383078,0.0004141148,0.00063969835,0.0007573989,0.00016361884],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00077915296,0.0003362748,0.0005830881,0.0008287507,0.00033458034,0.00018141924,0.00086170883,0.00040571773,0.000054935354],"category_scores_gemma":[0.00025666124,0.00034087914,0.00006628579,0.0014353257,0.00033942537,0.00024383121,0.000996815,0.0025453132,0.00001197834],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092692446,0.000070801034,0.058830265,0.0039037948,0.0008788301,0.0022685705,0.016207745,0.039378542,0.09703569,0.000033498527,0.46844536,0.31201997],"study_design_scores_gemma":[0.0032808043,0.0013287822,0.007450351,0.006673541,0.00021381468,0.000057996676,0.00026948092,0.08244542,0.10022372,0.002391714,0.7935356,0.0021288148],"about_ca_topic_score_codex":0.056970466,"about_ca_topic_score_gemma":0.001334807,"teacher_disagreement_score":0.32509023,"about_ca_system_score_codex":0.0015095804,"about_ca_system_score_gemma":0.0011495764,"threshold_uncertainty_score":0.99990433},"labels":[],"label_agreement":null},{"id":"W4386362546","doi":"10.1109/isbi53787.2023.10230503","title":"Improved HER2 Tumor Segmentation with Subtype Balancing Using Deep Generative Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"HORIZON EUROPE Health","keywords":"Overfitting; Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Generative adversarial network; Deep learning; Artificial neural network","score_opus":0.015904967455093875,"score_gpt":0.2513116573462662,"score_spread":0.23540668989117233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386362546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09151932,0.000020755935,0.9071408,0.000099562145,0.00047038583,0.00016387834,1.8564369e-7,0.00038612098,0.00019901407],"genre_scores_gemma":[0.8195504,0.000005414486,0.17960541,0.00038842237,0.00020478372,0.000024934494,0.0000030187427,0.000015747451,0.0002018706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991331,0.000041111965,0.00012449057,0.00030670429,0.00015711706,0.00023743889],"domain_scores_gemma":[0.9995381,0.000036875845,0.00008149606,0.0002237357,0.000073237155,0.000046522204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016654309,0.00010243903,0.000088374974,0.00007560601,0.00016532911,0.00013658313,0.000184153,0.000027872758,0.000014384631],"category_scores_gemma":[0.00000564794,0.00008494447,0.000019433446,0.00086739403,0.000018047196,0.0004963026,0.000088204615,0.00008772027,0.000015442412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058535352,0.000027125181,0.0057540354,0.000027643531,0.000086608474,0.00005573069,0.002409922,0.8120053,0.09677323,0.0015604991,0.0007404827,0.08050092],"study_design_scores_gemma":[0.00020050796,0.00009395827,0.0011837411,0.000008840275,0.0000045717943,0.00001610115,0.00014520234,0.97534215,0.02275936,0.00009962751,0.0000221172,0.00012381902],"about_ca_topic_score_codex":0.00026197443,"about_ca_topic_score_gemma":0.00039485373,"teacher_disagreement_score":0.7280311,"about_ca_system_score_codex":0.00017626479,"about_ca_system_score_gemma":0.00006276322,"threshold_uncertainty_score":0.3463935},"labels":[],"label_agreement":null},{"id":"W4386378172","doi":"10.1038/s41598-023-41424-7","title":"Cost-effective, portable, patient-dedicated three-dimensional automated breast ultrasound for point-of-care breast cancer screening","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Schulich School of Medicine and Dentistry, Western University; Ontario Institute for Cancer Research","keywords":"Breast cancer; Medicine; Point of care; Medical physics; Computer science; Ultrasound; Breast cancer screening; Breast ultrasound; Gynecology; Radiology; Cancer; Mammography; Internal medicine; Pathology","score_opus":0.01798125655363969,"score_gpt":0.2813765889921445,"score_spread":0.2633953324385048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386378172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7462491,0.0006693911,0.18913804,0.0012039032,0.04463398,0.010077786,0.0007918633,0.006908986,0.00032696663],"genre_scores_gemma":[0.9909083,0.0000026200387,0.007339924,0.000049966053,0.000113388225,0.0010815784,0.00026526747,0.00004639147,0.00019256059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583834,0.00006901801,0.00080104056,0.0014443982,0.0011441469,0.0007030523],"domain_scores_gemma":[0.996237,0.00023462383,0.00082572614,0.0012301196,0.0012462067,0.00022635472],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012590385,0.00028553672,0.0003637364,0.0005358408,0.0006914504,0.00033873314,0.0004844534,0.00013917698,0.000075395415],"category_scores_gemma":[0.0001295203,0.00026938607,0.00020340967,0.0031931263,0.0002963506,0.0008975951,0.00029925175,0.00016279978,0.000019378947],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024091463,0.00025897432,0.050247103,0.00049911224,0.00038057537,0.00053646736,0.002305477,0.038431004,0.08187759,0.00019244415,0.16584593,0.6591844],"study_design_scores_gemma":[0.0020321365,0.00047798868,0.30843654,0.0013894998,0.00018944511,0.007598016,0.00048303523,0.53964126,0.11163925,0.0063355486,0.01983805,0.0019392405],"about_ca_topic_score_codex":0.00035282693,"about_ca_topic_score_gemma":0.0002112523,"teacher_disagreement_score":0.65724516,"about_ca_system_score_codex":0.00024404505,"about_ca_system_score_gemma":0.00048218633,"threshold_uncertainty_score":0.99997586},"labels":[],"label_agreement":null},{"id":"W4386583626","doi":"10.1101/2023.09.08.556885","title":"Machine learning to identify clinically relevant <i>Candida</i> yeast species","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Precision Laboratories; Alberta Machine Intelligence Institute; University of Alberta; Government of Alberta","keywords":"Budding yeast; Candida albicans; Candida glabrata; Yeast; Artificial intelligence; Corpus albicans; Convolutional neural network; Candida auris; Biology; Antifungal; Microbiology; Saccharomyces cerevisiae; Computer science; Biochemistry","score_opus":0.028739759258849966,"score_gpt":0.2716680520894403,"score_spread":0.2429282928305903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386583626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23843239,0.001168183,0.71948487,0.005215947,0.023811612,0.0024218643,0.0003520146,0.0089891935,0.00012392279],"genre_scores_gemma":[0.96013874,0.00065144023,0.036564037,0.0006195512,0.0013413448,0.000283174,3.3871214e-7,0.00022600126,0.00017540331],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99456704,0.00031784532,0.0011062935,0.0021263289,0.0010008601,0.0008816602],"domain_scores_gemma":[0.995421,0.00021308084,0.00070638064,0.0025789377,0.00057006214,0.0005105404],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019428837,0.00068931066,0.0007657985,0.0005820367,0.00035307067,0.0010562188,0.0026800192,0.00056177744,0.00003218905],"category_scores_gemma":[0.0009453493,0.000775128,0.00029441254,0.0015329464,0.00010728134,0.00037714033,0.0037484241,0.0019654646,0.001431753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018825069,0.00035942654,0.039544523,0.0011607566,0.00071940216,0.0007896807,0.00026556826,0.009410012,0.93071306,0.0052507506,0.011423612,0.00017493471],"study_design_scores_gemma":[0.0018058971,0.00087892025,0.50269604,0.0028114084,0.00027227492,2.4897633e-7,0.000015783246,0.04180032,0.18325135,0.00013402924,0.26085258,0.0054811337],"about_ca_topic_score_codex":0.00016552099,"about_ca_topic_score_gemma":0.000017381188,"teacher_disagreement_score":0.74746174,"about_ca_system_score_codex":0.0006450387,"about_ca_system_score_gemma":0.0006770072,"threshold_uncertainty_score":0.9999808},"labels":[],"label_agreement":null},{"id":"W4386645916","doi":"10.1101/2023.09.12.23295132","title":"Decoding biological age from face photographs using deep learning","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Queen's University","funders":"National Institutes of Health; European Commission","keywords":"Medicine; Medical diagnosis; Cancer; Survival analysis; Skin cancer; Gerontology; Oncology; Internal medicine; Pathology","score_opus":0.11675820629282414,"score_gpt":0.3125904210829797,"score_spread":0.19583221479015556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386645916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46976975,0.00024222991,0.5265725,0.000047172638,0.0023155054,0.00014716086,0.0000029757464,0.0007911696,0.0001114724],"genre_scores_gemma":[0.92925954,0.00027655068,0.069917336,0.000060362898,0.00033053398,0.000046398185,0.000015833666,0.000039732848,0.000053740278],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972352,0.00030080564,0.0003898336,0.0012466261,0.00037252842,0.00045500929],"domain_scores_gemma":[0.9983212,0.00032651183,0.0003117183,0.00086693716,0.000055273245,0.00011837804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061121036,0.00033831483,0.00040583592,0.0002836884,0.0002565186,0.00036259208,0.0016172676,0.00044074235,0.000032328742],"category_scores_gemma":[0.00020811013,0.00033025417,0.00023633099,0.00058558985,0.00008509977,0.00014822502,0.002780422,0.0013075644,0.000109705456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044790468,0.000104204155,0.53684634,0.00020186,0.00055888935,0.0011786432,0.010579605,0.20072415,0.0806768,0.00053498073,0.00013255447,0.16841717],"study_design_scores_gemma":[0.00026145045,0.00007789076,0.04456576,0.00034068627,0.000037002003,0.000013233683,0.00019484379,0.9217785,0.010627183,0.019566357,0.0015314657,0.0010056033],"about_ca_topic_score_codex":0.0007060808,"about_ca_topic_score_gemma":0.000092634116,"teacher_disagreement_score":0.7210544,"about_ca_system_score_codex":0.00019231808,"about_ca_system_score_gemma":0.00005755713,"threshold_uncertainty_score":0.99991494},"labels":[],"label_agreement":null},{"id":"W4386698011","doi":"10.3389/frai.2023.1248977","title":"Early breast cancer detection and differentiation tool based on tissue impedance characteristics and machine learning","year":2023,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Tunis El Manar; Université de Tunis; Research Nova Scotia; Ecole Nationale d'Ingénieurs de Tunis; Mitacs; Cape Breton University","keywords":"Breast cancer; Breast tissue; Stage (stratigraphy); Cancer; Artificial intelligence; Computer science; Biomedical engineering; Medicine; Internal medicine; Biology","score_opus":0.020452296804985077,"score_gpt":0.258256425906232,"score_spread":0.2378041291012469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386698011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30757436,0.00006249102,0.6904133,0.00032201287,0.001308936,0.0001546194,0.000009557997,0.00014468312,0.000010062399],"genre_scores_gemma":[0.9970803,0.00029403862,0.0023311833,0.00005653841,0.00011811223,0.00005434121,0.000003159349,0.000015034446,0.000047283243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986704,0.000095321775,0.00028321342,0.00046564735,0.00022352951,0.0002618731],"domain_scores_gemma":[0.99949676,0.00007664893,0.0001218971,0.00019796622,0.00005095337,0.000055804736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029890344,0.00015546221,0.00017031125,0.00031957793,0.00019161386,0.00018833803,0.00018342122,0.000086980726,0.0000070626484],"category_scores_gemma":[0.000073850475,0.00016604357,0.000019141107,0.000708943,0.00007175488,0.00032471094,0.00008116149,0.00028199513,0.000013081583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069725305,0.000015570095,0.022565654,0.000023185787,0.000004665916,0.00000510421,0.00044976696,0.0019679845,0.0034548726,0.00025521932,0.000013542491,0.9711747],"study_design_scores_gemma":[0.000037652637,0.00010656609,0.13224152,0.000051466228,0.0000045706956,0.000002805102,0.000034611192,0.84822196,0.016737998,0.0022841226,0.00010985585,0.00016688729],"about_ca_topic_score_codex":0.00024200465,"about_ca_topic_score_gemma":0.000121888595,"teacher_disagreement_score":0.9710078,"about_ca_system_score_codex":0.00013921253,"about_ca_system_score_gemma":0.000025498743,"threshold_uncertainty_score":0.677106},"labels":[],"label_agreement":null},{"id":"W4386748033","doi":"10.32074/1591-951x-896","title":"Diagnostic concordance between traditional and digital workflows. A study on 1427 prostate biopsies","year":2023,"lang":"en","type":"article","venue":"Pathologica","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Hospital Foundation","funders":"","keywords":"Concordance; Concordance correlation coefficient; Prostate; Medicine; Biopsy; Reproducibility; Nuclear medicine; Pathology; Statistics; Internal medicine; Mathematics","score_opus":0.06301025778948428,"score_gpt":0.27065049694365484,"score_spread":0.20764023915417057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386748033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991916,0.000041216532,0.005367201,0.0007016934,0.0002834462,0.00042232618,0.000054534405,0.00055841386,0.00065517414],"genre_scores_gemma":[0.9989129,0.000026539712,0.0005631976,0.000088146095,0.00012291566,0.00017752976,0.000009304679,0.0000078617195,0.000091644884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987968,0.00006325757,0.0001685149,0.0004794551,0.00025371014,0.00023821901],"domain_scores_gemma":[0.99865156,0.0009194044,0.00006563068,0.00026955828,0.000029029672,0.000064792635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023303785,0.00013543274,0.00015676854,0.00009841662,0.00016973271,0.00021460126,0.00029848257,0.000041753214,0.0000035728056],"category_scores_gemma":[0.00029482605,0.00011185061,0.000029312818,0.0005440264,0.00010528905,0.0003226861,0.00013854002,0.00014372052,0.00018071578],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033464803,0.000385365,0.71864915,0.000023028879,0.000040938186,0.0010412659,0.0048315153,0.0002311225,0.0002728123,0.0019390105,0.0020798277,0.27047253],"study_design_scores_gemma":[0.00032673992,0.0013153682,0.98600507,0.000024790492,0.000005141628,0.000020961137,0.00015576495,0.00039210185,0.00012526798,0.011042382,0.00041330914,0.0001731089],"about_ca_topic_score_codex":0.0000017737644,"about_ca_topic_score_gemma":8.776764e-7,"teacher_disagreement_score":0.27029943,"about_ca_system_score_codex":0.000035734374,"about_ca_system_score_gemma":0.00001861139,"threshold_uncertainty_score":0.45611355},"labels":[],"label_agreement":null},{"id":"W4386849477","doi":"10.54254/2753-8818/5/20230386","title":"Function tissue unit segmentation based on UNext model","year":2023,"lang":"en","type":"article","venue":"Theoretical and Natural Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Pyramid (geometry); Segmentation; Pooling; Artificial intelligence; Inference; Pattern recognition (psychology); Image segmentation; Data mining; Computer vision; Mathematics","score_opus":0.011726257782678261,"score_gpt":0.27401868090463694,"score_spread":0.26229242312195866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386849477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22442877,0.00002725407,0.7645318,0.0044379043,0.0009668817,0.00021766705,0.0000018212488,0.0005187674,0.0048691556],"genre_scores_gemma":[0.9951078,0.0000067968376,0.0040763547,0.00062318676,0.00003201724,0.000008087419,0.000001270313,0.0000031683064,0.00014128828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988023,0.000032260516,0.00008737411,0.00036216268,0.00047007945,0.00024581514],"domain_scores_gemma":[0.9995086,0.00010696064,0.000025305475,0.00020642077,0.000057910387,0.000094792296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057214516,0.000081665916,0.000059933755,0.00016098729,0.00030403753,0.00013050635,0.00035181278,0.00003240504,0.000016966658],"category_scores_gemma":[0.00006381388,0.000060803177,0.00001370449,0.0015395357,0.00065142434,0.0004500154,0.00012221433,0.00013070076,0.00007798008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027057984,0.000007426708,0.000015849067,0.000003917803,5.9748646e-7,0.000001237632,0.00006534395,0.004309389,0.034719784,0.8542242,0.00005373483,0.10657148],"study_design_scores_gemma":[0.00011320902,0.00014052866,0.0012544142,0.000008205614,0.0000019571287,0.0000015944934,0.000008513857,0.82971567,0.02717886,0.14144817,0.00005005988,0.00007880765],"about_ca_topic_score_codex":0.000004180455,"about_ca_topic_score_gemma":8.308746e-7,"teacher_disagreement_score":0.8254063,"about_ca_system_score_codex":0.000048551512,"about_ca_system_score_gemma":0.00006992546,"threshold_uncertainty_score":0.24794815},"labels":[],"label_agreement":null},{"id":"W4387033775","doi":"10.1002/jemt.24426","title":"<scp>DeepHistoNet</scp>: A robust deep‐learning model for the classification of hepatocellular, lung, and colon carcinoma","year":2023,"lang":"en","type":"article","venue":"Microscopy Research and Technique","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Scheme for Promotion of Academic and Research Collaboration","keywords":"Artificial intelligence; Computer science; Machine learning; Convolutional neural network; Deep learning; Receiver operating characteristic; Population; Artificial neural network; Robustness (evolution); Identification (biology); Pattern recognition (psychology); Data mining; Medicine","score_opus":0.07862777500846391,"score_gpt":0.3476303328677812,"score_spread":0.2690025578593173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387033775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17687075,0.00091194274,0.8205162,0.00027713273,0.000033510398,0.0011215503,0.000005319858,0.00015043323,0.00011313877],"genre_scores_gemma":[0.96870226,0.000580284,0.028786184,0.0000127311605,0.000025345811,0.0010151521,0.0000056856015,0.000019876976,0.0008524911],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986085,0.000114516675,0.00018903289,0.0004155913,0.000279177,0.00039316088],"domain_scores_gemma":[0.9985257,0.00066137675,0.00008202606,0.00038832767,0.00026460126,0.00007799479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018624184,0.00010709263,0.00013658438,0.0002842947,0.00056032673,0.00012738432,0.00045621317,0.0001279484,5.636657e-7],"category_scores_gemma":[0.0001918778,0.00009102229,0.00003201164,0.0007880557,0.00031259216,0.00016574109,0.00034282956,0.0003911943,0.0000015970784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036526115,0.00003798736,0.0075184135,0.0002970653,0.000018152155,0.0000036447054,0.0018323611,0.00046586158,0.96803445,0.0045707338,0.0055111884,0.011673606],"study_design_scores_gemma":[0.00015952637,0.00027630263,0.0019137729,0.00002546719,0.0000037021275,0.000007178416,0.00009682954,0.862906,0.12950963,0.0032667266,0.0017941768,0.000040723968],"about_ca_topic_score_codex":0.000106605345,"about_ca_topic_score_gemma":0.00003543278,"teacher_disagreement_score":0.8624401,"about_ca_system_score_codex":0.000104491766,"about_ca_system_score_gemma":0.000110577676,"threshold_uncertainty_score":0.4309637},"labels":[],"label_agreement":null},{"id":"W4387211411","doi":"10.1007/978-3-031-43987-2_74","title":"ALL-IN: A Local GLobal Graph-Based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Histopathology; Computer science; Risk stratification; Artificial intelligence; Machine learning; Directed acyclic graph; Stratification (seeds); Artificial neural network; Pattern recognition (psychology); Pathology; Algorithm; Medicine; Internal medicine","score_opus":0.026802682470984152,"score_gpt":0.3208773817570254,"score_spread":0.29407469928604124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007257474,0.00007565374,0.99728954,0.00046633006,0.00038373683,0.00084785797,0.000019988527,0.00010082574,0.00009030421],"genre_scores_gemma":[0.75173354,0.000042104046,0.24781208,0.000101740945,0.000056130546,0.00019785698,0.000014806919,0.000022069436,0.000019675253],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699086,0.00007320088,0.00055480364,0.0013378563,0.00065330666,0.00038999302],"domain_scores_gemma":[0.9980495,0.0003637575,0.000640759,0.0006193479,0.00027233153,0.000054318236],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00089318753,0.00031041322,0.00042877762,0.0007260816,0.00010262579,0.000084209445,0.00084916817,0.00023164345,6.492622e-7],"category_scores_gemma":[0.000054503736,0.00030525232,0.00007585477,0.0010989051,0.00047400055,0.00039757637,0.00021826135,0.0005223954,7.6594e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027907801,0.000016262995,0.0071244584,0.000041610514,0.000002826266,0.0000047020526,0.00019647233,0.7700302,0.000081492806,0.0018251758,0.0000014199655,0.22064747],"study_design_scores_gemma":[0.00053318206,0.0001886877,0.013709282,0.00020142803,0.000011131614,0.0000046619857,5.7390264e-7,0.9108591,0.00025383563,0.073959626,0.00001037111,0.00026813013],"about_ca_topic_score_codex":0.00083365897,"about_ca_topic_score_gemma":0.0038619144,"teacher_disagreement_score":0.7510078,"about_ca_system_score_codex":0.0015626763,"about_ca_system_score_gemma":0.00071170396,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W4387211564","doi":"10.1007/978-3-031-43901-8_43","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Inference; Convolutional neural network; Machine learning; Transfer of learning; Transformer; Domain (mathematical analysis); Pattern recognition (psychology); Image segmentation; Data mining","score_opus":0.026439110046927145,"score_gpt":0.3025782687703767,"score_spread":0.2761391587234495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020380594,0.00009296737,0.99235266,0.0022203026,0.003586917,0.0010866843,0.00012427053,0.0003422568,0.0001735636],"genre_scores_gemma":[0.0014519441,0.00010712525,0.99516416,0.0019833534,0.00067429204,0.00009830498,0.00017235523,0.000087193795,0.00026126942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950277,0.00004969241,0.00069145655,0.0019157445,0.001552121,0.0007632668],"domain_scores_gemma":[0.9974267,0.00075987884,0.000273386,0.0010673084,0.0001986909,0.00027404798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019980299,0.0005483803,0.000490476,0.00083489215,0.00037523353,0.00050558156,0.0030153212,0.0004993851,0.000028722201],"category_scores_gemma":[0.00014428656,0.00051439187,0.00018119259,0.0007010262,0.00061869004,0.0012375365,0.0006154589,0.0007691121,0.00008665174],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020324846,0.00003911521,0.0000044366825,0.00012050752,0.000016384125,0.000071747316,0.00053573784,0.0017508991,0.0014766541,0.0025188872,0.00021013648,0.9932352],"study_design_scores_gemma":[0.0015040245,0.00053860404,0.000080501515,0.00071029906,0.000018204728,0.00009873728,7.298761e-7,0.90090895,0.009092381,0.08064355,0.0053733694,0.00103067],"about_ca_topic_score_codex":0.000042988966,"about_ca_topic_score_gemma":0.00067946437,"teacher_disagreement_score":0.9922045,"about_ca_system_score_codex":0.0005271811,"about_ca_system_score_gemma":0.00071379583,"threshold_uncertainty_score":0.99973077},"labels":[],"label_agreement":null},{"id":"W4387327086","doi":"","title":"Current status of discrete data capture in synoptic surgical pathology and cancer reporting","year":2015,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Current (fluid); Surgical pathology; Data science; Medicine; Pathology; Computer science; Geology; Oceanography","score_opus":0.42317847237394,"score_gpt":0.5872531607031526,"score_spread":0.16407468832921257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387327086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8788363,0.10949264,0.008586155,0.00024319261,0.0017457708,0.0003799566,0.000062055035,0.000033998047,0.0006199834],"genre_scores_gemma":[0.9768241,0.02159951,0.0013517713,0.000032791922,0.00011884449,0.000025063808,0.00000779514,0.00001969228,0.000020423884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99642783,0.0003418454,0.0014404865,0.00068988284,0.0006467257,0.00045323838],"domain_scores_gemma":[0.9957605,0.0002183201,0.0023796787,0.0010375433,0.00028547627,0.00031849204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028836245,0.00021605172,0.00071668584,0.00047859736,0.00007052886,0.00046725365,0.0031128293,0.0000948973,0.00014687983],"category_scores_gemma":[0.00087161944,0.00018812687,0.000052800136,0.00095996406,0.00015752853,0.0032393765,0.0035738205,0.0005064567,9.464988e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011716899,0.00010352836,0.82449716,0.00012972175,0.000052389478,0.0004404581,0.0008261145,0.0008593948,0.0028824585,0.00013152309,0.004341901,0.16561817],"study_design_scores_gemma":[0.002085588,0.00005050382,0.9239183,0.001519868,0.000097154676,0.0006178659,0.00023583784,0.021760512,0.0056965197,0.009041353,0.03405664,0.0009198653],"about_ca_topic_score_codex":0.00367081,"about_ca_topic_score_gemma":0.00041528026,"teacher_disagreement_score":0.1646983,"about_ca_system_score_codex":0.00021094792,"about_ca_system_score_gemma":0.000531946,"threshold_uncertainty_score":0.7671591},"labels":[],"label_agreement":null},{"id":"W4387478847","doi":"10.18178/ijml.2023.13.4.1146","title":"Automated Segmentation of Cervical Cell Images Using IMBMDCR-Net","year":2023,"lang":"en","type":"article","venue":"International Journal of Machine Learning","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Convolution (computer science); Pixel; Image segmentation; Residual; Cascade; Scale-space segmentation; Computer vision; Artificial neural network; Algorithm","score_opus":0.01562116147546236,"score_gpt":0.313560196145148,"score_spread":0.29793903466968563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387478847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5486054,0.00013389393,0.44777223,0.0010208193,0.0018226536,0.000051448245,0.0000042966167,0.00022799194,0.00036129213],"genre_scores_gemma":[0.9671937,0.000053029074,0.03240285,0.00004937324,0.00019995439,5.9563234e-7,0.0000041899225,0.000010461185,0.00008584815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853367,0.00012436419,0.00043984715,0.00011855746,0.0006671306,0.000116457035],"domain_scores_gemma":[0.9986704,0.0001376862,0.0006523191,0.00008057132,0.00041513928,0.000043857024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056666444,0.000084042316,0.00013525928,0.0004328893,0.000051862455,0.000084778585,0.0006083741,0.000037578404,0.000040432158],"category_scores_gemma":[0.000096929914,0.000078978745,0.00009077197,0.00035652082,0.000021943175,0.0005532001,0.0001724471,0.00028711505,0.000015465595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011199877,0.000100503385,0.030732477,0.00004473841,0.00020141165,0.00021018986,0.0015778292,0.58094954,0.33438158,0.00028307902,0.00096989336,0.050436743],"study_design_scores_gemma":[0.00061205204,0.0001378798,0.011636185,0.00006570639,0.00001101006,0.00019173161,0.00006078278,0.9356684,0.050705932,0.00035600338,0.00046990582,0.00008441649],"about_ca_topic_score_codex":0.000070904425,"about_ca_topic_score_gemma":0.0000018707083,"teacher_disagreement_score":0.41858834,"about_ca_system_score_codex":0.00014334722,"about_ca_system_score_gemma":0.000073062125,"threshold_uncertainty_score":0.32206598},"labels":[],"label_agreement":null},{"id":"W4387591718","doi":"10.1016/j.compbiomed.2023.107530","title":"Whole slide image representation in bone marrow cytology","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"William Osler Health System; University Health Network; McMaster University; University of Toronto","funders":"Canadian Cancer Society","keywords":"Digital pathology; Computer science; Artificial intelligence; Pattern recognition (psychology); Leverage (statistics); Bone marrow; Representation (politics); Construct (python library); Pathology; Medicine","score_opus":0.023963600529095862,"score_gpt":0.3405977118827151,"score_spread":0.31663411135361924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387591718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48442987,0.00101004,0.47199133,0.03670366,0.004064677,0.00033031253,0.0000013560458,0.00030334358,0.0011653958],"genre_scores_gemma":[0.9848793,0.00042764607,0.013148376,0.0011989144,0.00020849083,0.00002929653,0.000018982355,0.0000059831223,0.00008300337],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989445,0.00014816487,0.00023988904,0.00038415688,0.000053844877,0.00022943549],"domain_scores_gemma":[0.9993612,0.00028023825,0.000058503916,0.00024008671,0.000019057085,0.000040918836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050167675,0.00008775076,0.00022294342,0.0004360472,0.000038433835,0.000006204539,0.00022171946,0.00010258384,0.0000042635866],"category_scores_gemma":[0.00009039852,0.000077631514,0.000012148552,0.00077502837,0.00022588055,0.00012581449,0.00019605053,0.00017131877,0.000018214732],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013734282,0.00007478562,0.18184626,0.000096156386,0.000032794534,0.00086538104,0.0070417086,0.000335401,0.09588713,0.03942252,0.033061966,0.6411986],"study_design_scores_gemma":[0.0053493204,0.0010230958,0.6421318,0.00028124131,0.000008323097,0.00033076503,0.00038575238,0.18388997,0.0018174043,0.15123007,0.0131235095,0.00042875542],"about_ca_topic_score_codex":0.00012431898,"about_ca_topic_score_gemma":0.00010474973,"teacher_disagreement_score":0.6407698,"about_ca_system_score_codex":0.000046605383,"about_ca_system_score_gemma":0.000018070177,"threshold_uncertainty_score":0.31657213},"labels":[],"label_agreement":null},{"id":"W4387640692","doi":"10.1007/978-3-031-45673-2_32","title":"RelationalUNet for Image Segmentation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for International Peace and Security; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Image segmentation; Deep learning; Robustness (evolution); Pattern recognition (psychology); Medical imaging; Feature (linguistics); Computer vision","score_opus":0.023157825732713633,"score_gpt":0.27361904617680255,"score_spread":0.2504612204440889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387640692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008694098,0.000071377945,0.9922946,0.0012011133,0.0036843298,0.0006891149,0.000013703572,0.00035246924,0.0016846124],"genre_scores_gemma":[0.0033888144,0.0000354575,0.99274474,0.000782767,0.00082781055,0.000079234356,0.000025584677,0.000059687227,0.0020559293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693793,0.000018794595,0.00043392152,0.001298632,0.00085872656,0.00045202064],"domain_scores_gemma":[0.9977237,0.0007335457,0.0002869994,0.0008592662,0.00030598004,0.00009052757],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088458176,0.00034197213,0.00029364557,0.00077352393,0.0002799229,0.00042840667,0.0017150941,0.00025114923,0.000012927981],"category_scores_gemma":[0.00010872892,0.0003513671,0.00012161753,0.0006407004,0.00031881165,0.0008813848,0.00057699403,0.00042069567,0.000115076065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008992568,0.000010745093,0.000016599628,0.000062783976,0.000014802294,0.000019339559,0.0005003471,0.04144935,0.0006130256,0.045249112,0.00031297578,0.9117419],"study_design_scores_gemma":[0.00023591665,0.00013054175,0.00010022967,0.00012737152,0.0000061096803,0.000019789566,8.8843265e-8,0.5745712,0.0021160333,0.4212852,0.0010384807,0.00036900662],"about_ca_topic_score_codex":0.000010364069,"about_ca_topic_score_gemma":0.00004984303,"teacher_disagreement_score":0.9113729,"about_ca_system_score_codex":0.00058707816,"about_ca_system_score_gemma":0.00045528813,"threshold_uncertainty_score":0.99989384},"labels":[],"label_agreement":null},{"id":"W4387667700","doi":"10.3389/ti.2023.11783","title":"Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments","year":2023,"lang":"en","type":"article","venue":"Transplant International","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute","keywords":"Digital pathology; Medicine; Pathology; Digital image analysis; Computer science; Transplantation; Surgical pathology; Telepathology; Telemedicine; Surgery; Computer vision","score_opus":0.04574690773065399,"score_gpt":0.275130716929103,"score_spread":0.22938380919844903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387667700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03090849,0.000034842866,0.9613994,0.0011573003,0.003859815,0.00021973647,0.000050885905,0.00035236427,0.0020171704],"genre_scores_gemma":[0.9779268,0.00032451758,0.020948203,0.00007011784,0.00047056115,0.000062782085,0.00009206831,0.000015107009,0.00008986463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849635,0.000032661574,0.00033151198,0.00047526887,0.00039630308,0.00026787858],"domain_scores_gemma":[0.9995202,0.00013999674,0.00007474331,0.00015268072,0.00004759529,0.00006479828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028477516,0.00015185196,0.0001321925,0.00023784842,0.00010928929,0.0002628479,0.0006022876,0.0000836273,0.00003082128],"category_scores_gemma":[0.000016132788,0.00015688968,0.000049932914,0.00026224228,0.000067654226,0.0005967629,0.00012483406,0.00017999554,0.00015751454],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049497536,0.00006712735,0.00008113792,0.0000075030684,0.000046251687,0.00024995845,0.001327978,0.000023088078,0.00025173885,0.015623745,0.000045456785,0.98178107],"study_design_scores_gemma":[0.01917329,0.0020720672,0.016624374,0.0008253935,0.00007377436,0.0018712803,0.00053623033,0.6782003,0.010771316,0.23560263,0.030943958,0.0033054056],"about_ca_topic_score_codex":0.0000067823735,"about_ca_topic_score_gemma":0.000012899231,"teacher_disagreement_score":0.97847563,"about_ca_system_score_codex":0.00007326627,"about_ca_system_score_gemma":0.00003561123,"threshold_uncertainty_score":0.63977754},"labels":[],"label_agreement":null},{"id":"W4387670671","doi":"10.1007/s12553-023-00783-x","title":"Automatic detection of breast masses using deep learning with YOLO approach","year":2023,"lang":"en","type":"article","venue":"Health and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Public Health Agency of Canada","keywords":"Deep learning; Computer science; Artificial intelligence","score_opus":0.015986639043901917,"score_gpt":0.25989678722432596,"score_spread":0.24391014818042406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387670671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49042538,0.00025864015,0.5076318,0.00063119223,0.000067496476,0.00012205468,2.2576629e-7,0.0008285721,0.00003465212],"genre_scores_gemma":[0.9676151,0.000058090198,0.03225777,0.000026423839,0.000011219507,0.000017957751,5.3750705e-7,0.0000070839637,0.0000058144583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926525,0.00003805764,0.0001468413,0.00022258649,0.00009511102,0.00023215634],"domain_scores_gemma":[0.9995639,0.000024370964,0.00014036577,0.00018424676,0.000039650284,0.00004751396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018171211,0.00006876084,0.00014350367,0.0004340676,0.0001740324,0.000012987411,0.00013130842,0.000089395304,6.704287e-7],"category_scores_gemma":[0.000019101517,0.00006130101,0.000008426388,0.001559376,0.000081451406,0.00010794453,0.000087617176,0.00017763955,0.0000022558718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068239488,0.000014311269,0.0055920947,0.00029856738,0.000010557619,0.0000024954365,0.00032251666,0.00030094982,0.0016018347,0.0019899686,0.00000320636,0.98985666],"study_design_scores_gemma":[0.00027832453,0.0006154125,0.0034804717,0.000052353742,0.0000037601587,0.0007316545,0.0006567515,0.98989743,0.0019337141,0.0019965565,0.00024852244,0.00010505223],"about_ca_topic_score_codex":0.00007421171,"about_ca_topic_score_gemma":0.000023395754,"teacher_disagreement_score":0.98975164,"about_ca_system_score_codex":0.0000590686,"about_ca_system_score_gemma":0.00009271462,"threshold_uncertainty_score":0.24997827},"labels":[],"label_agreement":null},{"id":"W4387827378","doi":"10.1016/j.eswa.2023.122209","title":"Measurement of adverse cosmesis in breast cancer: A deep learning approach","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"Hamilton Health Sciences Foundation","keywords":"Cosmesis; Artificial intelligence; Computer science; Support vector machine; Preprocessor; Receiver operating characteristic; Breast cancer; Medicine; Machine learning; Medical physics; Cancer; Internal medicine","score_opus":0.021603929172689128,"score_gpt":0.2544504878006874,"score_spread":0.23284655862799827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387827378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018618178,0.0009316689,0.99405456,0.00043774644,0.00011752006,0.0010552916,0.0000039846827,0.00037798245,0.0011594159],"genre_scores_gemma":[0.9896097,0.000105881576,0.0034098781,0.000015847416,0.000080332204,0.0066946954,0.0000024334047,0.000015753312,0.00006548829],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985736,0.00007497855,0.00027355505,0.0003780113,0.00048621363,0.00021363563],"domain_scores_gemma":[0.99907964,0.000023486207,0.00016743447,0.0004835267,0.00018508994,0.00006081594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039209018,0.00011367654,0.0001827975,0.00021456671,0.00011506563,0.00001860296,0.0004191694,0.000047246856,0.0000020294035],"category_scores_gemma":[0.0000041124454,0.00010143832,0.000030473942,0.0016977347,0.000034782977,0.00017370179,0.000069985595,0.0001074742,0.000023802848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012488458,0.0007520962,0.07159104,0.0011086672,0.00036105647,0.00001042952,0.020441856,0.6799881,0.02455883,0.026304502,0.003829371,0.17092916],"study_design_scores_gemma":[0.0013885997,0.000098708675,0.04537481,0.00048011882,0.000017292055,0.00008949228,0.0043985583,0.91959095,0.0013696403,0.00007520331,0.026466927,0.00064972165],"about_ca_topic_score_codex":0.0013606162,"about_ca_topic_score_gemma":0.000089907,"teacher_disagreement_score":0.9906447,"about_ca_system_score_codex":0.00035644777,"about_ca_system_score_gemma":0.00011202075,"threshold_uncertainty_score":0.4136535},"labels":[],"label_agreement":null},{"id":"W4387844354","doi":"10.1016/j.heliyon.2023.e21369","title":"Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model","year":2023,"lang":"en","type":"article","venue":"Heliyon","topic":"AI in cancer detection","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Ultrasound; Artificial intelligence; Segmentation; Computer science; Image segmentation; Pattern recognition (psychology); Ultrasound imaging; Breast ultrasound; Breast tumor; Computer vision; Breast cancer; Medicine; Radiology; Mammography; Internal medicine; Cancer","score_opus":0.02564810022028016,"score_gpt":0.27304038700784017,"score_spread":0.24739228678756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387844354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6187156,0.000032218053,0.37959528,0.0002306723,0.000115363,0.00018852307,0.000015110253,0.0010213377,0.0000859084],"genre_scores_gemma":[0.9525776,0.00005048129,0.04705851,0.00008369168,0.00004972342,0.00003265026,0.000032324584,0.000022676928,0.00009233705],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889815,0.000046455145,0.00017515756,0.00039859783,0.00026320576,0.00021841016],"domain_scores_gemma":[0.9993725,0.00004834776,0.00012453453,0.0002997007,0.0000933281,0.000061614686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017143862,0.00013275023,0.00010638668,0.00015431561,0.00017402851,0.00020177726,0.00016373007,0.000027791886,0.000004403351],"category_scores_gemma":[0.000011726255,0.00012597546,0.000017262893,0.00061428786,0.000050740084,0.00076339097,0.000054986554,0.000083318126,0.000050647126],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005782276,0.000036185844,0.0012919223,0.00021112704,0.000024637242,0.000025130083,0.00087139383,0.018918617,0.9697722,0.00028614668,0.0007191642,0.007785617],"study_design_scores_gemma":[0.00036553506,0.00004572417,0.012915712,0.00008257632,0.000011265841,0.0002383862,0.00004668831,0.957218,0.0287057,0.00019562182,0.000017218725,0.00015760149],"about_ca_topic_score_codex":0.000022984606,"about_ca_topic_score_gemma":0.000017549335,"teacher_disagreement_score":0.94106656,"about_ca_system_score_codex":0.0001527213,"about_ca_system_score_gemma":0.000082466046,"threshold_uncertainty_score":0.513713},"labels":[],"label_agreement":null},{"id":"W4387951192","doi":"10.1109/ccece58730.2023.10289102","title":"Connected ResU-Net: A Deep Learning Model for Segmentation of Breast Cancer Ultrasound Images","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Breast cancer; Image segmentation; Deep learning; Computer vision; Cancer; Medicine; Internal medicine","score_opus":0.02074732426862655,"score_gpt":0.2900276136144603,"score_spread":0.2692802893458337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387951192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02974466,0.00002768128,0.96872604,0.00046412923,0.00018198809,0.00022107766,0.00001807399,0.00035188568,0.00026446165],"genre_scores_gemma":[0.9557508,0.00007679256,0.042443994,0.000074049385,0.000052909785,0.00014550988,0.000009783459,0.0000136215385,0.0014325372],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999187,0.000029524748,0.00017035066,0.0002570235,0.00017471457,0.00018138264],"domain_scores_gemma":[0.99932045,0.00020846061,0.00010420888,0.00016837931,0.0001663111,0.000032166325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019614957,0.00007958924,0.00009953083,0.00011204522,0.000103365506,0.00004960363,0.00021711852,0.00003809684,0.000024545468],"category_scores_gemma":[0.000039831695,0.00007697268,0.000041548417,0.000523176,0.000025923442,0.00037077616,0.000050328366,0.00006273626,0.000008307405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006910648,0.000024072577,0.0018061864,0.00009391801,0.000056452558,7.7073247e-7,0.0028083199,0.5446054,0.35986462,0.0020872308,0.003325099,0.08525881],"study_design_scores_gemma":[0.00035834697,0.00004011702,0.007079949,0.0000136737,0.000007050179,0.000005040092,0.0001418129,0.95456463,0.03593426,0.0017332833,0.00002470407,0.000097138065],"about_ca_topic_score_codex":0.00018229161,"about_ca_topic_score_gemma":0.00018132126,"teacher_disagreement_score":0.92628205,"about_ca_system_score_codex":0.00008838452,"about_ca_system_score_gemma":0.00005453912,"threshold_uncertainty_score":0.31388548},"labels":[],"label_agreement":null},{"id":"W4388021332","doi":"10.18280/ts.400504","title":"Unveiling Breast Tumor Characteristics: A ResNet152V2 and Mask R-CNN Based Approach for Type and Size Recognition in Mammograms","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Computer science; Artificial intelligence; Breast tumor; Speech recognition; Medicine; Breast cancer; Internal medicine; Cancer","score_opus":0.03812239432338698,"score_gpt":0.2520225732921183,"score_spread":0.2139001789687313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388021332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68135613,0.00003218698,0.31678706,0.00044671498,0.00019969752,0.00078776426,0.000050424584,0.00024511752,0.00009491571],"genre_scores_gemma":[0.97248614,0.000011381012,0.026938556,0.00020084539,0.00012209587,0.00015606392,0.000044911765,0.000014970829,0.000025011937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988771,0.000051189818,0.00023836514,0.0004086345,0.0001694867,0.0002551944],"domain_scores_gemma":[0.99948454,0.00017704314,0.00008266875,0.00012249447,0.00006423123,0.000069047856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055501604,0.00012864957,0.00014942106,0.00010936465,0.00008802171,0.00013440932,0.00013153741,0.000043089447,0.000019699515],"category_scores_gemma":[0.000035303186,0.00013265185,0.000022390093,0.0005071947,0.0000386399,0.0002151513,0.000056076085,0.00009135631,0.0000067667042],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011092954,0.0003731166,0.015195712,0.0010136665,0.00007380762,0.00005902765,0.0024539304,0.0006931479,0.02493456,0.00051742414,0.0008747126,0.95270157],"study_design_scores_gemma":[0.0019117503,0.00045090113,0.07200865,0.00010705893,0.000019120742,0.000032515174,0.00014860049,0.92250013,0.0010336601,0.0010086836,0.00045640554,0.0003225011],"about_ca_topic_score_codex":0.000022102766,"about_ca_topic_score_gemma":0.0000062021586,"teacher_disagreement_score":0.9523791,"about_ca_system_score_codex":0.00005639678,"about_ca_system_score_gemma":0.00004467981,"threshold_uncertainty_score":0.54093856},"labels":[],"label_agreement":null},{"id":"W4388207465","doi":"10.58496/adsa/2023/006","title":"Automated Grading System for Breast Cancer Histopathological Images Using Histogram of Oriented Gradients (HOG) Algorithm","year":2023,"lang":"en","type":"article","venue":"Applied Data Science and Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Breast cancer; Preprocessor; Histogram; Computer science; Support vector machine; Segmentation; Grading (engineering); Region of interest; Feature extraction; Mammography; Pattern recognition (psychology); Cancer; Algorithm; Medicine; Internal medicine; Image (mathematics)","score_opus":0.03668878669533639,"score_gpt":0.31361724911356664,"score_spread":0.27692846241823027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388207465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059324972,0.00005541839,0.9384651,0.000087514585,0.00033744995,0.0002813842,0.00073862844,0.00066791155,0.000041599724],"genre_scores_gemma":[0.9147391,0.000035837384,0.08502584,0.000024656541,0.00004024015,0.000053729767,0.000064598076,0.0000074749664,0.000008549785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760324,0.000023833314,0.00032905937,0.0010201255,0.0006171332,0.00040663267],"domain_scores_gemma":[0.99834114,0.000060148155,0.0002518462,0.0009764811,0.00025209945,0.000118270866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014990537,0.00014729609,0.00034490516,0.00087222434,0.0005426264,0.00014119946,0.0014536056,0.00004744999,0.000001881912],"category_scores_gemma":[0.000032891374,0.00012715337,0.000060395516,0.009316322,0.00045517628,0.000894464,0.00081093033,0.00006507528,0.000001931185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042952564,0.00015927655,0.011304354,0.00028031983,0.0006182827,0.00003116393,0.0009435666,0.0042779758,0.15880558,0.011080734,0.0013590856,0.8110967],"study_design_scores_gemma":[0.00017792977,0.000017094175,0.010808447,0.000018364686,0.00030940011,0.000011077539,0.00013752576,0.9864645,0.0017040722,0.00006471353,0.00013116225,0.000155704],"about_ca_topic_score_codex":0.00040417287,"about_ca_topic_score_gemma":0.000015128527,"teacher_disagreement_score":0.98218656,"about_ca_system_score_codex":0.00033045377,"about_ca_system_score_gemma":0.0001550266,"threshold_uncertainty_score":0.51851636},"labels":[],"label_agreement":null},{"id":"W4388210191","doi":"10.1088/1361-6560/ad092a","title":"Self-supervised enhanced thyroid nodule detection in ultrasound examination video sequences with multi-perspective evaluation","year":2023,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; Key Research and Development Projects of Shaanxi Province; China Scholarship Council; Ontario Institute for Cancer Research","keywords":"Computer science; Artificial intelligence; Context (archaeology); Computer vision; Precision and recall; Pattern recognition (psychology)","score_opus":0.13045573256780346,"score_gpt":0.37716238563475113,"score_spread":0.24670665306694767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388210191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7076467,0.00017545496,0.29029506,0.00057338836,0.000306571,0.00041463965,7.298918e-7,0.00012851406,0.0004588858],"genre_scores_gemma":[0.99623,0.00030418372,0.0030754386,0.00008765501,0.00016041088,0.00012360305,0.000008227569,0.0000058318296,0.000004651313],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987567,0.0002717626,0.00017753035,0.0004418039,0.00016156859,0.0001906463],"domain_scores_gemma":[0.99926454,0.0002883765,0.000084398074,0.00017232783,0.0001650887,0.000025242387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010078796,0.00011810943,0.00017775565,0.00023001377,0.000063133506,0.000013000528,0.00015106682,0.000073788775,0.0000023678972],"category_scores_gemma":[0.00015660594,0.00009122648,0.000010665479,0.0013145726,0.00011939106,0.00030646502,0.000035593537,0.00016603916,0.000004780597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005121537,0.00011760938,0.0039740517,0.000050677187,0.000035986704,0.000004841031,0.02437204,0.0015003621,0.50698465,0.004602572,0.000013518429,0.45829248],"study_design_scores_gemma":[0.0044329306,0.0018295475,0.07107144,0.00013044983,0.00002823996,0.000016744745,0.005225428,0.7730095,0.08983899,0.054017626,0.000029919453,0.00036923238],"about_ca_topic_score_codex":0.0004975683,"about_ca_topic_score_gemma":0.0012839326,"teacher_disagreement_score":0.7715091,"about_ca_system_score_codex":0.00027068664,"about_ca_system_score_gemma":0.000054610602,"threshold_uncertainty_score":0.3720108},"labels":[],"label_agreement":null},{"id":"W4388302233","doi":"10.1002/cjp2.347","title":"Engineering the future of <scp>3D</scp> pathology","year":2023,"lang":"en","type":"article","venue":"The Journal of Pathology Clinical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"U.S. National Library of Medicine; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; NIHR Oxford Biomedical Research Centre; Schweizerische Akademie der Medizinischen Wissenschaften; University of Oxford; National Institute for Health and Care Research; UK Research and Innovation; U.S. Department of Defense; Pancreatic Cancer UK; University of Bern; DOD Prostate Cancer Research Program; Department of Health and Social Care; National Institute of Biomedical Imaging and Bioengineering; Canary Foundation; Division of Cancer Prevention, National Cancer Institute; Prostate Cancer UK; National Science Foundation","keywords":"Computer science; Digital pathology; Pathology; High resolution; Visualization; Perspective (graphical); Artificial intelligence; Medicine; Geology","score_opus":0.13340571231387666,"score_gpt":0.45113913625873825,"score_spread":0.3177334239448616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388302233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93326676,0.0015337165,0.04706857,0.013307364,0.004187657,0.00022180825,0.0000033996755,0.000058076224,0.00035263592],"genre_scores_gemma":[0.9884299,0.005137288,0.0036647194,0.00032140073,0.002065104,0.000009460361,3.746441e-7,0.00001945373,0.0003522777],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.994516,0.0030013656,0.00091454934,0.0002145637,0.0008225068,0.00053100183],"domain_scores_gemma":[0.9827896,0.015181373,0.0003984539,0.0008599888,0.0006565736,0.000114037306],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.03528063,0.00010337369,0.0003480556,0.0003199403,0.00019867723,0.000028524868,0.0026976112,0.00024765194,0.000008476655],"category_scores_gemma":[0.006362922,0.00005523461,0.000184812,0.0014285549,0.00064422464,0.00014669451,0.00087284954,0.0026166202,0.00013449961],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003870922,0.0006292643,0.017919438,0.00019055663,0.00051169726,0.0074563194,0.017510002,0.012111662,0.050814554,0.027506044,0.19561146,0.66935194],"study_design_scores_gemma":[0.005186131,0.013730453,0.5621556,0.00033605055,0.00018979199,0.01675804,0.006164841,0.07869167,0.011695018,0.08486516,0.2198205,0.0004067375],"about_ca_topic_score_codex":0.0000022615889,"about_ca_topic_score_gemma":0.0000051689162,"teacher_disagreement_score":0.6689452,"about_ca_system_score_codex":0.00004721384,"about_ca_system_score_gemma":0.00028327317,"threshold_uncertainty_score":0.9996844},"labels":[],"label_agreement":null},{"id":"W4388336411","doi":"10.1016/j.jpi.2023.100347","title":"Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities","year":2023,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; William Osler Health System; Hamilton Health Sciences; Population Health Research Institute; McMaster University","funders":"","keywords":"Computer science; Random forest; Machine learning; Data science; Health care; Decision tree; Artificial intelligence; Knowledge management","score_opus":0.08867430323771677,"score_gpt":0.28600804656390316,"score_spread":0.1973337433261864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388336411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15124013,0.01113698,0.8309267,0.0052563683,0.00075004535,0.00020392668,0.000002079326,0.00010298663,0.0003807469],"genre_scores_gemma":[0.96962714,0.019455722,0.010213547,0.00046062493,0.00015764564,0.000012284948,0.000003418004,0.000018586574,0.000051001283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748737,0.00057498255,0.001059852,0.00011691933,0.00041341298,0.00034746208],"domain_scores_gemma":[0.9961727,0.0013120435,0.0019927735,0.0002841379,0.0001727937,0.00006554911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004093224,0.00017537348,0.00044834227,0.0001805325,0.00066952885,0.00013103943,0.00057236105,0.00009763728,9.306134e-7],"category_scores_gemma":[0.00022651993,0.000093095136,0.00006589698,0.0001751689,0.00018732318,0.0011279718,0.00026028522,0.00096894224,0.0000026231414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012812373,0.0000121897465,0.0008964358,0.00009437046,0.000056516135,0.00038920122,0.17492926,0.5935879,0.000010683206,0.005994096,0.00020999172,0.22369125],"study_design_scores_gemma":[0.0012643597,0.0008923537,0.0013402656,0.00024046977,0.000033783952,0.005695938,0.036698215,0.94081813,0.0000035124576,0.0062462967,0.0066210334,0.0001456545],"about_ca_topic_score_codex":0.000037720587,"about_ca_topic_score_gemma":0.00008090596,"teacher_disagreement_score":0.8207132,"about_ca_system_score_codex":0.00009737354,"about_ca_system_score_gemma":0.00017377119,"threshold_uncertainty_score":0.51495427},"labels":[],"label_agreement":null},{"id":"W4388341885","doi":"10.1016/j.jpi.2023.100344","title":"Learning to predict prostate cancer recurrence from tissue images","year":2023,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; DOD Prostate Cancer Research Program; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Defense","keywords":"Prostate cancer; Biochemical recurrence; Prostatectomy; Artificial intelligence; Prostate; Computer science; Medicine; Classifier (UML); Cancer; Machine learning; Internal medicine","score_opus":0.014250890906063804,"score_gpt":0.29222983254256146,"score_spread":0.27797894163649767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388341885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.665024,0.00020449623,0.32846534,0.0021505856,0.0034090197,0.00017715227,0.000021202568,0.00016512466,0.00038306805],"genre_scores_gemma":[0.8050375,0.0019397521,0.19038838,0.0011402073,0.0007642616,0.00004033653,0.00000579385,0.000025944786,0.00065779453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998677,0.00007049277,0.0006180094,0.0000781668,0.00031618157,0.00024011939],"domain_scores_gemma":[0.9987249,0.00012504216,0.00059278915,0.00019961288,0.00025293665,0.00010476994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007011097,0.00010168242,0.0002036771,0.0002913755,0.00009749376,0.00008626268,0.00059930497,0.0000707132,0.000012810245],"category_scores_gemma":[0.0002471212,0.00008758658,0.000050810635,0.00060910906,0.000038644146,0.0009542494,0.00022419434,0.00043732705,0.00014950166],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050544877,0.000024349056,0.011516175,0.000079198064,0.00007539742,0.00049670844,0.074715845,0.058193162,0.0049016355,0.00008031641,0.038612813,0.81125385],"study_design_scores_gemma":[0.0057386635,0.012507059,0.19447827,0.0024508256,0.00029866825,0.006909547,0.016761892,0.35043883,0.113383055,0.018562622,0.2759189,0.002551681],"about_ca_topic_score_codex":0.000010260669,"about_ca_topic_score_gemma":0.0000041180747,"teacher_disagreement_score":0.8087022,"about_ca_system_score_codex":0.000095373936,"about_ca_system_score_gemma":0.00014529764,"threshold_uncertainty_score":0.3571677},"labels":[],"label_agreement":null},{"id":"W4388378415","doi":"10.1016/j.jpi.2023.100348","title":"Performance of externally validated machine learning models based on histopathology images for the diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer: A systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; William Osler Health System; Hamilton Health Sciences; Population Health Research Institute; McMaster University","funders":"McMaster University","keywords":"Computer science; Breast cancer; Histopathology; Machine learning; Artificial intelligence; Outcome (game theory); Cancer; Medicine; Pathology; Mathematics; Internal medicine","score_opus":0.14132488141945432,"score_gpt":0.363340357748577,"score_spread":0.22201547632912266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388378415","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006665161,0.92299515,0.07101378,0.00035801696,0.00095338415,0.0042672125,0.00026563506,0.00006858507,0.000011565727],"genre_scores_gemma":[0.00042466738,0.9932457,0.00336038,0.00012350273,0.00007043574,0.0026544451,0.00002045227,0.00003610455,0.000064295244],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941784,0.000647953,0.004184244,0.00021018469,0.0004713652,0.00030783488],"domain_scores_gemma":[0.99085754,0.0013877047,0.0065478757,0.00063627685,0.00050761574,0.0000629643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032785328,0.0004350171,0.0026844975,0.0007104604,0.00014057927,0.000049193586,0.0011556711,0.0002673694,0.0000053847684],"category_scores_gemma":[0.0004111495,0.0002376957,0.0005263019,0.00080785836,0.00009209255,0.0005490412,0.00008728199,0.00065021106,0.0000063580783],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073731295,0.0002394856,0.0015911584,0.81695634,0.00021699652,0.00006147135,0.0007183808,0.016619705,4.6732254e-7,0.000030796153,0.00017612723,0.16331533],"study_design_scores_gemma":[0.0010555349,0.002547924,0.0004113339,0.40499103,0.0033819617,0.0029829321,0.00006281601,0.58024263,0.0000045134507,0.000014163455,0.003938221,0.0003669664],"about_ca_topic_score_codex":0.0000067380256,"about_ca_topic_score_gemma":0.00000796519,"teacher_disagreement_score":0.5636229,"about_ca_system_score_codex":0.0010376627,"about_ca_system_score_gemma":0.00071696244,"threshold_uncertainty_score":0.9692949},"labels":[],"label_agreement":null},{"id":"W4388407422","doi":"10.3390/curroncol30110708","title":"Photon Absorption Remote Sensing Imaging of Breast Needle Core Biopsies Is Diagnostically Equivalent to Gold Standard H&amp;E Histologic Assessment","year":2023,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Illumisonics (Canada); University of Waterloo","funders":"Centre for Bioengineering and Biotechnology, University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institutes of Health Research; University of Waterloo; Canada Foundation for Innovation; illumiSonics","keywords":"Concordance; Medicine; Gold standard (test); Histology; Breast cancer; Kappa; Pathology; Cancer; Nuclear medicine; Radiology; Internal medicine; Mathematics","score_opus":0.12729719870106468,"score_gpt":0.4161055382213312,"score_spread":0.2888083395202665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388407422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24226077,0.00024466394,0.74467844,0.0053576594,0.0056642853,0.0004589074,0.000046832945,0.00040909275,0.00087933417],"genre_scores_gemma":[0.9237478,0.00052015914,0.074710056,0.00050051324,0.0003081178,0.000016275228,0.000027344111,0.000032670276,0.00013707162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979062,0.00012817577,0.000467519,0.0005862128,0.0004425246,0.00046934912],"domain_scores_gemma":[0.9983806,0.00036651056,0.00025752792,0.0005349244,0.00031662532,0.00014378323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063582713,0.00020251576,0.00037746102,0.00037316373,0.00010238127,0.000046932284,0.0004464956,0.00008917592,0.00003483257],"category_scores_gemma":[0.00014502516,0.00020253629,0.00010077142,0.0009041937,0.00013400603,0.00017620847,0.00056335656,0.00027001541,0.00010620724],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000564414,0.00006608083,0.0024153965,0.00009773303,0.000018185943,0.000026185437,0.0011139185,0.0002538449,0.009158404,0.0005923505,0.020115824,0.9660856],"study_design_scores_gemma":[0.00244719,0.0020853071,0.06892731,0.00093370595,0.00014059462,0.0006493628,0.00061723153,0.47922763,0.006715714,0.018680945,0.41824132,0.0013336722],"about_ca_topic_score_codex":0.000080813305,"about_ca_topic_score_gemma":0.000043469547,"teacher_disagreement_score":0.96475196,"about_ca_system_score_codex":0.0013974535,"about_ca_system_score_gemma":0.00028553983,"threshold_uncertainty_score":0.82591903},"labels":[],"label_agreement":null},{"id":"W4388461068","doi":"10.1016/j.modpat.2023.100381","title":"A Preliminary Investigation into Search and Matching for Tumor Discrimination in World Health Organization Breast Taxonomy Using Deep Networks","year":2023,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada); University of Waterloo","funders":"World Health Organization; Memorial Sloan-Kettering Cancer Center; Government of Ontario; Mayo Foundation for Medical Education and Research; Singapore General Hospital; Mayo Clinic","keywords":"Breast cancer; Artificial intelligence; Taxonomy (biology); Computer science; Digital pathology; Deep learning; Histopathology; Pathology; Medicine; Information retrieval; Cancer; Biology; Internal medicine","score_opus":0.04410164583141942,"score_gpt":0.2842847001902203,"score_spread":0.24018305435880086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388461068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35495922,0.000051361123,0.64323723,0.0011375672,0.00014436501,0.00036774846,9.957164e-7,0.00009945894,0.000002033669],"genre_scores_gemma":[0.9347607,0.000009856133,0.0647194,0.0002741427,0.0000718486,0.00010280463,0.000028888067,0.000019626012,0.000012740082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987754,0.00018075373,0.00023913238,0.000426645,0.00010204559,0.00027599125],"domain_scores_gemma":[0.999483,0.00009568319,0.00009612792,0.0001914848,0.00007645981,0.000057282596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067413197,0.00010255838,0.00014290193,0.00041432862,0.00021523991,0.000069772505,0.00016491025,0.0000531386,6.8769873e-7],"category_scores_gemma":[0.00002865034,0.000116726405,0.000012847011,0.00096374203,0.00004850131,0.00048122572,0.00020692257,0.00013563434,0.000001586997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051433784,0.000040871488,0.024856742,0.00029322854,0.0000076001606,0.00003256711,0.029199924,0.56796545,0.004144096,0.0044140373,0.000059322952,0.36893475],"study_design_scores_gemma":[0.00023485272,0.00007650098,0.04264718,0.00004455144,0.0000025365252,0.00011172254,0.00015214847,0.9431157,0.0001691853,0.013344024,0.0000036566696,0.00009793398],"about_ca_topic_score_codex":0.000291007,"about_ca_topic_score_gemma":0.0010778982,"teacher_disagreement_score":0.5798015,"about_ca_system_score_codex":0.00029425815,"about_ca_system_score_gemma":0.000102783,"threshold_uncertainty_score":0.47599646},"labels":[],"label_agreement":null},{"id":"W4388463913","doi":"10.18280/ria.370530","title":"Improving Cancer Classification Using Deep Reinforcement Learning with Convolutional LSTM Networks","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Convolutional neural network; Deep learning; Machine learning","score_opus":0.05742308572518883,"score_gpt":0.28730958763067144,"score_spread":0.2298865019054826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388463913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011005034,0.00019495393,0.98673755,0.00031861145,0.0006562192,0.0002480996,2.8560498e-7,0.0004068692,0.00043238568],"genre_scores_gemma":[0.99338335,0.0001450779,0.005118843,0.000071391005,0.00023257955,0.0000905052,0.000007590934,0.000022393631,0.00092828146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824286,0.00006082182,0.0003761468,0.0005486234,0.00030580352,0.00046574807],"domain_scores_gemma":[0.99888974,0.00011757748,0.00025243164,0.0004519294,0.0001976034,0.00009073377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045473018,0.00017092953,0.00015091276,0.00018272175,0.0004848586,0.00015685591,0.0004736517,0.00008603693,0.00006995318],"category_scores_gemma":[0.00004520029,0.00016917863,0.00005669367,0.0014887453,0.00008757483,0.00050258264,0.00017245905,0.00030415415,0.00014303537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000110828,0.000008552535,0.0005955662,0.000020805224,0.000012184591,0.000004281181,0.0004159062,0.9281951,0.0037300144,0.0039202264,0.00004124041,0.063045025],"study_design_scores_gemma":[0.000040065388,0.00008862187,0.0002409725,0.000081062186,0.000010293768,0.000016885911,0.0004031452,0.99028116,0.0075858757,0.00016915947,0.0008606484,0.00022209383],"about_ca_topic_score_codex":0.00022166396,"about_ca_topic_score_gemma":0.000047707716,"teacher_disagreement_score":0.9823783,"about_ca_system_score_codex":0.00038186906,"about_ca_system_score_gemma":0.00012791553,"threshold_uncertainty_score":0.68989044},"labels":[],"label_agreement":null},{"id":"W4388478170","doi":"10.18280/ria.370518","title":"Efficient Feature Selection Using CNN, VGG16 and PCA for Breast Cancer Ultrasound Detection","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature selection; Breast cancer; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Computer science; Cancer detection; Cancer; Medicine; Internal medicine","score_opus":0.03562252867245017,"score_gpt":0.29115513330303355,"score_spread":0.25553260463058336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388478170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19037776,0.00017368472,0.80671674,0.0006679328,0.0011921325,0.00043559234,0.000016824077,0.00036255564,0.00005679624],"genre_scores_gemma":[0.9947329,0.00011951563,0.0039253803,0.000067644156,0.00033595314,0.00011355188,0.0000019192603,0.000026943579,0.00067616126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839973,0.00004819795,0.00026363612,0.0006561837,0.00019680052,0.00043545183],"domain_scores_gemma":[0.9990062,0.0002230132,0.00013749885,0.00032742808,0.00020990038,0.00009595573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043298161,0.00019112961,0.00017366963,0.0002499667,0.0005384734,0.00019321273,0.00028173087,0.00013514279,0.00002333734],"category_scores_gemma":[0.000066125605,0.00019889025,0.0000845552,0.0016446399,0.0000669617,0.00021039722,0.000091129594,0.0001932207,0.000048701993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049521583,0.000038368667,0.0003880196,0.00011600472,0.000026110005,0.0000021079904,0.0010190791,0.5645577,0.18888919,0.00070989307,0.0004075555,0.2437965],"study_design_scores_gemma":[0.00004966678,0.00007033933,0.00080526987,0.00006337425,0.000014856928,0.00015406504,0.0001556418,0.86045706,0.13619374,0.00065147044,0.0011779746,0.00020652608],"about_ca_topic_score_codex":0.000119656084,"about_ca_topic_score_gemma":0.000106738444,"teacher_disagreement_score":0.8043552,"about_ca_system_score_codex":0.0002894951,"about_ca_system_score_gemma":0.00006641009,"threshold_uncertainty_score":0.81105095},"labels":[],"label_agreement":null},{"id":"W4388479011","doi":"10.1145/3608164.3608167","title":"Patch-based deep learning models for breast mammographic mass classification","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Winnipeg; Western University; University of Manitoba","funders":"CancerCare Manitoba Foundation","keywords":"Interpretability; Mammography; Artificial intelligence; Breast cancer; Computer science; Machine learning; Deep learning; Breast imaging; Identification (biology); Breast cancer screening; Pattern recognition (psychology); Medicine; Cancer; Internal medicine","score_opus":0.048603671580579516,"score_gpt":0.2573319547039336,"score_spread":0.2087282831233541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388479011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019360213,0.000011072577,0.99356043,0.0018453602,0.0003063556,0.00022551022,0.000002762502,0.001174645,0.00093784905],"genre_scores_gemma":[0.94864875,0.000010415861,0.050498463,0.00012411813,0.00006397116,0.00018759586,0.000011483077,0.000015837004,0.00043938597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998952,0.000043864027,0.00015574988,0.00037553243,0.00021673586,0.0002561408],"domain_scores_gemma":[0.9993025,0.00011698638,0.000072791714,0.00033980582,0.00011086666,0.000057045516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033927595,0.00009596236,0.00008454323,0.00023787428,0.00018902097,0.00011661277,0.00037643028,0.00006779617,0.000010046122],"category_scores_gemma":[0.0000116760675,0.000094462695,0.00007915962,0.0010507706,0.000024202114,0.000425452,0.000039189214,0.00010224632,0.000055133154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032081716,0.000027807877,0.002562143,0.000063903455,0.000023301327,0.0000021206802,0.00023336727,0.25071058,0.007347528,0.064089134,0.00085693604,0.6740511],"study_design_scores_gemma":[0.00022578027,0.000051722654,0.0027241283,0.0000070370957,0.0000035885073,0.0000022414883,0.000047070673,0.97641784,0.0007488804,0.018875778,0.0007744785,0.00012144783],"about_ca_topic_score_codex":0.000031740758,"about_ca_topic_score_gemma":0.000035244597,"teacher_disagreement_score":0.94671273,"about_ca_system_score_codex":0.000063202875,"about_ca_system_score_gemma":0.000040056493,"threshold_uncertainty_score":0.3852077},"labels":[],"label_agreement":null},{"id":"W4388629053","doi":"10.3390/jimaging9110247","title":"Breast Cancer Detection with an Ensemble of Deep Learning Networks Using a Consensus-Adaptive Weighting Method","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Weighting; Artificial intelligence; Deep learning; Mammography; Key (lock); CAD; Breast cancer; Annotation; Pixel; Machine learning; Pattern recognition (psychology); Data mining; Computer vision; Cancer; Medicine","score_opus":0.01912822891537277,"score_gpt":0.29562316184281096,"score_spread":0.2764949329274382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388629053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14311156,0.00019463159,0.85598946,0.00012505957,0.0004253441,0.000048699196,2.9067184e-7,0.000060954255,0.000043990312],"genre_scores_gemma":[0.8341469,0.000022981374,0.16548844,0.000025004276,0.00029147114,0.0000013564058,5.975338e-8,0.000018776082,0.000004963983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984614,0.00027213234,0.0004078898,0.00020989284,0.00036624563,0.00028241464],"domain_scores_gemma":[0.99809724,0.00019893417,0.0009250839,0.00015346688,0.00053560693,0.00008969667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001257282,0.00013110475,0.00025451422,0.00036834838,0.00021849724,0.000094161034,0.00025602663,0.000036145564,0.0000037028071],"category_scores_gemma":[0.000027228361,0.00011323452,0.00007405674,0.0010391858,0.00004493642,0.0007723058,0.00008039923,0.00046833677,5.054436e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104781146,0.000008532714,0.0026785063,0.00001056734,0.000047724174,0.000054970158,0.00075091445,0.4683643,0.030332439,0.000018808973,0.000003405561,0.49762505],"study_design_scores_gemma":[0.00037542908,0.00014674329,0.0027502158,0.00021502998,0.000041026866,0.0028974125,0.0007418237,0.97823954,0.014244434,0.00020384144,0.000016175823,0.00012831522],"about_ca_topic_score_codex":0.00022963206,"about_ca_topic_score_gemma":0.00006320083,"teacher_disagreement_score":0.6910354,"about_ca_system_score_codex":0.00025023703,"about_ca_system_score_gemma":0.00012792299,"threshold_uncertainty_score":0.46175697},"labels":[],"label_agreement":null},{"id":"W4388707906","doi":"10.47363/jcrr/2023(5)178","title":"Supporting Cases for the Depletion Model of Immune Check pointInhibitor Therapy in Cancer","year":2023,"lang":"en","type":"article","venue":"Journal of Cancer Research Reviews & Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Multidisciplinary approach; Breast cancer; Personalized medicine; Precision medicine; Health care; Key (lock); Medicine; Health professionals; Cancer; Computer science; Data science; Bioinformatics; Political science; Pathology; Internal medicine; Computer security","score_opus":0.24427536305376582,"score_gpt":0.5020931618516563,"score_spread":0.25781779879789046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388707906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.606576,0.3159797,0.05383007,0.015239054,0.0036554986,0.004541717,0.000011171229,0.00006542779,0.00010136647],"genre_scores_gemma":[0.7762223,0.21938132,0.0023665735,0.00010227203,0.00069622294,0.00079830876,7.049241e-7,0.000033558954,0.00039877312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568546,0.00030320694,0.0020194827,0.00030308487,0.0011634623,0.0005253079],"domain_scores_gemma":[0.9954862,0.00052455673,0.0021619694,0.00061201723,0.0011287631,0.00008652247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016291974,0.00014464972,0.00055680034,0.00044236373,0.00017288623,0.00008755731,0.00063221966,0.00006553157,0.000024351391],"category_scores_gemma":[0.0012101053,0.00009202393,0.0003551821,0.0016092685,0.00009174214,0.0005512832,0.0001594783,0.0005393409,0.0000012340215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020841465,0.00009116692,0.005945835,0.0005549421,0.00009884575,0.00025137854,0.0013725031,0.015416214,0.054461412,0.000096998716,0.021518858,0.8999834],"study_design_scores_gemma":[0.0030382487,0.0025367695,0.022741253,0.0082933195,0.00010983163,0.0016690836,0.00058427075,0.24613865,0.26529336,0.014010462,0.43462253,0.0009622342],"about_ca_topic_score_codex":0.001102275,"about_ca_topic_score_gemma":0.000502944,"teacher_disagreement_score":0.8990212,"about_ca_system_score_codex":0.00045341798,"about_ca_system_score_gemma":0.001240795,"threshold_uncertainty_score":0.5646506},"labels":[],"label_agreement":null},{"id":"W4388814336","doi":"10.21203/rs.3.rs-3611888/v1","title":"Next-Generation Histopathology: A Clinical Trial of Advanced Virtual Histochemical Stains","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Histopathology; Medicine; Pathology; Dermatology","score_opus":0.35355157143579446,"score_gpt":0.49314304477259185,"score_spread":0.1395914733367974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388814336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6396264,0.000693721,0.33335543,0.0047328444,0.015000349,0.004884871,0.00009834808,0.00092982117,0.0006782027],"genre_scores_gemma":[0.9688489,0.0006861182,0.022293525,0.000052679414,0.0043502287,0.0013321202,0.00014543552,0.00008941571,0.0022015942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99304485,0.0018166812,0.0011466312,0.0015056423,0.0018305,0.0006556863],"domain_scores_gemma":[0.99515116,0.001077828,0.0004067041,0.002101368,0.0010370405,0.00022592652],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0062050773,0.00026887466,0.0006518879,0.0006375774,0.00019166346,0.0001494663,0.0020360597,0.0008203286,0.000018406596],"category_scores_gemma":[0.003367819,0.00028421087,0.0003801249,0.00079509063,0.00049094716,0.00028439026,0.0036192744,0.0027475064,0.00009027634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02498601,0.00249647,0.00038428462,0.0016767327,0.00020109426,0.00045644396,0.004218961,0.009129665,0.115786076,0.025198277,0.09224753,0.72321844],"study_design_scores_gemma":[0.10776449,0.042052668,0.00656929,0.0027581875,0.00013869622,0.00005703701,0.0012527788,0.6028768,0.03414719,0.07718511,0.120946124,0.004251617],"about_ca_topic_score_codex":0.00009985488,"about_ca_topic_score_gemma":0.000050647697,"teacher_disagreement_score":0.71896684,"about_ca_system_score_codex":0.0013468262,"about_ca_system_score_gemma":0.0018621205,"threshold_uncertainty_score":0.999961},"labels":[],"label_agreement":null},{"id":"W4388838998","doi":"10.1016/j.cor.2023.106483","title":"Evolutionary multi-objective design of autoencoders for compact representation of histopathology whole slide images","year":2023,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Brock University; Ontario Tech University","funders":"Government of Ontario; Ontario Research Foundation","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Dimensionality reduction; Evolutionary algorithm; Deep learning; Minification; Representation (politics); Contextual image classification; Digital pathology; Feature vector; Reduction (mathematics); Code (set theory); Set (abstract data type); Image (mathematics); Mathematics","score_opus":0.1664929482050457,"score_gpt":0.42645899678712795,"score_spread":0.2599660485820823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388838998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047776806,0.00010394144,0.9920614,0.001322699,0.00047231143,0.0010353639,0.000030622232,0.00013899826,0.000057019603],"genre_scores_gemma":[0.54198873,0.00004153719,0.45713875,0.000022300015,0.00006493006,0.0001885235,0.000036208414,0.000017331393,0.0005016983],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750674,0.0007216912,0.00041182037,0.00050045946,0.00050029677,0.00035899243],"domain_scores_gemma":[0.9968734,0.0011290371,0.00007402807,0.00062487146,0.0012311655,0.000067518515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013435883,0.00011517742,0.00025145113,0.0009077553,0.00040250213,0.00006371957,0.00077224645,0.00007793621,0.000004486259],"category_scores_gemma":[0.00042421333,0.00012270451,0.00009217768,0.0020350015,0.00034559032,0.0005954388,0.00026544483,0.00020370247,0.000025842945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046757195,0.000116634976,0.00027384795,0.000043747277,0.000027455593,0.0000053787394,0.002501421,0.9010072,0.06649228,0.0017677549,0.020581855,0.0071356697],"study_design_scores_gemma":[0.00054831564,0.00042646384,0.0131209735,0.00003419571,0.000004562796,0.0000096734175,0.00026332017,0.9589031,0.025464436,0.00094515865,0.0001786595,0.000101179685],"about_ca_topic_score_codex":0.00031039992,"about_ca_topic_score_gemma":0.000025032588,"teacher_disagreement_score":0.53721106,"about_ca_system_score_codex":0.00031238922,"about_ca_system_score_gemma":0.00046129845,"threshold_uncertainty_score":0.5003745},"labels":[],"label_agreement":null},{"id":"W4388898219","doi":"10.21203/rs.3.rs-3620182/v1","title":"Detection of Osteosarcoma using Deep Feature Extraction with Federated Learning and MLP from Histopathological Images","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Trent University; Nottingham Trent University","keywords":"Osteosarcoma; Computer science; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Feature (linguistics); Feature extraction; Random forest; Principal component analysis; Transfer of learning; Deep learning; AdaBoost; Machine learning; Support vector machine; Pathology; Medicine","score_opus":0.07209873375064127,"score_gpt":0.37975833832818673,"score_spread":0.3076596045775455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388898219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46864745,0.00123482,0.5282921,0.00032630475,0.00041532866,0.00058970746,0.000013150213,0.00039439122,0.00008674862],"genre_scores_gemma":[0.9815342,0.00028590948,0.017645067,0.0000033148528,0.00019820804,0.000077101,0.0000232294,0.000040486026,0.00019249518],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961757,0.0010163825,0.0002570042,0.0010488322,0.0010632323,0.00043885983],"domain_scores_gemma":[0.99792117,0.00052637624,0.00025896585,0.00047114186,0.0007058247,0.000116496696],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012108847,0.0002517905,0.00034741015,0.0005229134,0.0005625736,0.00046106914,0.00040302635,0.0005006528,0.000008416873],"category_scores_gemma":[0.00035236683,0.0002245912,0.000069486625,0.0007982257,0.00021674679,0.00034517914,0.0012384353,0.0027989675,0.000007981092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007988317,0.00017380323,0.0210184,0.001473775,0.00016597036,0.00078637386,0.0023764102,0.01453997,0.55419004,0.000068286776,0.00012148656,0.40428668],"study_design_scores_gemma":[0.0011930896,0.0023996404,0.19008754,0.0023394716,0.00006491847,0.00032471,0.0019356965,0.6251157,0.16919221,0.0052988813,0.0009582088,0.0010899564],"about_ca_topic_score_codex":0.0013802983,"about_ca_topic_score_gemma":0.00040712857,"teacher_disagreement_score":0.6105757,"about_ca_system_score_codex":0.00062781427,"about_ca_system_score_gemma":0.00021447269,"threshold_uncertainty_score":0.9995016},"labels":[],"label_agreement":null},{"id":"W4388966638","doi":"10.1109/jbhi.2023.3336372","title":"Center-Focused Affinity Loss for Class Imbalance Histology Image Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Terry Fox Foundation","keywords":"Softmax function; Computer science; Artificial intelligence; Deep learning; Class (philosophy); Feature (linguistics); Machine learning; Margin (machine learning); Pattern recognition (psychology); Feature vector","score_opus":0.06459826228157346,"score_gpt":0.3447091613112355,"score_spread":0.2801108990296621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388966638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022918483,0.00007478091,0.93827343,0.03575923,0.0026492793,0.00018155402,0.000017494556,0.000066863664,0.00005889568],"genre_scores_gemma":[0.7487928,0.0037001672,0.23826042,0.0075718653,0.0014956872,0.000032597105,0.000020802552,0.000023831859,0.00010179559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816763,0.00004022292,0.0010607237,0.0000760566,0.00035071274,0.00030464656],"domain_scores_gemma":[0.99825746,0.00014537452,0.0009679172,0.00016065635,0.0001879053,0.00028065927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016138684,0.00009061168,0.00026759348,0.00026562327,0.00016765714,0.000051143506,0.00036902362,0.000101185884,0.000001871836],"category_scores_gemma":[0.00007439512,0.00007263819,0.000058927842,0.00039547746,0.00015144731,0.00050603825,0.000047193138,0.00025427295,0.000013190269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014926052,0.00023245807,0.0013426314,0.0019681815,0.00006576756,0.000018513112,0.0059150313,0.000023757415,0.00053407834,0.00481063,0.22758913,0.75735056],"study_design_scores_gemma":[0.005076827,0.0033387414,0.019537864,0.00033839192,0.00001696802,0.00083198264,0.00044068496,0.43691495,0.00039426933,0.0086782295,0.52407414,0.00035694608],"about_ca_topic_score_codex":0.000004037814,"about_ca_topic_score_gemma":0.000003978939,"teacher_disagreement_score":0.7569936,"about_ca_system_score_codex":0.00020311475,"about_ca_system_score_gemma":0.00038923518,"threshold_uncertainty_score":0.29620996},"labels":[],"label_agreement":null},{"id":"W4389042111","doi":"10.1101/2023.11.26.568745","title":"A Multi-Granularity Approach to Similarity Search in Multiplexed Immunofluorescence Images","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalizability theory; Computer science; Granularity; Artificial intelligence; Pipeline (software); Robustness (evolution); Data mining; Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.04339316574468382,"score_gpt":0.2633988637846306,"score_spread":0.2200056980399468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389042111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18297088,0.0006241901,0.80574876,0.00092588173,0.0033092564,0.0033477664,0.00025711066,0.0028062416,0.000009913728],"genre_scores_gemma":[0.6874757,0.00011104325,0.31129736,0.00014999397,0.00017419437,0.0006701406,2.764589e-7,0.00011434203,0.0000069956677],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9935443,0.00053086726,0.000862429,0.002785705,0.0010312991,0.0012454183],"domain_scores_gemma":[0.9947443,0.00016489693,0.00028420158,0.0036771777,0.0006878048,0.0004416176],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025379905,0.00080342725,0.00084375875,0.0010430486,0.00027989247,0.00081754103,0.0038590317,0.0007945794,0.0000036571198],"category_scores_gemma":[0.0005734874,0.0009482864,0.00023183915,0.0028055464,0.00017335404,0.0005708432,0.004441958,0.002374628,0.00017846875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006652365,0.0007762093,0.019685462,0.00090218725,0.00011617228,0.00014343516,0.0002057821,0.0071374844,0.97004193,0.00043826347,0.00045476804,0.000031780935],"study_design_scores_gemma":[0.0010177459,0.00006383263,0.57648784,0.0004970687,0.000023364344,3.8550432e-8,0.00000678597,0.14380343,0.27629402,0.000007825125,0.0003274331,0.0014705773],"about_ca_topic_score_codex":0.0018839859,"about_ca_topic_score_gemma":0.000043355827,"teacher_disagreement_score":0.6937479,"about_ca_system_score_codex":0.0012785073,"about_ca_system_score_gemma":0.0009781701,"threshold_uncertainty_score":0.9999269},"labels":[],"label_agreement":null},{"id":"W4389054294","doi":"10.1007/s00521-023-09172-x","title":"VolPAM: Volumetric Phenotype-Activation-Map for data-driven discovery of 3D imaging phenotypes and interpretability","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; University of Manitoba","funders":"","keywords":"Interpretability; Phenotype; Convolutional neural network; Phenotypic screening; Artificial intelligence; Computational biology; Computer science; Autoencoder; Clinical phenotype; Machine learning; Deep learning; Pattern recognition (psychology); Biology; Genetics; Gene","score_opus":0.026910221674158512,"score_gpt":0.3003529253605365,"score_spread":0.27344270368637796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389054294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10427231,0.00011713512,0.89436984,0.00055963587,0.000109432185,0.00033619124,0.000023075707,0.00017803884,0.00003432157],"genre_scores_gemma":[0.97414154,0.00000826961,0.025603615,0.000055055454,0.00010281331,0.000035722263,0.000028328184,0.000007971654,0.000016679645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990734,0.000026553507,0.00020509052,0.0004519435,0.00009974539,0.00014329163],"domain_scores_gemma":[0.99872655,0.0005207359,0.00012699544,0.0005161522,0.0000769954,0.000032562053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021108313,0.00008911572,0.00012748981,0.00011613505,0.00022891449,0.00011855347,0.0003975693,0.000022104005,3.9389622e-7],"category_scores_gemma":[0.00006166226,0.00008908906,0.000019166993,0.0006214029,0.00007860728,0.00049747137,0.0005208379,0.000080843274,0.0000016938953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008699827,0.000034754812,0.0104135,0.00018545354,0.000018985242,1.07604265e-7,0.00037623054,0.0017175736,0.0034726574,0.0051231817,0.00044820635,0.9782007],"study_design_scores_gemma":[0.00012481767,0.000022509197,0.011886106,0.000017225175,0.000009822448,0.0000013096882,0.000035011737,0.98360986,0.0003774386,0.0024808391,0.0013417072,0.000093358714],"about_ca_topic_score_codex":0.000068796064,"about_ca_topic_score_gemma":0.000004471508,"teacher_disagreement_score":0.9818923,"about_ca_system_score_codex":0.000021050068,"about_ca_system_score_gemma":0.000024034687,"threshold_uncertainty_score":0.36329463},"labels":[],"label_agreement":null},{"id":"W4389217992","doi":"10.48550/arxiv.2311.17740","title":"A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Histopathology; Artificial intelligence; Digital pathology; Computer science; Pattern recognition (psychology); Machine learning; Pathology; Medicine","score_opus":0.24295037129158742,"score_gpt":0.23136938748573946,"score_spread":0.01158098380584796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389217992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17359185,0.00008185292,0.8245583,0.000051756302,0.00046262614,0.00040955795,0.000104256826,0.00028080487,0.00045895306],"genre_scores_gemma":[0.9937691,0.00018658253,0.004903916,0.000008083469,0.0001254045,0.00002147227,0.00007651726,0.000024232126,0.0008846826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803287,0.00010898597,0.00022747551,0.0012700562,0.00011615584,0.0002444743],"domain_scores_gemma":[0.99851507,0.00020426071,0.00038697722,0.000590408,0.00022778276,0.00007551572],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018532734,0.00025018284,0.0003539566,0.00020803079,0.00013353396,0.000083084655,0.0010555019,0.00033378715,0.0000097948605],"category_scores_gemma":[0.000057594243,0.00028482862,0.0002628599,0.0004481286,0.00017123285,0.00046142502,0.00050522905,0.0005260339,0.000009017144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045874287,0.00035438218,0.015953394,0.00044964263,0.00035951572,0.000083657775,0.004530143,0.92843205,0.0030418476,0.030403525,0.00033037952,0.015602733],"study_design_scores_gemma":[0.00042525138,0.00012883011,0.012740997,0.0000697762,0.000117995405,0.000001590499,0.00032559823,0.9645974,0.0005951332,0.020292422,0.00028967028,0.00041535948],"about_ca_topic_score_codex":0.00031124437,"about_ca_topic_score_gemma":0.000031367934,"teacher_disagreement_score":0.82017726,"about_ca_system_score_codex":0.00055282796,"about_ca_system_score_gemma":0.00017417407,"threshold_uncertainty_score":0.99996036},"labels":[],"label_agreement":null},{"id":"W4389340115","doi":"10.7717/peerj-cs.1651","title":"A deep learning approach for the detection and counting of colon cancer cells (HT-29 cells) bunches and impurities","year":2023,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Artificial intelligence; Colorectal cancer; Computer science; Pattern recognition (psychology); Cancer cell; Cancer; Machine learning; Medicine; Internal medicine","score_opus":0.01881575428924857,"score_gpt":0.2453289860026231,"score_spread":0.22651323171337454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389340115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105380096,0.00047091197,0.89258814,0.00016037365,0.0009090231,0.0003107623,0.0000012930399,0.00015464226,0.00002474409],"genre_scores_gemma":[0.9440735,0.00021511398,0.055329468,0.000063879044,0.00016982296,0.00009019166,2.4532716e-7,0.000009459727,0.00004834985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983542,0.00004446499,0.0002040306,0.00058620406,0.00044311222,0.00036799366],"domain_scores_gemma":[0.99886256,0.00041518806,0.00016512729,0.0002718553,0.00022207136,0.00006317568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014712502,0.0001381707,0.0001665632,0.00020059745,0.0008292056,0.00041730065,0.0006750575,0.0000465036,5.345106e-7],"category_scores_gemma":[0.000027990576,0.00011173641,0.00003620745,0.0011561868,0.0005093088,0.00063433324,0.0006015281,0.00015827653,9.1695887e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016007816,0.000017726123,0.0005488247,0.00022907316,0.000019992669,9.435665e-7,0.006638397,0.099586345,0.12387323,0.00047227024,0.00010288713,0.7684943],"study_design_scores_gemma":[0.00017468008,0.00013358265,0.0026251024,0.00001823535,0.000008757621,0.00000945608,0.0001415616,0.9399213,0.05609362,0.00022892778,0.000516864,0.00012789376],"about_ca_topic_score_codex":0.00020880175,"about_ca_topic_score_gemma":0.000040656716,"teacher_disagreement_score":0.84033495,"about_ca_system_score_codex":0.00007303944,"about_ca_system_score_gemma":0.00008298049,"threshold_uncertainty_score":0.6377663},"labels":[],"label_agreement":null},{"id":"W4389344229","doi":"10.21203/rs.3.rs-3650733/v1","title":"Harmonizing the Scale: An End-to-End Self-Supervised Framework for Cross-Modal Search and Retrieval in Histopathology Archives","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Waterloo","funders":"","keywords":"Harmonization; Computer science; Modal; Modalities; Data science; Scale (ratio); Scarcity; Representation (politics); Digital pathology; Artificial intelligence; Space (punctuation); Big data; Information retrieval; Machine learning; Data mining; Geography","score_opus":0.1566701881777867,"score_gpt":0.42961288341301374,"score_spread":0.2729426952352271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389344229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.587481,0.000717154,0.39793625,0.008224896,0.0012262107,0.0036432752,0.00013076057,0.00050773716,0.00013267565],"genre_scores_gemma":[0.85433406,0.00042488516,0.14292118,0.00011671088,0.00084566674,0.00092204445,0.000029692485,0.000105582454,0.00030018727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992948,0.0017608145,0.00049880013,0.0019324844,0.0014681644,0.0013917694],"domain_scores_gemma":[0.99356705,0.003508289,0.00007354605,0.0020629237,0.00041783892,0.00037035893],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0067023807,0.00034552687,0.00045709373,0.00113633,0.00084945385,0.0011835457,0.0030551197,0.00054469367,0.000014462013],"category_scores_gemma":[0.001117088,0.0003063496,0.00014140835,0.0014771618,0.0006092014,0.0003239293,0.005718414,0.0039646477,0.000028631997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038269702,0.0010083542,0.09479082,0.00880343,0.00021720715,0.0008936703,0.20765842,0.017568829,0.01402665,0.052499536,0.0009996934,0.59770644],"study_design_scores_gemma":[0.0010777614,0.0016899002,0.29622015,0.0012066285,0.000013453411,0.000057664354,0.0014245841,0.5184157,0.0037831469,0.17359993,0.0015959294,0.0009151898],"about_ca_topic_score_codex":0.00049767696,"about_ca_topic_score_gemma":0.0003123304,"teacher_disagreement_score":0.5967912,"about_ca_system_score_codex":0.0006607863,"about_ca_system_score_gemma":0.0010021128,"threshold_uncertainty_score":0.99993885},"labels":[],"label_agreement":null},{"id":"W4389442222","doi":"10.1212/wnl.86.16_supplement.p4.155","title":"Combining High-Resolution FLAIR and T <sub>2</sub> to Improve Multiple Sclerosis Lesion Conspicuity (P4.155)","year":2016,"lang":"en","type":"article","venue":"Neurology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multiple sclerosis; Fluid-attenuated inversion recovery; Medicine; Lesion; High resolution; Nuclear medicine; Radiology; Pathology; Magnetic resonance imaging; Psychiatry; History","score_opus":0.025747705845983865,"score_gpt":0.21872925659312092,"score_spread":0.19298155074713705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389442222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79393566,0.000022382597,0.1994122,0.0049063447,0.0012854234,0.00019720022,0.0000044509684,0.0002053918,0.00003096755],"genre_scores_gemma":[0.99650776,0.000043043,0.0014782844,0.0018127993,0.00009086404,0.000046489065,4.6761542e-7,0.00001411462,0.0000061610913],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998429,0.00016481041,0.00021083164,0.0006634777,0.00016327511,0.00036857792],"domain_scores_gemma":[0.9988966,0.00033145183,0.00010187215,0.00046685425,0.000070196125,0.00013304151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002267862,0.00015076276,0.00018019658,0.00012432117,0.00018878972,0.00004123253,0.00032784167,0.00015273714,0.0000028570842],"category_scores_gemma":[0.00013771489,0.00012634952,0.00003269337,0.00019696631,0.00011353116,0.0003137057,0.00044985005,0.00016287348,0.00008095221],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107547494,0.000019246188,0.0020329056,0.0000047336493,0.000004622719,0.0000057214847,0.00006624957,0.000039026927,0.8306057,0.001045992,0.00026244568,0.1658058],"study_design_scores_gemma":[0.0022936652,0.003251592,0.32635128,0.00003185039,0.000012324599,0.00006609186,0.0000014672004,0.014985941,0.64804375,0.0028369909,0.001764338,0.00036072393],"about_ca_topic_score_codex":0.00015121794,"about_ca_topic_score_gemma":0.00021798136,"teacher_disagreement_score":0.32431838,"about_ca_system_score_codex":0.000056094537,"about_ca_system_score_gemma":0.000035906665,"threshold_uncertainty_score":0.5152384},"labels":[],"label_agreement":null},{"id":"W4389473726","doi":"10.1109/tip.2023.3337666","title":"Neural Graph Refinement for Robust Recognition of Nuclei Communities in Histopathological Landscape","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Khalifa University of Science, Technology and Research; Terry Fox Foundation","keywords":"Computer science; Graph; Artificial intelligence; Traverse; Artificial neural network; Theoretical computer science; Pattern recognition (psychology); Machine learning; Cartography","score_opus":0.06548238828149557,"score_gpt":0.28092476678420325,"score_spread":0.2154423785027077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389473726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054485988,0.000039774503,0.9441151,0.00038802778,0.0003267876,0.00019210098,0.000013707199,0.0002664556,0.00017207644],"genre_scores_gemma":[0.9403065,0.00004306277,0.059322957,0.00008113999,0.00001843953,0.00017558913,0.0000057563893,0.000013365277,0.000033215092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990752,0.000066594584,0.0002769355,0.00020999646,0.00016150108,0.0002097828],"domain_scores_gemma":[0.99943,0.00011455548,0.0000998843,0.00021341631,0.00011416571,0.000027971528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034500138,0.00011035029,0.00014798641,0.00040826155,0.00022387905,0.000083965926,0.00026081182,0.00005912373,0.0000154959],"category_scores_gemma":[0.000006757312,0.00011070773,0.000069482725,0.00081082014,0.000076055854,0.00062886835,0.000003830619,0.00019985758,0.000006485155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105842744,0.0001900623,0.00003098246,0.00026153176,0.000006250647,0.0000073278425,0.0024325652,0.024921335,0.0066120857,0.000011067652,0.00014437771,0.9652766],"study_design_scores_gemma":[0.001206981,0.0004829803,0.0007439992,0.00027852782,0.000023134815,0.00002637614,0.0015306338,0.96124065,0.031875096,0.002159613,0.0001163731,0.00031566102],"about_ca_topic_score_codex":0.000036010424,"about_ca_topic_score_gemma":0.000098804834,"teacher_disagreement_score":0.96496093,"about_ca_system_score_codex":0.000067613095,"about_ca_system_score_gemma":0.000034847028,"threshold_uncertainty_score":0.45145303},"labels":[],"label_agreement":null},{"id":"W4389495561","doi":"10.2196/42505","title":"A Biobanking System for Diagnostic Images: Architecture Development, COVID-19–Related Use Cases, and Performance Evaluation","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; European Commission","keywords":"Biobank; Computer science; Upload; Data collection; Preprint; World Wide Web","score_opus":0.135499077101566,"score_gpt":0.42177432238429036,"score_spread":0.28627524528272436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389495561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8848907,0.0001656866,0.11039804,0.0006519162,0.00034318154,0.0028510105,0.000025746902,0.0005481752,0.00012559207],"genre_scores_gemma":[0.9951708,0.0000563091,0.0023160626,0.000034913188,0.000039562852,0.0022391314,0.000036648566,0.000017698805,0.000088892026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702847,0.00046940253,0.000349791,0.00045448882,0.0010726193,0.0006252415],"domain_scores_gemma":[0.99331385,0.005486587,0.00012483686,0.00037176395,0.0005013932,0.00020154826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046396665,0.00016326347,0.0001670303,0.00084849674,0.0011181394,0.00041677253,0.00046958172,0.00010334427,0.0000057081884],"category_scores_gemma":[0.002717331,0.00014526735,0.00003658249,0.0020420712,0.00014291077,0.0013330363,0.00044675125,0.00038642113,0.0000853771],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021265839,0.000080688675,0.0070059486,0.0033293816,0.00014619912,0.000067505134,0.08273755,0.0034135876,0.000679788,0.0025985658,0.008609836,0.8911183],"study_design_scores_gemma":[0.0032925396,0.0012940428,0.09110557,0.000956049,0.000018656492,0.00045356082,0.0030814786,0.87037987,0.00767269,0.0016391636,0.019347781,0.0007585756],"about_ca_topic_score_codex":0.000047684807,"about_ca_topic_score_gemma":0.000024575524,"teacher_disagreement_score":0.8903597,"about_ca_system_score_codex":0.0012180378,"about_ca_system_score_gemma":0.00074933714,"threshold_uncertainty_score":0.85999376},"labels":[],"label_agreement":null},{"id":"W4389537784","doi":"10.1109/embc40787.2023.10340335","title":"Composite Biomarker Image for Advanced Visualization in Histopathology","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Grand River Hospital; Vector Institute; University of Waterloo","funders":"","keywords":"Digital pathology; Computer science; Biomarker; Visualization; Artificial intelligence; Computer vision; H&E stain; Workflow; Pathology; Immunohistochemistry; Pattern recognition (psychology); Medicine","score_opus":0.02186244418329363,"score_gpt":0.32380846518813444,"score_spread":0.3019460210048408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389537784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030183844,0.00001531857,0.96657723,0.0007370167,0.000602835,0.00021653618,0.0000010550248,0.0004119247,0.0012542505],"genre_scores_gemma":[0.8549812,0.000024626757,0.14233339,0.0005731275,0.000043336993,0.00024795946,0.000019906907,0.000021425456,0.0017550493],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933887,0.000032751024,0.00013814932,0.00025148198,0.0000735913,0.00016519068],"domain_scores_gemma":[0.9996311,0.00006908354,0.000038260237,0.00019678523,0.000044812507,0.000019963716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021487186,0.000058341837,0.000077662065,0.0002148618,0.000045600646,0.000026278312,0.00020862326,0.000036774505,0.000006655951],"category_scores_gemma":[0.000025098323,0.000059845643,0.000024187846,0.0007343813,0.000019373121,0.0003311854,0.00008347299,0.000025966112,0.000059114074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007469778,0.0000621594,0.002608829,0.00006530362,0.000004818524,0.000028659693,0.0008895486,0.00081996265,0.71672493,0.048588835,0.009387065,0.22074519],"study_design_scores_gemma":[0.0011276463,0.00013914036,0.051202238,0.000014624087,0.0000022371166,0.000013093364,0.000028539565,0.8816081,0.039116632,0.010817383,0.015695965,0.00023438424],"about_ca_topic_score_codex":0.00001195467,"about_ca_topic_score_gemma":0.00003382258,"teacher_disagreement_score":0.88078815,"about_ca_system_score_codex":0.000101944446,"about_ca_system_score_gemma":0.000017697585,"threshold_uncertainty_score":0.24404344},"labels":[],"label_agreement":null},{"id":"W4389544981","doi":"10.1109/icit59216.2023.10335827","title":"Genetic Algorithm-Based Feature Selection for Accurate Breast Cancer Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Random forest; Feature selection; Computer science; Machine learning; Artificial intelligence; Breast cancer; Feature (linguistics); Binary classification; Genetic algorithm; Selection (genetic algorithm); Precision and recall; Recall; Pattern recognition (psychology); Data mining; Cancer; Support vector machine; Medicine","score_opus":0.02950919695893974,"score_gpt":0.2971635982718126,"score_spread":0.2676544013128729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389544981","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013392118,0.000021663302,0.98892367,0.0075071286,0.00088426436,0.00035099316,0.00001967414,0.0008504223,0.00010294924],"genre_scores_gemma":[0.4909488,0.00010145558,0.4984632,0.0014818207,0.001331869,0.0018947864,0.000032702108,0.00006335091,0.005682005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990209,0.000029014405,0.0001191914,0.00039996614,0.00018653928,0.00024440294],"domain_scores_gemma":[0.99936324,0.000057698704,0.00007900208,0.00025126655,0.00019597888,0.000052825348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013390013,0.00010799732,0.000081936865,0.00014855585,0.0001762111,0.00012549173,0.00030370604,0.00009088707,0.000023127905],"category_scores_gemma":[0.00000750226,0.00010062287,0.00005274353,0.0011915496,0.000015594365,0.00028308987,0.000030469591,0.000086602005,0.000055204273],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016060212,0.000018588817,0.00090915995,0.000029053046,0.000017813692,4.9554694e-7,0.000053093536,0.009535336,0.0066250823,0.00071242196,0.045439813,0.93664306],"study_design_scores_gemma":[0.0002529472,0.000039738887,0.07276125,0.000007945498,0.000006322893,0.0000071255477,0.000008187403,0.91504,0.004806456,0.00053032394,0.006413905,0.00012574958],"about_ca_topic_score_codex":0.00010106503,"about_ca_topic_score_gemma":0.00009457728,"teacher_disagreement_score":0.93651736,"about_ca_system_score_codex":0.00021941961,"about_ca_system_score_gemma":0.0001660526,"threshold_uncertainty_score":0.41032815},"labels":[],"label_agreement":null},{"id":"W4389611645","doi":"10.1136/jcp-2023-209203","title":"Evolving educational landscape in pathology: a comprehensive bibliometric and visual analysis including digital teaching and learning resources","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Digital pathology; Citation; Citation analysis; Virtual microscopy; Descriptive statistics; Pathology; Computer science; Medicine; Medical education; Data science; World Wide Web","score_opus":0.06561911578321154,"score_gpt":0.41886088118288684,"score_spread":0.3532417653996753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389611645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98273224,0.0008478253,0.014288804,0.001482469,0.0004156314,0.000039134713,8.001585e-7,0.000028418155,0.00016470265],"genre_scores_gemma":[0.9942229,0.00034829552,0.00493049,0.00016662481,0.000290602,0.0000017272001,0.0000012075313,0.0000073675087,0.000030796393],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971306,0.0010096869,0.0010067716,0.00034522644,0.00027291707,0.0002348546],"domain_scores_gemma":[0.9920288,0.0068417746,0.0007233078,0.00010698234,0.00017460198,0.00012454885],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.004670776,0.000114663664,0.0005857367,0.015988009,0.00019882567,0.00019066244,0.00024875806,0.00016078979,0.0000049615787],"category_scores_gemma":[0.0066309087,0.00010195275,0.00013569059,0.014068908,0.00013807954,0.0006866261,0.00046141678,0.001386027,0.000003992061],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000313458,0.000053491225,0.8412444,0.000010471262,0.00007626549,0.00026918782,0.000981678,0.00060362247,0.00011642275,0.000045451816,0.00010805046,0.15645963],"study_design_scores_gemma":[0.00057173695,0.000499795,0.95158243,0.00002776872,0.00004474104,0.00057314127,0.0004189404,0.044578217,0.0000015257616,0.0011641664,0.00043843218,0.00009907323],"about_ca_topic_score_codex":0.0000054065754,"about_ca_topic_score_gemma":0.000005143517,"teacher_disagreement_score":0.15636055,"about_ca_system_score_codex":0.000031614163,"about_ca_system_score_gemma":0.0000781626,"threshold_uncertainty_score":0.99516493},"labels":[],"label_agreement":null},{"id":"W4389919382","doi":"10.32920/24625203.v1","title":"Synthetic Data Generation Through Image Translation for Improving Out-of-domain MRI Lesion Segmentation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Synthetic data; Segmentation; Translation (biology); Scanner; Pattern recognition (psychology); Noise (video); Image segmentation; Image (mathematics); Computer vision","score_opus":0.21909355583364784,"score_gpt":0.371652170871301,"score_spread":0.15255861503765314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389919382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005738564,0.00008342954,0.99122596,0.0013732406,0.0044240956,0.0015387834,0.00013274803,0.00040955914,0.00023832642],"genre_scores_gemma":[0.03438321,0.00012461543,0.9635168,0.00004976382,0.0004907881,0.00025276406,0.0010041409,0.00004756419,0.00013038608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973193,0.0001252223,0.0006189153,0.0012694732,0.00044040673,0.0002267271],"domain_scores_gemma":[0.99718857,0.00016874356,0.00048719195,0.0019341385,0.00018888322,0.000032502678],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010670492,0.00025123023,0.0002686021,0.00015092056,0.00015488859,0.0002795133,0.0012729659,0.00023844633,0.000008669726],"category_scores_gemma":[0.00005886369,0.00025934083,0.000106222484,0.00018654673,0.000039070706,0.0015406675,0.00092265377,0.00020956705,0.000016715805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043508888,0.00007884705,0.000007524833,0.0013383266,0.00008486909,0.0000019727468,0.004456815,0.009874536,0.4432047,0.0028379315,0.004950299,0.53312063],"study_design_scores_gemma":[0.00031504536,0.00007277609,0.00001438228,0.000071477094,0.00004455198,0.0000010462957,0.00008091895,0.87793374,0.10402829,0.016813392,0.00036073502,0.00026365908],"about_ca_topic_score_codex":0.00024972067,"about_ca_topic_score_gemma":0.00034559402,"teacher_disagreement_score":0.8680592,"about_ca_system_score_codex":0.0002087336,"about_ca_system_score_gemma":0.00020389637,"threshold_uncertainty_score":0.9999859},"labels":[],"label_agreement":null},{"id":"W4390008348","doi":"10.1177/09691413231219952","title":"Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software","year":2023,"lang":"en","type":"review","venue":"Journal of Medical Screening","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Triage; Workload; Breast cancer; Mammography; Meta-analysis; Breast cancer screening; Artificial intelligence; Radiology; Cancer; Machine learning; Medical physics; Internal medicine; Computer science; Emergency medicine","score_opus":0.24870491529275998,"score_gpt":0.42295895886389673,"score_spread":0.17425404357113675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390008348","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028372074,0.47320136,0.5260402,0.000319668,0.00023575476,0.00016540609,0.000009548924,0.000024488556,7.378534e-7],"genre_scores_gemma":[0.00035771116,0.87350154,0.1252173,0.00001591441,0.0007783234,0.000062273175,0.0000040743885,0.000047455647,0.00001541445],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9934063,0.00052479067,0.0029564404,0.0005325061,0.0021739611,0.00040601907],"domain_scores_gemma":[0.9924038,0.0019378505,0.004410277,0.0003391829,0.0005735291,0.0003353659],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0068230913,0.00039352497,0.00429231,0.0014738753,0.00017926969,0.00012889736,0.0013546254,0.0004290332,0.000118513955],"category_scores_gemma":[0.0012730827,0.00029772846,0.003177008,0.0040586083,0.0001965561,0.00038408823,0.00040561325,0.001379287,3.9455202e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044207838,0.00001945145,0.0000072574617,0.0015489795,0.041887134,0.000016160851,0.00022659515,0.00301215,3.7109473e-7,0.000057397778,0.000010638093,0.95316964],"study_design_scores_gemma":[0.00062017224,0.000992454,0.000067178116,0.04195807,0.6565555,0.0022197461,0.0010173001,0.24637273,0.000038588387,0.001240622,0.04735132,0.0015663512],"about_ca_topic_score_codex":0.00019237783,"about_ca_topic_score_gemma":0.000060557893,"teacher_disagreement_score":0.9516033,"about_ca_system_score_codex":0.00010937984,"about_ca_system_score_gemma":0.00037124872,"threshold_uncertainty_score":0.9999475},"labels":[],"label_agreement":null},{"id":"W4390063900","doi":"10.1088/978-0-7503-4637-5ch5","title":"Artificial intelligence applications in pathology","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Computer science; Pathology; Medicine","score_opus":0.06461668773829116,"score_gpt":0.28925808700941524,"score_spread":0.2246413992711241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063900","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.0246665e-7,0.00002622594,0.6892322,0.00032082648,0.00039538718,0.0002067361,0.000002333814,0.00028433712,0.3095313],"genre_scores_gemma":[0.004298056,0.00041070377,0.03424846,0.00041946696,0.0006292758,0.00041955506,0.000022265434,0.00009559233,0.9594566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882656,0.000009691381,0.0003146275,0.0005248304,0.00016042667,0.00016387219],"domain_scores_gemma":[0.9990812,0.00011250661,0.0000936642,0.0006342492,0.000043244167,0.000035156743],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016793112,0.00015148736,0.00016733892,0.00030152622,0.00004439289,0.000040996667,0.00070030906,0.00024322975,0.00009264224],"category_scores_gemma":[0.000008031989,0.00015572396,0.00005543603,0.0001523154,0.000059948925,0.000087300374,0.00027820066,0.0003115814,0.0017908239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.589589e-7,0.000002933684,0.000001084633,0.0000041500266,0.0000020314385,0.000010679636,0.000042515225,0.000042963566,0.0000072659955,0.80480826,0.00012650446,0.19495115],"study_design_scores_gemma":[0.0000055238,0.000028036577,0.00001655564,0.000015978922,0.0000025465397,0.000008690533,0.000006503374,0.0033953604,0.00033402184,0.96440876,0.031589873,0.0001881543],"about_ca_topic_score_codex":0.000018473844,"about_ca_topic_score_gemma":0.0004026752,"teacher_disagreement_score":0.6549837,"about_ca_system_score_codex":0.0001182675,"about_ca_system_score_gemma":0.000073751515,"threshold_uncertainty_score":0.9989864},"labels":[],"label_agreement":null},{"id":"W4390189894","doi":"10.1109/iccvw60793.2023.00281","title":"ALFA – Leveraging All Levels of Feature Abstraction for Enhancing the Generalization of Histopathology Image Classification Across Unseen Hospitals","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Waterloo","funders":"","keywords":"Computer science; Generalizability theory; Abstraction; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Encoder; Feature (linguistics); Contextual image classification; Robustness (evolution); Feature vector; Machine learning; Image (mathematics); Mathematics","score_opus":0.0491325197272561,"score_gpt":0.32891859427462444,"score_spread":0.27978607454736837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390189894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1629809,0.00003363568,0.8333777,0.002447556,0.00056286826,0.00029188578,0.000013597413,0.0001232672,0.00016859938],"genre_scores_gemma":[0.9798804,0.000026894357,0.018930446,0.00010421902,0.000081370934,0.000054657674,0.000015086353,0.000012567627,0.0008943666],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989283,0.000060410737,0.00032109328,0.0002928455,0.00019650148,0.00020085933],"domain_scores_gemma":[0.99877685,0.00016358853,0.0003687168,0.00041223952,0.00025903963,0.000019551735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008301769,0.0000964946,0.0001441644,0.00008705805,0.0001297583,0.000038185182,0.00036814067,0.0000953027,0.0000049519754],"category_scores_gemma":[0.00008169613,0.0000790979,0.0000713562,0.00045559913,0.00006002996,0.0004688362,0.00007706325,0.000083751984,0.0000054985235],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008920588,0.000012076995,0.00021497457,0.00006557831,0.000011821335,5.1833575e-7,0.0034494416,0.0017386144,0.95677054,0.003417317,0.002399645,0.03191055],"study_design_scores_gemma":[0.00034513543,0.0001268507,0.16198164,0.000028535824,0.000017169916,0.000012232562,0.0007517906,0.13927342,0.6909546,0.004224473,0.0021026249,0.00018149719],"about_ca_topic_score_codex":0.000057712154,"about_ca_topic_score_gemma":0.00008679725,"teacher_disagreement_score":0.8168995,"about_ca_system_score_codex":0.00011724708,"about_ca_system_score_gemma":0.000047769347,"threshold_uncertainty_score":0.32255188},"labels":[],"label_agreement":null},{"id":"W4390397138","doi":"10.1007/s11517-023-03006-7","title":"Improved bioimpedance spectroscopy tissue classification through data augmentation from generative adversarial networks","year":2023,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Noise (video); Data mining; Generative adversarial network; Machine learning; Deep learning","score_opus":0.06125577374618365,"score_gpt":0.3214763118368277,"score_spread":0.26022053809064405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390397138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03387041,0.00018455271,0.96074206,0.0009431984,0.002921875,0.00022414241,0.000011243083,0.0010470188,0.000055506298],"genre_scores_gemma":[0.8521845,0.0001367634,0.14497726,0.00031087192,0.0020192943,0.000016458056,0.00033017516,0.00001724101,0.000007470887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754655,0.000118639946,0.0004537662,0.00096362375,0.00041538832,0.00050203165],"domain_scores_gemma":[0.9983678,0.00056408043,0.00014779539,0.0007216706,0.00004387434,0.00015480349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007132359,0.00023766095,0.00027562247,0.00005993476,0.00018215225,0.00012236048,0.0015114119,0.000279418,0.00005387488],"category_scores_gemma":[0.0005460087,0.00020501709,0.000043520547,0.0008517184,0.00007762999,0.00035349934,0.0010374087,0.0004972596,0.00007850802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094734285,0.00017500421,0.0019120381,0.00005146124,0.00023690189,0.00010300012,0.0013773689,0.20299599,0.26810825,0.008439989,0.0063449014,0.5101604],"study_design_scores_gemma":[0.00036728848,0.00010943231,0.006829842,0.000044675802,0.000005939816,0.000004104309,0.000019703117,0.987216,0.0031815828,0.0002537558,0.0017335712,0.00023408701],"about_ca_topic_score_codex":0.00013319017,"about_ca_topic_score_gemma":0.000005535762,"teacher_disagreement_score":0.8183141,"about_ca_system_score_codex":0.00016334382,"about_ca_system_score_gemma":0.00006759098,"threshold_uncertainty_score":0.83603543},"labels":[],"label_agreement":null},{"id":"W4390412016","doi":"10.18280/ts.400642","title":"Deep Learning Based Detection of Dermatological Diseases Using Convolutional Neural Networks and Decision Trees","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Decision tree; Machine learning; Pattern recognition (psychology)","score_opus":0.02272349396156901,"score_gpt":0.25211970625400887,"score_spread":0.22939621229243987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390412016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4000651,0.00012384314,0.599449,0.00003117222,0.00012986109,0.00007432925,0.0000010026849,0.00012350109,0.0000022353274],"genre_scores_gemma":[0.9964596,0.00001144367,0.0033742515,0.00004784906,0.000079416546,0.00001383962,0.00000550242,0.000007051423,0.0000010506004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988184,0.00010131427,0.00025315845,0.00028620264,0.0003249512,0.00021597905],"domain_scores_gemma":[0.99932975,0.00031793118,0.00011576665,0.00010080629,0.000059319547,0.00007643907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018938733,0.00011592105,0.0001452019,0.00015756737,0.00022289777,0.000058280846,0.00016636388,0.000057702866,0.000023904598],"category_scores_gemma":[0.000027588267,0.00010843949,0.00006235606,0.000464571,0.00007980662,0.00027257277,0.000097759716,0.00011489949,0.0000018437248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006702186,0.000027548193,0.014348117,0.000011701052,0.000011256096,0.0000094494935,0.000034953697,0.8622464,0.0035630434,0.00012178951,0.000010622057,0.11954812],"study_design_scores_gemma":[0.00046410316,0.00012654804,0.12121464,0.000018887982,0.000013701329,0.000016164518,0.000017795428,0.8769006,0.0007532989,0.0003497763,0.000027478392,0.00009701522],"about_ca_topic_score_codex":0.000010392464,"about_ca_topic_score_gemma":0.000011573151,"teacher_disagreement_score":0.5963945,"about_ca_system_score_codex":0.00006178599,"about_ca_system_score_gemma":0.000020992797,"threshold_uncertainty_score":0.4422034},"labels":[],"label_agreement":null},{"id":"W4390430259","doi":"10.18280/ts.400611","title":"Enhanced Skin Cancer Classification Through a Hybrid Optimized Approach: Deep Echo Network Machine Utilizing Pelican-Optimized Deep Kohonen Features","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Echo (communications protocol); Artificial intelligence; Pelican; Self-organizing map; Support vector machine; Computer science; Pattern recognition (psychology); Deep learning; Artificial neural network; Biology; Fishery","score_opus":0.034372930612942526,"score_gpt":0.27680437644633626,"score_spread":0.24243144583339374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390430259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031221232,0.00081822375,0.9875567,0.0011261386,0.00090823736,0.0011322007,0.000015961683,0.0011609981,0.004159427],"genre_scores_gemma":[0.793204,0.0006276169,0.20290682,0.0007386794,0.00089556415,0.0011854989,0.00011428967,0.00007141073,0.00025613335],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588853,0.00033051553,0.00071184844,0.0012170046,0.00089829415,0.0009538038],"domain_scores_gemma":[0.9982213,0.00022855533,0.00043219476,0.0007825588,0.00015738588,0.00017804948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008689606,0.0004915225,0.0005449968,0.00020430177,0.000532852,0.0003366538,0.0012433857,0.0001432701,0.00027539543],"category_scores_gemma":[0.000026582788,0.0004760601,0.00025781922,0.0014992035,0.00011292465,0.00083234935,0.00030814548,0.00047013923,0.00007421704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050399103,0.00021215987,0.000049552957,0.00009271486,0.00032538807,0.000017812887,0.004435879,0.7531556,0.0070151137,0.0027170542,0.007484448,0.22399029],"study_design_scores_gemma":[0.0028912078,0.0001253326,0.0014309377,0.00005926125,0.00006990006,0.0000130842345,0.00023755388,0.98334914,0.008186904,0.0012059228,0.0018469428,0.00058379513],"about_ca_topic_score_codex":0.00025255122,"about_ca_topic_score_gemma":0.00008120663,"teacher_disagreement_score":0.79008186,"about_ca_system_score_codex":0.00046690655,"about_ca_system_score_gemma":0.00014503748,"threshold_uncertainty_score":0.9997691},"labels":[],"label_agreement":null},{"id":"W4390450865","doi":"10.18280/ts.400628","title":"Hybrid Feature Selection Using the Firefly Algorithm for Automatic Detection of Benign/Malignant Breast Cancer in Ultrasound Images","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Firefly algorithm; Feature selection; Feature (linguistics); Artificial intelligence; Computer science; Pattern recognition (psychology); Ultrasound; Firefly protocol; Cancer; Algorithm; Medicine; Radiology; Internal medicine; Biology","score_opus":0.01472225436567153,"score_gpt":0.2657617763148253,"score_spread":0.25103952194915374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390450865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21942656,0.00007281759,0.7786701,0.0004194268,0.00047552763,0.000645122,0.00008281287,0.00020260416,0.0000050256103],"genre_scores_gemma":[0.9903852,0.000027829006,0.009016127,0.000050202467,0.00023606342,0.0002273519,0.000004359964,0.00001955158,0.00003332338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985292,0.00009656744,0.00031376333,0.0003606417,0.00036808458,0.0003317504],"domain_scores_gemma":[0.9992615,0.00018329197,0.00020299092,0.00018397471,0.00013079355,0.000037430862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006007058,0.00016923537,0.00018290836,0.00022139559,0.00023185217,0.00009273724,0.00033568067,0.000054417276,0.000023381253],"category_scores_gemma":[0.000009994304,0.0001359557,0.00009507101,0.00089936116,0.000046802255,0.00042519852,0.000046478584,0.00014221811,0.0000020138446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024365385,0.000059395566,0.00038818025,0.00009067113,0.00006620317,0.0000033889783,0.0007588069,0.017926844,0.4012848,0.000036753994,0.0003690826,0.5789915],"study_design_scores_gemma":[0.0004707488,0.00011844496,0.017860068,0.00007975355,0.000026748734,0.00007619236,0.000075967255,0.8129008,0.16769323,0.00048136228,0.00006939757,0.00014733306],"about_ca_topic_score_codex":0.00040043055,"about_ca_topic_score_gemma":0.00014257929,"teacher_disagreement_score":0.7949739,"about_ca_system_score_codex":0.0003493475,"about_ca_system_score_gemma":0.0001080169,"threshold_uncertainty_score":0.5544113},"labels":[],"label_agreement":null},{"id":"W4390450874","doi":"10.18280/ts.400635","title":"Breast Cancer Detection Using Comprising Fuzzy C-Means and Artificial Bee Colony Optimization Segmentation and Grading with Random Forest Classifier","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Random forest; Artificial intelligence; Grading (engineering); Pattern recognition (psychology); Segmentation; Classifier (UML); Fuzzy logic; Computer science; Machine learning; Biology; Ecology","score_opus":0.026907191837248396,"score_gpt":0.2557385431639067,"score_spread":0.2288313513266583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390450874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41518512,0.00001773229,0.58407575,0.00016269232,0.00016589698,0.00026277165,0.0000051079596,0.00011427545,0.00001066509],"genre_scores_gemma":[0.98786193,0.000036578287,0.011738152,0.0000555906,0.00022277719,0.000055334298,0.0000059805757,0.000017646153,0.000006032374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987783,0.00007658166,0.00023453704,0.00037870873,0.0002962149,0.00023569934],"domain_scores_gemma":[0.99952835,0.0000657226,0.00014514767,0.0000802996,0.00010887228,0.000071601215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029894125,0.00015326616,0.00014709147,0.00020818996,0.00045291442,0.00027719865,0.000084772626,0.00005309259,0.000009758117],"category_scores_gemma":[0.0000036738804,0.00014700838,0.000021465112,0.000549517,0.00006816491,0.0007340062,0.00005167506,0.00009664944,0.0000010351516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039041185,0.00003198891,0.0070492164,0.000058678146,0.00006934404,0.0000073340657,0.0014693588,0.83575284,0.053191535,0.0002082246,0.00004335667,0.10172771],"study_design_scores_gemma":[0.0013776135,0.00012117989,0.013048307,0.00006720779,0.000044702247,0.000049080034,0.00020593,0.98071104,0.0039098244,0.00026557303,0.00001571355,0.00018380738],"about_ca_topic_score_codex":0.00017787685,"about_ca_topic_score_gemma":0.0004561468,"teacher_disagreement_score":0.5726768,"about_ca_system_score_codex":0.00020264514,"about_ca_system_score_gemma":0.000043343345,"threshold_uncertainty_score":0.5994828},"labels":[],"label_agreement":null},{"id":"W4390580666","doi":"10.1177/12034754231220934","title":"Evaluation of Vision LLMs GTP-4V and LLaVA for the Recognition of Features Characteristic of Melanoma","year":2024,"lang":"en","type":"letter","venue":"Journal of Cutaneous Medicine and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dermatrials Research; Western University; McMaster University; University of Toronto","funders":"","keywords":"Medicine; Melanoma; Dermatology; Artificial intelligence; Cancer research","score_opus":0.05103814608982515,"score_gpt":0.3041818787602356,"score_spread":0.25314373267041046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390580666","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30123425,0.074121565,0.022433558,0.58546495,0.01474578,0.0015303105,0.000102604536,0.00003385604,0.00033310795],"genre_scores_gemma":[0.953588,0.0144913215,0.0010900891,0.023210863,0.00732519,0.000019659981,0.00003711955,0.00006199833,0.00017575674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974156,0.00021734029,0.0009302629,0.000181783,0.0011351254,0.0001198938],"domain_scores_gemma":[0.99372405,0.0032645953,0.0015923338,0.00020601597,0.0011789639,0.000034021337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003339446,0.00016161562,0.00071443117,0.0004607758,0.00003864915,0.000024894467,0.0001746547,0.00019266279,0.000016325412],"category_scores_gemma":[0.0008401932,0.000096252574,0.00015975331,0.00019065267,0.00016269289,0.00014229972,0.00003715283,0.00048442712,1.8043833e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001406774,0.000019719391,0.000065288295,0.0014989495,0.0003562325,0.00014656891,0.0008985566,0.000008578909,0.0027965072,0.0000050626713,0.47585893,0.5182049],"study_design_scores_gemma":[0.007402734,0.023728622,0.023857668,0.08642485,0.030187655,0.12306332,0.002018061,0.083157785,0.028738517,0.096931994,0.49147817,0.0030106215],"about_ca_topic_score_codex":0.000026636824,"about_ca_topic_score_gemma":0.0000041935286,"teacher_disagreement_score":0.65235376,"about_ca_system_score_codex":0.000050441227,"about_ca_system_score_gemma":0.00025655836,"threshold_uncertainty_score":0.3925066},"labels":[],"label_agreement":null},{"id":"W4390837850","doi":"10.1038/s41598-024-51723-2","title":"AI improves accuracy, agreement and efficiency of pathologists for Ki67 assessments in breast cancer","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; St. Michael's Hospital; Princess Margaret Cancer Centre; University Health Network; Toronto Metropolitan University; University of Toronto","funders":"Mitacs","keywords":"Medicine; Breast cancer; Kappa; Concordance; Turnaround time; Reproducibility; Consistency (knowledge bases); Diagnostic accuracy; Cohen's kappa; Cancer; Medical physics; Internal medicine; Artificial intelligence; Machine learning; Computer science; Statistics","score_opus":0.01751447108590855,"score_gpt":0.3350775172729329,"score_spread":0.31756304618702436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390837850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7034987,0.0019352966,0.26286912,0.002498618,0.02740551,0.0012634036,0.000025409798,0.0001850867,0.00031883232],"genre_scores_gemma":[0.99608135,0.000025046547,0.0032718957,0.00004730595,0.000042563162,0.00014305375,0.0000027616686,0.000007102148,0.00037892742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789625,0.000028790753,0.00046424588,0.00092748215,0.00041064245,0.0002725802],"domain_scores_gemma":[0.99893236,0.00006915558,0.00019212758,0.00060669275,0.00014361819,0.00005605042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016199677,0.00011795933,0.00015587873,0.00026691984,0.0001075019,0.00046065968,0.0002569553,0.000050860253,0.000011744059],"category_scores_gemma":[0.00004417971,0.000100702244,0.000054568,0.00078404427,0.00017118242,0.0006283174,0.00021817167,0.000095482064,0.0000014006945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023694045,0.00025750045,0.019173123,0.0008803832,0.00004088195,0.00045665452,0.0021936442,0.00051824807,0.24125876,0.0019965589,0.013176679,0.7200239],"study_design_scores_gemma":[0.0011690853,0.00057021953,0.14607127,0.0017718583,0.00008978661,0.002075306,0.00030137488,0.47861233,0.20709571,0.11185473,0.04885471,0.0015336142],"about_ca_topic_score_codex":0.0001415747,"about_ca_topic_score_gemma":0.000066046385,"teacher_disagreement_score":0.71849024,"about_ca_system_score_codex":0.0001595428,"about_ca_system_score_gemma":0.00037470166,"threshold_uncertainty_score":0.44421518},"labels":[],"label_agreement":null},{"id":"W4390840452","doi":"10.1007/s00784-023-05475-4","title":"Artificial intelligence for classification and detection of oral mucosa lesions on photographs: a systematic review and meta-analysis","year":2024,"lang":"en","type":"review","venue":"Clinical Oral Investigations","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Oral mucosa; Odds ratio; Diagnostic odds ratio; Confidence interval; Meta-analysis; Lesion; MEDLINE; Artificial intelligence; Diagnostic accuracy; Referral; Medical physics; Radiology; Pathology; Internal medicine; Computer science; Family medicine","score_opus":0.5944383168794447,"score_gpt":0.503488280078723,"score_spread":0.09095003680072167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390840452","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.075763e-7,0.8019461,0.1942067,0.000579521,0.00020183987,0.0028646868,0.00009746975,0.00009513774,0.000007756566],"genre_scores_gemma":[0.00037223555,0.98303485,0.013920337,0.00033954345,0.000033802364,0.002179418,0.00003819994,0.000028017908,0.00005358639],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99465424,0.00093625375,0.0029133835,0.0010191799,0.00028738112,0.0001895583],"domain_scores_gemma":[0.99514484,0.0020077585,0.0013812571,0.0010023554,0.00025282564,0.00021093374],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002722897,0.00041311752,0.004310033,0.00065872766,0.00018273808,0.00018498838,0.0004976029,0.0003532699,0.0000059998333],"category_scores_gemma":[0.0019610985,0.00028899306,0.002250463,0.0030608512,0.00045214756,0.00023015634,0.00015516413,0.00052141515,0.000018384559],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029301082,0.00014619416,7.269239e-7,0.69356614,0.047983807,0.0000012489061,0.00007156357,0.0000060240586,0.000002229098,0.037502512,0.00022588897,0.22049071],"study_design_scores_gemma":[0.000021272059,0.00036243416,0.0000018503015,0.018649306,0.93473166,0.000011642641,0.000014056395,0.013282618,0.0000128295815,0.024077376,0.008405702,0.00042926424],"about_ca_topic_score_codex":0.000023193114,"about_ca_topic_score_gemma":0.00011444571,"teacher_disagreement_score":0.88674784,"about_ca_system_score_codex":0.00006478768,"about_ca_system_score_gemma":0.00020041599,"threshold_uncertainty_score":0.99995625},"labels":[],"label_agreement":null},{"id":"W4390856231","doi":"10.5281/zenodo.7989955","title":"Fingerprinting and Building Large Reproducible Datasets - Artefact","year":2023,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Data mining","score_opus":0.0676906354289249,"score_gpt":0.29184822654930376,"score_spread":0.22415759112037886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390856231","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020470932,0.00040488897,0.9493743,0.0043566735,0.0019635078,0.0013735512,0.0013571043,0.008651914,0.0120470915],"genre_scores_gemma":[0.9506423,0.0009943239,0.034760773,0.00039994947,0.0013683217,6.042776e-7,0.005547055,0.0050100805,0.0012765903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967842,0.0003258944,0.0003468101,0.0015491439,0.00047790073,0.00051602843],"domain_scores_gemma":[0.99728364,0.00004843414,0.00025550448,0.001959973,0.00028937188,0.00016308718],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022861485,0.0002316506,0.0002249661,0.00041575788,0.0021876192,0.0026461154,0.0024363832,0.00014142517,0.00048555149],"category_scores_gemma":[0.0011895051,0.0002739309,0.00005514665,0.00064754783,0.00008076576,0.0004947706,0.018363543,0.0008189277,0.0020997152],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038349,0.00016655063,0.000027414624,0.0009186559,0.00020004257,0.00010929902,0.0040454986,0.0017506741,0.007319683,0.0177812,0.45319065,0.514452],"study_design_scores_gemma":[0.00025738325,0.000085077554,0.0008510973,0.00019585385,0.000014851923,0.000112432055,0.00007077552,0.02146084,0.0016966596,0.003549717,0.97131115,0.00039418272],"about_ca_topic_score_codex":0.00004601742,"about_ca_topic_score_gemma":7.146086e-7,"teacher_disagreement_score":0.9301714,"about_ca_system_score_codex":0.00022790492,"about_ca_system_score_gemma":0.000010139021,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W4390862500","doi":"10.57750/qmaz-gr91","title":"Peerannot: classification for crowdsourced image datasets with Python","year":2024,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Agence Nationale de la Recherche; Institute for Catastrophic Loss Reduction","keywords":"Python (programming language); Computer science; Crowdsourcing; Artificial intelligence; Information retrieval; Pattern recognition (psychology); World Wide Web; Programming language","score_opus":0.018335137435034787,"score_gpt":0.25266352131121206,"score_spread":0.23432838387617727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390862500","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004477874,0.000609265,0.95930225,0.022317888,0.0006521908,0.0010903993,0.0004528901,0.0009691722,0.010128045],"genre_scores_gemma":[0.37344214,0.0002052648,0.6161698,0.00020772495,0.00012720416,0.0009285174,0.0025213899,0.00015637133,0.0062416047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99489546,0.0018342643,0.00056665303,0.0016206305,0.00063050806,0.00045246808],"domain_scores_gemma":[0.99201006,0.0010623287,0.0005579102,0.0041533774,0.002029557,0.00018677159],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004548015,0.00045483635,0.00038793532,0.00033147624,0.00040969616,0.0016588296,0.0026935008,0.00033046055,0.00002542709],"category_scores_gemma":[0.0005804006,0.0004505748,0.00020836973,0.00067129877,0.00022795075,0.00037958313,0.0024066728,0.00089005945,0.00008469726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013949447,0.0009461864,0.00019834773,0.0027346418,0.00052057276,0.000031814765,0.022413779,0.0006156895,0.033364687,0.4700419,0.06041976,0.40857312],"study_design_scores_gemma":[0.0013659158,0.000004228576,0.0014890177,0.00402167,0.00020612226,0.00006645254,0.00013365872,0.66441774,0.14039682,0.04923028,0.13707232,0.001595769],"about_ca_topic_score_codex":0.0003656627,"about_ca_topic_score_gemma":0.0006726979,"teacher_disagreement_score":0.663802,"about_ca_system_score_codex":0.00033815013,"about_ca_system_score_gemma":0.00055330014,"threshold_uncertainty_score":0.9997946},"labels":[],"label_agreement":null},{"id":"W4390873608","doi":"10.1109/iccv51070.2023.01926","title":"CO-PILOT: Dynamic Top-Down Point Cloud with Conditional Neighborhood Aggregation for Multi-Gigapixel Histopathology Image Representation","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Point cloud; Cloud computing; Context (archaeology); Data mining; Artificial intelligence; Machine learning; Pattern recognition (psychology)","score_opus":0.031071687449159648,"score_gpt":0.3208668156601458,"score_spread":0.28979512821098613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012942605,0.000013978011,0.9818507,0.002274922,0.0007558654,0.00063304795,0.00003372665,0.00070835464,0.0007868376],"genre_scores_gemma":[0.85747075,0.000015821952,0.13901907,0.0005071599,0.00017032388,0.00043135067,0.00025753636,0.000031806692,0.0020961845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984164,0.000082203434,0.00028711258,0.0006212835,0.00028765324,0.0003053387],"domain_scores_gemma":[0.9988768,0.00017529566,0.00018835672,0.0004692811,0.00021981336,0.000070470676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032671142,0.00016350683,0.00016724617,0.00023526567,0.00023335827,0.000100170524,0.00034104355,0.00006785993,0.00004202705],"category_scores_gemma":[0.000082406084,0.00015175145,0.00006182989,0.0005638456,0.00010639982,0.00079425226,0.000060249662,0.00011766013,0.00018057194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012756332,0.001078375,0.008748226,0.00037804287,0.000220402,0.00029452398,0.0063844626,0.00997763,0.33475152,0.41969487,0.05298137,0.16421495],"study_design_scores_gemma":[0.0029083495,0.0010048299,0.034199685,0.000023552959,0.000020914207,0.00015984909,0.00018658703,0.9043316,0.01959042,0.036305204,0.0008607426,0.00040824746],"about_ca_topic_score_codex":0.000043446256,"about_ca_topic_score_gemma":0.00009202841,"teacher_disagreement_score":0.894354,"about_ca_system_score_codex":0.00029198604,"about_ca_system_score_gemma":0.00010886029,"threshold_uncertainty_score":0.6188244},"labels":[],"label_agreement":null},{"id":"W4390913508","doi":"10.1038/s41598-024-51244-y","title":"Prediction of sentinel lymph node metastasis in breast cancer patients based on preoperative features: a deep machine learning approach","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Sentinel lymph node; Breast cancer; Logistic regression; Biopsy; Radiology; Cancer; Metastasis; Lymph node; Oncology; Internal medicine","score_opus":0.013110479118021445,"score_gpt":0.23739604104970813,"score_spread":0.2242855619316867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390913508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6079646,0.0014005159,0.35738143,0.0009219829,0.02481852,0.0015644492,0.00013189444,0.00096051913,0.004856095],"genre_scores_gemma":[0.9967889,0.0000064962364,0.0024981045,0.000034240747,0.0000488552,0.00011635056,0.00006193651,0.0000182735,0.00042681975],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698,0.00016398568,0.0005084852,0.001160105,0.0009020825,0.00028530718],"domain_scores_gemma":[0.9987833,0.000044871507,0.00023495985,0.0006328027,0.00022919085,0.000074874304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012021648,0.00019274275,0.00021429594,0.0005986399,0.00019519177,0.00041801087,0.00025496894,0.000074252916,0.000029782057],"category_scores_gemma":[0.00006138013,0.00016390037,0.00010584192,0.0019418575,0.00010364042,0.0005908889,0.0001187084,0.0002614334,0.0000037479476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007354622,0.0008222442,0.49438098,0.0005606181,0.00011301656,0.00016061806,0.004103004,0.45372942,0.0036928393,0.00015804263,0.0019677286,0.04023794],"study_design_scores_gemma":[0.00023698031,0.000021813987,0.10461987,0.0002318373,0.000021977705,0.000057460275,0.000025743819,0.8905271,0.0036033927,0.00016918321,0.00033413357,0.0001505009],"about_ca_topic_score_codex":0.00025268868,"about_ca_topic_score_gemma":0.00001555037,"teacher_disagreement_score":0.43679768,"about_ca_system_score_codex":0.0003645119,"about_ca_system_score_gemma":0.00028556737,"threshold_uncertainty_score":0.6683663},"labels":[],"label_agreement":null},{"id":"W4390992147","doi":"10.1109/bibm58861.2023.10385410","title":"A Closer Look at Weak Supervision’s Limitations in WSI Recurrence Score Prediction","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Alberta","funders":"","keywords":"Computer science; Notice; Cluster analysis; Artificial intelligence; Graphical user interface; Machine learning; F1 score; Calculator; Pattern recognition (psychology)","score_opus":0.08246528623866789,"score_gpt":0.2705518893429427,"score_spread":0.18808660310427483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390992147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63651204,0.000316322,0.2662044,0.0133781405,0.006876447,0.0012578464,0.000024243185,0.0037508882,0.07167969],"genre_scores_gemma":[0.985019,0.00029687563,0.0059735035,0.00018560643,0.00011208503,0.0001458687,0.000013678214,0.000013281704,0.00824009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871755,0.000058975824,0.00022980926,0.00043545547,0.00030846594,0.00024975807],"domain_scores_gemma":[0.9992058,0.00016091048,0.000038826478,0.00045750372,0.00007310357,0.00006385179],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030439434,0.00009934969,0.00008921778,0.00029376312,0.00013279577,0.00007118854,0.0004168136,0.000070636655,0.000052868116],"category_scores_gemma":[0.00008902824,0.000096146,0.000039800256,0.0016665848,0.000029248284,0.00073944585,0.00031316877,0.00013767098,0.00087084546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005566481,0.00021986166,0.1405094,0.00010967638,0.000040443356,0.000038004633,0.007990729,0.009840363,0.0074075935,0.04621692,0.1861592,0.6014121],"study_design_scores_gemma":[0.0006369308,0.0002563536,0.37392905,0.00012349454,0.000005608213,0.000023924093,0.00024937262,0.57302284,0.0031639398,0.013699088,0.034558296,0.00033111376],"about_ca_topic_score_codex":0.000078876,"about_ca_topic_score_gemma":0.001208591,"teacher_disagreement_score":0.601081,"about_ca_system_score_codex":0.00027759775,"about_ca_system_score_gemma":0.0000780864,"threshold_uncertainty_score":0.9999071},"labels":[],"label_agreement":null},{"id":"W4391065733","doi":"10.1016/j.jpi.2023.100357","title":"Computational pathology: A survey review and the way forward","year":2024,"lang":"en","type":"review","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Research in Immunology and Cancer; University of New Brunswick; Université de Montréal; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science; Digital pathology; Information retrieval; Artificial intelligence","score_opus":0.04509413943455525,"score_gpt":0.3440009770589279,"score_spread":0.29890683762437265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391065733","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.242865e-7,0.87108517,0.12652558,0.0004986749,0.0013068337,0.00039000425,0.000027556547,0.000022842301,0.00014242208],"genre_scores_gemma":[0.000002701212,0.98042464,0.018154506,0.0012193007,0.00011446653,0.000021061202,0.000009319616,0.000015854692,0.000038151466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99606675,0.00094283646,0.0022573033,0.00013552877,0.00036823077,0.00022934686],"domain_scores_gemma":[0.9955129,0.0011026228,0.0024865398,0.00043437365,0.0003828637,0.00008067532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006875117,0.00032842235,0.0020432526,0.00034070844,0.00010430943,0.00014507794,0.0011689533,0.0002906191,0.000004987544],"category_scores_gemma":[0.0005360638,0.00017248478,0.00048080581,0.000593726,0.00032414412,0.00046304645,0.00048271316,0.0013401861,0.00007642294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048849515,0.000011367756,0.0000014149248,0.030769335,0.00025953335,0.00024477363,0.0008796476,0.000025422156,2.3663025e-9,0.0032518203,0.016889421,0.94766235],"study_design_scores_gemma":[0.00054347265,0.00023926314,0.00001526562,0.016669212,0.0027256112,0.06804663,0.000021477941,0.0020857283,2.7733797e-8,0.0065332083,0.9027977,0.00032237978],"about_ca_topic_score_codex":6.7922616e-7,"about_ca_topic_score_gemma":0.0000015752256,"teacher_disagreement_score":0.94734,"about_ca_system_score_codex":0.00012763019,"about_ca_system_score_gemma":0.0005193656,"threshold_uncertainty_score":0.70337254},"labels":[],"label_agreement":null},{"id":"W4391066052","doi":"10.1016/j.jhepr.2024.101008","title":"Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning","year":2024,"lang":"en","type":"article","venue":"JHEP Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Assistance publique-Hôpitaux de Paris","keywords":"Artificial intelligence; Hepatocellular carcinoma; Liver cancer; Cluster analysis; Intrahepatic Cholangiocarcinoma; Computer science; Medicine; Cancer; Pathology; Biopsy; Convolutional neural network; Pattern recognition (psychology); Radiology; Internal medicine","score_opus":0.03249325826326052,"score_gpt":0.2709599125736169,"score_spread":0.23846665431035638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391066052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5505118,0.004281464,0.43895575,0.00044899233,0.0035989506,0.00020896878,0.0000024257752,0.00082169316,0.0011699738],"genre_scores_gemma":[0.98008597,0.00011987077,0.018615242,0.00009129966,0.00062597235,0.00003796868,0.00001630309,0.000032075768,0.00037527588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980234,0.0000784504,0.00043070773,0.0007902804,0.00041216594,0.00026500772],"domain_scores_gemma":[0.9990322,0.000065502594,0.00020802807,0.000508496,0.00010042091,0.000085377666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036280756,0.00017645047,0.00018222652,0.0001456972,0.0001878455,0.00037233692,0.0002393118,0.00010696122,0.00011263833],"category_scores_gemma":[0.000036083522,0.0001751386,0.00009231422,0.0005822897,0.000035695906,0.0008526077,0.0001731846,0.0003209698,0.00003390927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000197082,0.000065686254,0.032768074,0.0001779334,0.00013974505,0.0028669867,0.0031280934,0.0051034023,0.46116674,0.00045079045,0.0007984514,0.4933144],"study_design_scores_gemma":[0.00007786748,0.000027152983,0.09466978,0.00017591465,0.000044195887,0.0005458408,0.00004271469,0.88767874,0.0074750506,0.0005695777,0.008375536,0.00031759863],"about_ca_topic_score_codex":0.0016770388,"about_ca_topic_score_gemma":0.000049500348,"teacher_disagreement_score":0.8825754,"about_ca_system_score_codex":0.00069276296,"about_ca_system_score_gemma":0.00026970461,"threshold_uncertainty_score":0.7141945},"labels":[],"label_agreement":null},{"id":"W4391069663","doi":"10.1067/j.cpradiol.2024.01.007","title":"Deep learning for computer-aided abnormalities classification in digital mammogram: A data-centric perspective","year":2024,"lang":"en","type":"article","venue":"Current Problems in Diagnostic Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Medicine; Mammography; Breast cancer; Usability; Machine learning; Artificial intelligence; Deep learning; Medical physics; Digital mammography; Cancer; Computer science; Human–computer interaction; Internal medicine","score_opus":0.052238620786753405,"score_gpt":0.31793899573627643,"score_spread":0.26570037494952303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391069663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0085708285,0.016242692,0.96945006,0.0006486398,0.0036507791,0.001017484,0.000016136904,0.00029140306,0.000111954505],"genre_scores_gemma":[0.99247885,0.0019858757,0.0043046647,0.00002124522,0.0004053453,0.0006085295,0.00015745508,0.000023112074,0.000014903609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975499,0.00015473965,0.000576779,0.001034396,0.00016064406,0.0005235606],"domain_scores_gemma":[0.99511725,0.0040465975,0.00012717077,0.00055004033,0.000094974166,0.000063977175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070942333,0.00022006831,0.00030235614,0.0005856921,0.000073551084,0.00035296788,0.0010421402,0.00012188878,0.00000421322],"category_scores_gemma":[0.0016791027,0.00022329674,0.00005958543,0.0009430895,0.00013147583,0.0013070633,0.00037380244,0.00052357436,0.00002645255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017057395,0.00027333043,0.03669354,0.00052211416,0.000049726,0.00004057191,0.0052548875,0.05387996,0.00001050566,0.10813629,0.001430398,0.79369164],"study_design_scores_gemma":[0.0005677182,0.00025288074,0.010894683,0.00033289642,0.000010573511,0.000094131276,0.00018324712,0.94757897,0.000004190087,0.024481263,0.015325928,0.0002735404],"about_ca_topic_score_codex":0.000054531753,"about_ca_topic_score_gemma":0.00008753274,"teacher_disagreement_score":0.98390806,"about_ca_system_score_codex":0.00069225836,"about_ca_system_score_gemma":0.00015341351,"threshold_uncertainty_score":0.91057765},"labels":[],"label_agreement":null},{"id":"W4391109864","doi":"10.1038/s41467-024-44824-z","title":"Segment anything in medical images","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":2390,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Vector Institute; University of Toronto; University Health Network","funders":"Alliance de recherche numérique du Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Computational biology; Medicine; Biology","score_opus":0.016690693557086668,"score_gpt":0.3341284663747068,"score_spread":0.3174377728176201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391109864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019853034,0.13144821,0.488455,0.32467064,0.0040652137,0.0004969372,0.000009094242,0.0019183299,0.046951257],"genre_scores_gemma":[0.9540514,0.0011225963,0.043788012,0.0008420001,0.00005368014,0.000041204137,0.0000035924802,0.0000065986537,0.000090965565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999149,0.00010521004,0.00014846332,0.00019087958,0.00028738176,0.00011901623],"domain_scores_gemma":[0.9981742,0.00031969754,0.000018051353,0.0014062728,0.000034557823,0.00004723512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050966145,0.00006268043,0.00006299455,0.00015456486,0.00010098177,0.00014701714,0.002126918,0.00017542571,0.000018439208],"category_scores_gemma":[0.00011443219,0.00005914675,0.00003188698,0.00073930406,0.000053421685,0.00037487017,0.00078733306,0.0013158283,0.000047587197],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017151727,0.000112250666,0.0007278841,0.00003968684,0.000029748433,0.000043800876,0.0021869515,0.00005078951,0.0008319743,0.43257138,0.03209383,0.53130996],"study_design_scores_gemma":[0.0002288565,0.00003543564,0.007346606,0.00043114813,0.000008186103,0.000119074815,0.00008313021,0.38989118,0.0019742572,0.0137199415,0.5858519,0.00031032076],"about_ca_topic_score_codex":0.000031428186,"about_ca_topic_score_gemma":0.00033227913,"teacher_disagreement_score":0.95206606,"about_ca_system_score_codex":0.00016977455,"about_ca_system_score_gemma":0.00015311758,"threshold_uncertainty_score":0.5716693},"labels":[],"label_agreement":null},{"id":"W4391136734","doi":"10.1038/s41598-024-52588-1","title":"Multi-channel feature extraction for virtual histological staining of photon absorption remote sensing images","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Illumisonics (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; Canadian Institutes of Health Research; University of Waterloo; Mitacs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; illumiSonics; Canada Foundation for Innovation; Centre for Bioengineering and Biotechnology, University of Waterloo; Alberta Precision Laboratories","keywords":"Digital pathology; Computer science; Staining; Artificial intelligence; H&E stain; Gold standard (test); Eosin; Feature (linguistics); Histology; Telepathology; Pattern recognition (psychology); Pathology; Biomedical engineering; Medicine; Radiology","score_opus":0.03114922442575336,"score_gpt":0.2996746390540886,"score_spread":0.26852541462833524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391136734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021502271,0.00050972466,0.9549103,0.00027104677,0.022053167,0.0003216884,0.000002266817,0.00033661682,0.00009291394],"genre_scores_gemma":[0.86653835,0.0000060502757,0.13059041,0.000013975031,0.00010484266,0.0000036227605,0.000012051166,0.000014408486,0.002716295],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979073,0.000047303733,0.0003899129,0.00096397626,0.00043147447,0.00026007553],"domain_scores_gemma":[0.9986891,0.000103230566,0.0002941992,0.0006017297,0.00026042387,0.00005130652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017410696,0.00013799858,0.00016905603,0.00029020626,0.00027081146,0.0004350513,0.00015312429,0.00012709497,0.0000048594434],"category_scores_gemma":[0.00021444816,0.00012629812,0.00013666533,0.0006081661,0.00014372487,0.00069666153,0.000087366534,0.0001911776,0.0000045664497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022971757,0.000029901215,0.0000037504756,0.00013184069,0.00002471635,0.0003477788,0.001280855,0.0019075214,0.6594789,0.000108029395,0.010170337,0.32649338],"study_design_scores_gemma":[0.00010105856,0.00010546713,0.000102421836,0.0001600479,0.000018786424,0.000862685,0.00011469504,0.7450032,0.22109808,0.009561468,0.02268013,0.0001919132],"about_ca_topic_score_codex":0.000036184883,"about_ca_topic_score_gemma":0.000008982566,"teacher_disagreement_score":0.8450361,"about_ca_system_score_codex":0.00024878068,"about_ca_system_score_gemma":0.00016154081,"threshold_uncertainty_score":0.5150288},"labels":[],"label_agreement":null},{"id":"W4391140823","doi":"10.1038/s41598-024-52613-3","title":"Comparison between a deep-learning and a pixel-based approach for the automated quantification of HIV target cells in foreskin tissue","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Natural Sciences and Engineering Research Council of Canada; National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; University of Toronto; International AIDS Vaccine Initiative","keywords":"Foreskin; Pixel; Artificial intelligence; Human immunodeficiency virus (HIV); Computer science; Computational biology; Deep learning; Machine learning; Pattern recognition (psychology); Computer vision; Virology; Biology; Genetics; Cell culture","score_opus":0.028004320440224603,"score_gpt":0.31142447718038246,"score_spread":0.28342015674015786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391140823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020225506,0.0007190228,0.9759407,0.00016551047,0.0018622681,0.00068597595,0.0000023971065,0.00031745216,0.000081144004],"genre_scores_gemma":[0.9412182,0.0000014159288,0.05837828,0.0000029140544,0.000034228946,0.00010152128,0.000032593547,0.000011694276,0.00021915798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800056,0.00008827593,0.0005541926,0.0007649431,0.00036534618,0.00022666129],"domain_scores_gemma":[0.99872833,0.00029321204,0.00027364137,0.00055355154,0.00010673802,0.0000445289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028196012,0.0001144701,0.00019918868,0.00029273916,0.00023043451,0.0005201895,0.000270056,0.00006803578,0.00000335225],"category_scores_gemma":[0.000088218694,0.0000903214,0.000049419297,0.0011540749,0.0001744265,0.00024985522,0.00008045934,0.00015039682,0.0000023091409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045348337,0.00034181497,0.065138236,0.00209744,0.00013402395,0.000060749797,0.010868006,0.3793205,0.28205806,0.0022431547,0.018726725,0.23896593],"study_design_scores_gemma":[0.00006712237,0.00003373675,0.0013696024,0.000042387303,0.000012171518,0.000008635382,0.00006008583,0.88085127,0.0958221,0.00095927104,0.020681674,0.00009196564],"about_ca_topic_score_codex":0.000024286586,"about_ca_topic_score_gemma":0.00001076365,"teacher_disagreement_score":0.9209927,"about_ca_system_score_codex":0.00007176221,"about_ca_system_score_gemma":0.00013314502,"threshold_uncertainty_score":0.50161994},"labels":[],"label_agreement":null},{"id":"W4391142191","doi":"10.2174/0115734056281578231212104108","title":"Automated Diagnosis of Bone Metastasis by Classifying Bone Scintigrams Usinga Self-defined Deep Learning Model","year":2024,"lang":"en","type":"article","venue":"Current Medical Imaging Formerly Current Medical Imaging Reviews","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Fundamental Research Funds for the Central Universities; Gansu Education Department; Natural Science Foundation of Gansu Province; National Natural Science Foundation of China","keywords":"Bone metastasis; Artificial intelligence; Bone scintigraphy; Computer science; Deep learning; Feature (linguistics); Metastasis; Convolutional neural network; Feature extraction; Radiology; Lung cancer; Pattern recognition (psychology); Artificial neural network; Medicine; Cancer; Pathology; Internal medicine","score_opus":0.03420030895518114,"score_gpt":0.3473024023136423,"score_spread":0.3131020933584612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391142191","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006485079,0.3992785,0.58513194,0.0050650123,0.006524947,0.000645464,0.00001219281,0.0025958654,0.000097561744],"genre_scores_gemma":[0.36146387,0.5592243,0.07072067,0.0022075446,0.0027518205,0.0024406714,0.00049529364,0.0006035181,0.00009229903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98724127,0.0008647536,0.0033224386,0.0020512042,0.0047859107,0.0017344354],"domain_scores_gemma":[0.9948257,0.00091880054,0.0010002219,0.001141702,0.0003667224,0.0017468419],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0072002723,0.0010527916,0.0019498512,0.00089176145,0.00050454715,0.00070896564,0.0021183195,0.00021607778,0.0003410008],"category_scores_gemma":[0.0049016755,0.0008817107,0.0009668982,0.0029363427,0.00080452394,0.0023461361,0.0011559741,0.0035472144,0.00022694167],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004855097,0.00044333973,0.0011342876,0.0029567087,0.00006914498,0.00005848989,0.0006146307,0.000028850889,0.000092096154,0.00045948644,0.06165745,0.93248063],"study_design_scores_gemma":[0.0005586282,0.00003024763,0.000022260036,0.008308867,0.00022427244,0.00018173813,0.000019551157,0.65468645,0.00013837981,0.00034158313,0.33490035,0.0005876436],"about_ca_topic_score_codex":0.00004952795,"about_ca_topic_score_gemma":0.000006675153,"teacher_disagreement_score":0.931893,"about_ca_system_score_codex":0.0007162058,"about_ca_system_score_gemma":0.0011666581,"threshold_uncertainty_score":0.99936336},"labels":[],"label_agreement":null},{"id":"W4391171924","doi":"10.1101/2024.01.22.24301559","title":"Machine Learning-Based Prediction of Pediatric Ulcerative Colitis Treatment Response using Diagnostic Histopathology","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Histopathology; Ulcerative colitis; Artificial intelligence; Medicine; Classifier (UML); Random forest; Diagnostic accuracy; Biopsy; Histogram; Pattern recognition (psychology); Machine learning; Internal medicine; Gastroenterology; Pathology; Computer science; Image (mathematics)","score_opus":0.03149509750832391,"score_gpt":0.27787559429068687,"score_spread":0.24638049678236296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391171924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80446917,0.001924371,0.18831861,0.00036655233,0.0037869434,0.0005595813,0.00014148686,0.00037162748,0.000061649305],"genre_scores_gemma":[0.9943916,0.00029249582,0.0044395416,0.000022476504,0.00038789262,0.00019491054,0.000019398958,0.00003788916,0.00021376718],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691063,0.001127685,0.0004919827,0.0008692536,0.00033596953,0.00026446726],"domain_scores_gemma":[0.9975914,0.0010695672,0.00039331446,0.00070410885,0.00015709785,0.00008453612],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008187563,0.00032853667,0.00042906147,0.0005904731,0.00011396387,0.000064299486,0.00043320167,0.00027796606,0.000021856355],"category_scores_gemma":[0.00062182423,0.00032013402,0.0001863515,0.00047725142,0.00008784019,0.000065235334,0.0005584262,0.000655656,0.000021376814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023183336,0.00084009446,0.27477956,0.0015469294,0.00030242724,0.0017452476,0.010360152,0.6770896,0.0035474056,0.00085455086,0.00033880456,0.026276896],"study_design_scores_gemma":[0.0007157387,0.0018190718,0.15607198,0.00018862732,0.00034146867,0.00006106011,0.000009450558,0.83221364,0.0047696647,0.0021081727,0.0013153029,0.0003858],"about_ca_topic_score_codex":0.00030797947,"about_ca_topic_score_gemma":0.000060231258,"teacher_disagreement_score":0.18992245,"about_ca_system_score_codex":0.001475364,"about_ca_system_score_gemma":0.00087679597,"threshold_uncertainty_score":0.9999251},"labels":[],"label_agreement":null},{"id":"W4391211129","doi":"10.3390/curroncol31010043","title":"Breast Cancer: A Multi-Disciplinary Approach from Imaging to Therapy","year":2024,"lang":"en","type":"editorial","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Cancer; Medical diagnosis; Medical physics; Family medicine; Internal medicine; Pathology","score_opus":0.07669743421946158,"score_gpt":0.4153047268189296,"score_spread":0.33860729259946803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391211129","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037852336,0.017557457,0.160774,0.0014339843,0.8183523,0.00051480095,0.00061250967,0.00047397107,0.00024316674],"genre_scores_gemma":[0.00023324492,0.0030405582,0.014261908,0.000079288926,0.980603,0.0012117526,0.00020510556,0.00010100245,0.0002641362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99619234,0.00022660986,0.00048388218,0.0017885943,0.00069505296,0.00061353063],"domain_scores_gemma":[0.9978305,0.00039573672,0.00025217628,0.0009837147,0.0002988643,0.00023900146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037002686,0.00053356716,0.0006845578,0.00037551566,0.00016685798,0.0002781191,0.0021756697,0.00056900294,0.000039631945],"category_scores_gemma":[0.000024781535,0.0004934337,0.00021479948,0.000663856,0.00009819015,0.00028118715,0.0014887193,0.001869749,0.00025079664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036797457,0.00015467919,0.000026200141,0.000047719284,0.000041683877,0.000013717911,0.0008616707,0.000033080792,0.000016427182,0.000013571243,0.5884321,0.41032234],"study_design_scores_gemma":[0.0007326088,0.000121767276,0.000098210505,0.00024236587,0.000039135917,0.000018957815,0.000033448297,0.027905883,0.000013282814,0.00048124683,0.96979356,0.0005195498],"about_ca_topic_score_codex":0.00048341564,"about_ca_topic_score_gemma":0.00011918074,"teacher_disagreement_score":0.4098028,"about_ca_system_score_codex":0.0023335102,"about_ca_system_score_gemma":0.0018573198,"threshold_uncertainty_score":0.99975175},"labels":[],"label_agreement":null},{"id":"W4391249656","doi":"10.1109/nss/mic44845.2022.10399058","title":"Deep Neural Networks-based Malignant Breast Lesions Detection and Segmentation from Mammography","year":2022,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"National Science Foundation","keywords":"Mammography; Artificial intelligence; Computer science; Receiver operating characteristic; Pattern recognition (psychology); Segmentation; Convolutional neural network; Test set; Sørensen–Dice coefficient; Artificial neural network; Computer-aided diagnosis; False positive paradox; Cross-validation; Image segmentation; Breast cancer; Machine learning; Cancer; Medicine","score_opus":0.009294902309842869,"score_gpt":0.2142276773555856,"score_spread":0.20493277504574273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391249656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078491725,0.000118040865,0.9196983,0.0004577977,0.00077222916,0.00016721839,0.0000041316093,0.00023921458,0.000051358926],"genre_scores_gemma":[0.988144,0.000005211981,0.0111294165,0.0005140539,0.000069792564,0.00010642736,0.000008898724,0.000009280991,0.000012957799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890137,0.00013359038,0.00015170604,0.0003808074,0.00025466137,0.00017784385],"domain_scores_gemma":[0.9994924,0.00006892382,0.00007879317,0.00026564638,0.000026698186,0.00006755106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013489851,0.00010524935,0.000080059246,0.0001447361,0.0005155831,0.000113706046,0.00023046533,0.000027685684,0.00010116167],"category_scores_gemma":[0.0000017324272,0.00010645123,0.000049323073,0.0005960549,0.000026502003,0.0003158894,0.00018649155,0.00014635561,0.000001831907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059223057,0.00005655659,0.004946944,0.0000034456582,0.000021664944,0.000009792883,0.00018215664,0.197889,0.009425026,0.00027139712,0.00010128133,0.7870335],"study_design_scores_gemma":[0.00032330185,0.00013051905,0.017048609,0.0000016128304,0.000009270258,0.00003903158,0.000099501034,0.9792925,0.002385413,0.000448834,0.00008975695,0.00013162445],"about_ca_topic_score_codex":0.0005423596,"about_ca_topic_score_gemma":0.00033939673,"teacher_disagreement_score":0.90965223,"about_ca_system_score_codex":0.000103462946,"about_ca_system_score_gemma":0.000013184238,"threshold_uncertainty_score":0.43409553},"labels":[],"label_agreement":null},{"id":"W4391266473","doi":"10.1109/icscan58655.2023.10394703","title":"PolyDiseaseNet: A Multimodal Machine Learning Approach for Comprehensive Disease Diagnosis and Prognosis","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Disease; Medicine","score_opus":0.042190621130812504,"score_gpt":0.28095122191727606,"score_spread":0.23876060078646355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391266473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06987543,0.00087368925,0.9225742,0.0022841997,0.00025811628,0.0015337095,0.000051284656,0.002317641,0.00023168902],"genre_scores_gemma":[0.940854,0.00016454009,0.056821357,0.0002509587,0.000093420116,0.0014792986,0.00002661926,0.00002298242,0.00028678382],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987608,0.000055826626,0.00014133651,0.0005411935,0.00020040196,0.00030039955],"domain_scores_gemma":[0.9991773,0.00022493063,0.000054161126,0.00023474419,0.000072985225,0.00023591076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009832835,0.0001514906,0.0001411112,0.00014815657,0.00026644248,0.00014104918,0.0002645587,0.00003714697,0.0000066849498],"category_scores_gemma":[0.000061785984,0.00013933134,0.00007675611,0.00048469828,0.000048563656,0.00028276225,0.00027922087,0.00009137837,0.000009926539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030418247,0.0005046744,0.48148096,0.00092706736,0.0002391261,0.000037239603,0.0015003919,0.035887096,0.0008114825,0.0061524627,0.015388176,0.45676714],"study_design_scores_gemma":[0.00048034074,0.00009465925,0.038481347,0.0000098402,0.000018227196,0.0000015910273,0.00003465561,0.9563889,0.00042981343,0.00029366696,0.0035803088,0.00018664017],"about_ca_topic_score_codex":0.00008929348,"about_ca_topic_score_gemma":0.000005348804,"teacher_disagreement_score":0.9205018,"about_ca_system_score_codex":0.000037505917,"about_ca_system_score_gemma":0.000037345093,"threshold_uncertainty_score":0.5681767},"labels":[],"label_agreement":null},{"id":"W4391295742","doi":"10.1038/s41598-024-52858-y","title":"Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Toronto Metropolitan University; University of Toronto; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Breast cancer; Medicine; Neoadjuvant therapy; Mammography; Transfer of learning; Radiology; Cancer; Computer science; Artificial intelligence; Internal medicine","score_opus":0.024559030995494554,"score_gpt":0.313528389494522,"score_spread":0.28896935849902744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391295742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37892136,0.0008982218,0.61404043,0.0006549293,0.004486762,0.000840947,0.000053191947,0.000096924254,0.0000072106964],"genre_scores_gemma":[0.98900855,0.000077817014,0.009171631,0.000010001261,0.000036874648,0.00024416717,0.0000031627685,0.00001618426,0.0014316238],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980745,0.00010135089,0.00047250895,0.0006967378,0.00044319147,0.00021175526],"domain_scores_gemma":[0.9981499,0.0007349485,0.00013530329,0.00060059427,0.00032338698,0.000055872344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017596727,0.00014045055,0.00019425762,0.00037888228,0.00021449389,0.00022506899,0.00023370174,0.000045413286,0.000017632156],"category_scores_gemma":[0.00016848829,0.00009531221,0.00015481949,0.0017459961,0.00017997857,0.00041234068,0.00002545295,0.00008137337,0.0000015330069],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005511317,0.00015914238,0.0012982597,0.00011082317,0.00019909909,0.000015728272,0.010579069,0.046160348,0.8252061,0.00014882135,0.0013597792,0.11421169],"study_design_scores_gemma":[0.00045748186,0.0009239078,0.039975863,0.00026720832,0.0000820436,0.00022641137,0.00038427563,0.12168359,0.81817114,0.0004972536,0.017130734,0.00020008459],"about_ca_topic_score_codex":0.00025980582,"about_ca_topic_score_gemma":0.000020416228,"teacher_disagreement_score":0.61008716,"about_ca_system_score_codex":0.00024158975,"about_ca_system_score_gemma":0.00034555752,"threshold_uncertainty_score":0.3886719},"labels":[],"label_agreement":null},{"id":"W4391426559","doi":"10.1016/j.euo.2024.01.004","title":"External Validation of a Digital Pathology-based Multimodal Artificial Intelligence Architecture in the NRG/RTOG 9902 Phase 3 Trial","year":2024,"lang":"en","type":"article","venue":"European Urology Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"National Cancer Institute; Foundation Medicine; University of California, San Francisco; EMD Serono; Astellas Pharma; Endocyte; Advanced Accelerator Applications; NRG Oncology; Varian Medical Systems; Sanofi; Invitae; Bristol-Myers Squibb; AstraZeneca; Amgen; Pfizer","keywords":"Medicine; Hazard ratio; Confidence interval; Oncology; Internal medicine; Randomized controlled trial; Clinical trial; Proportional hazards model; Histopathology; Pathology","score_opus":0.041464742584998965,"score_gpt":0.33211571387983935,"score_spread":0.2906509712948404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391426559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2912213,0.00013490119,0.70145273,0.0030659942,0.0019220554,0.00038649785,0.000010092256,0.0001270631,0.0016794016],"genre_scores_gemma":[0.9941841,0.000005265137,0.004577745,0.00061421137,0.000542003,0.000037440383,0.000008463935,0.000019801508,0.000010975729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648374,0.0017162883,0.00061799877,0.00061770144,0.00021892872,0.00034532175],"domain_scores_gemma":[0.99827826,0.00093601336,0.0001802376,0.00050872535,0.000050047445,0.00004671172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001710904,0.00019262049,0.00026319086,0.0003708314,0.00007143274,0.00010593995,0.00110685,0.00014525626,0.000034316916],"category_scores_gemma":[0.00026039695,0.00015113708,0.0001255285,0.00055925077,0.0003844156,0.00021234865,0.00018789695,0.0007100169,0.00016074904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006097445,0.000848818,0.00005869967,0.000022552103,0.000023135268,0.0020390148,0.0041443426,0.009046307,0.005580504,0.0073151183,0.00014281107,0.96468127],"study_design_scores_gemma":[0.04531971,0.06485826,0.0020982008,0.00015226843,0.00025807004,0.0047532506,0.00044382134,0.62625873,0.030423997,0.15560235,0.06795437,0.0018769783],"about_ca_topic_score_codex":0.000005558568,"about_ca_topic_score_gemma":0.000015865593,"teacher_disagreement_score":0.96280426,"about_ca_system_score_codex":0.00008726622,"about_ca_system_score_gemma":0.00023299716,"threshold_uncertainty_score":0.6163191},"labels":[],"label_agreement":null},{"id":"W4391539851","doi":"10.1016/j.ajpath.2024.01.012","title":"Model-Agnostic Binary Patch Grouping for Bone Marrow Whole Slide Image Representation","year":2024,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"William Osler Health System; McMaster University Medical Centre; University Health Network; McMaster University; University of Toronto","funders":"National Research Council Canada","keywords":"Computer science; Digital pathology; Pattern recognition (psychology); Artificial intelligence; Representation (politics); Parameterized complexity; Feature (linguistics); Domain (mathematical analysis); Pooling; Feature extraction; Data mining; Algorithm; Mathematics","score_opus":0.020400340295960863,"score_gpt":0.3052538746981257,"score_spread":0.2848535344021648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391539851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17710274,0.00042028047,0.81819606,0.0031835379,0.0008694704,0.00009132497,0.000004503227,0.000056936722,0.00007515416],"genre_scores_gemma":[0.8110571,0.000075518416,0.18823291,0.00030106158,0.00024217984,0.000015924505,0.0000012894095,0.000017255623,0.00005677049],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868083,0.0001427848,0.00043132566,0.0002991932,0.00019797054,0.00024786618],"domain_scores_gemma":[0.9987725,0.00035790558,0.00034827893,0.00026944067,0.0001736975,0.00007816068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057346997,0.00011675858,0.00028305242,0.00029360922,0.00007457814,0.0000901765,0.00036730265,0.00003807176,0.000003816169],"category_scores_gemma":[0.00014821839,0.00010946321,0.00014935515,0.0004943555,0.00015618041,0.0007112186,0.00009376612,0.00024635598,0.000012595633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016030516,0.00008696393,0.00048273275,0.000090193804,0.000088392604,0.0034654415,0.0039757476,0.025170164,0.33389533,0.0023011689,0.007886849,0.6223967],"study_design_scores_gemma":[0.0005030679,0.0028561351,0.0010211945,0.00015485054,0.00007278546,0.0063795294,0.00038923547,0.9552173,0.0051388703,0.026736148,0.0012428983,0.0002879759],"about_ca_topic_score_codex":0.000017196024,"about_ca_topic_score_gemma":0.0000036242027,"teacher_disagreement_score":0.93004715,"about_ca_system_score_codex":0.00013074338,"about_ca_system_score_gemma":0.00014047093,"threshold_uncertainty_score":0.44637802},"labels":[],"label_agreement":null},{"id":"W4391610047","doi":"10.1080/09500340.2024.2313724","title":"Breast mass regions classification from mammograms using convolutional neural networks and transfer learning.","year":2023,"lang":"en","type":"article","venue":"Journal of Modern Optics","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Government Council on Grants, Russian Federation","keywords":"Artificial intelligence; Mammography; Computer science; Convolutional neural network; Pattern recognition (psychology); Digital mammography; Segmentation; Transfer of learning; Artificial neural network; Region of interest; Deep learning; Intersection (aeronautics); Breast cancer; Sørensen–Dice coefficient; Image quality; Image segmentation; Computer vision; Image (mathematics); Cancer; Medicine; Cartography","score_opus":0.04760489988587305,"score_gpt":0.2601427027437144,"score_spread":0.21253780285784138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391610047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23512435,0.00017832307,0.7632954,0.00090045267,0.00040928554,0.000034651202,0.0000022062723,0.000043043885,0.000012272119],"genre_scores_gemma":[0.9842811,0.00019409516,0.015079623,0.00003573936,0.00036538366,9.4439497e-7,0.0000026753482,0.000012108828,0.000028286244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989687,0.000076834905,0.00029898444,0.00015749973,0.00032022086,0.00017772203],"domain_scores_gemma":[0.99932104,0.00010685306,0.00015268542,0.00013954958,0.00018245878,0.00009741157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026648326,0.000094454,0.00013940009,0.000121429715,0.00015507126,0.00013802019,0.00024774618,0.00008938123,0.000001950749],"category_scores_gemma":[0.00001136224,0.00009113109,0.00007048216,0.00029310747,0.000059128954,0.00046158323,0.000039781044,0.00039805408,0.0000013693145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003781872,0.0000181764,0.002597475,0.000004847265,0.000048541784,0.000022815517,0.00035776576,0.9430162,0.0030005293,0.0013851359,0.000079446654,0.049431257],"study_design_scores_gemma":[0.00029676006,0.00006148723,0.010599876,0.000026884847,0.000025979904,0.00039909384,0.000048509643,0.9836355,0.00002323117,0.004726215,0.00006617812,0.000090311936],"about_ca_topic_score_codex":0.000011385026,"about_ca_topic_score_gemma":0.0000045564366,"teacher_disagreement_score":0.7491568,"about_ca_system_score_codex":0.000115073286,"about_ca_system_score_gemma":0.00006191987,"threshold_uncertainty_score":0.37162182},"labels":[],"label_agreement":null},{"id":"W4391819303","doi":"10.1016/j.compbiomed.2024.108153","title":"Deep integrated fusion of local and global features for cervical cell classification","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Cervical cancer; Pattern recognition (psychology); Local binary patterns; Contextual image classification; Support vector machine; Feature extraction; Binary classification; Feature (linguistics); Image (mathematics); Medicine; Cancer; Histogram","score_opus":0.0152893903122251,"score_gpt":0.3099968735585302,"score_spread":0.2947074832463051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391819303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020329341,0.004837137,0.9709649,0.00244522,0.0011090197,0.000118642994,0.0000015869141,0.000041710762,0.00015246052],"genre_scores_gemma":[0.982615,0.00030327594,0.016741466,0.00023890483,0.00007803043,0.000007667686,0.000008903485,0.0000020402038,0.0000047334106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941075,0.00004292496,0.000146547,0.00026528118,0.000037195467,0.00009728036],"domain_scores_gemma":[0.9996253,0.00017942644,0.000029612516,0.00009939659,0.000029755694,0.000036464593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019391984,0.00007284318,0.00014002841,0.00007966332,0.00002727462,0.0000065941385,0.0001260751,0.00011423364,0.0000012653281],"category_scores_gemma":[0.000011821021,0.000051958574,0.0000119459455,0.000224837,0.00025617672,0.000048340262,0.000072904884,0.00009503352,2.5077662e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001218497,0.000022840364,0.0013556096,0.00020780964,0.0000136118415,0.0000043503173,0.0006182187,0.000026743935,0.0044988757,0.13873702,0.0013612795,0.8530318],"study_design_scores_gemma":[0.0014324945,0.0021578094,0.03775536,0.00038598254,0.000021865855,0.00009614397,0.00026598945,0.90333015,0.0016912256,0.04607184,0.006620351,0.0001707801],"about_ca_topic_score_codex":0.000040098952,"about_ca_topic_score_gemma":0.000029132261,"teacher_disagreement_score":0.96228564,"about_ca_system_score_codex":0.00004582576,"about_ca_system_score_gemma":0.000024252535,"threshold_uncertainty_score":0.2118809},"labels":[],"label_agreement":null},{"id":"W4391871139","doi":"10.1016/j.jwpe.2024.105692","title":"Evaluation of activated sludge settling characteristics from microscopy images with deep convolutional neural networks and transfer learning","year":2024,"lang":"en","type":"preprint","venue":"Journal of Water Process Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Vlaamse regering; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Convolutional neural network; Transfer of learning; Settling; Deep learning; Artificial intelligence; Computer science; Activated sludge; Microscopy; Artificial neural network; Materials science; Environmental science; Physics; Optics; Sewage treatment; Environmental engineering","score_opus":0.011444530711092325,"score_gpt":0.24432466624301247,"score_spread":0.23288013553192013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391871139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56226504,0.0009794735,0.43590558,0.00006401744,0.00065779523,0.00008774205,0.000003932124,0.000034370587,0.0000020356695],"genre_scores_gemma":[0.9942204,0.00007044889,0.00526196,0.000005983147,0.00038177436,0.000011320394,0.000010783327,0.000035044664,0.0000023365335],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982136,0.00006695538,0.000525979,0.00028946073,0.0006955426,0.0002084834],"domain_scores_gemma":[0.99866784,0.000053723244,0.00021697565,0.0001316407,0.000863076,0.00006672424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089183083,0.00024745683,0.00038124353,0.00024157732,0.000044523415,0.00022119726,0.0003143374,0.00016048741,0.000005260929],"category_scores_gemma":[0.000032656568,0.0001871974,0.00006950704,0.00012703727,0.000029368446,0.00037110123,0.0001759898,0.0013189695,2.4495455e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003917335,0.000009150287,0.00016310789,0.00035078393,0.00018354572,0.000010001455,0.0012511928,0.8994816,0.093928486,0.000002431517,0.0000011341496,0.004579423],"study_design_scores_gemma":[0.00032804007,0.0000863824,0.00066540914,0.00078513415,0.0002398807,0.000081784485,0.00002103554,0.8492525,0.1480988,0.00025153195,0.0000051757406,0.00018431083],"about_ca_topic_score_codex":0.000007702419,"about_ca_topic_score_gemma":7.1237184e-7,"teacher_disagreement_score":0.4319553,"about_ca_system_score_codex":0.0001895262,"about_ca_system_score_gemma":0.00014622121,"threshold_uncertainty_score":0.76336884},"labels":[],"label_agreement":null},{"id":"W4391881543","doi":"10.1007/s11042-024-18608-y","title":"Enhancing cervical cancer diagnosis with graph convolution network: AI-powered segmentation, feature analysis, and classification for early detection","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Computer science; Interpretability; Segmentation; Cervical cancer; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Convolution (computer science); Cervix; Cancer; Medicine; Artificial neural network","score_opus":0.016798352148598903,"score_gpt":0.2792571502656605,"score_spread":0.2624587981170616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391881543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009591114,0.0017091145,0.9854272,0.0017946219,0.00015502682,0.0010183167,0.00007181192,0.00021740036,0.000015376321],"genre_scores_gemma":[0.9421658,0.0008196349,0.0457144,0.00012139107,0.00037053478,0.0106642265,0.000083364175,0.000017259295,0.000043403812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988283,0.000031337637,0.00019683424,0.0005782774,0.00015699418,0.00020825736],"domain_scores_gemma":[0.99917674,0.0002556001,0.0000887648,0.00023859872,0.00014452876,0.00009577932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016904189,0.00014817397,0.00015611533,0.0001679269,0.0003567394,0.00044901282,0.000118405434,0.00010970249,0.0000063883203],"category_scores_gemma":[0.000008457093,0.00013248801,0.000054325144,0.0013416401,0.00007011938,0.0006160461,0.000034458884,0.00014628077,0.0000029652779],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034064527,0.000043925927,0.021942114,0.00014634745,0.0004310592,4.641233e-7,0.0008032877,0.0005447498,0.011827378,0.003979244,0.00048982335,0.95975757],"study_design_scores_gemma":[0.0006882007,0.00014837104,0.4053675,0.00009066285,0.0007865189,0.000007931691,0.00009676691,0.5569457,0.017641818,0.003141793,0.014604761,0.00048003986],"about_ca_topic_score_codex":0.0001236366,"about_ca_topic_score_gemma":0.001191761,"teacher_disagreement_score":0.9592775,"about_ca_system_score_codex":0.00010313491,"about_ca_system_score_gemma":0.000049182323,"threshold_uncertainty_score":0.54027045},"labels":[],"label_agreement":null},{"id":"W4391929741","doi":"10.1109/bibe60311.2023.00052","title":"A Novel Deep Learning Approach for Breast Cancer Detection on Screening Mammography","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Mammography; Breast cancer; Computer science; Cancer detection; Cancer; Artificial intelligence; Mammography screening; Medicine; Internal medicine","score_opus":0.028402738404342487,"score_gpt":0.26115467779000007,"score_spread":0.23275193938565758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391929741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020602592,0.000013985017,0.99478096,0.00029187888,0.00040883952,0.0002855868,0.000004328571,0.0011351563,0.0010189856],"genre_scores_gemma":[0.87352073,0.00001724367,0.12500133,0.00019110134,0.00028690492,0.0004591013,0.000003472628,0.000028458302,0.0004916453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987152,0.00002511324,0.00014628939,0.0005039114,0.0002658822,0.00034356237],"domain_scores_gemma":[0.999437,0.00008164054,0.00007796885,0.00025158603,0.00008484906,0.000066987064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032293427,0.00013696722,0.000113000046,0.0003647776,0.00034140132,0.00013227903,0.00033401576,0.00007608091,0.000009048454],"category_scores_gemma":[0.000014778384,0.00013042515,0.00011140979,0.0015420936,0.000021618853,0.00033761366,0.00009897466,0.00019076047,0.0000128434895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039514507,0.000020104417,0.00036934274,0.00002242006,0.0000289283,3.3651898e-7,0.00014958557,0.08054296,0.0049253614,0.00084350206,0.000093962684,0.912964],"study_design_scores_gemma":[0.00042215674,0.00012294271,0.012716623,0.0000143290545,0.0000068557492,0.000019402032,0.0000831402,0.9797055,0.0053160083,0.00013009763,0.001271037,0.00019186574],"about_ca_topic_score_codex":0.00020006443,"about_ca_topic_score_gemma":0.00007891637,"teacher_disagreement_score":0.9127721,"about_ca_system_score_codex":0.00008090584,"about_ca_system_score_gemma":0.000016853592,"threshold_uncertainty_score":0.5318583},"labels":[],"label_agreement":null},{"id":"W4391929788","doi":"10.1109/bibe60311.2023.00028","title":"A Two-Stage Neural Network Model for Breast Ultrasound Image Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Stage (stratigraphy); Artificial neural network; Artificial intelligence; Contextual image classification; Pattern recognition (psychology); Image (mathematics); Computer vision; Geology","score_opus":0.04657452073596536,"score_gpt":0.30000467148676474,"score_spread":0.2534301507507994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391929788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051746015,0.000006134039,0.9895378,0.0013588065,0.00050444243,0.0002841063,0.0000159245,0.0008759604,0.0022422601],"genre_scores_gemma":[0.8776913,0.0000075129765,0.115969025,0.0003574227,0.00032174002,0.00015131182,0.000012042113,0.00001913876,0.0054704593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891806,0.00002447115,0.00016737565,0.00038317204,0.00017504659,0.00033185145],"domain_scores_gemma":[0.99916476,0.00015522617,0.000067664456,0.00046525238,0.00008550976,0.000061603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029932655,0.000103777515,0.00008877889,0.00006347469,0.0001824391,0.0001922626,0.00046150954,0.00004024367,0.000013165633],"category_scores_gemma":[0.000017064893,0.00009920441,0.00006495643,0.0006432553,0.000030104928,0.00062779983,0.00008651865,0.00007830946,0.00008495825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052267413,0.000039548668,0.00047078353,0.000047632497,0.000028449658,0.00000339564,0.0006159637,0.64405316,0.028257137,0.17823328,0.057930253,0.09026815],"study_design_scores_gemma":[0.00023065423,0.000020867754,0.002288699,0.0000030871388,0.000003093305,0.0000136089675,0.000025387535,0.9887574,0.00024826528,0.00793644,0.00035078428,0.00012174261],"about_ca_topic_score_codex":0.000023142971,"about_ca_topic_score_gemma":0.000057600595,"teacher_disagreement_score":0.8735687,"about_ca_system_score_codex":0.00007956059,"about_ca_system_score_gemma":0.00004911689,"threshold_uncertainty_score":0.40454382},"labels":[],"label_agreement":null},{"id":"W4391951835","doi":"10.1016/j.media.2024.103109","title":"LESS: Label-efficient multi-scale learning for cytological whole slide image screening","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Compute Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Task (project management); Supervised learning; Artificial neural network","score_opus":0.03090864510067017,"score_gpt":0.3249026520584386,"score_spread":0.29399400695776845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391951835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00827045,0.0005772002,0.98585254,0.0039559505,0.00027572337,0.0001550819,0.000006054459,0.00064478995,0.00026218186],"genre_scores_gemma":[0.42845616,0.000043482178,0.5689256,0.000459683,0.00036249592,0.00014023492,0.000031153293,0.00003306092,0.0015481266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996963,0.0001952975,0.0004576965,0.0009275891,0.00092362124,0.0005327877],"domain_scores_gemma":[0.99845886,0.0005266431,0.00008673879,0.0004619518,0.00016182775,0.00030399565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014842548,0.00022165506,0.00043943003,0.00045877352,0.00030620684,0.0005411681,0.0008778444,0.00017914148,0.00021106323],"category_scores_gemma":[0.0007392883,0.00018336841,0.00044996402,0.0025204944,0.00020770263,0.00038591455,0.0004091261,0.00060594425,0.000115761555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030846946,0.00037320456,0.0015153119,0.00018018384,0.0014475668,0.00068838696,0.0014093975,0.010594615,0.016744385,0.00039438473,0.0044477377,0.962174],"study_design_scores_gemma":[0.00034889005,0.00007866487,0.00058841245,0.000052072588,0.00035642553,0.00001595169,0.00020682743,0.9892053,0.001961864,0.000067945926,0.006893431,0.00022422103],"about_ca_topic_score_codex":0.00009439413,"about_ca_topic_score_gemma":0.00008293421,"teacher_disagreement_score":0.9786107,"about_ca_system_score_codex":0.00012032126,"about_ca_system_score_gemma":0.00009703815,"threshold_uncertainty_score":0.7477547},"labels":[],"label_agreement":null},{"id":"W4392091091","doi":"10.6019/s-biad1045","title":"HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2024,"lang":"en","type":"dataset","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Histology; Pipeline (software); Artificial intelligence; Computer science; Placenta; Biology; Pathology; Medicine; Pregnancy; Fetus","score_opus":0.014272443439699075,"score_gpt":0.2921865803064923,"score_spread":0.2779141368667932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392091091","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035800565,0.0009501236,0.6210274,0.0012806408,0.0035535991,0.000617546,0.3720204,0.0004194926,0.0001272186],"genre_scores_gemma":[0.00024153925,0.00044776706,0.1267117,0.002536492,0.0014298542,0.0011382474,0.8446688,0.00017822039,0.022647392],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996401,0.00011050015,0.0006168239,0.0015739436,0.00038926434,0.0009084844],"domain_scores_gemma":[0.99784553,0.0003727488,0.00028402626,0.0011379301,0.00015718133,0.00020258507],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006442484,0.0005416006,0.00061139144,0.00050833874,0.00041230387,0.00054880144,0.0019656904,0.00044598978,0.00008634988],"category_scores_gemma":[0.00015690828,0.0005518466,0.0002020736,0.0008392574,0.000085233856,0.00031591012,0.001416942,0.0009710192,0.0024329242],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016667967,0.00002458616,0.0000019082768,0.00045152198,0.000027482374,0.000045849254,0.0002770892,0.00041295853,0.0005984558,0.000027512331,0.9768716,0.02124433],"study_design_scores_gemma":[0.00027796085,0.00020813382,0.0000023071345,0.00013666725,0.000038057868,0.000071938295,0.00017199294,0.010564455,0.0017462523,0.0003988341,0.985778,0.00060545624],"about_ca_topic_score_codex":0.0005581883,"about_ca_topic_score_gemma":0.0013703551,"teacher_disagreement_score":0.4943157,"about_ca_system_score_codex":0.00040764344,"about_ca_system_score_gemma":0.00013196259,"threshold_uncertainty_score":0.9996933},"labels":[],"label_agreement":null},{"id":"W4392158123","doi":"10.1109/globecom54140.2023.10436915","title":"Mammogram Tumor Segmentation with Preserved Local Resolution: An Explainable AI System","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Image segmentation; Computer vision; Resolution (logic)","score_opus":0.017123472110559916,"score_gpt":0.251873401264616,"score_spread":0.23474992915405607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392158123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02302042,0.000012320549,0.9720385,0.00053317996,0.00033110674,0.00032702181,9.943552e-7,0.0018798322,0.0018566453],"genre_scores_gemma":[0.9747499,0.0000013684331,0.023011243,0.00015251484,0.00009891187,0.00020951839,0.00000876224,0.000014827922,0.0017529443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986293,0.000096390824,0.00016546431,0.00041313868,0.00039413033,0.00030157864],"domain_scores_gemma":[0.99916065,0.000025537796,0.00006016535,0.00054376584,0.0001121792,0.0000977132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033807993,0.000109903965,0.0000998248,0.0001293997,0.00021964786,0.00021026627,0.00042972743,0.000035674988,0.000015051237],"category_scores_gemma":[0.0000038992266,0.00009204599,0.000022933742,0.0010878547,0.000037922786,0.0013558062,0.00013211624,0.00008985527,0.00013941897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082213007,0.00047620732,0.009211615,0.0017053762,0.00025047548,0.0012294389,0.006416015,0.44177553,0.0062879235,0.2617597,0.08878849,0.18127713],"study_design_scores_gemma":[0.000465807,0.00054324785,0.0018300104,0.000043669803,0.0000057539846,0.00007136735,0.0019063805,0.983145,0.009713772,0.00029233613,0.0017938621,0.00018877003],"about_ca_topic_score_codex":0.0005726532,"about_ca_topic_score_gemma":0.00034347424,"teacher_disagreement_score":0.9517295,"about_ca_system_score_codex":0.0002945374,"about_ca_system_score_gemma":0.00008224958,"threshold_uncertainty_score":0.37535268},"labels":[],"label_agreement":null},{"id":"W4392200359","doi":"10.18280/isi.290109","title":"Swin Transformer and Attention Guided Thyroid Nodule Segmentation on Ultrasound Images","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Nodule (geology); Thyroid nodules; Computer vision; Transformer; Artificial intelligence; Ultrasound; Thyroid; Computer science; Radiology; Medicine; Biology; Internal medicine; Engineering; Electrical engineering","score_opus":0.018715839541135107,"score_gpt":0.2604885441197629,"score_spread":0.24177270457862782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392200359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102284946,0.00603858,0.86408854,0.0022315306,0.007264115,0.0009876709,0.00011972194,0.00061800715,0.016366893],"genre_scores_gemma":[0.9866832,0.0019544745,0.008084853,0.00047218855,0.00045056498,0.00013415642,0.00014387659,0.000035752953,0.002040951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975826,0.00014611703,0.00085740996,0.0003915388,0.0005547668,0.00046755446],"domain_scores_gemma":[0.9988614,0.00019805382,0.00022321842,0.00032639492,0.0002635032,0.00012748675],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0008283213,0.00035969482,0.00024049799,0.0004863774,0.00045678418,0.0024425709,0.00024137294,0.00024296912,0.00009720522],"category_scores_gemma":[0.0001093039,0.00037887724,0.00012816042,0.0008742495,0.00027439135,0.0143263005,0.000040687148,0.00032637763,0.00062344415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000522588,0.00004534339,0.00023438327,0.0026532088,0.00014356496,0.0000117109585,0.021668298,0.0013550462,0.023048786,0.024236256,0.013032495,0.91351867],"study_design_scores_gemma":[0.005036832,0.004809031,0.052760966,0.012086385,0.0007298056,0.0043414016,0.008614665,0.35331193,0.3051712,0.08206748,0.1666402,0.0044300947],"about_ca_topic_score_codex":0.00030480933,"about_ca_topic_score_gemma":0.00002495413,"teacher_disagreement_score":0.90908855,"about_ca_system_score_codex":0.0010551574,"about_ca_system_score_gemma":0.00017152181,"threshold_uncertainty_score":0.9998663},"labels":[],"label_agreement":null},{"id":"W4392200579","doi":"10.18280/isi.290134","title":"Integration of ML Techniques for Early Detection of Breast Cancer: Dimensionality Reduction Approach","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dimensionality reduction; Breast cancer; Reduction (mathematics); Computer science; Cancer; Pattern recognition (psychology); Artificial intelligence; Medicine; Mathematics; Internal medicine","score_opus":0.015878989193126487,"score_gpt":0.25523649895716655,"score_spread":0.23935750976404005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392200579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078686155,0.00014766613,0.9188505,0.000053910397,0.00077050575,0.00056489423,0.000053043375,0.00034139882,0.00053193164],"genre_scores_gemma":[0.9667618,0.000042996046,0.032740097,0.0000073328633,0.00010140377,0.00029980027,0.000023552579,0.000009211895,0.000013800467],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998669,0.000050149116,0.0006506637,0.00018661033,0.0002961692,0.00014737606],"domain_scores_gemma":[0.9986668,0.0000468638,0.00037133563,0.00026569952,0.00061777595,0.000031530173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006164876,0.00013729968,0.00018957556,0.00040627245,0.000121979814,0.00013197656,0.00021305292,0.00013108535,0.000002612879],"category_scores_gemma":[0.000042467134,0.00012872055,0.000106195315,0.0007984437,0.00010459411,0.004642039,0.00005036019,0.00011266226,0.0000018290465],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007705775,0.000022801067,0.00003212508,0.0010224348,0.00004319247,5.2588813e-8,0.003550397,0.00033105665,0.11286204,0.013071893,0.0000876394,0.8688993],"study_design_scores_gemma":[0.00019531378,0.00031560482,0.006630717,0.00062133285,0.00004013822,0.00009810113,0.00037879817,0.2274209,0.74661195,0.016845627,0.00059458124,0.0002469194],"about_ca_topic_score_codex":0.000519163,"about_ca_topic_score_gemma":0.000007398754,"teacher_disagreement_score":0.88807565,"about_ca_system_score_codex":0.00047339746,"about_ca_system_score_gemma":0.00012913086,"threshold_uncertainty_score":0.5249072},"labels":[],"label_agreement":null},{"id":"W4392349280","doi":"10.18280/ts.410131","title":"Automated Classification of Liver Cancer Stages Using Deep Learning on Histopathological Images","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Deep learning; Cancer; Computer science; Liver cancer; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.046611573869015065,"score_gpt":0.30332379124407244,"score_spread":0.2567122173750574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392349280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36705938,0.0009274709,0.62986976,0.0002606727,0.00042743163,0.00017757379,0.0000049718988,0.000980527,0.00029225132],"genre_scores_gemma":[0.9933443,0.00006578083,0.006331178,0.000041803614,0.00010379882,0.000027366912,0.0000020911586,0.00001084924,0.000072811345],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987849,0.00012097632,0.00023593963,0.0003641671,0.00032147847,0.0001725538],"domain_scores_gemma":[0.9995781,0.00008600207,0.00009555526,0.00013980074,0.00006322383,0.00003730989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003070837,0.0001200617,0.00012264554,0.0001496837,0.000097034455,0.00009152156,0.0002410438,0.000056212695,0.00017065385],"category_scores_gemma":[0.000010760351,0.00010603688,0.00005792157,0.00030766707,0.000060471542,0.00029997277,0.00005325097,0.00017418618,0.000016374972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004187826,0.00013046621,0.0017670208,0.0001944569,0.000050769522,0.000083956285,0.0020044586,0.053846482,0.56884557,0.006367767,0.0006482977,0.3660189],"study_design_scores_gemma":[0.000118944,0.00022412994,0.03353229,0.00010371436,0.000018000193,0.000009436442,0.00002683434,0.9463878,0.018303158,0.00008796647,0.0010605003,0.00012717981],"about_ca_topic_score_codex":0.000052551466,"about_ca_topic_score_gemma":0.000005037608,"teacher_disagreement_score":0.89254135,"about_ca_system_score_codex":0.0003244823,"about_ca_system_score_gemma":0.000055768993,"threshold_uncertainty_score":0.43240583},"labels":[],"label_agreement":null},{"id":"W4392386754","doi":"10.18280/ts.410110","title":"A Comparative Analysis of Machine Learning Algorithms for Breast Cancer Detection and Identification of Key Predictive Features","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identification (biology); Key (lock); Computer science; Machine learning; Artificial intelligence; Algorithm; Breast cancer; Cancer; Medicine; Internal medicine; Computer security","score_opus":0.018137851165327762,"score_gpt":0.29085155509463273,"score_spread":0.27271370392930494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392386754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067168266,0.0007772,0.9311783,0.00011876004,0.00016453165,0.00028424515,0.00022415657,0.00006360824,0.000020974128],"genre_scores_gemma":[0.99829316,0.000045421926,0.0014409409,0.0000061070523,0.00005588958,0.00010739487,0.000009856049,0.0000046555456,0.000036575617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902606,0.00005920043,0.00028656182,0.00029802317,0.00023216176,0.000097996206],"domain_scores_gemma":[0.9994218,0.00011585353,0.00017610229,0.000092259186,0.00016567022,0.000028353223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031806855,0.0000962239,0.0002154265,0.00035712743,0.000074182484,0.000059922135,0.00012487166,0.00003629601,0.000019113355],"category_scores_gemma":[0.000004286103,0.00008840797,0.00009336262,0.00084320933,0.000052778,0.00030439635,0.00003231082,0.0000901025,2.24751e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039658564,0.00014696759,0.002184219,0.00042280936,0.004462331,0.0000012808007,0.018360913,0.122572616,0.33170637,0.002170747,0.000084671854,0.5174905],"study_design_scores_gemma":[0.00018388817,0.00019058256,0.07171359,0.000034039964,0.00040065031,0.0000031289062,0.000097803015,0.8636152,0.06346929,0.00015646964,0.00006581429,0.000069528716],"about_ca_topic_score_codex":0.00020350014,"about_ca_topic_score_gemma":0.00016315248,"teacher_disagreement_score":0.93112487,"about_ca_system_score_codex":0.00009255154,"about_ca_system_score_gemma":0.000033465585,"threshold_uncertainty_score":0.36051726},"labels":[],"label_agreement":null},{"id":"W4392511208","doi":"10.1038/s44303-023-00005-z","title":"Artificial intelligence unravels interpretable malignancy grades of prostate cancer on histology images","year":2024,"lang":"en","type":"article","venue":"npj Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Université Laval; Université de Montréal; Canada First Research Excellence Fund; Centre Hospitalier Universitaire de Québec; McGill University Health Centre; McGill University","keywords":"Prostate cancer; Malignancy; Histology; Medicine; Artificial intelligence; Prostate; Cancer; Computer science; Pathology; Internal medicine","score_opus":0.01983742175380213,"score_gpt":0.298922384383597,"score_spread":0.2790849626297948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392511208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063696657,0.0059271003,0.9774434,0.0036957162,0.0036033408,0.0002158606,0.000010759276,0.0003132449,0.0024209167],"genre_scores_gemma":[0.99263376,0.00015351463,0.0065991967,0.0001855196,0.000108214015,0.00005372425,5.8131457e-7,0.000019210045,0.00024625432],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985756,0.000054514367,0.00033307963,0.00051312736,0.00021548146,0.00030818637],"domain_scores_gemma":[0.9993198,0.000110269946,0.00009023608,0.00036530755,0.00007083756,0.000043564192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002257311,0.00015648875,0.00018026892,0.00025459926,0.000071665236,0.00015705169,0.0004953037,0.000032467786,0.00005702016],"category_scores_gemma":[0.000029445822,0.00014870778,0.00006994686,0.00050787214,0.00013755933,0.0004381562,0.00015667433,0.00021882479,0.000048242495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014501593,0.000023404982,0.00053113495,0.00012601953,0.0000202423,0.000049266684,0.0021973378,0.0007175091,0.024758298,0.026059689,0.0005207187,0.9449819],"study_design_scores_gemma":[0.00003350373,0.00010785736,0.00031903933,0.00069363636,0.000020346079,0.000055717624,0.00012011551,0.27494216,0.6528376,0.06659031,0.0039623543,0.0003174072],"about_ca_topic_score_codex":0.00023828637,"about_ca_topic_score_gemma":0.000020279587,"teacher_disagreement_score":0.9862641,"about_ca_system_score_codex":0.00022166179,"about_ca_system_score_gemma":0.00012598273,"threshold_uncertainty_score":0.60641277},"labels":[],"label_agreement":null},{"id":"W4392667554","doi":"10.1007/978-3-031-55088-1_7","title":"Self Supervised Multi-view Graph Representation Learning in Digital Pathology","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Digital pathology; Graph; Economic shortage; Artificial intelligence; Representation (politics); Machine learning; External Data Representation; Deep learning; Labeled data; Theoretical computer science; Pattern recognition (psychology)","score_opus":0.02083813577045536,"score_gpt":0.26638915533550206,"score_spread":0.2455510195650467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392667554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035607108,0.0015025615,0.99211586,0.0005070129,0.002770116,0.00046364847,0.0000029323248,0.00053821714,0.0017435912],"genre_scores_gemma":[0.36644566,0.00082017074,0.6293773,0.0010006375,0.0008233262,0.00007698072,0.000021765687,0.00013875504,0.0012954196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99584717,0.000046945974,0.0006306428,0.002079206,0.0007651528,0.00063085696],"domain_scores_gemma":[0.9981019,0.00038425325,0.00020512516,0.0010192911,0.00017391096,0.00011555258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074620737,0.00049655687,0.00051815907,0.0015365311,0.00016121747,0.0009255863,0.0020419364,0.00038599092,0.000009752704],"category_scores_gemma":[0.00011122202,0.0004905681,0.00015753155,0.0015559569,0.0003899034,0.0012636713,0.0013482565,0.0015180425,0.00011221805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005186223,0.00003440444,0.0004524891,0.00011988234,0.000012357683,0.00048668307,0.0025112578,0.042537723,0.000092918715,0.004559634,0.0000053545236,0.9491821],"study_design_scores_gemma":[0.00034745465,0.00019184845,0.0002323508,0.0005769906,0.000008176041,0.00022317226,7.3569373e-7,0.8737018,0.0003922311,0.12244549,0.0012511885,0.0006285842],"about_ca_topic_score_codex":0.000024332576,"about_ca_topic_score_gemma":0.0001250663,"teacher_disagreement_score":0.9485535,"about_ca_system_score_codex":0.00056956225,"about_ca_system_score_gemma":0.0003743494,"threshold_uncertainty_score":0.9997546},"labels":[],"label_agreement":null},{"id":"W4392718073","doi":"10.1117/12.3002980","title":"Virtual histology with photon absorption remote sensing (PARS)","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Illumisonics (Canada); University of Waterloo","funders":"","keywords":"Absorption (acoustics); Histology; Materials science; Photon; Optics; Optoelectronics; Computer science; Physics; Medicine; Pathology","score_opus":0.013998509647828573,"score_gpt":0.2370894492083021,"score_spread":0.22309093956047354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392718073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020247648,0.00007278252,0.96603745,0.0009925269,0.0012361516,0.000070934024,1.7827098e-7,0.0007010914,0.010641252],"genre_scores_gemma":[0.8560852,0.000017585588,0.14054558,0.00032246983,0.0001383851,5.02664e-7,6.841511e-7,0.00001337079,0.0028762436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991901,0.000029613377,0.00010477511,0.0003594891,0.00015787577,0.0001581695],"domain_scores_gemma":[0.99957675,0.000046123147,0.000023171717,0.00028567182,0.000032461863,0.000035811474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000129309,0.000086629414,0.00007935286,0.000113283284,0.000056346333,0.00010911727,0.00015449965,0.00005409669,0.00003530191],"category_scores_gemma":[0.0000046654136,0.00007006065,0.000024935738,0.0003316301,0.000038847887,0.00033225902,0.000058517086,0.00013065188,0.00018435753],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012735694,0.0000028113477,0.0000020377108,0.000011403422,0.000014804939,0.00006278893,0.0003934674,0.00016491243,0.009004063,0.008263097,0.0021033785,0.9799645],"study_design_scores_gemma":[0.00010461874,0.00020482946,0.000046502846,0.000042394367,0.000006964875,0.00042504378,0.000018655519,0.9016551,0.017567322,0.0025644857,0.07721292,0.00015116479],"about_ca_topic_score_codex":0.00021547757,"about_ca_topic_score_gemma":0.00010207083,"teacher_disagreement_score":0.97981334,"about_ca_system_score_codex":0.00020486163,"about_ca_system_score_gemma":0.000063843756,"threshold_uncertainty_score":0.28569904},"labels":[],"label_agreement":null},{"id":"W4392737249","doi":"10.48550/arxiv.2403.06104","title":"Debiased Noise Editing on Foundation Models for Fair Medical Image Classification","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Image (mathematics); Computer science; Image editing; Artificial intelligence; Psychology","score_opus":0.1205657689989373,"score_gpt":0.23281636464252367,"score_spread":0.11225059564358637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392737249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03423326,0.000009805188,0.9575485,0.00080092327,0.0026336128,0.0005642096,0.000020508593,0.0005860058,0.0036031834],"genre_scores_gemma":[0.99463177,0.000038336082,0.004022354,0.00012936747,0.00056946726,0.000016625805,0.00005419605,0.000032039818,0.0005058272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977517,0.00010101628,0.00025765796,0.0013411498,0.0002532974,0.00029515542],"domain_scores_gemma":[0.9981587,0.00023324027,0.00026840347,0.00091921684,0.00025082417,0.00016962392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053478614,0.00027417557,0.00022777525,0.00035214543,0.00019377733,0.00025161545,0.0012430886,0.00043009478,0.000022839751],"category_scores_gemma":[0.00012609473,0.00032353227,0.00021785828,0.0004801365,0.00011002032,0.000585979,0.00095824373,0.0007378936,0.0001256863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011404888,0.00015668847,0.00009025216,0.0005846653,0.00015257337,0.00012244645,0.0004900842,0.31287333,0.00027180937,0.65421623,0.0038351219,0.02709276],"study_design_scores_gemma":[0.0002623153,0.000053056734,0.00009218019,0.00020276735,0.000042048123,0.0000016106185,0.00003581818,0.7869675,0.0003015745,0.21152832,0.0002831872,0.00022959366],"about_ca_topic_score_codex":0.00008239753,"about_ca_topic_score_gemma":0.00006663924,"teacher_disagreement_score":0.9603985,"about_ca_system_score_codex":0.000826448,"about_ca_system_score_gemma":0.00045311524,"threshold_uncertainty_score":0.9999217},"labels":[],"label_agreement":null},{"id":"W4392851625","doi":"10.54254/2755-2721/47/20241357","title":"Prediction of patient breast cancer probability","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Breast cancer; Cancer; Medicine; Internal medicine","score_opus":0.007037028037619113,"score_gpt":0.18677232085494655,"score_spread":0.17973529281732745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392851625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08338136,0.0002697679,0.9153726,0.00016991486,0.00034101566,0.00010323094,0.000017995562,0.00021694967,0.00012712188],"genre_scores_gemma":[0.9827202,0.0000073988913,0.017159507,0.000013187717,0.000049308972,0.000042016924,0.0000020098514,0.000004721276,0.0000016268102],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951047,0.000002618792,0.00011681969,0.00017220883,0.00013171679,0.00006615902],"domain_scores_gemma":[0.9998276,0.000041550436,0.000016051896,0.00006148334,0.000028072296,0.000025196594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048425398,0.000057768364,0.000056387613,0.00005478309,0.000020843747,0.000033903943,0.000057569006,0.000021138068,0.0000035159944],"category_scores_gemma":[0.0000011127361,0.00005659025,0.000015550133,0.00019089054,0.000011545496,0.00012053882,0.0000414839,0.000057432702,0.0000011539182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024072242,0.0000088390825,0.00006045465,0.00012197943,0.000019112931,4.557993e-7,0.00028625713,0.74304456,0.0010565371,0.13985136,0.000029907318,0.11551814],"study_design_scores_gemma":[0.000053263295,0.000014059646,0.009870041,0.000038885282,0.0000035000294,0.000016253136,0.0000038289227,0.97734517,0.00050637487,0.011775469,0.00032012686,0.000053004114],"about_ca_topic_score_codex":0.00000835586,"about_ca_topic_score_gemma":2.2215448e-7,"teacher_disagreement_score":0.89933884,"about_ca_system_score_codex":0.000048759917,"about_ca_system_score_gemma":0.00003478666,"threshold_uncertainty_score":0.23076832},"labels":[],"label_agreement":null},{"id":"W4392862598","doi":"10.5070/d330163299","title":"Advancing dermatology education with AI-generated images.","year":2024,"lang":"en","type":"article","venue":"Dermatology Online Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Dermatology","score_opus":0.00661959535437406,"score_gpt":0.28297130287483546,"score_spread":0.2763517075204614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392862598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058933266,0.005860164,0.8755067,0.05463416,0.004138737,0.000116622694,0.000003904154,0.00042101898,0.00038543835],"genre_scores_gemma":[0.8779044,0.0004750937,0.11619368,0.004422315,0.0007010484,0.000020683572,0.000018112325,0.000041883988,0.0002227661],"study_design_codex":"design_other","study_design_gemma":"case_report","domain_scores_codex":[0.998386,0.00017811815,0.00041771645,0.00036967374,0.00021433421,0.000434125],"domain_scores_gemma":[0.9990256,0.00007723433,0.00013888816,0.0003131291,0.00027928356,0.00016590663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012639318,0.00020178405,0.00025754303,0.00046953457,0.0002490498,0.00029681818,0.0005258501,0.00014155387,0.000035514808],"category_scores_gemma":[0.00003103815,0.00016541463,0.00006589188,0.0006916714,0.0000920774,0.0011822082,0.00009128219,0.000850767,0.00006903145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080414924,0.0005516729,0.0069698365,0.00032343634,0.0004351588,0.009129536,0.0012107173,0.0016797314,0.0110648535,0.01321034,0.31332946,0.64201486],"study_design_scores_gemma":[0.0006524266,0.00014692008,0.0011195109,0.00027412415,0.00006811934,0.5901247,0.00015719584,0.18593293,0.025875274,0.0069472883,0.1881719,0.000529563],"about_ca_topic_score_codex":0.000009008645,"about_ca_topic_score_gemma":0.000044498156,"teacher_disagreement_score":0.81897116,"about_ca_system_score_codex":0.00018715163,"about_ca_system_score_gemma":0.0015053604,"threshold_uncertainty_score":0.6745413},"labels":[],"label_agreement":null},{"id":"W4392882143","doi":"10.1016/j.compbiomed.2024.108317","title":"CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Similarity (geometry); Image (mathematics); Artificial intelligence; Pattern recognition (psychology); Cosine similarity; Computer science; Variation (astronomy); Class (philosophy); Discrete cosine transform; Computer vision; Structural similarity; Image synthesis","score_opus":0.012491706736767801,"score_gpt":0.32022863231840176,"score_spread":0.30773692558163396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392882143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017114675,0.00029574745,0.96325135,0.016614618,0.002258596,0.00022135336,0.000022499638,0.00012677016,0.00009441752],"genre_scores_gemma":[0.9462664,0.00008665658,0.048198633,0.0049873968,0.00032243918,0.000040062318,0.00007835344,0.0000145207805,0.0000055527844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833626,0.00019207154,0.00038116323,0.00062937307,0.00016411132,0.00029703576],"domain_scores_gemma":[0.99879223,0.0006157161,0.000042996016,0.0003759373,0.000024472783,0.00014866678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010413593,0.00017830839,0.00031594074,0.000504504,0.000046089663,0.000047944926,0.0005184258,0.00016124616,0.000036920126],"category_scores_gemma":[0.00025190783,0.0001513569,0.000021351228,0.00058442174,0.0002569205,0.00023248776,0.00037007488,0.00040455128,0.000012700463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005630476,0.0006701072,0.00473317,0.0023217017,0.00017339287,0.0034478414,0.009267046,0.00059623056,0.1801159,0.029329337,0.040961858,0.7278204],"study_design_scores_gemma":[0.0020202936,0.0008108338,0.015298346,0.0037425216,0.00001292289,0.00016965542,0.000018952185,0.96018463,0.0014151807,0.0052074073,0.010729614,0.00038965803],"about_ca_topic_score_codex":0.00013410168,"about_ca_topic_score_gemma":0.00010065855,"teacher_disagreement_score":0.9595884,"about_ca_system_score_codex":0.00018553961,"about_ca_system_score_gemma":0.00009263517,"threshold_uncertainty_score":0.6172155},"labels":[],"label_agreement":null},{"id":"W4392883923","doi":"10.1016/j.media.2024.103143","title":"CellViT: Vision Transformers for precise cell segmentation and classification","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Universität Duisburg-Essen","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Deep learning; Encoder; Pattern recognition (psychology); Cluster analysis; Computer vision; Scale-space segmentation; Image segmentation","score_opus":0.010348644571440708,"score_gpt":0.308377914807403,"score_spread":0.2980292702359623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392883923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004219302,0.00044049433,0.99128693,0.0029059346,0.00019654655,0.00017239281,0.0000046228192,0.00013025204,0.0006434921],"genre_scores_gemma":[0.9611568,0.00050860125,0.037434228,0.00017884398,0.00010579067,0.00010128451,0.000034512155,0.00001134404,0.00046860133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987049,0.000047550766,0.00022589853,0.00042594445,0.00045009397,0.0001456155],"domain_scores_gemma":[0.9994453,0.00017918626,0.000036502373,0.00015268355,0.000053634227,0.00013268608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055577216,0.00009068858,0.00013610041,0.00029621198,0.00008800035,0.00024501278,0.00017792336,0.000081232254,0.00010168447],"category_scores_gemma":[0.00003470469,0.0000777243,0.00013976237,0.0011178998,0.000057651592,0.0006418491,0.000027760207,0.00010684496,0.00002382061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008897473,0.00003670826,0.00005263535,0.00012426877,0.00014561896,0.0000061906567,0.00061119173,0.00001885171,0.02617229,0.00016546847,0.0024085303,0.97024935],"study_design_scores_gemma":[0.0001902091,0.00007324032,0.0004622704,0.000016937487,0.00035798276,0.0000019046281,0.00005877757,0.9754264,0.0189446,0.00044726318,0.00392042,0.000100042875],"about_ca_topic_score_codex":0.000018381916,"about_ca_topic_score_gemma":0.00002923841,"teacher_disagreement_score":0.9754075,"about_ca_system_score_codex":0.00007769169,"about_ca_system_score_gemma":0.000058384772,"threshold_uncertainty_score":0.31695047},"labels":[],"label_agreement":null},{"id":"W4392927763","doi":"10.32920/25412656.v1","title":"Domain Generalization Across Multi-centre Digital Pathology Images for Lymph Node Segmentation and Classification","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Deep learning; Computer science; Digital pathology; Artificial intelligence; Machine learning; Transfer of learning; Generalization; Segmentation; Workflow; Medical diagnosis; Domain (mathematical analysis); Task (project management); Medicine; Pathology","score_opus":0.029867150346093153,"score_gpt":0.313594560318499,"score_spread":0.28372740997240586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392927763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038256444,0.00032573842,0.9566909,0.0016922475,0.0016513463,0.0006808901,0.0001745404,0.00039601457,0.00013187043],"genre_scores_gemma":[0.37506133,0.00028145188,0.62096465,0.0003267941,0.0004007999,0.00052203337,0.000601237,0.00006412094,0.0017775918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982414,0.000052103387,0.00033484603,0.0009467753,0.00017518838,0.0002496573],"domain_scores_gemma":[0.99907506,0.00005328718,0.00019776748,0.00045670295,0.0001614023,0.00005580662],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00023567388,0.00023895838,0.00018479826,0.000106086474,0.00013354377,0.0010664776,0.00032553164,0.0002697353,0.0000029175335],"category_scores_gemma":[0.000020699044,0.00023475978,0.00007807093,0.00014736564,0.00006738691,0.00040970067,0.00094604853,0.00014912496,0.000023750466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006458492,0.00027192457,0.0057387347,0.0018875204,0.00019922278,0.000024158493,0.010992928,0.0054486496,0.05273935,0.03168753,0.0069912835,0.8839541],"study_design_scores_gemma":[0.0015614142,0.00004756641,0.007755177,0.00017232493,0.00004559953,0.000061869,0.0006447839,0.90850717,0.014434228,0.063564695,0.0023797452,0.0008254053],"about_ca_topic_score_codex":0.00001744692,"about_ca_topic_score_gemma":0.000015399495,"teacher_disagreement_score":0.9030585,"about_ca_system_score_codex":0.00032243086,"about_ca_system_score_gemma":0.00009192476,"threshold_uncertainty_score":0.9999705},"labels":[],"label_agreement":null},{"id":"W4392927829","doi":"10.32920/25412656","title":"Domain Generalization Across Multi-centre Digital Pathology Images for Lymph Node Segmentation and Classification","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Deep learning; Digital pathology; Computer science; Artificial intelligence; Transfer of learning; Workflow; Generalization; Segmentation; Machine learning; Domain (mathematical analysis); Medical diagnosis; Task (project management); Pattern recognition (psychology); Medicine; Pathology","score_opus":0.029867150346093153,"score_gpt":0.313594560318499,"score_spread":0.28372740997240586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392927829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038256444,0.00032573842,0.9566909,0.0016922475,0.0016513463,0.0006808901,0.0001745404,0.00039601457,0.00013187043],"genre_scores_gemma":[0.37506133,0.00028145188,0.62096465,0.0003267941,0.0004007999,0.00052203337,0.000601237,0.00006412094,0.0017775918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982414,0.000052103387,0.00033484603,0.0009467753,0.00017518838,0.0002496573],"domain_scores_gemma":[0.99907506,0.00005328718,0.00019776748,0.00045670295,0.0001614023,0.00005580662],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00023567388,0.00023895838,0.00018479826,0.000106086474,0.00013354377,0.0010664776,0.00032553164,0.0002697353,0.0000029175335],"category_scores_gemma":[0.000020699044,0.00023475978,0.00007807093,0.00014736564,0.00006738691,0.00040970067,0.00094604853,0.00014912496,0.000023750466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006458492,0.00027192457,0.0057387347,0.0018875204,0.00019922278,0.000024158493,0.010992928,0.0054486496,0.05273935,0.03168753,0.0069912835,0.8839541],"study_design_scores_gemma":[0.0015614142,0.00004756641,0.007755177,0.00017232493,0.00004559953,0.000061869,0.0006447839,0.90850717,0.014434228,0.063564695,0.0023797452,0.0008254053],"about_ca_topic_score_codex":0.00001744692,"about_ca_topic_score_gemma":0.000015399495,"teacher_disagreement_score":0.9030585,"about_ca_system_score_codex":0.00032243086,"about_ca_system_score_gemma":0.00009192476,"threshold_uncertainty_score":0.9999705},"labels":[],"label_agreement":null},{"id":"W4392943560","doi":"10.1109/mosicom59118.2023.10458789","title":"A Study to Evaluate Various Machine Learning Approaches for Breast Cancer Prediction and Detection","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"","keywords":"Computer science; Machine learning; Breast cancer; Artificial intelligence; Cancer; Medicine; Internal medicine","score_opus":0.05698122016613104,"score_gpt":0.29503972065365275,"score_spread":0.2380585004875217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392943560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24420978,0.00002389132,0.7526894,0.00066651095,0.00054181286,0.0009595523,0.000009915221,0.000803005,0.00009611233],"genre_scores_gemma":[0.9967658,0.00001216817,0.0018208777,0.000043371234,0.00013048988,0.0006232834,0.000001228277,0.0000145167105,0.0005882658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888486,0.00007617698,0.0001440074,0.0004627688,0.0002267689,0.00020542859],"domain_scores_gemma":[0.99957114,0.00005600469,0.00004547305,0.00018936141,0.0000683058,0.00006969817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006852432,0.00010844425,0.000104620216,0.00019402092,0.00028094347,0.00012340314,0.00015357544,0.000031275908,0.000006168197],"category_scores_gemma":[0.000026226779,0.000098263656,0.000024551628,0.00071845733,0.000009642397,0.0002916228,0.00017032414,0.00010539873,0.000012978508],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073116236,0.00006311391,0.009922693,0.000023110717,0.00005451093,0.0000013215138,0.003833457,0.04291204,0.0007114077,0.00008812379,0.000110250774,0.94220686],"study_design_scores_gemma":[0.00049894996,0.0006046758,0.09973807,0.000006321879,0.000019699644,0.000023774448,0.00031235875,0.89762646,0.00050353655,0.0002953098,0.00026035088,0.00011048431],"about_ca_topic_score_codex":0.00057714,"about_ca_topic_score_gemma":0.0011794167,"teacher_disagreement_score":0.94209635,"about_ca_system_score_codex":0.00013353927,"about_ca_system_score_gemma":0.000029480605,"threshold_uncertainty_score":0.40070757},"labels":[],"label_agreement":null},{"id":"W4392949341","doi":"10.21203/rs.3.rs-4004164/v1","title":"Validating Large Language Models for Identifying Pathologic Complete Responses After Neoadjuvant Chemotherapy for Breast Cancer Using a Population-Based Pathologic Report Data","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Chemotherapy; Medicine; Oncology; Neoadjuvant therapy; Population; Cancer; Pathology; Internal medicine","score_opus":0.2879053930948052,"score_gpt":0.4922161359139098,"score_spread":0.2043107428191046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392949341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14623591,0.0025054887,0.83345443,0.0015270332,0.0010417602,0.0035696297,0.01121395,0.00044126742,0.00001051728],"genre_scores_gemma":[0.8607091,0.000056693014,0.13431081,0.0001759249,0.00072005333,0.0027790093,0.0010130267,0.00011817153,0.00011725792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99358076,0.0007226336,0.0008295655,0.0024781206,0.0012439888,0.0011449608],"domain_scores_gemma":[0.9941203,0.0010460838,0.00043756203,0.0033314032,0.0009185017,0.00014612472],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0077674543,0.00045883123,0.00061035086,0.0007487596,0.0006172814,0.0012164123,0.0022521713,0.00043164272,0.000034343757],"category_scores_gemma":[0.0006125546,0.00042539454,0.00030608595,0.0007089192,0.00008338317,0.00051998283,0.0043221563,0.0011755239,0.0000044552266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009661813,0.0018077488,0.029225942,0.07291776,0.0015118563,0.021704627,0.024466628,0.35842967,0.061494675,0.0061333836,0.0065625287,0.40608335],"study_design_scores_gemma":[0.0006248588,0.00009320506,0.0029869503,0.0019973863,0.00003997918,0.0002142356,0.0002048285,0.96852905,0.00039541678,0.024249688,0.00015979163,0.0005046161],"about_ca_topic_score_codex":0.001207139,"about_ca_topic_score_gemma":0.00030233563,"teacher_disagreement_score":0.7144731,"about_ca_system_score_codex":0.0012214711,"about_ca_system_score_gemma":0.0011863287,"threshold_uncertainty_score":0.9998204},"labels":[],"label_agreement":null},{"id":"W4392950384","doi":"10.21203/rs.3.rs-1452983/v1","title":"Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pancreas Centre (Canada)","funders":"Tsinghua University; National Natural Science Foundation of China","keywords":"Cancer; Biomarker discovery; Medicine; Artificial intelligence; Computer science; Internal medicine; Biology; Proteomics","score_opus":0.15853263267112444,"score_gpt":0.4774507811312098,"score_spread":0.31891814846008537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392950384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3767931,0.03612672,0.5652122,0.0034204028,0.006338347,0.00959859,0.0005023435,0.0006155343,0.0013927484],"genre_scores_gemma":[0.98580605,0.0046326993,0.0077635464,0.000006172164,0.000314052,0.0009803572,0.000024566023,0.00004594823,0.00042662767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99577487,0.000675286,0.0007974652,0.0010199349,0.0012096054,0.00052283413],"domain_scores_gemma":[0.99616313,0.0014129416,0.0003477631,0.0008064147,0.0011561215,0.00011365669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003988248,0.00021028022,0.00051983976,0.0006119308,0.00009630627,0.00018863389,0.0013061154,0.00040846615,0.00003142077],"category_scores_gemma":[0.00077347184,0.00019427559,0.00049604516,0.00092724327,0.0003745917,0.00020949884,0.0035419706,0.0016332399,0.00000834647],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000622303,0.00053162413,0.06257842,0.02707851,0.001760415,0.000050511786,0.0025579121,0.0028624227,0.0017474312,0.0027189497,0.010639956,0.88685155],"study_design_scores_gemma":[0.0011999853,0.0030932676,0.06586477,0.008973495,0.0002094471,0.0000066423204,0.0005750574,0.8533712,0.041216765,0.015466184,0.009065051,0.00095811795],"about_ca_topic_score_codex":0.0011530372,"about_ca_topic_score_gemma":0.00023674444,"teacher_disagreement_score":0.8858934,"about_ca_system_score_codex":0.0003380126,"about_ca_system_score_gemma":0.0013737284,"threshold_uncertainty_score":0.7922329},"labels":[],"label_agreement":null},{"id":"W4393012000","doi":"10.3389/fonc.2024.1343627","title":"Breast cancer risk prediction using machine learning: a systematic review","year":2024,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Breast cancer; Artificial intelligence; Mammography; Machine learning; Medicine; Breast imaging; Radiomics; Predictive modelling; Risk assessment; Computer science; Benchmarking; Personalized medicine; Precision medicine; Medical physics; Cancer; Bioinformatics; Pathology; Internal medicine","score_opus":0.03068124242432841,"score_gpt":0.3474463769112952,"score_spread":0.3167651344869668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393012000","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.248167e-8,0.89331406,0.09397297,0.00009648648,0.01013317,0.002043863,0.000095035364,0.00024585275,0.00009851668],"genre_scores_gemma":[3.46512e-7,0.9885956,0.009531281,0.000072519564,0.00033424195,0.0010707467,0.000015244974,0.000063689906,0.000316312],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949929,0.0019245204,0.0013882917,0.0009371036,0.00032902643,0.00042813056],"domain_scores_gemma":[0.9977339,0.00013601924,0.0012434473,0.0007177684,0.00007344616,0.000095457515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015991408,0.00050486147,0.0034817304,0.0006970711,0.00011282588,0.00007684856,0.0010790367,0.0005626689,0.000015745085],"category_scores_gemma":[0.00013437157,0.00039917266,0.0004731548,0.001703873,0.00006955964,0.00024489473,0.00038452755,0.0017980633,0.000051092833],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014429744,0.000016608501,0.0000201612,0.58930016,0.00022805501,0.000038379894,0.000051168823,0.00003504735,8.972342e-9,0.00001426013,0.004453915,0.4058408],"study_design_scores_gemma":[0.00008430653,0.000073212155,3.9703664e-7,0.4645408,0.0037642373,0.0009791541,0.0000053885865,0.04453737,2.0901066e-8,0.00010380221,0.48564517,0.00026612362],"about_ca_topic_score_codex":0.00029261547,"about_ca_topic_score_gemma":0.00006876146,"teacher_disagreement_score":0.48119128,"about_ca_system_score_codex":0.0054929215,"about_ca_system_score_gemma":0.0011766852,"threshold_uncertainty_score":0.99984604},"labels":[],"label_agreement":null},{"id":"W4393072351","doi":"10.1111/his.15178","title":"Transforming diagnostics: The implementation of digital pathology in clinical laboratories","year":2024,"lang":"en","type":"review","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Transformative learning; Digital pathology; Medicine; Health care; Medical physics; Pathology; Data science; Computer science; Psychology; Political science","score_opus":0.05037233363245755,"score_gpt":0.40643451017193105,"score_spread":0.3560621765394735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393072351","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046828318,0.9831694,0.0122051975,0.00012634147,0.0036529973,0.0004982189,0.00007229663,0.00006837038,0.00016036718],"genre_scores_gemma":[0.00034985886,0.9987133,0.0004176479,0.000038735227,0.00019730369,0.00020536802,0.00001797938,0.000025470235,0.00003430885],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973175,0.00043047307,0.0012804953,0.0005642455,0.00014801345,0.0002592729],"domain_scores_gemma":[0.9982815,0.0006232284,0.00040155533,0.00059976574,0.00006307619,0.000030913314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009506137,0.00025269508,0.0010264346,0.00027549572,0.000044923425,0.000049226954,0.0008189378,0.0003298302,0.0000065356817],"category_scores_gemma":[0.00014356633,0.00017730147,0.00028048854,0.00077134516,0.000278534,0.00022433251,0.00021811626,0.0006355441,0.000053635056],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.3725794e-7,0.000015891448,0.00010466552,0.0012701445,0.0000049358932,0.0002154464,0.0006347094,1.3425407e-7,2.6671398e-7,0.008472647,0.00029887244,0.98898137],"study_design_scores_gemma":[0.000103388644,0.00019637571,0.0001124616,0.0007064318,0.00017686267,0.000342904,0.00006759246,0.0000050855456,0.000001554318,0.0018045327,0.9963102,0.00017266397],"about_ca_topic_score_codex":0.000011503798,"about_ca_topic_score_gemma":0.00011687438,"teacher_disagreement_score":0.99601126,"about_ca_system_score_codex":0.00021935813,"about_ca_system_score_gemma":0.00060387846,"threshold_uncertainty_score":0.7230144},"labels":[],"label_agreement":null},{"id":"W4393082940","doi":"10.32920/21428604.v2","title":"piNET: An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Calculator; Index (typography); Breast cancer; Proliferation index; Computer science; Cancer; Medicine; Internal medicine; Operating system; World Wide Web","score_opus":0.018422673843743853,"score_gpt":0.33935096733702197,"score_spread":0.3209282934932781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393082940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004897962,0.00033173178,0.97742575,0.00528885,0.00562775,0.0013882868,0.0002056595,0.0046670483,0.00016695257],"genre_scores_gemma":[0.80422986,0.000045401477,0.18992122,0.00078717485,0.002152506,0.0022117945,0.00004576309,0.00009333283,0.0005129384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974192,0.00006779431,0.0004220724,0.0012808552,0.00042378742,0.00038634086],"domain_scores_gemma":[0.9981187,0.000056150042,0.00019965389,0.0011108576,0.00036278513,0.00015188204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028266036,0.00039875522,0.00034014162,0.00024030718,0.00014050688,0.0010347,0.00097629376,0.00064154825,0.00006957804],"category_scores_gemma":[0.000025133364,0.0003619148,0.00015558818,0.0003940983,0.000044914683,0.00041295926,0.001098786,0.00081161916,0.0000351856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033689165,0.00057892397,0.005117377,0.0059804926,0.001349304,0.000045379486,0.0046339147,0.18986627,0.0030209208,0.2030722,0.10186102,0.4841373],"study_design_scores_gemma":[0.00013256412,0.00005514825,0.0050194645,0.0003243603,0.000034182947,0.000022041782,0.000008333112,0.9105641,0.002585647,0.08036182,0.00044004677,0.00045227754],"about_ca_topic_score_codex":0.0005616726,"about_ca_topic_score_gemma":0.00021655911,"teacher_disagreement_score":0.7993319,"about_ca_system_score_codex":0.00057419075,"about_ca_system_score_gemma":0.0007764276,"threshold_uncertainty_score":0.9998833},"labels":[],"label_agreement":null},{"id":"W4393092446","doi":"10.1007/s11042-024-18947-w","title":"Forward attention-based deep network for classification of breast histopathology image","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Contextual image classification; Deep learning; Pattern recognition (psychology); Image (mathematics); Machine learning","score_opus":0.019132501733826916,"score_gpt":0.27096771475091835,"score_spread":0.25183521301709144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393092446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005036464,0.00038095057,0.99619174,0.0016457062,0.00021929026,0.00061717053,0.00010348236,0.00014988561,0.00018809864],"genre_scores_gemma":[0.5128793,0.000043471708,0.4829901,0.00010421948,0.00051037467,0.003160229,0.00016594351,0.000021735574,0.00012464749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992086,0.000018619317,0.0002132549,0.00033185098,0.00008461818,0.00014302415],"domain_scores_gemma":[0.99916893,0.00029353367,0.000075872034,0.00030774702,0.000105684274,0.000048206573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018112581,0.00008302398,0.000107039545,0.00006288235,0.00011833444,0.000083771396,0.00020298692,0.000062374,0.000006424347],"category_scores_gemma":[0.000012890504,0.00008192863,0.00006222947,0.0002936199,0.00008927389,0.00021445953,0.00003158513,0.000065639564,0.000015419497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008016344,0.000047884427,0.00047650436,0.0001361577,0.0000107752485,3.9207126e-7,0.00009172277,0.00021609427,0.03704734,0.037623484,0.001535238,0.9228064],"study_design_scores_gemma":[0.00021100145,0.000037470218,0.026552597,0.000023639988,0.00002565104,0.000010583722,0.000011847258,0.9307657,0.00043997835,0.0053569255,0.036448665,0.00011598181],"about_ca_topic_score_codex":0.000006819874,"about_ca_topic_score_gemma":0.00001077881,"teacher_disagreement_score":0.93054956,"about_ca_system_score_codex":0.00005171429,"about_ca_system_score_gemma":0.000054909327,"threshold_uncertainty_score":0.33409524},"labels":[],"label_agreement":null},{"id":"W4393143092","doi":"10.1101/2024.03.20.585977","title":"PHARAOH: A collaborative crowdsourcing platform for PHenotyping And Regional Analysis Of Histology","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Université de Sherbrooke; McMaster University; Université Laval; Princess Margaret Cancer Centre","funders":"Princess Margaret Cancer Foundation","keywords":"Crowdsourcing; Histology; Computer science; Data science; World Wide Web; Biology; Genetics","score_opus":0.0211697673662587,"score_gpt":0.24709260520612786,"score_spread":0.22592283783986916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393143092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33886716,0.010022752,0.64524245,0.00088125264,0.002627909,0.0013083786,0.0003748715,0.0006566116,0.000018589695],"genre_scores_gemma":[0.95387024,0.00019067388,0.045137715,0.00015395302,0.00023861446,0.00034113284,3.8755095e-7,0.00006259413,0.0000046893842],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970754,0.00007592338,0.00066955,0.0013804826,0.00035332437,0.00044531573],"domain_scores_gemma":[0.9969534,0.00028494574,0.00068406155,0.0010947691,0.0008244208,0.00015838773],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072512316,0.00046340708,0.0009284568,0.0012460644,0.00018229186,0.00025338776,0.0007983191,0.00045911313,0.0000058322985],"category_scores_gemma":[0.00013853626,0.00051540876,0.0002678388,0.0025126126,0.00019570546,0.0002518526,0.0010560881,0.00057231204,0.000003828057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053777685,0.00039997892,0.0035490084,0.0073531778,0.019549813,0.00014365962,0.0018883836,0.010518812,0.75437886,0.19758175,0.0034254456,0.00067336054],"study_design_scores_gemma":[0.0015188055,0.0002872333,0.016398324,0.0013873244,0.0049870186,1.8494035e-7,0.00003442807,0.8126044,0.14542904,0.0007877901,0.014061042,0.0025043553],"about_ca_topic_score_codex":0.000061847466,"about_ca_topic_score_gemma":0.000017723496,"teacher_disagreement_score":0.80208564,"about_ca_system_score_codex":0.00058530306,"about_ca_system_score_gemma":0.00090740365,"threshold_uncertainty_score":0.99972975},"labels":[],"label_agreement":null},{"id":"W4393182497","doi":"10.4108/eetpht.10.5549","title":"Deep Learning in Medical Imaging: A Case Study on Lung Tissue Classification","year":2024,"lang":"en","type":"article","venue":"EAI Endorsed Transactions on Pervasive Health and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Artificial intelligence; Medical imaging; Lung; Computer science; Computer vision; Medicine; Internal medicine","score_opus":0.017377707678576434,"score_gpt":0.32730877350413273,"score_spread":0.3099310658255563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393182497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050837144,0.0016776647,0.9027972,0.04183291,0.0007710022,0.0007687087,0.000001671203,0.0011773644,0.00013633053],"genre_scores_gemma":[0.9980458,0.00033649532,0.0007455753,0.00045188513,0.000031303003,0.00031206786,0.0000012193567,0.000018548197,0.000057122314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812853,0.00018397122,0.00034314784,0.00069775165,0.00028295838,0.00036363877],"domain_scores_gemma":[0.9991367,0.00022632557,0.000057775724,0.00035407467,0.0000454658,0.0001796943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003799728,0.00017423207,0.00021313594,0.0012343851,0.00035915076,0.00006996105,0.00023576099,0.00016150529,0.000026349198],"category_scores_gemma":[0.000055824934,0.00017291906,0.00002847573,0.0014817192,0.00009602427,0.00020812315,0.000012704234,0.0012237646,0.000025881307],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014139201,0.00022959626,0.00069097796,0.000062509316,0.00001746618,0.0021704356,0.002915143,0.00014790049,0.0000413665,0.0025553408,0.000031516265,0.9911236],"study_design_scores_gemma":[0.002636216,0.0041627474,0.0013937821,0.00041786002,0.000027286682,0.013825783,0.02461515,0.93626547,0.0008653434,0.0015653183,0.013636258,0.00058875844],"about_ca_topic_score_codex":0.00029949308,"about_ca_topic_score_gemma":0.0008515063,"teacher_disagreement_score":0.99053484,"about_ca_system_score_codex":0.00034411225,"about_ca_system_score_gemma":0.00037649184,"threshold_uncertainty_score":0.7051434},"labels":[],"label_agreement":null},{"id":"W4393187453","doi":"10.1016/j.media.2024.103145","title":"DermSynth3D: Synthesis of in-the-wild annotated dermatology images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; BC Cancer Foundation; Fonds National de la Recherche Luxembourg; Nvidia","keywords":"Artificial intelligence; Computer science; Dermatology; Computer vision; Pattern recognition (psychology); Medicine","score_opus":0.006955562316105821,"score_gpt":0.2746487435462664,"score_spread":0.26769318123016056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393187453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013731787,0.0010313599,0.96508116,0.01814313,0.00018637929,0.00007915604,0.00000483715,0.00015831087,0.0015838622],"genre_scores_gemma":[0.9943614,0.00015388084,0.0049744155,0.0003835451,0.00004356042,0.000038967537,0.0000025239333,0.0000074110008,0.00003432039],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780893,0.0003355032,0.00044038374,0.00041377352,0.00073756865,0.00026382343],"domain_scores_gemma":[0.99808425,0.0011189898,0.00006574233,0.00058052025,0.00006806208,0.00008245267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008469836,0.00012800733,0.00037106048,0.0007301729,0.000048139605,0.000118181364,0.0011301916,0.00010881835,0.00028399762],"category_scores_gemma":[0.00069359585,0.000090809284,0.00024935033,0.004617208,0.00023408038,0.00037181654,0.00015067431,0.00028813127,0.00006274699],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019651,0.0003957151,0.008708091,0.00047499087,0.0030552258,0.0066460334,0.0033832872,0.00020834176,0.0034971228,0.0032415066,0.026518231,0.9438518],"study_design_scores_gemma":[0.00021689375,0.000046791516,0.011124879,0.00018020411,0.0013333654,0.0004066229,0.0002784425,0.91852623,0.059609424,0.0026436944,0.0052204933,0.0004129402],"about_ca_topic_score_codex":0.00028515418,"about_ca_topic_score_gemma":0.00015521303,"teacher_disagreement_score":0.98062956,"about_ca_system_score_codex":0.00004492911,"about_ca_system_score_gemma":0.00011293231,"threshold_uncertainty_score":0.3703095},"labels":[],"label_agreement":null},{"id":"W4393270996","doi":"10.1038/s41467-024-46986-2","title":"Mapping cell-to-tissue graphs across human placenta histology whole slide images using deep learning with HAPPY","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Common Fund; NIH Office of the Director; National Institute of Mental Health; National Heart, Lung, and Blood Institute; Eunice Kennedy Shriver National Institute of Child Health and Human Development; European Regional Development Fund; National Institutes of Health; National Cancer Institute; Eesti Teadusagentuur; National Human Genome Research Institute; Wellcome Trust; NIHR Oxford Biomedical Research Centre; Research Councils UK; National Institute on Drug Abuse; Engineering and Physical Sciences Research Council; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research; Bill and Melinda Gates Foundation; Li Ka Shing Foundation; Wellcome","keywords":"Histology; Placenta; Artificial intelligence; Segmentation; Biology; Human placenta; Computer science; Pathology; Pattern recognition (psychology); Medicine; Pregnancy; Fetus; Genetics","score_opus":0.02193260740453406,"score_gpt":0.3323284584564394,"score_spread":0.3103958510519053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393270996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0357199,0.024967093,0.92432344,0.008220217,0.0010024097,0.00053623156,0.000013047274,0.0012385916,0.003979096],"genre_scores_gemma":[0.8457483,0.000084881765,0.153393,0.00024665715,0.00004377086,0.00004397282,0.000014609691,0.000028150753,0.0003966511],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985318,0.00020501063,0.00023023064,0.00046482106,0.00021970259,0.0003484166],"domain_scores_gemma":[0.9975378,0.00027437028,0.000099127334,0.0018600709,0.00013933175,0.00008932433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003302763,0.00018220428,0.0001731113,0.00026876805,0.0012436961,0.00037103158,0.0022412827,0.00021428584,0.0000065464797],"category_scores_gemma":[0.000041658317,0.00018263861,0.000052402214,0.0013722206,0.00016138212,0.00048463428,0.001056226,0.0016996976,0.00004534106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036696187,0.00038263257,0.008603706,0.00040298855,0.00034233808,0.00012510722,0.06089901,0.017208597,0.652821,0.08153899,0.017513368,0.16012555],"study_design_scores_gemma":[0.00044081928,0.00026906963,0.0044075963,0.00049211277,0.000047485322,0.00029911057,0.0016993098,0.09678644,0.01791102,0.0021463516,0.8745571,0.000943629],"about_ca_topic_score_codex":0.00013322687,"about_ca_topic_score_gemma":0.0008053561,"teacher_disagreement_score":0.8570437,"about_ca_system_score_codex":0.0003217883,"about_ca_system_score_gemma":0.000073986164,"threshold_uncertainty_score":0.95656306},"labels":[],"label_agreement":null},{"id":"W4393300106","doi":"10.1117/12.3006049","title":"Benchmarking image transformers for prostate cancer detection from ultrasound data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Benchmarking; Prostate cancer; Ultrasound; Cancer detection; Computer science; Artificial intelligence; Medicine; Radiology; Medical physics; Computer vision; Cancer; Internal medicine; Business","score_opus":0.03373899678156435,"score_gpt":0.31141567389307606,"score_spread":0.2776766771115117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393300106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039722207,0.0011725513,0.97865677,0.0009206015,0.010658173,0.0013742978,0.0014402872,0.000704289,0.001100795],"genre_scores_gemma":[0.7326725,0.0023730267,0.25700137,0.00039189323,0.003285755,0.002177676,0.00093517255,0.00015927231,0.0010033384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99685687,0.00004422173,0.0004288048,0.0018829142,0.00037945798,0.00040774493],"domain_scores_gemma":[0.9980238,0.00023520284,0.00016654274,0.0013557639,0.00012391713,0.000094781026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004768028,0.00037665258,0.0003085065,0.00018135982,0.00016549941,0.0009595549,0.0017254802,0.00029287292,0.00008009325],"category_scores_gemma":[0.000029433482,0.00036093706,0.00015412476,0.0002894488,0.00005633678,0.0006933297,0.0016145646,0.00080017326,0.000024486528],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041545532,0.000016816939,0.000016346094,0.0005052383,0.00025129406,0.0000037978768,0.0009612981,0.0005652785,0.015489902,0.00008253962,0.0041420734,0.97792387],"study_design_scores_gemma":[0.0003951689,0.00009949731,0.0001608382,0.00044286228,0.00021522232,0.000008964248,0.000078322446,0.8544935,0.06853789,0.052414447,0.02227652,0.00087677076],"about_ca_topic_score_codex":0.006734909,"about_ca_topic_score_gemma":0.006340362,"teacher_disagreement_score":0.9770471,"about_ca_system_score_codex":0.00054150686,"about_ca_system_score_gemma":0.0004572082,"threshold_uncertainty_score":0.99988425},"labels":[],"label_agreement":null},{"id":"W4393317705","doi":"10.6000/1929-6029.2024.13.04","title":"Adaptive Elastic Net on High-Dimensional Sparse Data with Multicollinearity: Application to Lipomatous Tumor Classification","year":2024,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Siriraj Foundation","keywords":"Multicollinearity; Elastic net regularization; Net (polyhedron); Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics; Statistics; Feature selection; Regression analysis; Geometry","score_opus":0.09876984620822425,"score_gpt":0.43053498212556957,"score_spread":0.3317651359173453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393317705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056177927,0.000067099485,0.984357,0.008481911,0.00096534635,0.00022115443,0.0001213534,0.000023756631,0.00014459057],"genre_scores_gemma":[0.866884,0.000051109473,0.1320969,0.00028155211,0.00057800784,0.000026031576,0.000028276228,0.000015883745,0.000038256963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934383,0.00025755356,0.00057535595,0.00045966124,0.005002316,0.0002667851],"domain_scores_gemma":[0.99484473,0.002928384,0.00013057164,0.00042565886,0.0013689505,0.00030167412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034569,0.0001162915,0.00017346357,0.00088390737,0.00006270247,0.00026025713,0.0023287733,0.00007243819,0.00006360302],"category_scores_gemma":[0.003012505,0.00009261163,0.000017930935,0.00077381264,0.0001631626,0.00037580155,0.0004975467,0.0011804826,0.00013113992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096305955,0.00050041126,0.00020899402,0.00004009986,0.00016192748,0.0036582618,0.0002835851,0.010305894,0.0003836715,0.23619367,0.022633597,0.72466683],"study_design_scores_gemma":[0.00051563885,0.00068747526,0.0035957422,0.0005826347,0.0000055416886,0.00031198302,0.000040080584,0.97818726,0.0001258193,0.008427469,0.0074193836,0.00010094966],"about_ca_topic_score_codex":0.0001770497,"about_ca_topic_score_gemma":0.00024700846,"teacher_disagreement_score":0.9678814,"about_ca_system_score_codex":0.0007036715,"about_ca_system_score_gemma":0.0014060711,"threshold_uncertainty_score":0.5128675},"labels":[],"label_agreement":null},{"id":"W4393333906","doi":"10.1016/j.bspc.2024.106255","title":"Gan-based data augmentation to improve breast ultrasound and mammography mass classification","year":2024,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mammography; Computer science; Ultrasound; Breast ultrasound; Medicine; Artificial intelligence; Breast cancer; Medical physics; Radiology; Internal medicine; Cancer","score_opus":0.0153357221304948,"score_gpt":0.2674335946052457,"score_spread":0.2520978724747509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393333906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022342415,0.0011794142,0.9911288,0.004753832,0.00021414993,0.00018569059,0.000055756525,0.00020435246,0.000043771943],"genre_scores_gemma":[0.9948948,0.000011048945,0.0042015268,0.0005725041,0.00023136724,0.00004057092,0.000025000474,0.000009015008,0.000014180379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861425,0.000046045883,0.00019394752,0.0006123889,0.0003418747,0.00019151274],"domain_scores_gemma":[0.9993276,0.00015940922,0.000048155725,0.00021798548,0.00004746033,0.00019937166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000436011,0.000119996585,0.00011186998,0.00016432707,0.00015956371,0.0006723686,0.00030530468,0.00007746618,0.0000075110165],"category_scores_gemma":[0.000019231491,0.00010004927,0.000017509956,0.00050640514,0.00012950701,0.0004994198,0.000026245523,0.00012292467,0.0000053623053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034690416,0.000019230858,0.0001771786,0.00011830724,0.000015307332,0.0000036881756,0.000070465736,0.0000036284566,0.12552334,0.00009508827,0.0002800518,0.873659],"study_design_scores_gemma":[0.00080948544,0.00021944933,0.0039896746,0.00018193068,0.00004809323,0.000042397787,0.00005113483,0.9869931,0.0012301443,0.001318041,0.00490331,0.0002132791],"about_ca_topic_score_codex":0.000023671671,"about_ca_topic_score_gemma":0.000002119067,"teacher_disagreement_score":0.9926605,"about_ca_system_score_codex":0.000040786086,"about_ca_system_score_gemma":0.00014548792,"threshold_uncertainty_score":0.64836663},"labels":[],"label_agreement":null},{"id":"W4393555909","doi":"10.5281/zenodo.7981074","title":"UV-PARS Virtual Histology","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Histology; Medicine; Pathology","score_opus":0.03938524423875045,"score_gpt":0.2587159470315528,"score_spread":0.21933070279280237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393555909","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012866437,0.000082754945,0.037749186,0.0013424901,0.0026691929,0.0005841877,0.94417024,0.003621211,0.009767889],"genre_scores_gemma":[0.0000849474,0.00043762286,0.0003803227,0.00028619054,0.000499681,1.3992589e-7,0.99530965,0.0014613406,0.0015401082],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969021,0.00052010565,0.0003793674,0.0009711454,0.00066132995,0.00056593464],"domain_scores_gemma":[0.9974342,0.00006267938,0.00026036164,0.0015830953,0.00045319126,0.00020644536],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007784214,0.00027775776,0.00028754812,0.0006509184,0.001954851,0.0010655442,0.004860255,0.00027067988,0.00317649],"category_scores_gemma":[0.0006552243,0.00032124968,0.0000928841,0.0012306079,0.00021807083,0.00038527916,0.0048339395,0.00078547467,0.11927384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013634592,0.000040835144,2.34192e-8,0.000044945788,0.000037173653,0.000048631297,0.0000938876,0.000038434053,0.000038209993,0.0007163008,0.94419366,0.05473424],"study_design_scores_gemma":[0.00024400296,0.00037816117,0.00001757634,0.000031011776,0.00001570337,0.00020247865,0.00002340881,0.0004404707,0.000028613385,0.00017234728,0.9981359,0.00031028484],"about_ca_topic_score_codex":0.0001116276,"about_ca_topic_score_gemma":0.0000026254838,"teacher_disagreement_score":0.116097346,"about_ca_system_score_codex":0.0006089695,"about_ca_system_score_gemma":0.000015506837,"threshold_uncertainty_score":0.99997145},"labels":[],"label_agreement":null},{"id":"W4393588685","doi":"10.5281/zenodo.7742473","title":"Dataset: CODEX highly multiplexed tissue imaging in pancreas","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pancreas; Multiplexing; Computer science; Computer graphics (images); Medicine; Internal medicine; Telecommunications","score_opus":0.033971942394430965,"score_gpt":0.27537336616983743,"score_spread":0.24140142377540647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393588685","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010864111,0.000100063306,0.006449239,0.0007803782,0.0006852124,0.0006093645,0.98943114,0.0011906675,0.0007430436],"genre_scores_gemma":[0.00022847373,0.00030404155,0.0005822954,0.00021515563,0.00028374977,2.456449e-7,0.997076,0.0011158317,0.00019425481],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640477,0.0005762786,0.0004857599,0.0011351536,0.00074121216,0.000656817],"domain_scores_gemma":[0.9972629,0.00007899351,0.0002607646,0.0018816157,0.00030691133,0.00020880974],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011622346,0.00032651878,0.0003148851,0.0008619612,0.0012267655,0.0016635965,0.004639677,0.00015793931,0.0012297871],"category_scores_gemma":[0.00075421564,0.00038153303,0.00004813387,0.0016315429,0.00014667139,0.0007141243,0.0050856466,0.00075956364,0.05088201],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018486144,0.000057805963,2.8051358e-7,0.00008865067,0.000015736177,0.00012653941,0.00008654413,0.00006212768,0.00040341748,0.00008637589,0.95103824,0.048015773],"study_design_scores_gemma":[0.0004909102,0.00009135764,0.000099417965,0.000098234705,0.000011565583,0.00011659358,0.000028425797,0.0018246253,0.00013634174,0.00009969333,0.9966207,0.00038213588],"about_ca_topic_score_codex":0.0010180365,"about_ca_topic_score_gemma":0.000024652163,"teacher_disagreement_score":0.049652223,"about_ca_system_score_codex":0.00055719254,"about_ca_system_score_gemma":0.000015990838,"threshold_uncertainty_score":0.9998637},"labels":[],"label_agreement":null},{"id":"W4393599010","doi":"10.5281/zenodo.7742474","title":"Dataset: CODEX highly multiplexed tissue imaging in pancreas","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multiplexing; Computer science; Pancreas; Computer graphics (images); Computational biology; Biology; Medicine; Internal medicine; Telecommunications","score_opus":0.033971942394430965,"score_gpt":0.27537336616983743,"score_spread":0.24140142377540647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393599010","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010864111,0.000100063306,0.006449239,0.0007803782,0.0006852124,0.0006093645,0.98943114,0.0011906675,0.0007430436],"genre_scores_gemma":[0.00022847373,0.00030404155,0.0005822954,0.00021515563,0.00028374977,2.456449e-7,0.997076,0.0011158317,0.00019425481],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640477,0.0005762786,0.0004857599,0.0011351536,0.00074121216,0.000656817],"domain_scores_gemma":[0.9972629,0.00007899351,0.0002607646,0.0018816157,0.00030691133,0.00020880974],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011622346,0.00032651878,0.0003148851,0.0008619612,0.0012267655,0.0016635965,0.004639677,0.00015793931,0.0012297871],"category_scores_gemma":[0.00075421564,0.00038153303,0.00004813387,0.0016315429,0.00014667139,0.0007141243,0.0050856466,0.00075956364,0.05088201],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018486144,0.000057805963,2.8051358e-7,0.00008865067,0.000015736177,0.00012653941,0.00008654413,0.00006212768,0.00040341748,0.00008637589,0.95103824,0.048015773],"study_design_scores_gemma":[0.0004909102,0.00009135764,0.000099417965,0.000098234705,0.000011565583,0.00011659358,0.000028425797,0.0018246253,0.00013634174,0.00009969333,0.9966207,0.00038213588],"about_ca_topic_score_codex":0.0010180365,"about_ca_topic_score_gemma":0.000024652163,"teacher_disagreement_score":0.049652223,"about_ca_system_score_codex":0.00055719254,"about_ca_system_score_gemma":0.000015990838,"threshold_uncertainty_score":0.9998637},"labels":[],"label_agreement":null},{"id":"W4393609853","doi":"10.5281/zenodo.6382975","title":"Clinical Dataset SE objects - GSE20194","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Computer science; Cartography; Artificial intelligence; Geography","score_opus":0.07652695166620381,"score_gpt":0.3264504886732548,"score_spread":0.249923537007051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393609853","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007494461,0.00009799286,0.0050617363,0.0002991902,0.0014218133,0.0005095436,0.988875,0.00091621565,0.002811037],"genre_scores_gemma":[0.000055970493,0.0005536108,0.0003949614,0.00063273055,0.00046082688,1.2569477e-7,0.9967949,0.00089522824,0.00021168054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950453,0.0014271453,0.0006282392,0.0013064333,0.0010211813,0.0005716928],"domain_scores_gemma":[0.99601656,0.00009161319,0.0004225354,0.0028386596,0.00032131042,0.00030930302],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0021987418,0.0003202036,0.00035867296,0.00045444208,0.0030523054,0.0016828215,0.0071370313,0.0002225996,0.09980321],"category_scores_gemma":[0.0008282923,0.00036643146,0.00012677097,0.0011025798,0.00020762393,0.0006227306,0.011413507,0.0014975836,0.01408762],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026617054,0.00014304365,8.2063075e-8,0.00006501504,0.0000540098,0.00005205351,0.00014221681,0.000023915365,0.0000053787003,0.000089474954,0.96268356,0.036714613],"study_design_scores_gemma":[0.0004008631,0.0005194153,0.000011959318,0.000022870163,0.000033449473,0.00017649877,0.00006461588,0.00019983851,0.000008103436,0.00007745735,0.99810433,0.00038057743],"about_ca_topic_score_codex":0.00011509132,"about_ca_topic_score_gemma":0.000002443871,"teacher_disagreement_score":0.085715584,"about_ca_system_score_codex":0.00044969766,"about_ca_system_score_gemma":0.000027687722,"threshold_uncertainty_score":0.99987876},"labels":[],"label_agreement":null},{"id":"W4393629454","doi":"10.5281/zenodo.8115040","title":"UV-PARS Virtual Histology","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Histology; Computer science; Biology","score_opus":0.03938524423875045,"score_gpt":0.2587159470315528,"score_spread":0.21933070279280237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393629454","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012866437,0.000082754945,0.037749186,0.0013424901,0.0026691929,0.0005841877,0.94417024,0.003621211,0.009767889],"genre_scores_gemma":[0.0000849474,0.00043762286,0.0003803227,0.00028619054,0.000499681,1.3992589e-7,0.99530965,0.0014613406,0.0015401082],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969021,0.00052010565,0.0003793674,0.0009711454,0.00066132995,0.00056593464],"domain_scores_gemma":[0.9974342,0.00006267938,0.00026036164,0.0015830953,0.00045319126,0.00020644536],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007784214,0.00027775776,0.00028754812,0.0006509184,0.001954851,0.0010655442,0.004860255,0.00027067988,0.00317649],"category_scores_gemma":[0.0006552243,0.00032124968,0.0000928841,0.0012306079,0.00021807083,0.00038527916,0.0048339395,0.00078547467,0.11927384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013634592,0.000040835144,2.34192e-8,0.000044945788,0.000037173653,0.000048631297,0.0000938876,0.000038434053,0.000038209993,0.0007163008,0.94419366,0.05473424],"study_design_scores_gemma":[0.00024400296,0.00037816117,0.00001757634,0.000031011776,0.00001570337,0.00020247865,0.00002340881,0.0004404707,0.000028613385,0.00017234728,0.9981359,0.00031028484],"about_ca_topic_score_codex":0.0001116276,"about_ca_topic_score_gemma":0.0000026254838,"teacher_disagreement_score":0.116097346,"about_ca_system_score_codex":0.0006089695,"about_ca_system_score_gemma":0.000015506837,"threshold_uncertainty_score":0.99997145},"labels":[],"label_agreement":null},{"id":"W4393829929","doi":"10.5281/zenodo.10535022","title":"HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pipeline (software); Histology; Computer science; Placenta; Artificial intelligence; Biology; Medicine; Pathology; Pregnancy","score_opus":0.023841463822312087,"score_gpt":0.27411477614960356,"score_spread":0.25027331232729144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393829929","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020561392,0.00064708677,0.47830886,0.0019269257,0.0014380851,0.0013446336,0.5128332,0.0018108313,0.0016698096],"genre_scores_gemma":[0.0011512694,0.0004450256,0.0074750492,0.0006079907,0.00083008263,0.0000023917269,0.9818291,0.0026126024,0.005046482],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960954,0.00043244314,0.000554856,0.0014317929,0.0005741578,0.00091135927],"domain_scores_gemma":[0.99745697,0.00011653773,0.0003044588,0.0011740315,0.00064779737,0.0003002353],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012403795,0.00041947237,0.00041917476,0.0007134846,0.0027283975,0.0022783673,0.0036328048,0.00026932027,0.0012120266],"category_scores_gemma":[0.0008608433,0.0004833206,0.00013506065,0.0013999616,0.00016497076,0.00041870857,0.004838812,0.0010816379,0.026580771],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003881182,0.000052501608,9.6724854e-8,0.00043505663,0.000034635774,0.000041145664,0.00082867267,0.00029029537,0.0015793063,0.00007358527,0.9208282,0.07579769],"study_design_scores_gemma":[0.00037514948,0.00040096338,0.0000034966874,0.00013657754,0.000029841243,0.00017764998,0.0002466725,0.003224376,0.0006297546,0.00017703968,0.99412155,0.00047695526],"about_ca_topic_score_codex":0.00008088811,"about_ca_topic_score_gemma":0.000008018556,"teacher_disagreement_score":0.4708338,"about_ca_system_score_codex":0.00059924694,"about_ca_system_score_gemma":0.00001676659,"threshold_uncertainty_score":0.9997618},"labels":[],"label_agreement":null},{"id":"W4393843868","doi":"10.5281/zenodo.10535021","title":"HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pipeline (software); Histology; Placenta; Computer science; Artificial intelligence; Biology; Pathology; Medicine; Pregnancy; Fetus","score_opus":0.023841463822312087,"score_gpt":0.27411477614960356,"score_spread":0.25027331232729144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393843868","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020561392,0.00064708677,0.47830886,0.0019269257,0.0014380851,0.0013446336,0.5128332,0.0018108313,0.0016698096],"genre_scores_gemma":[0.0011512694,0.0004450256,0.0074750492,0.0006079907,0.00083008263,0.0000023917269,0.9818291,0.0026126024,0.005046482],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960954,0.00043244314,0.000554856,0.0014317929,0.0005741578,0.00091135927],"domain_scores_gemma":[0.99745697,0.00011653773,0.0003044588,0.0011740315,0.00064779737,0.0003002353],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012403795,0.00041947237,0.00041917476,0.0007134846,0.0027283975,0.0022783673,0.0036328048,0.00026932027,0.0012120266],"category_scores_gemma":[0.0008608433,0.0004833206,0.00013506065,0.0013999616,0.00016497076,0.00041870857,0.004838812,0.0010816379,0.026580771],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003881182,0.000052501608,9.6724854e-8,0.00043505663,0.000034635774,0.000041145664,0.00082867267,0.00029029537,0.0015793063,0.00007358527,0.9208282,0.07579769],"study_design_scores_gemma":[0.00037514948,0.00040096338,0.0000034966874,0.00013657754,0.000029841243,0.00017764998,0.0002466725,0.003224376,0.0006297546,0.00017703968,0.99412155,0.00047695526],"about_ca_topic_score_codex":0.00008088811,"about_ca_topic_score_gemma":0.000008018556,"teacher_disagreement_score":0.4708338,"about_ca_system_score_codex":0.00059924694,"about_ca_system_score_gemma":0.00001676659,"threshold_uncertainty_score":0.9997618},"labels":[],"label_agreement":null},{"id":"W4393860463","doi":"10.32920/24624879","title":"Telepathology Implementation Challenges and Benefits: A Scoping Review","year":2024,"lang":"en","type":"review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Telepathology; Computer science; Business; Process management; Political science; Telemedicine; Health care; Law","score_opus":0.16839219601785663,"score_gpt":0.43999734684239616,"score_spread":0.2716051508245395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393860463","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3432846e-9,0.9934514,0.003200685,0.0006064036,0.0005402314,0.0012164133,0.0000028685674,0.00024269936,0.0007392743],"genre_scores_gemma":[2.7909087e-8,0.9953453,0.0038391938,0.00018784458,0.00011749763,0.00044366834,0.000005318212,0.000021852125,0.000039316277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831015,0.00013487846,0.0004982558,0.0007072004,0.00015130604,0.00019818709],"domain_scores_gemma":[0.9991879,0.00008111249,0.00018850343,0.00046367876,0.00003175105,0.00004706369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046895965,0.00026827177,0.00092508463,0.00017455909,0.000042144988,0.00007985493,0.00038820592,0.0001243597,0.000025472698],"category_scores_gemma":[0.000012554519,0.00020116281,0.00014096113,0.00028182656,0.000019002202,0.00023031056,0.00044094768,0.00020197743,0.00010937639],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.0552282e-8,0.0000010671843,5.0792845e-9,0.19323279,0.000014199769,0.0000036045772,0.00002339245,6.393777e-9,2.82932e-9,0.005563483,0.00019459924,0.8009668],"study_design_scores_gemma":[0.000022639242,0.00005213453,1.4934686e-7,0.4502003,0.00030165052,0.0003011665,0.0000045665283,0.0000059075514,2.908987e-7,0.00039455536,0.54850715,0.00020950497],"about_ca_topic_score_codex":0.000005386272,"about_ca_topic_score_gemma":0.000089100344,"teacher_disagreement_score":0.80075735,"about_ca_system_score_codex":0.000099990175,"about_ca_system_score_gemma":0.0002081327,"threshold_uncertainty_score":0.8203181},"labels":[],"label_agreement":null},{"id":"W4393903088","doi":"10.32920/24624879.v1","title":"Telepathology Implementation Challenges and Benefits: A Scoping Review","year":2024,"lang":"en","type":"review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Telepathology; Computer science; Operations research; Risk analysis (engineering); Engineering; Business; Telemedicine; Political science; Health care","score_opus":0.16839219601785663,"score_gpt":0.43999734684239616,"score_spread":0.2716051508245395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393903088","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3432846e-9,0.9934514,0.003200685,0.0006064036,0.0005402314,0.0012164133,0.0000028685674,0.00024269936,0.0007392743],"genre_scores_gemma":[2.7909087e-8,0.9953453,0.0038391938,0.00018784458,0.00011749763,0.00044366834,0.000005318212,0.000021852125,0.000039316277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831015,0.00013487846,0.0004982558,0.0007072004,0.00015130604,0.00019818709],"domain_scores_gemma":[0.9991879,0.00008111249,0.00018850343,0.00046367876,0.00003175105,0.00004706369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046895965,0.00026827177,0.00092508463,0.00017455909,0.000042144988,0.00007985493,0.00038820592,0.0001243597,0.000025472698],"category_scores_gemma":[0.000012554519,0.00020116281,0.00014096113,0.00028182656,0.000019002202,0.00023031056,0.00044094768,0.00020197743,0.00010937639],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.0552282e-8,0.0000010671843,5.0792845e-9,0.19323279,0.000014199769,0.0000036045772,0.00002339245,6.393777e-9,2.82932e-9,0.005563483,0.00019459924,0.8009668],"study_design_scores_gemma":[0.000022639242,0.00005213453,1.4934686e-7,0.4502003,0.00030165052,0.0003011665,0.0000045665283,0.0000059075514,2.908987e-7,0.00039455536,0.54850715,0.00020950497],"about_ca_topic_score_codex":0.000005386272,"about_ca_topic_score_gemma":0.000089100344,"teacher_disagreement_score":0.80075735,"about_ca_system_score_codex":0.000099990175,"about_ca_system_score_gemma":0.0002081327,"threshold_uncertainty_score":0.8203181},"labels":[],"label_agreement":null},{"id":"W4393982763","doi":"10.1101/2024.04.03.24305251","title":"Using Deep Learning to Automate Eosinophil Counting in Pediatric Ulcerative Colitis Histopathological Images","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"National Institutes of Health","keywords":"Ulcerative colitis; Eosinophil; Artificial intelligence; Computer science; Medicine; Pathology; Internal medicine; Asthma","score_opus":0.0299662444894978,"score_gpt":0.2943951983450407,"score_spread":0.2644289538555429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393982763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83097726,0.00075447164,0.1621479,0.00053854944,0.003271251,0.00041318932,0.000004555507,0.00079335016,0.0010994844],"genre_scores_gemma":[0.95477074,0.00010455737,0.04408568,0.00011962712,0.0006251113,0.00010771953,0.0000019637578,0.000040829953,0.00014377142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674785,0.00040946202,0.00053298334,0.001301293,0.00048052467,0.00052788213],"domain_scores_gemma":[0.9988213,0.00014888252,0.00024250952,0.0005275304,0.00014343955,0.0001162922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012570975,0.00036620843,0.0004465981,0.00065073505,0.0001730989,0.0005172579,0.0009208743,0.00029617088,0.000014888918],"category_scores_gemma":[0.0002844716,0.00038269346,0.00011642781,0.00097337755,0.000050872277,0.00018755157,0.0031858662,0.0016557204,0.00011679371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012161606,0.00024315073,0.30018672,0.0033451468,0.00008686002,0.0064161066,0.031117162,0.5107058,0.005638644,0.004294086,0.00069055415,0.13715412],"study_design_scores_gemma":[0.00022499598,0.0001493242,0.34689975,0.00044397556,0.00006043244,0.00015266413,0.00007091624,0.6376994,0.0013151678,0.011337892,0.00060395093,0.0010415281],"about_ca_topic_score_codex":0.00016548141,"about_ca_topic_score_gemma":0.00008567804,"teacher_disagreement_score":0.13611259,"about_ca_system_score_codex":0.0011179296,"about_ca_system_score_gemma":0.00023837862,"threshold_uncertainty_score":0.9998625},"labels":[],"label_agreement":null},{"id":"W4393992991","doi":"10.3390/s24072312","title":"Advancing Breast Cancer Diagnosis through Breast Mass Images, Machine Learning, and Regression Models","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Support vector machine; Artificial intelligence; Naive Bayes classifier; Machine learning; Decision tree; Breast cancer; Computer science; Classifier (UML); Cross-validation; Computer-aided diagnosis; Cancer; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.009837236044524375,"score_gpt":0.26904943620935157,"score_spread":0.2592122001648272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393992991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11596823,0.044161428,0.79041123,0.0328264,0.0056759976,0.0008118275,0.0004200794,0.0037053868,0.0060194214],"genre_scores_gemma":[0.97148854,0.0073846965,0.0190875,0.0001602926,0.0003609956,0.00009497722,0.000003959088,0.0000534562,0.0013655799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846786,0.000092590984,0.00018201709,0.00062555645,0.00029283945,0.00033910942],"domain_scores_gemma":[0.99940395,0.00010750147,0.000064383654,0.00027072668,0.00006018545,0.000093219416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017017915,0.00020861543,0.00017374125,0.00009782715,0.00019977338,0.00024196123,0.00021997667,0.00007936088,0.00007160673],"category_scores_gemma":[0.000010226298,0.00017329595,0.000058766993,0.00042389092,0.00005941434,0.0010195852,0.00017774072,0.00036535843,0.000021030546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049667564,0.000041569565,0.011284876,0.00034944323,0.00010669925,0.0002502648,0.0029303632,0.04065839,0.003921191,0.0029236015,0.008463767,0.92902017],"study_design_scores_gemma":[0.00024220356,0.000050280367,0.0010787586,0.00065097306,0.000028048524,0.0006732881,0.00008645662,0.9652232,0.004660531,0.0054281377,0.021478947,0.00039915278],"about_ca_topic_score_codex":0.00094483,"about_ca_topic_score_gemma":0.00007051322,"teacher_disagreement_score":0.928621,"about_ca_system_score_codex":0.00020348211,"about_ca_system_score_gemma":0.000053415813,"threshold_uncertainty_score":0.7066804},"labels":[],"label_agreement":null},{"id":"W4394020581","doi":"10.5281/zenodo.1238084","title":"Visualizing Histopathologic Deep Learning Classification And Anomaly Detection Using Nonlinear Feature Space Dimensionality Reduction","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Dimensionality reduction; Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Anomaly (physics); Nonlinear dimensionality reduction; Reduction (mathematics); Feature (linguistics); Computer science; Curse of dimensionality; Space (punctuation); Feature vector; Mathematics; Physics; Philosophy; Quantum mechanics; Geometry","score_opus":0.047184602433285136,"score_gpt":0.28357726490318613,"score_spread":0.23639266246990098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394020581","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03921767,0.0021164203,0.60334104,0.0024567032,0.0070637153,0.00430736,0.33017337,0.008393633,0.0029300805],"genre_scores_gemma":[0.038764264,0.000954278,0.018532826,0.00012964352,0.0022729773,5.261112e-7,0.9372873,0.0017046637,0.0003535738],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966241,0.0009541189,0.00033779067,0.0011149944,0.0005703643,0.0003986479],"domain_scores_gemma":[0.9976399,0.000030883366,0.00053034944,0.00082837464,0.000809264,0.00016124005],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012529261,0.0003090842,0.00026148962,0.00049977936,0.0040454823,0.0011648565,0.0010259005,0.0003606431,0.00029622825],"category_scores_gemma":[0.0005899127,0.00034684825,0.00006752168,0.00092032034,0.00027021853,0.00071304024,0.0015944918,0.0009230923,0.0005070199],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011439998,0.00014500353,0.0000019959114,0.00029007965,0.000059074548,0.000023962271,0.0004926498,0.00022534371,0.034396656,0.00021787222,0.8835473,0.08048566],"study_design_scores_gemma":[0.0002159494,0.000375323,0.00024773797,0.000067624096,0.000040318897,0.00081631,0.00008560495,0.029320255,0.00062216586,0.000078102275,0.96778697,0.00034366635],"about_ca_topic_score_codex":0.000075433905,"about_ca_topic_score_gemma":0.0000025000181,"teacher_disagreement_score":0.6071139,"about_ca_system_score_codex":0.00087638735,"about_ca_system_score_gemma":0.000012125828,"threshold_uncertainty_score":0.9998984},"labels":[],"label_agreement":null},{"id":"W4394692788","doi":"10.1007/s11548-024-03104-3","title":"LensePro: label noise-tolerant prototype-based network for improving cancer detection in prostate ultrasound with limited annotations","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Ultrasound; Prostate cancer; Noise (video); Cancer detection; Cancer; Medicine; Artificial intelligence; Radiology; Internal medicine","score_opus":0.01757174294646738,"score_gpt":0.26675021382128594,"score_spread":0.24917847087481856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394692788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22961068,0.0009880104,0.7641861,0.0016060608,0.0032800096,0.0002695575,0.000006935604,0.0000488517,0.000003803529],"genre_scores_gemma":[0.9672555,0.000084000865,0.03128437,0.00043558888,0.00079395436,0.00011812159,0.0000058554842,0.000014694884,0.000007927353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986609,0.00013813231,0.0004981781,0.00027841935,0.00021155704,0.00021279579],"domain_scores_gemma":[0.99780065,0.0013187362,0.0002762721,0.00009903675,0.00045064578,0.000054636555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007352762,0.00014221846,0.0002600339,0.00041651103,0.00008610796,0.00020686915,0.00022766102,0.00008135365,0.0000020092273],"category_scores_gemma":[0.000040292438,0.00011513127,0.000089871086,0.00036709456,0.00007095384,0.00050789106,0.00002255299,0.00029051368,4.030899e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020965673,0.00016285208,0.028256087,0.00019790936,0.00066824385,0.0004894945,0.00070695305,0.07234836,0.0039393744,0.000495363,0.0012005193,0.8894383],"study_design_scores_gemma":[0.0015517144,0.0007334755,0.07892375,0.0007566317,0.000046868354,0.0029728783,0.000011335566,0.9096156,0.0012244233,0.0009823284,0.0028714696,0.00030957293],"about_ca_topic_score_codex":0.00002468064,"about_ca_topic_score_gemma":0.0000756934,"teacher_disagreement_score":0.8891287,"about_ca_system_score_codex":0.0001885358,"about_ca_system_score_gemma":0.00041175145,"threshold_uncertainty_score":0.4694917},"labels":[],"label_agreement":null},{"id":"W4394727442","doi":"10.1038/s41598-024-57740-5","title":"Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"King Saud University","keywords":"Machine learning; Artificial intelligence; Computer science; Decision tree; Random forest; Naive Bayes classifier; Context (archaeology); Logistic regression; Precision and recall; Decision tree learning; Breast cancer; Field (mathematics); Support vector machine; Cancer; Medicine; Mathematics","score_opus":0.026228362396232868,"score_gpt":0.25029994291768626,"score_spread":0.2240715805214534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394727442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20938073,0.00030593062,0.7878679,0.00022579049,0.0012129619,0.0008271922,0.00004747186,0.000056504643,0.00007548995],"genre_scores_gemma":[0.99776226,0.0000058212695,0.0017622561,0.00001457923,0.000015449361,0.00021485423,0.000040225463,0.000010565748,0.00017397443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821675,0.00007284267,0.0004082391,0.00060049404,0.00052147877,0.0001802158],"domain_scores_gemma":[0.9987934,0.00006902312,0.00025863867,0.000470655,0.00038144417,0.000026802292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011427471,0.000100675476,0.00014038348,0.00017674571,0.00013876027,0.00025929054,0.00023716257,0.00004349706,0.0000023107025],"category_scores_gemma":[0.000045551562,0.000069001486,0.00004519067,0.000902034,0.000111312744,0.0009267033,0.000049450482,0.00015473507,1.6271957e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043599537,0.0011184511,0.09621555,0.0016911913,0.00022047634,0.00003182218,0.048727963,0.62106323,0.01585508,0.0036165705,0.016070636,0.19495302],"study_design_scores_gemma":[0.0001264166,0.00007718317,0.0006249048,0.0001336675,0.000013014696,0.00002199048,0.00033489362,0.9948854,0.0019417023,0.00042586253,0.0013367691,0.00007821491],"about_ca_topic_score_codex":0.00043482106,"about_ca_topic_score_gemma":0.000057079764,"teacher_disagreement_score":0.7883815,"about_ca_system_score_codex":0.00013630596,"about_ca_system_score_gemma":0.00018091216,"threshold_uncertainty_score":0.28137988},"labels":[],"label_agreement":null},{"id":"W4394881033","doi":"10.1364/ol.514077","title":"Simultaneous deep ultraviolet transmission and scattering microscopy for virtual histology","year":2024,"lang":"en","type":"article","venue":"Optics Letters","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alberta Innovates","keywords":"Histology; Ultraviolet; Virtual microscopy; Microscopy; Materials science; Scattering; Transmission (telecommunications); Transmission electron microscopy; Optics; Computer science; Optoelectronics; Nanotechnology; Physics; Medicine; Pathology; Telecommunications","score_opus":0.006972909518260879,"score_gpt":0.24737034501680677,"score_spread":0.2403974354985459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394881033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054249167,0.0003093267,0.93711704,0.0068587055,0.0011138499,0.00014018643,0.0000027541532,0.00016749711,0.000041465373],"genre_scores_gemma":[0.7179667,0.000093835675,0.27923784,0.0023702064,0.00018532666,0.000030436004,0.0000032035412,0.00002937133,0.000083099316],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991485,0.000017039245,0.00013957283,0.0003810613,0.00008873626,0.00022512418],"domain_scores_gemma":[0.9994571,0.0002611238,0.000022650951,0.00018372934,0.000016359989,0.000059033064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009384078,0.000118051226,0.000106860476,0.00008722187,0.000101458194,0.00016423533,0.00022942065,0.00006245911,0.0000029673722],"category_scores_gemma":[0.000010930126,0.00011893404,0.00004203577,0.00010582933,0.00007483843,0.00016865921,0.000037464775,0.00012243615,0.000007715558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001341513,0.000006356308,0.000004628166,0.00007287786,0.000014067905,0.00004131275,0.0007528221,0.0027550193,0.7753621,0.00079491624,0.0005142596,0.21966824],"study_design_scores_gemma":[0.0002629244,0.00022062348,0.000012616355,0.0000783498,0.000021249441,0.00018160052,0.000015894113,0.89933807,0.042106472,0.0002495283,0.057255268,0.00025743543],"about_ca_topic_score_codex":0.000005109934,"about_ca_topic_score_gemma":0.0000011055297,"teacher_disagreement_score":0.896583,"about_ca_system_score_codex":0.00009370581,"about_ca_system_score_gemma":0.000017776092,"threshold_uncertainty_score":0.48499894},"labels":[],"label_agreement":null},{"id":"W4394930478","doi":"10.7759/cureus.58496","title":"The Evaluation of Artificial Intelligence Technology for the Differentiation of Fresh Human Blood Cells From Other Species Blood in the Investigation of Crime Scenes","year":2024,"lang":"en","type":"article","venue":"Cureus","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern College","funders":"","keywords":"Human blood; Artificial intelligence; Computer science; Biology; Physiology","score_opus":0.090757621387777,"score_gpt":0.323457207660463,"score_spread":0.232699586272686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394930478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9009265,0.0031044828,0.09364373,0.00084961386,0.0007614015,0.0006251596,0.000013419166,0.00003045465,0.000045273402],"genre_scores_gemma":[0.9988454,0.00006402349,0.0009021413,0.000011482301,0.00009926285,0.000063503896,0.000002035987,0.0000060361535,0.0000060974935],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988388,0.00014653188,0.00036221367,0.00018392646,0.00037526523,0.00009325437],"domain_scores_gemma":[0.9985167,0.00055448187,0.00020651074,0.0004761685,0.00023994448,0.000006187261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010609212,0.00007639804,0.00009943067,0.00008833458,0.00009786979,0.000053520493,0.00071371644,0.00006991462,0.00001188666],"category_scores_gemma":[0.000131899,0.000043388955,0.000046584653,0.00055723323,0.00023458834,0.00012427031,0.00006534451,0.00009678754,8.346095e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010334129,0.00008225891,0.0007144795,0.000047394486,0.000107589425,1.1485351e-7,0.0052577844,0.00075155956,0.80603707,0.14757599,0.00009124759,0.03932415],"study_design_scores_gemma":[0.000051938634,0.00011004433,0.0034723647,0.000050507988,0.00011583654,3.5416642e-7,0.00048376658,0.050499078,0.7665714,0.17856452,0.000042074993,0.00003810305],"about_ca_topic_score_codex":0.00019635056,"about_ca_topic_score_gemma":0.00079117843,"teacher_disagreement_score":0.09791895,"about_ca_system_score_codex":0.00002737984,"about_ca_system_score_gemma":0.00007494024,"threshold_uncertainty_score":0.17693503},"labels":[],"label_agreement":null},{"id":"W4394933157","doi":"10.3390/curroncol31040169","title":"Deep Learning Prediction of Axillary Lymph Node Metastasis in Breast Cancer Patients Using Clinical Implication-Applied Preprocessed CT Images","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea","keywords":"Medicine; Breast cancer; Deep learning; Receiver operating characteristic; Convolutional neural network; Artificial intelligence; Radiology; Lymph node; Preprocessor; Computer science; Cancer; Pattern recognition (psychology); Pathology; Internal medicine","score_opus":0.07468558188072558,"score_gpt":0.4057143816285331,"score_spread":0.3310287997478075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394933157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72080755,0.0033518292,0.27019885,0.00033865124,0.0042765685,0.00044761944,0.000044442375,0.00027977617,0.00025471812],"genre_scores_gemma":[0.99665195,0.00081567693,0.0021713702,0.000021545797,0.00018927654,0.00011802703,0.000013851867,0.000015695372,0.0000026092755],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980893,0.00018509681,0.00063383754,0.0006303411,0.00022393414,0.00023745473],"domain_scores_gemma":[0.9990377,0.00020129453,0.00025631546,0.0002703103,0.00017284577,0.000061562874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056713086,0.00014127912,0.00029061918,0.00022935934,0.00006858448,0.000043140102,0.00034650363,0.00008161614,0.000019654666],"category_scores_gemma":[0.00005003331,0.00014027423,0.000078715726,0.0007307037,0.000090911875,0.00036269493,0.00021295172,0.00032368157,0.000008493426],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030020114,0.00026373478,0.2555828,0.00018830637,0.000039414706,0.0000018985396,0.00026431234,0.005895198,0.0007062181,0.000098688455,0.000088393164,0.736841],"study_design_scores_gemma":[0.001141168,0.00012988104,0.5358288,0.00021712352,0.00008861961,0.00003788205,0.00005309673,0.4556502,0.0015244834,0.0005033606,0.0045997994,0.00022555054],"about_ca_topic_score_codex":0.000064397704,"about_ca_topic_score_gemma":0.000006762505,"teacher_disagreement_score":0.7366155,"about_ca_system_score_codex":0.0006725708,"about_ca_system_score_gemma":0.00039282395,"threshold_uncertainty_score":0.5720217},"labels":[],"label_agreement":null},{"id":"W4395004524","doi":"10.1515/cclm-2023-1124","title":"Computational pathology: an evolving concept","year":2024,"lang":"en","type":"article","venue":"Clinical Chemistry and Laboratory Medicine (CCLM)","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Computer science; Pathology; Computational biology; Medicine; Biology","score_opus":0.03125122517656599,"score_gpt":0.3598386271981349,"score_spread":0.32858740202156894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395004524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46372524,0.02330298,0.4840813,0.013966014,0.006793969,0.0003235804,0.000057908994,0.0018712236,0.005877777],"genre_scores_gemma":[0.9907856,0.0001101798,0.0050987783,0.0016634006,0.002084567,0.000011101494,0.000019070021,0.000015096393,0.00021222403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983512,0.00012213549,0.00046121492,0.00064527575,0.0002342581,0.0001858952],"domain_scores_gemma":[0.99846685,0.0006593584,0.00007765018,0.00035444926,0.00019175472,0.00024992134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001004555,0.00015113597,0.00025227215,0.000020591227,0.0001088316,0.00007923098,0.00033387865,0.00019714619,0.00017560185],"category_scores_gemma":[0.00046665294,0.00012912875,0.00003669522,0.00036851977,0.0005591279,0.00042824788,0.00010798466,0.0005243024,0.000014504427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016611758,0.0007700026,0.016063957,0.0023051284,0.0005252836,0.0036917594,0.0097201215,0.0017663484,0.039441235,0.027207172,0.30258226,0.5957606],"study_design_scores_gemma":[0.00451424,0.0021108508,0.021552766,0.001528118,0.00021724869,0.00064208335,0.0010769786,0.66594416,0.011739781,0.044039324,0.24483962,0.0017948156],"about_ca_topic_score_codex":0.0000020994723,"about_ca_topic_score_gemma":4.1992104e-7,"teacher_disagreement_score":0.66417783,"about_ca_system_score_codex":0.000039389823,"about_ca_system_score_gemma":0.00023935374,"threshold_uncertainty_score":0.52657175},"labels":[],"label_agreement":null},{"id":"W4395029409","doi":"10.1101/2024.04.19.24306099","title":"Machine Learning-driven Histotype Diagnosis of Ovarian Carcinoma: Insights from the OCEAN AI Challenge","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; BC Cancer Foundation","keywords":"Ovarian carcinoma; Artificial intelligence; Computer science; Oceanography; Medicine; Ovarian cancer; Internal medicine; Geology; Cancer","score_opus":0.02178269431218645,"score_gpt":0.2400892485528591,"score_spread":0.21830655424067263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395029409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83362865,0.061650857,0.046833675,0.033261124,0.017098295,0.0013232215,0.00013194673,0.001239015,0.0048332163],"genre_scores_gemma":[0.9970308,0.00083381624,0.0011029515,0.0001758802,0.0005605744,0.00007103951,0.000019572297,0.000048844202,0.00015654574],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974544,0.000341926,0.00044254135,0.0009884345,0.0005326484,0.00024007332],"domain_scores_gemma":[0.99759024,0.00032927253,0.00030574793,0.0015534097,0.0001337838,0.00008753813],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025233455,0.00035489688,0.00043351157,0.00016789138,0.00014425337,0.00013070014,0.0021571426,0.00029903091,0.000052211413],"category_scores_gemma":[0.00008538334,0.00026664138,0.00023807991,0.0003528406,0.00011521769,0.000100538244,0.0030400937,0.001881015,0.00008611123],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014982998,0.0007533602,0.7162175,0.0019773622,0.0017603318,0.0007292699,0.07588357,0.02054095,0.0005122634,0.070259556,0.01528931,0.0959267],"study_design_scores_gemma":[0.000937095,0.0007364281,0.16049258,0.0012707755,0.0004922211,0.000017528935,0.00008405001,0.45754835,0.0057102605,0.19811586,0.1728187,0.0017761525],"about_ca_topic_score_codex":0.0026373214,"about_ca_topic_score_gemma":0.0005429636,"teacher_disagreement_score":0.5557249,"about_ca_system_score_codex":0.00025972188,"about_ca_system_score_gemma":0.00023099867,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W4395052875","doi":"10.1055/s-0044-1783005","title":"Variability in Computer-Aided Detection effect on Adenoma Detection Rate in randomized controlled trials: a meta-regression analysis","year":2024,"lang":"en","type":"article","venue":"Endoscopy","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Medicine; Meta-analysis; Meta-regression; Randomized controlled trial; Artificial intelligence; Adenoma; Regression; Regression analysis; Statistics; Internal medicine; Machine learning; Computer science","score_opus":0.025295385527697372,"score_gpt":0.3210378660950875,"score_spread":0.2957424805673901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395052875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1725223,0.0007193055,0.82067364,0.00020889865,0.002749258,0.002629658,0.0000023881719,0.00040737237,0.00008716432],"genre_scores_gemma":[0.99458593,0.00004995911,0.0028615852,0.000055801218,0.00029305575,0.002097738,0.0000027740696,0.000022785576,0.000030376032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9750868,0.0208902,0.0018464082,0.001234487,0.00052407285,0.0004180372],"domain_scores_gemma":[0.9744256,0.024136605,0.00051240355,0.0007684976,0.00006478385,0.000092118615],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.044609018,0.00051262876,0.0052040834,0.0023811827,0.000109774526,0.0004204365,0.0004306429,0.00024944489,0.000061772625],"category_scores_gemma":[0.004834232,0.0003158308,0.0023515595,0.0040759146,0.000063689804,0.0006201708,0.00010742843,0.000654976,0.000039070947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26198483,0.0005283761,0.00051096437,0.00040174817,0.022018773,0.00023912883,0.001810177,0.089904204,0.078101724,0.0008183191,0.000036637983,0.5436451],"study_design_scores_gemma":[0.08868828,0.0004584501,0.00052078103,0.000112743684,0.0025354035,0.00000221586,0.0000026098196,0.81782556,0.08739608,0.0021884388,0.000028626317,0.00024080163],"about_ca_topic_score_codex":0.00049379776,"about_ca_topic_score_gemma":0.00052920316,"teacher_disagreement_score":0.8220636,"about_ca_system_score_codex":0.0007901388,"about_ca_system_score_gemma":0.0000936853,"threshold_uncertainty_score":0.99992937},"labels":[],"label_agreement":null},{"id":"W4395074559","doi":"10.18280/ria.380207","title":"Mammographic Masses Descriptor for Breast Cancer Classification and Automatic Diagnosis","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Artificial intelligence; BI-RADS; Mammography; Pattern recognition (psychology); Medicine; Computer science; Cancer; Radiology; Internal medicine","score_opus":0.05331578384913945,"score_gpt":0.30000922739992403,"score_spread":0.24669344355078457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395074559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026934354,0.0040244283,0.9597039,0.0063708713,0.0017192397,0.0005238436,0.000037879745,0.00053868745,0.00014675291],"genre_scores_gemma":[0.985989,0.0013757239,0.011011451,0.0001106549,0.00019632613,0.0009406007,0.0000020112573,0.000023607421,0.00035063125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986138,0.00003636963,0.00032462445,0.0005968647,0.00014634202,0.0002820486],"domain_scores_gemma":[0.9990055,0.0003141032,0.00006832089,0.00042116258,0.00010270738,0.00008822729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031680326,0.00016001011,0.00015079061,0.00022451866,0.00018823527,0.0004464294,0.0003875255,0.00007969179,0.000093367715],"category_scores_gemma":[0.000036145102,0.00015435262,0.00009074743,0.00083897245,0.00008882209,0.0006040657,0.00007728816,0.00012232043,0.000060283914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047820554,0.000041535233,0.001965931,0.00047345756,0.000033850738,0.0000035825826,0.0008044003,0.0006541403,0.0026739254,0.029588936,0.002126009,0.96162945],"study_design_scores_gemma":[0.000019114543,0.000062712876,0.0018283189,0.00031936908,0.000025382533,0.00004880979,0.00016278369,0.9648574,0.012764197,0.0069136634,0.012792691,0.00020555338],"about_ca_topic_score_codex":0.00005212013,"about_ca_topic_score_gemma":0.000037948517,"teacher_disagreement_score":0.96420324,"about_ca_system_score_codex":0.00012124085,"about_ca_system_score_gemma":0.000072204624,"threshold_uncertainty_score":0.62943166},"labels":[],"label_agreement":null},{"id":"W4395077743","doi":"10.18280/ria.380237","title":"Using Deep Learning to Generate and Classify Thyroid Cytopathology Reports According to The Bethesda System","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Nuclear University MEPhI","keywords":"Cytopathology; Thyroid; Medicine; Medical physics; Computer science; Pathology; Artificial intelligence; Internal medicine; Cytology","score_opus":0.052641469023685036,"score_gpt":0.29902117242208953,"score_spread":0.24637970339840448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395077743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12870103,0.0011497128,0.86539435,0.001397239,0.0021205926,0.00030999494,4.8425153e-7,0.00031597482,0.00061062374],"genre_scores_gemma":[0.9814576,0.00003410106,0.017429663,0.00020705673,0.00037138053,0.000050384213,3.8660946e-7,0.000026055202,0.00042336783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796546,0.00016410365,0.00045775244,0.00081971014,0.00019203368,0.00040092538],"domain_scores_gemma":[0.99882054,0.00019254591,0.00009125969,0.0006696169,0.0000892229,0.00013682283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012426967,0.00018301498,0.00020240975,0.00021364432,0.00046484353,0.0005559036,0.00045321175,0.000083027735,0.000006044772],"category_scores_gemma":[0.00013651681,0.00015079316,0.00006494995,0.0011177313,0.000041980617,0.00027957762,0.00046844844,0.00033548693,0.00020467993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007631804,0.000008781101,0.00029857815,0.00012198533,0.000017450637,0.0004165656,0.00839817,0.6232509,0.06816087,0.009145227,0.00012584114,0.29004797],"study_design_scores_gemma":[0.000005352575,0.00011943291,0.000019731242,0.0002059739,0.000011571075,0.0013545682,0.0022189976,0.9328789,0.05153689,0.00030855424,0.011145429,0.00019458482],"about_ca_topic_score_codex":0.0000605353,"about_ca_topic_score_gemma":0.000023215,"teacher_disagreement_score":0.85275656,"about_ca_system_score_codex":0.0002475675,"about_ca_system_score_gemma":0.000053268657,"threshold_uncertainty_score":0.6149166},"labels":[],"label_agreement":null},{"id":"W4395465270","doi":"10.18280/isi.290217","title":"Inception-v3 with reduce learning rate for optimization of lung cancer histopathology classification","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Histopathology; Lung cancer; Medicine; Cancer; Pathology; Internal medicine","score_opus":0.016799291623321923,"score_gpt":0.26731397193930273,"score_spread":0.2505146803159808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395465270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01374841,0.0003486813,0.9833475,0.00020390838,0.00073997554,0.00045421015,0.000007909425,0.00047644597,0.0006729621],"genre_scores_gemma":[0.95599675,0.00010794339,0.043198496,0.00004481708,0.00008618405,0.00041601443,0.00005066285,0.00001763491,0.00008151439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989255,0.00007544401,0.00044806168,0.00019796874,0.0001720939,0.0001809121],"domain_scores_gemma":[0.99894685,0.00009614022,0.00033898337,0.0002066119,0.00037781868,0.00003362896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005138286,0.0001291677,0.00014851837,0.00032341128,0.00020092048,0.0002122761,0.00021818148,0.00009880792,0.000010741551],"category_scores_gemma":[0.00008646476,0.00012101183,0.000044000684,0.00058748916,0.000094287076,0.0040022554,0.00003747275,0.00012849801,0.000006630492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010596147,0.000014030378,0.00083147717,0.0015055641,0.00005061145,9.0494206e-7,0.012764445,0.7269127,0.0032216373,0.022101814,0.00064302,0.23184788],"study_design_scores_gemma":[0.00020999643,0.000157227,0.0019479796,0.00027413492,0.000028200799,0.00001926536,0.0001763551,0.99167615,0.0022961576,0.00058638287,0.002476338,0.00015182975],"about_ca_topic_score_codex":0.000045403074,"about_ca_topic_score_gemma":0.0000068875297,"teacher_disagreement_score":0.94224834,"about_ca_system_score_codex":0.000690847,"about_ca_system_score_gemma":0.00025488864,"threshold_uncertainty_score":0.49347192},"labels":[],"label_agreement":null},{"id":"W4396511291","doi":"10.3390/info15050253","title":"Transformer-Based Approach to Pathology Diagnosis Using Audio Spectrogram","year":2024,"lang":"en","type":"article","venue":"Information","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Spectrogram; Computer science; Transformer; Speech recognition; Engineering; Electrical engineering","score_opus":0.020862403873731315,"score_gpt":0.26349126352855723,"score_spread":0.24262885965482592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396511291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014341506,0.00004495707,0.9786702,0.00061668054,0.0007148088,0.000282102,0.0000035299308,0.0004439437,0.004882294],"genre_scores_gemma":[0.8920219,0.0000061076803,0.107159294,0.00056128576,0.00008260599,0.00014895068,0.000008765717,0.0000056479516,0.0000054357506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992261,0.000020528907,0.00021832196,0.00014147029,0.00019970277,0.00019390845],"domain_scores_gemma":[0.99963254,0.000030270307,0.00003216554,0.0002107999,0.000041661595,0.000052556225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021927274,0.00009090954,0.00007804732,0.00029466426,0.000077686054,0.0003211868,0.00024114677,0.00006247059,0.000006670256],"category_scores_gemma":[0.000012031005,0.00008754522,0.000054164142,0.0007289725,0.0000148706895,0.002142011,0.000019447914,0.000108509834,0.00015858619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000106058205,0.000033568696,0.00011298336,0.00016864981,0.000014864727,0.000003853024,0.0046011186,0.042443704,0.0004978992,0.016082438,0.0013662056,0.93466413],"study_design_scores_gemma":[0.00015402462,0.00014762518,0.00033867403,0.00004060889,0.000009380234,0.00005116491,0.00004348229,0.9241823,0.014801787,0.0007521804,0.05929364,0.0001851372],"about_ca_topic_score_codex":0.000025548296,"about_ca_topic_score_gemma":0.0000033553931,"teacher_disagreement_score":0.934479,"about_ca_system_score_codex":0.00022907839,"about_ca_system_score_gemma":0.000089678375,"threshold_uncertainty_score":0.35699904},"labels":[],"label_agreement":null},{"id":"W4396566553","doi":"10.1016/j.displa.2024.102735","title":"Enhancing chest X-ray diagnosis with text-to-image generation: A data augmentation case study","year":2024,"lang":"en","type":"article","venue":"Displays","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Computer science; Text generation; Image (mathematics); Artificial intelligence; Natural language processing; Medicine; Computer vision; Radiology","score_opus":0.048095452058262086,"score_gpt":0.3229706963746805,"score_spread":0.2748752443164184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396566553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30004376,0.00009596013,0.6979698,0.00048936263,0.0006206382,0.00044375015,0.000016261503,0.00018645532,0.00013404986],"genre_scores_gemma":[0.96827006,0.000007110129,0.030795068,0.00014292897,0.0003558846,0.00031164676,0.000021960972,0.000018337896,0.00007698409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985452,0.000059997394,0.00018796415,0.0007262639,0.00030142211,0.00017914154],"domain_scores_gemma":[0.9988021,0.00008910308,0.000036465182,0.0009412281,0.000048196613,0.000082900304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000343471,0.00013889285,0.00010191567,0.00011938197,0.00019989997,0.000662172,0.0005102123,0.000026042306,0.000037506416],"category_scores_gemma":[0.000022572953,0.00011976797,0.000016233986,0.0007028015,0.000015939078,0.0014704564,0.0003139974,0.00011114024,0.00014046932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009117314,0.0020053813,0.017328598,0.000737261,0.00084804883,0.03899706,0.11912432,0.01039038,0.08293069,0.0034208416,0.065657444,0.6584688],"study_design_scores_gemma":[0.00128955,0.0021066694,0.0063669644,0.00032534622,0.00025838727,0.0025099814,0.007940837,0.9187237,0.0481063,0.00006592578,0.011062598,0.0012437227],"about_ca_topic_score_codex":0.0004090401,"about_ca_topic_score_gemma":0.0029943185,"teacher_disagreement_score":0.90833336,"about_ca_system_score_codex":0.00011760566,"about_ca_system_score_gemma":0.0000851017,"threshold_uncertainty_score":0.63853395},"labels":[],"label_agreement":null},{"id":"W4396590223","doi":"10.1007/s11517-024-03084-1","title":"BraNet: a mobil application for breast image classification based on deep learning algorithms","year":2024,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universitat Politècnica de València","keywords":"Artificial intelligence; Computer science; Mammography; Breast ultrasound; Segmentation; Machine learning; Cohen's kappa; Deep learning; Medical diagnosis; Python (programming language); Breast imaging; Contextual image classification; Confusion matrix; Medical imaging; Algorithm; Breast cancer; Medicine; Image (mathematics); Radiology; Cancer","score_opus":0.012917446278106275,"score_gpt":0.2601910600174069,"score_spread":0.2472736137393006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396590223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032446976,0.00015831806,0.99297965,0.0011507669,0.00065359,0.00032561537,0.000002644614,0.0013384459,0.00014627817],"genre_scores_gemma":[0.9330237,0.000008892706,0.06601102,0.00020248242,0.0005985915,0.00010387182,0.000022087637,0.000021945925,0.0000074054856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807477,0.00006361718,0.00034392337,0.0007257532,0.00039489337,0.00039701644],"domain_scores_gemma":[0.9984735,0.0009571851,0.000060403978,0.0002678981,0.00006194547,0.00017902898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009695504,0.00021198459,0.00020583133,0.0001364411,0.00014708782,0.0001525051,0.0005616423,0.00023820842,0.000028575088],"category_scores_gemma":[0.0003507288,0.00017391267,0.00011819724,0.00054605596,0.000054188615,0.00011070684,0.00011386673,0.0005699604,0.000069154106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008383577,0.00003839527,0.0000805746,0.00008637639,0.000011089605,0.000006938769,0.0000459945,0.055397265,0.00407587,0.0031892005,0.00003057948,0.93702936],"study_design_scores_gemma":[0.000193289,0.00018376525,0.0043330565,0.00014146544,0.0000042863267,0.00003580678,0.0000049789924,0.990046,0.00025155122,0.00013598139,0.0044626393,0.00020714242],"about_ca_topic_score_codex":0.0000070444557,"about_ca_topic_score_gemma":3.1865565e-7,"teacher_disagreement_score":0.9368222,"about_ca_system_score_codex":0.00018172461,"about_ca_system_score_gemma":0.00005657727,"threshold_uncertainty_score":0.7091953},"labels":[],"label_agreement":null},{"id":"W4396669394","doi":"10.1016/j.media.2024.103197","title":"Multi-scale relational graph convolutional network for multiple instance learning in histopathology images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Convolutional neural network; Magnification; Computer science; Graph; Pattern recognition (psychology); Artificial intelligence; Embedding; Theoretical computer science","score_opus":0.014425377078651583,"score_gpt":0.2764111777591579,"score_spread":0.2619858006805063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396669394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028093809,0.0020668432,0.9917524,0.0023719692,0.0005119376,0.000114583265,0.000008876252,0.00023302983,0.0001309906],"genre_scores_gemma":[0.5056401,0.00011984915,0.4921838,0.00047564317,0.0003696051,0.00016606283,0.00007130135,0.000017894763,0.0009557603],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979531,0.00017419191,0.0004041367,0.0006187097,0.00050184765,0.00034801124],"domain_scores_gemma":[0.9987364,0.0007249888,0.000074074575,0.00023527726,0.00011100898,0.00011828006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012026606,0.00013624274,0.0002826623,0.0004628131,0.00016282649,0.000076649165,0.0003884848,0.00014496525,0.0001333001],"category_scores_gemma":[0.0005819536,0.0001339028,0.00026650054,0.0023902885,0.00020491306,0.00046851975,0.00012393256,0.0004690824,0.000031852433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015690188,0.00059796113,0.5231619,0.00031774296,0.001407111,0.0010969627,0.0026631537,0.20611317,0.0076627913,0.013533197,0.038102336,0.20518677],"study_design_scores_gemma":[0.0003657664,0.00002800207,0.055159368,0.000031715426,0.000086617365,0.000012689545,0.000012273267,0.93351096,0.00005163861,0.0013023437,0.009297067,0.0001415611],"about_ca_topic_score_codex":0.00008720698,"about_ca_topic_score_gemma":0.00074744277,"teacher_disagreement_score":0.7273978,"about_ca_system_score_codex":0.00021734441,"about_ca_system_score_gemma":0.00018322797,"threshold_uncertainty_score":0.5460397},"labels":[],"label_agreement":null},{"id":"W4396676987","doi":"10.1158/2767-9764.crc-24-0031","title":"Use of Deep Learning to Evaluate Tumor Microenvironmental Features for Prediction of Colon Cancer Recurrence","year":2024,"lang":"en","type":"article","venue":"Cancer Research Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"National Institutes of Health; National Cancer Institute; Sanofi; Mayo Clinic; Center for Cancer Research","keywords":"Colorectal cancer; Deep learning; Artificial intelligence; Medicine; Internal medicine; Oncology; Cancer; Computer science","score_opus":0.18696357518641435,"score_gpt":0.44859527983426,"score_spread":0.2616317046478457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396676987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39476854,0.11006196,0.44959816,0.028898226,0.00340997,0.009119274,0.0024884187,0.00070152676,0.000953923],"genre_scores_gemma":[0.96617156,0.005769936,0.02505781,0.000040496056,0.000066402456,0.0024894902,0.000020243282,0.000023243772,0.00036081517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981142,0.00040849927,0.00029765264,0.00035992754,0.00052909454,0.0002906193],"domain_scores_gemma":[0.9972798,0.00087108935,0.000090885755,0.0012328777,0.00043546784,0.00008987769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010988935,0.00009970925,0.00015385546,0.00032569212,0.00033123608,0.00011347617,0.0014893487,0.00004700631,0.000028452254],"category_scores_gemma":[0.0002512314,0.00010284494,0.00007158694,0.0010814626,0.00030893722,0.00048175314,0.00085591763,0.0005022267,0.0000061037267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016083311,0.0001657134,0.0021201787,0.0005063942,0.00018133072,9.449105e-7,0.0070989747,0.016214356,0.30580932,0.005560864,0.014353371,0.6478277],"study_design_scores_gemma":[0.0005500477,0.001203321,0.019547,0.0017129107,0.00007325638,0.000013238467,0.0005031415,0.57750666,0.18125026,0.0018575203,0.21543182,0.0003508358],"about_ca_topic_score_codex":0.0012370595,"about_ca_topic_score_gemma":0.0008987378,"teacher_disagreement_score":0.64747685,"about_ca_system_score_codex":0.0007760105,"about_ca_system_score_gemma":0.0003364941,"threshold_uncertainty_score":0.4193895},"labels":[],"label_agreement":null},{"id":"W4396690597","doi":"10.12688/f1000research.127142.2","title":"Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data","year":2024,"lang":"en","type":"preprint","venue":"F1000Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Kingston Health Sciences Centre; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Queen's University","funders":"Canadian Institutes of Health Research; Canadian Cancer Society","keywords":"Python (programming language); Computer science; Leverage (statistics); Raw data; Open data; Software; Open source; Open science; Data processing; Artificial intelligence; Data science; Public domain; Pipeline (software); Data mining; Machine learning; Database; World Wide Web; Operating system; Programming language","score_opus":0.2625381255296846,"score_gpt":0.4641635305209739,"score_spread":0.20162540499128934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396690597","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032758198,0.0066945907,0.97342014,0.014253464,0.0012323221,0.0018894372,0.00064144534,0.00086691236,0.00067410845],"genre_scores_gemma":[0.07267336,0.0015137482,0.9066597,0.0010323614,0.008235109,0.001064763,0.0058974577,0.0007293468,0.0021941033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918107,0.00051105645,0.0007679497,0.003841553,0.0021482736,0.0009204731],"domain_scores_gemma":[0.99041533,0.0007987002,0.0002551278,0.0074961097,0.00052494835,0.0005097617],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.011062688,0.00046209912,0.00053949194,0.00040574954,0.0006377366,0.008997883,0.02438914,0.0003217858,0.00003734898],"category_scores_gemma":[0.0036800157,0.00043131318,0.00003563663,0.0006949894,0.00035406003,0.0042438987,0.13996688,0.0025433998,0.000022490907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003053291,0.000059137034,0.000087167355,0.0018510574,0.00003571432,0.000084653075,0.0006568477,0.00013271795,0.00030759088,0.00016857107,0.05017782,0.9464082],"study_design_scores_gemma":[0.0003199811,0.000048770587,0.000040786945,0.0014420098,0.000032646996,0.00010283098,0.00027942727,0.96483076,0.00024516528,0.0054361625,0.026753457,0.00046800546],"about_ca_topic_score_codex":0.00086967525,"about_ca_topic_score_gemma":0.0005202492,"teacher_disagreement_score":0.964698,"about_ca_system_score_codex":0.00019627053,"about_ca_system_score_gemma":0.00279869,"threshold_uncertainty_score":0.99981385},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4396780833","doi":"10.1016/j.cell.2024.03.035","title":"Analysis of 3D pathology samples using weakly supervised AI","year":2024,"lang":"en","type":"article","venue":"Cell","topic":"AI in cancer detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"DOD Prostate Cancer Research Program; National Center for Advancing Translational Sciences; National Human Genome Research Institute; Clarendon Fund; National Institutes of Health; Johns Hopkins University; UK Research and Innovation; University of Washington; National Institute of Biomedical Imaging and Bioengineering; University of Southampton; Canary Foundation; National Institute of General Medical Sciences; Massachusetts General Hospital; Harvard University; U.S. Department of Defense; National Cancer Institute; Brigham and Women's Hospital; U.S. Department of Veterans Affairs","keywords":"Digital pathology; Biology; Virtual microscopy; Histopathology; Computer science; Artificial intelligence; Pathology; Medicine","score_opus":0.031183638427060942,"score_gpt":0.2756412212527695,"score_spread":0.24445758282570856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396780833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2648538,0.000616115,0.73313206,0.0001109232,0.0005265211,0.000033030414,0.000004630216,0.000089807596,0.00063310564],"genre_scores_gemma":[0.97260153,0.000020023808,0.02713022,0.00010512124,0.000044114902,0.0000020867997,0.0000018367956,0.000005733475,0.00008933717],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932355,0.00004391383,0.00014063237,0.0002614048,0.000110614914,0.00011986049],"domain_scores_gemma":[0.99950576,0.000067486835,0.000027676851,0.00033545095,0.000039130242,0.000024493618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014574263,0.00006175792,0.00013902446,0.00030164534,0.000030327827,0.00005156983,0.0002698059,0.000045631004,0.00006115238],"category_scores_gemma":[0.0000057259886,0.000059428578,0.000086333865,0.0012600363,0.000031402305,0.00016313582,0.00009771385,0.00007392434,0.000016368756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011443032,0.00009630812,0.0050036153,0.00031891477,0.00057023845,0.00014295285,0.0058077965,0.039961938,0.80974823,0.0030582384,0.0009810904,0.1342992],"study_design_scores_gemma":[0.000045589677,0.000034044995,0.0014758597,0.000010312412,0.00017430437,0.000005267692,0.000019350351,0.94396937,0.05154771,0.0004657649,0.0021650614,0.00008734266],"about_ca_topic_score_codex":0.00008810404,"about_ca_topic_score_gemma":0.000021798473,"teacher_disagreement_score":0.90400743,"about_ca_system_score_codex":0.000051315612,"about_ca_system_score_gemma":0.00005962566,"threshold_uncertainty_score":0.24234271},"labels":[],"label_agreement":null},{"id":"W4396781237","doi":"10.1038/s43856-024-00502-1","title":"A comprehensive AI model development framework for consistent Gleason grading","year":2024,"lang":"en","type":"article","venue":"Communications Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agency for Science, Technology and Research","keywords":"Computer science; Workflow; Artificial intelligence; Scanner; Grading (engineering); Digital pathology; Scalability; Image quality; Pattern recognition (psychology); Machine learning; Computer vision; Image (mathematics); Database","score_opus":0.14621984737485097,"score_gpt":0.39569463913919184,"score_spread":0.24947479176434087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396781237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001346156,0.012749255,0.9426036,0.04233587,0.00062783196,0.00037226814,0.000001972089,0.00038232352,0.0007923005],"genre_scores_gemma":[0.38414675,0.00048012237,0.61318034,0.0016294452,0.00008100927,0.00030759073,0.000013822232,0.000015144599,0.00014575744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989509,0.000052875555,0.000309877,0.00029137355,0.00020667352,0.00018830465],"domain_scores_gemma":[0.99702436,0.00089265575,0.00005951856,0.0017271683,0.00021386436,0.00008244442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002724955,0.00012983431,0.00017729419,0.00017104822,0.00037232402,0.000076350894,0.0013930842,0.00006780772,0.0000056825274],"category_scores_gemma":[0.00012084898,0.00011541135,0.000047776193,0.0005094596,0.00018527206,0.00020791993,0.00044152868,0.0003120445,0.000023569008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054152465,0.000037240152,0.000015674685,0.00014921796,0.000079207624,0.0000012274398,0.0061022984,0.0006657081,0.0005077455,0.7948643,0.012934093,0.18463787],"study_design_scores_gemma":[0.00014377899,0.00004800784,0.000039542265,0.0005803749,0.000018214154,0.0000132830655,0.00012708538,0.703261,0.00023899028,0.07155804,0.22386083,0.000110845955],"about_ca_topic_score_codex":0.000012020152,"about_ca_topic_score_gemma":0.000009432068,"teacher_disagreement_score":0.72330624,"about_ca_system_score_codex":0.00027170373,"about_ca_system_score_gemma":0.00023604509,"threshold_uncertainty_score":0.47063383},"labels":[],"label_agreement":null},{"id":"W4396802978","doi":"10.1038/s41467-024-48062-1","title":"VOLTA: an enVironment-aware cOntrastive ceLl represenTation leArning for histopathology","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research; Terry Fox Research Institute; Michael Smith Health Research BC; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Histopathology; Computer science; Representation (politics); Artificial intelligence; Identification (biology); Machine learning; Pathology; Medicine; Biology","score_opus":0.024453128733681193,"score_gpt":0.31838350303888874,"score_spread":0.2939303743052075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396802978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010309569,0.0073391097,0.98476857,0.003835188,0.0007144248,0.00036212552,0.000010236325,0.00042717057,0.0015122112],"genre_scores_gemma":[0.95247674,0.0003704416,0.04598321,0.0001634031,0.000082369166,0.00021134583,0.00007880237,0.000015684587,0.00061797356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989818,0.00025175585,0.00015621715,0.00035228214,0.000113394184,0.00014455621],"domain_scores_gemma":[0.9979194,0.0006344485,0.0000679127,0.0012642221,0.00007000626,0.0000440361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031763388,0.00009434555,0.000093789786,0.00011001417,0.00036405312,0.00010802258,0.0011032977,0.00019227805,0.000007440669],"category_scores_gemma":[0.00007787945,0.000101035555,0.000057488964,0.0002315928,0.00008636781,0.0005367412,0.000272025,0.00080394646,0.000030442634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011494902,0.0007601548,0.0045868037,0.00019714973,0.00013597218,0.000027765976,0.01912743,0.010240085,0.10979511,0.33275798,0.033322513,0.4889341],"study_design_scores_gemma":[0.0002852032,0.00022224139,0.0048992257,0.000022980395,0.000038079346,0.000025443738,0.00023188525,0.5602908,0.0037845843,0.004456418,0.42549837,0.00024474788],"about_ca_topic_score_codex":0.000011824716,"about_ca_topic_score_gemma":0.000042129053,"teacher_disagreement_score":0.9514458,"about_ca_system_score_codex":0.0002071959,"about_ca_system_score_gemma":0.00005894304,"threshold_uncertainty_score":0.41201103},"labels":[],"label_agreement":null},{"id":"W4396903761","doi":"10.1177/10406387241241270","title":"The use of telepathology in veterinary medicine: a scoping review","year":2024,"lang":"en","type":"review","venue":"Journal of Veterinary Diagnostic Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Telepathology; Pace; Veterinary medicine; Medicine; Digital pathology; MEDLINE; Telemedicine; Pathology; Health care; Biology; Political science","score_opus":0.22741858380451216,"score_gpt":0.411718147721583,"score_spread":0.18429956391707084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396903761","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012510503,0.99333245,0.001933804,0.0007761405,0.0028495463,0.0009468528,0.0000029914145,0.000023051858,0.000010074765],"genre_scores_gemma":[0.000033940505,0.9955035,0.0037726425,0.00020279076,0.00033630643,0.000103275386,0.0000035141318,0.000032875145,0.000011162962],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99502134,0.0013119677,0.0025210478,0.00035010235,0.00053066213,0.00026485647],"domain_scores_gemma":[0.9900842,0.0065051992,0.0024298565,0.00063614873,0.00023831753,0.00010628985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023514605,0.0003678549,0.0016456504,0.0005963618,0.00007749656,0.000082047714,0.0010726048,0.00020991912,0.0000045014694],"category_scores_gemma":[0.005863784,0.00023224528,0.00034595476,0.0012164701,0.0003332312,0.0007336169,0.0003635552,0.00085399376,0.0000121701005],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006806136,0.000017494638,0.000002998337,0.11955036,0.000060292,0.0011524045,0.00017989628,0.000015875237,0.000012316966,0.00023048307,0.0027705056,0.8760006],"study_design_scores_gemma":[0.00010417957,0.0020605645,0.000016352806,0.73001814,0.00042119465,0.0073250947,0.0000033857043,0.00010696422,0.0000013079133,0.0006125598,0.25914457,0.00018569673],"about_ca_topic_score_codex":0.000015592386,"about_ca_topic_score_gemma":0.0000029881974,"teacher_disagreement_score":0.87581486,"about_ca_system_score_codex":0.00034876337,"about_ca_system_score_gemma":0.0009813815,"threshold_uncertainty_score":0.94706875},"labels":[],"label_agreement":null},{"id":"W4396918066","doi":"10.1109/iccams60113.2023.10526133","title":"A Various CAD systems using mammogram for diagnosing breast cancer","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Loblaw Companies (Canada)","funders":"","keywords":"Breast cancer; CAD; Stage (stratigraphy); Medicine; Cancer; Mammography; Computer-aided diagnosis; Medical physics; Computer science; Radiology; Internal medicine; Engineering drawing","score_opus":0.0411276652317519,"score_gpt":0.3118696746544805,"score_spread":0.27074200942272864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396918066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02099068,0.00016169802,0.97300506,0.0008089274,0.0034287209,0.00045345532,0.000020331483,0.00093028956,0.00020081592],"genre_scores_gemma":[0.9827101,0.00004685841,0.015415958,0.00019782291,0.00056229334,0.00039378065,0.0000015829659,0.000029167337,0.00064239046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892217,0.000025491721,0.00016538407,0.00034673364,0.00019519428,0.00034504628],"domain_scores_gemma":[0.99933344,0.00012926829,0.000067485445,0.00030759085,0.000096555814,0.00006566011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022899538,0.00010603256,0.00012641009,0.00013540454,0.00020122292,0.00027335997,0.00034402075,0.000059264185,0.0000059316226],"category_scores_gemma":[0.000010893876,0.00009918503,0.00005471482,0.0008084659,0.000017964996,0.0003562407,0.0001283236,0.0000635662,0.000021126567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046984725,0.00011406566,0.013445031,0.00065848173,0.00022985,0.000072455645,0.002263161,0.22346725,0.0081021665,0.034564454,0.03463289,0.6824032],"study_design_scores_gemma":[0.00020999691,0.000027196878,0.0017677105,0.000069139904,0.000010170545,0.00007730146,0.000043795888,0.9920121,0.0004963052,0.00042031173,0.004692559,0.00017344707],"about_ca_topic_score_codex":0.0046301,"about_ca_topic_score_gemma":0.00023492004,"teacher_disagreement_score":0.96171945,"about_ca_system_score_codex":0.00027797327,"about_ca_system_score_gemma":0.00010905326,"threshold_uncertainty_score":0.69993573},"labels":[],"label_agreement":null},{"id":"W4396921451","doi":"10.1177/20552076241251660","title":"Malignancy pattern analysis of breast ultrasound images using clinical features and a graph convolutional network","year":2024,"lang":"en","type":"article","venue":"Digital Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Malignancy; Graph; Convolutional neural network; Computer science; Pattern recognition (psychology); Radiology; Artificial intelligence; Medicine; Pathology; Theoretical computer science","score_opus":0.02437559914736798,"score_gpt":0.3339759355197307,"score_spread":0.3096003363723627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396921451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08994301,0.006421621,0.90143704,0.0006290656,0.00081752066,0.00013377257,0.00028573358,0.00014294795,0.00018926624],"genre_scores_gemma":[0.9973038,0.00017230191,0.0020748822,0.00022710343,0.00017064401,0.00000225182,0.000017571901,0.0000071718605,0.000024309458],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987386,0.00005904688,0.0003658741,0.00038269605,0.00021693124,0.00023685643],"domain_scores_gemma":[0.9992063,0.0003004236,0.000111202564,0.00021781842,0.00005221145,0.00011206058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034451243,0.00010135607,0.00026003356,0.0001768222,0.000084569125,0.0002700556,0.00016503244,0.000048652095,0.000003895608],"category_scores_gemma":[0.000012276847,0.000092910326,0.00014528829,0.0011763606,0.00011444747,0.0005310009,0.00008337005,0.00013540199,0.0000017816074],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025065337,0.000114289665,0.36486313,0.0003344721,0.0009895207,0.000024007111,0.00043763453,0.0017880828,0.000026717864,0.007967074,0.0049808268,0.6184492],"study_design_scores_gemma":[0.00016478107,0.0001895549,0.9530441,0.00026085367,0.000090691894,0.00032727493,0.00002375646,0.038692784,0.000012111906,0.006738867,0.00024743722,0.00020777498],"about_ca_topic_score_codex":0.00023304694,"about_ca_topic_score_gemma":0.0000586609,"teacher_disagreement_score":0.90736073,"about_ca_system_score_codex":0.00006768687,"about_ca_system_score_gemma":0.00019403624,"threshold_uncertainty_score":0.3788773},"labels":[],"label_agreement":null},{"id":"W4397024240","doi":"10.1016/j.jpi.2024.100383","title":"Eye tracking in digital pathology: A comprehensive literature review","year":2024,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Ontario Institute for Cancer Research","keywords":"Digital pathology; Computer science; Information retrieval; Pathology; Data science; Medicine; Artificial intelligence","score_opus":0.01559855707016024,"score_gpt":0.3050227086437557,"score_spread":0.28942415157359547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397024240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18100585,0.20971556,0.59568113,0.0049699578,0.0062783686,0.00045267332,0.000020132065,0.00019345123,0.0016828442],"genre_scores_gemma":[0.7659128,0.10858669,0.1137282,0.010784854,0.00078671984,0.00002080819,0.000011694853,0.000047515576,0.000120765435],"study_design_codex":"design_other","study_design_gemma":"case_report","domain_scores_codex":[0.99837834,0.000058703583,0.00101481,0.000091622656,0.00024083727,0.000215692],"domain_scores_gemma":[0.9988504,0.00013879588,0.00041121218,0.0002493334,0.00029256937,0.000057705933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006115316,0.00014422169,0.00036654933,0.00043162378,0.000033073236,0.00028151003,0.00052510865,0.00014440953,0.0000037276259],"category_scores_gemma":[0.00015034617,0.00011313957,0.00014317848,0.00076297583,0.00006037741,0.0028701294,0.00012881878,0.00085624127,0.000033409477],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035007153,0.00013219162,0.0014059279,0.0087992195,0.0001239224,0.037727356,0.057138253,0.00090203434,0.0007591328,0.0066289026,0.013220916,0.87312716],"study_design_scores_gemma":[0.003924585,0.0044838637,0.013312098,0.12360489,0.00029277607,0.41925508,0.0029259827,0.11520302,0.0011921561,0.04966011,0.26384312,0.002302308],"about_ca_topic_score_codex":6.6998275e-8,"about_ca_topic_score_gemma":3.7158142e-7,"teacher_disagreement_score":0.8708248,"about_ca_system_score_codex":0.00011725811,"about_ca_system_score_gemma":0.00012766154,"threshold_uncertainty_score":0.46136975},"labels":[],"label_agreement":null},{"id":"W4398236183","doi":"10.3390/cancers16111976","title":"Practical Application of Deep Learning in Diagnostic Neuropathology—Reimagining a Histological Asset in the Era of Precision Medicine","year":2024,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Neuropathology; Deep learning; Workflow; Artificial intelligence; Computer science; Focus (optics); Data science; Neuroscience; Medicine; Psychology; Pathology; Disease","score_opus":0.026466252987368478,"score_gpt":0.3302935790772044,"score_spread":0.3038273260898359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398236183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06255835,0.0016352406,0.92754775,0.006684368,0.0005801068,0.00028422792,4.897832e-7,0.00006122528,0.0006482189],"genre_scores_gemma":[0.9957961,0.00019245358,0.0037503673,0.00012783507,0.000048489208,0.00007635473,9.947618e-7,0.0000049201067,0.0000025038412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987515,0.00028766994,0.00031756525,0.00029068088,0.00022487296,0.0001276631],"domain_scores_gemma":[0.9969569,0.002644378,0.000118569296,0.00022839272,0.000033781842,0.000018000708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000992906,0.00007199123,0.00015776255,0.00012461496,0.000019815463,0.000010825654,0.00030885328,0.000052388314,0.00000636029],"category_scores_gemma":[0.0017691237,0.000047238802,0.00002217997,0.00078949146,0.0001485271,0.00018209178,0.00006561516,0.0006127338,0.0000027298913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005283695,0.000032107386,0.018703602,0.00013170758,0.0000062156446,0.0001958132,0.007580824,0.031143555,0.0044025606,0.011518612,0.00048354382,0.92574865],"study_design_scores_gemma":[0.000345027,0.00052904105,0.06662691,0.00029870876,0.00001591184,0.00012727114,0.00032514203,0.92240363,0.0004383323,0.003476485,0.0053009037,0.000112651585],"about_ca_topic_score_codex":0.00025271982,"about_ca_topic_score_gemma":0.00009974568,"teacher_disagreement_score":0.93323773,"about_ca_system_score_codex":0.00041131096,"about_ca_system_score_gemma":0.00017447301,"threshold_uncertainty_score":0.26620576},"labels":[],"label_agreement":null},{"id":"W4398930513","doi":"10.7910/dvn/rhsbxv","title":"Enhancing Astronomers’ Appreciation for High-Dimensional Data (Visualization)","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Visualization; Data science; Astronomy; Computer science; Computer graphics (images); Physics; Data mining","score_opus":0.03035079691250743,"score_gpt":0.2714897715364724,"score_spread":0.241138974623965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398930513","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.6186855e-7,7.7561765e-7,0.44266048,0.000020933809,0.0017587537,0.00034303547,0.5551192,0.00009345115,0.0000027582032],"genre_scores_gemma":[0.00001480072,0.000033680684,0.052248508,0.00055137725,0.0010029704,0.000082221,0.94600093,0.000027049171,0.00003845547],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970041,0.00010566368,0.00052551425,0.0014051598,0.0005916629,0.00036792643],"domain_scores_gemma":[0.9957935,0.00021115084,0.00053705147,0.0031499043,0.00015297694,0.00015540537],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005083468,0.00035166266,0.0003801382,0.0002065504,0.00024008591,0.00031043802,0.003296175,0.00024198637,0.00094694225],"category_scores_gemma":[0.000417827,0.00040234617,0.00006875131,0.00040315872,0.00004126734,0.001977552,0.0025971662,0.00028745225,0.022350103],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025008683,0.00003129136,5.10657e-7,0.000108244094,0.00007061954,0.000003911777,0.000015801754,0.00013389786,0.000045931818,0.0003665869,0.99704,0.0021581943],"study_design_scores_gemma":[0.0004883112,0.00009528853,0.000010268645,0.00006241825,0.0000885986,0.000005060124,0.0000068720396,0.019866401,0.00033155363,0.000100089106,0.9785642,0.00038095636],"about_ca_topic_score_codex":0.00016303195,"about_ca_topic_score_gemma":0.00017303311,"teacher_disagreement_score":0.3908817,"about_ca_system_score_codex":0.0002678311,"about_ca_system_score_gemma":0.0004766109,"threshold_uncertainty_score":0.9999663},"labels":[],"label_agreement":null},{"id":"W4399069988","doi":"10.1007/s12312-024-01337-6","title":"Erklärbare Künstliche Intelligenz in der Pathologie","year":2024,"lang":"de","type":"article","venue":"Forum","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pathology; Computer science; Medicine","score_opus":0.02856792922776958,"score_gpt":0.29396724658774404,"score_spread":0.26539931735997446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399069988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00794279,0.12429751,0.7996389,0.022162708,0.038119886,0.00073089235,0.00003966737,0.001163774,0.005903867],"genre_scores_gemma":[0.9908347,0.0011216996,0.0040802904,0.0011707285,0.00078775507,0.00006925615,0.000005988252,0.00005030035,0.001879261],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762905,0.00011375001,0.0003888739,0.0008306399,0.0003157137,0.00072198967],"domain_scores_gemma":[0.9989505,0.00016255377,0.00004893825,0.00069261104,0.000051572442,0.000093826784],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004834298,0.00025696444,0.00021911158,0.00030098783,0.000097765515,0.00046542453,0.0008244426,0.00026090833,0.00014677533],"category_scores_gemma":[0.00008571842,0.00025220396,0.00013088199,0.0012752103,0.000094770454,0.00057260273,0.0006093782,0.0006620872,0.003840524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002244602,0.00007541378,0.002652047,0.0002608909,0.00007350576,0.0009495244,0.0035846825,0.0008725003,0.0003617537,0.015744418,0.0658087,0.9095941],"study_design_scores_gemma":[0.00019181197,0.0003855602,0.0015828836,0.0006821115,0.000041878324,0.000069090245,0.00043486126,0.24521993,0.0075378353,0.022621913,0.7205931,0.00063901755],"about_ca_topic_score_codex":0.000091808775,"about_ca_topic_score_gemma":0.0002067979,"teacher_disagreement_score":0.9828919,"about_ca_system_score_codex":0.00050072896,"about_ca_system_score_gemma":0.0002737858,"threshold_uncertainty_score":0.999993},"labels":[],"label_agreement":null},{"id":"W4399117207","doi":"10.1117/12.3025631","title":"Recovering unprocessed digital mammograms from processed mammograms for quantitative analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Artificial intelligence; Mammography; Pattern recognition (psychology); Computer science; Mean squared error; Artificial neural network; Mathematics; Digital mammography; Similarity (geometry); Computer vision; Breast cancer; Statistics; Medicine; Image (mathematics)","score_opus":0.020275076468086524,"score_gpt":0.28544408417399597,"score_spread":0.26516900770590945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399117207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021682741,0.00044385367,0.97393864,0.00052695285,0.00061127724,0.00031209306,0.000047503192,0.0011011077,0.0013358552],"genre_scores_gemma":[0.8892751,0.000016431017,0.10961266,0.00008461714,0.00010139065,0.000177313,0.000055183395,0.000024616911,0.0006527389],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817955,0.000014143742,0.00030624098,0.00085210206,0.00031570176,0.0003322829],"domain_scores_gemma":[0.99884576,0.00041469073,0.0000745031,0.00040505576,0.00016641054,0.00009357688],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00017220894,0.00021027295,0.0002643157,0.00032249253,0.00011234697,0.0023354406,0.0006422323,0.000084904575,0.00003218096],"category_scores_gemma":[0.00007283172,0.00018565686,0.0002658497,0.003322204,0.000039972263,0.0025111476,0.00011963431,0.00012380467,0.00005943332],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012230733,0.00014507417,0.001399295,0.00046233743,0.0030127915,0.000030312038,0.003338819,0.003948315,0.0020425972,0.025363486,0.0012033632,0.9589313],"study_design_scores_gemma":[0.00024760043,0.00025233548,0.00029396586,0.00006675926,0.00022135234,0.000002376363,0.00037178473,0.9502781,0.0068454402,0.027384233,0.013596908,0.000439149],"about_ca_topic_score_codex":0.00020424445,"about_ca_topic_score_gemma":0.00027183507,"teacher_disagreement_score":0.95849216,"about_ca_system_score_codex":0.00013064736,"about_ca_system_score_gemma":0.00011758629,"threshold_uncertainty_score":0.9987002},"labels":[],"label_agreement":null},{"id":"W4399117227","doi":"10.1117/12.3025375","title":"Towards improved breast cancer detection on digital mammograms using local self-attention-based transformer","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Adaptability; Pattern recognition (psychology); Transformer; Feature extraction; Artificial neural network; Mammography; Deep learning; Workload; Breast cancer; Residual neural network; Machine learning; Cancer","score_opus":0.009465053917809621,"score_gpt":0.2487526869988386,"score_spread":0.23928763308102896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399117227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020534791,0.000048710514,0.97415197,0.00086960715,0.0020581782,0.00024203034,0.000019372323,0.0012442913,0.0008310288],"genre_scores_gemma":[0.99608046,0.00000635677,0.003305319,0.00020074248,0.00022045402,0.00005442267,0.0000020482169,0.000027857584,0.00010235175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984869,0.000021730697,0.00022965946,0.0005722998,0.0003561761,0.00033326395],"domain_scores_gemma":[0.99946123,0.000030785803,0.000034191893,0.00028508654,0.000085175554,0.000103552804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012244323,0.00020986951,0.00012808818,0.00020337726,0.0001420686,0.00072438444,0.00027375444,0.000111386405,0.000059683138],"category_scores_gemma":[0.0000017473529,0.00017970162,0.00016758303,0.00079415983,0.000043880762,0.0011004289,0.000022682476,0.00022116938,0.000049101694],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025241625,0.00004826747,0.00005180173,0.000055155124,0.000043171138,0.000005697058,0.000060936207,0.0015773994,0.00616948,0.00022046134,0.000024646555,0.99171776],"study_design_scores_gemma":[0.00027393654,0.00016511448,0.0007562946,0.000079550446,0.00002364444,0.000057325517,0.000023044193,0.9558245,0.040985126,0.00023266984,0.0013144278,0.00026437067],"about_ca_topic_score_codex":0.00078576885,"about_ca_topic_score_gemma":0.0002094612,"teacher_disagreement_score":0.99145335,"about_ca_system_score_codex":0.00080611644,"about_ca_system_score_gemma":0.00027847328,"threshold_uncertainty_score":0.7328019},"labels":[],"label_agreement":null},{"id":"W4399324723","doi":"10.1200/jco.2024.42.16_suppl.1523","title":"AI-assisted clinical summary and treatment planning for cancer care: A comparative study of human vs. AI-based approaches.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Western University; University of Toronto; Cancer Care Ontario; London Health Sciences Centre; BC Cancer Agency","funders":"","keywords":"Medicine; Cancer; Cancer treatment; Intensive care medicine; Oncology; Internal medicine","score_opus":0.48414117189728556,"score_gpt":0.5651371833581372,"score_spread":0.08099601146085167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399324723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92722976,0.0035252944,0.056107722,0.0065999557,0.0051202322,0.0010405811,0.000012667349,0.00005359833,0.000310176],"genre_scores_gemma":[0.9921589,0.000068524,0.00613369,0.0006223063,0.00091099,0.00005822703,0.000001189592,0.000012056892,0.000034115954],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956906,0.000881698,0.0024965734,0.00043497645,0.00029511945,0.0002010469],"domain_scores_gemma":[0.99381965,0.004166677,0.0012080235,0.00025043177,0.00035262288,0.00020261323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002604801,0.00017788493,0.0015160016,0.0001728299,0.000095132425,0.000056390054,0.00039155805,0.00028528034,0.0000041718354],"category_scores_gemma":[0.00017439258,0.00012860069,0.00042164084,0.00022940205,0.00022490577,0.00024481482,0.000091607944,0.0007526898,6.152261e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036994878,0.0054816385,0.09588073,0.00014949603,0.0018240944,0.0002917897,0.0063670226,0.0024094165,0.00003788953,0.0005221261,0.007758423,0.87557787],"study_design_scores_gemma":[0.036172554,0.31161547,0.34460348,0.0008171831,0.0018182178,0.000114202594,0.003804912,0.15905914,0.00046742646,0.0014056909,0.13941501,0.000706712],"about_ca_topic_score_codex":0.000070181464,"about_ca_topic_score_gemma":0.0004685231,"teacher_disagreement_score":0.8748712,"about_ca_system_score_codex":0.0004154788,"about_ca_system_score_gemma":0.0019236517,"threshold_uncertainty_score":0.5244184},"labels":[],"label_agreement":null},{"id":"W4399509388","doi":"10.21203/rs.3.rs-4438861/v1","title":"GestaltMatcher Database - A global reference for facial phenotypic variability in rare human diseases","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Health Research Foundation","funders":"National Institutes of Health; ZonMw; Wellcome Trust","keywords":"Benchmarking; Medicine; Computer science; Database","score_opus":0.11473777765071984,"score_gpt":0.44077176376205657,"score_spread":0.3260339861113367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399509388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21813564,0.007760461,0.6886913,0.00888204,0.006116587,0.021146344,0.022132697,0.0034559914,0.023678929],"genre_scores_gemma":[0.9925132,0.000040351406,0.0042519243,0.000029526362,0.0005234273,0.0020318162,0.000365041,0.000035523066,0.00020920804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99441504,0.0010597295,0.00048751562,0.0019553183,0.0011658446,0.0009165221],"domain_scores_gemma":[0.99617076,0.00058391795,0.00009269592,0.002260016,0.0006152541,0.00027737458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031473583,0.00035191834,0.00041875563,0.0003457847,0.0002826384,0.000801484,0.002309702,0.0003924293,0.0000677483],"category_scores_gemma":[0.0010027434,0.00035195705,0.00014670541,0.0011434896,0.00021519077,0.00033863218,0.007779653,0.0019933933,0.00008450283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009520939,0.0021833335,0.022324659,0.05312018,0.00033676196,0.0005788203,0.0039251787,0.0016677077,0.0010080918,0.52981764,0.040428348,0.34365717],"study_design_scores_gemma":[0.0005358628,0.0002841424,0.016408654,0.0016133725,0.000021647784,0.000003919702,0.000107930326,0.032651797,0.00016116827,0.9408159,0.0067724306,0.00062313053],"about_ca_topic_score_codex":0.001473944,"about_ca_topic_score_gemma":0.0010892906,"teacher_disagreement_score":0.7743775,"about_ca_system_score_codex":0.0024160354,"about_ca_system_score_gemma":0.0018434011,"threshold_uncertainty_score":0.99989325},"labels":[],"label_agreement":null},{"id":"W4399544575","doi":"10.1038/s41467-024-48666-7","title":"Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Cancer Institute; School of Medicine, New York University; Vetenskapsrådet; National Institutes of Health; Biotechnology and Biological Sciences Research Council; University of Glasgow; Research Councils UK; York University","keywords":"Phenotype; Digital pathology; Computational biology; Pathology; Artificial intelligence; Biology; Immunophenotyping; Computer science; Phenotypic screening; Medicine; Gene; Genetics","score_opus":0.045708039361773874,"score_gpt":0.30891862937403425,"score_spread":0.2632105900122604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399544575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64798814,0.14958358,0.13717872,0.04627941,0.0045039477,0.0011719248,0.00003913477,0.0030421827,0.010212994],"genre_scores_gemma":[0.9731123,0.00087473483,0.0255196,0.00035223347,0.00005096058,0.000035881552,0.0000059320537,0.000011375377,0.000037003727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887025,0.0003619298,0.00020422609,0.0002460291,0.00016466553,0.00015288757],"domain_scores_gemma":[0.9979743,0.00064562407,0.00008994648,0.0011306634,0.0001353838,0.00002413346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038849795,0.00010879577,0.00013544186,0.00015142,0.00037414028,0.000069975096,0.0015433327,0.00019103962,0.000014469636],"category_scores_gemma":[0.00009587956,0.00007754084,0.000064017135,0.0009922347,0.000114422764,0.00013906023,0.0004411096,0.0012627186,0.000009803353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079664576,0.00067795266,0.01437757,0.00033564164,0.00076900056,0.00009012979,0.0459706,0.0346909,0.12799935,0.34508854,0.012366111,0.41755453],"study_design_scores_gemma":[0.00018860334,0.000117268864,0.005474342,0.0001883622,0.000038168822,0.00006484234,0.00028370836,0.92494905,0.0014633967,0.0012985409,0.06570829,0.00022542714],"about_ca_topic_score_codex":0.000041556777,"about_ca_topic_score_gemma":0.000052071933,"teacher_disagreement_score":0.89025813,"about_ca_system_score_codex":0.00014427582,"about_ca_system_score_gemma":0.00012054187,"threshold_uncertainty_score":0.5485954},"labels":[],"label_agreement":null},{"id":"W4399556309","doi":"10.1016/j.jelectrocard.2024.05.025","title":"Saliency maps to enhance explainability of occlusion myocardial infarction classification among pre-hospital chest pain patients","year":2024,"lang":"en","type":"article","venue":"Journal of Electrocardiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"North York General Hospital; University of Toronto","funders":"","keywords":"Chest pain; Medicine; Myocardial infarction; Occlusion; Cardiology; Internal medicine","score_opus":0.00454872141782096,"score_gpt":0.25301945394739933,"score_spread":0.24847073252957838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399556309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.531945,0.0002237313,0.46507618,0.00065653055,0.0017419573,0.00020233892,0.0000011422735,0.00003816005,0.00011495482],"genre_scores_gemma":[0.99684274,0.00010569624,0.0024488673,0.00008740228,0.00047279595,0.000015842701,0.0000022945774,0.000012712659,0.000011655439],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975685,0.0005633998,0.00072181603,0.00038617585,0.00045480527,0.00030534127],"domain_scores_gemma":[0.998362,0.00024408227,0.00040596302,0.000367536,0.00051486254,0.00010556887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022443382,0.0001609534,0.00037701693,0.00034544143,0.00008264621,0.000053542062,0.0005831108,0.00016542219,0.0000028716395],"category_scores_gemma":[0.0005485257,0.0001456089,0.00025002877,0.00071479316,0.000076200595,0.0007263943,0.00013892411,0.00041341913,0.0000057576085],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000598594,0.00045655583,0.20976862,0.00024762106,0.00057634496,0.00003828691,0.0053725005,0.0019423435,0.10819425,0.004214908,0.010043798,0.65854615],"study_design_scores_gemma":[0.00032527756,0.007556934,0.94870234,0.00014112696,0.00005996981,0.000089667745,0.00007088569,0.0053193695,0.02135737,0.008060501,0.007977185,0.00033936906],"about_ca_topic_score_codex":0.000022485347,"about_ca_topic_score_gemma":0.0000083088335,"teacher_disagreement_score":0.73893374,"about_ca_system_score_codex":0.0006242599,"about_ca_system_score_gemma":0.0002860335,"threshold_uncertainty_score":0.5937758},"labels":[],"label_agreement":null},{"id":"W4399648285","doi":"10.58532/v3bict4p2ch2","title":"A REVIEW ON DIFFERENT MACHINE LEARNING ALGORITHMS TO BREAST CANCER RISK PREDICTION","year":2023,"lang":"en","type":"review","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Machine learning; Cancer; Algorithm; Medicine; Cancer recurrence; Disease; Artificial intelligence; Variety (cybernetics); Quarter (Canadian coin); Oncology; Computer science; Internal medicine; Geography","score_opus":0.054897378140391986,"score_gpt":0.3437594560034655,"score_spread":0.28886207786307355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399648285","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.029212e-8,0.9220615,0.07294551,0.0003639751,0.0017254086,0.0013755565,0.00028238856,0.0010556525,0.00018999758],"genre_scores_gemma":[1.5098809e-7,0.99441665,0.00065280707,0.00037211762,0.00059731683,0.0012724489,0.000031496787,0.000078585974,0.0025784466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967948,0.0003701223,0.00074919406,0.0011132247,0.0005662734,0.00040634023],"domain_scores_gemma":[0.9979692,0.00032368823,0.0005151547,0.0008931928,0.00008869973,0.00021007478],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055266015,0.0005660292,0.0014152403,0.00034317566,0.00020836966,0.00012827798,0.0010214278,0.00019290541,0.00014358334],"category_scores_gemma":[0.00011877612,0.00039229728,0.0004570214,0.0015190582,0.000013886037,0.00015030884,0.000507659,0.0010600839,0.0008999297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.44616e-7,0.000019595098,0.0000052659834,0.015299829,0.000072221694,0.0000025671204,0.0000112925245,0.000027398093,1.7551018e-8,0.000019854046,0.006284611,0.9782566],"study_design_scores_gemma":[0.000059938724,0.00016885888,0.000031371215,0.1001282,0.00030877997,0.000047409634,4.6172102e-7,0.0067253504,3.6213217e-7,0.000017647222,0.8921643,0.0003473204],"about_ca_topic_score_codex":0.0005072063,"about_ca_topic_score_gemma":0.00012294679,"teacher_disagreement_score":0.97790927,"about_ca_system_score_codex":0.0009311099,"about_ca_system_score_gemma":0.00015483936,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W4399660468","doi":"10.1016/j.heliyon.2024.e32892","title":"Ensemble-based deep learning improves detection of invasive breast cancer in routine histopathology images","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Vetenskapsrådet; Cancerfonden; VINNOVA; Swedish e-Science Research Centre; Emissions Reduction Alberta","keywords":"Dice; Convolutional neural network; Computer science; Artificial intelligence; Ensemble forecasting; Ensemble learning; Sørensen–Dice coefficient; Test set; Pattern recognition (psychology); Set (abstract data type); Machine learning; Mathematics; Statistics; Image (mathematics); Image segmentation","score_opus":0.007825467683546933,"score_gpt":0.24056109582835813,"score_spread":0.2327356281448112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399660468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37573975,0.008929274,0.61187065,0.000839833,0.0017872197,0.00022410908,0.0000066473635,0.00035448227,0.00024801903],"genre_scores_gemma":[0.9981818,0.0004588496,0.0010136357,0.00006284691,0.00010649918,0.000064160944,8.5929673e-7,0.000016023536,0.00009528683],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988656,0.00011936393,0.0002387414,0.00039939638,0.00015888968,0.00021798698],"domain_scores_gemma":[0.99944884,0.0001273389,0.00009193729,0.00021694571,0.00008132206,0.00003363178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002465956,0.00012361618,0.00016052467,0.00031613364,0.000050081548,0.000047929658,0.00021127149,0.00009103556,0.00001635248],"category_scores_gemma":[0.000034235443,0.00012447793,0.000055898214,0.00060051144,0.000050498136,0.00031720413,0.00007686714,0.00028644013,0.000015945601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027316964,0.000014514821,0.0008964762,0.00034611317,0.0000038113255,0.000028106499,0.0006763978,0.0022549613,0.7283119,0.00007173777,0.0000025506492,0.26736614],"study_design_scores_gemma":[0.00053113454,0.00035004164,0.065182835,0.0007615805,0.000018371267,0.00012958953,0.00008119549,0.0712864,0.8603892,0.00050546083,0.0004649302,0.00029926057],"about_ca_topic_score_codex":0.0003396958,"about_ca_topic_score_gemma":0.0011689079,"teacher_disagreement_score":0.62244207,"about_ca_system_score_codex":0.00038717838,"about_ca_system_score_gemma":0.00014219854,"threshold_uncertainty_score":0.50760627},"labels":[],"label_agreement":null},{"id":"W4399722597","doi":"10.32920/26052403.v1","title":"Automatic Diagnosis of Endometrial Cancer With Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Endometrial cancer; Artificial intelligence; Cancer; Computer science; Medicine; Internal medicine","score_opus":0.019404885211756248,"score_gpt":0.2793411020639954,"score_spread":0.2599362168522391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399722597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13089013,0.006061646,0.8428109,0.0012794357,0.008303112,0.0010303876,0.000007918897,0.0018791183,0.0077373073],"genre_scores_gemma":[0.95076835,0.0004943333,0.04728437,0.000034822115,0.00032293773,0.0006882366,0.000001242098,0.0000300087,0.00037568557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826735,0.00008323302,0.0003273955,0.00061333325,0.00050306553,0.00020563653],"domain_scores_gemma":[0.99870014,0.00031043522,0.0002597738,0.0005609991,0.00011278581,0.00005586525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028554988,0.00021974719,0.00036998314,0.00043316453,0.000042830245,0.00018395745,0.00079169404,0.00016021206,0.0002969351],"category_scores_gemma":[0.000078493205,0.00017160834,0.000120278586,0.0008229359,0.00004731611,0.000099236764,0.0017281423,0.00077184883,0.00003265456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013361155,0.00003470687,0.0031862063,0.0011010879,0.00033967383,0.000016618958,0.0012308366,0.037008226,0.000032128508,0.002130369,0.0005415132,0.95436525],"study_design_scores_gemma":[0.0005705901,0.00038840738,0.0010582245,0.0013873777,0.00016938747,0.00001220137,0.000049151764,0.9695432,0.015298003,0.008922995,0.0020283184,0.0005721498],"about_ca_topic_score_codex":0.001196983,"about_ca_topic_score_gemma":0.00029138802,"teacher_disagreement_score":0.9537931,"about_ca_system_score_codex":0.00029270636,"about_ca_system_score_gemma":0.00030408168,"threshold_uncertainty_score":0.69979846},"labels":[],"label_agreement":null},{"id":"W4399722809","doi":"10.32920/26052403","title":"Automatic Diagnosis of Endometrial Cancer With Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Endometrial cancer; Cancer; Deep learning; Artificial intelligence; Computer science; Medicine; Internal medicine","score_opus":0.019404885211756248,"score_gpt":0.2793411020639954,"score_spread":0.2599362168522391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399722809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13089013,0.006061646,0.8428109,0.0012794357,0.008303112,0.0010303876,0.000007918897,0.0018791183,0.0077373073],"genre_scores_gemma":[0.95076835,0.0004943333,0.04728437,0.000034822115,0.00032293773,0.0006882366,0.000001242098,0.0000300087,0.00037568557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826735,0.00008323302,0.0003273955,0.00061333325,0.00050306553,0.00020563653],"domain_scores_gemma":[0.99870014,0.00031043522,0.0002597738,0.0005609991,0.00011278581,0.00005586525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028554988,0.00021974719,0.00036998314,0.00043316453,0.000042830245,0.00018395745,0.00079169404,0.00016021206,0.0002969351],"category_scores_gemma":[0.000078493205,0.00017160834,0.000120278586,0.0008229359,0.00004731611,0.000099236764,0.0017281423,0.00077184883,0.00003265456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013361155,0.00003470687,0.0031862063,0.0011010879,0.00033967383,0.000016618958,0.0012308366,0.037008226,0.000032128508,0.002130369,0.0005415132,0.95436525],"study_design_scores_gemma":[0.0005705901,0.00038840738,0.0010582245,0.0013873777,0.00016938747,0.00001220137,0.000049151764,0.9695432,0.015298003,0.008922995,0.0020283184,0.0005721498],"about_ca_topic_score_codex":0.001196983,"about_ca_topic_score_gemma":0.00029138802,"teacher_disagreement_score":0.9537931,"about_ca_system_score_codex":0.00029270636,"about_ca_system_score_gemma":0.00030408168,"threshold_uncertainty_score":0.69979846},"labels":[],"label_agreement":null},{"id":"W4399828500","doi":"10.32920/26060578","title":"Computational Classification Methods in Renal Pathology","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Renal pathology; Pathology; Computer science; Medicine; Kidney; Internal medicine","score_opus":0.07313148493870185,"score_gpt":0.40505770059392354,"score_spread":0.3319262156552217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828500","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007621661,0.00026094483,0.9818528,0.0034993885,0.002628004,0.00020276527,0.0000029350012,0.00037015256,0.010420802],"genre_scores_gemma":[0.073818095,0.000017684779,0.9252296,0.00023743758,0.00014086961,0.00013006355,0.000014959896,0.000013158312,0.00039809666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805254,0.00034778714,0.0003867203,0.00082836027,0.00021341443,0.00017116212],"domain_scores_gemma":[0.9990174,0.00019233192,0.00011915921,0.00055259076,0.00008086739,0.000037608064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097468076,0.00016548406,0.00020151342,0.00041340973,0.000027404069,0.00016807122,0.0007064434,0.0002987566,0.000032557477],"category_scores_gemma":[0.00003480752,0.00016395502,0.0000782524,0.00040180705,0.000043668835,0.00008417667,0.0016907997,0.0008879669,0.000116775984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005797899,0.00004388264,0.00007911881,0.00013343041,0.000028586916,0.00005155912,0.0007777862,0.08155969,0.0012634653,0.32971284,0.003016121,0.5833277],"study_design_scores_gemma":[0.00004504627,0.000012459149,0.0022928985,0.000032037864,0.0000032104658,0.000022316399,0.0000052018377,0.5783703,0.00032971468,0.41796497,0.000810671,0.00011123167],"about_ca_topic_score_codex":0.00004524053,"about_ca_topic_score_gemma":0.000029752215,"teacher_disagreement_score":0.5832165,"about_ca_system_score_codex":0.00037216392,"about_ca_system_score_gemma":0.00033869126,"threshold_uncertainty_score":0.6685892},"labels":[],"label_agreement":null},{"id":"W4399828570","doi":"10.32920/26060578.v1","title":"Computational Classification Methods in Renal Pathology","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Renal pathology; Pathology; Computer science; Medicine; Kidney; Internal medicine","score_opus":0.07313148493870185,"score_gpt":0.40505770059392354,"score_spread":0.3319262156552217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007621661,0.00026094483,0.9818528,0.0034993885,0.002628004,0.00020276527,0.0000029350012,0.00037015256,0.010420802],"genre_scores_gemma":[0.073818095,0.000017684779,0.9252296,0.00023743758,0.00014086961,0.00013006355,0.000014959896,0.000013158312,0.00039809666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805254,0.00034778714,0.0003867203,0.00082836027,0.00021341443,0.00017116212],"domain_scores_gemma":[0.9990174,0.00019233192,0.00011915921,0.00055259076,0.00008086739,0.000037608064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097468076,0.00016548406,0.00020151342,0.00041340973,0.000027404069,0.00016807122,0.0007064434,0.0002987566,0.000032557477],"category_scores_gemma":[0.00003480752,0.00016395502,0.0000782524,0.00040180705,0.000043668835,0.00008417667,0.0016907997,0.0008879669,0.000116775984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005797899,0.00004388264,0.00007911881,0.00013343041,0.000028586916,0.00005155912,0.0007777862,0.08155969,0.0012634653,0.32971284,0.003016121,0.5833277],"study_design_scores_gemma":[0.00004504627,0.000012459149,0.0022928985,0.000032037864,0.0000032104658,0.000022316399,0.0000052018377,0.5783703,0.00032971468,0.41796497,0.000810671,0.00011123167],"about_ca_topic_score_codex":0.00004524053,"about_ca_topic_score_gemma":0.000029752215,"teacher_disagreement_score":0.5832165,"about_ca_system_score_codex":0.00037216392,"about_ca_system_score_gemma":0.00033869126,"threshold_uncertainty_score":0.6685892},"labels":[],"label_agreement":null},{"id":"W4399866885","doi":"10.1007/s11548-024-03213-z","title":"Using diffusion models to generate synthetic labeled data for medical image segmentation","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pipeline (software); Dice; Synthetic data; Image segmentation; Pattern recognition (psychology); Similarity (geometry); Image (mathematics); Machine learning; Computer vision; Data mining","score_opus":0.08073924164035598,"score_gpt":0.34416084829595317,"score_spread":0.2634216066555972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399866885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09687656,0.0005757566,0.89237314,0.0037316985,0.0063265613,0.00006726177,0.000012180487,0.000030736344,0.000006086472],"genre_scores_gemma":[0.6597542,0.00032852552,0.33660805,0.0013149293,0.0019344374,0.0000059180143,0.000024956258,0.000016166043,0.000012794629],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985334,0.00015769723,0.00049980875,0.00029380652,0.00037665947,0.00013859067],"domain_scores_gemma":[0.9983222,0.00093901844,0.00015411101,0.00019511876,0.00027644087,0.000113106784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012830747,0.00010566331,0.00023375443,0.00041791284,0.00006538683,0.0002177174,0.00073604874,0.00008994321,0.00000829744],"category_scores_gemma":[0.00007249267,0.00008831103,0.00008520706,0.0001404479,0.000045405173,0.0008559719,0.00028418153,0.00015873802,0.0000013807871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002898562,0.00012502768,0.0003204977,0.00007211678,0.00092784956,0.0008561129,0.00062152103,0.008608984,0.018864524,0.0037937453,0.022409337,0.9431104],"study_design_scores_gemma":[0.00022557218,0.00005631435,0.00026894108,0.00020131761,0.00002081987,0.0037668815,0.0000049088044,0.9917446,0.0004380699,0.0016446875,0.0015298899,0.000098031625],"about_ca_topic_score_codex":0.0000056329327,"about_ca_topic_score_gemma":0.0000020116252,"teacher_disagreement_score":0.9831356,"about_ca_system_score_codex":0.00010735664,"about_ca_system_score_gemma":0.0002585685,"threshold_uncertainty_score":0.36012194},"labels":[],"label_agreement":null},{"id":"W4399873374","doi":"10.1148/ryai.240263","title":"Navigating Clinical Variability: Transfer Learning’s Impact on Imaging Model Performance","year":2024,"lang":"en","type":"letter","venue":"Radiology Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Intégré de Santé et de Services Sociaux des Laurentides","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence","score_opus":0.06518302432630502,"score_gpt":0.3727762012536321,"score_spread":0.30759317692732707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399873374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01147947,0.00017849453,0.8396998,0.14155304,0.0053261146,0.00039368216,0.000013789637,0.00073995616,0.0006156614],"genre_scores_gemma":[0.8190873,0.00032920684,0.006259672,0.16521546,0.008340332,0.00014836362,0.000042721862,0.00015643737,0.00042044793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939683,0.0010525313,0.0014502174,0.0020145327,0.00049844256,0.0010159527],"domain_scores_gemma":[0.9966175,0.0016381163,0.00021045144,0.0012335458,0.00017287422,0.00012751854],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030735554,0.0006921061,0.0008544541,0.00016726556,0.00035765933,0.00029186264,0.0018310136,0.001233315,0.00008452224],"category_scores_gemma":[0.00033875625,0.00060887606,0.0006046962,0.0006015697,0.0005673044,0.00043075767,0.00024662027,0.011917777,0.0011716844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007904953,0.00005871218,0.00047710355,0.00017091252,0.00016370388,0.00030621252,0.0010140088,0.2162859,0.000078268255,0.0029369018,0.07998127,0.69844794],"study_design_scores_gemma":[0.000019273426,0.00048023448,0.000028171722,0.00026002093,0.00004890758,0.00020204358,0.000009017208,0.9639894,0.0009903784,0.022464223,0.010902816,0.0006055445],"about_ca_topic_score_codex":0.00003470621,"about_ca_topic_score_gemma":0.0000020540222,"teacher_disagreement_score":0.8334401,"about_ca_system_score_codex":0.0005895923,"about_ca_system_score_gemma":0.00047115938,"threshold_uncertainty_score":0.99963623},"labels":[],"label_agreement":null},{"id":"W4399875001","doi":"10.1200/cci.23.00184","title":"Prostate Cancer Risk Stratification by Digital Histopathology and Deep Learning","year":2024,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Histopathology; Prostate cancer; Medicine; Grading (engineering); Prostatectomy; Concordance; Risk stratification; Risk assessment; Nomogram; Artificial intelligence; Radiology; Oncology; Pathology; Cancer; Computer science; Internal medicine","score_opus":0.02225807846600339,"score_gpt":0.3411788368971125,"score_spread":0.3189207584311091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399875001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18111748,0.017108332,0.7870991,0.0025126305,0.006317648,0.0007812837,0.0001636874,0.0012340152,0.003665815],"genre_scores_gemma":[0.9747787,0.016475629,0.006290357,0.00057499297,0.000377693,0.00022384635,0.000021622007,0.000028375327,0.0012287811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821556,0.00007024692,0.00088681135,0.00029375075,0.0002673932,0.00026621678],"domain_scores_gemma":[0.9988049,0.00034332645,0.00032732007,0.0002967532,0.00010030932,0.00012737096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006503097,0.00016412405,0.00022495033,0.000074175885,0.00015809642,0.00061409734,0.00032075614,0.00015664172,0.00002207542],"category_scores_gemma":[0.00017036495,0.00014627138,0.00007020499,0.00032220726,0.0001655771,0.0017264441,0.00015977389,0.0007149155,0.00005046835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000120555505,0.000013838124,0.013761396,0.0001113251,0.000018245928,0.0000020222858,0.0026122038,0.0006037679,0.000011168349,0.00067087304,0.0029155645,0.97926754],"study_design_scores_gemma":[0.0004254349,0.0003600892,0.0072480584,0.0001124893,0.00005028518,0.00001925635,0.00025976685,0.640079,0.00010950804,0.0026176006,0.34832117,0.00039733082],"about_ca_topic_score_codex":0.00007736922,"about_ca_topic_score_gemma":0.00005524878,"teacher_disagreement_score":0.9788702,"about_ca_system_score_codex":0.00020546647,"about_ca_system_score_gemma":0.00019759838,"threshold_uncertainty_score":0.5964774},"labels":[],"label_agreement":null},{"id":"W4399921919","doi":"10.3791/66889","title":"Generating and Analyzing High-Parameter Histology Images with Histoflow Cytometry","year":2024,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Histology; Cytometry; Flow cytometry; Computer science; Pathology; Biology; Medicine; Molecular biology","score_opus":0.02011325865242477,"score_gpt":0.3800726523214335,"score_spread":0.35995939366900875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399921919","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41658512,0.009934907,0.57198894,0.00021984274,0.0011299681,0.000049512273,5.1002957e-7,0.000043032025,0.000048136135],"genre_scores_gemma":[0.7637426,0.00009686516,0.23572639,0.00013039944,0.00018799661,0.000004743041,2.0426673e-7,0.00001639705,0.00009440025],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986997,0.0001073044,0.00039846613,0.0002657596,0.00033062688,0.00019810491],"domain_scores_gemma":[0.999256,0.000119787575,0.00024080953,0.00018135543,0.000102270526,0.00009976257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003395468,0.00015065352,0.0002891885,0.00047659458,0.00009873751,0.00027232934,0.00027896647,0.00005813603,0.000022320915],"category_scores_gemma":[0.00003542603,0.000115732146,0.00006513457,0.00041057225,0.00006494977,0.0006384988,0.00009615698,0.00022234565,0.000004209008],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016672311,0.00011345236,0.0008079257,0.00008476834,0.00047164605,0.0006713033,0.0028383431,0.00027733555,0.88403094,0.0012019158,0.002998841,0.10633678],"study_design_scores_gemma":[0.0035066365,0.002920041,0.000987474,0.0006593441,0.00017194857,0.0037254577,0.00020952386,0.09092995,0.88042474,0.0010951989,0.0145307295,0.00083896087],"about_ca_topic_score_codex":0.000019002993,"about_ca_topic_score_gemma":6.5134066e-7,"teacher_disagreement_score":0.34715748,"about_ca_system_score_codex":0.00032447,"about_ca_system_score_gemma":0.00009606734,"threshold_uncertainty_score":0.471942},"labels":[],"label_agreement":null},{"id":"W4400006107","doi":"10.1007/978-3-031-62881-8_33","title":"An Improved Deep CNN for Early Breast Cancer Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Breast cancer; Medicine; Artificial intelligence; Computer science; Cancer; Internal medicine","score_opus":0.00962056074851074,"score_gpt":0.23371363485022445,"score_spread":0.2240930741017137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400006107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053301024,0.016020844,0.97430426,0.000118414784,0.0071055046,0.00096787093,0.000026378686,0.00022106666,0.0011823601],"genre_scores_gemma":[0.99047875,0.00056396954,0.00050750584,0.0001179294,0.0047311685,0.00037665907,0.000009548896,0.000113495604,0.00310095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806005,0.00003080747,0.00042089503,0.00091747876,0.0001947066,0.00037608176],"domain_scores_gemma":[0.99884367,0.0001690808,0.00021885622,0.0005427902,0.00012037647,0.00010524717],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030166638,0.00041724564,0.00046757646,0.00020807332,0.00013480119,0.0005665988,0.00038072187,0.0008021422,0.000004414574],"category_scores_gemma":[0.0000049136365,0.00036814448,0.00011660854,0.00013358246,0.00004610691,0.00023855426,0.00008368635,0.00067592016,0.000002560098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093366005,0.0000089006235,0.00006901124,0.00052086817,0.00014520246,0.0000139746135,0.0004276159,0.14021216,0.00015728222,0.0059308214,0.000041700074,0.8523791],"study_design_scores_gemma":[0.00022107802,0.00023350111,0.000073151175,0.0005704516,0.000046127505,0.00008689661,0.0000015320319,0.9814919,0.000023714389,0.011483148,0.0053213686,0.0004471056],"about_ca_topic_score_codex":0.00077885075,"about_ca_topic_score_gemma":0.0032370705,"teacher_disagreement_score":0.99042547,"about_ca_system_score_codex":0.00032959864,"about_ca_system_score_gemma":0.00005035385,"threshold_uncertainty_score":0.99987704},"labels":[],"label_agreement":null},{"id":"W4400042735","doi":"10.18280/ts.410302","title":"DLF: A Deep Learning Framework Using Convolution Neural Network Algorithm for Breast Cancer Detection and Classification","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Convolution (computer science); Artificial neural network; Deep learning; Breast cancer; Pattern recognition (psychology); Convolutional neural network; Algorithm; Machine learning; Cancer; Medicine; Internal medicine","score_opus":0.02667783704448092,"score_gpt":0.27904549006332624,"score_spread":0.25236765301884534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400042735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018614778,0.0010594715,0.9778478,0.00037483685,0.0013744414,0.00038404277,0.000007971916,0.00032789382,0.0000087576245],"genre_scores_gemma":[0.9431572,0.00006123659,0.055169035,0.00009012918,0.0013217037,0.00016163875,0.0000031242776,0.000021628692,0.000014299743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865645,0.00008257985,0.00024247025,0.0004812559,0.00022974868,0.00030751072],"domain_scores_gemma":[0.99949497,0.00013555255,0.00009584474,0.0001157409,0.00008883675,0.00006908214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003625671,0.00015787901,0.0001240234,0.000102045946,0.00037175874,0.00034074998,0.00014137817,0.00010671149,0.000030062296],"category_scores_gemma":[0.000005671952,0.00016287818,0.00006249938,0.00043822845,0.000044573735,0.0006333741,0.00004814141,0.00025580244,0.0000031573177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019351253,0.000010071193,0.00019524858,0.000043636985,0.00003664842,0.0000013115256,0.0003151411,0.02793862,0.005430079,0.0011479725,0.000025913028,0.964836],"study_design_scores_gemma":[0.00020022326,0.00012276888,0.008068102,0.000115564384,0.00004178766,0.00005325767,0.000037849644,0.98808813,0.0003264658,0.0017887766,0.0009793938,0.0001776958],"about_ca_topic_score_codex":0.000047345005,"about_ca_topic_score_gemma":0.000023983042,"teacher_disagreement_score":0.9646583,"about_ca_system_score_codex":0.00035517768,"about_ca_system_score_gemma":0.0000480549,"threshold_uncertainty_score":0.6641979},"labels":[],"label_agreement":null},{"id":"W4400137488","doi":"10.21203/rs.3.rs-4559295/v1","title":"Bias in Histopathology Datasets: A Comprehensive Investigation on Possible Factors","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Brock University; Ontario Tech University","funders":"","keywords":"Histopathology; Computer science; Medicine; Pathology","score_opus":0.27235427163714804,"score_gpt":0.426866932588683,"score_spread":0.15451266095153499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400137488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9767207,0.0031799718,0.0040092026,0.005840009,0.0043246313,0.0025041816,0.00092812366,0.0007301168,0.0017630835],"genre_scores_gemma":[0.9959286,0.00024300795,0.0020674423,0.00016087138,0.0002512619,0.00038280277,0.00061868783,0.000052164454,0.00029515513],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99503845,0.0012551555,0.0004072713,0.0014135471,0.0012491713,0.00063638674],"domain_scores_gemma":[0.99693245,0.0007617505,0.000112372414,0.0017263781,0.00028666042,0.0001803908],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00133701,0.00030195268,0.00035354728,0.0018955144,0.00015201476,0.00043513454,0.0015695012,0.000435188,0.000022529277],"category_scores_gemma":[0.0004175077,0.0002862475,0.00009868956,0.001664143,0.00025580087,0.00019698922,0.0046329107,0.0035818494,0.00036573652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061257975,0.0013859568,0.061438274,0.02555478,0.00030465057,0.0076940274,0.0742092,0.047493696,0.012643715,0.16276039,0.39258748,0.21331525],"study_design_scores_gemma":[0.0013780333,0.002849227,0.16761601,0.010497797,0.00002762172,0.00008681002,0.0017665646,0.13655616,0.021227207,0.59468204,0.06095808,0.0023544182],"about_ca_topic_score_codex":0.0014166547,"about_ca_topic_score_gemma":0.00040224442,"teacher_disagreement_score":0.43192166,"about_ca_system_score_codex":0.0019569728,"about_ca_system_score_gemma":0.0009907047,"threshold_uncertainty_score":0.999959},"labels":[],"label_agreement":null},{"id":"W4400188830","doi":"10.1016/j.media.2024.103257","title":"The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Orionin Tutkimussäätiö; Turun Yliopisto; Vetenskapsrådet; Cancerfonden; VINNOVA; Karolinska Institutet; European Commission; Swedish e-Science Research Centre; Turun Yliopistosäätiö; Syöpäsäätiö; European Federation of Pharmaceutical Industries and Associations","keywords":"Computer science; Artificial intelligence; Image registration; Breast cancer; Computer vision; Pattern recognition (psychology); Cancer; Medicine; Image (mathematics)","score_opus":0.0076311122557927704,"score_gpt":0.3052339521346472,"score_spread":0.29760283987885444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400188830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019811785,0.0033926333,0.9414963,0.05002761,0.0006595439,0.00010255783,0.000007947701,0.00021548974,0.0021167195],"genre_scores_gemma":[0.99292874,0.0019082312,0.0020884124,0.00017346363,0.00034175153,0.00007764833,0.0000050782182,0.000011388293,0.0024652581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813557,0.00010981927,0.00033769137,0.00031102585,0.0009246971,0.00018120198],"domain_scores_gemma":[0.99896675,0.00021560941,0.00009474151,0.00052886584,0.0000999282,0.000094112416],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009095488,0.00009394227,0.0001860047,0.00014503142,0.00012264041,0.0001876299,0.00069116853,0.000068976726,0.0014041587],"category_scores_gemma":[0.00009934783,0.00006261398,0.00014402179,0.0015410284,0.00015827577,0.00033939208,0.00012899695,0.0001998074,0.00008195495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023074333,0.000026432403,0.000030316123,0.00007611152,0.0006360157,0.000049772672,0.00035051137,0.00005810735,0.0006477595,0.0021542625,0.007872759,0.98809564],"study_design_scores_gemma":[0.00006624952,0.000035233836,0.0012503562,0.0000649188,0.0003597944,0.000021926722,0.000044534652,0.98664904,0.0010168147,0.0011500159,0.009236962,0.00010417455],"about_ca_topic_score_codex":0.0004616556,"about_ca_topic_score_gemma":0.0011330431,"teacher_disagreement_score":0.9909476,"about_ca_system_score_codex":0.00010548507,"about_ca_system_score_gemma":0.00019247358,"threshold_uncertainty_score":0.9995087},"labels":[],"label_agreement":null},{"id":"W4400309420","doi":"10.1093/humrep/deae108.378","title":"O-321 A foundation model for embryology trained on time-lapse images","year":2024,"lang":"en","type":"article","venue":"Human Reproduction","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Embryology; Foundation (evidence); Biology; Anatomy; Geography; Archaeology","score_opus":0.040634293715597555,"score_gpt":0.31068788155643823,"score_spread":0.27005358784084066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400309420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020624673,0.00010246496,0.97108936,0.003262853,0.0020879516,0.00050362747,0.000002561358,0.00094640657,0.0013800896],"genre_scores_gemma":[0.9506365,0.000012670509,0.022516806,0.00014731937,0.0019298377,0.00031864943,0.000034841316,0.000041564803,0.024361813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984069,0.00004417545,0.00021143268,0.0009775859,0.00016788249,0.0001920341],"domain_scores_gemma":[0.9990539,0.00003771096,0.00006301246,0.00071532256,0.000099544144,0.00003053125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056231976,0.00012925506,0.00011644735,0.00022515356,0.00023778854,0.00020407041,0.00021928154,0.000070339294,0.000026837875],"category_scores_gemma":[0.00006502658,0.00013149808,0.000078807454,0.00026384753,0.00004578773,0.0005240986,0.000041491505,0.00013049161,0.00017630644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009428922,0.00013485311,0.0000025833433,0.00019960971,0.00006867169,0.000005665288,0.0023452367,0.026377948,0.24245618,0.112251826,0.03615527,0.5799079],"study_design_scores_gemma":[0.00022398238,0.00036946035,0.00008793747,0.00003081304,0.000017748462,0.000039415507,0.000008209653,0.8817946,0.026448954,0.08350424,0.0072809057,0.0001937677],"about_ca_topic_score_codex":0.000007217494,"about_ca_topic_score_gemma":0.0000047779504,"teacher_disagreement_score":0.9485726,"about_ca_system_score_codex":0.00020451288,"about_ca_system_score_gemma":0.00005979075,"threshold_uncertainty_score":0.5362336},"labels":[],"label_agreement":null},{"id":"W4400395416","doi":"10.58496/mjaih/2024/009","title":"DARKNET-53 Convolutional Neural Network-Based Image Processing for Breast Cancer Detection","year":2024,"lang":"en","type":"article","venue":"Mesopotamian Journal of Artificial Intelligence in Healthcare","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Computer science; Breast cancer; Artificial intelligence; Pattern recognition (psychology); Image processing; Artificial neural network; Image (mathematics); Cancer; Medicine; Internal medicine","score_opus":0.04309260936328517,"score_gpt":0.34680654958743695,"score_spread":0.30371394022415177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400395416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011547505,0.004750842,0.96208733,0.014623951,0.006378464,0.00047221652,0.000031229272,0.000102390026,0.0000060570455],"genre_scores_gemma":[0.9790716,0.00006755144,0.017909799,0.00041884364,0.0024098484,0.00008392635,0.0000013577771,0.000030041687,0.000007028553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971213,0.00020700712,0.0011390398,0.00044439692,0.0005085418,0.000579725],"domain_scores_gemma":[0.99813277,0.0002708456,0.0003846087,0.00021297137,0.0008026929,0.00019611894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013787423,0.00022817537,0.0003217482,0.00045418803,0.00027152215,0.00040707676,0.0005829682,0.0001490121,0.000019806499],"category_scores_gemma":[0.000072648705,0.00021816824,0.00019631008,0.0012742927,0.00013091056,0.0011237842,0.00004487355,0.00074077136,0.0000063044477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020407523,0.000034125584,0.0003596692,0.0003465977,0.000012951306,0.00006147162,0.00035808363,0.04352632,0.0009859931,0.0019707833,0.00010375313,0.9520362],"study_design_scores_gemma":[0.000068192305,0.00037734376,0.0013479838,0.00078504765,0.000014480141,0.00030806576,0.00011054906,0.96531683,0.008687427,0.022280335,0.00046898966,0.00023477005],"about_ca_topic_score_codex":0.00024503205,"about_ca_topic_score_gemma":0.000983505,"teacher_disagreement_score":0.9675241,"about_ca_system_score_codex":0.00091755093,"about_ca_system_score_gemma":0.0012500585,"threshold_uncertainty_score":0.88966423},"labels":[],"label_agreement":null},{"id":"W4400527069","doi":"10.1109/icmi60790.2024.10586152","title":"Deep Learning-Based Melanoma Detection UsingAttention Maps","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology)","score_opus":0.010819901340009519,"score_gpt":0.23559243325366486,"score_spread":0.22477253191365534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400527069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004198687,0.00019833325,0.98852277,0.0005088679,0.0019030547,0.000088699744,1.324074e-7,0.0014168398,0.0031626204],"genre_scores_gemma":[0.98870856,0.0000048528696,0.009876617,0.00010702854,0.0001484093,0.000020255862,0.0000017214173,0.000013386667,0.0011191907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990208,0.00006800234,0.00013715685,0.00037603438,0.0002230057,0.00017496166],"domain_scores_gemma":[0.9995963,0.000055311768,0.000030210143,0.0002275814,0.000046072197,0.00004450995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023452505,0.00009908056,0.00006635706,0.00019970203,0.00014726094,0.0003533962,0.0002049944,0.00006942429,0.000071643786],"category_scores_gemma":[0.000016699958,0.00009360887,0.00007276654,0.00061328965,0.000019125873,0.00052765204,0.00005135243,0.00020551187,0.00039515243],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008606324,0.00001945242,0.00018672366,0.00006492511,0.000022566792,0.000023611346,0.00015272455,0.017928917,0.013712279,0.0052442523,0.00024291384,0.96239305],"study_design_scores_gemma":[0.00009348915,0.00013710285,0.0004916745,0.000021636864,0.0000067042474,0.000025793634,0.000011232451,0.93681425,0.036796838,0.0013374182,0.024138771,0.00012507488],"about_ca_topic_score_codex":0.00006766392,"about_ca_topic_score_gemma":0.00010484838,"teacher_disagreement_score":0.9845098,"about_ca_system_score_codex":0.00020158556,"about_ca_system_score_gemma":0.000038855655,"threshold_uncertainty_score":0.50790167},"labels":[],"label_agreement":null},{"id":"W4400575212","doi":"10.1007/s10278-024-01182-y","title":"Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification—Part 1: Report of the MIDI Task Group - Best Practices and Recommendations, Tools for Conventional Approaches to De-identification, International Approaches to De-identification, and Industry Panel on Image De-identification","year":2024,"lang":"en","type":"editorial","venue":"Journal of Imaging Informatics in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; National Cancer Institute; Frederick National Laboratory for Cancer Research","keywords":"Identification (biology); Task (project management); MIDI; Task group; Computer science; Best practice; Informatics; Data science; Engineering management; Engineering; Political science; Systems engineering","score_opus":0.1616151152043639,"score_gpt":0.3749821189076779,"score_spread":0.21336700370331402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400575212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012761225,0.0006076318,0.6148096,0.14734687,0.22057873,0.0024884045,0.0007055784,0.000057062738,0.00064492744],"genre_scores_gemma":[0.46829563,0.00916019,0.1643813,0.0074290317,0.3278109,0.0049951673,0.0032066456,0.00052518205,0.014195933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925746,0.00035665068,0.0034505809,0.00049804733,0.0027734402,0.00034670753],"domain_scores_gemma":[0.9895926,0.0023477832,0.005594341,0.0006869339,0.001543304,0.00023505521],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.014234382,0.0003633729,0.00053505483,0.0009965828,0.00031168593,0.0006879638,0.00198134,0.00046012356,0.000016317466],"category_scores_gemma":[0.024894185,0.00028690993,0.00016234345,0.0010273767,0.0006246411,0.0022178676,0.00043668682,0.0018580792,0.0000032152204],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022465897,0.00043679553,0.0010590254,0.001102487,0.00043855692,0.00001073567,0.0074256132,0.002760163,0.0016950534,0.004857871,0.9426001,0.037388965],"study_design_scores_gemma":[0.0055554905,0.0005473681,0.032667685,0.02705642,0.0014967389,0.0019848312,0.015807837,0.19459744,0.009113539,0.021189291,0.6881061,0.0018772066],"about_ca_topic_score_codex":0.000108730004,"about_ca_topic_score_gemma":0.00008902637,"teacher_disagreement_score":0.45553443,"about_ca_system_score_codex":0.0015106938,"about_ca_system_score_gemma":0.0024995827,"threshold_uncertainty_score":0.9999583},"labels":[],"label_agreement":null},{"id":"W4400748060","doi":"10.1016/j.modpat.2024.100563","title":"Evaluation of Artificial Intelligence-Based Gleason Grading Algorithms “in the Wild”","year":2024,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Radboud Universitair Medisch Centrum; Health~Holland","keywords":"Grading (engineering); Computer science; Pathology; Algorithm; Artificial intelligence; Medical physics; Medicine; Biology","score_opus":0.09863510812397899,"score_gpt":0.341038808473111,"score_spread":0.24240370034913203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400748060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055436213,0.00085642835,0.9411983,0.0011083005,0.0008955281,0.0002024795,0.0000014444994,0.00006734899,0.00023394123],"genre_scores_gemma":[0.9905251,0.0000071456084,0.00919638,0.00010320699,0.0000915045,0.00006580483,0.0000013128927,0.0000066685648,0.0000028542563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982546,0.0004943769,0.00022978215,0.0003429821,0.00050999084,0.00016828885],"domain_scores_gemma":[0.99931705,0.00016127438,0.000048890142,0.00036698088,0.00009203069,0.000013783983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032087062,0.00008301654,0.00010228045,0.00018252758,0.000043730935,0.000057453828,0.00043638988,0.000074326104,0.0000090372305],"category_scores_gemma":[0.00007869558,0.000065774075,0.000049378632,0.0004824208,0.000064261105,0.00015709584,0.0000413505,0.00017068864,0.000017735483],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003112076,0.00002592053,0.000029653245,0.0000101233945,0.0000034732595,0.000023662891,0.002344865,0.020351497,0.0016876719,0.0077881347,0.000019261173,0.96771264],"study_design_scores_gemma":[0.000031004623,0.00007891283,0.00023389257,0.00002260593,0.000014747945,0.000029880262,0.00003958809,0.827286,0.004748403,0.1674189,0.00004258552,0.00005346642],"about_ca_topic_score_codex":0.000028835213,"about_ca_topic_score_gemma":0.00005925982,"teacher_disagreement_score":0.9676592,"about_ca_system_score_codex":0.00014363328,"about_ca_system_score_gemma":0.00016300635,"threshold_uncertainty_score":0.26821887},"labels":[],"label_agreement":null},{"id":"W4400807654","doi":"10.1038/s41698-024-00652-4","title":"Learning generalizable AI models for multi-center histopathology image classification","year":2024,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; University of Calgary; Vancouver General Hospital; University of British Columbia","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Artificial intelligence; Deep learning; Computer science; Convolutional neural network; Pattern recognition (psychology); Machine learning; Normalization (sociology); Digital pathology","score_opus":0.0913080024716017,"score_gpt":0.38200252904209114,"score_spread":0.29069452657048944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400807654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014099812,0.0004417364,0.98870593,0.0027236652,0.0037484874,0.00039523852,0.0000047478984,0.00048637023,0.0020838329],"genre_scores_gemma":[0.23594832,0.0002550462,0.75587696,0.0011131829,0.00043873844,0.0005583717,0.000024813213,0.00005297038,0.0057315785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981149,0.00025990483,0.00036345597,0.00075672363,0.00017079167,0.0003342445],"domain_scores_gemma":[0.99892133,0.0002889548,0.00010216252,0.00041568436,0.00019846731,0.00007339825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078382425,0.0001540151,0.00022789216,0.00025596668,0.00018668141,0.0001457101,0.0005330435,0.0002680788,0.0000345167],"category_scores_gemma":[0.00010393321,0.00014737646,0.00011107506,0.00028678344,0.000065450186,0.0008695136,0.00021632305,0.00035257384,0.00015816232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086120366,0.00026597467,0.000054189568,0.00005997962,0.000017449058,0.00003919736,0.0017332159,0.010976112,0.04038655,0.03584445,0.037284616,0.87325215],"study_design_scores_gemma":[0.0005088213,0.00039061098,0.000059392707,0.00001557755,0.000006614668,0.00006961685,0.000013141865,0.70218205,0.00078357756,0.00777659,0.28808564,0.00010839922],"about_ca_topic_score_codex":0.000013142777,"about_ca_topic_score_gemma":0.000018542294,"teacher_disagreement_score":0.87314373,"about_ca_system_score_codex":0.0007402566,"about_ca_system_score_gemma":0.00022427473,"threshold_uncertainty_score":0.60098374},"labels":[],"label_agreement":null},{"id":"W4400969513","doi":"10.1177/09622802241262521","title":"Analyzing heterogeneity in biomarker discriminative performance through partial time-dependent receiver operating characteristic curve modeling","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Texas at Austin; Pfizer; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Discriminative model; Receiver operating characteristic; Biomarker; Computer science; Artificial intelligence; Biology; Machine learning","score_opus":0.19317553433438792,"score_gpt":0.5356551573303712,"score_spread":0.3424796229959832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400969513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032659527,0.0003539761,0.9641966,0.00094380864,0.0005854366,0.00032305828,0.00001402637,0.0000846249,0.00083893485],"genre_scores_gemma":[0.60360765,0.0003029555,0.39570796,0.000045305558,0.00012455821,0.00014568502,0.000005790317,0.000022739297,0.00003735701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98974013,0.0053686057,0.0008185493,0.0011337069,0.0019300194,0.0010089865],"domain_scores_gemma":[0.9921864,0.0068578315,0.00003697581,0.00044789442,0.00017776621,0.00029312077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01951289,0.00022168148,0.00040944695,0.00046424606,0.00020090696,0.00035191394,0.0009561215,0.00022127708,0.00047824648],"category_scores_gemma":[0.011647317,0.00019023991,0.000049629867,0.0017666867,0.0003961135,0.00072851975,0.0008705633,0.0021371462,0.00008118749],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005176137,0.00008913627,0.0005387084,0.00023124929,0.000025655561,0.0004879834,0.0014253939,0.0005912264,0.0014982356,0.0068038353,0.000044234508,0.9882126],"study_design_scores_gemma":[0.00023083463,0.00014211438,0.0020005137,0.0005822065,0.0000046545415,0.000020455785,0.000059854166,0.9843782,0.0015839861,0.01064104,0.00015216092,0.00020393333],"about_ca_topic_score_codex":0.00035568178,"about_ca_topic_score_gemma":0.00006661537,"teacher_disagreement_score":0.9880086,"about_ca_system_score_codex":0.00074833666,"about_ca_system_score_gemma":0.0005702381,"threshold_uncertainty_score":0.996678},"labels":[],"label_agreement":null},{"id":"W4401042127","doi":"10.18653/v1/2024.naacl-long.273","title":"Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Stage (stratigraphy); Coding (social sciences); Information retrieval; Rank (graph theory); Artificial intelligence; Statistics; Mathematics","score_opus":0.09033078776927157,"score_gpt":0.35529865324410836,"score_spread":0.2649678654748368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401042127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008985,0.000053150143,0.99079627,0.0064586042,0.0005906611,0.00020590973,0.0000037206592,0.0005426228,0.00045058798],"genre_scores_gemma":[0.5253812,0.00006578524,0.47162288,0.00065324845,0.00007895943,0.00005680189,0.0000042736456,0.00001388662,0.0021229787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916106,0.000022081993,0.00018395549,0.00031395734,0.00017901491,0.00013994979],"domain_scores_gemma":[0.9994754,0.000237139,0.0000267682,0.00015695293,0.000030508176,0.000073209536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006364466,0.00007624074,0.00008527168,0.00008261761,0.00008710575,0.00018655183,0.00018474789,0.0000775312,0.00008024284],"category_scores_gemma":[0.0001322719,0.00006681437,0.000029635288,0.00020611421,0.000020606632,0.0005182245,0.000104716106,0.00010820779,0.000009650627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076155693,0.000024578047,0.000018284096,0.00037883496,0.000033323766,0.0000059457025,0.0021085034,0.00036561664,0.00070977444,0.029247044,0.011161796,0.9559387],"study_design_scores_gemma":[0.00021239894,0.00003575382,0.000017080907,0.000054924498,0.000004284873,0.000007945494,0.000023178949,0.995027,0.00066931365,0.0015894143,0.0022716222,0.00008709498],"about_ca_topic_score_codex":0.000011619513,"about_ca_topic_score_gemma":0.000046801717,"teacher_disagreement_score":0.9946614,"about_ca_system_score_codex":0.0000993097,"about_ca_system_score_gemma":0.00009368033,"threshold_uncertainty_score":0.2724611},"labels":[],"label_agreement":null},{"id":"W4401073399","doi":"10.1109/memea60663.2024.10596808","title":"Overlapping Cervical Cell Region Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Image segmentation; Computer vision","score_opus":0.017806260685521522,"score_gpt":0.2519882484497787,"score_spread":0.23418198776425717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401073399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002618781,0.00015506918,0.9707507,0.0015133128,0.0010740389,0.0000627826,8.070401e-8,0.00056005275,0.023265185],"genre_scores_gemma":[0.9697356,0.00003265165,0.027231017,0.00038859248,0.00015717556,0.00001147893,5.9410974e-7,0.0000063044763,0.0024365874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994221,0.000017784614,0.0000847054,0.00023400462,0.000141668,0.00009976639],"domain_scores_gemma":[0.99973625,0.000033806376,0.000012357708,0.00017403964,0.000014664003,0.000028864035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006874396,0.000051273935,0.00003649192,0.00006408577,0.000042060918,0.0002005642,0.0001681091,0.000030778217,0.000034845816],"category_scores_gemma":[0.0000016544221,0.00004623233,0.00002901592,0.00030915777,0.0000072844055,0.00054393505,0.00006706977,0.000070549184,0.0002180796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068327413,0.00004251686,0.00029438914,0.00026395076,0.000022342387,0.00009314633,0.0022975847,0.0006660436,0.045676414,0.14267772,0.053401582,0.7545575],"study_design_scores_gemma":[0.00018127785,0.00011523951,0.00093431625,0.00005847132,0.000007383505,0.00007092541,0.00009332667,0.8416897,0.092482485,0.011930002,0.052176416,0.00026047006],"about_ca_topic_score_codex":0.000025874173,"about_ca_topic_score_gemma":0.000004113419,"teacher_disagreement_score":0.96711683,"about_ca_system_score_codex":0.000114104376,"about_ca_system_score_gemma":0.000030432144,"threshold_uncertainty_score":0.28030446},"labels":[],"label_agreement":null},{"id":"W4401075207","doi":"10.1007/978-3-031-65392-6_14","title":"3D Segmentation and Subtypes Classification of Breast Cancer Using Ultrasound Images Through Hybrid Approach of CNN and LSTM","year":2024,"lang":"en","type":"book-chapter","venue":"Learning and analytics in intelligent systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Breast cancer; Breast ultrasound; Cancer; Medicine; Internal medicine; Mammography","score_opus":0.039723456639888355,"score_gpt":0.2941745401887532,"score_spread":0.25445108354886486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401075207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019427655,0.03323183,0.92034453,0.00007405598,0.0010903587,0.0007292004,0.00010024321,0.00010566727,0.02489648],"genre_scores_gemma":[0.9757868,0.009564812,0.0026703908,0.0000045858656,0.00012564867,0.0000081480985,0.00001402887,0.000036068217,0.011789537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860376,0.00004484843,0.0005026715,0.0004586008,0.00027129904,0.00011878983],"domain_scores_gemma":[0.99905974,0.00012890484,0.0004826575,0.00016678656,0.0001283962,0.000033535303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036366397,0.00020167143,0.00037607626,0.0002714191,0.00006198403,0.00014207349,0.000117016105,0.00012724128,0.0000037817392],"category_scores_gemma":[0.000013574544,0.00019441993,0.00003882392,0.00011081205,0.00016439927,0.00016638044,0.00008370685,0.0003245819,6.908e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000226152,0.0002298143,0.09040855,0.037043173,0.002924126,0.000046997662,0.026449189,0.1885957,0.038234677,0.40027148,0.00029510452,0.21527505],"study_design_scores_gemma":[0.00023303487,0.00015618932,0.00079500495,0.0044928985,0.000354859,0.00033822694,0.001523337,0.9805426,0.0028353466,0.0054824073,0.0025999981,0.00064610987],"about_ca_topic_score_codex":0.0005439021,"about_ca_topic_score_gemma":0.0000099897925,"teacher_disagreement_score":0.95635915,"about_ca_system_score_codex":0.00014303511,"about_ca_system_score_gemma":0.00004196966,"threshold_uncertainty_score":0.79282147},"labels":[],"label_agreement":null},{"id":"W4401110297","doi":"10.1109/cai59869.2024.00177","title":"MyriadAL: Active Few Shot Learning for Histopathology","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"HORIZON EUROPE Health; Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Shot (pellet); Computer science; Histopathology; One shot; Artificial intelligence; Materials science; Engineering; Medicine; Mechanical engineering; Metallurgy; Pathology","score_opus":0.03145163079747109,"score_gpt":0.300815621680674,"score_spread":0.2693639908832029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401110297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015163994,0.00018942326,0.97978646,0.0016932415,0.0020717524,0.00012376581,4.3800327e-7,0.0006777515,0.013940801],"genre_scores_gemma":[0.94601816,0.000015766003,0.040991005,0.000334452,0.0002808774,0.0000983558,0.0000013182447,0.000016705138,0.012243362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993092,0.00004008351,0.000085662214,0.0003246729,0.00008067021,0.00015971984],"domain_scores_gemma":[0.9995615,0.00019997022,0.000018150798,0.00015861182,0.000033103686,0.000028673072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021916117,0.00006737387,0.000074032614,0.000083493476,0.00008328467,0.000087666864,0.00023630436,0.00004877328,0.00004391562],"category_scores_gemma":[0.000041268708,0.00006117508,0.00005036976,0.0001939503,0.000020711324,0.00031683967,0.00008449053,0.00013780328,0.00007403087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032689,0.000015254562,0.000029456047,0.000066440974,0.000018806806,0.000030774987,0.0020816254,0.0006835219,0.015460416,0.16064064,0.013682545,0.80725783],"study_design_scores_gemma":[0.00017166909,0.00037755954,0.00069757213,0.000023066437,0.000010330355,0.00008656781,0.00006817757,0.30203372,0.020531025,0.014917827,0.66086006,0.00022243534],"about_ca_topic_score_codex":0.000018968249,"about_ca_topic_score_gemma":0.000015464506,"teacher_disagreement_score":0.94450176,"about_ca_system_score_codex":0.00016522386,"about_ca_system_score_gemma":0.00006412098,"threshold_uncertainty_score":0.24946474},"labels":[],"label_agreement":null},{"id":"W4401201142","doi":"10.48550/arxiv.2407.19059","title":"The IBEX Knowledge-Base: Achieving more together with open science","year":2024,"lang":"en","type":"preprint","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity; McMaster University; McMaster University Medical Centre","funders":"NHLBI Division of Intramural Research; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Heart, Lung, and Blood Institute; NIHR Cambridge Biomedical Research Centre; Wellcome Trust; Biotechnology and Biological Sciences Research Council; Department of Health and Social Care; Medical Research Council; Common Fund; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Directorate for Biological Sciences; National Institutes of Health; Instituto Politécnico Nacional; Institute of Infection and Immunity; Fundação de Amparo à Pesquisa do Estado de São Paulo; Newcastle University; National Institute of General Medical Sciences; Institute of Circulatory and Respiratory Health; National Institute for Health and Care Research; NHS Blood and Transplant; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Canadian Allergy, Asthma and Immunology Foundation; NIH Office of the Director; Instituto Nacional de Ciência e Tecnologia de Doenças Tropicais; Canadian Institute for Advanced Research; Canadian Institutes of Health Research; Damon Runyon Cancer Research Foundation","keywords":"Resource (disambiguation); Knowledge base; Computer science; Base (topology); Knowledge management; Data science; Nanotechnology; World Wide Web; Mathematics; Materials science","score_opus":0.03499414431567971,"score_gpt":0.2868129096101361,"score_spread":0.2518187652944564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401201142","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084370784,0.027972648,0.25968897,0.0836014,0.048738483,0.02310842,0.000045203084,0.004031005,0.4684431],"genre_scores_gemma":[0.96538967,0.000100924335,0.007056929,0.0002846051,0.0007250882,0.009761592,0.0000013212975,0.00007752618,0.016602334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99675846,0.000099857265,0.00026390795,0.0013764816,0.00069253455,0.00080876297],"domain_scores_gemma":[0.9969662,0.0001617546,0.00018485733,0.002245437,0.00023711506,0.00020464633],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003338712,0.0003013476,0.00023436872,0.0001965664,0.0006588059,0.0047763437,0.010364922,0.00012128197,0.0000041531002],"category_scores_gemma":[0.00014281785,0.00018852526,0.00007425937,0.0012646763,0.0006180721,0.00046326983,0.020910613,0.0010230802,0.00005593738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018546598,0.000025540774,0.00016917757,0.00010369502,0.000058238456,0.000008686035,0.0011290192,0.00053151743,0.000015109196,0.008036456,0.0028810229,0.987023],"study_design_scores_gemma":[0.0018092025,0.0002896318,0.23072846,0.002129648,0.0003527222,0.0003340892,0.0007002843,0.11057959,0.021029767,0.12179789,0.5050682,0.0051805056],"about_ca_topic_score_codex":0.00011417759,"about_ca_topic_score_gemma":0.00024002367,"teacher_disagreement_score":0.98184246,"about_ca_system_score_codex":0.00083632587,"about_ca_system_score_gemma":0.0017229301,"threshold_uncertainty_score":0.99625677},"labels":[],"label_agreement":null},{"id":"W4401282853","doi":"10.1038/s41598-024-69119-7","title":"Comparative analysis of vision transformers and convolutional neural networks in osteoporosis detection from X-ray images","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Osteoporosis; Pattern recognition (psychology); Computer vision; Medicine; Pathology","score_opus":0.011296772729118448,"score_gpt":0.2673122503732844,"score_spread":0.25601547764416593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401282853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6392272,0.00106048,0.35495386,0.00007465614,0.004356663,0.0001453843,0.000005454084,0.000079043195,0.000097241216],"genre_scores_gemma":[0.9987016,0.000012212791,0.0011549317,0.0000063495468,0.00002584107,0.000013828323,0.000021616366,0.0000035106575,0.000060163577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805254,0.00007720896,0.00047176005,0.0008061908,0.00041456762,0.00017772664],"domain_scores_gemma":[0.99926287,0.00011454471,0.00014223241,0.0003281263,0.000094406285,0.000057821257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008997826,0.00011397812,0.00025782528,0.0007200698,0.00013088468,0.0003703483,0.00012099679,0.000060512353,0.000023083947],"category_scores_gemma":[0.0000115020985,0.00010526293,0.00011510071,0.0030990385,0.00024605714,0.0008337853,0.000055611592,0.00013860017,9.932164e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006536513,0.00014619426,0.015150338,0.00007446822,0.0008121684,0.00028274712,0.011216816,0.4910758,0.22686574,0.00016325069,0.001479828,0.25266725],"study_design_scores_gemma":[0.000058995247,0.000041364416,0.053809606,0.000028917873,0.00009464075,0.000013703741,0.000098917815,0.9323611,0.012109678,0.0009569576,0.00032033556,0.00010573137],"about_ca_topic_score_codex":0.0003694858,"about_ca_topic_score_gemma":0.00068423065,"teacher_disagreement_score":0.4412853,"about_ca_system_score_codex":0.00011120724,"about_ca_system_score_gemma":0.000055812972,"threshold_uncertainty_score":0.42924976},"labels":[],"label_agreement":null},{"id":"W4401330485","doi":"10.3390/cancers16152761","title":"The Performance and Clinical Applicability of HER2 Digital Image Analysis in Breast Cancer: A Systematic Review","year":2024,"lang":"en","type":"review","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Faculty of Medicine and Health, University of Sydney; Al-Farabi Kazakh National University","keywords":"Computer science; Standardization; Reliability (semiconductor); Systematic review; Ground truth; Data mining; Information retrieval; Set (abstract data type); Machine learning; Medical physics; Data science; Artificial intelligence; MEDLINE; Medicine","score_opus":0.025047320431451994,"score_gpt":0.3595287261739193,"score_spread":0.3344814057424673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401330485","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000064275996,0.99690163,0.00067701837,0.00011893125,0.00037507378,0.0016728673,0.00009614177,0.000049742026,0.000102187034],"genre_scores_gemma":[0.0002149832,0.99857587,0.00006531766,0.000038249123,0.000066668734,0.0009602437,0.000003233018,0.00002005921,0.00005537041],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9965962,0.0002726665,0.0017056328,0.00079721806,0.00035349256,0.00027475427],"domain_scores_gemma":[0.99718416,0.00047687648,0.0008174926,0.0013271724,0.00010199707,0.000092313596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016568226,0.00034705698,0.0028833533,0.00017182746,0.000064835986,0.00020249249,0.0011849017,0.000144703,0.0000036164104],"category_scores_gemma":[0.0000721235,0.000206804,0.0007900148,0.002986559,0.0002980849,0.00031129626,0.00036307448,0.0005376871,0.000012847381],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010910177,0.0000034083719,0.00003846547,0.59439623,0.0005051915,0.0000014186412,0.000013016416,0.0000037942852,2.7117495e-9,0.000018727816,0.00018353223,0.40483513],"study_design_scores_gemma":[0.00012255447,0.00006681642,0.00008173961,0.87393564,0.015011281,0.000072756084,0.000019829724,0.014199265,1.1856912e-7,0.000042330692,0.095815554,0.000632117],"about_ca_topic_score_codex":0.00015628723,"about_ca_topic_score_gemma":0.0001423122,"teacher_disagreement_score":0.40420303,"about_ca_system_score_codex":0.0020699508,"about_ca_system_score_gemma":0.00133607,"threshold_uncertainty_score":0.8433223},"labels":[],"label_agreement":null},{"id":"W4401402416","doi":"10.21203/rs.3.rs-4854790/v1","title":"Enhancing Convergence of Optimization Algorithms for Logistic Regression: A Breast Cancer Diagnosis Application","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Rate of convergence; Mathematical optimization; Convergence (economics); Heuristic; Computer science; Logistic regression; Algorithm; Process (computing); Optimization problem; Mathematics; Machine learning","score_opus":0.09516128063970199,"score_gpt":0.4359082333555524,"score_spread":0.3407469527158504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401402416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033018793,0.0033037364,0.9895166,0.0028651156,0.0013566874,0.002011981,0.00035713008,0.00019640026,0.00006212978],"genre_scores_gemma":[0.8349247,0.006143472,0.12740359,0.00003521475,0.0013207016,0.029594649,0.00011347688,0.000097991535,0.00036622325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965856,0.00022188212,0.00048682935,0.0011325086,0.0011025241,0.0004706215],"domain_scores_gemma":[0.9963173,0.0005058002,0.0002652698,0.0011084671,0.0016737378,0.00012939815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014851601,0.00024207603,0.0003384158,0.0004897215,0.00020169718,0.00020887579,0.0012290939,0.00033576222,0.00007335385],"category_scores_gemma":[0.0002239306,0.00022311215,0.00015998216,0.0011256443,0.00015401181,0.00016918349,0.0021195682,0.00086032,0.000018084842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017516287,0.00032578883,0.0012503515,0.023366679,0.0002663083,0.000019111389,0.0023405224,0.41898587,0.0020219297,0.010161592,0.014852313,0.5262343],"study_design_scores_gemma":[0.0001565253,0.00011097086,0.00041963396,0.0032422089,0.000023811053,0.0000062572017,0.00006243075,0.9674724,0.01369258,0.013859983,0.0006925189,0.00026068874],"about_ca_topic_score_codex":0.0009658896,"about_ca_topic_score_gemma":0.00009970438,"teacher_disagreement_score":0.86211306,"about_ca_system_score_codex":0.0008741661,"about_ca_system_score_gemma":0.000994401,"threshold_uncertainty_score":0.9098249},"labels":[],"label_agreement":null},{"id":"W4401415272","doi":"10.1109/cec60901.2024.10611837","title":"Feature Selection-driven Bias Deduction in Histopathology Images: Tackling Site-Specific Influences","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Brock University; Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Selection (genetic algorithm); Feature selection; Pattern recognition (psychology); Computer vision","score_opus":0.021797862544135516,"score_gpt":0.2652614928238623,"score_spread":0.24346363027972678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401415272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31240228,0.0031533,0.6663102,0.006448266,0.0059428625,0.00028156483,0.0000017876438,0.0014662682,0.003993472],"genre_scores_gemma":[0.9433265,0.0002326972,0.05310481,0.00018628991,0.00043090197,0.00004479536,0.0000020271561,0.000016425867,0.0026556],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871635,0.00008884623,0.00017472496,0.0005898621,0.00018649967,0.0002437334],"domain_scores_gemma":[0.99952394,0.00009238979,0.000042420117,0.00023498278,0.00006536326,0.000040917286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026103124,0.00013589225,0.0001252608,0.0004258032,0.00010357553,0.00026584437,0.00029314499,0.00012423535,0.000049218386],"category_scores_gemma":[0.00002470785,0.00012666671,0.00005283978,0.0013043621,0.00005263057,0.0008278576,0.000082212384,0.00037554684,0.0001915501],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005185615,0.000148055,0.04288731,0.0002562109,0.000035916313,0.00043568417,0.009760812,0.045699734,0.3546446,0.04460726,0.13519455,0.36627802],"study_design_scores_gemma":[0.00056291174,0.0005230024,0.054102454,0.00033495153,0.000021521419,0.0012909243,0.0003700901,0.34638023,0.06285397,0.011072637,0.5212305,0.0012567934],"about_ca_topic_score_codex":0.000100284386,"about_ca_topic_score_gemma":0.00024443725,"teacher_disagreement_score":0.63092417,"about_ca_system_score_codex":0.00044529635,"about_ca_system_score_gemma":0.00009571782,"threshold_uncertainty_score":0.5165319},"labels":[],"label_agreement":null},{"id":"W4401506922","doi":"10.1109/access.2024.3442374","title":"Ultrasound Breast Image Classification Through Domain Knowledge Integration Into Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial neural network; Artificial intelligence; Image (mathematics); Domain (mathematical analysis); Deep learning; Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.02701097292145783,"score_gpt":0.3276297319187769,"score_spread":0.3006187589973191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401506922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015155061,0.0006767674,0.97509533,0.0010096685,0.005395484,0.00021976698,0.0000019171498,0.00061353744,0.0018324745],"genre_scores_gemma":[0.98704904,0.000055227316,0.011562541,0.00015047692,0.0009921864,0.00009025607,0.000010629541,0.000024835424,0.00006477934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984978,0.00012467265,0.00028675838,0.00060578523,0.00021725093,0.00026776813],"domain_scores_gemma":[0.9989533,0.00020419732,0.00008189166,0.0005608693,0.00013848436,0.00006127961],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00027246022,0.00019307353,0.00013364741,0.00011950892,0.00019788953,0.0016400462,0.0011292966,0.000121185,0.000023876511],"category_scores_gemma":[0.000015513959,0.00017534371,0.00007980862,0.0011468367,0.000091038884,0.0046270494,0.00011799588,0.00033567921,0.00009760288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003239532,0.000108335014,0.00034949023,0.00012674305,0.000059827216,0.000026316553,0.0076773744,0.0031439138,0.030466922,0.029295295,0.012408034,0.91630536],"study_design_scores_gemma":[0.00012313854,0.000035903515,0.003380586,0.000055325425,0.000012912377,0.00016969047,0.000066003275,0.96039534,0.0047005094,0.02931544,0.0014825405,0.00026259318],"about_ca_topic_score_codex":0.00016583341,"about_ca_topic_score_gemma":0.00035474056,"teacher_disagreement_score":0.971894,"about_ca_system_score_codex":0.00034592365,"about_ca_system_score_gemma":0.00005519923,"threshold_uncertainty_score":0.9993963},"labels":[],"label_agreement":null},{"id":"W4401598927","doi":"10.1016/j.jpi.2024.100394","title":"Globalization of a telepathology network with artificial intelligence applications in Colombia: The GLORIA program study protocol","year":2024,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Faculty of Medicine, Dalhousie University; Universidad Cooperativa de ​Colo​mb​ia; Program for Nonferrous Metals Vacuum Metallurgy Innovation Team of Ministry of Science and Technology; Ministerio de Ciencia, Tecnología e Innovación","keywords":"Telepathology; Medical diagnosis; Digital pathology; Pathology; Protocol (science); Medicine; Government (linguistics); Breast cancer; Cancer; Medical physics; Computer science; Health care; Telemedicine; Alternative medicine; Internal medicine","score_opus":0.020655400519148475,"score_gpt":0.33785083085554557,"score_spread":0.3171954303363971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401598927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018919855,0.000024499386,0.95410275,0.00024409915,0.00044947574,0.025951233,0.0000010605588,0.000052944462,0.00025406328],"genre_scores_gemma":[0.79866254,0.000016742686,0.16787271,0.0001489389,0.0004747616,0.032797355,0.0000012439721,0.00001810901,0.0000075890853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821055,0.00015599547,0.0010810075,0.000088898545,0.00027745025,0.00018612859],"domain_scores_gemma":[0.998599,0.0001500392,0.0006561556,0.00029233485,0.0002721793,0.00003030699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001413645,0.0001096458,0.00023221372,0.00017797621,0.00007283704,0.00009130357,0.0006255637,0.000088027984,0.0000030580818],"category_scores_gemma":[0.000044785374,0.00006698915,0.000045458033,0.0014181191,0.00014705137,0.00048427482,0.000111523375,0.0003590542,0.0000049597975],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027872442,0.0013630195,0.018231113,0.0003726562,0.00013847409,0.00033089338,0.034595888,0.06812945,0.000042124644,0.039148718,0.0010861128,0.83628285],"study_design_scores_gemma":[0.002264338,0.039074924,0.03022038,0.0010530842,0.0003940137,0.012287469,0.029710978,0.7447433,0.0014335047,0.08540077,0.05229751,0.0011197693],"about_ca_topic_score_codex":0.0000022292897,"about_ca_topic_score_gemma":0.000041879626,"teacher_disagreement_score":0.83516306,"about_ca_system_score_codex":0.00010217532,"about_ca_system_score_gemma":0.00025895357,"threshold_uncertainty_score":0.2731738},"labels":[],"label_agreement":null},{"id":"W4401686393","doi":"10.3390/jimaging10080201","title":"Artificial Intelligence (AI) and Nuclear Features from the Fine Needle Aspirated (FNA) Tissue Samples to Recognize Breast Cancer","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Breast cancer; Mammography; Artificial intelligence; Breast cancer screening; Cancer; Fine-needle aspiration; Medicine; Radiology; Computer science; Biopsy; Internal medicine","score_opus":0.02345709623405835,"score_gpt":0.2955892779004274,"score_spread":0.27213218166636904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401686393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07800772,0.008786105,0.7521444,0.155995,0.004565585,0.00017780488,0.000044665823,0.00013854589,0.00014016927],"genre_scores_gemma":[0.9840596,0.000119607066,0.012505949,0.0019886037,0.0012808316,0.000002201947,2.7316355e-7,0.000018597397,0.000024353561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990276,0.000054267177,0.00028265791,0.00021150231,0.00025487048,0.00016911382],"domain_scores_gemma":[0.9992979,0.00017252262,0.00010749124,0.00016835118,0.0001664152,0.000087280685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035096507,0.00011154015,0.00013992992,0.000117871685,0.00013410712,0.00077680516,0.00045312042,0.000025980966,0.000080195],"category_scores_gemma":[0.00006140423,0.00007735901,0.00004437035,0.0004794211,0.00004537453,0.0006746195,0.00014552215,0.00037437503,0.000018029321],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024549123,0.0000065940603,0.00022093098,0.000006703438,0.000028489134,0.00003768588,0.0018754536,0.00028408912,0.013034522,0.00037139785,0.009071431,0.9750382],"study_design_scores_gemma":[0.00049420126,0.0008057925,0.08544171,0.0054045767,0.0004169,0.00770934,0.0037317697,0.36550134,0.17329362,0.096355624,0.25883934,0.0020057906],"about_ca_topic_score_codex":0.00064193725,"about_ca_topic_score_gemma":0.00015250237,"teacher_disagreement_score":0.97303236,"about_ca_system_score_codex":0.00010489364,"about_ca_system_score_gemma":0.000101846956,"threshold_uncertainty_score":0.749075},"labels":[],"label_agreement":null},{"id":"W4401754059","doi":"10.1109/ichi61247.2024.00016","title":"Multiple Multi-Modal Methods of Malignant Mammogram Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Government of Canada; University of Manitoba","keywords":"Computer science; Modal; Artificial intelligence; Pattern recognition (psychology); Materials science","score_opus":0.07026919003620555,"score_gpt":0.3767617999546647,"score_spread":0.30649260991845917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401754059","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001639877,0.00026759654,0.99458766,0.0004430102,0.0011366688,0.00014618973,0.000001595517,0.0004630941,0.0013142948],"genre_scores_gemma":[0.46542385,0.000015290918,0.5340187,0.000024192874,0.00002896661,0.000021831884,6.549097e-7,0.0000060679236,0.0004604596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899405,0.000100600686,0.00023019449,0.0003592229,0.00016745694,0.00014847195],"domain_scores_gemma":[0.9992213,0.00018319313,0.00004646032,0.000441395,0.0000635999,0.00004405386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052385946,0.00008801554,0.00010382592,0.00013809517,0.00003639023,0.00009308669,0.00039226018,0.00006374272,0.000024509678],"category_scores_gemma":[0.00004099652,0.00007282494,0.00007408912,0.00054368743,0.00003841588,0.0003524017,0.0001108141,0.00009583764,0.000046597765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031626353,0.000038316713,0.00031553608,0.00005261407,0.000020062143,0.0000024195613,0.00037267565,0.00008584441,0.12134122,0.02655959,0.00036805007,0.8508405],"study_design_scores_gemma":[0.00009390432,0.000045604993,0.003766832,0.000021041034,0.0000051282627,0.000008810529,0.000037569553,0.86174613,0.12478445,0.0009949007,0.008405744,0.00008985759],"about_ca_topic_score_codex":0.00011286421,"about_ca_topic_score_gemma":0.000028133829,"teacher_disagreement_score":0.8616603,"about_ca_system_score_codex":0.00007470041,"about_ca_system_score_gemma":0.000060540373,"threshold_uncertainty_score":0.2969715},"labels":[],"label_agreement":null},{"id":"W4401769119","doi":"10.18280/isi.290437","title":"3D Synthetic View for X-Ray Breast Cancer Mammogram Images","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Artificial intelligence; Mammography; Cancer; Computer science; Computer vision; Medicine; Internal medicine","score_opus":0.0175663946436,"score_gpt":0.2646264640568318,"score_spread":0.24706006941323183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009237229,0.033061247,0.9398852,0.0047066025,0.015093037,0.001271349,0.0007127397,0.0008193867,0.0035267298],"genre_scores_gemma":[0.9249853,0.0075437347,0.05512012,0.0012735454,0.0026301378,0.002600443,0.00011374989,0.0001342681,0.005598711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973077,0.00011515899,0.0009358925,0.0004269619,0.00046754346,0.0007467481],"domain_scores_gemma":[0.998125,0.00024574902,0.00029824467,0.0005406566,0.00062186003,0.00016850224],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00090580125,0.00041547682,0.00036762157,0.0004137552,0.00046057976,0.002744527,0.0005940657,0.0002829632,0.00026438487],"category_scores_gemma":[0.00010502167,0.0004259154,0.00024673075,0.0012276266,0.0003574193,0.011402216,0.00017696036,0.00031457888,0.00058477296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002716604,0.000021096963,0.000030787785,0.005502939,0.00012241404,0.000006210021,0.004851972,0.0024982665,0.000070181464,0.011351936,0.0080252625,0.96749175],"study_design_scores_gemma":[0.00032206683,0.00020488528,0.00094026915,0.0049680183,0.00016906859,0.0006457076,0.0002606917,0.45485613,0.000832918,0.0075060576,0.5286376,0.0006566213],"about_ca_topic_score_codex":0.0006462247,"about_ca_topic_score_gemma":0.000050013947,"teacher_disagreement_score":0.96683514,"about_ca_system_score_codex":0.0016022624,"about_ca_system_score_gemma":0.0006187423,"threshold_uncertainty_score":0.9998193},"labels":[],"label_agreement":null},{"id":"W4401831771","doi":"10.18280/ria.380428","title":"Catalyzing Healthcare Advancements: Integrating IoT-Driven Smart Systems and Deep Learning for Precision Breast Cancer Detection in Telemedicine","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Internet of Things; Telemedicine; Breast cancer; Computer science; Health care; Healthcare system; Artificial intelligence; Cancer; Embedded system; Medicine","score_opus":0.027551073367922563,"score_gpt":0.31004301415214647,"score_spread":0.2824919407842239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401831771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02433584,0.008097737,0.9635385,0.0010037266,0.0020382793,0.0007249369,0.0000049378964,0.00021215607,0.000043864962],"genre_scores_gemma":[0.9951747,0.00094791286,0.0029947069,0.000036067988,0.00026497288,0.0003717391,0.0000042390548,0.000027059185,0.00017859098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980072,0.00009281622,0.0005773516,0.00072960556,0.00020417488,0.00038886745],"domain_scores_gemma":[0.9989933,0.00033856375,0.0001308906,0.00029125868,0.00015451404,0.00009147363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007029326,0.00019674153,0.00024464392,0.00032015546,0.0002559185,0.0002336908,0.00028551588,0.00009682131,0.000007527226],"category_scores_gemma":[0.00011146416,0.00018813806,0.000052579628,0.0009026665,0.000045859026,0.0004974478,0.00012306221,0.0003989993,0.000013858714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002272338,0.000014566052,0.0013792774,0.00050843495,0.000011623799,0.000006668548,0.0026535552,0.070771046,0.005456771,0.0008628429,0.000009798952,0.9183027],"study_design_scores_gemma":[0.000057203793,0.00019056122,0.00013804059,0.0016272307,0.000008144811,0.00008649298,0.0015490535,0.98332125,0.00839671,0.00035245548,0.004084209,0.0001886212],"about_ca_topic_score_codex":0.001152919,"about_ca_topic_score_gemma":0.0012540212,"teacher_disagreement_score":0.97083884,"about_ca_system_score_codex":0.00050331175,"about_ca_system_score_gemma":0.000060648013,"threshold_uncertainty_score":0.76720476},"labels":[],"label_agreement":null},{"id":"W4401835368","doi":"10.18280/ria.380405","title":"Data Augmentation by Wavelet Transform for Breast Cancer Based on Deep Learning","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Wavelet transform; Wavelet; Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Cancer; Medicine; Internal medicine","score_opus":0.049007312693386915,"score_gpt":0.3178882298732041,"score_spread":0.26888091717981716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401835368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022540233,0.00053725025,0.9911244,0.005478815,0.0010689477,0.00039846715,0.00019977262,0.00030112738,0.0006658201],"genre_scores_gemma":[0.9881186,0.00026975118,0.009015949,0.0004118797,0.0002852974,0.00023711941,0.00012722351,0.000042399795,0.0014917812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836135,0.000040237992,0.00030654532,0.0007561483,0.00022635532,0.00030936205],"domain_scores_gemma":[0.9988583,0.00027933368,0.00005703124,0.00066625123,0.00006763938,0.000071466784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004793787,0.00016339624,0.00013052727,0.00012420511,0.0002154154,0.00028803034,0.00086124084,0.00007038792,0.00019223719],"category_scores_gemma":[0.000026009728,0.00016212533,0.000070306516,0.0005629533,0.000038810085,0.0006593621,0.00006465173,0.00022510423,0.00013431512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026113077,0.00003675495,0.000005799288,0.00012112473,0.000013294244,0.0000024831365,0.00041931777,0.08039927,0.001871694,0.0011597313,0.0030546733,0.9128897],"study_design_scores_gemma":[0.000040173807,0.00012895711,0.00000722621,0.00015015875,0.00001292156,0.000008768175,0.00009593198,0.8991899,0.047092676,0.00065383245,0.0524415,0.00017795926],"about_ca_topic_score_codex":0.000055643028,"about_ca_topic_score_gemma":0.000047144043,"teacher_disagreement_score":0.9878932,"about_ca_system_score_codex":0.000216454,"about_ca_system_score_gemma":0.00008366953,"threshold_uncertainty_score":0.6611279},"labels":[],"label_agreement":null},{"id":"W4401992416","doi":"10.3390/curroncol31090374","title":"A Novel Deep Learning Model for Breast Tumor Ultrasound Image Classification with Lesion Region Perception","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Perception; Deep learning; Artificial intelligence; Breast tumor; Lesion; Ultrasound; Radiology; Image (mathematics); Pathology; Breast cancer; Pattern recognition (psychology); Bioinformatics; Internal medicine; Computer science; Cancer; Neuroscience; Biology","score_opus":0.126416113621349,"score_gpt":0.37543630911037107,"score_spread":0.24902019548902207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401992416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01436678,0.00020239431,0.98246163,0.00087195827,0.0011337837,0.00037895818,0.0000043334617,0.00039116788,0.00018898204],"genre_scores_gemma":[0.93777126,0.000096450596,0.061336126,0.00003677494,0.00033996376,0.00025179132,0.000021502407,0.000025431435,0.00012067021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870807,0.000061537,0.00020846914,0.00058983645,0.00017594121,0.00025611828],"domain_scores_gemma":[0.9992268,0.00017281053,0.00011590283,0.00024591445,0.00017340653,0.000065164575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027261855,0.00015106371,0.00014864915,0.00016443382,0.00019281408,0.00015397459,0.00027267387,0.00008282971,0.0000051523984],"category_scores_gemma":[0.000033824526,0.00013269697,0.000065121894,0.00031301597,0.000080431884,0.00065677695,0.0000535143,0.00032263153,0.00002953607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096508986,0.00015280217,0.00016052871,0.00016742629,0.000012755698,0.0000035815478,0.0019240879,0.003471927,0.05200058,0.0049002585,0.00077511766,0.93633443],"study_design_scores_gemma":[0.0004075874,0.00035876702,0.0026071551,0.00009436114,0.00002503956,0.0006877241,0.00014719254,0.9873213,0.000090808404,0.0009201201,0.007170309,0.00016960113],"about_ca_topic_score_codex":0.0000050826566,"about_ca_topic_score_gemma":0.000026880367,"teacher_disagreement_score":0.9838494,"about_ca_system_score_codex":0.0008056766,"about_ca_system_score_gemma":0.00021030089,"threshold_uncertainty_score":0.5411225},"labels":[],"label_agreement":null},{"id":"W4402083765","doi":"10.1016/j.ajpath.2024.08.006","title":"A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images","year":2024,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency; Vancouver General Hospital; Pancreas Centre (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; BC Cancer Foundation; Michael Smith Health Research BC; VGH and UBC Hospital Foundation","keywords":"Pancreatic ductal adenocarcinoma; Pathology; Adenocarcinoma; Identification (biology); Pancreas; Medicine; Pancreatic cancer; Biology; Cancer; Internal medicine","score_opus":0.007795242050368955,"score_gpt":0.242654639906388,"score_spread":0.23485939785601903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402083765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27083254,0.0012124941,0.72665644,0.0008448059,0.0002882956,0.00012271342,0.000002386891,0.00001098854,0.000029351073],"genre_scores_gemma":[0.9804474,0.000029600289,0.01930041,0.0001047765,0.00006782456,0.00001975314,6.4057195e-7,0.000013785168,0.000015793485],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983591,0.00051599904,0.00050609146,0.0002252029,0.0002307859,0.00016284574],"domain_scores_gemma":[0.99806404,0.0005119479,0.0008126561,0.00039588378,0.00019037597,0.000025083038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010671061,0.00010739097,0.00028501346,0.00018069554,0.00007749475,0.000028508483,0.0007015534,0.000039933955,0.000001633555],"category_scores_gemma":[0.00027651593,0.00006662546,0.00020475061,0.00051149854,0.00047696623,0.00010282467,0.00006752112,0.00030176798,0.0000010093299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002510814,0.000166342,0.009906663,0.00018231978,0.00020622798,0.00029306478,0.0040923995,0.1329713,0.6922044,0.0045660767,0.000082254046,0.15507787],"study_design_scores_gemma":[0.00069507636,0.0046630767,0.09752547,0.00012558093,0.0004027112,0.003713124,0.0017154317,0.7432863,0.14444697,0.0029788804,0.00018320924,0.00026414843],"about_ca_topic_score_codex":0.0000074704158,"about_ca_topic_score_gemma":5.945991e-7,"teacher_disagreement_score":0.7096149,"about_ca_system_score_codex":0.00005194699,"about_ca_system_score_gemma":0.00011813421,"threshold_uncertainty_score":0.27169073},"labels":[],"label_agreement":null},{"id":"W4402094962","doi":"10.1016/j.artmed.2024.102972","title":"SG-Fusion: A swin-transformer and graph convolution-based multi-modal deep neural network for glioma prognosis","year":2024,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Machine learning; Pattern recognition (psychology); Data mining","score_opus":0.05309072937119139,"score_gpt":0.32983427025973255,"score_spread":0.27674354088854114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402094962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032729615,0.002470301,0.95355016,0.0075011086,0.0026682243,0.00081042736,0.000002692807,0.00023435666,0.000033116936],"genre_scores_gemma":[0.9742414,0.00006524369,0.024233367,0.00048560736,0.0006688445,0.0002706626,0.0000055359315,0.00002027026,0.000009069624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978422,0.00007078942,0.0006016176,0.00066345785,0.00033010164,0.0004918344],"domain_scores_gemma":[0.9988124,0.00060322904,0.00006291042,0.00026576727,0.00012558667,0.00013013094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008558291,0.00022846843,0.00027721544,0.00035071984,0.00019620666,0.0001125846,0.0003879963,0.00012301498,0.000038976905],"category_scores_gemma":[0.00013192432,0.00019368243,0.00008053709,0.0016271686,0.00034071007,0.0003605122,0.000037019217,0.00027191947,0.000013684488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016206462,0.000110518464,0.0012167153,0.00021962887,0.000032522174,0.00008193164,0.0028296555,0.017124593,0.006336959,0.030829012,0.00044391965,0.9406125],"study_design_scores_gemma":[0.00012207022,0.00051895814,0.00042561785,0.000279662,0.000023584005,0.000023429291,0.00019997716,0.9600089,0.0092825405,0.028277796,0.00062609836,0.00021135824],"about_ca_topic_score_codex":0.0003702434,"about_ca_topic_score_gemma":0.0012139115,"teacher_disagreement_score":0.9428843,"about_ca_system_score_codex":0.00009675381,"about_ca_system_score_gemma":0.00008251227,"threshold_uncertainty_score":0.78981405},"labels":[],"label_agreement":null},{"id":"W4402282873","doi":"10.1016/j.media.2024.103342","title":"ATEC23 Challenge: Automated prediction of treatment effectiveness in ovarian cancer using histopathological images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Taiwan University of Science and Technology; Tri-Service General Hospital; National Science and Technology Council","keywords":"Bevacizumab; Medicine; Ovarian cancer; Perforation; Oncology; Cancer; Internal medicine; Adverse effect; Medical physics; Chemotherapy","score_opus":0.0252842723934936,"score_gpt":0.33213852774531333,"score_spread":0.3068542553518197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402282873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15168187,0.0019048991,0.844237,0.00070555863,0.0004981609,0.00018016936,0.000022149978,0.0005739384,0.00019623882],"genre_scores_gemma":[0.9954727,0.00044904847,0.003857853,0.000016504415,0.00008465,0.00007927341,0.0000067460446,0.0000096897775,0.000023479668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979739,0.0003693782,0.00037679827,0.00057609443,0.00047034686,0.00023345479],"domain_scores_gemma":[0.99921536,0.00018490407,0.00007053063,0.00035067232,0.000073859264,0.000104658975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008325869,0.00016250071,0.0004287013,0.00061894365,0.00004975363,0.000059813454,0.00030782536,0.00015359145,0.00016010768],"category_scores_gemma":[0.00009793762,0.00012659654,0.00022002966,0.0025677285,0.00013375978,0.00035322306,0.00010464699,0.00017867745,0.000006781287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018730205,0.0018157377,0.052882742,0.0012307415,0.0053243376,0.005655008,0.004766189,0.03232094,0.1910229,0.001274247,0.00038470753,0.70313513],"study_design_scores_gemma":[0.0003073335,0.00016655627,0.036125567,0.000136398,0.0004044323,0.00001598349,0.000011490148,0.9556322,0.006831997,0.00017016874,0.00009382543,0.000104061335],"about_ca_topic_score_codex":0.0020918672,"about_ca_topic_score_gemma":0.00017785408,"teacher_disagreement_score":0.92331123,"about_ca_system_score_codex":0.0011146647,"about_ca_system_score_gemma":0.00024190432,"threshold_uncertainty_score":0.51624566},"labels":[],"label_agreement":null},{"id":"W4402308777","doi":"10.18280/ts.410436","title":"An Improved Deep Network Model to Isolate Lung Nodules from Histopathological Images Using an Orchestrated and Shifted Window Vision Transformer","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformer; Window (computing); Artificial intelligence; Lung; Computer science; Computer vision; Medicine; Engineering; Electrical engineering; Internal medicine; Voltage","score_opus":0.02246586199714019,"score_gpt":0.2828871926642287,"score_spread":0.2604213306670885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402308777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42242718,0.00021179751,0.57654375,0.00015400717,0.00015224994,0.00023594766,0.000011400644,0.0002469441,0.000016746517],"genre_scores_gemma":[0.83546543,0.000010609765,0.16400322,0.0002272236,0.00022887452,0.000024051575,0.00001297355,0.000022446497,0.00000516735],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980009,0.00013090244,0.00034245217,0.0008504524,0.000265094,0.00041017708],"domain_scores_gemma":[0.99933994,0.000047281992,0.000046700992,0.00028362765,0.00005169813,0.00023077326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004251707,0.00026085152,0.0002185213,0.00011127664,0.00021913517,0.0005353875,0.00039397203,0.0001223601,0.00004193001],"category_scores_gemma":[0.0000026331925,0.00023208065,0.000056670742,0.00037159224,0.000059955244,0.0014213402,0.0000489441,0.00023027,0.0000033644171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016580703,0.00013090439,0.00017272713,0.000031676867,0.00003310522,0.00005333367,0.002615768,0.14151926,0.7656598,0.0004922646,0.000040394963,0.08908491],"study_design_scores_gemma":[0.00032924008,0.00065455306,0.00451047,0.000057483612,0.00003554879,0.000014423323,0.000021548725,0.98607045,0.0044436203,0.0035307582,0.000028590808,0.00030331337],"about_ca_topic_score_codex":0.000089192916,"about_ca_topic_score_gemma":0.000052816024,"teacher_disagreement_score":0.8445512,"about_ca_system_score_codex":0.00018240178,"about_ca_system_score_gemma":0.000074727286,"threshold_uncertainty_score":0.9463974},"labels":[],"label_agreement":null},{"id":"W4402351346","doi":"10.1109/ijcnn60899.2024.10650015","title":"ProtoTree-MIL: Interpretable Multiple Instance Learning for Whole Slide Image Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Contextual image classification; Pattern recognition (psychology); Image (mathematics); Machine learning; Computer vision","score_opus":0.021682841450478697,"score_gpt":0.2829549025629385,"score_spread":0.26127206111245976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402351346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016572981,0.00018131407,0.98755115,0.001271791,0.00069463754,0.00084455294,0.0000018574958,0.0010092357,0.006788139],"genre_scores_gemma":[0.84964097,0.0000099742465,0.14278291,0.00011696483,0.00012612366,0.00095197407,0.000004481328,0.000022965212,0.006343635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988575,0.00003672709,0.000203696,0.00050160446,0.00016360341,0.00023685217],"domain_scores_gemma":[0.99930185,0.00016729096,0.00004994401,0.0003413943,0.00009323298,0.000046282126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030666258,0.00011576042,0.00010034777,0.00010703593,0.00014250995,0.00047289766,0.00040893393,0.000055779732,0.000016391628],"category_scores_gemma":[0.00010990271,0.00010697611,0.00006730104,0.00040601805,0.000028948147,0.0013386713,0.00010708792,0.00019195642,0.0001589857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060770493,0.000061296305,0.0007788863,0.00045641113,0.00005235855,0.000007074604,0.0019460781,0.0013417716,0.23721316,0.049802735,0.02082117,0.6874583],"study_design_scores_gemma":[0.00013228497,0.00008468409,0.00023215506,0.00006422758,0.0000030470922,0.0000042868087,0.000057394052,0.7826361,0.018432925,0.002300144,0.1959331,0.000119613156],"about_ca_topic_score_codex":0.000028006894,"about_ca_topic_score_gemma":0.000047125268,"teacher_disagreement_score":0.84798366,"about_ca_system_score_codex":0.0001924941,"about_ca_system_score_gemma":0.00008536851,"threshold_uncertainty_score":0.4560163},"labels":[],"label_agreement":null},{"id":"W4402452652","doi":"10.11159/icbes24.151","title":"Convolutional networks applied to X-ray images for disease classification","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Instituto Politécnico Nacional","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Contextual image classification; Pattern recognition (psychology); Computer vision; Remote sensing; Image (mathematics); Geology","score_opus":0.008420069339681457,"score_gpt":0.21691841335341183,"score_spread":0.20849834401373038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402452652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012948434,0.0010417533,0.980723,0.0011411712,0.0032013874,0.0006098665,0.0000026418197,0.00021223396,0.00011951106],"genre_scores_gemma":[0.99648786,0.000011199591,0.0029241734,0.000057926416,0.00024113788,0.00010038317,8.738387e-8,0.000006593903,0.00017061377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888813,0.0000024115711,0.00016593834,0.0004415394,0.00027285563,0.00022909377],"domain_scores_gemma":[0.9994632,0.00011750679,0.00004590015,0.0001035917,0.00012755636,0.00014226322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037757462,0.00011283541,0.00012619812,0.00024223117,0.00016810579,0.00053737086,0.00047656827,0.000020756175,7.15416e-8],"category_scores_gemma":[0.000021187416,0.00008223757,0.000029168988,0.0011273929,0.000081004684,0.00023164108,0.00014104115,0.000113351656,3.0889046e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028298671,0.000020438445,0.00019947914,0.000284726,0.000018898685,3.6265072e-7,0.000061551,0.045491733,0.007119498,0.90186864,0.0040342207,0.04087218],"study_design_scores_gemma":[0.00006961782,0.000058988186,0.0039205304,0.00018201752,0.000005637714,0.0000041529047,0.0000012836585,0.99186087,0.00046798016,0.00016212832,0.0031605235,0.00010629537],"about_ca_topic_score_codex":0.000002074192,"about_ca_topic_score_gemma":8.652938e-8,"teacher_disagreement_score":0.98353946,"about_ca_system_score_codex":0.00006674112,"about_ca_system_score_gemma":0.000043983124,"threshold_uncertainty_score":0.51818794},"labels":[],"label_agreement":null},{"id":"W4402509827","doi":"10.1109/tpami.2024.3461321","title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute","keywords":"Artificial intelligence; Image segmentation; Computer vision; Computer science; Segmentation; Medical imaging; Image processing; Image (mathematics); Anatomy; Pattern recognition (psychology); Medicine","score_opus":0.022208921524262615,"score_gpt":0.2997916370499746,"score_spread":0.27758271552571195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402509827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009124611,0.00046217383,0.98742497,0.0022731426,0.00023402703,0.00013341632,0.000022049206,0.00025718496,0.00006842398],"genre_scores_gemma":[0.99307895,0.0006776108,0.00553955,0.00040334236,0.00006351816,0.000034490586,0.000007205718,0.000018646286,0.00017669657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794877,0.00010311759,0.00040102768,0.0006992822,0.00060446135,0.00024335651],"domain_scores_gemma":[0.9990348,0.00021442358,0.00008700214,0.00040042936,0.00009858385,0.00016474677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004073311,0.00023957634,0.00027668785,0.0006909823,0.00019224307,0.0003739435,0.0003529297,0.00007834517,0.00036624778],"category_scores_gemma":[0.000008657887,0.0001892042,0.0001605607,0.0022481722,0.0000754895,0.0005557129,0.0000071579116,0.0003901242,0.000035055047],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012059476,0.000043587643,0.0002649881,0.000055649885,0.0004893375,0.000076364835,0.00038815418,0.002829461,0.0009579168,0.000035876845,0.000011222257,0.9948354],"study_design_scores_gemma":[0.00012336129,0.00020704948,0.00046813482,0.00022580192,0.0005935926,0.00008691949,0.0000896376,0.86565256,0.13190515,0.00009471188,0.00021454025,0.0003385395],"about_ca_topic_score_codex":0.00084302004,"about_ca_topic_score_gemma":0.0011203615,"teacher_disagreement_score":0.9944968,"about_ca_system_score_codex":0.00009760181,"about_ca_system_score_gemma":0.00005824788,"threshold_uncertainty_score":0.7715524},"labels":[],"label_agreement":null},{"id":"W4402565067","doi":"10.1016/j.media.2024.103346","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Institut TransMedTech; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Institut Du Cancer de Montréal; Canada First Research Excellence Fund; Université de Montréal","keywords":"Normalization (sociology); Distillation; Computer science; Artificial intelligence; Transfer of learning; Machine learning; Chemistry; Chromatography","score_opus":0.011029659896524527,"score_gpt":0.25581270989714217,"score_spread":0.24478305000061765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402565067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009145434,0.0006661491,0.9883373,0.0003020779,0.00051092636,0.0002830177,0.00005318535,0.00038447,0.00031746665],"genre_scores_gemma":[0.98908275,0.00013665638,0.009297894,0.000053122825,0.0006992996,0.00014099006,0.00040975245,0.000024804694,0.00015470604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997875,0.00019969883,0.0003475322,0.00058114255,0.0006943175,0.0003023525],"domain_scores_gemma":[0.99891573,0.0003712448,0.000033456865,0.00027178088,0.00023333127,0.00017446846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009019383,0.00018945892,0.0003147447,0.00028005484,0.00019957162,0.00027792162,0.00030553262,0.000120079865,0.00028768016],"category_scores_gemma":[0.00009115776,0.00015139987,0.0002480909,0.003133422,0.00009884154,0.0008655455,0.00005482052,0.00016428813,0.000020662246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011249335,0.0010613035,0.021281539,0.0017451342,0.018604608,0.00040049807,0.010424368,0.08400949,0.0045993333,0.014599918,0.021979766,0.8201691],"study_design_scores_gemma":[0.00035046233,0.00019330665,0.0026192656,0.00005046155,0.001344502,0.000008411209,0.000024127407,0.9895144,0.0007902459,0.00008283031,0.004848176,0.00017380426],"about_ca_topic_score_codex":0.00009043668,"about_ca_topic_score_gemma":0.0010053688,"teacher_disagreement_score":0.9799373,"about_ca_system_score_codex":0.00014589576,"about_ca_system_score_gemma":0.00016025295,"threshold_uncertainty_score":0.61739075},"labels":[],"label_agreement":null},{"id":"W4402574396","doi":"10.1093/ibd/izae204","title":"Deployment of an Artificial Intelligence Histology Tool to Aid Qualitative Assessment of Histopathology Using the Nancy Histopathology Index in Ulcerative Colitis","year":2024,"lang":"en","type":"article","venue":"Inflammatory Bowel Diseases","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Takeda Foundation","keywords":"Histopathology; Ulcerative colitis; Artificial intelligence; Medicine; Histology; Confusion; Correlation; Pathology; Machine learning; Gastroenterology; Computer science; Mathematics; Disease; Psychology","score_opus":0.03584519418996793,"score_gpt":0.35877422790267255,"score_spread":0.32292903371270465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402574396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67595077,0.00033212,0.3218447,0.00024219796,0.0010274348,0.0004334046,0.00003669723,0.00007519913,0.000057489342],"genre_scores_gemma":[0.99169576,0.000012494804,0.007849364,0.00013692278,0.00007087249,0.00019757892,0.0000027302424,0.000019652087,0.000014594573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99664944,0.0011678722,0.0008888306,0.0006207171,0.00034533598,0.00032780654],"domain_scores_gemma":[0.9983958,0.00041752288,0.00027203117,0.00063429313,0.00018557494,0.000094768846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000809885,0.00022256804,0.00037777587,0.00044702392,0.00009599756,0.000035829427,0.00068176823,0.00010805886,0.000027854672],"category_scores_gemma":[0.00016351668,0.00020190995,0.000105694584,0.0004984921,0.00047465172,0.00045686436,0.00025910832,0.0002332013,0.0000046906275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008892013,0.00088020856,0.019511247,0.0008178161,0.000078310695,0.0019968462,0.10563445,0.041346934,0.01838755,0.6839052,0.00018219861,0.12637007],"study_design_scores_gemma":[0.000413289,0.0015677651,0.5852693,0.000540275,0.000112092566,0.00019878767,0.0061360765,0.27562574,0.0071500484,0.12101291,0.0009993494,0.0009744193],"about_ca_topic_score_codex":0.00017036527,"about_ca_topic_score_gemma":0.0006726602,"teacher_disagreement_score":0.565758,"about_ca_system_score_codex":0.0010090036,"about_ca_system_score_gemma":0.0008561796,"threshold_uncertainty_score":0.8233649},"labels":[],"label_agreement":null},{"id":"W4402643858","doi":"10.1016/j.neucom.2024.128630","title":"A systematic review on deep learning based methods for cervical cell image analysis","year":2024,"lang":"en","type":"review","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Image (mathematics); Deep learning; Pattern recognition (psychology); Machine learning","score_opus":0.04125037562090792,"score_gpt":0.40512952083324055,"score_spread":0.3638791452123326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402643858","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.816894e-9,0.5010517,0.4964902,0.000032607524,0.00036952074,0.001601143,0.0000011055463,0.0003376936,0.00011598297],"genre_scores_gemma":[8.8223453e-7,0.77285016,0.22569592,0.0004750388,0.00018793019,0.0006105588,0.000012497269,0.000093947856,0.00007306305],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99314374,0.0026640499,0.0016270108,0.001589209,0.0004374848,0.00053850934],"domain_scores_gemma":[0.9932858,0.0039430712,0.0012273308,0.0012607937,0.00014447303,0.00013853042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031365016,0.00071825273,0.0039310553,0.00087628135,0.00025435694,0.00051173294,0.0017077266,0.00022464356,0.000006690868],"category_scores_gemma":[0.0006419558,0.0005599605,0.0026695938,0.004165719,0.000020192647,0.00011667478,0.0004829417,0.0012245927,0.00014354699],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.8301417e-7,0.000010638856,9.695787e-9,0.6416455,0.00019487232,0.000009023165,0.000011971157,0.00023098208,2.2769562e-7,0.000036901594,0.000037001824,0.3578226],"study_design_scores_gemma":[0.000049363527,0.000105510044,3.428128e-8,0.32497317,0.013838505,0.000019736939,9.401943e-7,0.5659982,0.0000031625502,0.000022816956,0.09459414,0.00039442087],"about_ca_topic_score_codex":0.0000023709279,"about_ca_topic_score_gemma":4.7104615e-7,"teacher_disagreement_score":0.5657672,"about_ca_system_score_codex":0.00032375322,"about_ca_system_score_gemma":0.00017193741,"threshold_uncertainty_score":0.99968517},"labels":[],"label_agreement":null},{"id":"W4402693911","doi":"10.1136/jcp-2024-209643","title":"Assessment of AI-based computational H&amp;E staining versus chemical H&amp;E staining for primary diagnosis in lymphomas: a brief interim report","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Concordance; Medical diagnosis; Stain; Lymph node; Pathology; Medicine; Staining; Histology; Digital pathology; Telepathology; Chemical pathology; Differential diagnosis; Radiology; Internal medicine","score_opus":0.12835644305900648,"score_gpt":0.48160717194749414,"score_spread":0.35325072888848763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402693911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31122616,0.00016207797,0.683813,0.0017247904,0.0027432472,0.00013401467,0.000006808012,0.00003202474,0.000157898],"genre_scores_gemma":[0.7273553,0.000019191242,0.27171174,0.0005060752,0.00034851188,0.000027229815,0.000008595705,0.000015840613,0.0000075349267],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957074,0.00038877566,0.0026149026,0.0004771595,0.00051892677,0.00029285045],"domain_scores_gemma":[0.9912856,0.006630167,0.0011255399,0.00032813745,0.00049940165,0.00013114166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054866057,0.0001715049,0.000798723,0.00035947465,0.0000368713,0.000071985254,0.00053501525,0.00024153868,0.000017083814],"category_scores_gemma":[0.0025897757,0.00016141399,0.0004345776,0.00040361471,0.00019864205,0.00037372537,0.00019878318,0.0007929846,0.0000014514346],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046931873,0.003041002,0.26731813,0.0014126925,0.00085680664,0.0077327434,0.0019346755,0.06349244,0.0034169003,0.017030602,0.0064316154,0.6226392],"study_design_scores_gemma":[0.034216247,0.015955376,0.40229136,0.0043150363,0.00048854714,0.006537416,0.00029516555,0.3732641,0.0016949879,0.082289636,0.076834545,0.0018175755],"about_ca_topic_score_codex":0.0000056399326,"about_ca_topic_score_gemma":0.00000990132,"teacher_disagreement_score":0.62082165,"about_ca_system_score_codex":0.00047284304,"about_ca_system_score_gemma":0.0022748234,"threshold_uncertainty_score":0.65822715},"labels":[],"label_agreement":null},{"id":"W4402727251","doi":"10.1109/mwscas60917.2024.10658872","title":"A Novel Super-pixel Grid Mixing-Based Augmentation with a Feature Fusion of Convolutional Networks for Breast Ultrasound Image Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pixel; Feature (linguistics); Pattern recognition (psychology); Segmentation; Convolutional neural network; Computer vision; Fusion; Grid; Breast ultrasound; Image fusion; Image (mathematics); Image segmentation; Mammography; Medicine; Mathematics; Breast cancer","score_opus":0.008436894991083337,"score_gpt":0.24210005383299293,"score_spread":0.2336631588419096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402727251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068820226,0.000107909495,0.9903121,0.000980986,0.00078346685,0.00053662603,0.0000936274,0.00020755148,0.00009570801],"genre_scores_gemma":[0.58667356,0.0000072069097,0.41226724,0.00022512476,0.00029057282,0.00015121618,0.00016129165,0.00002216817,0.00020164733],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988346,0.00002470934,0.00019403858,0.00041314255,0.00033759978,0.0001958913],"domain_scores_gemma":[0.99921227,0.0002460109,0.00007970937,0.00019968179,0.00021184322,0.000050493487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022107273,0.00015177457,0.00012094641,0.0001381521,0.00012120979,0.00018570952,0.00019800071,0.000077392804,0.00003633029],"category_scores_gemma":[0.000007699918,0.00012564557,0.00007331152,0.00052153744,0.00006632639,0.0007672248,0.000028316368,0.000112559515,0.0000031523807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004749322,0.0002157969,0.0005635958,0.00040601954,0.00013534512,0.0000032405621,0.0006460702,0.034824904,0.9093094,0.0071538934,0.009550469,0.03671636],"study_design_scores_gemma":[0.001528196,0.0003927454,0.003251564,0.00017896762,0.000044723645,0.00016583804,0.00011259501,0.9514733,0.04196222,0.00021673179,0.0004308023,0.000242323],"about_ca_topic_score_codex":0.00006887539,"about_ca_topic_score_gemma":0.00010000294,"teacher_disagreement_score":0.9166484,"about_ca_system_score_codex":0.00023654403,"about_ca_system_score_gemma":0.00019397118,"threshold_uncertainty_score":0.5123677},"labels":[],"label_agreement":null},{"id":"W4402754242","doi":"10.1109/mwscas60917.2024.10658856","title":"PathoWAve: A Deep Learning-Based Weight Averaging Method for Improving Domain Generalization in Histopathology Images","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Generalization; Artificial intelligence; Computer science; Domain (mathematical analysis); Deep learning; Pattern recognition (psychology); Computer vision; Mathematics; Mathematical analysis","score_opus":0.00790910982879102,"score_gpt":0.26787042114582,"score_spread":0.259961311317029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402754242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010138083,0.0005921302,0.99511945,0.0011213523,0.0009821786,0.0002601508,8.181088e-7,0.00050475943,0.0004053455],"genre_scores_gemma":[0.19892216,0.0000071850523,0.7999364,0.00036723496,0.00013954003,0.00015736381,0.000005105827,0.00002458835,0.00044039727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846244,0.00025488823,0.0002507643,0.00059843046,0.00014157694,0.00029193034],"domain_scores_gemma":[0.9993544,0.00024351342,0.000060722774,0.0002457369,0.0000564289,0.00003915878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011312058,0.00014152304,0.00014994598,0.00036511134,0.00011269659,0.00017926672,0.00027437502,0.00008743319,0.000018442097],"category_scores_gemma":[0.000070433816,0.00013692454,0.0000716924,0.00053353264,0.000021361522,0.00041168477,0.0000867193,0.00019144372,0.000008324972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025128054,0.000036907673,0.0007168344,0.00034567525,0.0000074469576,0.00012475472,0.0021458818,0.047614224,0.11229276,0.038660955,0.00039566326,0.79763377],"study_design_scores_gemma":[0.00028966667,0.00008720068,0.00019542659,0.00002019532,0.000005513199,0.000027329332,0.000026485226,0.9684699,0.017531665,0.0074797086,0.0056941663,0.00017274864],"about_ca_topic_score_codex":0.00009471295,"about_ca_topic_score_gemma":0.00011809765,"teacher_disagreement_score":0.92085564,"about_ca_system_score_codex":0.000548335,"about_ca_system_score_gemma":0.00010510393,"threshold_uncertainty_score":0.5583621},"labels":[],"label_agreement":null},{"id":"W4402782644","doi":"10.1007/978-3-031-71602-7_11","title":"Comparative Study of Deep Learning Models in Melanoma Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning","score_opus":0.03130110894724508,"score_gpt":0.27035391171462075,"score_spread":0.23905280276737567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402782644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061674286,0.00060813414,0.9872357,0.00004530372,0.001829707,0.00067517033,7.754276e-7,0.00016837523,0.0032693988],"genre_scores_gemma":[0.9768119,0.000018652092,0.02279222,0.00003799595,0.00016104557,0.00002638623,6.136496e-7,0.000027622615,0.000123564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613357,0.0000822722,0.0007052004,0.0015958435,0.0010210745,0.00046207037],"domain_scores_gemma":[0.99812424,0.0003672274,0.00034339094,0.00086824043,0.00021408434,0.00008281959],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008778174,0.00046970986,0.00070657494,0.0017231003,0.00014874758,0.00027581843,0.0018698104,0.00026484954,0.0000063258153],"category_scores_gemma":[0.000022834036,0.0004584724,0.00009603727,0.0014377577,0.00031023854,0.0008146521,0.0011121588,0.0014743557,0.000020679032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011802766,0.000052342373,0.000043976557,0.000036531503,0.0000163749,0.000045796492,0.0093073975,0.6649181,0.0001674141,0.0018904508,2.9923615e-7,0.3235095],"study_design_scores_gemma":[0.00027414146,0.00089819933,0.00014098475,0.00023574008,0.0000098751325,0.000030517043,0.000007448039,0.87608695,0.0020470184,0.119848326,0.000039402505,0.00038140986],"about_ca_topic_score_codex":0.00017262429,"about_ca_topic_score_gemma":0.0028003918,"teacher_disagreement_score":0.9706445,"about_ca_system_score_codex":0.000745473,"about_ca_system_score_gemma":0.00018566789,"threshold_uncertainty_score":0.9997867},"labels":[],"label_agreement":null},{"id":"W4402839663","doi":"10.1007/s13721-024-00489-8","title":"Deep learning for breast cancer diagnosis from histopathological images: classification and gene expression: review","year":2024,"lang":"en","type":"article","venue":"Network Modeling Analysis in Health Informatics and Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breast cancer; Gene; Cancer; Gene expression; Pathology; Artificial intelligence; Medicine; Computational biology; Biology; Bioinformatics; Internal medicine; Computer science; Genetics","score_opus":0.041071749373315904,"score_gpt":0.31211135656639205,"score_spread":0.2710396071930761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402839663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011853423,0.046214804,0.9504375,0.0014176145,0.0002022193,0.000363613,0.000027636737,0.00012339775,0.000027890099],"genre_scores_gemma":[0.12828143,0.29234546,0.576823,0.001841597,0.00017414248,0.00044192135,0.0000733055,0.000012143722,0.0000070225883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974988,0.00007171395,0.001559977,0.0002264766,0.0002746707,0.00036832743],"domain_scores_gemma":[0.998738,0.00026532888,0.00043272568,0.00030511798,0.00011303557,0.00014581563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017327396,0.00020390213,0.0005061021,0.00026750492,0.0003107208,0.00030498434,0.00023365309,0.000119908866,0.000007556435],"category_scores_gemma":[0.00004356061,0.00016527215,0.000105233485,0.0011108012,0.000036750625,0.00082855107,0.00015259681,0.00033424477,0.0000016682612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057461957,0.0000082241895,0.0020528305,0.0026736213,0.000057133493,4.813768e-7,0.0017898041,0.4932922,4.6357923e-7,0.00016743722,0.00045088926,0.49950117],"study_design_scores_gemma":[0.00012152121,0.000040645624,0.0004419604,0.0018201066,0.00011796205,0.000008408909,0.00015428835,0.99544924,0.0000012064811,0.0004774223,0.001182861,0.00018437924],"about_ca_topic_score_codex":0.00008791336,"about_ca_topic_score_gemma":0.00003330314,"teacher_disagreement_score":0.50215703,"about_ca_system_score_codex":0.00021300894,"about_ca_system_score_gemma":0.00009429384,"threshold_uncertainty_score":0.67396027},"labels":[],"label_agreement":null},{"id":"W4402907310","doi":"10.1016/j.ijrobp.2024.07.1424","title":"A Machine-Learning Model to Predict Axillary Node Positivity from Clinical Characteristics and Large-Scale DNA Organization Features in Breast Cancer Biopsy Specimens","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Breast cancer; Scale (ratio); Biopsy; Node (physics); Medicine; Oncology; Artificial intelligence; Computer science; Internal medicine; Computational biology; Cancer; Biology; Engineering; Geography; Cartography","score_opus":0.012808068235413342,"score_gpt":0.31458814692121234,"score_spread":0.301780078685799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402907310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45229194,0.00038684055,0.5367443,0.006526843,0.0034402476,0.000111608264,0.0003736551,0.0000799564,0.000044619064],"genre_scores_gemma":[0.9831827,0.0012262344,0.012329375,0.00092016184,0.0022222472,0.00000621186,0.00006810494,0.000026323034,0.000018641444],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818915,0.00029065198,0.0006603978,0.00039792815,0.00025722422,0.00020463932],"domain_scores_gemma":[0.9984691,0.00036574877,0.00045791874,0.00013535426,0.0004465039,0.00012534733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006821226,0.00017953834,0.00034273035,0.00022106229,0.00007773346,0.00015231276,0.0004919322,0.00024111665,0.000019166027],"category_scores_gemma":[0.00014721336,0.00017089072,0.00008712269,0.00038700047,0.000066416105,0.00064416014,0.00022685305,0.0007246638,0.000010431569],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015531133,0.00022271123,0.78362125,0.000008429763,0.0002672235,0.00007112926,0.0016703261,0.0079531595,0.00592987,0.00364693,0.0004943697,0.1959593],"study_design_scores_gemma":[0.0011092745,0.00018862975,0.40343535,0.00011189607,0.00004200279,0.00024196182,0.00002237522,0.5874091,0.000437222,0.0044038864,0.0023957386,0.0002026107],"about_ca_topic_score_codex":0.00006557951,"about_ca_topic_score_gemma":0.00002894914,"teacher_disagreement_score":0.5794559,"about_ca_system_score_codex":0.0007653311,"about_ca_system_score_gemma":0.00045350537,"threshold_uncertainty_score":0.6968722},"labels":[],"label_agreement":null},{"id":"W4402916180","doi":"10.1109/cvprw63382.2024.00683","title":"Vim4Path: Self-Supervised Vision Mamba for Histopathology Images","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer; Université de Montréal; Concordia University","funders":"","keywords":"Computer science; Computer vision; Histopathology; Artificial intelligence; Medicine; Pathology","score_opus":0.010209608220247336,"score_gpt":0.2736540836292124,"score_spread":0.26344447540896504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402916180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024295263,0.0005900066,0.98593754,0.0027957552,0.0024272983,0.00023293275,0.000004267827,0.0014444949,0.0041381707],"genre_scores_gemma":[0.38580254,0.00006934226,0.60823077,0.0009225432,0.00038192206,0.00016668778,0.000003910925,0.000032444557,0.00438982],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899286,0.000042998083,0.00015187253,0.0004706043,0.00013056185,0.00021109656],"domain_scores_gemma":[0.9993432,0.00015801858,0.000017824397,0.00037859485,0.000053725893,0.000048629092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003548552,0.00010640834,0.000102688646,0.00012545093,0.000087058754,0.0001744046,0.00038983248,0.00006822733,0.000049246366],"category_scores_gemma":[0.000017453764,0.000091573944,0.000080790356,0.00024618593,0.000021935866,0.0005171006,0.00013638703,0.00008566573,0.00017338252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003475695,0.000089940826,0.000053524607,0.00028155532,0.000020955686,0.000106581574,0.0012796964,0.000053001848,0.065673545,0.059955206,0.12277063,0.74968064],"study_design_scores_gemma":[0.00037193554,0.0007422258,0.0006615536,0.000037071633,0.000018083354,0.00014437786,0.00002018973,0.7097993,0.030638041,0.01380242,0.24343033,0.00033446174],"about_ca_topic_score_codex":0.000011236508,"about_ca_topic_score_gemma":0.0000060903917,"teacher_disagreement_score":0.74934614,"about_ca_system_score_codex":0.00015738302,"about_ca_system_score_gemma":0.000068748435,"threshold_uncertainty_score":0.3734277},"labels":[],"label_agreement":null},{"id":"W4402916765","doi":"10.1109/cvprw63382.2024.00008","title":"Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Object (grammar); Artificial intelligence; Biology; Mathematics; Neuroscience","score_opus":0.026092899309972346,"score_gpt":0.24571434466758096,"score_spread":0.2196214453576086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402916765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092282135,0.00042111974,0.9949973,0.0006896082,0.00074133696,0.0002807742,0.0000032265084,0.00034056118,0.0016032135],"genre_scores_gemma":[0.7566567,0.000018305094,0.24228723,0.00015437845,0.00008650909,0.00008940888,0.0000063645934,0.000018670777,0.0006824428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905914,0.000046438192,0.00024308734,0.00032405564,0.0001788472,0.00014845892],"domain_scores_gemma":[0.9992761,0.00013306292,0.00004880537,0.0004037308,0.000107954904,0.000030332472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024632696,0.000091994996,0.00012492704,0.00017163937,0.00006135026,0.00004739369,0.00037079322,0.00008297299,0.000014166641],"category_scores_gemma":[0.000025923044,0.00008749103,0.00007194745,0.0003899078,0.00003722415,0.00052259146,0.00008805305,0.00005101013,0.000006944278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038201044,0.00003190868,0.000018606012,0.00022604216,0.00003923778,0.0000011861042,0.0043420764,0.36030692,0.0024387068,0.44238263,0.004315653,0.18585883],"study_design_scores_gemma":[0.00020832833,0.00013237323,0.000006587437,0.000019021034,0.0000075750845,0.0000063935195,0.000097955446,0.86533904,0.002378483,0.12498978,0.006730334,0.000084142644],"about_ca_topic_score_codex":0.0001621766,"about_ca_topic_score_gemma":0.0001502254,"teacher_disagreement_score":0.75573385,"about_ca_system_score_codex":0.00014612598,"about_ca_system_score_gemma":0.000117430325,"threshold_uncertainty_score":0.35677806},"labels":[],"label_agreement":null},{"id":"W4402925369","doi":"10.2196/58149","title":"AI-Supported Digital Microscopy Diagnostics in Primary Health Care Laboratories: Protocol for a Scoping Review","year":2024,"lang":"en","type":"review","venue":"JMIR Research Protocols","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Protocol (science); Primary care; Telepathology; Medicine; Data science; Health care; Computer science; World Wide Web; Family medicine; Telemedicine; Alternative medicine; Pathology; Political science","score_opus":0.3248335631052684,"score_gpt":0.6540183144835056,"score_spread":0.32918475137823716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402925369","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0821623e-10,0.42016205,0.0012304517,0.00046485823,0.00003721942,0.57764703,0.000165485,0.00020149915,0.00009139911],"genre_scores_gemma":[1.4550829e-10,0.36424655,0.0016069438,0.00038914813,0.00025960346,0.63324094,0.00006879156,0.00011023979,0.00007780924],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.99163395,0.0010564134,0.002135841,0.0019519768,0.0015933791,0.0016284089],"domain_scores_gemma":[0.9947618,0.0009548077,0.000668301,0.0020411809,0.0011902378,0.00038366267],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003141317,0.0007875978,0.0025383239,0.0008836791,0.00031871852,0.0020009186,0.0028213533,0.00047003513,0.000014440073],"category_scores_gemma":[0.00079626555,0.000651797,0.00044911559,0.005413021,0.00019989256,0.0011197015,0.0016575222,0.0024808794,0.00017180982],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000013861302,0.00008059786,8.341648e-7,0.52844274,0.000012420085,0.000024220106,0.00009722497,3.5200102e-8,6.5488905e-8,0.00007749798,0.09391571,0.3773348],"study_design_scores_gemma":[0.00033845007,0.00075529906,7.959096e-8,0.47830978,0.000004063423,0.000007691674,0.000003467043,0.000002672527,0.000003087181,0.00007931541,0.5202118,0.00028427818],"about_ca_topic_score_codex":0.00001022553,"about_ca_topic_score_gemma":0.000027194557,"teacher_disagreement_score":0.42629611,"about_ca_system_score_codex":0.0042055454,"about_ca_system_score_gemma":0.026258308,"threshold_uncertainty_score":0.9998204},"labels":[],"label_agreement":null},{"id":"W4402954579","doi":"10.48550/arxiv.2409.01883","title":"Boosting Vision-Language Models for Histopathology Classification: Predict all at once","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Boosting (machine learning); Histopathology; Artificial intelligence; Computer science; Natural language processing; Machine learning; Medicine; Pathology","score_opus":0.10815536474819278,"score_gpt":0.2333326338782174,"score_spread":0.12517726913002464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402954579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055603664,0.0005283932,0.93491024,0.0004326533,0.0023306515,0.0005659807,0.000045925713,0.0007001896,0.004882299],"genre_scores_gemma":[0.98462456,0.00010615164,0.009221411,0.00015212302,0.0001926515,0.000012984129,0.000029183317,0.000036012876,0.0056249164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744415,0.0001336357,0.00026505784,0.0016652095,0.000115956434,0.00037600164],"domain_scores_gemma":[0.9978111,0.00025404905,0.00029372657,0.0013601327,0.00015134896,0.00012966881],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047170187,0.00030631706,0.00029565603,0.00027842898,0.000207773,0.000111890644,0.0015228498,0.00038331194,0.000012443475],"category_scores_gemma":[0.000046525285,0.00036986815,0.00023070943,0.0003655476,0.00011667274,0.00034659647,0.0032045806,0.000593604,0.0000791864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017015687,0.00009366621,0.00017194853,0.00070359395,0.00012496255,0.0006255325,0.0030579532,0.76249695,0.0019378563,0.2159028,0.006849285,0.007865273],"study_design_scores_gemma":[0.00022819241,0.0000851314,0.00012942152,0.0001273176,0.000079969126,0.000022423037,0.000054696833,0.9187232,0.00016454115,0.0780215,0.0020386437,0.0003249335],"about_ca_topic_score_codex":0.000055980505,"about_ca_topic_score_gemma":0.00005246015,"teacher_disagreement_score":0.9290209,"about_ca_system_score_codex":0.0015672777,"about_ca_system_score_gemma":0.00024039933,"threshold_uncertainty_score":0.9998753},"labels":[],"label_agreement":null},{"id":"W4402980415","doi":"10.1109/icme57554.2024.10687771","title":"Second-Order Self-Supervised Learning for Breast Cancer Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; Ministry of Education","keywords":"Computer science; Artificial intelligence; Machine learning; Breast cancer; Cancer; Supervised learning; Medicine; Artificial neural network; Internal medicine","score_opus":0.021923940451273872,"score_gpt":0.28000419046441083,"score_spread":0.25808025001313695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402980415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026585702,0.0002554455,0.9840556,0.004601345,0.0013305303,0.00023832786,0.000005184124,0.0013516251,0.0055033797],"genre_scores_gemma":[0.92436886,0.00006724383,0.067428134,0.00040936074,0.0004558528,0.00033604016,0.00000298356,0.000026871585,0.006904665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991263,0.000025487749,0.0001337281,0.00039456473,0.00013576236,0.0001841157],"domain_scores_gemma":[0.99951494,0.000080198675,0.000024948446,0.00021390498,0.00012140807,0.00004462953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017438811,0.00009303484,0.00007387311,0.00008860543,0.00012134872,0.00027927433,0.00027049638,0.000059120735,0.0004792707],"category_scores_gemma":[0.0000058646992,0.00008349037,0.00004902627,0.00046921158,0.000010713834,0.0006112832,0.000051309213,0.00013348927,0.00007913457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007978158,0.000020674031,0.0003169872,0.00018179788,0.000060309896,0.0000011746083,0.0009985785,0.00052509154,0.006849078,0.03672029,0.008875948,0.9454421],"study_design_scores_gemma":[0.00012257535,0.000029661853,0.0025367881,0.000020223852,0.000007615096,0.000014804298,0.00003544531,0.910873,0.0012120218,0.0007227922,0.084299445,0.00012559883],"about_ca_topic_score_codex":0.000029095,"about_ca_topic_score_gemma":0.00005841729,"teacher_disagreement_score":0.9453165,"about_ca_system_score_codex":0.00019218608,"about_ca_system_score_gemma":0.00016785499,"threshold_uncertainty_score":0.5247678},"labels":[],"label_agreement":null},{"id":"W4403024188","doi":"10.1109/pacrim61180.2024.10690205","title":"A Novel Computational Method to Find Tumour Nuclei Traits Predictive of Breast Tumour Malignancy Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Malignancy; Machine learning; Artificial intelligence; Pathology; Medicine","score_opus":0.02354095060365021,"score_gpt":0.2924142625203643,"score_spread":0.2688733119167141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403024188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016709076,0.0000902718,0.9811776,0.0005888443,0.00029845425,0.0001995671,0.000047285874,0.0002975431,0.00059135153],"genre_scores_gemma":[0.52050054,4.5582624e-7,0.47918355,0.000067580004,0.00007209258,0.0000061283995,0.0000016221683,0.000015191596,0.00015283811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837947,0.00009539819,0.0003226405,0.0005301887,0.0004312399,0.00024109073],"domain_scores_gemma":[0.99933153,0.00020402491,0.0000854093,0.00011629658,0.0001591381,0.00010360944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046508975,0.0001695641,0.0002053972,0.00028571428,0.00010989478,0.00013938983,0.00037844942,0.000054005333,0.00006097813],"category_scores_gemma":[0.000024689707,0.00016226394,0.00008912258,0.00093794457,0.000023909082,0.00049795234,0.00023423239,0.00024062874,0.000022535913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003541181,0.00007579477,0.00013906954,0.00009951128,0.00008408621,0.000017408878,0.0024597389,0.58235675,0.3449642,0.015069488,0.00012042511,0.054578125],"study_design_scores_gemma":[0.00020953441,0.00015534654,0.012148417,0.00018140594,0.000016733666,0.00048174552,0.000048242815,0.97595394,0.0090638455,0.0014591421,0.00011168189,0.00016997919],"about_ca_topic_score_codex":0.00029967364,"about_ca_topic_score_gemma":0.000013485754,"teacher_disagreement_score":0.50379145,"about_ca_system_score_codex":0.00017031582,"about_ca_system_score_gemma":0.0002002236,"threshold_uncertainty_score":0.66169316},"labels":[],"label_agreement":null},{"id":"W4403046557","doi":"10.1007/978-3-031-62523-7_33","title":"Computer-Aided System for Breast Cancer Lesion Segmentation and Classification Using Ultrasound Images","year":2024,"lang":"en","type":"book-chapter","venue":"World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Segmentation; Breast cancer; Artificial intelligence; Ultrasound; Computer science; Lesion; Breast ultrasound; Computer vision; Radiology; Pattern recognition (psychology); Medicine; Cancer; Pathology; Mammography; Internal medicine","score_opus":0.02136795534792597,"score_gpt":0.2705593535739269,"score_spread":0.24919139822600095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403046557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011966313,0.0063516293,0.9511856,0.0027451587,0.019731967,0.0030820724,0.0017950595,0.001858621,0.012053269],"genre_scores_gemma":[0.55037117,0.022010172,0.07625537,0.005844143,0.048238114,0.0022043632,0.0026400608,0.0026361458,0.28980047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655706,0.000034257213,0.000704099,0.0010641014,0.0011731463,0.00046734916],"domain_scores_gemma":[0.9980627,0.00035910634,0.0003343695,0.00055212626,0.00014511883,0.00054658187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004253795,0.0006414949,0.00066990906,0.00036158864,0.00019160289,0.00031902545,0.0005511875,0.00047365017,0.000052179494],"category_scores_gemma":[0.000010871555,0.00058046967,0.00017168105,0.00021740167,0.0003400545,0.0002916082,0.00031835146,0.0008424396,0.000021749907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016785276,0.00031613672,0.000030979638,0.009067433,0.0016032251,0.00027477453,0.00038816273,0.0013691478,0.011043173,0.21787658,0.06549742,0.6923651],"study_design_scores_gemma":[0.001493339,0.00021323698,0.00021647097,0.0068701734,0.00032962993,0.00026757945,0.000011571868,0.8440227,0.00054396363,0.0018185464,0.14293842,0.0012743938],"about_ca_topic_score_codex":0.000030360965,"about_ca_topic_score_gemma":0.000024043684,"teacher_disagreement_score":0.8749302,"about_ca_system_score_codex":0.0004088529,"about_ca_system_score_gemma":0.00017847358,"threshold_uncertainty_score":0.99966466},"labels":[],"label_agreement":null},{"id":"W4403064636","doi":"10.1186/s12911-024-02677-y","title":"Validation of large language models for detecting pathologic complete response in breast cancer using population-based pathology reports","year":2024,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"Canadian Institutes of Health Research","keywords":"Health informatics; Breast cancer; Medicine; Pathology; Population; Cancer; Computer science; Natural language processing; Internal medicine; Public health","score_opus":0.05551034995085824,"score_gpt":0.36933556699723785,"score_spread":0.3138252170463796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403064636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47245798,0.000110479836,0.5270388,0.000014407472,0.00022412906,0.00010795308,0.000010377893,0.00003244607,0.0000034434643],"genre_scores_gemma":[0.7017179,0.0000057386164,0.29810557,0.00012201054,0.000024285813,0.000016057931,0.0000025943282,0.0000055565442,2.7173888e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982677,0.00009400037,0.00080765685,0.00018994484,0.00044590872,0.00019474972],"domain_scores_gemma":[0.9974343,0.0019270711,0.00026536916,0.00024277788,0.000076876386,0.000053582047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003172863,0.0001018337,0.00020744206,0.0003442785,0.0000900025,0.000097708784,0.0001498642,0.00013241409,0.000010243215],"category_scores_gemma":[0.00046079812,0.000086050604,0.00005289742,0.0003880203,0.000022417113,0.00044676257,0.00013781931,0.00013878019,3.2126079e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005736813,0.000045454162,0.0067166765,0.0010073455,0.000011358464,0.000246156,0.004299121,0.4260486,0.00089546375,0.001782622,0.000024166176,0.5583494],"study_design_scores_gemma":[0.0002798872,0.000035151756,0.0015454439,0.0008553213,0.0000057368566,0.0003031544,0.00016698119,0.9895337,0.00009437554,0.007081125,0.0000054623492,0.00009362146],"about_ca_topic_score_codex":0.00002715785,"about_ca_topic_score_gemma":0.000033792174,"teacher_disagreement_score":0.56348515,"about_ca_system_score_codex":0.00011060798,"about_ca_system_score_gemma":0.00023976802,"threshold_uncertainty_score":0.3509042},"labels":[],"label_agreement":null},{"id":"W4403069597","doi":"10.1007/978-3-031-72117-5_63","title":"Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Notre-Dame; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Bayesian probability; Bayesian network; Artificial intelligence; Image (mathematics); Uncertainty quantification; Pattern recognition (psychology); Data mining; Machine learning","score_opus":0.012559819493931356,"score_gpt":0.26304059310897415,"score_spread":0.2504807736150428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403069597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007567348,0.00077535736,0.9914425,0.0019462932,0.0033061767,0.00041419585,0.0000044790936,0.00027050817,0.0017648272],"genre_scores_gemma":[0.8753739,0.00016482979,0.12210578,0.0010233338,0.0009118565,0.00004350062,0.000021424958,0.00006584586,0.00028954892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935439,0.00008076177,0.00094300235,0.0025580171,0.0020518566,0.00082246255],"domain_scores_gemma":[0.9967042,0.0005733614,0.00031542595,0.0019027421,0.00022486877,0.00027939855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026090879,0.000592363,0.0007470421,0.002862049,0.0001808343,0.00081075996,0.0036327287,0.00058172113,0.00006610915],"category_scores_gemma":[0.0001339046,0.0005499503,0.00029294626,0.0049880524,0.00082868873,0.00036736176,0.0012909326,0.0015945453,0.000076225624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005406979,0.000025067271,0.00004031319,0.000026933498,0.00003517524,0.00016758025,0.00030071347,0.7546275,0.000011123814,0.009080765,0.000014192536,0.23566522],"study_design_scores_gemma":[0.00014337117,0.000061977364,0.0001963141,0.00038477822,0.000050135495,0.000036165693,2.9399757e-7,0.96733123,0.00011039269,0.030759972,0.000385903,0.00053946837],"about_ca_topic_score_codex":0.0002093228,"about_ca_topic_score_gemma":0.0018099545,"teacher_disagreement_score":0.8752982,"about_ca_system_score_codex":0.0012855394,"about_ca_system_score_gemma":0.0007821849,"threshold_uncertainty_score":0.9996952},"labels":[],"label_agreement":null},{"id":"W4403075145","doi":"10.1007/978-3-031-73471-7_16","title":"Boosting Vision-Language Models for Histopathology Classification: Predict All at Once","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Boosting (machine learning); Computer science; Artificial intelligence; Natural language processing; Machine learning","score_opus":0.03131464875024249,"score_gpt":0.28710032805145835,"score_spread":0.2557856793012159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403075145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042027026,0.0023093906,0.98349595,0.0020616194,0.0050987564,0.00073257496,0.00002024526,0.00046967942,0.005769769],"genre_scores_gemma":[0.17633884,0.00012893348,0.8111888,0.0030195888,0.002194657,0.00017824226,0.000030639476,0.00015290274,0.006767376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953283,0.000038820912,0.00065333006,0.0023845185,0.0008727444,0.0007222572],"domain_scores_gemma":[0.996687,0.0009087653,0.00036402166,0.0016332628,0.00024223412,0.00016469265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013666605,0.0005431042,0.0004988063,0.00075421674,0.00035239072,0.00044363562,0.0028949962,0.00045425943,0.000012352355],"category_scores_gemma":[0.000105007624,0.00052605587,0.0001870169,0.00048217614,0.0006249554,0.00080429064,0.0017599793,0.0007900386,0.000057823967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034746303,0.00002711156,0.000006759131,0.0002461374,0.000019102603,0.00017328608,0.003799398,0.11999189,0.0026051255,0.06705549,0.00044129338,0.80559963],"study_design_scores_gemma":[0.00015715195,0.00023256117,0.00001602561,0.00035230487,0.00001536233,0.0001819583,3.0634428e-7,0.8229963,0.00064681564,0.16824244,0.0067054667,0.0004532853],"about_ca_topic_score_codex":0.000013188869,"about_ca_topic_score_gemma":0.0000811594,"teacher_disagreement_score":0.80514634,"about_ca_system_score_codex":0.001861523,"about_ca_system_score_gemma":0.0004640746,"threshold_uncertainty_score":0.9997191},"labels":[],"label_agreement":null},{"id":"W4403103868","doi":"10.1111/his.15331","title":"A deep learning approach to case prioritisation of colorectal biopsies","year":2024,"lang":"en","type":"article","venue":"Histopathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"Enterprise Ireland","keywords":"Digital pathology; Workflow; Artificial intelligence; Medicine; Triage; Colorectal cancer; Dysplasia; Computer science; Biopsy; Deep learning; Radiology; Pathology; Machine learning; Medical physics; Cancer; Internal medicine; Database","score_opus":0.012809874156427287,"score_gpt":0.24364833199254599,"score_spread":0.2308384578361187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403103868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24932913,0.0007321703,0.7454247,0.00011719126,0.0010555346,0.00011826287,7.023318e-7,0.0002416792,0.0029806322],"genre_scores_gemma":[0.93771684,0.000008177336,0.061932806,0.000032965145,0.00005917251,0.000043701755,0.000001170651,0.0000089778905,0.0001961864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991378,0.000100887635,0.00016590334,0.0003446444,0.00010040424,0.00015035979],"domain_scores_gemma":[0.99964315,0.000054366727,0.00004100347,0.00017481335,0.000047725152,0.000038916558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025945206,0.00007854288,0.00013018277,0.00022602805,0.00007948132,0.00003152218,0.0001757106,0.00007358431,0.000005240361],"category_scores_gemma":[0.00005744612,0.000084337764,0.00003886588,0.00044273617,0.00006588695,0.00016124334,0.00011202716,0.00015273449,0.000036582172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007252626,0.000182394,0.0018573079,0.00057819043,0.0000163244,0.0074598673,0.07663804,0.017155804,0.1559528,0.112018794,0.0010270136,0.6270409],"study_design_scores_gemma":[0.00038242966,0.0015373855,0.013260706,0.000069885646,0.000038903123,0.05652786,0.0005855257,0.87956655,0.0074460246,0.0024690276,0.03752703,0.0005887028],"about_ca_topic_score_codex":0.000054588912,"about_ca_topic_score_gemma":0.000024816676,"teacher_disagreement_score":0.8624107,"about_ca_system_score_codex":0.00018085116,"about_ca_system_score_gemma":0.000048054062,"threshold_uncertainty_score":0.34391943},"labels":[],"label_agreement":null},{"id":"W4403204511","doi":"10.1007/978-3-031-72744-3_6","title":"Unpaired Modality Translation for Pseudo Labeling of Histology Images","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Translation (biology); Modality (human–computer interaction); Artificial intelligence; Natural language processing; Computer vision","score_opus":0.028538653747653374,"score_gpt":0.2719103739428772,"score_spread":0.24337172019522382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403204511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048231683,0.0015318395,0.99120957,0.0019045598,0.003466719,0.0005294013,0.000019605275,0.00016682992,0.0011232627],"genre_scores_gemma":[0.13625395,0.000054607426,0.86259747,0.00029207795,0.00041591775,0.000029862673,0.000004786246,0.000042985837,0.00030832415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970154,0.000025329382,0.0006120965,0.0013418795,0.0005806195,0.0004246552],"domain_scores_gemma":[0.9978158,0.0005974476,0.00029744126,0.0009200847,0.00029616573,0.00007305082],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009520366,0.00036818616,0.0005122798,0.00075264444,0.000138189,0.00015638568,0.0017203072,0.0003388046,0.00000627222],"category_scores_gemma":[0.000052283976,0.00036278105,0.00018739256,0.0005361479,0.0005869758,0.00034971497,0.00035441443,0.00048817685,0.000007684054],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018455516,0.000017179198,0.00000906178,0.0003218468,0.000022196338,0.000011573365,0.0008585461,0.036136728,0.004492958,0.033950537,0.00002304092,0.9241379],"study_design_scores_gemma":[0.00018010807,0.00016385493,0.000009599991,0.00024639087,0.000016720747,0.00002560269,9.140822e-8,0.5412924,0.009682998,0.44725055,0.0008322163,0.00029946785],"about_ca_topic_score_codex":0.00003719855,"about_ca_topic_score_gemma":0.00007310782,"teacher_disagreement_score":0.92383844,"about_ca_system_score_codex":0.00044358542,"about_ca_system_score_gemma":0.00046915066,"threshold_uncertainty_score":0.9998824},"labels":[],"label_agreement":null},{"id":"W4403228757","doi":"10.1007/978-3-031-73376-5_14","title":"UltraWeak: Enhancing Breast Ultrasound Cancer Detection with Deformable DETR and Weak Supervision","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Breast cancer; Ultrasound; Computer vision; Artificial intelligence; Cancer; Radiology; Medicine; Internal medicine","score_opus":0.006969525455863386,"score_gpt":0.2194938775062529,"score_spread":0.21252435205038953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403228757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018874939,0.0017787559,0.9909442,0.00029275494,0.0025788706,0.0004272438,0.000010829001,0.00034647709,0.0017333707],"genre_scores_gemma":[0.91980904,0.0006110325,0.07719304,0.00045863967,0.0009606855,0.00004897297,0.000003178361,0.00010129967,0.0008141361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99570125,0.00002397683,0.00048448896,0.001962065,0.001069807,0.00075841317],"domain_scores_gemma":[0.9979604,0.00035396905,0.0002166247,0.0009876209,0.00026620587,0.00021520398],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006927772,0.00065529434,0.00048922864,0.0009325547,0.00046151792,0.0011446623,0.0013629543,0.00036282217,0.000024900282],"category_scores_gemma":[0.000022352955,0.00053513085,0.00008704356,0.0010897716,0.00058841525,0.0014866731,0.00065397023,0.0011394963,0.00003115457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027090193,0.000012600993,0.000118467695,0.00019587901,0.000032721895,0.000042255,0.00096867105,0.021430835,0.009187587,0.001383058,0.0000058692485,0.966595],"study_design_scores_gemma":[0.00083335047,0.0010429012,0.0009958703,0.0043635825,0.000097199045,0.0055285394,0.0000041127746,0.77888405,0.11206899,0.09042293,0.0031301833,0.0026282822],"about_ca_topic_score_codex":0.0003897362,"about_ca_topic_score_gemma":0.0040924875,"teacher_disagreement_score":0.96396667,"about_ca_system_score_codex":0.0009953884,"about_ca_system_score_gemma":0.0005410282,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W4403228877","doi":"10.1007/978-3-031-73376-5_6","title":"Performance Evaluation of Deep Learning and Transformer Models Using Multimodal Data for Breast Cancer Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Instituto Tecnológico y de Estudios Superiores de Monterrey","keywords":"Computer science; Transformer; Artificial intelligence; Deep learning; Machine learning; Breast cancer; Cancer; Electrical engineering; Medicine","score_opus":0.08320250091894528,"score_gpt":0.3309169773386779,"score_spread":0.24771447641973265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403228877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011769753,0.0013414252,0.9949818,0.00024557943,0.0011301091,0.0007223864,0.00004983433,0.000067655834,0.0002842005],"genre_scores_gemma":[0.8286249,0.0002685487,0.17067826,0.000040861243,0.0002834041,0.00003133491,0.00001263082,0.000032896547,0.000027184298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967328,0.000029987197,0.00045182245,0.0014022564,0.0010459219,0.00033726348],"domain_scores_gemma":[0.99805087,0.00017733575,0.0002769588,0.0008450146,0.0005823823,0.000067449175],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019279033,0.00031587775,0.00032721506,0.00054107007,0.00022127073,0.0002250788,0.0014203129,0.00022706465,0.000007969428],"category_scores_gemma":[0.000023618953,0.0003004489,0.000052942156,0.0004214875,0.00035953676,0.0016026672,0.0004198102,0.00047177039,9.0634757e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008027619,0.000004459543,0.00002733822,0.000100518795,0.000010459054,2.2462581e-7,0.00034763812,0.31038198,0.00054795766,0.000659145,3.2155447e-7,0.6879119],"study_design_scores_gemma":[0.00026888278,0.00006577478,0.00020135177,0.00048974826,0.000068897614,0.00003577474,6.767372e-7,0.97749764,0.00054491806,0.0204679,0.000048155885,0.0003102707],"about_ca_topic_score_codex":0.000056204277,"about_ca_topic_score_gemma":0.0001189909,"teacher_disagreement_score":0.8274479,"about_ca_system_score_codex":0.0005660293,"about_ca_system_score_gemma":0.0006038374,"threshold_uncertainty_score":0.99994475},"labels":[],"label_agreement":null},{"id":"W4403251157","doi":"10.1016/j.ygyno.2024.07.394","title":"Machine learning for prediction of concurrent endometrial carcinoma patients diagnosed with endometrial intraepithelial neoplasia","year":2024,"lang":"en","type":"article","venue":"Gynecologic Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Carcinoma; Oncology; Internal medicine; Gynecology","score_opus":0.021735532683258032,"score_gpt":0.26814216648218225,"score_spread":0.24640663379892422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403251157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6064437,0.0007048474,0.36715657,0.00029599498,0.02152427,0.0023201306,0.00022060746,0.0005596935,0.0007742111],"genre_scores_gemma":[0.9938539,0.00008331635,0.0048111225,0.000040967443,0.00066504383,0.00042325284,0.000059571845,0.000019586745,0.00004323606],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977163,0.00033737678,0.0005527613,0.0006436374,0.00032575743,0.00042418804],"domain_scores_gemma":[0.994283,0.0048675574,0.0003027554,0.00023170067,0.00021876587,0.000096181466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008012559,0.00022632295,0.0005023618,0.0006225983,0.00014558672,0.0000648389,0.00046595963,0.00026243896,0.00006642006],"category_scores_gemma":[0.0018848411,0.00017977117,0.00014697753,0.0011164898,0.00014281113,0.00029549442,0.00017329988,0.00040452162,0.0000145748945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090630486,0.00048089464,0.05457148,0.00013501466,0.00018395267,0.000056414192,0.00093934516,0.0009241246,0.0007283311,0.003672529,0.0008167599,0.93658483],"study_design_scores_gemma":[0.059492245,0.14905225,0.16408709,0.00012677068,0.0005302362,0.00013859793,0.00013323732,0.2858637,0.010589561,0.0031391408,0.325721,0.0011261995],"about_ca_topic_score_codex":0.000058075773,"about_ca_topic_score_gemma":0.00007065647,"teacher_disagreement_score":0.93545866,"about_ca_system_score_codex":0.00073206547,"about_ca_system_score_gemma":0.0004822025,"threshold_uncertainty_score":0.7330856},"labels":[],"label_agreement":null},{"id":"W4403285678","doi":"10.21203/rs.3.rs-5028318/v1","title":"MedMAE: A Self-Supervised Backbone for Medical Imaging Tasks","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Autoencoder; Medical imaging; Artificial intelligence; Task (project management); Deep learning; Domain (mathematical analysis); Machine learning; Code (set theory); Backbone network; Representation (politics); Pattern recognition (psychology)","score_opus":0.04915794766473349,"score_gpt":0.4094112989268251,"score_spread":0.3602533512620916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403285678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040510288,0.016902862,0.8674218,0.08200822,0.009136715,0.0064294105,0.00021275289,0.0038137946,0.010023415],"genre_scores_gemma":[0.8158594,0.002394045,0.1619847,0.000830145,0.0074971775,0.008487443,0.00017102099,0.00041258713,0.0023634871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99236476,0.00053781044,0.00052235264,0.0017192892,0.0036848995,0.0011708818],"domain_scores_gemma":[0.9954794,0.0010427972,0.000076118675,0.0018868864,0.0009785362,0.0005362518],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0057360404,0.0003583723,0.00043631103,0.00084400707,0.00033531766,0.0010781661,0.0033205342,0.00051051413,0.00018698956],"category_scores_gemma":[0.00089762406,0.00033935273,0.00033534618,0.0011121626,0.00017742021,0.00021262125,0.009407685,0.0036152026,0.00040592608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084069936,0.0003098882,0.00022510039,0.012943973,0.0003609612,0.0006831339,0.004809337,0.0001631687,0.00031256687,0.027943013,0.19001225,0.76215255],"study_design_scores_gemma":[0.00050675217,0.00012273391,0.000093364644,0.0017620064,0.000017824215,0.000051870953,0.00013092808,0.8638697,0.0006990264,0.0865943,0.04570874,0.00044270497],"about_ca_topic_score_codex":0.0002674432,"about_ca_topic_score_gemma":0.00007090228,"teacher_disagreement_score":0.8637066,"about_ca_system_score_codex":0.0011204234,"about_ca_system_score_gemma":0.0031577284,"threshold_uncertainty_score":0.9999588},"labels":[],"label_agreement":null},{"id":"W4403351809","doi":"10.1007/978-3-031-72787-0_13","title":"Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Race (biology); Artificial intelligence; Pattern recognition (psychology); Computer vision; Geology","score_opus":0.009194023668238571,"score_gpt":0.23954633746550333,"score_spread":0.23035231379726476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403351809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000309042,0.0009751923,0.9807224,0.005024023,0.009744038,0.0004774828,0.000108062595,0.00071074127,0.0019290198],"genre_scores_gemma":[0.47154605,0.00062864134,0.5034412,0.013010745,0.0072011696,0.00017401396,0.000106752166,0.00029198962,0.0035994346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934459,0.00006293985,0.00075916,0.0027821753,0.0021896816,0.00076019176],"domain_scores_gemma":[0.99673176,0.0006096962,0.00015642011,0.0017442269,0.00027055756,0.00048734955],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007882188,0.0007327795,0.00064310135,0.0010443238,0.00023797198,0.0010997326,0.0045971754,0.000649124,0.000114864415],"category_scores_gemma":[0.00023017485,0.00066892087,0.00015796185,0.0011393859,0.0005844822,0.00059757795,0.0028590942,0.0017066931,0.00029182388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019574536,0.000031661704,0.00003967158,0.000042841246,0.000045834626,0.00027635487,0.0020709818,0.01372846,0.0020754433,0.0038009598,0.00093022786,0.976938],"study_design_scores_gemma":[0.00024513653,0.00033799294,0.00022680702,0.0014395647,0.000024375544,0.00012077426,3.429143e-7,0.76197,0.010465964,0.22014241,0.004105414,0.00092120125],"about_ca_topic_score_codex":0.00018242934,"about_ca_topic_score_gemma":0.00036105985,"teacher_disagreement_score":0.97601676,"about_ca_system_score_codex":0.0008723592,"about_ca_system_score_gemma":0.0008208281,"threshold_uncertainty_score":0.99993724},"labels":[],"label_agreement":null},{"id":"W4403511948","doi":"10.1109/iv64223.2024.00058","title":"A Visual Analytics Solution for Analyzing and Mining Infectious Disease Data","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Visual analytics; Computer science; Analytics; Infectious disease (medical specialty); Data science; Data analysis; Data visualization; Disease; Visualization; Data mining; Medicine","score_opus":0.048111861881957985,"score_gpt":0.3379410958898079,"score_spread":0.28982923400784993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403511948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008688794,0.0005627108,0.9890696,0.000617695,0.00049350434,0.00010339589,0.0000067456017,0.00031955767,0.00013800079],"genre_scores_gemma":[0.9660542,0.00003626541,0.033442713,0.00008550264,0.0001876781,0.000012045944,0.000010150385,0.000007897741,0.00016353684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992354,0.0000138586265,0.0001081593,0.0004081092,0.000096336546,0.00013816195],"domain_scores_gemma":[0.99941444,0.00012191414,0.000020090414,0.00034060533,0.000028029952,0.000074928954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025139836,0.00006842087,0.00006334023,0.00012973225,0.000108682674,0.00036336674,0.00022636281,0.000023097735,0.00000303714],"category_scores_gemma":[0.00006260397,0.00006422708,0.000022368622,0.00035010057,0.00001971196,0.0008556964,0.00033070226,0.000045937802,0.0000035960816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016981565,0.0000328053,0.0044466783,0.00025346485,0.00011167001,0.00001657527,0.00036108354,0.0006316622,0.00050373183,0.01395425,0.00876877,0.9709023],"study_design_scores_gemma":[0.00007718487,0.000047798167,0.00073047174,0.000026220701,0.000032840708,0.0000061228056,0.000006586224,0.9934658,0.000046406654,0.0014515858,0.0040219836,0.000087010594],"about_ca_topic_score_codex":0.000025189203,"about_ca_topic_score_gemma":0.000059050668,"teacher_disagreement_score":0.99283415,"about_ca_system_score_codex":0.000060521612,"about_ca_system_score_gemma":0.00008283665,"threshold_uncertainty_score":0.35039538},"labels":[],"label_agreement":null},{"id":"W4403561638","doi":"10.1016/j.ibmed.2024.100174","title":"Combining a forward supervised filter learning with a sparse NMF for breast cancer histopathological image classification","year":2024,"lang":"en","type":"article","venue":"Intelligence-Based Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Non-negative matrix factorization; Computer science; Cancer; Breast cancer; Medicine; Internal medicine; Matrix decomposition","score_opus":0.053483664455098244,"score_gpt":0.3110067640157046,"score_spread":0.25752309956060637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403561638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042102,0.00062748604,0.97967374,0.012768637,0.0010538038,0.000508853,0.000013562655,0.0005789248,0.0005647996],"genre_scores_gemma":[0.9725214,0.000087384484,0.025162645,0.00079624966,0.0005034908,0.0005361511,0.000016623851,0.00003690225,0.0003391051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784243,0.00009777877,0.00041752786,0.00077494065,0.00045716405,0.00041016174],"domain_scores_gemma":[0.99850893,0.0004980188,0.0001173029,0.00042749423,0.00029338335,0.00015488193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007384924,0.00026360006,0.00031962415,0.00028362885,0.00018102698,0.00011913723,0.0005193663,0.00011024793,0.0002684085],"category_scores_gemma":[0.000120809964,0.00018548856,0.000089523404,0.0007643289,0.0003033311,0.0003696756,0.000050371083,0.00042496726,0.00003509691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052541826,0.000104064384,0.0011620596,0.0005158289,0.000062145635,0.0001668484,0.0034759222,0.003916498,0.021381682,0.011048906,0.002629006,0.9550116],"study_design_scores_gemma":[0.0006079377,0.001556093,0.001302452,0.0013433726,0.000081387945,0.0001538316,0.00037441327,0.9721944,0.008941368,0.0022260456,0.010841674,0.00037704132],"about_ca_topic_score_codex":0.00011325545,"about_ca_topic_score_gemma":0.000031118274,"teacher_disagreement_score":0.96831125,"about_ca_system_score_codex":0.00042304466,"about_ca_system_score_gemma":0.0003148684,"threshold_uncertainty_score":0.7564004},"labels":[],"label_agreement":null},{"id":"W4403566673","doi":"10.2196/65033","title":"Exploring the Potential of Claude 3 Opus in Renal Pathological Diagnosis: Performance Evaluation","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Opus; Computer science; Medicine; World Wide Web; Operating system","score_opus":0.06628436664538431,"score_gpt":0.3155159567021457,"score_spread":0.2492315900567614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403566673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9343206,0.00020739165,0.062492415,0.0009078854,0.001196431,0.000323946,9.802682e-7,0.000111045025,0.0004392603],"genre_scores_gemma":[0.9961618,0.00046697605,0.0024144033,0.00019885809,0.00015153641,0.0005956775,0.0000019440008,0.0000042234474,0.000004535304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767375,0.00008884353,0.0005852013,0.00011173196,0.0013344948,0.00020596657],"domain_scores_gemma":[0.9993242,0.000158028,0.00008773703,0.00029489901,0.000065277476,0.00006983454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001872898,0.00009574135,0.00012776414,0.00013725425,0.000055846664,0.000086439366,0.0006455837,0.0000889502,0.000049434795],"category_scores_gemma":[0.00014175495,0.000060926326,0.000053091266,0.00061063713,0.00010406228,0.0012768452,0.00023971044,0.0004626132,0.000037311427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069821845,0.000033495773,0.00024276822,0.0001323147,0.000008472975,0.000012426966,0.0060795876,0.0015208108,0.000028264214,0.0011914718,0.00050496095,0.9902384],"study_design_scores_gemma":[0.00021906888,0.00013565879,0.0116847865,0.0003821591,0.000007465716,0.000050349205,0.0003235988,0.98398197,0.0010442699,0.00053490704,0.0015474061,0.000088386216],"about_ca_topic_score_codex":0.0000050079375,"about_ca_topic_score_gemma":0.0000029547602,"teacher_disagreement_score":0.99015003,"about_ca_system_score_codex":0.00012253619,"about_ca_system_score_gemma":0.00020543656,"threshold_uncertainty_score":0.24845035},"labels":[],"label_agreement":null},{"id":"W4403649753","doi":"10.1007/978-3-031-72390-2_60","title":"MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bridging (networking); Computer science; Image segmentation; Computer vision; Artificial intelligence; Image (mathematics); Segmentation; Computer security","score_opus":0.009981602077675383,"score_gpt":0.2561293308092154,"score_spread":0.24614772873154003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403649753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012952866,0.0006284864,0.9855542,0.0038825346,0.0032821763,0.00031923427,0.000007034628,0.00033933998,0.0058574695],"genre_scores_gemma":[0.081962936,0.0005599302,0.91087997,0.00269817,0.0022451598,0.0000214697,0.000012789148,0.00012661536,0.001492972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953387,0.000039032606,0.00047347366,0.0017944705,0.00176361,0.00059071585],"domain_scores_gemma":[0.9982117,0.0002796491,0.00019711327,0.00082962814,0.0001952863,0.0002866566],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010935256,0.0005131952,0.0004330203,0.0009181697,0.00025381416,0.0010591706,0.0020770945,0.00036295652,0.00007703095],"category_scores_gemma":[0.00009804141,0.000490566,0.0001066657,0.00072973646,0.0011856921,0.0013535557,0.0020770254,0.0011600622,0.000086169646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005420048,0.000009162636,0.0000059399686,0.00009414099,0.00001667386,0.0003527538,0.0009355014,0.00034490682,0.0009873332,0.0066832234,0.00010289871,0.99046206],"study_design_scores_gemma":[0.0003986957,0.00020494428,0.0000804716,0.00082013727,0.000025688996,0.0004764832,0.0000013851933,0.8940752,0.00804599,0.09352183,0.001522305,0.00082684256],"about_ca_topic_score_codex":0.000099656274,"about_ca_topic_score_gemma":0.000110329594,"teacher_disagreement_score":0.9896352,"about_ca_system_score_codex":0.00078077783,"about_ca_system_score_gemma":0.0009106001,"threshold_uncertainty_score":0.9999778},"labels":[],"label_agreement":null},{"id":"W4403649759","doi":"10.1007/978-3-031-72390-2_52","title":"Few-Shot Adaptation of Medical Vision-Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Computer science; Adaptation (eye); Shot (pellet); Artificial intelligence; Computer vision; Computer graphics (images); Neuroscience; Psychology","score_opus":0.026128904070784647,"score_gpt":0.28997014136125493,"score_spread":0.26384123729047027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403649759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007915021,0.001928224,0.9879821,0.0013246142,0.0034714427,0.00028150505,0.000005897103,0.0002148912,0.004712162],"genre_scores_gemma":[0.66721314,0.0002788114,0.32936117,0.0010983929,0.00110727,0.000021127433,0.00000782737,0.00008462731,0.00082763896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944688,0.00003104802,0.0006614016,0.001462476,0.0029212285,0.00045505786],"domain_scores_gemma":[0.99762374,0.0004164949,0.00027771725,0.001267012,0.00022243742,0.00019262436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013854007,0.00042584722,0.0004873562,0.0010215692,0.00011527489,0.00034610648,0.0036492713,0.0005231307,0.00005822923],"category_scores_gemma":[0.000072601506,0.00038374745,0.00015779903,0.00088861724,0.0006518259,0.00081890565,0.0016248835,0.0010441995,0.000049757342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049098558,0.000017536755,8.674078e-7,0.00009608061,0.000012337949,0.00010559117,0.0029611052,0.15262775,0.000086352775,0.058695577,0.000027873082,0.78536403],"study_design_scores_gemma":[0.00011820894,0.00015800945,0.0000029866255,0.00072896597,0.00000719583,0.00006831422,9.0705925e-7,0.78260005,0.0008466753,0.21480364,0.00036908526,0.000295984],"about_ca_topic_score_codex":0.00013922378,"about_ca_topic_score_gemma":0.00021490338,"teacher_disagreement_score":0.78506804,"about_ca_system_score_codex":0.00039528174,"about_ca_system_score_gemma":0.0009861116,"threshold_uncertainty_score":0.9998614},"labels":[],"label_agreement":null},{"id":"W4403649873","doi":"10.1007/978-3-031-72390-2_50","title":"FACMIC: Federated Adaptative CLIP Model for Medical Image Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Image (mathematics); Artificial intelligence; Computer vision; Information retrieval; Computer graphics (images)","score_opus":0.04088328140346871,"score_gpt":0.30107180040890424,"score_spread":0.26018851900543555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403649873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010937912,0.00037454534,0.98889685,0.0035913254,0.0029834667,0.00075914944,0.000022476284,0.0004142732,0.002946954],"genre_scores_gemma":[0.14164996,0.000116873096,0.8523327,0.002198969,0.0010493227,0.00015101818,0.000024284944,0.00010870354,0.0023681591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949914,0.000028863438,0.0006790147,0.0021406233,0.0015116755,0.00064838614],"domain_scores_gemma":[0.9973551,0.00062778604,0.0002875784,0.00096216286,0.00052881584,0.00023852508],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012563383,0.00055429724,0.00049185555,0.00074823794,0.00035398526,0.0009869662,0.0027637985,0.00058936863,0.000015596557],"category_scores_gemma":[0.00020776782,0.0005085138,0.0001824436,0.0006698409,0.0007642884,0.00077013916,0.00093137403,0.0011337465,0.000082281804],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026897316,0.00003135171,0.0000017980456,0.00012045519,0.00003552996,0.0000478854,0.0017149821,0.044528972,0.0007528499,0.11018962,0.00045827683,0.8420914],"study_design_scores_gemma":[0.00017209337,0.000111925096,0.000004565838,0.00022548124,0.000009089983,0.000032780776,2.9803363e-7,0.73344487,0.000770345,0.2640735,0.00075301115,0.00040203743],"about_ca_topic_score_codex":0.000014398546,"about_ca_topic_score_gemma":0.00019160048,"teacher_disagreement_score":0.84168935,"about_ca_system_score_codex":0.000897348,"about_ca_system_score_gemma":0.0017685865,"threshold_uncertainty_score":0.99973667},"labels":[],"label_agreement":null},{"id":"W4403666775","doi":"10.1016/s2589-7500(24)00154-7","title":"Unleashing the strengths of unlabelled data in deep learning-assisted pan-cancer abdominal organ quantification: the FLARE22 challenge","year":2024,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Toronto Rehabilitation Institute; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cancer; Medicine; Artificial intelligence; Deep learning; Medical physics; Computer science; Internal medicine","score_opus":0.17124965762228372,"score_gpt":0.4181453178305883,"score_spread":0.24689566020830456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403666775","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011294109,0.9799315,0.0030112693,0.01398937,0.0010180301,0.0011434952,0.00016414998,0.00015796066,0.00057295244],"genre_scores_gemma":[0.007953298,0.9904193,0.00011871138,0.00016814089,0.00078252517,0.00016358685,0.00010498616,0.000056584715,0.00023282375],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958664,0.0008819386,0.00107425,0.00090599427,0.00066500634,0.00060638826],"domain_scores_gemma":[0.9936048,0.0016730553,0.0010450602,0.003530357,0.00007904016,0.000067690504],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0028425471,0.00043288816,0.0013489277,0.00012570966,0.00040156944,0.00062244106,0.0063577574,0.00015124917,0.000009252724],"category_scores_gemma":[0.000281631,0.0002038441,0.00017893205,0.0017581924,0.00021924017,0.00056562497,0.0015590321,0.0017683235,0.00008431811],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009118437,0.000033299726,0.000004978229,0.0041275667,0.000083698666,0.0000027109902,0.00090514246,0.000013919625,4.1583156e-8,0.0024360735,0.0010557289,0.9913277],"study_design_scores_gemma":[0.00020909165,0.000108466484,0.000075827294,0.00694395,0.00012389115,0.000049411003,0.00027241258,0.0072570993,4.055269e-7,0.00074262166,0.9839357,0.00028113613],"about_ca_topic_score_codex":0.00027274885,"about_ca_topic_score_gemma":0.0011086554,"teacher_disagreement_score":0.9910466,"about_ca_system_score_codex":0.00038886402,"about_ca_system_score_gemma":0.0011386691,"threshold_uncertainty_score":0.9990183},"labels":[],"label_agreement":null},{"id":"W4403729760","doi":"10.3390/curroncol31110486","title":"Predicting Breast Cancer Relapse from Histopathological Images with Ensemble Machine Learning Models","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Artificial intelligence; Machine learning; Ensemble learning; Cancer; Pathology; Medical physics; Computer science; Internal medicine","score_opus":0.07114679812488701,"score_gpt":0.33488569616193786,"score_spread":0.26373889803705086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403729760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0975672,0.017678423,0.8735932,0.0024950623,0.0055368994,0.00020087049,0.00004949928,0.0011275702,0.0017512585],"genre_scores_gemma":[0.99127793,0.0007833043,0.0069521046,0.000060551483,0.0005797131,0.00011751077,0.000009845803,0.000022168952,0.00019684872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983637,0.0001902951,0.00021988158,0.00068594754,0.00022432832,0.0003158459],"domain_scores_gemma":[0.9992709,0.00020624252,0.00009291422,0.00026053458,0.00007665323,0.00009273535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025817868,0.00017822714,0.00023142414,0.000105129475,0.00015649281,0.0001027515,0.000396994,0.00011141544,0.00006085894],"category_scores_gemma":[0.00001848037,0.00013874046,0.00005479574,0.0003109738,0.000096270654,0.0005291957,0.00026100068,0.0007983881,0.0000335597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007886855,0.00011787398,0.017822547,0.000057974015,0.000036125184,0.00024174494,0.0018302415,0.011826988,0.0014203724,0.0018349622,0.001660673,0.96307164],"study_design_scores_gemma":[0.00041986114,0.0004086285,0.00315139,0.00020717042,0.000046578043,0.0003997917,0.00003389633,0.95340633,0.00031999595,0.004214121,0.037128907,0.00026334677],"about_ca_topic_score_codex":0.0002672162,"about_ca_topic_score_gemma":0.00012380641,"teacher_disagreement_score":0.9628083,"about_ca_system_score_codex":0.0006839893,"about_ca_system_score_gemma":0.0002386738,"threshold_uncertainty_score":0.56576717},"labels":[],"label_agreement":null},{"id":"W4403792148","doi":"10.1145/3664647.3681274","title":"A Simple and Provable Approach for Learning on Noisy Labeled Medical Images","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Simple (philosophy); Computer science; Artificial intelligence; Medical imaging; Epistemology; Philosophy","score_opus":0.013818399492536822,"score_gpt":0.2758047122140912,"score_spread":0.26198631272155437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403792148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025114613,0.00020706555,0.98865485,0.001019367,0.00014953897,0.00020754903,5.1709236e-7,0.0004547694,0.0067949034],"genre_scores_gemma":[0.8598332,0.000030107101,0.13381156,0.0003476218,0.00023458031,0.00018879886,0.0000031994962,0.000019298137,0.005531639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916524,0.00002569362,0.00008780311,0.00034078944,0.00021864254,0.00016185705],"domain_scores_gemma":[0.99961984,0.00015598422,0.000012433699,0.00012827318,0.000023116185,0.000060379738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004160377,0.00006982021,0.000076544704,0.000058220558,0.00009354327,0.00020852461,0.0001845321,0.00005128817,0.000024939092],"category_scores_gemma":[0.000084027095,0.000054113778,0.000023514254,0.00019060686,0.000024528788,0.00022216549,0.000101143756,0.00015594464,0.000010937668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030540094,0.000079113146,0.00021976241,0.00047990275,0.00005863712,0.000020060403,0.00071929983,0.0007255577,0.0028191586,0.07155197,0.032239284,0.8910567],"study_design_scores_gemma":[0.00018247923,0.00024569596,0.00003517265,0.000017311124,0.000003324586,0.000022711678,0.000022966327,0.9592715,0.0061496496,0.0021518865,0.03180463,0.000092663846],"about_ca_topic_score_codex":0.000021390499,"about_ca_topic_score_gemma":0.0000030874867,"teacher_disagreement_score":0.9585459,"about_ca_system_score_codex":0.000034477467,"about_ca_system_score_gemma":0.00006996761,"threshold_uncertainty_score":0.22066958},"labels":[],"label_agreement":null},{"id":"W4403896347","doi":"10.1016/j.bspc.2024.107074","title":"MFCPNet: Real time medical image segmentation network via multi-scale feature fusion and channel pruning","year":2024,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Pruning; Computer science; Artificial intelligence; Feature (linguistics); Segmentation; Channel (broadcasting); Scale (ratio); Pattern recognition (psychology); Image (mathematics); Image segmentation; Computer vision; Cartography; Computer network","score_opus":0.00576902465657069,"score_gpt":0.24328672899819637,"score_spread":0.23751770434162567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403896347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025790592,0.0041634915,0.98799956,0.0043778024,0.0002812785,0.00017334064,0.0000030195517,0.00034948942,0.00007296093],"genre_scores_gemma":[0.9750387,0.00018648051,0.02261179,0.00060364365,0.0012502135,0.00004533198,0.0000126234245,0.000023235429,0.00022797869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825925,0.00009139208,0.00021740297,0.00051327434,0.0005912108,0.0003274972],"domain_scores_gemma":[0.99936527,0.00012363597,0.00006410133,0.00008955971,0.0000478165,0.00030959805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006647577,0.00017146935,0.00020511648,0.00008437275,0.00030957002,0.00038381174,0.00019715974,0.00022976125,0.000029404913],"category_scores_gemma":[0.000016668688,0.00013483227,0.000033303328,0.0003831697,0.0002200462,0.00044040792,0.000114503615,0.00032144005,0.000011500069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003545295,0.00003220288,0.00003518374,0.00015157572,0.00001798638,0.000050797426,0.0005465941,0.000007903069,0.04346705,0.000014023005,0.0010649273,0.9545763],"study_design_scores_gemma":[0.00090438843,0.00018022826,0.0003999375,0.00040787758,0.000026502745,0.00011643707,0.000020618658,0.99550503,0.0002646407,0.0005488762,0.0014529342,0.00017251605],"about_ca_topic_score_codex":0.000027780972,"about_ca_topic_score_gemma":0.0000042452507,"teacher_disagreement_score":0.99549717,"about_ca_system_score_codex":0.000051677118,"about_ca_system_score_gemma":0.00014157068,"threshold_uncertainty_score":0.5498301},"labels":[],"label_agreement":null},{"id":"W4403909087","doi":"10.1038/s41698-024-00700-z","title":"Exploiting common patterns in diverse cancer types via multi-task learning","year":2024,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Council; Ministry of Science and Technology, Taiwan; Ministry of Health and Welfare","keywords":"Task (project management); Computer science; Artificial intelligence; Machine learning; Engineering","score_opus":0.04540894552096319,"score_gpt":0.3625464895415055,"score_spread":0.3171375440205423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403909087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38380498,0.0011283618,0.607693,0.00092249445,0.0045555644,0.00026088275,0.0000037877692,0.00047960292,0.0011513114],"genre_scores_gemma":[0.9931857,0.00030729178,0.005726186,0.00018695931,0.00018472255,0.000087735454,0.0000018072777,0.000017568545,0.00030200894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838597,0.00027751995,0.00029781973,0.00052577234,0.00021706309,0.00029587024],"domain_scores_gemma":[0.99902076,0.00053158106,0.00008284897,0.00025465008,0.000047046946,0.00006313939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005389068,0.00013527641,0.00021914403,0.0002672697,0.0001094548,0.00009502648,0.0004801705,0.00016910849,0.00014934452],"category_scores_gemma":[0.00006510226,0.00012950353,0.000056121786,0.00045442485,0.000030171324,0.00048508676,0.00036629272,0.0005644665,0.00019480733],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015410033,0.00003905733,0.012275582,0.000019930982,0.0000108802615,0.00011193281,0.002267086,0.0030832363,0.0032355655,0.00012163547,0.0002676656,0.97855204],"study_design_scores_gemma":[0.0010449047,0.0006942731,0.025568014,0.0004988403,0.000019466977,0.000082107195,0.00042411935,0.8420453,0.0070374813,0.0019047591,0.12020968,0.00047106037],"about_ca_topic_score_codex":0.000948186,"about_ca_topic_score_gemma":0.0022876963,"teacher_disagreement_score":0.9780809,"about_ca_system_score_codex":0.00072275166,"about_ca_system_score_gemma":0.00012699979,"threshold_uncertainty_score":0.5281001},"labels":[],"label_agreement":null},{"id":"W4403964658","doi":"10.3390/engproc2024076067","title":"A Self-Organizing Map Artificial Neural Network to Improve the K-Means Algorithm on the Classification of Different Cancers","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Artificial neural network; Computer science; Artificial intelligence; Self-organizing map; Pattern recognition (psychology); Algorithm","score_opus":0.021644939950410568,"score_gpt":0.2478724727081009,"score_spread":0.22622753275769034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403964658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014928946,0.00009841337,0.9435914,0.033829946,0.0055921827,0.00066627556,0.0000038391195,0.0004430515,0.00084591523],"genre_scores_gemma":[0.99057627,0.000008717741,0.007058565,0.0010777178,0.0009541988,0.000098438555,5.9092025e-7,0.000017379822,0.00020811611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998767,0.00009167457,0.00022065984,0.00036138057,0.0003203417,0.00023890744],"domain_scores_gemma":[0.99901855,0.0002641417,0.00005780834,0.0005616233,0.000054389006,0.000043473363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003032988,0.00012770326,0.00009659779,0.00004501933,0.0001960614,0.00023649848,0.0006427907,0.000040791238,0.000019647985],"category_scores_gemma":[0.000011736867,0.000066587745,0.00006287609,0.0006271957,0.000032177795,0.00012404453,0.0001449186,0.00021839466,0.000046534347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015896221,0.000038353115,0.000028762393,0.000040622905,0.00009038149,0.0000024892581,0.0038659663,0.0061057056,0.011782657,0.17877948,0.017196942,0.78205276],"study_design_scores_gemma":[0.000026105701,0.00015609867,0.0006092673,0.000025157957,0.000012122626,0.0000018696949,0.00015811523,0.9803198,0.010582834,0.0032168208,0.004794357,0.00009744755],"about_ca_topic_score_codex":0.00010443596,"about_ca_topic_score_gemma":0.00018052965,"teacher_disagreement_score":0.97564733,"about_ca_system_score_codex":0.00034410233,"about_ca_system_score_gemma":0.00008994641,"threshold_uncertainty_score":0.27153695},"labels":[],"label_agreement":null},{"id":"W4403978527","doi":"10.1016/j.ibmed.2024.100172","title":"Exploring the business aspects of digital pathology, deep learning in cancers","year":2024,"lang":"en","type":"article","venue":"Intelligence-Based Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Digital pathology; Pathology; Medicine","score_opus":0.07132914390205705,"score_gpt":0.2872618088322843,"score_spread":0.21593266493022725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403978527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035603493,0.002849856,0.95045775,0.004962356,0.0027802573,0.00018324843,7.996962e-7,0.00023442374,0.0029277909],"genre_scores_gemma":[0.99872035,0.00041513628,0.0003628444,0.00011867378,0.00026800478,0.00006122354,0.0000016500043,0.000014048564,0.00003809844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857056,0.00006211993,0.00036810868,0.00037946613,0.0003574346,0.00026229635],"domain_scores_gemma":[0.99879235,0.0006024583,0.00007747241,0.00035520017,0.00012154697,0.000050959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005669068,0.00014815044,0.00020619675,0.0003452589,0.000056392506,0.000053577354,0.00058221555,0.000039986695,0.000025258689],"category_scores_gemma":[0.00038492132,0.00009991149,0.000040888885,0.0020684134,0.00030253327,0.000507734,0.000082120394,0.00039273794,0.000019453966],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019199359,0.00001273576,0.00048053055,0.00012242932,0.000012562874,0.00019229262,0.00373843,0.04730318,0.00062334724,0.008666111,0.000026924194,0.93880224],"study_design_scores_gemma":[0.00062756555,0.0015520959,0.009150605,0.00605419,0.000059034537,0.00022761858,0.0039490066,0.8408176,0.08193718,0.03721555,0.017621808,0.00078777387],"about_ca_topic_score_codex":0.00040227408,"about_ca_topic_score_gemma":0.00018261175,"teacher_disagreement_score":0.9631168,"about_ca_system_score_codex":0.000322925,"about_ca_system_score_gemma":0.00030616482,"threshold_uncertainty_score":0.40742725},"labels":[],"label_agreement":null},{"id":"W4403988904","doi":"10.1038/s41598-024-74305-8","title":"Integrative hybrid deep learning for enhanced breast cancer diagnosis: leveraging the Wisconsin Breast Cancer Database and the CBIS-DDSM dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Air (Canada)","funders":"","keywords":"Breast cancer; Cancer; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.015360023571077326,"score_gpt":0.2827648674454471,"score_spread":0.26740484387436975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403988904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043184184,0.017592186,0.853712,0.035626993,0.04315539,0.003060503,0.0028013526,0.0006407135,0.00022666359],"genre_scores_gemma":[0.9946112,0.00044369447,0.0009138587,0.00034646623,0.00042806912,0.0023531627,0.00020339602,0.00003099995,0.0006691364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967596,0.00022367912,0.00047836525,0.0014839075,0.0005803119,0.00047413146],"domain_scores_gemma":[0.9975054,0.00055677403,0.0003033708,0.0012810708,0.0002452084,0.000108134096],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030859162,0.00027734166,0.00025428087,0.00015231132,0.0015255464,0.002388423,0.00064595003,0.000037368063,0.00009630576],"category_scores_gemma":[0.00014655646,0.00015545356,0.00010415767,0.0008605667,0.0009435845,0.0013894961,0.0005314294,0.00044633637,0.000007211108],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012880754,0.000063397245,0.0013427505,0.0002584437,0.00036817358,0.00028200832,0.011141587,0.0034197238,0.0058997967,0.0020846582,0.25171095,0.7232997],"study_design_scores_gemma":[0.0014597244,0.00006120032,0.0028270986,0.0026365092,0.00046054687,0.007827053,0.0019047136,0.48344797,0.06342478,0.02768674,0.40675196,0.0015116966],"about_ca_topic_score_codex":0.0013466829,"about_ca_topic_score_gemma":0.00103635,"teacher_disagreement_score":0.95142704,"about_ca_system_score_codex":0.00024292244,"about_ca_system_score_gemma":0.00046767623,"threshold_uncertainty_score":0.99977434},"labels":[],"label_agreement":null},{"id":"W4404052940","doi":"10.1136/jitc-2024-sitc2024.0103","title":"103 A deep-learning approach to guide acquisition region selection for Imaging Mass Cytometry","year":2024,"lang":"en","type":"article","venue":"Regular and Young Investigator Award Abstracts","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Standards Association","funders":"","keywords":"Mass cytometry; Computer science; Selection (genetic algorithm); Artificial intelligence; Deep learning; Machine learning; Chemistry","score_opus":0.01268774742898928,"score_gpt":0.24808452451177052,"score_spread":0.23539677708278123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404052940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024204869,0.00091284805,0.97003436,0.0015003529,0.00095971784,0.00044586632,0.0000018021126,0.000750934,0.001189232],"genre_scores_gemma":[0.8793749,0.000035288438,0.11882524,0.00044265,0.0005038738,0.00013495827,0.000013596224,0.00004650173,0.0006229662],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980224,0.000074031595,0.00034250968,0.0008065835,0.000340735,0.00041378083],"domain_scores_gemma":[0.9990528,0.0000717856,0.000097117314,0.00027138676,0.00013055088,0.00037635065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071305037,0.00023591114,0.00019415801,0.0004042668,0.0003227218,0.0007462918,0.00026471925,0.00012333744,9.692936e-7],"category_scores_gemma":[0.00019170741,0.00024608392,0.00009663837,0.0008583129,0.000064388274,0.0010016112,0.00007959231,0.0002702036,0.000019020012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018954997,0.000172396,0.01155147,0.0032052572,0.00044413382,0.00014446865,0.008532709,0.047465146,0.46371964,0.04162877,0.064830616,0.35811585],"study_design_scores_gemma":[0.00043812857,0.00022758546,0.007816968,0.00039467067,0.000077067256,0.0010193196,0.00020166313,0.8463171,0.04814537,0.00960466,0.084990084,0.00076736783],"about_ca_topic_score_codex":0.00005973266,"about_ca_topic_score_gemma":0.0000034468471,"teacher_disagreement_score":0.8551701,"about_ca_system_score_codex":0.0003533429,"about_ca_system_score_gemma":0.00016769062,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W4404059079","doi":"10.3390/ai5040111","title":"Enhancing Medical Image Classification with Unified Model Agnostic Computation and Explainable AI","year":2024,"lang":"en","type":"article","venue":"AI","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Computation; Image (mathematics); Pattern recognition (psychology); Algorithm","score_opus":0.014525626186200064,"score_gpt":0.2789679975838674,"score_spread":0.26444237139766735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404059079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010731247,0.00012847039,0.9818394,0.0061281673,0.00019590084,0.0001032841,4.949347e-7,0.0002706254,0.00060236955],"genre_scores_gemma":[0.9692135,0.000025973222,0.02991629,0.0006248376,0.00005750046,0.000025291227,0.0000029644596,0.00000993943,0.00012374397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990747,0.000030952237,0.00012783767,0.0003209377,0.00030592855,0.00013963859],"domain_scores_gemma":[0.99955094,0.00012265888,0.00002585497,0.0001589102,0.000070927366,0.00007071325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024147707,0.00008022355,0.00007274304,0.00008646234,0.00009765833,0.00023790043,0.00014809314,0.000055649594,0.000005655234],"category_scores_gemma":[0.000039265014,0.000069875336,0.000011778225,0.0003038774,0.000048184465,0.00080759433,0.00006123157,0.00017498955,0.00002481387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007182981,0.00014422322,0.00022677235,0.00095941557,0.00011695778,0.00033885028,0.009951269,0.075153306,0.041919425,0.23706327,0.0163764,0.6176783],"study_design_scores_gemma":[0.000117135816,0.00006454503,0.00019668404,0.00010638192,0.0000069806365,0.00004099996,0.000028444869,0.9868568,0.003223512,0.009000533,0.00026767942,0.00009030214],"about_ca_topic_score_codex":0.00003568327,"about_ca_topic_score_gemma":0.000039152357,"teacher_disagreement_score":0.9584822,"about_ca_system_score_codex":0.00008941678,"about_ca_system_score_gemma":0.00020994518,"threshold_uncertainty_score":0.28494337},"labels":[],"label_agreement":null},{"id":"W4404091030","doi":"10.2139/ssrn.5010345","title":"GardnerNet: An Interpretable Deep Learning Model for Quantitative Human Blastocyst Evaluation - A Retrospective Model Development and Validation Study","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Blastocyst; Artificial intelligence; Computer science; Deep learning; Machine learning; Biology; Embryo; Embryogenesis","score_opus":0.05308604765636022,"score_gpt":0.35454558192851704,"score_spread":0.3014595342721568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404091030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30431455,0.0008297482,0.693161,0.000048432914,0.00028856425,0.0011490354,0.0000019358358,0.00011402674,0.00009267621],"genre_scores_gemma":[0.96677667,0.00012231103,0.031778544,0.00000989385,0.00012894963,0.0005294129,0.000019308764,0.000063828615,0.0005710865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995712,0.0003665463,0.00064712204,0.0011254023,0.0008985464,0.0012503942],"domain_scores_gemma":[0.99813926,0.0000503384,0.0005941327,0.0003820714,0.00073039904,0.000103816696],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0071081617,0.00041656208,0.00042804008,0.00045788568,0.0006702342,0.00079069525,0.0007016861,0.0002062436,0.0000017361468],"category_scores_gemma":[0.00012926747,0.0004261292,0.000118043485,0.00020757737,0.000036553807,0.0006816528,0.000756822,0.0039140605,0.0000035600788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008292301,0.00013701594,0.00011172685,0.00004960794,0.0005259882,8.0395307e-7,0.030067327,0.8826532,0.0003229832,0.0439776,0.000007661207,0.04206318],"study_design_scores_gemma":[0.00040865593,0.0008404607,0.000043517946,0.000072016424,0.00012418082,0.000022309567,0.0013370124,0.58265686,0.000116100004,0.41412234,0.0000019222166,0.0002546438],"about_ca_topic_score_codex":0.00004879476,"about_ca_topic_score_gemma":0.0017231692,"teacher_disagreement_score":0.6624621,"about_ca_system_score_codex":0.0080771465,"about_ca_system_score_gemma":0.005102929,"threshold_uncertainty_score":0.99981904},"labels":[],"label_agreement":null},{"id":"W4404313480","doi":"10.48550/arxiv.2410.19820","title":"Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Terry Fox Foundation","keywords":"Scarcity; Histopathology; Data science; Computer science; Economics; Medicine; Pathology","score_opus":0.07453608724444986,"score_gpt":0.22340422876323227,"score_spread":0.14886814151878242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404313480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026093312,0.012176447,0.95771605,0.0007589163,0.0007769812,0.000440183,0.0000048425295,0.00042958173,0.0016036787],"genre_scores_gemma":[0.98411864,0.009479573,0.005249198,0.00043608434,0.000069340356,0.0000031423915,0.000021389491,0.00003611375,0.0005865466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970621,0.00029741725,0.0002348775,0.0018832935,0.00012070244,0.00040161292],"domain_scores_gemma":[0.99740934,0.00010672919,0.00023318939,0.0020633596,0.00008234604,0.00010505537],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070348306,0.0003039726,0.00044010777,0.00039858272,0.00009482581,0.00007070759,0.0025163733,0.00021746187,0.000016109807],"category_scores_gemma":[0.000058784848,0.00033266612,0.00007423619,0.0011785721,0.000105465006,0.00045496598,0.006806411,0.0017485113,0.00007126058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007608192,0.000103729784,0.009968708,0.005540074,0.00013133894,0.005760566,0.00065551104,0.89783984,0.00007639717,0.0425181,0.0006998779,0.03662976],"study_design_scores_gemma":[0.00043763043,0.00013352641,0.001983975,0.006077378,0.000250372,0.00016809079,0.000100150195,0.9424715,0.000027232618,0.041467294,0.0059915506,0.0008913018],"about_ca_topic_score_codex":0.00022777212,"about_ca_topic_score_gemma":0.0012087043,"teacher_disagreement_score":0.9580253,"about_ca_system_score_codex":0.0010035364,"about_ca_system_score_gemma":0.00038524196,"threshold_uncertainty_score":0.99991256},"labels":[],"label_agreement":null},{"id":"W4404381059","doi":"10.18280/ts.410512","title":"Design of an Efficient Multimodal Correlation Engine for Smart IoMT Imaging System for Pre-Emptive Analysis of Breast Cancer Stages","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Breast cancer; Correlation; Cancer; Medicine; Mathematics; Internal medicine","score_opus":0.013976219295592084,"score_gpt":0.27904294899231646,"score_spread":0.2650667296967244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404381059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045818895,0.00019178743,0.9519521,0.00007104181,0.00043874138,0.0010566043,0.00034698975,0.00011970702,0.000004139754],"genre_scores_gemma":[0.9617124,0.0000020911866,0.037759136,0.000007496119,0.000081911625,0.000385469,0.000023571602,0.000015348902,0.000012557111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985217,0.000072428804,0.00044539658,0.00042263325,0.00032637062,0.0002114582],"domain_scores_gemma":[0.99894696,0.0003147467,0.00019944616,0.00020636556,0.00028056512,0.000051899096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073453126,0.00015262174,0.00028355123,0.0004656773,0.000073648014,0.00006369289,0.00026429154,0.00003815593,0.000017269447],"category_scores_gemma":[0.000005492887,0.0001428994,0.00017026784,0.00075034046,0.000035889872,0.00029677234,0.000031859756,0.000051816187,3.4819624e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018189242,0.0000796276,0.00035990973,0.00035928978,0.00053369004,7.7321914e-7,0.0018934257,0.9464049,0.012558609,0.00076261663,0.000029946159,0.036835365],"study_design_scores_gemma":[0.000554097,0.0002302189,0.0062150047,0.00016116486,0.00055633,0.0000023635178,0.000110064895,0.9761673,0.015831335,0.000023470693,0.000014110457,0.00013452714],"about_ca_topic_score_codex":0.00015852666,"about_ca_topic_score_gemma":0.000014442903,"teacher_disagreement_score":0.9158935,"about_ca_system_score_codex":0.00032644605,"about_ca_system_score_gemma":0.000116303105,"threshold_uncertainty_score":0.58272684},"labels":[],"label_agreement":null},{"id":"W4404518252","doi":"10.1200/cci.24.00110","title":"Classifying Tumor Reportability Status From Unstructured Electronic Pathology Reports Using Language Models in a Population-Based Cancer Registry Setting","year":2024,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Provincial Health Services Authority; University of British Columbia","funders":"","keywords":"Medical diagnosis; Artificial intelligence; Population; Computer science; Cancer registry; Pipeline (software); Natural language processing; Machine learning; Cancer; Set (abstract data type); Medicine; Medical physics; Pathology; Internal medicine","score_opus":0.045028483084341965,"score_gpt":0.38469053729813535,"score_spread":0.33966205421379336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404518252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77692527,0.0016437595,0.21773769,0.00022891871,0.0026210176,0.00036013135,0.00005376268,0.0003356296,0.0000938385],"genre_scores_gemma":[0.96433556,0.00010513581,0.03418767,0.0008412914,0.0003558944,0.00009917159,0.00003805187,0.000029483923,0.000007757158],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952434,0.00018898903,0.0026482197,0.0006422383,0.0005440323,0.00073315896],"domain_scores_gemma":[0.99684775,0.0005797836,0.0011682815,0.0011194594,0.00012547743,0.000159224],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017076095,0.0002874929,0.00053859496,0.00018597659,0.000120735625,0.00027553426,0.0003852391,0.00028771508,0.000042989595],"category_scores_gemma":[0.0005070664,0.00027537142,0.00019521995,0.0008095597,0.00008915973,0.0012281013,0.00018361956,0.0011810976,0.0000017544329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073561365,0.000054504355,0.52732116,0.00060999044,0.00008699128,0.0006175245,0.0042665345,0.321431,0.00013685624,0.0004982693,0.00017386631,0.14472973],"study_design_scores_gemma":[0.00031355798,0.000038349266,0.027276801,0.00034700596,0.00003955622,0.000056392986,0.00014450315,0.96174246,0.0001653245,0.009055715,0.0004915257,0.00032879072],"about_ca_topic_score_codex":0.009180221,"about_ca_topic_score_gemma":0.0043960125,"teacher_disagreement_score":0.6403115,"about_ca_system_score_codex":0.0020257381,"about_ca_system_score_gemma":0.0029284703,"threshold_uncertainty_score":0.99996984},"labels":[],"label_agreement":null},{"id":"W4404548366","doi":"10.1177/10668969241294239","title":"Identification of Distinct Visual Scan Paths for Pathologists in Rare-Element Search Tasks","year":2024,"lang":"en","type":"article","venue":"International Journal of Surgical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Visual search; Fixation (population genetics); Saccade; Computer science; Eye tracking; Gaze; Task (project management); Digital pathology; Eye movement; Medicine; Artificial intelligence","score_opus":0.02678253291498406,"score_gpt":0.3669080253111848,"score_spread":0.34012549239620077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404548366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5108519,0.00051573873,0.48193464,0.002845538,0.0035213763,0.00015050155,0.00003666919,0.000024672543,0.00011891889],"genre_scores_gemma":[0.9972898,0.00013273692,0.0021373234,0.000032053016,0.00033497688,0.000016344875,0.000006480924,0.000008350155,0.00004198404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997933,0.00017617086,0.00091118837,0.00026540214,0.0005350521,0.00017921237],"domain_scores_gemma":[0.99858713,0.00042219777,0.0002924824,0.00013245828,0.0005131866,0.000052560026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018722292,0.000100349775,0.00022240398,0.00050182344,0.00002263476,0.000087091816,0.0007487244,0.0000903313,0.000026494377],"category_scores_gemma":[0.00012335743,0.00008663348,0.00016163533,0.0002546367,0.00010887652,0.0003585143,0.00015661553,0.0002590776,0.00000698026],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009489013,0.0009119411,0.014531082,0.00018623317,0.00023776249,0.011606243,0.0025480103,0.0035023731,0.057640646,0.06708928,0.0010145622,0.83978295],"study_design_scores_gemma":[0.011759913,0.006737046,0.21355312,0.0014879999,0.000119985874,0.026909383,0.0006408484,0.41828698,0.15282305,0.108231775,0.05796717,0.0014827453],"about_ca_topic_score_codex":0.000009397018,"about_ca_topic_score_gemma":0.000008572761,"teacher_disagreement_score":0.8383002,"about_ca_system_score_codex":0.00028223576,"about_ca_system_score_gemma":0.0001666909,"threshold_uncertainty_score":0.35328108},"labels":[],"label_agreement":null},{"id":"W4404635302","doi":"10.1371/journal.pone.0303415","title":"Causal debiasing for unknown bias in histopathology—A colon cancer use case","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University Health Network; Ontario Institute for Cancer Research","funders":"National Cancer Institute","keywords":"Debiasing; Computer science; Spurious relationship; Histopathology; Population; Artificial intelligence; Statistics; Machine learning; Data mining; Medicine; Pathology; Mathematics","score_opus":0.21361538929912946,"score_gpt":0.3159046316965338,"score_spread":0.10228924239740436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404635302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93934375,0.0012009637,0.05640658,0.0013726011,0.0008941417,0.00039773472,0.000014784402,0.00030128233,0.00006818991],"genre_scores_gemma":[0.968333,0.0000695104,0.030110864,0.00023888957,0.0001998829,0.0002788016,0.0000014531701,0.00002186442,0.00074570545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989409,0.000058355945,0.00018546704,0.00041166224,0.00015099368,0.00025262643],"domain_scores_gemma":[0.9992721,0.00030610722,0.000038635462,0.00027137357,0.00006364724,0.000048106787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026038988,0.000104975865,0.00015755193,0.00018296535,0.000078712175,0.00014652952,0.0001798434,0.000081991304,0.000009745223],"category_scores_gemma":[0.00012447454,0.00011001572,0.00003475077,0.00041739843,0.00003552907,0.0004997752,0.00008575508,0.00017419487,0.000015241378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047853598,0.0037393968,0.031455602,0.0042313365,0.0006001906,0.035828512,0.027453747,0.0029221233,0.39136627,0.039942548,0.013819365,0.44816238],"study_design_scores_gemma":[0.0011521393,0.0007179763,0.0025175142,0.0015253713,0.00019845506,0.0013044885,0.000041178788,0.869182,0.10313158,0.0034216603,0.015956037,0.0008516049],"about_ca_topic_score_codex":0.00076987327,"about_ca_topic_score_gemma":0.0033940398,"teacher_disagreement_score":0.8662599,"about_ca_system_score_codex":0.0005993856,"about_ca_system_score_gemma":0.0001506326,"threshold_uncertainty_score":0.44863108},"labels":[],"label_agreement":null},{"id":"W4404732966","doi":"10.1016/j.clinimag.2024.110369","title":"Diversity, inclusivity and traceability of mammography datasets used in development of Artificial Intelligence technologies: a systematic review","year":2024,"lang":"en","type":"review","venue":"Clinical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"National Institute for Health and Care Research","keywords":"Traceability; Medicine; Diversity (politics); Mammography; Medical physics; Artificial intelligence; Data science; Internal medicine; Software engineering; Computer science","score_opus":0.16026318672061754,"score_gpt":0.44592336085391887,"score_spread":0.28566017413330136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404732966","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001919113,0.9625256,0.035470985,0.000078138204,0.0002889184,0.0014454852,0.00003328989,0.00013492984,0.0000034462635],"genre_scores_gemma":[0.000963257,0.9888633,0.0100683095,0.000015439568,0.000008203353,0.00006413231,0.0000072812604,0.000009698936,3.8726455e-7],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9951614,0.0005291447,0.0029368212,0.0008070667,0.0003691633,0.00019638405],"domain_scores_gemma":[0.9964345,0.0012405874,0.0010914917,0.0011166858,0.00007053642,0.000046161338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057427734,0.00028236376,0.0026603346,0.00032347164,0.000096957636,0.00003210614,0.0015822777,0.00016623615,9.871784e-7],"category_scores_gemma":[0.0015256102,0.0002223702,0.00036357378,0.0015791924,0.00040873772,0.0002307102,0.007775752,0.00066883623,0.000005066779],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.826073e-7,0.000050060873,0.000087307424,0.48050177,0.00003648351,0.0000059038925,0.00007994862,3.958552e-8,3.3315207e-8,0.00005431591,0.0000103584,0.5191733],"study_design_scores_gemma":[0.000038309106,0.00004182884,0.000022071285,0.9902698,0.0012505255,0.000022838194,0.00007366145,0.0012735004,0.000009429644,0.0035520322,0.0030310606,0.000414958],"about_ca_topic_score_codex":0.000013231158,"about_ca_topic_score_gemma":0.000032804386,"teacher_disagreement_score":0.51875836,"about_ca_system_score_codex":0.00013947058,"about_ca_system_score_gemma":0.00029901238,"threshold_uncertainty_score":0.96919185},"labels":[],"label_agreement":null},{"id":"W4404889079","doi":"10.62527/joiv.8.3-2.1912","title":"Applying Deep Learning Models to Breast Ultrasound Images for Automating Breast Cancer Diagnosis","year":2024,"lang":"en","type":"article","venue":"JOIV International Journal on Informatics Visualization","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Universiti Tun Hussein Onn Malaysia","keywords":"Breast cancer; Breast ultrasound; Ultrasound; Artificial intelligence; Deep learning; Medicine; Computer science; Radiology; Medical physics; Cancer; Internal medicine; Mammography","score_opus":0.02395013338700199,"score_gpt":0.3282982160173187,"score_spread":0.3043480826303167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404889079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033561627,0.00006675182,0.99101275,0.0010777882,0.0032028442,0.00042639236,0.00006626238,0.00035936915,0.00043168047],"genre_scores_gemma":[0.9420281,0.00057484116,0.05201214,0.0018459796,0.0017543061,0.0015038879,0.000047433416,0.00006629268,0.00016703074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976924,0.000051229203,0.000797888,0.00020320294,0.00096518704,0.00029010835],"domain_scores_gemma":[0.9981185,0.00038585087,0.00038929787,0.00014005243,0.00082133705,0.00014495815],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00070061267,0.00021482776,0.000170527,0.0007209126,0.0003560452,0.002474987,0.0007002614,0.000084545354,0.00006077082],"category_scores_gemma":[0.000106835796,0.00020230551,0.00013586778,0.0005305197,0.000016248905,0.0037770623,0.0001266969,0.00031264772,0.000044007746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039721894,0.000050432798,0.00069678226,0.00013034299,0.0001986305,0.000005683078,0.005971066,0.57118267,0.00026331618,0.026512137,0.004559931,0.3903893],"study_design_scores_gemma":[0.0002917652,0.000085062056,0.00050814025,0.00070716813,0.000018714367,0.00070329645,0.00031484233,0.9872531,0.00084111845,0.0025796224,0.00644317,0.00025397242],"about_ca_topic_score_codex":0.000016063374,"about_ca_topic_score_gemma":0.0000032453831,"teacher_disagreement_score":0.9390006,"about_ca_system_score_codex":0.0009472492,"about_ca_system_score_gemma":0.00013319957,"threshold_uncertainty_score":0.99856055},"labels":[],"label_agreement":null},{"id":"W4405012360","doi":"10.1016/j.compbiomed.2024.109489","title":"Predicting cancer content in tiles of lung squamous cell carcinoma tumours with validation against pathologist labels","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Government of Ontario; London Health Sciences Foundation; Ontario Institute for Cancer Research; Merck","keywords":"Basal cell; Lung cancer; Pathology; Medicine; Lung; Cancer; Squamous carcinoma; Carcinoma; Internal medicine","score_opus":0.025962118968421016,"score_gpt":0.2930219672264615,"score_spread":0.2670598482580405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405012360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9291653,0.0058580968,0.06237888,0.0010505281,0.0011166494,0.00018131999,0.00000300965,0.00005352724,0.00019267661],"genre_scores_gemma":[0.99767274,0.00025474763,0.0017160627,0.00020751967,0.00010218988,0.00002470444,0.000005675002,0.0000052851374,0.000011092797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904835,0.00009767947,0.00025648257,0.0003514306,0.000072255505,0.00017380466],"domain_scores_gemma":[0.99946845,0.0002361966,0.000078912024,0.0001459108,0.000035786692,0.000034774555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003787688,0.00011149485,0.00022300557,0.00022923303,0.000028805445,0.00000884998,0.0001858169,0.00007973808,0.0000018701624],"category_scores_gemma":[0.000020825852,0.00008053128,0.000011921832,0.0003105522,0.00024055323,0.00008436463,0.00008844559,0.00018997538,2.4071994e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042878888,0.000034626475,0.95059425,0.00028411267,0.000007906989,0.000114478775,0.0034612285,0.0007804428,0.0067810616,0.0016931345,0.0002434584,0.03596242],"study_design_scores_gemma":[0.0040451414,0.0021047604,0.59706116,0.002218895,0.000039074064,0.0001052856,0.0005538618,0.3768393,0.014917425,0.0014236938,0.0002731327,0.0004182814],"about_ca_topic_score_codex":0.0005640141,"about_ca_topic_score_gemma":0.00014303166,"teacher_disagreement_score":0.37605885,"about_ca_system_score_codex":0.00010186168,"about_ca_system_score_gemma":0.0000583698,"threshold_uncertainty_score":0.32839704},"labels":[],"label_agreement":null},{"id":"W4405046335","doi":"10.1182/blood-2024-209372","title":"Machine Learning Classification of Spatial Patterns of Malignant Cells Reveals Implications in Prognosis and Tumor Microenvironment Composition in Lymphoma","year":2024,"lang":"en","type":"article","venue":"Blood","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre","funders":"","keywords":"Tumor microenvironment; Lymphoma; Cancer research; Medicine; Pathology; Biology; Tumor cells","score_opus":0.01148385358076656,"score_gpt":0.2232925651426285,"score_spread":0.21180871156186193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405046335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9577214,0.00032230935,0.041334566,0.00028400452,0.00004522444,0.00023786536,0.000014774112,0.000022243423,0.000017612196],"genre_scores_gemma":[0.9975607,0.0001440396,0.0021946437,0.00000899071,0.000011383429,0.000061982835,0.0000063667117,0.0000065368954,0.0000053894164],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991827,0.000073860596,0.00029686105,0.00025135724,0.000100503166,0.00009474198],"domain_scores_gemma":[0.9996593,0.000046493897,0.00010822351,0.00015503216,0.000011906308,0.000019071773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018185773,0.00006809053,0.000113370275,0.00016291575,0.000018265839,0.00002143947,0.00012531932,0.000028199338,0.000002568972],"category_scores_gemma":[0.0000031749494,0.00007040405,0.00002120521,0.00018089215,0.000021545906,0.000115786504,0.00006908811,0.00005870105,0.0000014261368],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000415601,0.0002487694,0.30879548,0.00014599792,0.000007720697,0.0000033198742,0.00039230654,0.000102847946,0.66568094,0.00048664224,0.0000010186616,0.024130777],"study_design_scores_gemma":[0.00033251807,0.00009187982,0.7273615,0.00020802305,0.0000105945655,0.000013095173,0.000012417018,0.01849237,0.2532436,0.00015074128,0.000025211213,0.00005805425],"about_ca_topic_score_codex":0.00041004352,"about_ca_topic_score_gemma":0.00008040656,"teacher_disagreement_score":0.41856605,"about_ca_system_score_codex":0.00006786919,"about_ca_system_score_gemma":0.000019837491,"threshold_uncertainty_score":0.2870994},"labels":[],"label_agreement":null},{"id":"W4405099123","doi":"10.22215/etd/2024-16316","title":"Cervical Cell Separation using Deep Learning Techniques","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Pipeline (software); Segmentation; Artificial intelligence; Deep learning; Computer science; Transfer of learning; Process (computing); Pattern recognition (psychology); Image segmentation","score_opus":0.013946054770170288,"score_gpt":0.31674159182486683,"score_spread":0.30279553705469653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405099123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008909542,0.0007381224,0.9037273,0.00005097549,0.002547704,0.00029963886,3.3178168e-7,0.0019039053,0.081822485],"genre_scores_gemma":[0.555442,0.0002630852,0.3707029,0.00019649332,0.0012841736,0.00016031694,0.00021947417,0.00017069849,0.07156091],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854964,0.00005830596,0.00027073314,0.0005714474,0.0003477832,0.0002020827],"domain_scores_gemma":[0.99937034,0.000031855463,0.00013843391,0.00029503822,0.00011692563,0.000047384205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017214112,0.00022332485,0.00017702041,0.00027063477,0.00014337414,0.00039681757,0.00042091263,0.0003568986,0.00007067198],"category_scores_gemma":[0.000008548487,0.00022339895,0.0001010452,0.00048038873,0.000008024404,0.0004152125,0.00007710027,0.0006107552,0.00017337894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007037234,0.0001327832,0.000089218156,0.002760866,0.00013420964,0.00008902105,0.014447929,0.003652674,0.20880452,0.019575872,0.0031840021,0.7470585],"study_design_scores_gemma":[0.000053869382,0.00013705072,0.00006055246,0.00018575687,0.000052020376,0.000017091861,0.0003351811,0.5298422,0.44749713,0.0038386786,0.017427674,0.00055278797],"about_ca_topic_score_codex":0.00012349637,"about_ca_topic_score_gemma":0.00019445513,"teacher_disagreement_score":0.74650574,"about_ca_system_score_codex":0.00028478957,"about_ca_system_score_gemma":0.00012681994,"threshold_uncertainty_score":0.9109945},"labels":[],"label_agreement":null},{"id":"W4405315434","doi":"10.1016/j.ebiom.2024.105501","title":"Where, why, and how is bias learned in medical image analysis models? A study of bias encoding within convolutional networks using synthetic data","year":2024,"lang":"en","type":"article","venue":"EBioMedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Parkinson Association of Alberta; Canada Research Chairs; Parkinson Vereniging; Alberta Innovates; Killam Trusts; Calgary Foundation","keywords":"Computer science; Artificial intelligence; Encoding (memory); Image (mathematics); Computational biology; Pattern recognition (psychology); Biology","score_opus":0.13589943027342094,"score_gpt":0.3434554820434194,"score_spread":0.20755605176999847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405315434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13947093,0.0041633793,0.85140705,0.00403759,0.000557821,0.00021393847,0.000009637612,0.00008741266,0.00005225038],"genre_scores_gemma":[0.9947061,0.0001972372,0.004754973,0.00012512674,0.0001591991,0.00000602268,0.000008740341,0.000012493976,0.00003011306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974324,0.0002289234,0.00040187797,0.0007793194,0.0009204417,0.00023702964],"domain_scores_gemma":[0.99848247,0.00037417116,0.0001361017,0.00080377667,0.00007738309,0.00012607255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022962266,0.00016620662,0.00041149225,0.0008509142,0.00006875108,0.00013140497,0.0007397843,0.0000995018,0.00005194584],"category_scores_gemma":[0.00018664327,0.00013746967,0.000038849637,0.0031930092,0.0002376857,0.00081025076,0.0006727047,0.00033444943,8.3563083e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007644626,0.004402864,0.091360584,0.0039109,0.015507822,0.0061226287,0.14998399,0.23427522,0.011828273,0.009836738,0.039681483,0.43232504],"study_design_scores_gemma":[0.00052435044,0.00017966348,0.00046957788,0.00039949454,0.00021325765,0.000051621846,0.00073441607,0.99682266,0.000025149488,0.00036037783,0.00009534569,0.00012410514],"about_ca_topic_score_codex":0.0010601776,"about_ca_topic_score_gemma":0.00075145037,"teacher_disagreement_score":0.85523516,"about_ca_system_score_codex":0.00011556172,"about_ca_system_score_gemma":0.00016854375,"threshold_uncertainty_score":0.5605851},"labels":[],"label_agreement":null},{"id":"W4405475062","doi":"10.1561/116.20240048","title":"When Federated Learning Meets Medical Image Analysis: A Systematic Review with Challenges and Solutions","year":2024,"lang":"en","type":"review","venue":"APSIPA Transactions on Signal and Information Processing","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Image (mathematics); Data science; Information retrieval; Artificial intelligence","score_opus":0.029388595797864417,"score_gpt":0.2824501714748403,"score_spread":0.2530615756769759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405475062","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.458781e-8,0.5751549,0.423464,0.00046832612,0.000029752087,0.00043713689,0.0000031691927,0.00017315512,0.00026953267],"genre_scores_gemma":[0.00026286257,0.9975034,0.0014238172,0.00021098579,0.000016747761,0.00048795334,0.00001997353,0.000016749602,0.00005748878],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99745566,0.00023529434,0.0009842372,0.00039562478,0.00067441707,0.00025476824],"domain_scores_gemma":[0.9987696,0.00013254672,0.00052348117,0.0002039541,0.00020465776,0.00016579518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009516231,0.00039987272,0.001357209,0.0007814357,0.0006248437,0.00080738426,0.0002599975,0.00021862573,0.00002776161],"category_scores_gemma":[0.000032315456,0.0002673955,0.00019819806,0.0012474129,0.000086716085,0.0037136541,0.000023783276,0.00078022084,0.000041607484],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011560959,0.000007847102,2.0788629e-9,0.4110192,0.00037865972,0.000002120535,0.0004734011,0.000011343829,1.40708485e-8,0.00014395747,0.000009728998,0.58795255],"study_design_scores_gemma":[0.00021010404,0.00024791138,2.31132e-7,0.8098323,0.017362162,0.00071674987,0.00033027073,0.09308586,0.0000011772464,0.00011308833,0.07733754,0.0007626388],"about_ca_topic_score_codex":0.000006644958,"about_ca_topic_score_gemma":0.000015629956,"teacher_disagreement_score":0.5871899,"about_ca_system_score_codex":0.00011151721,"about_ca_system_score_gemma":0.00039340035,"threshold_uncertainty_score":0.9999778},"labels":[],"label_agreement":null},{"id":"W4405489389","doi":"10.1109/embc53108.2024.10782494","title":"Semantic AutoSAM: Self-Prompting Segment Anything Model for Semantic Segmentation of Medical Images","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"HORIZON EUROPE Health; Alberta Innovates","keywords":"Computer science; Segmentation; Image segmentation; Artificial intelligence; Natural language processing; Semantics (computer science); Computer vision; Information retrieval; Programming language","score_opus":0.023684299931967932,"score_gpt":0.3085619806043522,"score_spread":0.2848776806723843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405489389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012437287,0.00021958325,0.98241955,0.0028141383,0.0007203485,0.000386058,0.000002372259,0.0007570876,0.00024358691],"genre_scores_gemma":[0.70031095,0.000042979325,0.29909706,0.00014657923,0.00009726928,0.0000618326,0.0000028505228,0.00001671766,0.00022377026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804515,0.000038183112,0.00040050334,0.0004662847,0.0007853199,0.0002645675],"domain_scores_gemma":[0.9992826,0.00019305243,0.000083616804,0.0002852026,0.00007639305,0.00007916035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010239987,0.00014303575,0.00017456019,0.0001676065,0.00010647145,0.00020765085,0.00049301283,0.00009196286,0.000021490458],"category_scores_gemma":[0.00003927884,0.00012718127,0.00009546615,0.0003290724,0.00002673811,0.00070763414,0.00022225246,0.00014514172,0.0000123283035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034253404,0.00045303977,0.00035520954,0.0090307975,0.0006982454,0.000076358956,0.028030554,0.08075699,0.13220021,0.10162933,0.013702494,0.6330325],"study_design_scores_gemma":[0.00021135982,0.0000661443,0.000031833068,0.00021989034,0.000027798013,0.000024860574,0.000085891676,0.95969623,0.035614833,0.0038379044,0.000046412835,0.00013683233],"about_ca_topic_score_codex":0.00005864436,"about_ca_topic_score_gemma":0.000017614966,"teacher_disagreement_score":0.8789393,"about_ca_system_score_codex":0.00016328685,"about_ca_system_score_gemma":0.00020259865,"threshold_uncertainty_score":0.51863015},"labels":[],"label_agreement":null},{"id":"W4405532782","doi":"10.1007/s12672-024-01671-0","title":"Research trends on AI in breast cancer diagnosis, and treatment over two decades","year":2024,"lang":"en","type":"review","venue":"Discover Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Oncology; Medicine; Internal medicine; Cancer","score_opus":0.13044557425960818,"score_gpt":0.5274658566583412,"score_spread":0.39702028239873305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405532782","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000056103276,0.9936112,0.000040982683,0.0025474976,0.0014961621,0.00045786824,0.00015778409,0.00006186432,0.001570506],"genre_scores_gemma":[0.0003347229,0.9938088,0.000054792545,0.00021407648,0.00054318877,0.0040733023,0.000013517343,0.000044989978,0.0009125798],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99671596,0.0006687673,0.00044809622,0.0012041262,0.00038058855,0.0005824663],"domain_scores_gemma":[0.99847996,0.0006179465,0.000121921905,0.0006233418,0.000036207948,0.000120638935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049319596,0.00043504566,0.0011637595,0.0013844052,0.00009135203,0.00023799548,0.000632521,0.00038345152,0.000094104],"category_scores_gemma":[0.000008685164,0.00030597777,0.00021779476,0.001809474,0.0001748964,0.00029046537,0.0004920052,0.00095348776,0.00010105841],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011947331,0.00015620893,0.00009863555,0.00055668957,0.000100978825,0.00014076053,0.00017087162,0.000005306909,8.926727e-8,0.0029270786,0.012943022,0.9828884],"study_design_scores_gemma":[0.00041711263,0.0005735662,0.0004895406,0.0033418597,0.00015774125,0.00009183178,0.0000070311958,0.00015331781,0.0000015312446,0.00038453317,0.99410254,0.00027940856],"about_ca_topic_score_codex":0.002615325,"about_ca_topic_score_gemma":0.0047933212,"teacher_disagreement_score":0.982609,"about_ca_system_score_codex":0.005359221,"about_ca_system_score_gemma":0.0014140961,"threshold_uncertainty_score":0.9999392},"labels":[],"label_agreement":null},{"id":"W4405623091","doi":"10.1200/cci.24.00107","title":"Automated Identification of Breast Cancer Relapse in Computed Tomography Reports Using Natural Language Processing","year":2024,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Faculty of Medicine, University of British Columbia","keywords":"Breast cancer; Medicine; Confidence interval; Computed tomography; Cancer; Radiology; Internal medicine; Artificial intelligence; Oncology; Computer science","score_opus":0.029643454300587242,"score_gpt":0.38676365956981323,"score_spread":0.357120205269226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405623091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8383387,0.009601181,0.13900909,0.0006319441,0.009588755,0.0007494293,0.000064070686,0.0018618072,0.00015505822],"genre_scores_gemma":[0.989547,0.00011824321,0.009860375,0.00019959165,0.00019180628,0.000036637364,0.000007225939,0.000017303944,0.000021820293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996603,0.0000738229,0.0022427961,0.00030309314,0.0004965752,0.00028068785],"domain_scores_gemma":[0.9981776,0.00014457032,0.0008470873,0.00049251487,0.00025884574,0.00007936849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012226589,0.00018285593,0.0003554332,0.000391115,0.000069555026,0.00026415888,0.00042754877,0.00017293906,0.000009346684],"category_scores_gemma":[0.00006537484,0.00016681614,0.00014906717,0.0021516974,0.00012007052,0.0016997324,0.00017939672,0.0005121497,0.0000033617969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007479523,0.00018015885,0.047011364,0.0030346462,0.0001609749,0.000109681234,0.013064908,0.029941507,0.0014032201,0.00024496418,0.0021753286,0.90259844],"study_design_scores_gemma":[0.00020571801,0.000020478365,0.042472173,0.00084001163,0.000029101288,0.000078655044,0.00013756735,0.95515543,0.00057764887,0.000092902694,0.0001963696,0.00019397236],"about_ca_topic_score_codex":0.0004264178,"about_ca_topic_score_gemma":0.00012990479,"teacher_disagreement_score":0.9252139,"about_ca_system_score_codex":0.0003161499,"about_ca_system_score_gemma":0.00058833667,"threshold_uncertainty_score":0.6802565},"labels":[],"label_agreement":null},{"id":"W4405785065","doi":"10.1109/iros58592.2024.10802477","title":"A Novel Approach for Precise Tissue Tracking in Breast Lumpectomy","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canada Foundation for Innovation","keywords":"Lumpectomy; Computer science; Breast tissue; Breast cancer; Medicine; Mastectomy; Internal medicine; Cancer","score_opus":0.02762631795563309,"score_gpt":0.2910885867010455,"score_spread":0.2634622687454124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405785065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006096208,0.00016008028,0.99290425,0.00055493036,0.00044865636,0.00033003505,0.0000035158594,0.00034089328,0.004648045],"genre_scores_gemma":[0.650353,0.0000031663858,0.34837064,0.00005852908,0.00016138218,0.0001731021,0.0000013099313,0.000012894521,0.0008659612],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991313,0.000009040231,0.00013831913,0.00040147192,0.0001286664,0.00019119942],"domain_scores_gemma":[0.99962854,0.00006521956,0.000014840396,0.00023088061,0.000026918296,0.000033593384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022584561,0.00008449309,0.00008682358,0.00014049714,0.000032035823,0.00024406357,0.0003425611,0.000048266756,0.000011541093],"category_scores_gemma":[0.000006855368,0.000076382086,0.000035055822,0.00051837857,0.000012227255,0.0005663738,0.000073441806,0.000096930075,0.000012245051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013835904,0.0001190116,0.00006583391,0.00021302394,0.000017051014,0.000005884118,0.0013858604,0.0012705133,0.03012157,0.038007572,0.0019023822,0.92687744],"study_design_scores_gemma":[0.00028507315,0.00004131273,0.0010524521,0.0000442763,0.0000033365122,0.00015342125,0.000028040333,0.97995657,0.009355574,0.0013803339,0.0075358497,0.00016377456],"about_ca_topic_score_codex":0.000091545095,"about_ca_topic_score_gemma":0.000030352005,"teacher_disagreement_score":0.97868603,"about_ca_system_score_codex":0.00012270229,"about_ca_system_score_gemma":0.00006511595,"threshold_uncertainty_score":0.31147712},"labels":[],"label_agreement":null},{"id":"W4405907103","doi":"10.1109/access.2024.3524428","title":"A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute of Dental and Craniofacial Research; National Institutes of Health; Vlaamse regering; KU Leuven; Fonds Wetenschappelijk Onderzoek","keywords":"Autoencoder; Face (sociological concept); Phenotype; Space (punctuation); Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision; Genetics; Biology; Artificial neural network; Gene","score_opus":0.09323882946100862,"score_gpt":0.38201044232670794,"score_spread":0.2887716128656993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405907103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20397873,0.0016207915,0.79060304,0.00019504846,0.0030929174,0.00019186626,0.000003020293,0.00023687733,0.00007772363],"genre_scores_gemma":[0.8949923,0.00003087115,0.10457146,0.00011991324,0.00019122194,0.000010471831,4.3315745e-7,0.000026506372,0.000056853944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978384,0.0001455614,0.00053535413,0.00065511453,0.00050338375,0.0003222212],"domain_scores_gemma":[0.9984757,0.0004030813,0.00017857083,0.0007203474,0.0001233515,0.00009898644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054984156,0.00018764092,0.00032879255,0.00062613783,0.00008105211,0.00041713365,0.0012366497,0.00013964062,0.000032695865],"category_scores_gemma":[0.00012751271,0.00017995574,0.0001586102,0.00333485,0.000101827,0.0006565556,0.00019320872,0.00026413257,0.000032179818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009236928,0.0004580435,0.011985547,0.0012850651,0.00041267084,0.0005252177,0.0006888487,0.3720562,0.0062791123,0.00049790356,0.0032231167,0.6024959],"study_design_scores_gemma":[0.00031030647,0.00018287101,0.004473255,0.00014821072,0.000050058545,0.000028708886,0.0000036285744,0.98682445,0.0057379785,0.0005230128,0.0014832632,0.0002342471],"about_ca_topic_score_codex":0.00019983639,"about_ca_topic_score_gemma":0.000009672365,"teacher_disagreement_score":0.6910135,"about_ca_system_score_codex":0.00016637423,"about_ca_system_score_gemma":0.0004765615,"threshold_uncertainty_score":0.7338382},"labels":[],"label_agreement":null},{"id":"W4405923428","doi":"10.1038/s41598-024-81724-0","title":"Attention-guided convolutional network for bias-mitigated and interpretable oral lesion classification","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Interpretability; Artificial intelligence; Computer science; Ground truth; Deep learning; Segmentation; Robustness (evolution); Pattern recognition (psychology); Lesion; Categorization; Convolutional neural network; Machine learning; Medicine; Pathology","score_opus":0.07339478128583878,"score_gpt":0.3112205826537794,"score_spread":0.23782580136794063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405923428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083917595,0.0008394257,0.88462526,0.0010836574,0.027895667,0.00056919927,0.0000040660057,0.0005296078,0.0005354963],"genre_scores_gemma":[0.97298133,0.000008610115,0.02250924,0.00004501277,0.0001988258,0.00010912981,0.00006534366,0.000013781276,0.0040687174],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781454,0.00005333603,0.00046219546,0.0009963672,0.00038145797,0.0002920994],"domain_scores_gemma":[0.9988247,0.00009747152,0.00016711377,0.0005682362,0.000250602,0.00009186885],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021355473,0.00012395461,0.00012829425,0.00017530264,0.00047357247,0.0012469415,0.00018540557,0.00007755864,0.000019613999],"category_scores_gemma":[0.000110361194,0.00011580028,0.000084264735,0.0008679859,0.00018030181,0.0008695968,0.000123446,0.00009909357,0.000019615909],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021381687,0.00007176377,0.008365809,0.00030559747,0.000104308274,0.000113647424,0.00054417213,0.0017641828,0.09106655,0.068850815,0.72692716,0.101864584],"study_design_scores_gemma":[0.00011555244,0.000048216298,0.0052442793,0.00020730383,0.000022777487,0.00043906542,0.000019275065,0.7452238,0.0026837655,0.098972835,0.1467919,0.00023122366],"about_ca_topic_score_codex":0.000020053723,"about_ca_topic_score_gemma":0.000016802012,"teacher_disagreement_score":0.8890637,"about_ca_system_score_codex":0.00015652577,"about_ca_system_score_gemma":0.00025133122,"threshold_uncertainty_score":0.99978983},"labels":[],"label_agreement":null},{"id":"W4406019053","doi":"10.5858/arpa.2024-0378-oa","title":"The Effect of Window Size on Pathologists’ Search for Rare Elements in a Digital Pathology Setting","year":2025,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Context (archaeology); Window (computing); Digital pathology; Computer science; Pixel; Lymph node; Medicine; Magnification; Pathology; Computer vision; Artificial intelligence","score_opus":0.006996786672000468,"score_gpt":0.28784529065803766,"score_spread":0.28084850398603717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406019053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95928,0.00086676166,0.034444746,0.0024783555,0.00076047296,0.00091874367,0.0000626573,0.000057157373,0.0011310714],"genre_scores_gemma":[0.99689627,0.00007692157,0.0024317226,0.00032434295,0.00006052579,0.00014413914,0.000006410677,0.000011455354,0.000048227463],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99759936,0.00063216523,0.00063999795,0.000502397,0.00021944454,0.00040661206],"domain_scores_gemma":[0.9912039,0.007652514,0.0002767426,0.000718455,0.00010442511,0.000043983095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018580896,0.00020176191,0.0004967865,0.00030749955,0.00013149758,0.000010563951,0.0008641487,0.00010282546,0.000001565966],"category_scores_gemma":[0.0023986963,0.00013677588,0.000071835835,0.0006220097,0.0011177608,0.000115939736,0.0002876456,0.00033224793,0.0000010175386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018835478,0.00017898995,0.30653742,0.0006828293,0.000115070114,0.0006239468,0.00601326,0.00022164568,0.19741827,0.0150973955,0.0005449337,0.47068268],"study_design_scores_gemma":[0.021288492,0.029038643,0.5291837,0.0025748305,0.00012891315,0.00015148074,0.0018330015,0.004894549,0.37849158,0.02839852,0.0032299252,0.00078637846],"about_ca_topic_score_codex":0.000003834925,"about_ca_topic_score_gemma":0.00001134746,"teacher_disagreement_score":0.46989632,"about_ca_system_score_codex":0.00004581851,"about_ca_system_score_gemma":0.00017312556,"threshold_uncertainty_score":0.5577559},"labels":[],"label_agreement":null},{"id":"W4406116768","doi":"10.1038/s41598-024-80495-y","title":"Out-of-distribution generalization for segmentation of lymph node metastasis in breast cancer","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute; St. Michael's Hospital; Toronto Metropolitan University; University of Toronto","funders":"Mitacs; Canada Research Chairs; Canadian Cancer Society","keywords":"Computer science; Segmentation; Generalization; Artificial intelligence; Breast cancer; Cluster analysis; Machine learning; Data mining; Medicine; Cancer; Mathematics","score_opus":0.01848699997656767,"score_gpt":0.300350447591776,"score_spread":0.2818634476152083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406116768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07231327,0.00012277602,0.91593903,0.00037532632,0.010773923,0.00033514528,0.000043144562,0.000031071806,0.00006630368],"genre_scores_gemma":[0.9884991,0.000012969256,0.010954046,0.000023233217,0.000027708556,0.00012081759,0.00009058289,0.0000043731757,0.00026718096],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985566,0.00004037708,0.00053414196,0.0004428756,0.0002863201,0.00013968749],"domain_scores_gemma":[0.9986675,0.000022863293,0.00043164857,0.00046494207,0.00039235316,0.000020719155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009778858,0.00007502743,0.00014649436,0.0002305731,0.00008439366,0.0000686972,0.0001641815,0.00004159183,0.000007873693],"category_scores_gemma":[0.000041011845,0.00007659937,0.00006158846,0.0011433992,0.00007122823,0.00037892873,0.00006127226,0.000023468972,3.222213e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092241615,0.00043512415,0.13436432,0.00096980005,0.00014534754,0.000013728664,0.0019789876,0.081392564,0.49180663,0.009805682,0.02804954,0.25094604],"study_design_scores_gemma":[0.00056130794,0.000017363263,0.032721233,0.00023397183,0.000051590014,0.000015288451,0.0000739719,0.09304825,0.8507166,0.01880072,0.0035566378,0.00020309466],"about_ca_topic_score_codex":0.00021136348,"about_ca_topic_score_gemma":0.000078211444,"teacher_disagreement_score":0.9161858,"about_ca_system_score_codex":0.00027653534,"about_ca_system_score_gemma":0.00031115694,"threshold_uncertainty_score":0.31236315},"labels":[],"label_agreement":null},{"id":"W4406130316","doi":"10.3389/fonc.2024.1420328","title":"Artificial intelligence in breast cancer survival prediction: a comprehensive systematic review and meta-analysis","year":2025,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Meta-analysis; Cancer; Medicine; Oncology; Internal medicine","score_opus":0.10969258954259996,"score_gpt":0.391081729755036,"score_spread":0.28138914021243605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406130316","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.8272225e-9,0.81973344,0.17555593,0.00069892674,0.0016849668,0.0020770489,0.000116479896,0.00004338993,0.00008982067],"genre_scores_gemma":[0.000001207803,0.9909652,0.0057845567,0.0004013333,0.000050264993,0.0026476854,0.000011944385,0.000013705231,0.00012414213],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9941636,0.0021922896,0.0019170911,0.0010643605,0.00029357392,0.00036909946],"domain_scores_gemma":[0.997379,0.0006446382,0.00085508934,0.00088951003,0.0001536614,0.00007810992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001169257,0.00048649163,0.009560597,0.001457377,0.000060059938,0.00005823825,0.0011039209,0.00045398038,0.000043360804],"category_scores_gemma":[0.00008924648,0.00039518878,0.0009959799,0.004801386,0.00013522855,0.00019486452,0.0003990616,0.00071008335,0.000005306824],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046886857,0.00006445439,0.000012887634,0.6880349,0.034409333,0.000046203408,0.000098162185,0.00011485564,3.2834673e-9,0.00043916368,0.0012717512,0.2755036],"study_design_scores_gemma":[0.00007543149,0.00010687759,0.000012449899,0.06073611,0.85935825,0.00014234878,0.00009400864,0.00550494,8.405729e-8,0.0014331902,0.07172924,0.0008070431],"about_ca_topic_score_codex":0.00018861103,"about_ca_topic_score_gemma":0.0005684822,"teacher_disagreement_score":0.82494897,"about_ca_system_score_codex":0.0016148256,"about_ca_system_score_gemma":0.0008603144,"threshold_uncertainty_score":0.99985},"labels":[],"label_agreement":null},{"id":"W4406246512","doi":"10.1016/j.ypat.2013.12.020","title":"10.1016/j.ypat.2013.12.020","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Virtual microscopy; Prostate; Microscopy; Pathology; Medical physics; Internal medicine","score_opus":0.006607233332723009,"score_gpt":0.17219304527796417,"score_spread":0.16558581194524116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406246512","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000707845,0.000039275932,0.0016257162,0.000988747,0.000008431889,0.00014436847,0.0000021194155,0.00039769767,0.9967229],"genre_scores_gemma":[0.00020514497,3.8328264e-7,0.0031318644,0.00010401715,0.00018338927,0.000023535647,0.000001108382,0.0000139004605,0.99633664],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896437,0.000037822563,0.00014732615,0.0003469579,0.00023814949,0.00026535432],"domain_scores_gemma":[0.99918896,0.000033450255,0.000030447123,0.0005801825,0.000035586796,0.00013139412],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001266513,0.00011981636,0.00011458817,0.00007269146,0.00008891657,0.000100797275,0.0006832034,0.000054653818,0.986641],"category_scores_gemma":[0.000010026965,0.00012283481,0.000046940506,0.0003123083,0.000020889496,0.00029843114,0.000108039225,0.00010521202,0.9954069],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010966897,0.000012083951,4.247474e-8,0.0000017268704,0.0000044269314,0.0000026570744,0.000025225823,0.00023014446,0.000035146786,0.0000034085658,0.23392944,0.76574475],"study_design_scores_gemma":[0.00012532498,0.00015947956,0.000018155923,0.000008768729,0.0000032465568,0.000014183426,1.8089156e-7,0.009139779,0.00048370773,0.00004834418,0.9898385,0.00016035912],"about_ca_topic_score_codex":0.000060675546,"about_ca_topic_score_gemma":9.5314306e-7,"teacher_disagreement_score":0.76558435,"about_ca_system_score_codex":0.00008558346,"about_ca_system_score_gemma":0.00004632997,"threshold_uncertainty_score":0.5009058},"labels":[],"label_agreement":null},{"id":"W4406437837","doi":"10.1038/s41467-024-55780-z","title":"PHARAOH: A collaborative crowdsourcing platform for phenotyping and regional analysis of histology","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Université de Sherbrooke; Centre hospitalier de l'Université Laval; University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"Government of Canada; Princess Margaret Cancer Foundation; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Crowdsourcing; Computer science; Data science; Computational biology; Biology; World Wide Web","score_opus":0.026089373026270582,"score_gpt":0.33718812207634313,"score_spread":0.31109874905007256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406437837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003959097,0.019066274,0.96112466,0.012357437,0.00023120793,0.00036267005,0.00002496947,0.00008528514,0.002788392],"genre_scores_gemma":[0.90304023,0.0002523788,0.09603915,0.0005091629,0.0000075759103,0.000069975766,0.000016044925,0.000002726839,0.000062739135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943477,0.000047292997,0.00018440561,0.00017658707,0.000068515015,0.000088425644],"domain_scores_gemma":[0.9977119,0.00078132434,0.00014636775,0.0009966117,0.00034530513,0.000018487799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002051797,0.00006554333,0.00018180096,0.00042236794,0.00028354046,0.000026001342,0.0008932977,0.00013338446,9.656171e-7],"category_scores_gemma":[0.00012968552,0.000068917616,0.00005877893,0.0020728495,0.00012791037,0.00017634696,0.0003024335,0.00025467976,1.5369925e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031107316,0.000055676213,0.0013787501,0.000026896774,0.00081952615,1.0200683e-7,0.0020489027,0.0003546018,0.0012961198,0.9479443,0.0030962704,0.04294778],"study_design_scores_gemma":[0.000762003,0.00004908072,0.015682712,0.00007069448,0.00070974574,0.0000034719571,0.00039884626,0.7895897,0.0012766503,0.018227777,0.17299871,0.00023062227],"about_ca_topic_score_codex":0.000019892766,"about_ca_topic_score_gemma":0.00067935284,"teacher_disagreement_score":0.92971647,"about_ca_system_score_codex":0.0001101175,"about_ca_system_score_gemma":0.00012952153,"threshold_uncertainty_score":0.2810379},"labels":[],"label_agreement":null},{"id":"W4406447456","doi":"10.1016/s1040-1741(13)00157-7","title":"10.1016/s1040-1741(13)00157-7","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Mammography; Medical physics; Internal medicine; Breast cancer; Cancer","score_opus":0.005570625415000565,"score_gpt":0.17154190904677513,"score_spread":0.16597128363177457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406447456","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001249471,0.000046342484,0.0014426734,0.0006684674,0.000009515606,0.00014922868,0.0000024527437,0.00044036083,0.997116],"genre_scores_gemma":[0.00024535324,2.6182653e-7,0.0026844493,0.0001055785,0.00019712551,0.000025651376,0.000001252736,0.000015521213,0.9967248],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998848,0.000041508774,0.00016258912,0.00038127045,0.00026847314,0.00029816088],"domain_scores_gemma":[0.99909747,0.000039118146,0.000032599288,0.0006432294,0.000046970326,0.00014063172],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000162065,0.0001324906,0.00012676125,0.00008697474,0.00010341704,0.000116634204,0.0007564607,0.000060379967,0.9806589],"category_scores_gemma":[0.000014168335,0.00013686348,0.000051529125,0.00047512783,0.000024261102,0.0003457261,0.0001208784,0.00011827657,0.99405],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000117314885,0.00001456399,4.0571702e-8,0.0000019400584,0.000005102355,0.0000033698557,0.000025855594,0.0002963434,0.00003923004,0.0000031209706,0.19850986,0.80108887],"study_design_scores_gemma":[0.00013954958,0.00015961543,0.00003563358,0.000010145317,0.0000037568834,0.000018192028,2.3849398e-7,0.008325654,0.0005294991,0.00007238284,0.99052763,0.0001776782],"about_ca_topic_score_codex":0.000046220164,"about_ca_topic_score_gemma":7.3155184e-7,"teacher_disagreement_score":0.8009112,"about_ca_system_score_codex":0.000104634644,"about_ca_system_score_gemma":0.000045147524,"threshold_uncertainty_score":0.5581131},"labels":[],"label_agreement":null},{"id":"W4406472074","doi":"10.1007/978-3-031-77786-8_14","title":"Structured Model Pruning for Efficient Inference in Computational Pathology","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Pruning; Inference; Artificial intelligence; Natural language processing","score_opus":0.019139342656572925,"score_gpt":0.27559528598759614,"score_spread":0.25645594333102323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406472074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019193953,0.0001920325,0.9953537,0.00065426703,0.0018947932,0.00084093376,0.000018752164,0.00014989682,0.00070366677],"genre_scores_gemma":[0.32930544,0.000008211043,0.6695021,0.0008457757,0.00012568475,0.00004769728,0.0000091345455,0.000021267373,0.00013472655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959561,0.000041812254,0.0006921733,0.0018442451,0.00075754354,0.0007081253],"domain_scores_gemma":[0.9968965,0.0013124918,0.0003315679,0.00096656056,0.0003917356,0.00010116101],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008757457,0.0005192052,0.0005885023,0.0015488948,0.00024818096,0.00030227084,0.0026284517,0.0004393969,0.000004115717],"category_scores_gemma":[0.00026917204,0.0005341019,0.00012368939,0.0008716239,0.0004985501,0.00031771982,0.001176944,0.00086978666,0.0000037494372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008454281,0.000011699473,0.000018742228,0.000039278355,0.0000035665275,0.000013192945,0.00041499216,0.75487703,0.000045297216,0.042157482,0.0000057113684,0.20240454],"study_design_scores_gemma":[0.00032360083,0.000076043885,0.00007392971,0.00023947349,0.0000037013094,0.000013491835,1.0676649e-7,0.6868749,0.0002277251,0.31177163,0.000056762354,0.0003385774],"about_ca_topic_score_codex":0.0000120823515,"about_ca_topic_score_gemma":0.00014217578,"teacher_disagreement_score":0.3291135,"about_ca_system_score_codex":0.00088332035,"about_ca_system_score_gemma":0.0017160103,"threshold_uncertainty_score":0.99971104},"labels":[],"label_agreement":null},{"id":"W4406479500","doi":"10.1016/s0029-7437(11)70092-1","title":"10.1016/s0029-7437(11)70092-1","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mammography; Medical physics; Medicine; Internal medicine; Breast cancer; Cancer","score_opus":0.006994802473245633,"score_gpt":0.18321819261183933,"score_spread":0.1762233901385937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406479500","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009223591,0.000039649258,0.0023837565,0.00073192985,0.0000020478747,0.00015543726,0.0000025048696,0.0005228788,0.99606955],"genre_scores_gemma":[0.0002016426,2.2724753e-7,0.003845953,0.00009617069,0.00019976679,0.000026336675,0.000001169642,0.000015797388,0.9956129],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883187,0.000043525015,0.00016546538,0.0003897659,0.00026909148,0.00030026573],"domain_scores_gemma":[0.9990737,0.000044499942,0.000033398992,0.00066366175,0.000046229154,0.00013852846],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016719551,0.00013510189,0.00012940484,0.00008726403,0.000107273394,0.000121697405,0.0007854491,0.000062096886,0.98694247],"category_scores_gemma":[0.000015325395,0.00014001052,0.00005388255,0.00046656214,0.000024708661,0.00034964463,0.00012361632,0.00010467093,0.9945145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073587466,0.000017708422,5.575838e-8,0.0000018379529,0.000003722914,0.0000022025738,0.000020077667,0.00015178836,0.00002830637,0.0000046575083,0.5005579,0.49920437],"study_design_scores_gemma":[0.00013138822,0.00017400445,0.000025927764,0.000010685346,0.0000038158028,0.0000182479,2.2648334e-7,0.008841685,0.00050855806,0.000070276794,0.9900343,0.00018089238],"about_ca_topic_score_codex":0.00004124023,"about_ca_topic_score_gemma":6.3018825e-7,"teacher_disagreement_score":0.49902347,"about_ca_system_score_codex":0.00010422767,"about_ca_system_score_gemma":0.000042594093,"threshold_uncertainty_score":0.57094634},"labels":[],"label_agreement":null},{"id":"W4406482306","doi":"10.1007/978-3-031-77610-6_3","title":"Segmentation Style Discovery: Application to Skin Lesion Images","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Style (visual arts); Segmentation; Artificial intelligence; Computer vision; Skin lesion; Pattern recognition (psychology); Visual arts; Dermatology; Medicine; Art","score_opus":0.009770671149005724,"score_gpt":0.2633745012469739,"score_spread":0.2536038300979682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406482306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004350315,0.00015764883,0.9931667,0.0014434711,0.0017266609,0.0008636367,0.000009537737,0.00020655975,0.0023823245],"genre_scores_gemma":[0.16466221,0.00008231501,0.8283434,0.0032189281,0.0007696154,0.00013209155,0.000020710337,0.000047543577,0.0027231835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635434,0.000035940942,0.00045725194,0.0017448505,0.0009482822,0.00045935102],"domain_scores_gemma":[0.9977224,0.00026106337,0.00026004217,0.001417442,0.00021967315,0.00011938437],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000608951,0.0004333989,0.00035938562,0.0010421171,0.00028327477,0.00081124075,0.0024241034,0.00023628202,0.0000062920044],"category_scores_gemma":[0.000049017264,0.00043071122,0.000097833756,0.0010982977,0.00021605896,0.0012723624,0.0013449088,0.0004760416,0.00006195828],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000726904,0.000014739121,0.000016514834,0.000035489185,0.0000052785726,0.000004843062,0.00032581404,0.02451578,0.002152862,0.005420995,0.00016810084,0.9673323],"study_design_scores_gemma":[0.00065645296,0.000563318,0.00083969574,0.001068673,0.000029495732,0.00004134451,0.000001193054,0.6792039,0.1382539,0.16760044,0.009873798,0.0018677613],"about_ca_topic_score_codex":0.00008024212,"about_ca_topic_score_gemma":0.00012720136,"teacher_disagreement_score":0.96546453,"about_ca_system_score_codex":0.0010136493,"about_ca_system_score_gemma":0.00047355404,"threshold_uncertainty_score":0.99981445},"labels":[],"label_agreement":null},{"id":"W4406572248","doi":"10.1016/j.ccol.2024.02.004","title":"10.1016/j.ccol.2024.02.004","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Modalities; Medical physics; Medicine; Breast cancer; Cancer; Breast cancer screening; Mammography; Internal medicine; Sociology","score_opus":0.005409504634466421,"score_gpt":0.17419597018781913,"score_spread":0.1687864655533527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406572248","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000796851,0.00004129095,0.0011566671,0.0006396032,0.000014736605,0.00016428962,0.0000021329467,0.00039447082,0.9975071],"genre_scores_gemma":[0.00017867432,2.0864069e-7,0.0025216662,0.000105369276,0.0001886492,0.00003254174,7.6408804e-7,0.000014611117,0.99695754],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989474,0.00003460768,0.00014645848,0.00035430194,0.00025130884,0.00026595307],"domain_scores_gemma":[0.99919975,0.000036300495,0.00002760237,0.0005727991,0.000041327807,0.0001222378],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001444904,0.00011912035,0.000114728704,0.00008192305,0.00008935807,0.00011494804,0.00067162584,0.000056632376,0.9862522],"category_scores_gemma":[0.00001232005,0.00012378138,0.000049195736,0.00050911354,0.000020178757,0.00031000597,0.00011524655,0.00011703322,0.9936911],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009981343,0.000012610839,4.7110614e-8,0.000002114574,0.0000050278672,0.000003138474,0.000022583881,0.00028109027,0.00003539041,0.000003854014,0.23532319,0.76430094],"study_design_scores_gemma":[0.00011854111,0.00016063424,0.000022625441,0.000010699682,0.0000036674676,0.0000146696375,2.4557488e-7,0.0065581915,0.00071970915,0.000072246585,0.99215865,0.00016012219],"about_ca_topic_score_codex":0.00003136737,"about_ca_topic_score_gemma":3.6048655e-7,"teacher_disagreement_score":0.76414084,"about_ca_system_score_codex":0.00011425203,"about_ca_system_score_gemma":0.000051271683,"threshold_uncertainty_score":0.5047658},"labels":[],"label_agreement":null},{"id":"W4406584143","doi":"10.1016/j.ypat.2015.06.005","title":"10.1016/j.ypat.2015.06.005","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Resection; Digital pathology; Workstation; Cancer; Radiology; Pathology; Surgery; Internal medicine; Computer science; Operating system","score_opus":0.00583176206895726,"score_gpt":0.18425233018716508,"score_spread":0.17842056811820783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406584143","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006676112,0.00005669075,0.0018745685,0.00097546336,0.000007601264,0.0001437208,0.0000024387166,0.00041128707,0.99646145],"genre_scores_gemma":[0.00023647753,2.6159205e-7,0.0031450973,0.00010249184,0.00019229065,0.00002271385,0.0000013857268,0.000014051378,0.99628526],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894565,0.00003893899,0.0001492268,0.00034601323,0.00024769033,0.00027247303],"domain_scores_gemma":[0.99915963,0.000034474073,0.00003078409,0.00060694804,0.000036609563,0.00013156603],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014767166,0.00012032564,0.00011522281,0.00007776734,0.00008927667,0.00010269977,0.00068986625,0.000055842338,0.97523147],"category_scores_gemma":[0.0000122504825,0.00012353073,0.00004661788,0.00039878662,0.000021273408,0.00034028292,0.000111419766,0.000106360465,0.99504197],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007696046,0.000012698536,5.0944923e-8,0.0000015671816,0.000004592124,0.000002456181,0.00002236826,0.0002003871,0.000034766177,0.000003597476,0.27278557,0.72692424],"study_design_scores_gemma":[0.00012467729,0.0001277278,0.00002871639,0.000009123582,0.000003476311,0.000015202851,1.8873061e-7,0.009027488,0.00047939373,0.000060043043,0.9899624,0.00016158614],"about_ca_topic_score_codex":0.000026065089,"about_ca_topic_score_gemma":2.738452e-7,"teacher_disagreement_score":0.72676265,"about_ca_system_score_codex":0.00009942918,"about_ca_system_score_gemma":0.000043374086,"threshold_uncertainty_score":0.50374365},"labels":[],"label_agreement":null},{"id":"W4406734294","doi":"10.1016/b978-1-4160-5909-7.00040-0","title":"10.1016/b978-1-4160-5909-7.00040-0","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lymph node; Sampling (signal processing); Medicine; Computer science; Internal medicine; Computer vision","score_opus":0.009233890910518521,"score_gpt":0.17540101248703344,"score_spread":0.16616712157651492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406734294","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.10933e-8,0.00025545948,0.00075286214,0.0003143409,0.000030525713,0.00038221,0.00002599306,0.0006839467,0.9975546],"genre_scores_gemma":[7.5966915e-7,0.000001504091,0.0016704513,0.00011859217,0.0006455074,0.000033896224,0.000013322425,0.0000957507,0.9974202],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975421,0.00002711815,0.00041102504,0.0009569912,0.0006168278,0.00044595645],"domain_scores_gemma":[0.99789715,0.000075341806,0.00018384053,0.0014722256,0.000115792136,0.00025563524],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001907282,0.0005003905,0.0004513235,0.0003563911,0.0001421018,0.00019979381,0.0016002684,0.0004082431,0.98719066],"category_scores_gemma":[0.000011671344,0.000552115,0.00021509033,0.00013879129,0.000068926856,0.0003003305,0.00042157294,0.000517144,0.9964419],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018186733,0.000007255722,8.967421e-10,0.000008984685,0.000031895826,0.000017242975,0.000013076932,0.000059064376,0.0000031410011,0.00028575075,0.2844045,0.71515095],"study_design_scores_gemma":[0.00014635103,0.00026058874,4.2134445e-7,0.00011637983,0.00002797765,0.000047214326,5.9744806e-8,0.00072302326,0.00005377104,0.0020495276,0.99595475,0.00061992597],"about_ca_topic_score_codex":0.000021155542,"about_ca_topic_score_gemma":6.696532e-7,"teacher_disagreement_score":0.714531,"about_ca_system_score_codex":0.00034679836,"about_ca_system_score_gemma":0.00017176341,"threshold_uncertainty_score":0.99969304},"labels":[],"label_agreement":null},{"id":"W4406757901","doi":"10.1016/j.cmpbup.2025.100181","title":"ECgMLP: A novel gated MLP model for enhanced endometrial cancer diagnosis","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine Update","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Endometrial cancer; Cancer; Computer science; Medicine; Internal medicine","score_opus":0.07496147026046904,"score_gpt":0.40577578483124216,"score_spread":0.33081431457077315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406757901","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025776695,0.0016653598,0.98808444,0.0032540539,0.0029953627,0.0011658332,0.000013102699,0.00020916859,0.000035041536],"genre_scores_gemma":[0.03607052,0.00080721045,0.9598707,0.0013233697,0.00035476152,0.001477467,0.000015243346,0.00001707009,0.00006368571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771535,0.00016037695,0.0005729387,0.00085881253,0.00019731485,0.00049517513],"domain_scores_gemma":[0.9984636,0.0005714857,0.00017053596,0.00050282234,0.0001697577,0.00012181978],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017608904,0.00028599784,0.0005398347,0.00073417893,0.00012702143,0.00016404482,0.00068672985,0.00016091425,0.000004175],"category_scores_gemma":[0.000087211585,0.00024557707,0.0000945436,0.002339064,0.00016090492,0.00026532845,0.00043484615,0.00022304342,6.0531494e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007638857,0.00011615241,0.00026438394,0.00010247144,0.0000636037,0.0000011373673,0.00036174507,0.00028074533,0.0017679185,0.0021799665,0.00070205913,0.9940834],"study_design_scores_gemma":[0.0041702795,0.00034919087,0.00020863597,0.0002954253,0.00003897398,0.0000030952194,0.000008150107,0.9388931,0.0088395,0.008610872,0.038309027,0.0002737546],"about_ca_topic_score_codex":0.00010735932,"about_ca_topic_score_gemma":0.000033594282,"teacher_disagreement_score":0.9938097,"about_ca_system_score_codex":0.00013466417,"about_ca_system_score_gemma":0.00013281056,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4406786807","doi":"10.18280/isi.300112","title":"Region of Interest-Based Breast Cancer Detection with Oversampling Technique","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Oversampling; Breast cancer; Oncology; Medicine; Computer science; Cancer; Internal medicine; Telecommunications; Bandwidth (computing)","score_opus":0.019025007821846525,"score_gpt":0.24574175838925963,"score_spread":0.2267167505674131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406786807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01808428,0.00006076953,0.979865,0.00013433267,0.00032584986,0.0003863561,0.0000054081534,0.00026553383,0.0008724599],"genre_scores_gemma":[0.989977,0.000013855883,0.00950568,0.0002405393,0.000020739439,0.00021860706,0.0000032734588,0.0000058663622,0.000014428367],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990793,0.00004126089,0.0003977747,0.00015154228,0.00015500745,0.00017511524],"domain_scores_gemma":[0.99879754,0.000049225182,0.0003700607,0.0003582369,0.00039351638,0.000031400294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021639054,0.0001396027,0.00015664834,0.0004886039,0.00015320159,0.00013081914,0.0003131824,0.00010614361,0.0000050313624],"category_scores_gemma":[0.000033973898,0.00012817717,0.000047306934,0.0010520774,0.00009651789,0.0026367279,0.000068005145,0.00013908953,0.0000025734337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043439996,0.000045106935,0.002971185,0.0014912715,0.00009448346,0.0000027939718,0.0017303556,0.014534061,0.008600924,0.007935009,0.00045697243,0.9617034],"study_design_scores_gemma":[0.001783196,0.00055781583,0.022462342,0.004118899,0.000066585686,0.00026875062,0.00047395728,0.27398425,0.68191,0.008948194,0.0046898415,0.0007361973],"about_ca_topic_score_codex":0.0003758265,"about_ca_topic_score_gemma":0.0000998021,"teacher_disagreement_score":0.9718927,"about_ca_system_score_codex":0.00066621974,"about_ca_system_score_gemma":0.00022194712,"threshold_uncertainty_score":0.52269137},"labels":[],"label_agreement":null},{"id":"W4406802277","doi":"10.18280/isi.300116","title":"Attention-Guided Hybrid Network for Cervical Cancer Classification","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Prince Sattam bin Abdulaziz University","keywords":"Cervical cancer; Cancer; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.024815504891016776,"score_gpt":0.2787422502708496,"score_spread":0.25392674537983284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406802277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009252549,0.00014395836,0.98115337,0.0009182627,0.0022126418,0.0006416289,0.000014920634,0.00037630193,0.0052863965],"genre_scores_gemma":[0.96626407,0.00005518199,0.031065539,0.0010213429,0.00025841856,0.0009370211,0.0000773597,0.000009168951,0.00031192132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985897,0.000047873036,0.0006069922,0.00021370957,0.00021833561,0.00032337397],"domain_scores_gemma":[0.99864435,0.00009949535,0.00030574607,0.0004141164,0.0004843619,0.000051956187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004617514,0.00015320368,0.00017003465,0.00021048363,0.0004531476,0.0004048315,0.0004856585,0.00009458473,0.000012279411],"category_scores_gemma":[0.00011227499,0.00015969071,0.00009690402,0.000742325,0.00006232566,0.0031827388,0.000101577934,0.00010634375,0.00003781857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000577137,0.000027246511,0.005622914,0.0006636123,0.00010174518,3.6118684e-7,0.00074397994,0.0104349265,0.00034814363,0.20022908,0.06197242,0.71979785],"study_design_scores_gemma":[0.00087876327,0.00007771675,0.061113257,0.00034699877,0.000038414415,0.000013632155,0.00011854534,0.78855,0.0018947938,0.071434624,0.075161576,0.0003716806],"about_ca_topic_score_codex":0.00010236301,"about_ca_topic_score_gemma":0.00002905607,"teacher_disagreement_score":0.9570115,"about_ca_system_score_codex":0.00073587504,"about_ca_system_score_gemma":0.00022468141,"threshold_uncertainty_score":0.6511998},"labels":[],"label_agreement":null},{"id":"W4406891930","doi":"10.1109/jbhi.2025.3535541","title":"Coarse for Fine: Bounding Box Supervised Thyroid Ultrasound Image Segmentation Using Spatial Arrangement and Hierarchical Prediction Consistency","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Minimum bounding box; Segmentation; Artificial intelligence; Computer science; Image segmentation; Pattern recognition (psychology); Consistency (knowledge bases); Computer vision; Bounding overwatch; Image (mathematics)","score_opus":0.030050702865322403,"score_gpt":0.3235242563556821,"score_spread":0.2934735534903597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406891930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085284114,0.00023493447,0.9095036,0.0031781592,0.0014669829,0.0002765498,0.000016653867,0.000015616457,0.000023412455],"genre_scores_gemma":[0.3245046,0.0013449205,0.67078304,0.0026469473,0.00067249313,0.0000141418695,0.0000117842255,0.000009199752,0.00001285221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982649,0.000043728873,0.0010418644,0.00008266114,0.0003541494,0.00021267125],"domain_scores_gemma":[0.9989126,0.00017736705,0.00047483915,0.00008835888,0.00014342337,0.00020344023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012930259,0.00010082148,0.00023495742,0.00026780617,0.00033637992,0.00015088353,0.0001305995,0.0000716793,0.0000022491624],"category_scores_gemma":[0.0000730506,0.00008346271,0.00004282873,0.00020032655,0.00016006648,0.0006179671,0.000037024955,0.00021088414,2.1937991e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035027644,0.00027611086,0.0018646423,0.004275589,0.000217295,0.000007012492,0.017141845,0.000119545235,0.015768034,0.0020140123,0.013098738,0.9448669],"study_design_scores_gemma":[0.007768685,0.0037813112,0.0036303909,0.0012118104,0.00011334798,0.000678035,0.0019748583,0.9620226,0.0024197432,0.0063171517,0.009773578,0.00030849557],"about_ca_topic_score_codex":0.000027205248,"about_ca_topic_score_gemma":0.000009597069,"teacher_disagreement_score":0.96190304,"about_ca_system_score_codex":0.00017177952,"about_ca_system_score_gemma":0.0004939112,"threshold_uncertainty_score":0.34035107},"labels":[],"label_agreement":null},{"id":"W4407159013","doi":"10.1016/j.compbiomed.2025.109725","title":"Sam2Rad: A segmentation model for medical images with learnable prompts","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Alberta","funders":"Alberta Innovates; Arthritis Society","keywords":"Segmentation; Artificial intelligence; Computer science; Computer vision; Image segmentation; Pattern recognition (psychology); Computer graphics (images)","score_opus":0.014159680038758685,"score_gpt":0.3354138102833464,"score_spread":0.3212541302445877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407159013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005370739,0.00046834484,0.9830409,0.010047243,0.00047143688,0.0002679883,5.1046726e-7,0.000052318082,0.00028049035],"genre_scores_gemma":[0.67799455,0.0003843569,0.31536624,0.005336249,0.00018210533,0.00017608156,0.000013303577,0.000007533303,0.0005395682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992788,0.00003948736,0.00015521317,0.00029657356,0.00007216782,0.00015775108],"domain_scores_gemma":[0.99955493,0.00018351105,0.00004207501,0.00013830078,0.0000374433,0.00004371043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037633284,0.00008407786,0.0001668314,0.00014983753,0.000071311035,0.0000073208375,0.000223885,0.000084477644,0.0000020643117],"category_scores_gemma":[0.000047194586,0.000059501148,0.000009253308,0.00020167025,0.00020340348,0.000091774746,0.00008700676,0.00011431412,2.7592225e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030283476,0.00010400703,0.011508766,0.00027221395,0.000095631585,0.000016935664,0.002197612,0.002813624,0.0028307203,0.13043581,0.013741461,0.83568037],"study_design_scores_gemma":[0.0021041855,0.0004594425,0.0012638223,0.00022298841,0.000007673962,0.000019319888,0.000030020998,0.9676427,0.00040715616,0.027029978,0.0007326832,0.000079989826],"about_ca_topic_score_codex":0.000025231722,"about_ca_topic_score_gemma":0.000028343677,"teacher_disagreement_score":0.9648291,"about_ca_system_score_codex":0.000045043555,"about_ca_system_score_gemma":0.0001000672,"threshold_uncertainty_score":0.24263863},"labels":[],"label_agreement":null},{"id":"W4407162180","doi":"10.1200/cci-24-00180","title":"Advancements in Interoperability: Achieving Anatomic Pathology Reports That Adhere to International Standards and Are Both Human-Readable and Readily Computable","year":2025,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre","funders":"","keywords":"SNOMED CT; Interoperability; Systematized Nomenclature of Medicine; Health care; Medicine; Biobank; Semantic interoperability; Computer science; Health informatics; Pathology; Terminology; Medical physics; Public health; Bioinformatics; World Wide Web; Political science","score_opus":0.03992014322044101,"score_gpt":0.4160129922427628,"score_spread":0.37609284902232176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407162180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8759597,0.00047960266,0.116512656,0.0012788264,0.0023665389,0.00048858795,0.000029605604,0.000098772674,0.0027857176],"genre_scores_gemma":[0.98174214,0.00057451305,0.014171935,0.0031950534,0.00005849747,0.00006712132,0.0000038067726,0.000009180936,0.0001777472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99775296,0.00008321439,0.0011590787,0.00038159225,0.00034715197,0.0002759708],"domain_scores_gemma":[0.9986504,0.00017984143,0.00040008538,0.00048548006,0.0001721029,0.000112120964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017142247,0.0001746706,0.0004198985,0.00020646672,0.00011813275,0.00021907622,0.00038802242,0.00013117518,0.000017501785],"category_scores_gemma":[0.00020523694,0.00016590214,0.000041154395,0.00027449412,0.00011894405,0.00093545945,0.00086857594,0.00038767984,0.0000016871619],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009226586,0.0000777703,0.7412825,0.00022589492,0.000051371546,0.000032622123,0.0015411439,0.0010238196,0.000017591346,0.000600625,0.0032289024,0.25182548],"study_design_scores_gemma":[0.005419365,0.0012404254,0.60937774,0.0030878189,0.00007554819,0.00016218699,0.0029808609,0.12658459,0.0006417521,0.010807943,0.2382732,0.0013485728],"about_ca_topic_score_codex":0.00014748905,"about_ca_topic_score_gemma":0.0007441089,"teacher_disagreement_score":0.25047693,"about_ca_system_score_codex":0.0005264944,"about_ca_system_score_gemma":0.00021962005,"threshold_uncertainty_score":0.6765293},"labels":[],"label_agreement":null},{"id":"W4407269389","doi":"10.1016/j.media.2025.103491","title":"HistoKernel: Whole slide image level Maximum Mean Discrepancy kernels for pan-cancer predictive modelling","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"EPSRC Centre for Doctoral Training in Medical Imaging; Engineering and Physical Sciences Research Council; Sierra Oncology","keywords":"Artificial intelligence; Mathematics; Computer science; Pattern recognition (psychology); Computer vision","score_opus":0.02527294268600958,"score_gpt":0.311818302738887,"score_spread":0.2865453600528774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407269389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014889919,0.00073945033,0.98925394,0.005731067,0.00056221586,0.0003392027,0.000092311115,0.00030675434,0.0014860784],"genre_scores_gemma":[0.60674495,0.00054125086,0.37471643,0.0029646934,0.0008491424,0.0012665126,0.00010091906,0.000082649465,0.012733461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964197,0.00013970355,0.0006852465,0.0011111697,0.001040674,0.000603496],"domain_scores_gemma":[0.9977457,0.0003122078,0.00023441465,0.0010112363,0.00042613837,0.0002703187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093296025,0.000316621,0.0006481783,0.00058384705,0.00031280352,0.0002442166,0.0014258445,0.00019652699,0.00019214586],"category_scores_gemma":[0.00028789183,0.00029040675,0.00063566625,0.002437599,0.00024654274,0.00097224914,0.0004443599,0.0003981758,0.000034310542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003979172,0.0010024306,0.003150128,0.0006181946,0.011134838,0.00023179155,0.0056278473,0.031439397,0.0061986167,0.006252405,0.049973104,0.88397336],"study_design_scores_gemma":[0.0006430049,0.00005741869,0.0004406068,0.000082552375,0.0011451007,0.0000016398951,0.0000853301,0.974929,0.0032843864,0.012700619,0.006334374,0.00029597097],"about_ca_topic_score_codex":0.0010701766,"about_ca_topic_score_gemma":0.00045209622,"teacher_disagreement_score":0.9434896,"about_ca_system_score_codex":0.00052206166,"about_ca_system_score_gemma":0.00038782659,"threshold_uncertainty_score":0.9999548},"labels":[],"label_agreement":null},{"id":"W4407338145","doi":"10.1177/10935266251316782","title":"Validation of A Nationwide Digital Pediatric Pathology Consultation Network","year":2025,"lang":"en","type":"article","venue":"Pediatric and Developmental Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saskatchewan Health Authority; Memorial University of Newfoundland; University of Manitoba; Health Sciences Centre; London Health Sciences Centre; Royal University Hospital; University of Toronto; Western University; Izaak Walton Killam Health Centre; Children's Hospital of Eastern Ontario; Université de Montréal; University of Saskatchewan; Hospital for Sick Children; University of British Columbia; University of Ottawa; Centre Hospitalier Universitaire Sainte-Justine; Dalhousie University; BC Children's Hospital","funders":"Garron Family Cancer Centre","keywords":"Medicine; Digital pathology; Pathology; Medical physics","score_opus":0.00751372102338303,"score_gpt":0.22695850839401274,"score_spread":0.21944478737062972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407338145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67688817,0.00057192676,0.31918833,0.0001523773,0.0007623388,0.00017932025,0.0000055640267,0.000086581626,0.0021653953],"genre_scores_gemma":[0.9725198,0.00043688997,0.02652508,0.00015741774,0.00015106858,0.00003516494,0.00001729326,0.000005488455,0.00015176229],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99878997,0.000072738,0.0004067752,0.0003753576,0.00013867923,0.0002164746],"domain_scores_gemma":[0.9991696,0.0003371726,0.0001965028,0.00012662967,0.00013093058,0.000039149574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029240295,0.00012805751,0.00018842194,0.00032117133,0.00013074928,0.000046571335,0.00020313334,0.00012923862,0.000005708275],"category_scores_gemma":[0.00023152184,0.00013459184,0.000028760547,0.0010325069,0.000058177742,0.0003964627,0.00023017869,0.000106473155,0.000017915969],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053235035,0.00014775779,0.91221046,0.0001581237,0.000024143399,0.00005650846,0.0016595878,0.00031786656,0.0003078404,0.015253251,0.0027219553,0.06708925],"study_design_scores_gemma":[0.003431635,0.00045468847,0.9221393,0.000016425633,0.0001365384,0.0005852748,0.00034193852,0.0022626799,0.0028599796,0.06562008,0.0013221229,0.00082932995],"about_ca_topic_score_codex":0.0000026716068,"about_ca_topic_score_gemma":0.0000015253626,"teacher_disagreement_score":0.29563165,"about_ca_system_score_codex":0.000057142264,"about_ca_system_score_gemma":0.00023537443,"threshold_uncertainty_score":0.5488496},"labels":[],"label_agreement":null},{"id":"W4407374607","doi":"10.1109/tce.2025.3540502","title":"DiffusionClusNet: Deep Clustering-Driven Diffusion Models for Ultrasound Image Enhancement","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Federation for the Humanities and Social Sciences","keywords":"Cluster analysis; Computer science; Artificial intelligence; Diffusion; Image (mathematics); Image enhancement; Computer vision; Physics","score_opus":0.010067279379831342,"score_gpt":0.25552594253463967,"score_spread":0.24545866315480833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407374607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026667078,0.0005566356,0.99273473,0.00064005767,0.0015818186,0.0009140574,0.000013941924,0.00032236893,0.0005697013],"genre_scores_gemma":[0.94434047,0.001713238,0.050782453,0.0007325185,0.00003839266,0.00071721215,0.0000052152777,0.000040879666,0.0016296161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777275,0.00007338689,0.00041409797,0.00075214833,0.0003269556,0.0006606533],"domain_scores_gemma":[0.9984061,0.0003774516,0.00011545902,0.0008192687,0.0001832307,0.00009844984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018640721,0.00032137247,0.0002831382,0.00030379253,0.0006892032,0.00017664034,0.00072495436,0.00016572031,0.000034165936],"category_scores_gemma":[0.000007122598,0.00033771418,0.00021070208,0.00058156,0.00008138237,0.00051352195,0.000012494572,0.000413664,0.000026630618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048237998,0.0012163328,0.0000072234784,0.00020784562,0.00047910627,0.0000039699253,0.0010203737,0.22971319,0.18164387,0.0070237117,0.0012049471,0.57699704],"study_design_scores_gemma":[0.001219031,0.0003261178,0.0000066867456,0.000053369695,0.00007305953,0.000010202229,0.000016442742,0.878052,0.108796336,0.005113496,0.0060104686,0.00032276212],"about_ca_topic_score_codex":0.00003176575,"about_ca_topic_score_gemma":0.0005081625,"teacher_disagreement_score":0.9419522,"about_ca_system_score_codex":0.0007982964,"about_ca_system_score_gemma":0.0003120751,"threshold_uncertainty_score":0.9999075},"labels":[],"label_agreement":null},{"id":"W4407425120","doi":"10.1007/978-3-031-77789-9_15","title":"Vision Mamba for Classification of Breast Ultrasound Images","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Breast ultrasound; Medicine; Mammography; Internal medicine; Breast cancer","score_opus":0.012980205699294752,"score_gpt":0.267407593559223,"score_spread":0.25442738785992824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407425120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018895988,0.0002482433,0.99373996,0.000875859,0.002045363,0.00059854606,0.000042677202,0.00011747967,0.0023129678],"genre_scores_gemma":[0.21617277,0.000096014955,0.78133285,0.0005769649,0.0005768738,0.00004996433,0.000019775,0.000040867777,0.0011339427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969693,0.000027506325,0.0005587928,0.0013326225,0.0007133438,0.00039846887],"domain_scores_gemma":[0.99657786,0.0010170283,0.0004448344,0.001347176,0.0005340684,0.00007904192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079609384,0.00037155976,0.00043468905,0.0008667115,0.00019852618,0.00028538733,0.0024047815,0.00030178684,0.000008785646],"category_scores_gemma":[0.000114465955,0.00035809056,0.00015830732,0.0006789397,0.00059102447,0.000631081,0.00051580084,0.00039759444,0.0000059516565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019420291,0.00003243087,0.00003781527,0.00015831355,0.0000124952185,0.000002763649,0.00015848652,0.0032243137,0.010420776,0.019244567,0.00029077395,0.9663978],"study_design_scores_gemma":[0.0007890106,0.0006674544,0.003405007,0.0016618237,0.000039579292,0.00017145558,4.8892997e-7,0.5847402,0.0404105,0.3635532,0.0033867792,0.0011744704],"about_ca_topic_score_codex":0.000019650597,"about_ca_topic_score_gemma":0.000034473538,"teacher_disagreement_score":0.9652234,"about_ca_system_score_codex":0.0004408545,"about_ca_system_score_gemma":0.0006378176,"threshold_uncertainty_score":0.9998871},"labels":[],"label_agreement":null},{"id":"W4407463850","doi":"10.1016/j.ibmed.2025.100224","title":"Hybrid deep learning and active contour approach for enhanced breast lesion segmentation and classification in mammograms","year":2025,"lang":"en","type":"article","venue":"Intelligence-Based Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Segmentation; Active contour model; Deep learning; Computer science; Pattern recognition (psychology); Lesion; Mammography; Computer vision; Medicine; Image segmentation; Breast cancer; Pathology; Internal medicine; Cancer","score_opus":0.02897732523378391,"score_gpt":0.3115068216683414,"score_spread":0.2825294964345575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407463850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017626274,0.00032185006,0.979368,0.0010293841,0.0001939134,0.00063311495,0.0000012595825,0.00007004696,0.0007561919],"genre_scores_gemma":[0.9778349,0.000228271,0.021387815,0.00017753827,0.000058323356,0.00020649197,0.000022237924,0.0000070169276,0.000077400204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880964,0.0000867507,0.0002852035,0.00046380336,0.0001725603,0.00018206556],"domain_scores_gemma":[0.99920464,0.00032229052,0.00013495388,0.0001506282,0.00012985684,0.000057646997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004582502,0.00013733572,0.00019020302,0.0002800003,0.00011362542,0.000038529044,0.00014659752,0.000060009756,0.0000034374561],"category_scores_gemma":[0.00012247705,0.00012341519,0.000018963408,0.00036860676,0.00013872379,0.00021639335,0.000035491423,0.00017371152,6.2976085e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015491134,0.00003256317,0.0005120064,0.00009422564,0.000008765516,6.9183164e-7,0.00060145854,0.0005565468,0.019480158,0.0015239358,0.000013522296,0.9770212],"study_design_scores_gemma":[0.0012239625,0.00050233793,0.005728754,0.0003590506,0.000026669972,0.000012884338,0.0018267988,0.80049247,0.18399222,0.0053598033,0.00028031442,0.00019471862],"about_ca_topic_score_codex":0.00009353808,"about_ca_topic_score_gemma":0.000035021287,"teacher_disagreement_score":0.9768265,"about_ca_system_score_codex":0.0001919374,"about_ca_system_score_gemma":0.000059770875,"threshold_uncertainty_score":0.50327253},"labels":[],"label_agreement":null},{"id":"W4407618624","doi":"10.3390/bioengineering12020190","title":"Semantic-Attention Enhanced DSC-Transformer for Lymph Node Ultrasound Classification and Remote Diagnostics","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Ultrasound; Lymph node; Materials science; Medicine; Radiology; Pathology","score_opus":0.011517959671406055,"score_gpt":0.24806031809138282,"score_spread":0.23654235841997676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407618624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034653816,0.00029113784,0.96296316,0.0005801786,0.0008867549,0.0002370243,0.000003519678,0.00020054265,0.00018385402],"genre_scores_gemma":[0.93166405,0.00037895038,0.067637995,0.0000659376,0.00007053246,0.00003314617,0.000005628323,0.000010612966,0.00013315321],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992679,0.000007534729,0.00017154252,0.00027733843,0.00009113997,0.00018458546],"domain_scores_gemma":[0.9994519,0.00017979767,0.000036577367,0.00023625305,0.000061513914,0.000033998545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012570071,0.00010975582,0.0000986451,0.00012515289,0.00009503787,0.00009959638,0.00016915255,0.00006947875,6.163427e-7],"category_scores_gemma":[0.00009343513,0.00012014975,0.000037735834,0.00027550175,0.000018472372,0.00024799316,0.000018501563,0.00005252281,0.0000034757938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011696304,0.000020526555,0.0005934086,0.0003675805,0.00004800791,5.7648566e-7,0.00019240909,0.0013012553,0.81411624,0.010882194,0.00024860672,0.17221749],"study_design_scores_gemma":[0.0008337918,0.00004877769,0.078042135,0.0003044384,0.000046566274,0.000010080077,0.000049760496,0.77222735,0.14107896,0.0021032223,0.0048860516,0.00036886003],"about_ca_topic_score_codex":0.000011106883,"about_ca_topic_score_gemma":0.0000036857691,"teacher_disagreement_score":0.8970102,"about_ca_system_score_codex":0.00010713567,"about_ca_system_score_gemma":0.000026681852,"threshold_uncertainty_score":0.48995647},"labels":[],"label_agreement":null},{"id":"W4407633965","doi":"10.1007/s12672-025-01973-x","title":"Benchmarking histopathology foundation models for ovarian cancer bevacizumab treatment response prediction from whole slide images","year":2025,"lang":"en","type":"article","venue":"Discover Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"Benchmarking; Bevacizumab; Histopathology; Ovarian cancer; Foundation (evidence); Medicine; Medical physics; Computer science; Oncology; Cancer; Internal medicine; Pathology; Chemotherapy; Geography; Business","score_opus":0.02478473114011203,"score_gpt":0.32355331010624905,"score_spread":0.298768578966137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407633965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05161754,0.00031166855,0.9359947,0.0059134667,0.004197939,0.00060083024,0.00015446031,0.00014670807,0.0010626977],"genre_scores_gemma":[0.9559775,0.0001462368,0.038595516,0.0008435988,0.0004666884,0.0016321095,0.00012710312,0.000020999258,0.0021902316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982111,0.00031181032,0.00034435533,0.000700579,0.00012440307,0.000307779],"domain_scores_gemma":[0.9986459,0.0005065534,0.000187618,0.00050828676,0.000105992,0.000045666176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003635049,0.00019089582,0.00029451045,0.0002253759,0.00027018678,0.000093521754,0.00034939282,0.00019392507,0.000024826231],"category_scores_gemma":[0.00005143861,0.00018854806,0.00010450665,0.000258428,0.000077607925,0.0008253589,0.0001350596,0.000108955006,0.000008894911],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003498937,0.00035258767,0.001576037,0.000025573274,0.00016904903,0.000028723227,0.0034837073,0.025530692,0.042641662,0.014959363,0.00584173,0.90189195],"study_design_scores_gemma":[0.006476574,0.0029755924,0.040687356,0.00008861387,0.00024819438,0.000020824022,0.00017149789,0.5224315,0.015307652,0.09778252,0.3133299,0.000479775],"about_ca_topic_score_codex":0.0013689059,"about_ca_topic_score_gemma":0.0009080013,"teacher_disagreement_score":0.90436,"about_ca_system_score_codex":0.0037697752,"about_ca_system_score_gemma":0.0010234579,"threshold_uncertainty_score":0.9857831},"labels":[],"label_agreement":null},{"id":"W4407637147","doi":"10.2196/67551","title":"Evaluating the Diagnostic Accuracy of ChatGPT-4 Omni and ChatGPT-4 Turbo in Identifying Melanoma: Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Melanoma; Computer science; Medicine; Cancer research; World Wide Web","score_opus":0.06754269392955682,"score_gpt":0.4176163842670595,"score_spread":0.3500736903375027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407637147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869955,0.0010942932,0.008261739,0.0015277476,0.0005190507,0.0011735887,7.349381e-7,0.000052494684,0.00037483577],"genre_scores_gemma":[0.99869543,0.000026678428,0.0006553495,0.00017423826,0.000016671938,0.00040478093,5.2083664e-7,0.000004854466,0.000021485223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980946,0.0005680312,0.0004662324,0.00040979992,0.00020889686,0.00025241057],"domain_scores_gemma":[0.99629086,0.0028322057,0.00024521025,0.00051616406,0.00008938919,0.000026166284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045633008,0.0001526426,0.0003710403,0.00025925148,0.00015851622,0.00007100468,0.0006446618,0.00007434237,0.0000050496415],"category_scores_gemma":[0.00037776292,0.00012329446,0.000033983146,0.000748347,0.0001348771,0.00034384028,0.00052587694,0.00026523523,0.000007743709],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001834093,0.0012085235,0.6913726,0.00066633045,0.00039481977,0.00025120823,0.14959256,0.00118661,0.0031892445,0.025734974,0.0015865511,0.12463322],"study_design_scores_gemma":[0.00310458,0.00050749525,0.84465635,0.0002765127,0.00005456067,0.000287084,0.0053925263,0.12334921,0.009433666,0.01226462,0.00030185064,0.0003715222],"about_ca_topic_score_codex":0.000116809344,"about_ca_topic_score_gemma":0.00029482553,"teacher_disagreement_score":0.15328382,"about_ca_system_score_codex":0.00006500799,"about_ca_system_score_gemma":0.0001020614,"threshold_uncertainty_score":0.50278026},"labels":[],"label_agreement":null},{"id":"W4407682377","doi":"10.54097/1azdbv04","title":"Revolutionizing Disease Detection with U-Net: Enhancing Biomedical Image Segmentation in Healthcare","year":2025,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Health care; Image segmentation; Computer science; Artificial intelligence; Computer vision; Segmentation; Disease; Medicine; Pathology; Economics","score_opus":0.00337156223611111,"score_gpt":0.22571554176250466,"score_spread":0.22234397952639356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407682377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3196532,0.0003353831,0.6735504,0.0055697146,0.00041713254,0.00015811103,4.043511e-7,0.0003007369,0.000014850829],"genre_scores_gemma":[0.9697915,0.000069753754,0.030034943,0.000022738815,0.000013080765,0.00005772736,2.51104e-7,0.0000037330394,0.000006308781],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883395,0.000012678075,0.00019286443,0.0004640741,0.00019018365,0.00030626872],"domain_scores_gemma":[0.99956197,0.00003178618,0.000037330065,0.00025620675,0.000053355285,0.00005938387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035961595,0.00009884614,0.00010958992,0.0018523735,0.00014104375,0.00006025168,0.00031758292,0.000074803516,1.9309974e-7],"category_scores_gemma":[0.00009207039,0.000090382404,0.0000067117235,0.004843563,0.00023864802,0.0005253787,0.00012965102,0.00020424201,0.0000026013884],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029445198,0.00008050761,0.0078132395,0.00024193068,0.000006845302,0.000104451225,0.00050669105,0.0028711974,0.69808435,0.20772675,0.000010804961,0.082523786],"study_design_scores_gemma":[0.0011864507,0.0002851203,0.040628634,0.0009387539,0.0000067501724,0.000056472447,0.00017014112,0.5309749,0.41595894,0.0080227805,0.0012734343,0.0004975679],"about_ca_topic_score_codex":0.00008514572,"about_ca_topic_score_gemma":0.00018526333,"teacher_disagreement_score":0.65013826,"about_ca_system_score_codex":0.00044726132,"about_ca_system_score_gemma":0.00016877156,"threshold_uncertainty_score":0.36856875},"labels":[],"label_agreement":null},{"id":"W4407764510","doi":"10.1016/j.semcancer.2025.02.009","title":"Biomarkers, omics and artificial intelligence for early detection of pancreatic cancer","year":2025,"lang":"en","type":"review","venue":"Seminars in Cancer Biology","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pancreas Centre (Canada)","funders":"","keywords":"Biomarker; Pancreatic ductal adenocarcinoma; Pancreatic cancer; Omics; Biomarker discovery; Medicine; Disease; Population; Cancer; Bioinformatics; Internal medicine; Biology; Proteomics; Environmental health; Gene","score_opus":0.05149028492997009,"score_gpt":0.37459167454093617,"score_spread":0.32310138961096607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407764510","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006311988,0.87057525,0.12583214,0.00005811921,0.002242948,0.001010677,0.00014372251,0.000038082864,0.000035932568],"genre_scores_gemma":[0.0004288686,0.9939455,0.003700258,0.00002365701,0.00017057039,0.0016355729,0.000009643079,0.000021274123,0.0000646964],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976604,0.00018985836,0.0008407053,0.00084397284,0.00008722683,0.0003778607],"domain_scores_gemma":[0.997993,0.0008229134,0.00055989425,0.000475307,0.00010154522,0.000047376227],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047223497,0.00035619477,0.0012483454,0.00058141345,0.0000705256,0.00003135132,0.0006922832,0.0005694775,0.0000067193087],"category_scores_gemma":[0.00011809843,0.00033479917,0.00019339395,0.0010667101,0.00021916801,0.00010617254,0.0002591331,0.00029048938,0.0000010935524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027342649,0.000013547427,0.000043627388,0.0056161936,0.000100110825,6.390251e-7,0.000088415094,0.0000056020717,0.00007493098,0.00060160534,0.0000378207,0.99339014],"study_design_scores_gemma":[0.00036306775,0.001485555,0.000063332445,0.05461852,0.0012029965,0.000040297895,0.00007364352,0.0061782585,0.008429342,0.03417162,0.8915239,0.0018494956],"about_ca_topic_score_codex":0.001509395,"about_ca_topic_score_gemma":0.0011626584,"teacher_disagreement_score":0.9915407,"about_ca_system_score_codex":0.0006266021,"about_ca_system_score_gemma":0.0006834094,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"id":"W4407827279","doi":"10.1038/s41598-025-90024-0","title":"Generalizable deep neural networks for image quality classification of cervical images","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Queen's University; McGill University","funders":"National Cancer Institute","keywords":"Artificial intelligence; Computer science; Artificial neural network; Pattern recognition (psychology); Image (mathematics); Deep neural networks; Image quality; Computer vision; Machine learning","score_opus":0.02750160837232631,"score_gpt":0.31674484410428616,"score_spread":0.28924323573195987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407827279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013465483,0.0001996156,0.9735013,0.00068938924,0.010433455,0.0003753405,0.0000013184557,0.00012778255,0.00120627],"genre_scores_gemma":[0.94777787,0.0000025387012,0.050391562,0.00007155398,0.00008149956,0.00008981625,0.000018237826,0.0000074719583,0.0015594355],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977573,0.00009374633,0.0006856917,0.0008327855,0.0003473783,0.0002830921],"domain_scores_gemma":[0.99755716,0.000093593444,0.00043963338,0.0013650772,0.0004859135,0.00005858975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020720165,0.00011424489,0.00019662277,0.00017143681,0.00030130488,0.0003859597,0.00045591235,0.00007864864,0.0000119759525],"category_scores_gemma":[0.00016979138,0.00011023307,0.00012931657,0.0010259477,0.00021929241,0.0005504448,0.00018199743,0.000087791086,0.0000013365321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009752652,0.00055101636,0.018114237,0.00079604576,0.0001293123,0.0000684608,0.00079677167,0.0565592,0.42148998,0.058876902,0.15039699,0.29212353],"study_design_scores_gemma":[0.00014370713,0.000024791329,0.010233271,0.000015414756,0.000013424668,0.00002164017,0.000023254965,0.8994214,0.050728206,0.032987095,0.00623494,0.00015287232],"about_ca_topic_score_codex":0.000050964023,"about_ca_topic_score_gemma":0.000033043794,"teacher_disagreement_score":0.9343124,"about_ca_system_score_codex":0.000099749755,"about_ca_system_score_gemma":0.00011463444,"threshold_uncertainty_score":0.44951743},"labels":[],"label_agreement":null},{"id":"W4407845039","doi":"10.3390/ai6030043","title":"GeNetFormer: Transformer-Based Framework for Gene Expression Prediction in Breast Cancer","year":2025,"lang":"en","type":"article","venue":"AI","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breast cancer; Gene; Artificial intelligence; Transcriptome; Computational biology; Computer science; Gene expression; Pattern recognition (psychology); Biology; Cancer; Genetics","score_opus":0.010280378729971566,"score_gpt":0.2860700789559414,"score_spread":0.2757897002259698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407845039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011448495,0.00021484717,0.98165065,0.0048237937,0.0011990904,0.00035762228,0.000034793542,0.00012504609,0.00014564808],"genre_scores_gemma":[0.9072835,0.00007981008,0.08921258,0.0024137844,0.00018799499,0.00069072563,0.0000058752557,0.000012305209,0.00011341857],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909663,0.000019814259,0.00019324046,0.0003251398,0.00014150665,0.00022367609],"domain_scores_gemma":[0.9995115,0.00006408593,0.00004100876,0.00029020716,0.000058053465,0.000035170237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001313631,0.0001023055,0.000107864274,0.00015559782,0.00010028992,0.000046539477,0.0003006061,0.0001272102,0.000024209652],"category_scores_gemma":[0.0000074871687,0.00009909423,0.000056050452,0.0004874622,0.000019201478,0.000334246,0.00001865002,0.0001480065,0.0000034575876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000372539,0.00021731944,0.031134875,0.00025837167,0.000041693325,0.0000024844758,0.0007483478,0.023184508,0.08314008,0.0095979525,0.011734576,0.83956724],"study_design_scores_gemma":[0.0018571448,0.00014856613,0.043718033,0.0006274958,0.00002091415,0.000004403024,0.000022073864,0.29869887,0.60150975,0.03785574,0.015210694,0.00032633584],"about_ca_topic_score_codex":0.000111835434,"about_ca_topic_score_gemma":0.00005221467,"teacher_disagreement_score":0.895835,"about_ca_system_score_codex":0.0002333057,"about_ca_system_score_gemma":0.00020574388,"threshold_uncertainty_score":0.40409455},"labels":[],"label_agreement":null},{"id":"W4407849425","doi":"10.1016/j.bspc.2025.107686","title":"Sift-BCD: SIFT-CNN integrated machine learning-based breast cancer detection","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Scale-invariant feature transform; Computer science; Artificial intelligence; Pattern recognition (psychology); Cancer detection; Breast cancer; Machine learning; Cancer; Feature extraction; Medicine","score_opus":0.0048925433988405076,"score_gpt":0.23234233018450498,"score_spread":0.22744978678566447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407849425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028723727,0.0021935366,0.98870367,0.00523715,0.00033593105,0.00015709031,0.000010936358,0.00040203196,0.00008725473],"genre_scores_gemma":[0.99786025,0.00002057946,0.00043023395,0.0012188738,0.00017293231,0.00008320748,0.0000042746233,0.000011074958,0.00019855333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983324,0.00014051356,0.00029706437,0.000519084,0.00037304172,0.0003379412],"domain_scores_gemma":[0.99925727,0.00012390508,0.00013754173,0.00013639363,0.00017454699,0.00017035993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038398837,0.00021140912,0.0002539258,0.00023356301,0.00042885134,0.00026220415,0.0003224063,0.00018181573,0.000049685586],"category_scores_gemma":[0.000045041434,0.00016947927,0.000058243084,0.0009575876,0.00020776819,0.00024793085,0.000054628155,0.0004613012,0.000005698683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016343291,0.0000618164,0.00060998165,0.000084312735,0.000029696039,0.0000054654056,0.000040399933,0.00020994598,0.014085112,0.000024363306,0.00007461586,0.98461086],"study_design_scores_gemma":[0.0020047566,0.0001965117,0.0016846643,0.00024831848,0.000043230604,0.000015012754,0.00001776949,0.9781091,0.0029416985,0.00037379735,0.0141529525,0.00021215454],"about_ca_topic_score_codex":0.0005260729,"about_ca_topic_score_gemma":0.00006271,"teacher_disagreement_score":0.9949879,"about_ca_system_score_codex":0.00016680999,"about_ca_system_score_gemma":0.00044342785,"threshold_uncertainty_score":0.6911164},"labels":[],"label_agreement":null},{"id":"W4407959414","doi":"10.1016/j.labinv.2025.104121","title":"Artificial Intelligence–Assisted Detection of Breast Cancer Lymph Node Metastases in the Post-Neoadjuvant Treatment Setting","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Waterloo; Sunnybrook Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation; Canadian Cancer Society; Ontario Research Foundation","keywords":"Medicine; Breast cancer; Lymph node; Oncology; Neoadjuvant therapy; Cancer; Internal medicine; Radiology","score_opus":0.02197880933588754,"score_gpt":0.2776362922732254,"score_spread":0.25565748293733787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407959414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90160173,0.00040832616,0.090289526,0.0059052957,0.0009840522,0.00048446056,0.000103504455,0.00014035993,0.000082775114],"genre_scores_gemma":[0.99658674,0.00002493039,0.0024070584,0.0007265909,0.00006885991,0.00016661498,0.000007401891,0.0000066348953,0.0000051583047],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984155,0.00037208607,0.00044710128,0.0003297552,0.0002554505,0.00018009862],"domain_scores_gemma":[0.99887156,0.0001622629,0.0002322745,0.00040781483,0.00029151994,0.00003459257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052460365,0.00015496378,0.0001650336,0.00026608558,0.00015262158,0.000089781,0.0003339982,0.00007761582,0.0000051680204],"category_scores_gemma":[0.0000823801,0.00012207087,0.00004616314,0.0020061154,0.000110981935,0.00046010935,0.000040712468,0.00010257749,0.000004364567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000559577,0.00014291613,0.010209369,0.0000781087,0.00006711237,0.000006660366,0.00338114,0.004815507,0.32263336,0.01167056,0.000027885793,0.64691144],"study_design_scores_gemma":[0.00017993346,0.000099283556,0.15951897,0.0001889265,0.000058099125,0.0000085570755,0.0008571016,0.04211219,0.7882097,0.008409981,0.0001487577,0.00020854024],"about_ca_topic_score_codex":0.001117689,"about_ca_topic_score_gemma":0.0010644414,"teacher_disagreement_score":0.6467029,"about_ca_system_score_codex":0.0005280615,"about_ca_system_score_gemma":0.0005308892,"threshold_uncertainty_score":0.49779052},"labels":[],"label_agreement":null},{"id":"W4408006890","doi":"10.18280/ts.420101","title":"Hybrid Ensemble Model with Bagging (HEMBAGG) Leveraging Machine Learning for Breast Carcinoma Diagnosis","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ensemble learning; Computer science; Artificial intelligence; Machine learning; Breast carcinoma; Bootstrap aggregating; Ensemble forecasting; Breast cancer; Medicine; Internal medicine; Cancer","score_opus":0.015687970684293947,"score_gpt":0.2261899447998361,"score_spread":0.21050197411554214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408006890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098971255,0.00014322656,0.89821714,0.001351624,0.00013249753,0.00038640448,0.000009518338,0.00023635509,0.00055196177],"genre_scores_gemma":[0.97026986,0.000008777579,0.02851111,0.0004572689,0.0000848703,0.00032559145,0.000007093458,0.000020892185,0.00031452376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984065,0.00004735913,0.00026322834,0.00056018133,0.00030309183,0.00041960558],"domain_scores_gemma":[0.99929184,0.00015123194,0.00011164345,0.00026149952,0.00010869849,0.00007510794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033875176,0.0002246005,0.00021061294,0.00020359429,0.0004149632,0.00019206424,0.00046708598,0.000030688992,0.000027292865],"category_scores_gemma":[0.000008344562,0.00021328258,0.00008671982,0.00026720768,0.0000305245,0.0004535043,0.00013899703,0.00019548931,0.00000357206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021049067,0.00017433122,0.02766112,0.00021905567,0.00016235404,0.00002486765,0.0011815517,0.4966383,0.0042335195,0.0064088316,0.0019464125,0.46113917],"study_design_scores_gemma":[0.001139107,0.00015620046,0.0019699717,0.000103244995,0.000036280253,0.000033163546,0.000024855903,0.97659564,0.017317725,0.0013348148,0.0010443173,0.0002447025],"about_ca_topic_score_codex":0.00010636616,"about_ca_topic_score_gemma":0.000025279076,"teacher_disagreement_score":0.8712986,"about_ca_system_score_codex":0.0002564299,"about_ca_system_score_gemma":0.00015442068,"threshold_uncertainty_score":0.8697411},"labels":[],"label_agreement":null},{"id":"W4408010992","doi":"10.18280/isi.300219","title":"Harnessing CNN for Early Breast Cancer Detection: Enhancing Precision in Image-Based Diagnosis","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology); Computer vision; Cancer; Medicine; Internal medicine","score_opus":0.009966978078474997,"score_gpt":0.25517037252896474,"score_spread":0.24520339445048975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408010992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09155546,0.00010767994,0.9052606,0.00030914627,0.0012561581,0.00061582227,0.00001321676,0.000242719,0.00063916086],"genre_scores_gemma":[0.980874,0.000021302778,0.017443787,0.0002538407,0.000075473545,0.0012920889,0.0000056117833,0.000009484494,0.00002439174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984373,0.00006592938,0.0006563259,0.00025472778,0.00024981776,0.00033592925],"domain_scores_gemma":[0.9986537,0.00024194848,0.00029712488,0.00034436528,0.00041500514,0.00004782721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006030652,0.00018742314,0.00021146711,0.0006693466,0.00038036055,0.000700668,0.0003947829,0.0001382145,0.0000097582215],"category_scores_gemma":[0.00019208438,0.00019818092,0.000085213826,0.0013217202,0.00006056913,0.0062217955,0.00009458098,0.00015677049,0.000014678051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008488781,0.000019940844,0.0047126226,0.00040648284,0.000013377413,5.5083353e-7,0.0016361804,0.003084645,0.001142872,0.00029486636,0.00012726744,0.98847634],"study_design_scores_gemma":[0.0023732204,0.0001890663,0.17725445,0.002800452,0.00003391978,0.000016005248,0.00034068045,0.5221061,0.28114355,0.010124824,0.0029315895,0.00068609865],"about_ca_topic_score_codex":0.0005831581,"about_ca_topic_score_gemma":0.00036258379,"teacher_disagreement_score":0.9877902,"about_ca_system_score_codex":0.0013473389,"about_ca_system_score_gemma":0.00028893386,"threshold_uncertainty_score":0.80815834},"labels":[],"label_agreement":null},{"id":"W4408033664","doi":"10.18280/ts.420129","title":"An Accurate Diagnosis and Classification of Breast Mammogram Using Transfer Learning in Deep Convolutional Neural Network","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Transfer of learning; Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Artificial neural network; Machine learning","score_opus":0.028235520377171017,"score_gpt":0.2763999050975973,"score_spread":0.2481643847204263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408033664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5260554,0.000097049124,0.47334012,0.00020932517,0.000095925636,0.0001367254,0.0000015965165,0.000037246366,0.0000266026],"genre_scores_gemma":[0.9966556,0.000019078869,0.0031360576,0.000071138165,0.000060869887,0.000044377564,0.0000048411894,0.000005002342,0.0000030314889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988932,0.00015306249,0.00029052017,0.00028713528,0.00017887099,0.00019720718],"domain_scores_gemma":[0.999641,0.00008723644,0.000056033907,0.000115268806,0.000059705893,0.000040749223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033342757,0.0001033526,0.0001292209,0.00013234194,0.00011015697,0.00006892374,0.00020128209,0.000051374733,0.000022946426],"category_scores_gemma":[0.0000035544413,0.00011116023,0.00003188795,0.0005015529,0.00006342582,0.00047196096,0.000030466328,0.00013914108,4.349586e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009412555,0.00017819268,0.26254886,0.000056983856,0.00003660709,0.0000029640698,0.00059809064,0.4758521,0.01349517,0.011328566,0.000026111888,0.23578222],"study_design_scores_gemma":[0.00032729865,0.00006983511,0.3607405,0.000036429195,0.000008898786,0.0000046734394,0.000030857966,0.638094,0.00025808378,0.0003091958,0.00005291648,0.00006729774],"about_ca_topic_score_codex":0.000060354712,"about_ca_topic_score_gemma":0.000098449644,"teacher_disagreement_score":0.4706002,"about_ca_system_score_codex":0.000096930045,"about_ca_system_score_gemma":0.00005608977,"threshold_uncertainty_score":0.45329827},"labels":[],"label_agreement":null},{"id":"W4408037351","doi":"10.18280/ts.420139","title":"Fine-Tuning Pre-Trained Networks with Attention Mechanisms for Improved Multi-Classification of Breast Cancer Histology Images","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Histology; Artificial intelligence; Computer science; Breast cancer; Pattern recognition (psychology); Cancer; Computer vision; Medicine; Pathology; Internal medicine","score_opus":0.014238495849983115,"score_gpt":0.2618530273700996,"score_spread":0.24761453152011648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408037351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008234812,0.00007137369,0.98877907,0.001683085,0.00037998983,0.0007020986,0.000022856642,0.000096104675,0.000030626325],"genre_scores_gemma":[0.9297401,0.000006823654,0.069368735,0.00010314454,0.00006180477,0.00046099382,0.000012355857,0.000011531061,0.00023456634],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883515,0.00005456997,0.00032843853,0.00041009218,0.0001289302,0.00024280406],"domain_scores_gemma":[0.9991432,0.0000695656,0.00027271724,0.00023877752,0.00023943382,0.000036342648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028149897,0.00015429872,0.00019790207,0.00014198633,0.0001322925,0.00003931324,0.00034670025,0.00007728065,0.000022034646],"category_scores_gemma":[0.0000051125126,0.00014029676,0.000067521156,0.0003105914,0.000060353323,0.00021652401,0.00004948215,0.00009185536,3.0606103e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047651192,0.00023367417,0.0009800146,0.00015419567,0.00018368612,7.7099236e-7,0.00022719882,0.01083898,0.7735536,0.011772474,0.0005498429,0.20102903],"study_design_scores_gemma":[0.0019307941,0.0002664659,0.06727995,0.00009903582,0.00006163582,0.000004974657,0.000025989457,0.92205787,0.007494344,0.0004911894,0.00012958635,0.00015815483],"about_ca_topic_score_codex":0.00010443379,"about_ca_topic_score_gemma":0.00023509968,"teacher_disagreement_score":0.9215052,"about_ca_system_score_codex":0.00021162948,"about_ca_system_score_gemma":0.00011728749,"threshold_uncertainty_score":0.5721136},"labels":[],"label_agreement":null},{"id":"W4408063886","doi":"10.3390/diagnostics15050582","title":"Enhanced Multi-Class Breast Cancer Classification from Whole-Slide Histopathology Images Using a Proposed Deep Learning Model","year":2025,"lang":"en","type":"article","venue":"Diagnostics","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"Commonwealth Cyber Initiative","keywords":"Breast cancer; Malignancy; Histopathology; Artificial intelligence; Deep learning; Class (philosophy); Cancer; Medicine; Machine learning; Pattern recognition (psychology); Computer science; Pathology; Internal medicine","score_opus":0.02598355000387062,"score_gpt":0.29530388209879316,"score_spread":0.26932033209492257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408063886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048172772,0.0005880315,0.94820595,0.0012740042,0.0010052773,0.00025489632,0.000033374512,0.00026884346,0.00019685461],"genre_scores_gemma":[0.89278007,0.00032152302,0.105917834,0.0004832128,0.00010853896,0.00008191866,0.000013017666,0.00002193986,0.00027195652],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983669,0.00013605093,0.00032248063,0.0006357138,0.00020908375,0.0003297728],"domain_scores_gemma":[0.99857646,0.00034733527,0.00022155729,0.0005068129,0.00028181158,0.00006601088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015078027,0.00020621989,0.0002331523,0.00017044268,0.00027127875,0.00012748229,0.0005472757,0.00016205017,0.000008224694],"category_scores_gemma":[0.00034384066,0.00022484313,0.000059802845,0.00044946678,0.000106519044,0.00037201343,0.00022355033,0.00036410612,0.000020028061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049345213,0.0002748878,0.008679708,0.00007313315,0.00005062847,0.000030848616,0.001997581,0.25365594,0.4767401,0.002379849,0.0008938184,0.25517416],"study_design_scores_gemma":[0.00046842464,0.000018335242,0.021691648,0.00010564737,0.000041322313,0.0000030884844,0.000056784258,0.95390993,0.021715008,0.0015401691,0.00023078415,0.00021887696],"about_ca_topic_score_codex":0.00036212444,"about_ca_topic_score_gemma":0.00017144307,"teacher_disagreement_score":0.8446073,"about_ca_system_score_codex":0.00080845586,"about_ca_system_score_gemma":0.00028859617,"threshold_uncertainty_score":0.91688365},"labels":[],"label_agreement":null},{"id":"W4408066260","doi":"10.18280/ts.420105","title":"A Robust Breast Cancer Classification System Using Multilayer Perceptron and Grey Wolf Optimization","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Breast cancer; Pattern recognition (psychology); Computer science; Perceptron; Machine learning; Cancer; Biology; Artificial neural network; Genetics","score_opus":0.03724279310616258,"score_gpt":0.2622358296882333,"score_spread":0.2249930365820707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408066260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044505704,0.000109404245,0.9535716,0.0006107654,0.0004055351,0.0003324789,0.000008470286,0.00018362365,0.00027240577],"genre_scores_gemma":[0.9641512,0.000020070931,0.03542261,0.0001520049,0.00012014921,0.000072876486,0.0000028611282,0.00000982923,0.000048385005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879646,0.00007665434,0.00026419622,0.0004297121,0.00023279809,0.00020015669],"domain_scores_gemma":[0.9994441,0.000024620304,0.000118263204,0.00021211489,0.000147157,0.000053700336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021863576,0.00014627763,0.00013438,0.00016572702,0.00022990875,0.0002003237,0.00022928153,0.000070059934,0.000060959796],"category_scores_gemma":[0.0000025020029,0.0001457619,0.00003484779,0.00037456834,0.000036863657,0.0005714128,0.00007776327,0.000092081726,0.0000028824193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006863171,0.00008090313,0.005568437,0.00022293655,0.000072435105,0.000002069649,0.00084899063,0.90551,0.018473316,0.00494736,0.00044059497,0.0637643],"study_design_scores_gemma":[0.00048188015,0.000021571332,0.020710059,0.00015456279,0.00003098878,0.000015683609,0.00022449593,0.9776389,0.00048859307,0.000010451497,0.00008798905,0.00013481194],"about_ca_topic_score_codex":0.00019586616,"about_ca_topic_score_gemma":0.000025129744,"teacher_disagreement_score":0.9196455,"about_ca_system_score_codex":0.00062278536,"about_ca_system_score_gemma":0.00010461576,"threshold_uncertainty_score":0.59439975},"labels":[],"label_agreement":null},{"id":"W4408072393","doi":"10.1186/s12874-025-02516-2","title":"The reporting quality and methodological quality of dynamic prediction models for cancer prognosis","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Quality (philosophy); Medicine; Computer science; Data science","score_opus":0.8402655165870867,"score_gpt":0.6765423709087541,"score_spread":0.16372314567833257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408072393","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028567888,0.0018804311,0.9585141,0.009164685,0.00074363366,0.0007976836,0.000007701981,0.00008447428,0.0002394101],"genre_scores_gemma":[0.17161728,0.0018599142,0.82443726,0.00021794187,0.0001105613,0.0014906547,0.0000019398208,0.000009653531,0.00025479234],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95685273,0.037345298,0.0024470177,0.00096963445,0.0016289987,0.0007563019],"domain_scores_gemma":[0.75800556,0.23786607,0.0013333602,0.0010791325,0.0014176,0.0002982798],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23567729,0.00013206537,0.0006723541,0.00019990069,0.00051628385,0.000054158525,0.001043637,0.0003934761,0.000009790073],"category_scores_gemma":[0.33534938,0.000087647764,0.0001513119,0.0008503282,0.0011701627,0.00016667004,0.0009004363,0.00077392027,2.631845e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042849535,0.000051981053,0.0049346043,0.0005770432,0.00007468965,0.0000010175961,0.00025369012,0.00011207023,0.0028575591,0.1932534,0.00031396112,0.7971415],"study_design_scores_gemma":[0.0006220438,0.0002737577,0.05880402,0.00013313873,0.000014058394,0.000008214977,0.00030086405,0.386795,0.0034284992,0.5485188,0.0009901715,0.00011145837],"about_ca_topic_score_codex":0.0012027198,"about_ca_topic_score_gemma":0.0019090478,"teacher_disagreement_score":0.79703003,"about_ca_system_score_codex":0.00022329148,"about_ca_system_score_gemma":0.0016976588,"threshold_uncertainty_score":0.78703105},"labels":[],"label_agreement":null},{"id":"W4408205304","doi":"10.47852/bonviewjdsis52024868","title":"Experts' Cognition-driven Safe Noisy Labels Learning for Precise Segmentation of Residual Tumor in Breast Cancer","year":2025,"lang":"en","type":"article","venue":"Journal of Data Science and Intelligent Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Breast cancer; Machine learning; Artificial intelligence; Cognition; Conceptualization; Segmentation; Residual; Generalization; Natural language processing; Cancer; Medicine; Algorithm; Mathematics","score_opus":0.04692141047577228,"score_gpt":0.3507744324729029,"score_spread":0.3038530219971306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408205304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16139132,0.002231683,0.83102393,0.0014229732,0.0028148296,0.0007912801,0.00009346345,0.000016358636,0.00021416476],"genre_scores_gemma":[0.99503845,0.00065016805,0.0040486543,0.0000664109,0.00012015888,0.000020914207,0.0000027416788,0.0000036674867,0.00004880709],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983263,0.000070766655,0.0006190348,0.00028275134,0.0005310725,0.0001700657],"domain_scores_gemma":[0.99830395,0.0001603747,0.00051978143,0.0002604283,0.0006970684,0.000058380047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019934357,0.000083060186,0.00021002218,0.00046232672,0.0001347058,0.00018121909,0.0010115567,0.000026408137,0.00000385423],"category_scores_gemma":[0.00014746512,0.00006912569,0.000021150981,0.00079640164,0.00013381465,0.0028361424,0.00023355777,0.00011049675,5.1532214e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007486704,0.00053532753,0.051730562,0.0013992346,0.00022561895,0.000025588171,0.009551349,0.0261718,0.3494766,0.0042661536,0.016555427,0.5393137],"study_design_scores_gemma":[0.0024409331,0.001029991,0.010202577,0.006283125,0.000111363486,0.00045179916,0.011167784,0.7822847,0.17433596,0.000664255,0.01046696,0.0005605508],"about_ca_topic_score_codex":0.0001603426,"about_ca_topic_score_gemma":0.000032398006,"teacher_disagreement_score":0.83364713,"about_ca_system_score_codex":0.00021114064,"about_ca_system_score_gemma":0.0005914446,"threshold_uncertainty_score":0.28188637},"labels":[],"label_agreement":null},{"id":"W4408364279","doi":"10.1148/ryai.240287","title":"External Testing of a Commercial AI Algorithm for Breast Cancer Detection at Screening Mammography","year":2025,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of Calgary; Kelowna General Hospital","funders":"Mitacs; Canadian Cancer Society","keywords":"Receiver operating characteristic; Medicine; Breast cancer; Mammography; Algorithm; Breast cancer screening; Area under the curve; Area under curve; Retrospective cohort study; Machine learning; Cancer; Artificial intelligence; Internal medicine; Oncology; Mathematics; Computer science","score_opus":0.04239276374823154,"score_gpt":0.32273398706420203,"score_spread":0.2803412233159705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408364279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013676197,0.00031462454,0.98291665,0.0006373576,0.0018917233,0.0003313226,0.000035178855,0.00013236063,0.00006455992],"genre_scores_gemma":[0.8409838,0.000026882879,0.15797661,0.00041358278,0.00037112948,0.000171772,9.054535e-7,0.000012068267,0.000043264106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983028,0.000120832396,0.0005319083,0.00052049453,0.00014393654,0.00038003974],"domain_scores_gemma":[0.99852467,0.0005078032,0.00023409302,0.0003466965,0.00033028884,0.000056472378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049013086,0.0001790913,0.00028545858,0.00033446203,0.0003903393,0.000041226285,0.000626276,0.00017050246,0.000024471547],"category_scores_gemma":[0.000090554764,0.00019115998,0.00014080813,0.001057593,0.00026308344,0.00024790288,0.0001948743,0.00023311397,0.00000503224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000835507,0.0000264477,0.0019821103,0.000018361872,0.000037540063,0.0000016371266,0.00009848984,0.0017810748,0.016574807,0.0028069834,0.000056554112,0.97653246],"study_design_scores_gemma":[0.00007607161,0.00019146099,0.011520179,0.00011021324,0.00003186115,0.00009837576,0.000027606262,0.6804549,0.28779727,0.019189686,0.00028844416,0.00021392191],"about_ca_topic_score_codex":0.0004042326,"about_ca_topic_score_gemma":0.00041576548,"teacher_disagreement_score":0.97631854,"about_ca_system_score_codex":0.00016753518,"about_ca_system_score_gemma":0.00009677906,"threshold_uncertainty_score":0.7795278},"labels":[],"label_agreement":null},{"id":"W4408664434","doi":"10.2196/62833","title":"Association Between Risk Factors and Major Cancers: Explainable Machine Learning Approach","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Association (psychology); Risk factor; Cancer; Protective factor; Factor (programming language); Medicine; Oncology; Psychology; Computer science; Internal medicine; World Wide Web","score_opus":0.013740002775210761,"score_gpt":0.26878272529189196,"score_spread":0.2550427225166812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408664434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5950649,0.0035621382,0.38732946,0.0014511416,0.0014814023,0.0009977453,0.000060098802,0.00075490883,0.009298212],"genre_scores_gemma":[0.9910553,0.0004211114,0.0022727447,0.0000971574,0.00019080515,0.00032747333,0.0000069627513,0.000014461652,0.0056140022],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864733,0.000120221215,0.0001883005,0.00046259095,0.00026280957,0.00031874984],"domain_scores_gemma":[0.9992528,0.00013876462,0.00022539287,0.00024355993,0.00007695792,0.00006254024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030663155,0.00016713794,0.00021678848,0.00015059415,0.00035826108,0.00016976171,0.00030918478,0.0001291187,0.000022424027],"category_scores_gemma":[0.000055379653,0.00015554264,0.000049757873,0.00061974255,0.000022760129,0.00049106305,0.00018227099,0.00040911618,0.0000035313508],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072003436,0.000009682775,0.9601413,0.000056758003,0.00015778615,3.7842156e-7,0.00092890114,0.0015128391,0.00004754755,0.0002741704,0.0023398877,0.034523565],"study_design_scores_gemma":[0.0016813719,0.0001717667,0.6753166,0.00013164271,0.00019253837,9.887488e-7,0.0003277319,0.13498403,0.005459778,0.0021298667,0.17883983,0.00076389854],"about_ca_topic_score_codex":0.0072165937,"about_ca_topic_score_gemma":0.00032582512,"teacher_disagreement_score":0.39599037,"about_ca_system_score_codex":0.0017167924,"about_ca_system_score_gemma":0.00016856896,"threshold_uncertainty_score":0.9993944},"labels":[],"label_agreement":null},{"id":"W4408666203","doi":"10.1016/j.iswa.2025.200505","title":"Deep learning for efficient high-resolution image processing: A systematic review","year":2025,"lang":"en","type":"review","venue":"Intelligent Systems with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Deutsche Gesellschaft für Internationale Zusammenarbeit; International Development Research Centre","keywords":"Computer science; Artificial intelligence; Deep learning; Image processing; Image (mathematics); Computer vision","score_opus":0.025824936897122893,"score_gpt":0.3184706109502528,"score_spread":0.2926456740531299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408666203","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.5474615e-10,0.49334657,0.4937649,0.000025464684,0.00015201535,0.012317596,0.000006326367,0.0002724221,0.00011469613],"genre_scores_gemma":[0.000006949971,0.89987475,0.010653355,0.000029033949,0.00014363842,0.08820164,0.000086165455,0.000058565933,0.0009459079],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9956899,0.0003985879,0.0017414487,0.0011592524,0.00054924405,0.0004615557],"domain_scores_gemma":[0.9950186,0.0006406773,0.0019309272,0.0015608321,0.00071743777,0.00013150761],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001063865,0.000612709,0.0024292248,0.00043123774,0.0004958294,0.00041426072,0.0016500943,0.00024360971,0.0000019605127],"category_scores_gemma":[0.00017107725,0.0004560674,0.00041083116,0.0020395285,0.00006275755,0.0001531888,0.00017668486,0.00043336474,0.00016610857],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.644769e-7,0.000040574785,1.695872e-8,0.85706717,0.000096838085,5.757164e-7,0.000025983945,0.0011242799,6.297504e-8,0.005233367,0.00012837363,0.13628191],"study_design_scores_gemma":[0.000048348465,0.000056221146,1.0952492e-8,0.59656817,0.0015524034,0.00007399686,0.000018183471,0.04172993,0.0000011256685,0.000028703605,0.3595319,0.00039100033],"about_ca_topic_score_codex":0.000026175821,"about_ca_topic_score_gemma":0.0000042659863,"teacher_disagreement_score":0.48311156,"about_ca_system_score_codex":0.0009710696,"about_ca_system_score_gemma":0.0006536006,"threshold_uncertainty_score":0.9997891},"labels":[],"label_agreement":null},{"id":"W4408795740","doi":"10.1016/j.labinv.2024.103610","title":"1372 Elevating Pathologist TNM Staging Performance with AI Assistance","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; London Health Sciences Centre; Vancouver General Hospital; Western University","funders":"","keywords":"Medicine; Pathology; Radiology","score_opus":0.0071872258351668925,"score_gpt":0.22592284688365005,"score_spread":0.21873562104848315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58514494,0.00011007771,0.41061267,0.002173319,0.00040417942,0.00016139295,0.000003318782,0.00042964309,0.00096045015],"genre_scores_gemma":[0.95588905,0.000010612436,0.0404451,0.003362091,0.000058760947,0.00006625369,0.000004672962,0.000010342875,0.00015311922],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987017,0.00010504826,0.00024431283,0.00043619127,0.00027531304,0.00023745805],"domain_scores_gemma":[0.99885184,0.000050672414,0.00018080117,0.00052377034,0.0003350887,0.00005782182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044242284,0.00015257431,0.00012825993,0.0001407268,0.00032105276,0.00021093522,0.00038947377,0.00007219522,0.000003261606],"category_scores_gemma":[0.00008023461,0.00014550294,0.000014364037,0.0017565544,0.00015710398,0.0013718033,0.000076117496,0.00026238238,0.00001493003],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053747874,0.000054459324,0.7160545,0.0005590811,0.00006560681,0.00002990197,0.0026406404,0.008935695,0.078947514,0.11825736,0.006901012,0.06750048],"study_design_scores_gemma":[0.001097888,0.00032640027,0.36735532,0.00078523066,0.000034973447,0.0000069977727,0.0002590369,0.20257513,0.39950114,0.009388825,0.017738976,0.0009300752],"about_ca_topic_score_codex":0.000011261665,"about_ca_topic_score_gemma":0.00002001868,"teacher_disagreement_score":0.3707441,"about_ca_system_score_codex":0.00026030972,"about_ca_system_score_gemma":0.0004572042,"threshold_uncertainty_score":0.5933438},"labels":[],"label_agreement":null},{"id":"W4408795937","doi":"10.1016/j.labinv.2024.103822","title":"1580 Neighborhood Clustering Analysis to Define Epithelial-Stromal Interface for Tumor Infiltrating Lymphocyte Evaluation","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stromal cell; Cluster analysis; Lymphocyte; Interface (matter); Computer science; Pathology; Computational biology; Immunology; Medicine; Biology; Artificial intelligence","score_opus":0.01623950670233624,"score_gpt":0.2937445918472119,"score_spread":0.27750508514487565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26495862,0.00010993934,0.7323058,0.00092442456,0.0006844011,0.00060552964,0.000023908035,0.00019643208,0.00019096008],"genre_scores_gemma":[0.9077815,0.0000017686882,0.09017776,0.0014659485,0.000118661395,0.0003933911,0.000019412228,0.000013348581,0.000028250592],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980557,0.0002063126,0.00048171167,0.0005961518,0.0003868884,0.00027321946],"domain_scores_gemma":[0.99816966,0.00015091372,0.0002489228,0.00058019976,0.00073265994,0.00011767159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011417908,0.00019941725,0.00025060697,0.0005526712,0.00025044658,0.00027281593,0.00045418693,0.00007924461,0.000008697261],"category_scores_gemma":[0.00060651195,0.00022560604,0.000078839694,0.0038286434,0.00003906868,0.0008117894,0.00014150402,0.00010277428,0.000015756561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012784274,0.00006019335,0.019201472,0.00022967889,0.0007864282,0.0000018415794,0.0041203615,0.39180937,0.46586546,0.019622682,0.0009355021,0.097239144],"study_design_scores_gemma":[0.0005919458,0.00011801391,0.00830978,0.00007006607,0.00023275639,6.869966e-7,0.000080024656,0.80080914,0.18527436,0.003683042,0.00060891506,0.00022127118],"about_ca_topic_score_codex":0.00006171153,"about_ca_topic_score_gemma":0.00024597117,"teacher_disagreement_score":0.64282286,"about_ca_system_score_codex":0.00077916007,"about_ca_system_score_gemma":0.0007185735,"threshold_uncertainty_score":0.9199947},"labels":[],"label_agreement":null},{"id":"W4408796288","doi":"10.1016/j.labinv.2024.103849","title":"1606 Cell-Centered Deep-Learning Feature Extraction Reveals Specific Stromal Features During Intraductal Papillary Mucinous Neoplasm Progression","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal","funders":"","keywords":"Intraductal papillary mucinous neoplasm; Stromal cell; Pathology; Neoplasm; Feature (linguistics); Medicine; Internal medicine; Pancreas","score_opus":0.006259669993049259,"score_gpt":0.2362012751170511,"score_spread":0.22994160512400186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408796288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769796,0.002116541,0.014972771,0.0017121248,0.0023475662,0.0005385833,0.0000052542287,0.0008088111,0.00051874295],"genre_scores_gemma":[0.97411805,0.00019962761,0.024375994,0.00025836303,0.00044735539,0.00007058901,0.0000341905,0.00003084643,0.0004649672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997562,0.00039171425,0.00037567096,0.00078113546,0.00048116126,0.00040833387],"domain_scores_gemma":[0.99854314,0.00007492126,0.00038336086,0.0005620556,0.00027978266,0.00015672178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032106426,0.00031317456,0.00023483105,0.00032109948,0.0006182914,0.00039202205,0.0004548566,0.00031438685,0.000008908362],"category_scores_gemma":[0.000079791236,0.00033004716,0.00006465461,0.001444835,0.0001006735,0.0014472259,0.00015566868,0.00085388747,0.000022485372],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007014678,0.00006995612,0.018961465,0.00030292544,0.000035460223,0.00005939032,0.0014583709,0.0008528841,0.9488816,0.0019166042,0.0044680806,0.02292312],"study_design_scores_gemma":[0.0014073038,0.00024967236,0.2543184,0.00064477423,0.00003800171,0.000064893655,0.00034837477,0.0047283545,0.7251043,0.002609882,0.009745092,0.00074098015],"about_ca_topic_score_codex":0.0000111372865,"about_ca_topic_score_gemma":0.00001659084,"teacher_disagreement_score":0.23535691,"about_ca_system_score_codex":0.00048049723,"about_ca_system_score_gemma":0.00018849882,"threshold_uncertainty_score":0.9999152},"labels":[],"label_agreement":null},{"id":"W4408797241","doi":"10.1016/j.labinv.2024.103617","title":"1379 Digital Pathology and Artificial Intelligence-Assisted Tissue Microarray Generation Workflow","year":2025,"lang":"en","type":"article","venue":"Laboratory Investigation","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Workflow; Digital pathology; Pathology; Computer science; Artificial intelligence; Medicine; Database","score_opus":0.025613826756473324,"score_gpt":0.259745562602929,"score_spread":0.2341317358464557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408797241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20470193,0.0003110936,0.79060143,0.0022424047,0.001084596,0.00021775159,0.0000076273823,0.00023569493,0.00059746666],"genre_scores_gemma":[0.96142155,0.000018005161,0.036582083,0.0011662174,0.0002317785,0.00004806696,0.00002568028,0.000011413017,0.0004951937],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989153,0.00008589076,0.00029141782,0.0004220458,0.00013157485,0.00015376281],"domain_scores_gemma":[0.9992682,0.000045656932,0.000107964726,0.0003236098,0.00018615971,0.0000684203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020581952,0.00013160537,0.00011812487,0.00016993991,0.00017773511,0.0003727668,0.00020268201,0.0001400029,0.0000054666757],"category_scores_gemma":[0.000096836375,0.00014516007,0.00001480059,0.00081545825,0.00015896783,0.00085084705,0.000077207165,0.00013398354,0.000032567965],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006179751,0.000014932914,0.0005359634,0.000020771631,0.000014138909,0.000012006409,0.0007634912,0.00019935593,0.3275856,0.08866222,0.0012310084,0.5809543],"study_design_scores_gemma":[0.000111905574,0.00012264954,0.0023525292,0.00006553327,0.00001683079,0.000017512248,0.00005568828,0.03376936,0.7816174,0.17471083,0.006820731,0.00033904397],"about_ca_topic_score_codex":0.00000341052,"about_ca_topic_score_gemma":0.000029543206,"teacher_disagreement_score":0.75671965,"about_ca_system_score_codex":0.00013159642,"about_ca_system_score_gemma":0.00022684895,"threshold_uncertainty_score":0.5919456},"labels":[],"label_agreement":null},{"id":"W4408921799","doi":"10.1097/pai.0000000000001258","title":"Toward Accurate Deep Learning-Based Prediction of Ki67, ER, PR, and HER2 Status From H&amp;E-Stained Breast Cancer Images","year":2025,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Breast cancer; Medicine; Cancer; Oncology; Internal medicine; Gynecology; Artificial intelligence; Computer science","score_opus":0.006813031752496037,"score_gpt":0.24657730170164233,"score_spread":0.2397642699491463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408921799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4044765,0.0029817978,0.5903439,0.0005402998,0.00035259486,0.00030063817,0.000094380375,0.00021556036,0.0006943224],"genre_scores_gemma":[0.99120134,0.00015863156,0.0077341627,0.00032344097,0.000031511914,0.00028000705,0.000111539,0.000028218325,0.00013116216],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99790436,0.00008326741,0.00047236722,0.0008419036,0.00024535647,0.00045276055],"domain_scores_gemma":[0.9984332,0.00009583089,0.00034690334,0.0008331484,0.00020103464,0.00008991112],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015309158,0.0003252452,0.00040581133,0.00012568358,0.00014856049,0.00005818964,0.0005884972,0.00027683235,0.000076667566],"category_scores_gemma":[0.00004728856,0.0003762784,0.00009404062,0.00047046677,0.000337715,0.0001100841,0.0003227103,0.000468547,0.000005118222],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001799168,0.00005713529,0.00026510606,0.00007481886,0.0001196215,0.000014585812,0.00014849032,0.0024197882,0.98460776,0.00012675901,0.00024794837,0.01173808],"study_design_scores_gemma":[0.0023184905,0.000079638994,0.009084292,0.00007749767,0.00012681013,0.00004070305,0.00010034282,0.0067584678,0.97887635,0.0011491956,0.0009604661,0.00042771632],"about_ca_topic_score_codex":0.00085121416,"about_ca_topic_score_gemma":0.0000013450929,"teacher_disagreement_score":0.5867248,"about_ca_system_score_codex":0.00045371673,"about_ca_system_score_gemma":0.00031728396,"threshold_uncertainty_score":0.9998689},"labels":[],"label_agreement":null},{"id":"W4408972975","doi":"10.1093/aje/kwaf067","title":"Interactions between genetic and epidemiological factors influencing mammographic density","year":2025,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of British Columbia; BC Cancer Agency","funders":"National Cancer Institute; Medical Research Council; Ministerio de Sanidad, Servicios Sociales e Igualdad; Department of Health and Social Care; National Institute for Health and Care Research; Genome Canada; NIHR Cambridge Biomedical Research Centre; European Commission; Breast Cancer Research Foundation; Servicio Gallego de Salud; Instituto de Salud Carlos III; Amgen; Cancer Council Western Australia; Pfizer; Fondation du cancer du sein du Québec; National Institutes of Health; Ovarian Cancer Research Fund; National Health and Medical Research Council; Cancer Research UK; Xunta de Galicia; Government of Canada; Canadian Institutes of Health Research; Pharmavite","keywords":"Epidemiology; MAMMOGRAPHIC DENSITY; Medicine; Genetic epidemiology; Environmental health; Mammography; Genetics; Biology; Breast cancer; Internal medicine; Cancer","score_opus":0.041373250282705346,"score_gpt":0.3408884061418635,"score_spread":0.29951515585915817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408972975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5529379,0.00031363798,0.44408804,0.002223226,0.00034074052,0.000032596126,4.777752e-7,0.000020565218,0.000042792908],"genre_scores_gemma":[0.92688584,0.000274332,0.07107024,0.0016382969,0.000117332755,0.000002008537,2.6956138e-7,0.000004180887,0.000007475376],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966217,0.0016177899,0.0010106907,0.00032408437,0.00007919935,0.00034647848],"domain_scores_gemma":[0.99015474,0.008129754,0.0010664541,0.00031552784,0.00015829624,0.00017523205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002339662,0.00016760522,0.00090094475,0.00045642353,0.00013570058,0.000014201543,0.0005356169,0.000074225434,0.000005121046],"category_scores_gemma":[0.003901483,0.00012671824,0.0001836861,0.00067566754,0.0005862454,0.00023711889,0.00021205608,0.000611053,0.0000016866826],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010748483,0.0000073531187,0.8960295,0.0000036911883,0.000089262474,0.000005056313,0.00008655704,0.00018174408,0.000111222595,0.00190919,0.00023817546,0.10132752],"study_design_scores_gemma":[0.00011171246,0.00045344807,0.96707225,0.000040734296,0.00003996147,0.0001477868,0.0001187401,0.00081662694,0.00008439186,0.029087337,0.0019218283,0.00010521161],"about_ca_topic_score_codex":0.00029865513,"about_ca_topic_score_gemma":0.000026421394,"teacher_disagreement_score":0.37394795,"about_ca_system_score_codex":0.000129022,"about_ca_system_score_gemma":0.000095452764,"threshold_uncertainty_score":0.516742},"labels":[],"label_agreement":null},{"id":"W4408984064","doi":"10.1038/s41598-025-94806-4","title":"Multimodal contrastive learning for enhanced explainability in pediatric brain tumor molecular diagnosis","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Medicine; Neuroscience; Bioinformatics; Psychology; Biology","score_opus":0.006738988142629094,"score_gpt":0.2624814601500018,"score_spread":0.2557424720073727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408984064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50887287,0.00010754647,0.48518768,0.00041459076,0.004374806,0.00067320856,4.0145335e-7,0.00011019212,0.00025872886],"genre_scores_gemma":[0.9933514,0.0000021191736,0.0052568847,0.00008328031,0.000038326998,0.00082738063,0.0000036392892,0.000007839043,0.0004291373],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972673,0.00013625769,0.0005415392,0.0012824878,0.00035090797,0.0004214972],"domain_scores_gemma":[0.9981711,0.00045289838,0.00027665184,0.00073715666,0.00029104634,0.00007114175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024546112,0.0001554038,0.0002231352,0.00042169142,0.0003112472,0.00032144345,0.00035276133,0.000062159954,0.000007073545],"category_scores_gemma":[0.0025162152,0.00016558378,0.00011408991,0.0016731344,0.00011009711,0.00043530783,0.00019268037,0.00019475579,0.000003203916],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020842129,0.0011748311,0.45458406,0.001136863,0.00010474822,0.0017470159,0.012072477,0.083304405,0.1686871,0.0056538573,0.01766857,0.25365767],"study_design_scores_gemma":[0.0013275779,0.00022269566,0.053480405,0.00012981638,0.00003457444,0.000038258877,0.00028394136,0.08892703,0.76508445,0.077892184,0.011819733,0.00075933506],"about_ca_topic_score_codex":0.000049825154,"about_ca_topic_score_gemma":0.000059334117,"teacher_disagreement_score":0.59639734,"about_ca_system_score_codex":0.00033169435,"about_ca_system_score_gemma":0.0004118789,"threshold_uncertainty_score":0.67523104},"labels":[],"label_agreement":null},{"id":"W4409098678","doi":"10.1109/tai.2025.3556990","title":"A Cervical Cell Classification Framework Based on Multiview Supervised Contrastive Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Supervised learning; Natural language processing; Artificial neural network","score_opus":0.04593820595481749,"score_gpt":0.30938432836576346,"score_spread":0.26344612241094595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409098678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012886992,0.000027824675,0.9922366,0.002041337,0.0018735824,0.00045554945,0.0000057770844,0.0004409124,0.001629712],"genre_scores_gemma":[0.98114884,0.00003848215,0.017383058,0.0009988779,0.000054881788,0.00017415054,0.0000011323251,0.00001821915,0.00018238385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976157,0.00030272073,0.0005027118,0.0007892599,0.00041331965,0.00037627795],"domain_scores_gemma":[0.997725,0.0011958187,0.00011506293,0.0006475,0.00020308267,0.00011350209],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036583352,0.00027424708,0.00024804554,0.0004007881,0.0005410942,0.00021107071,0.00065345253,0.00023596329,0.00014547852],"category_scores_gemma":[0.00006341526,0.00028771153,0.00018234448,0.0014912655,0.00012785134,0.00026869468,0.0000040797577,0.0010128967,0.0004402721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021260754,0.0006357639,0.000012741262,0.000043131404,0.000020069145,0.000004381125,0.0005040592,0.2709102,0.0050112847,0.01337052,0.000023274726,0.709252],"study_design_scores_gemma":[0.000055886576,0.00025666397,0.000093143346,0.00016124586,0.000017609316,5.183995e-7,0.00014718717,0.72802013,0.2661157,0.004620768,0.00031277075,0.00019833849],"about_ca_topic_score_codex":0.000053479467,"about_ca_topic_score_gemma":0.00005062919,"teacher_disagreement_score":0.9798601,"about_ca_system_score_codex":0.0003241064,"about_ca_system_score_gemma":0.00019905472,"threshold_uncertainty_score":0.9999575},"labels":[],"label_agreement":null},{"id":"W4409099006","doi":"10.3390/bioengineering12040377","title":"Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Convolutional neural network; Pathology; Lung cancer; Classifier (UML); Lung; Artificial intelligence; Medicine; Computer science; Radiology; Internal medicine","score_opus":0.008171835007880263,"score_gpt":0.22286123084428183,"score_spread":0.21468939583640156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409099006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47667822,0.00031773502,0.52240986,0.000036850503,0.0003249502,0.000059147947,4.3260428e-7,0.000033153658,0.00013967614],"genre_scores_gemma":[0.9884132,5.9355926e-7,0.011527069,0.000011124271,0.00003198334,0.0000060633806,3.8551235e-7,0.0000041426338,0.0000054333273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938345,0.000029700785,0.00018720556,0.00016121764,0.00009941367,0.0001390369],"domain_scores_gemma":[0.99962676,0.00010037733,0.000053154214,0.00017021562,0.00003781499,0.000011656644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018646744,0.00006796258,0.00008168757,0.00019065631,0.00004987924,0.000015938986,0.00024244074,0.000043345393,4.4640748e-7],"category_scores_gemma":[0.000022600203,0.00006456813,0.000026235102,0.0005460073,0.000020340585,0.00012463909,0.00011810679,0.00010683759,3.5459564e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002435219,0.000011392736,0.03224657,0.00007237252,0.0000020963869,0.0000039305082,0.00042962143,0.9351295,0.028535679,0.0029327816,0.000008209811,0.0006253829],"study_design_scores_gemma":[0.00015659306,0.000013262329,0.07337672,0.000019395553,0.0000036162344,0.0000084586545,0.00004876393,0.91987544,0.0061904564,0.00025415476,0.000005781891,0.000047350084],"about_ca_topic_score_codex":0.00015022888,"about_ca_topic_score_gemma":0.000015530539,"teacher_disagreement_score":0.51173496,"about_ca_system_score_codex":0.00037917116,"about_ca_system_score_gemma":0.00009022084,"threshold_uncertainty_score":0.2633012},"labels":[],"label_agreement":null},{"id":"W4409148359","doi":"10.1038/s41598-025-89210-x","title":"Investigation on potential bias factors in histopathology datasets","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Brock University; Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Digital pathology; Metric (unit); Machine learning; Precision medicine; Deep learning; Pattern recognition (psychology); Artificial neural network; Data mining; Pathology; Medicine","score_opus":0.04264991251651127,"score_gpt":0.267237179877191,"score_spread":0.22458726736067972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409148359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081691,0.000051145602,0.05384455,0.0008148122,0.035388038,0.00027852357,0.00000416747,0.00018478271,0.0012648992],"genre_scores_gemma":[0.9974112,9.0161024e-7,0.0013323496,0.0001417624,0.000022316577,0.0000149763355,0.00006688008,0.0000039028946,0.0010057418],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980089,0.000106741754,0.00039702,0.00090617355,0.00035261092,0.0002285532],"domain_scores_gemma":[0.99842465,0.00003705257,0.00019926988,0.0012312619,0.000053234606,0.000054508804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012521502,0.000109187415,0.00012417612,0.0006197232,0.00020233238,0.00025335164,0.00036362885,0.000073835974,0.000011522418],"category_scores_gemma":[0.00022963765,0.000104252875,0.000039345352,0.0012496988,0.00017299085,0.0004349919,0.00019070646,0.00014954292,0.000017271166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003809565,0.00033916737,0.21051294,0.00013780531,0.00002554017,0.004638379,0.0038390285,0.00742349,0.2976426,0.021776656,0.38163528,0.07199104],"study_design_scores_gemma":[0.0004945271,0.00016192866,0.17144844,0.00021201384,0.00001869653,0.0003240396,0.00009055222,0.021492641,0.41595426,0.23697935,0.15212077,0.0007027612],"about_ca_topic_score_codex":0.000096577,"about_ca_topic_score_gemma":0.00010114648,"teacher_disagreement_score":0.22951451,"about_ca_system_score_codex":0.00025650614,"about_ca_system_score_gemma":0.00026025702,"threshold_uncertainty_score":0.42513087},"labels":[],"label_agreement":null},{"id":"W4409157115","doi":"10.1126/sciadv.ads4593","title":"FairDiffusion: Enhancing equity in latent diffusion models via fair Bayesian perturbation","year":2025,"lang":"en","type":"article","venue":"Science Advances","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Eye Institute","keywords":"Generative grammar; Computer science; Equity (law); Generative model; Health equity; Bayesian probability; Machine learning; Modalities; Artificial intelligence; Health care; Data science; Political science; Sociology","score_opus":0.014952257858875698,"score_gpt":0.30426833868134867,"score_spread":0.28931608082247295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409157115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036979876,0.00062607793,0.95351195,0.0011463334,0.0015818974,0.00024172268,3.7977483e-7,0.00018542439,0.005726306],"genre_scores_gemma":[0.9784643,0.00009045553,0.02068336,0.00031558133,0.000038496808,0.000037702564,4.1252363e-7,0.0000043463433,0.00036536192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975508,0.000049520746,0.00034146954,0.00083198416,0.00072841346,0.0004978055],"domain_scores_gemma":[0.99900407,0.0000792876,0.00012077083,0.00057115225,0.00013655647,0.00008817093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009428873,0.0001634479,0.00017480801,0.00051982445,0.00050609827,0.00022764961,0.0014241406,0.000057909576,0.0000074139793],"category_scores_gemma":[0.000086082415,0.00014644828,0.00004567536,0.0030092122,0.00026145598,0.0048084566,0.0009342696,0.00018283434,0.000009590246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000134155225,0.00007397438,0.00089625496,0.00004220307,0.0000016074358,0.0000048913294,0.0012341656,0.021093873,0.1280065,0.021404853,0.000015601643,0.8272127],"study_design_scores_gemma":[0.00026612857,0.000070214635,0.003422545,0.00016117522,0.0000021116293,0.0000041572835,0.00011819128,0.7016306,0.071899846,0.22185183,0.00035481775,0.00021838976],"about_ca_topic_score_codex":0.0000790727,"about_ca_topic_score_gemma":0.00037774706,"teacher_disagreement_score":0.9414844,"about_ca_system_score_codex":0.0006622409,"about_ca_system_score_gemma":0.00032920306,"threshold_uncertainty_score":0.5971987},"labels":[],"label_agreement":null},{"id":"W4409180185","doi":"10.1007/978-981-96-3863-5_27","title":"Patch-Level Up-Sampling for Multi-instance Learning in H&amp;E Tissue Micro-Array Based Recurrence Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sampling (signal processing); Computer science; Artificial intelligence; Pattern recognition (psychology); Biomedical engineering; Materials science; Engineering; Computer vision","score_opus":0.034680461237951654,"score_gpt":0.27057491423697194,"score_spread":0.2358944529990203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409180185","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002691971,0.002657153,0.99425143,0.00015427124,0.0014718116,0.0007614184,0.000018312034,0.00043290964,0.00022578689],"genre_scores_gemma":[0.06212213,0.00033572625,0.93232715,0.0002396917,0.00054513186,0.0003729064,0.00007997777,0.00016694465,0.0038103706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971798,0.000032810305,0.0006585317,0.0010919222,0.00033818334,0.00069872354],"domain_scores_gemma":[0.9979492,0.0011456308,0.00020029952,0.00048936874,0.00013057422,0.00008494618],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040724222,0.00056333444,0.0005874649,0.0009832586,0.00010719391,0.000103461716,0.00069430395,0.00076892134,0.0000057776874],"category_scores_gemma":[0.0012595447,0.0006579786,0.00013951412,0.0007736807,0.000022267594,0.00019457082,0.0000793907,0.0021792836,0.0000045165457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049393584,0.000025557632,0.00009789361,0.0003997158,0.00002595553,0.0000068149325,0.00020386491,0.6215872,0.011302302,0.0013732823,0.000024822755,0.36490318],"study_design_scores_gemma":[0.0008536914,0.00015760209,0.00010195065,0.0014580573,0.000017678904,0.000008150039,2.2963721e-7,0.94942373,0.016990848,0.0016010319,0.028674487,0.000712535],"about_ca_topic_score_codex":0.000046790155,"about_ca_topic_score_gemma":0.00022681041,"teacher_disagreement_score":0.36419064,"about_ca_system_score_codex":0.0013453538,"about_ca_system_score_gemma":0.00030535823,"threshold_uncertainty_score":0.9995871},"labels":[],"label_agreement":null},{"id":"W4409185342","doi":"10.1117/12.3048961","title":"Predicting response to therapy in pancreatic ductal adenocarcinoma using convolutional neural networks","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Pancreatic ductal adenocarcinoma; Convolutional neural network; Computer science; Artificial intelligence; Internal medicine; Medicine; Pancreatic cancer; Cancer","score_opus":0.021982263736549688,"score_gpt":0.2735686799673633,"score_spread":0.25158641623081357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409185342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5922362,0.00022313381,0.4059515,0.0007298622,0.0004975433,0.00015060227,2.4990047e-7,0.000087579254,0.00012332831],"genre_scores_gemma":[0.9873421,0.00000439447,0.011511166,0.0008463247,0.00009298128,0.000022517106,2.811561e-7,0.0000056607755,0.00017456111],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987961,0.000193165,0.00022302028,0.00035214802,0.0001659851,0.00026960418],"domain_scores_gemma":[0.9993111,0.00025107551,0.00003781378,0.00029799802,0.00005166817,0.00005033875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046287323,0.00010687743,0.000121568366,0.00023917094,0.000116707124,0.000087225955,0.00036822897,0.000057119374,0.000012488132],"category_scores_gemma":[0.000064505846,0.00010512158,0.000034846686,0.0009812218,0.000027367365,0.00030202416,0.00017604697,0.0001548253,0.000002623201],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008234454,0.00004072173,0.79857665,0.0000064015103,0.000029673287,0.000030829084,0.00059446803,0.18222794,0.005681691,0.0027288035,0.00024901392,0.0090103755],"study_design_scores_gemma":[0.00027539156,0.00007605856,0.3298563,0.000019574265,0.0000014310546,0.000018113453,0.000026006968,0.66919315,0.00023113748,0.00020861805,0.000026528176,0.00006768805],"about_ca_topic_score_codex":0.00030798843,"about_ca_topic_score_gemma":0.000053148244,"teacher_disagreement_score":0.4869652,"about_ca_system_score_codex":0.00031368915,"about_ca_system_score_gemma":0.00013929504,"threshold_uncertainty_score":0.42867336},"labels":[],"label_agreement":null},{"id":"W4409229222","doi":"10.1093/jncics/pkaf037","title":"Deep learning analysis of hematoxylin and eosin-stained benign breast biopsies to predict future invasive breast cancer","year":2025,"lang":"en","type":"article","venue":"JNCI Cancer Spectrum","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Division of Cancer Epidemiology and Genetics, National Cancer Institute; National Cancer Institute; National Institutes of Health; Breast Cancer Research Foundation","keywords":"Medicine; H&E stain; Pathological; Receiver operating characteristic; Breast cancer; Logistic regression; Diagnostic accuracy; Disease; Pathology; Artificial intelligence; Cancer; Internal medicine; Computer science; Immunohistochemistry","score_opus":0.004232689961310168,"score_gpt":0.24196779790207032,"score_spread":0.23773510794076014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409229222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6473903,0.0076078884,0.29118747,0.046873312,0.0035612793,0.0011065828,0.00034794465,0.0006603329,0.0012648747],"genre_scores_gemma":[0.9961465,0.0010466852,0.0013518969,0.00045426693,0.0004125871,0.00016563093,0.0000050444123,0.000020564445,0.00039681353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977335,0.00009299927,0.00043937954,0.0008162054,0.00043449408,0.00048345773],"domain_scores_gemma":[0.99863434,0.00010166687,0.00027049117,0.0006040121,0.00022235,0.0001671547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022786837,0.00030507013,0.0006226819,0.0009336534,0.00024371284,0.0001530512,0.0006584818,0.00013940955,0.00013776857],"category_scores_gemma":[0.000020407324,0.00029475774,0.00017177025,0.004509466,0.000098653196,0.0004048197,0.00040315848,0.0003100379,0.0000027503054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006270514,0.00017670635,0.6152224,0.000644776,0.005338766,0.00004084354,0.008549941,0.107829824,0.006169863,0.016336361,0.0030186696,0.23604481],"study_design_scores_gemma":[0.0009672694,0.00019091589,0.85900986,0.0003932164,0.0009705201,0.000055097888,0.0010720862,0.118446246,0.015040579,0.0010714433,0.0020745993,0.000708168],"about_ca_topic_score_codex":0.0038860184,"about_ca_topic_score_gemma":0.012875428,"teacher_disagreement_score":0.3487562,"about_ca_system_score_codex":0.0006763639,"about_ca_system_score_gemma":0.00044616792,"threshold_uncertainty_score":0.99995047},"labels":[],"label_agreement":null},{"id":"W4409259105","doi":"10.1016/j.modpat.2025.100767","title":"Spatially Resolved Single-Cell Morphometry of Benign Breast Disease Biopsy Images Uncovers Quantitative Cytomorphometric Features Predictive of Subsequent Invasive Breast Cancer Risk","year":2025,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"U.S. Department of Health and Human Services; National Cancer Institute; National Institutes of Health; Division of Cancer Epidemiology and Genetics, National Cancer Institute; Kaiser Permanente; Breast Cancer Research Foundation","keywords":"Breast cancer; Medicine; Biopsy; Pathology; Disease; Cancer; Internal medicine","score_opus":0.012527877926647533,"score_gpt":0.2462412282863282,"score_spread":0.23371335035968066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409259105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4175987,0.002072656,0.5763588,0.00032375858,0.0006239415,0.0004022113,0.0022987064,0.000085096115,0.00023614052],"genre_scores_gemma":[0.98822564,0.00036136303,0.011054677,0.00009094551,0.000036098394,0.00008369804,0.00002045702,0.000025833739,0.00010128955],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970144,0.0005016874,0.00058973307,0.0009455839,0.00050808466,0.00044048167],"domain_scores_gemma":[0.9967284,0.0006232814,0.00081620616,0.0009097891,0.000773507,0.0001488123],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004083664,0.00034833027,0.0006232968,0.0013292745,0.0001302094,0.00004143948,0.0009287848,0.00020309522,0.000019398529],"category_scores_gemma":[0.00028219513,0.00034053516,0.00021130106,0.0024597528,0.00055388897,0.00040092823,0.00047434878,0.00036269933,0.00000319341],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048124124,0.0021571727,0.34280834,0.000966324,0.00077808154,0.0006601251,0.005648504,0.080370404,0.5067662,0.0022293061,0.0011983253,0.05160482],"study_design_scores_gemma":[0.0026120462,0.0008944349,0.7761895,0.00032882564,0.00035938228,0.00019349606,0.00025085142,0.02618164,0.1834833,0.008911578,0.00000960534,0.00058535556],"about_ca_topic_score_codex":0.0015380669,"about_ca_topic_score_gemma":0.00023101365,"teacher_disagreement_score":0.5706269,"about_ca_system_score_codex":0.0004907326,"about_ca_system_score_gemma":0.00078245805,"threshold_uncertainty_score":0.9999047},"labels":[],"label_agreement":null},{"id":"W4409259931","doi":"10.1371/journal.pdig.0000811","title":"Subgroup evaluation to understand performance gaps in deep learning-based classification of regions of interest on mammography","year":2025,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Cancer Institute","keywords":"False positive paradox; Medicine; Mammography; Univariate; Artificial intelligence; Multivariate statistics; Subgroup analysis; Convolutional neural network; Breast cancer; Internal medicine; Computer science; Machine learning; Confidence interval; Cancer","score_opus":0.09049813221488646,"score_gpt":0.3237286303025327,"score_spread":0.23323049808764623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409259931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74279684,0.00008462475,0.25325346,0.0016950938,0.00012316875,0.0005092895,0.0000032035166,0.0000485509,0.0014857885],"genre_scores_gemma":[0.99929917,0.000018792238,0.00047232036,0.00015041628,0.0000067009755,0.000026019141,0.000007763751,0.000005260762,0.000013567396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988263,0.00008986925,0.0003628111,0.0002651888,0.00028057612,0.00017522537],"domain_scores_gemma":[0.99913967,0.00013078975,0.00020730123,0.00032486123,0.00014479642,0.000052604013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004217987,0.00008369314,0.00015541064,0.0005832629,0.000056360856,0.00003490639,0.00025017114,0.000039919607,0.0000013847633],"category_scores_gemma":[0.00009118502,0.00008808451,0.000037025005,0.0013147566,0.000043801374,0.00038095276,0.000040496765,0.00013491149,0.0000031788886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061918853,0.0016297962,0.10083883,0.00196428,0.000054449632,6.5630053e-7,0.003998563,0.04031823,0.0007397179,0.06437298,0.00036741712,0.7850959],"study_design_scores_gemma":[0.00107184,0.00268516,0.26936892,0.0015410377,0.000007906147,6.261854e-7,0.0006019221,0.7141212,0.00504507,0.0051939697,0.00016796704,0.00019435934],"about_ca_topic_score_codex":0.000028977765,"about_ca_topic_score_gemma":0.00029791743,"teacher_disagreement_score":0.78490156,"about_ca_system_score_codex":0.00047372995,"about_ca_system_score_gemma":0.00027960096,"threshold_uncertainty_score":0.3591982},"labels":[],"label_agreement":null},{"id":"W4409449502","doi":"10.1016/j.semdp.2025.150905","title":"An adapted &amp; improved validation protocol for digital pathology implementation","year":2025,"lang":"en","type":"review","venue":"Seminars in Diagnostic Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Digital pathology; Pathology; Protocol (science); Computer science; Medicine","score_opus":0.04618372960825541,"score_gpt":0.4162019781658773,"score_spread":0.3700182485576219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409449502","genre_codex":"methods","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008279735,0.2286276,0.5428628,0.000088700064,0.0015305132,0.22602333,0.00035086856,0.00035955527,0.00014838346],"genre_scores_gemma":[0.000007655368,0.3491614,0.023203343,0.00007309524,0.00017093668,0.6265108,0.00075540564,0.000049452374,0.00006792572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958054,0.0006001494,0.0013327787,0.0014160008,0.00018910036,0.000656617],"domain_scores_gemma":[0.99326634,0.004334897,0.00086441275,0.0012785527,0.00016457021,0.000091205315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009535468,0.0005666252,0.0012901695,0.0007868166,0.00012205622,0.00017492623,0.001332582,0.0007108155,0.000018925286],"category_scores_gemma":[0.0027335773,0.00057156535,0.0002582529,0.0008891844,0.000100476216,0.00065317313,0.00037234862,0.0004447315,0.000025115616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011198446,0.00012374322,0.000034818273,0.0034467704,0.000013309738,0.000067539615,0.00015147308,0.000007864332,0.00000768233,0.00048184948,0.00061052595,0.9950432],"study_design_scores_gemma":[0.0016985278,0.0012945151,0.00003633438,0.009259953,0.00016795419,0.00050199794,0.00003521805,0.00036330818,0.00008700374,0.0059777605,0.9796455,0.000931926],"about_ca_topic_score_codex":0.00000989982,"about_ca_topic_score_gemma":0.00006955338,"teacher_disagreement_score":0.9941113,"about_ca_system_score_codex":0.00053970265,"about_ca_system_score_gemma":0.00076533295,"threshold_uncertainty_score":0.9996736},"labels":[],"label_agreement":null},{"id":"W4409450173","doi":"10.1016/j.inffus.2025.103180","title":"TinyVit-LightGBM: A lightweight and smart feature fusion framework for IoMT-based cancer diagnosis","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Brandon University","funders":"Guangxi Medical University","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.008306047253932252,"score_gpt":0.2639217185502225,"score_spread":0.25561567129629026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409450173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014668858,0.00040732336,0.962063,0.018331137,0.0022415211,0.0007817192,0.000027288595,0.00030983178,0.0011692998],"genre_scores_gemma":[0.70474803,0.0011606491,0.2707296,0.017834704,0.0004574437,0.004119467,0.000108377826,0.00003173896,0.00080996426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887174,0.000031956126,0.0003166371,0.0002491131,0.0002877825,0.00024277795],"domain_scores_gemma":[0.99878806,0.00027955443,0.0002139892,0.00040615804,0.00023759011,0.00007465622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023715214,0.00018305586,0.00016999677,0.00036266807,0.00038528966,0.0002975332,0.00035575364,0.00026200837,0.000039910028],"category_scores_gemma":[0.000117175376,0.00016106428,0.00007224263,0.00076201063,0.000030959498,0.0014412603,0.00019195954,0.00020313253,0.000022286005],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016284955,0.00006614942,0.008533259,0.00046660137,0.000032551678,7.615207e-7,0.0015275923,0.00036175986,0.00058088335,0.05814631,0.10705547,0.8230658],"study_design_scores_gemma":[0.0013969186,0.00017497304,0.01733363,0.0007392965,0.000033505465,0.0000016973419,0.00004539675,0.14920776,0.029364862,0.016083008,0.7852191,0.00039985808],"about_ca_topic_score_codex":0.00007650347,"about_ca_topic_score_gemma":0.00004146524,"teacher_disagreement_score":0.8226659,"about_ca_system_score_codex":0.00018666466,"about_ca_system_score_gemma":0.00015170385,"threshold_uncertainty_score":0.6568011},"labels":[],"label_agreement":null},{"id":"W4409503873","doi":"10.1148/ryai.250125","title":"Beyond Double Reading: Multiple Deep Learning Models Enhancing Radiologist-led Breast Screening","year":2025,"lang":"en","type":"letter","venue":"Radiology Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre intégré de santé et de services sociaux de Chaudière-Appalaches","funders":"","keywords":"Reading (process); Computer science; Deep learning; Medicine; Medical physics; Radiology; Artificial intelligence; Linguistics","score_opus":0.05101416837256416,"score_gpt":0.28152450101798093,"score_spread":0.23051033264541676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409503873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008814906,0.0006493811,0.92119884,0.06961906,0.0041845418,0.00060344033,0.000011992969,0.00089792506,0.0027466398],"genre_scores_gemma":[0.38669476,0.0013211629,0.25000423,0.32344395,0.025038878,0.0013557307,0.00063426635,0.0004586455,0.0110483775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99339294,0.0008489845,0.0014329173,0.0022821294,0.0005072854,0.0015357184],"domain_scores_gemma":[0.9952337,0.001969171,0.00078686577,0.0014930732,0.00037171145,0.00014545661],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0014432217,0.00087116484,0.0012064438,0.000830584,0.00094017206,0.00035602457,0.0030030662,0.0021519146,0.00009751633],"category_scores_gemma":[0.00034417753,0.0009360505,0.00040855422,0.0011570172,0.0005511745,0.0008474929,0.0007790273,0.005195661,0.00020606734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043241042,0.000077277735,0.00016970081,0.0003080117,0.00060577993,0.0009971892,0.0025251533,0.38294622,0.002664692,0.039566446,0.10633963,0.4633675],"study_design_scores_gemma":[0.00014094204,0.0002501845,0.000011471276,0.00025002516,0.00008757089,0.0010162136,0.00013204265,0.89621145,0.013640177,0.05176283,0.03519385,0.0013032277],"about_ca_topic_score_codex":0.00040755665,"about_ca_topic_score_gemma":0.00018437786,"teacher_disagreement_score":0.6711946,"about_ca_system_score_codex":0.00061906874,"about_ca_system_score_gemma":0.0003097409,"threshold_uncertainty_score":0.999309},"labels":[],"label_agreement":null},{"id":"W4409605504","doi":"10.2196/70924","title":"Using a Large Language Model for Breast Imaging Reporting and Data System Classification and Malignancy Prediction to Enhance Breast Ultrasound Diagnosis: Retrospective Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"BI-RADS; Preprint; Malignancy; Breast imaging; Ultrasound; Medicine; Computer science; Radiology; Mammography; Breast cancer; Pathology; Cancer; World Wide Web; Internal medicine","score_opus":0.031036924711424666,"score_gpt":0.3650558444411161,"score_spread":0.33401891972969144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409605504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23589411,0.00006696583,0.7622509,0.00023026543,0.00019088738,0.0009806906,0.00014519997,0.00016440736,0.000076582815],"genre_scores_gemma":[0.9777837,0.000013256464,0.021589909,0.0001836731,0.000080865546,0.0003132244,0.000014279593,0.000008708222,0.0000124242515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780285,0.000039959978,0.0010324043,0.00037221686,0.00048812394,0.00026444206],"domain_scores_gemma":[0.99821895,0.00010319153,0.00062870135,0.00073857186,0.00016528864,0.00014527544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017852446,0.00014968318,0.00024993232,0.0001565876,0.00027993124,0.00025309928,0.00045800427,0.000081049446,9.30104e-7],"category_scores_gemma":[0.00043892083,0.00014133111,0.00002035718,0.00041438674,0.000041462416,0.0013374119,0.00054403325,0.0001896605,6.3920817e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012780452,0.00073584466,0.4402355,0.003823952,0.00028316752,0.000031164196,0.10376683,0.0004164152,0.00082294864,0.00667208,0.0026436313,0.44044065],"study_design_scores_gemma":[0.00035512488,0.00003192514,0.039947607,0.00075352617,0.00003115503,0.0002855996,0.0096013285,0.94875515,0.000034453267,0.00007400856,0.000013013421,0.00011710065],"about_ca_topic_score_codex":0.000030467185,"about_ca_topic_score_gemma":0.000034990942,"teacher_disagreement_score":0.94833875,"about_ca_system_score_codex":0.0002838909,"about_ca_system_score_gemma":0.00016553538,"threshold_uncertainty_score":0.57633156},"labels":[],"label_agreement":null},{"id":"W4409629442","doi":"10.1158/1538-7445.am2025-2435","title":"Abstract 2435: Automatic detection of prostate cancer in 3D pathology datasets based on synthetic immunolabeling of cytokeratins","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Immunolabeling; Pathology; Prostate cancer; Prostate; Cancer; Medicine; Internal medicine; Immunohistochemistry","score_opus":0.03515513617067792,"score_gpt":0.37998604888797954,"score_spread":0.3448309127173016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409629442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836186,0.0013234409,0.012154846,0.0007167973,0.0007902735,0.0008542058,0.00020020656,0.0000696314,0.0002719762],"genre_scores_gemma":[0.9984697,0.00028320486,0.00068470865,0.000042474265,0.000020669817,0.00045605123,0.0000040634236,0.000012138564,0.000027001186],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99773616,0.0003281475,0.00048333866,0.00048527398,0.00055539113,0.00041170232],"domain_scores_gemma":[0.9982497,0.00045340802,0.00016205062,0.00081049494,0.00028580875,0.000038531936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015674077,0.00013264568,0.00026960872,0.000852119,0.000118206546,0.00004172513,0.0006850576,0.00010278483,0.00006043383],"category_scores_gemma":[0.00021910186,0.00013040741,0.000040767016,0.0016836001,0.00019210982,0.0002363808,0.00019245154,0.00054854923,0.0000058409037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018913628,0.0001494905,0.0011603708,0.0008716279,0.00002565055,0.00001695257,0.00052513496,0.021235399,0.55756277,0.00012433699,0.00009259995,0.4180465],"study_design_scores_gemma":[0.0009761807,0.00026488112,0.02475183,0.0017428098,0.000007132296,0.0000014682776,0.00005583522,0.25786987,0.71359724,0.00036566652,0.0002185416,0.00014854742],"about_ca_topic_score_codex":0.0021260649,"about_ca_topic_score_gemma":0.0011055545,"teacher_disagreement_score":0.41789797,"about_ca_system_score_codex":0.00072870863,"about_ca_system_score_gemma":0.00092461443,"threshold_uncertainty_score":0.53178596},"labels":[],"label_agreement":null},{"id":"W4409651419","doi":"10.23977/jaip.2025.080206","title":"A two-stage cervical pathology cell detection model based on YOLOv7x and K-means","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stage (stratigraphy); Pathology; Medicine; Computer science; Biology; Paleontology","score_opus":0.03386071167995914,"score_gpt":0.3352474627157263,"score_spread":0.3013867510357672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409651419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006232187,0.00009685001,0.9827237,0.0066241585,0.001170438,0.0001194064,0.0000010958164,0.000038765094,0.0029933657],"genre_scores_gemma":[0.8809064,0.000074159325,0.1165115,0.002280135,0.00013108963,0.000005041651,9.202991e-8,0.000008863027,0.00008273865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998018,0.00033952942,0.0006673311,0.00033492505,0.000395116,0.00024507777],"domain_scores_gemma":[0.9973961,0.0010247731,0.0006234126,0.00036080426,0.00048936106,0.000105522326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016039801,0.00016296022,0.00022669048,0.0004264276,0.00019445016,0.00021776218,0.0004964727,0.00012549461,0.000011866146],"category_scores_gemma":[0.0008858676,0.0001530328,0.0000965336,0.0006212576,0.00009059241,0.0011498948,0.000106376734,0.0007451166,0.000021268994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012522844,0.0005749025,0.00003112569,0.000048726644,0.000032188993,0.00019918995,0.0010855045,0.4989956,0.02237387,0.030907875,0.00008287223,0.44441584],"study_design_scores_gemma":[0.00009446467,0.00058687764,0.000017255294,0.000031082862,0.000038315065,0.00009565983,0.00040295714,0.8776072,0.10672971,0.012881523,0.0013974973,0.00011743101],"about_ca_topic_score_codex":0.000036957907,"about_ca_topic_score_gemma":0.000040675983,"teacher_disagreement_score":0.8746742,"about_ca_system_score_codex":0.00019503737,"about_ca_system_score_gemma":0.00029057433,"threshold_uncertainty_score":0.62404966},"labels":[],"label_agreement":null},{"id":"W4409768228","doi":"10.1007/s00292-025-01429-7","title":"Foundation Modelle in der Pathologie","year":2025,"lang":"en","type":"review","venue":"Die Pathologie","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Foundation (evidence); Philosophy; Political science","score_opus":0.11883986192703076,"score_gpt":0.3872419784034829,"score_spread":0.2684021164764521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409768228","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.4266926e-7,0.7121224,0.28231898,0.00006210897,0.0014141648,0.0005308974,0.0000068453787,0.00034551197,0.0031981512],"genre_scores_gemma":[0.000016663369,0.9819038,0.016864244,0.000106459054,0.00008336153,0.0005475983,0.0000344321,0.000022550568,0.00042089078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99703574,0.00044451532,0.00068017986,0.0010960222,0.00024623933,0.00049730076],"domain_scores_gemma":[0.99777853,0.00046746797,0.00031099902,0.0013262826,0.00007179912,0.000044895478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076224486,0.00044555432,0.0011223523,0.00057933974,0.00010119059,0.00014216622,0.0016385746,0.00056774047,0.000009558994],"category_scores_gemma":[0.0004338311,0.00038752164,0.0003073448,0.000966842,0.000068996575,0.00037366536,0.000988063,0.0006495389,0.00024955135],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.5728465e-7,0.000029293837,0.0000055394808,0.002135067,0.000007824818,0.00017875028,0.000038617367,0.000067320405,2.183464e-7,0.0007324328,0.00018804632,0.996616],"study_design_scores_gemma":[0.0001992209,0.00009075555,0.000030670715,0.005375977,0.000105665735,0.00004840446,0.000008235715,0.0021761404,0.000006844333,0.011565907,0.97967654,0.00071564806],"about_ca_topic_score_codex":0.000013104523,"about_ca_topic_score_gemma":0.000025280318,"teacher_disagreement_score":0.9959004,"about_ca_system_score_codex":0.0006781045,"about_ca_system_score_gemma":0.00066882675,"threshold_uncertainty_score":0.99985766},"labels":[],"label_agreement":null},{"id":"W4409786770","doi":"10.1097/01.gox.0001112524.79751.30","title":"144. A Video-based Learning Module in an Effective Way to Teach the Interpretation of Pre-operative Electrodiagnostic Studies","year":2025,"lang":"en","type":"article","venue":"Plastic & Reconstructive Surgery Global Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph's Hospital","funders":"","keywords":"Interpretation (philosophy); Computer science; Multimedia; Artificial intelligence; Mathematics education; Psychology; Programming language","score_opus":0.012865983006923015,"score_gpt":0.31264553734481904,"score_spread":0.29977955433789605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409786770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6400057,0.00013805795,0.35686487,0.00022695951,0.0010804874,0.0012273594,0.0000107681435,0.000048355116,0.00039740163],"genre_scores_gemma":[0.99477017,0.000007589882,0.004345884,0.0001721614,0.000021952308,0.00066009257,0.0000028810919,0.000007580634,0.000011685653],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971216,0.0010634391,0.00050750014,0.00071882806,0.00024346336,0.00034517606],"domain_scores_gemma":[0.99116033,0.0077249296,0.0002463431,0.00037886412,0.00042408268,0.00006546048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011565441,0.00025061643,0.00057223224,0.00028037027,0.00020785148,0.00021006717,0.000858321,0.00006910055,0.0000065017266],"category_scores_gemma":[0.00547672,0.00020301147,0.00008496935,0.0016964328,0.00019699469,0.0009739388,0.00047174987,0.0003064058,0.000007647084],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015784061,0.00018245696,0.23046933,0.00008882763,0.00038978225,0.000012803146,0.0037767694,0.14883591,0.00055204757,0.007288434,0.00035503195,0.60647017],"study_design_scores_gemma":[0.0010152076,0.0011645287,0.6395569,0.0015691,0.00008085748,0.000023535129,0.0015786093,0.32847267,0.013361309,0.0125124175,0.00009004926,0.00057484355],"about_ca_topic_score_codex":0.00035004746,"about_ca_topic_score_gemma":0.0011155437,"teacher_disagreement_score":0.60589534,"about_ca_system_score_codex":0.0009869542,"about_ca_system_score_gemma":0.00034070294,"threshold_uncertainty_score":0.8278568},"labels":[],"label_agreement":null},{"id":"W4409944483","doi":"10.1016/j.jpi.2025.100426","title":"Erratum to “MiNuGAN: Dual segmentation of mitoses and nuclei using conditional GANs on multi-center breast H&amp;E images” [Journal of Pathology Informatics Volume 13, 2022, 100002]","year":2025,"lang":"en","type":"erratum","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto Metropolitan University","funders":"Ryerson University","keywords":"Computer science; Center (category theory); Volume (thermodynamics); Segmentation; Dual (grammatical number); Informatics; Information retrieval; Artificial intelligence; Chemistry; Physics; Crystallography; Linguistics; Philosophy","score_opus":0.01795409713291108,"score_gpt":0.2833186146243428,"score_spread":0.26536451749143175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409944483","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078918844,0.00038518332,0.8833562,0.0007254622,0.03404304,0.00052733795,0.0007839482,0.000032528777,0.0012274395],"genre_scores_gemma":[0.04256425,0.0021469807,0.93865716,0.005457073,0.0038410109,0.000019752373,0.00036330076,0.00014318018,0.0068073077],"study_design_codex":"not_applicable","study_design_gemma":"case_report","domain_scores_codex":[0.9941865,0.00027916254,0.003841101,0.00016211948,0.001064856,0.00046623455],"domain_scores_gemma":[0.9902913,0.00020549839,0.0068516387,0.00049756584,0.0019215818,0.00023239944],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014869834,0.0005057933,0.001253925,0.0019412299,0.000186102,0.00017253438,0.0009883967,0.0007579471,0.000027744389],"category_scores_gemma":[0.00033994814,0.0004640047,0.00033353493,0.000569848,0.00034295928,0.0018729544,0.0004453172,0.0020692116,0.000013292332],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048569287,0.0010270085,0.0014938213,0.00208256,0.00078348414,0.00097232295,0.031937964,0.007519789,0.0025505659,0.00016507755,0.9293161,0.021665629],"study_design_scores_gemma":[0.040642712,0.020287875,0.036732905,0.016263044,0.0036303408,0.55708694,0.027525656,0.15201306,0.0074939737,0.004296893,0.12810479,0.00592179],"about_ca_topic_score_codex":0.0000032659573,"about_ca_topic_score_gemma":0.000011639487,"teacher_disagreement_score":0.8012113,"about_ca_system_score_codex":0.00047988884,"about_ca_system_score_gemma":0.0012054467,"threshold_uncertainty_score":0.9997812},"labels":[],"label_agreement":null},{"id":"W4409982039","doi":"10.18280/ts.420212","title":"Enhancing Breast Cancer Diagnosis: A Semi-Supervised Deep Learning Model for Automated MRI Tumor Segmentation","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Abdulaziz University; Cardiff Metropolitan University","keywords":"Artificial intelligence; Breast cancer; Segmentation; Breast tumor; Deep learning; Computer science; Medicine; Cancer; Pattern recognition (psychology); Radiology; Internal medicine","score_opus":0.012536168355105888,"score_gpt":0.2697164897952877,"score_spread":0.25718032144018177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409982039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03410892,0.0001716916,0.9626401,0.0010759871,0.00033709643,0.00071365846,0.000020387075,0.00087270717,0.000059428086],"genre_scores_gemma":[0.95355433,0.0000449298,0.041894462,0.000881803,0.00012214671,0.0033206036,0.000012728877,0.000020664516,0.00014832994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983413,0.000072938084,0.00039067524,0.00051587104,0.00030434603,0.00037485838],"domain_scores_gemma":[0.9993098,0.00012443379,0.00014448418,0.00018503187,0.00016572075,0.000070566224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035046562,0.00020737162,0.0001974722,0.00018491822,0.00033578224,0.00018798493,0.0003974509,0.000054022523,0.00009583579],"category_scores_gemma":[0.00001076107,0.00021787453,0.00009620453,0.00045937172,0.000023205266,0.0006038104,0.000095952746,0.00013804731,0.000006121214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120342906,0.00016988543,0.0030585474,0.00029557603,0.00017346231,0.0000039806346,0.0038680017,0.8105038,0.05009783,0.00085370295,0.002612694,0.12824218],"study_design_scores_gemma":[0.0011682014,0.00007334697,0.0016188549,0.00017576254,0.000044654065,0.0000037305483,0.00014002711,0.96537304,0.030745042,0.0003068087,0.00013934277,0.00021118036],"about_ca_topic_score_codex":0.00009410982,"about_ca_topic_score_gemma":0.00015862912,"teacher_disagreement_score":0.9207457,"about_ca_system_score_codex":0.00050134724,"about_ca_system_score_gemma":0.00018433768,"threshold_uncertainty_score":0.88846654},"labels":[],"label_agreement":null},{"id":"W4409992249","doi":"10.1109/tuffc.2025.3566340","title":"Synthetic Versus Classic Data Augmentation: Impacts on Breast Ultrasound Image Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ultrasound; Contextual image classification; Ultrasonic imaging; Computer science; Breast ultrasound; Artificial intelligence; Image (mathematics); Computer vision; Mammography; Pattern recognition (psychology); Acoustics; Medicine; Breast cancer; Physics; Internal medicine","score_opus":0.025690117568199656,"score_gpt":0.28112965807096524,"score_spread":0.25543954050276557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409992249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003053404,0.00033478116,0.988656,0.0027243348,0.0020259486,0.0005921897,0.00022413275,0.0002889689,0.0021002532],"genre_scores_gemma":[0.9955488,0.0007877773,0.0028372325,0.00050980074,0.000059214493,0.00010380541,0.000019618903,0.000026369577,0.00010740258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997268,0.00018951322,0.0004735125,0.0010712958,0.0004754566,0.0005222029],"domain_scores_gemma":[0.99641407,0.0014174973,0.00019237412,0.0016062318,0.00019821296,0.00017160737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005016573,0.00036379858,0.00031060743,0.00049798586,0.0006052943,0.0004584076,0.0010497156,0.00020723642,0.0000281962],"category_scores_gemma":[0.0000895784,0.00036823447,0.00010127308,0.0013976925,0.00012517693,0.0009724763,0.0000038463313,0.00065294246,0.000035438774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016068033,0.0013251588,0.00012359918,0.00013550706,0.0008750514,0.000023707293,0.00037183618,0.0025923871,0.12870683,0.054847322,0.0017418187,0.80764997],"study_design_scores_gemma":[0.01573596,0.0029012966,0.0057654977,0.00034159078,0.0008380973,0.00028757445,0.0001685502,0.9346112,0.026181955,0.010106537,0.0012561472,0.0018055772],"about_ca_topic_score_codex":0.000093539296,"about_ca_topic_score_gemma":0.00014902075,"teacher_disagreement_score":0.99249536,"about_ca_system_score_codex":0.000645463,"about_ca_system_score_gemma":0.0004387995,"threshold_uncertainty_score":0.999877},"labels":[],"label_agreement":null},{"id":"W4410162006","doi":"10.7759/cureus.83656","title":"Enhancing Organ Allocation Efficiency: A Pilot Study Evaluating Artificial Intelligence-Assisted Assessment of Donor Kidney Pathology","year":2025,"lang":"en","type":"article","venue":"Cureus","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Iron Ore Company (Canada); Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Pathology; Medical physics","score_opus":0.07015673116999986,"score_gpt":0.3833451504106798,"score_spread":0.3131884192406799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410162006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21366929,0.000045756286,0.7830253,0.00038445686,0.0013785195,0.00048071402,8.736902e-7,0.0001116873,0.0009033506],"genre_scores_gemma":[0.96654636,0.0000037684983,0.033136033,0.00012556277,0.000056511206,0.000087986395,0.000001758031,0.0000075463804,0.00003444839],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979643,0.0003144295,0.0005989869,0.0005260883,0.00035816332,0.0002379829],"domain_scores_gemma":[0.99852383,0.00017463932,0.00026040094,0.0006699524,0.00031209897,0.00005908366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014768447,0.00014488818,0.00022872748,0.00018142178,0.00018947935,0.00007731309,0.0006955065,0.000048321297,0.00001965069],"category_scores_gemma":[0.00046819646,0.00014620463,0.00003553713,0.0010724908,0.000055335175,0.00021258014,0.00029452104,0.00017621428,0.0000070055426],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062075356,0.003153645,0.0037637772,0.00012723113,0.0001292766,0.000013473764,0.0051222113,0.0023588766,0.6502938,0.05047545,0.00012356027,0.2843766],"study_design_scores_gemma":[0.0007430059,0.013932283,0.049237356,0.00031226288,0.000181213,0.000022044402,0.0027623656,0.59325624,0.30731097,0.0315204,0.00006210957,0.00065976824],"about_ca_topic_score_codex":0.00014099905,"about_ca_topic_score_gemma":0.0002621146,"teacher_disagreement_score":0.7528771,"about_ca_system_score_codex":0.00038359777,"about_ca_system_score_gemma":0.00095864676,"threshold_uncertainty_score":0.59620523},"labels":[],"label_agreement":null},{"id":"W4410268068","doi":"10.22214/ijraset.2025.70514","title":"A Comprehensive Analysis of Hybrid ConvNeXt and Vision Transformer Architectures for Skin Cancer Classification: Evaluating Simpler vs. Advanced Models on the HAM10000 Dataset","year":2025,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Pattern recognition (psychology); Machine learning; Engineering; Electrical engineering","score_opus":0.1002092352246625,"score_gpt":0.46703609499178267,"score_spread":0.36682685976712015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410268068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35440758,0.00019751168,0.6301516,0.014135306,0.00025199843,0.000672659,0.000108003995,0.000026207037,0.00004909364],"genre_scores_gemma":[0.98935705,0.00013589342,0.0100960275,0.000112169575,0.000016475045,0.0002710495,0.0000043502646,0.0000039439146,0.0000030159977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985471,0.000016637181,0.00025537453,0.00033061457,0.00058350817,0.00026678172],"domain_scores_gemma":[0.99844486,0.00069291337,0.00006870234,0.0002108028,0.000546713,0.0000360056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018503758,0.00008439324,0.00015543708,0.002269635,0.00024969477,0.00013574975,0.001008634,0.00003691148,0.0000013066558],"category_scores_gemma":[0.00017519783,0.00006446174,0.00002984525,0.0016882889,0.00036658687,0.00012359931,0.00014154996,0.00032434246,7.999191e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026253046,0.00003144084,0.00003886253,0.000041503787,0.00019211827,0.0000012429261,0.00022962135,0.28877184,0.10098212,0.17795932,0.00024890853,0.43124047],"study_design_scores_gemma":[0.0004213392,0.00012490671,0.00044874466,0.00006213727,0.000010939087,0.000007655493,0.00010853086,0.942248,0.017826425,0.03640561,0.0022760038,0.0000597457],"about_ca_topic_score_codex":0.000013065339,"about_ca_topic_score_gemma":0.000011985572,"teacher_disagreement_score":0.6534761,"about_ca_system_score_codex":0.00021267214,"about_ca_system_score_gemma":0.00018859172,"threshold_uncertainty_score":0.26286733},"labels":[],"label_agreement":null},{"id":"W4410296630","doi":"10.1109/isbi60581.2025.10980899","title":"Attention-Enhanced UNet for Automated Gleason Score 3 Tumor Segmentation in Histopathological Whole Slide Images","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Computer science; Segmentation; Artificial intelligence; Image segmentation; Computer vision; Pattern recognition (psychology)","score_opus":0.012873458476067853,"score_gpt":0.2870896016529281,"score_spread":0.2742161431768602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410296630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13541125,0.000059440525,0.8601875,0.0012252278,0.0006417919,0.00049096014,0.0000035280948,0.0007834434,0.0011968655],"genre_scores_gemma":[0.8585843,0.0000046249565,0.13801467,0.00055212725,0.000027071856,0.00029715648,0.0000126733985,0.000006368285,0.0025010295],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889946,0.000059108705,0.0002601231,0.00043206435,0.00013403787,0.00021522489],"domain_scores_gemma":[0.9994677,0.000079363606,0.00008269642,0.0002592804,0.000083613035,0.000027381418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024554098,0.00011357089,0.00014193474,0.00017315903,0.000093915834,0.000095405725,0.00032156496,0.000052416,0.000012390641],"category_scores_gemma":[0.00006445268,0.000106149724,0.000052603187,0.0005625326,0.0000334999,0.00042926392,0.00009506783,0.00008222598,0.000024065914],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105897416,0.00024133228,0.008903582,0.00016791011,0.000017008617,0.000022182217,0.00032800928,0.0040527065,0.8508483,0.00863301,0.0316993,0.09498072],"study_design_scores_gemma":[0.0021737642,0.00031590892,0.15700288,0.00017440272,0.000014522514,0.0000112195285,0.00018612738,0.5282948,0.30196634,0.008046068,0.0014345251,0.0003794344],"about_ca_topic_score_codex":0.000047271824,"about_ca_topic_score_gemma":0.00008329318,"teacher_disagreement_score":0.723173,"about_ca_system_score_codex":0.00034325305,"about_ca_system_score_gemma":0.00006725634,"threshold_uncertainty_score":0.432866},"labels":[],"label_agreement":null},{"id":"W4410319792","doi":"10.1016/j.jpi.2025.100446","title":"Digital slide scanning at scale: Comparison of whole slide imaging devices in a clinical setting","year":2025,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute; Division of Cancer Prevention, National Cancer Institute; National Institutes of Health; Warren Alpert Foundation","keywords":"Computer science; Scale (ratio); Computer graphics (images); Digital pathology; Artificial intelligence; Cartography","score_opus":0.016188278460585764,"score_gpt":0.3434714364393204,"score_spread":0.32728315797873464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410319792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69291437,0.00022464976,0.30300027,0.00061442604,0.00088128017,0.000064029,0.0000021182866,0.000018011122,0.0022808677],"genre_scores_gemma":[0.93572927,0.000011113263,0.063741475,0.0004239275,0.00005383006,0.000001160584,7.102808e-7,0.0000042437255,0.000034254997],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969281,0.000100229874,0.0023680557,0.000089858746,0.00027465416,0.00023912612],"domain_scores_gemma":[0.99718314,0.00044390038,0.0018182413,0.00025842935,0.00023749057,0.000058792648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018295193,0.000119723285,0.00048398608,0.000464768,0.00007999881,0.00010008528,0.00067874684,0.00010235335,0.0000014186925],"category_scores_gemma":[0.00039870667,0.00010950126,0.0001336876,0.0004718471,0.0001243361,0.0016009151,0.00043154054,0.00055801723,0.000006797111],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000256479,0.000057465928,0.77731526,0.00009857894,0.000021447364,0.00004951446,0.0043947734,0.0027662464,0.00017440038,0.00007913654,0.001107539,0.21391001],"study_design_scores_gemma":[0.0033566402,0.0006296083,0.3668273,0.001916339,0.00008318269,0.0021810122,0.009428779,0.5986038,0.004663783,0.0017786971,0.01006106,0.00046978265],"about_ca_topic_score_codex":0.0000013336393,"about_ca_topic_score_gemma":0.000013800498,"teacher_disagreement_score":0.59583753,"about_ca_system_score_codex":0.00018678146,"about_ca_system_score_gemma":0.00020547527,"threshold_uncertainty_score":0.4465332},"labels":[],"label_agreement":null},{"id":"W4410361163","doi":"10.2196/67457","title":"Automating Colon Polyp Classification in Digital Pathology by Evaluation of a “Machine Learning as a Service” AI Model: Algorithm Development and Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Alberta","funders":"","keywords":"Preprint; Service (business); Computer science; Service model; Artificial intelligence; Digital pathology; Medicine; World Wide Web","score_opus":0.07303212742839817,"score_gpt":0.4331372897543279,"score_spread":0.36010516232592976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410361163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7888599,0.000057579688,0.20937026,0.00039143866,0.00003351231,0.0008960288,0.0000026796874,0.000046585923,0.00034200453],"genre_scores_gemma":[0.9967744,0.000005063125,0.0025810318,0.000024476492,0.0000037997754,0.0005485933,0.000022468152,0.000005549786,0.00003465074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751157,0.00058875215,0.0004102507,0.00030617075,0.0009481386,0.00023509869],"domain_scores_gemma":[0.9985718,0.00018865078,0.00015052187,0.00019288916,0.0008627321,0.00003336998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004103276,0.00009826687,0.00014813228,0.00059014274,0.00023404954,0.0001596088,0.00027086915,0.00007179021,0.000002036562],"category_scores_gemma":[0.00018112196,0.00009834468,0.000011890176,0.0014026664,0.000042971882,0.0012888449,0.0003434134,0.00040220493,0.000006425578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002937052,0.00035488405,0.0050439676,0.000079519115,0.000022963353,8.040075e-7,0.04484235,0.0024618227,0.001774582,0.00055479986,0.000046274236,0.94478863],"study_design_scores_gemma":[0.0008317895,0.00027164246,0.01866373,0.000072609415,0.000002720464,0.0000018219285,0.0017341623,0.97137374,0.004364817,0.0025898211,0.000018128972,0.000075014555],"about_ca_topic_score_codex":0.00007125657,"about_ca_topic_score_gemma":0.0000432201,"teacher_disagreement_score":0.96891195,"about_ca_system_score_codex":0.00062442996,"about_ca_system_score_gemma":0.00048009874,"threshold_uncertainty_score":0.401038},"labels":[],"label_agreement":null},{"id":"W4410416263","doi":"10.1007/978-981-97-9855-1_42","title":"Harnessing Collective Intelligence Without Data Sharing: A Federated Random Forest Approach for Lung Tumor Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Learning and analytics in intelligent systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Computer science; Collective intelligence; Data sharing; Information sharing; Data science; Artificial intelligence; World Wide Web; Medicine","score_opus":0.06437580814327888,"score_gpt":0.30576492425366464,"score_spread":0.24138911611038577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410416263","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012369387,0.0023234312,0.9516927,0.000024110963,0.0010599716,0.0013396855,0.000042215932,0.00022788737,0.04327766],"genre_scores_gemma":[0.3126561,0.0018230865,0.023134721,0.00007490144,0.0011611852,0.0004616382,0.0008673023,0.00024258175,0.6595785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632084,0.00010075235,0.0010280444,0.0017198842,0.00042522434,0.00040522698],"domain_scores_gemma":[0.9975685,0.00046104135,0.0006883989,0.0008506652,0.0003248639,0.000106522304],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016607133,0.00050135545,0.00085838686,0.00071773183,0.00055306416,0.0011340235,0.0012266599,0.00036013755,0.0000037985806],"category_scores_gemma":[0.00037634524,0.0005087318,0.000116148796,0.00033931687,0.0001076705,0.00034303858,0.0008151858,0.001068837,0.000002307413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008814655,0.00019359271,0.017375533,0.007334909,0.0019236992,0.000058816768,0.0032836774,0.7691478,0.00002210228,0.14102118,0.003850145,0.054907057],"study_design_scores_gemma":[0.00035790275,0.00011244788,0.0000061821875,0.0022772253,0.0001314209,0.00004048007,0.00024429863,0.9843015,0.000031688123,0.0020772603,0.0099990135,0.0004205618],"about_ca_topic_score_codex":0.0001520899,"about_ca_topic_score_gemma":0.000047543796,"teacher_disagreement_score":0.92855793,"about_ca_system_score_codex":0.0008013767,"about_ca_system_score_gemma":0.00033746214,"threshold_uncertainty_score":0.9999029},"labels":[],"label_agreement":null},{"id":"W4410518910","doi":"10.3390/cells14100737","title":"Recognizing Epithelial Cells in Prostatic Glands Using Deep Learning","year":2025,"lang":"en","type":"article","venue":"Cells","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Occupational Cancer Research Centre; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Biopsy; Prostate; Artificial intelligence; Prostate biopsy; Stain; Pathology; Medicine; Feulgen stain; Computer science; Staining; Internal medicine; Cancer","score_opus":0.013343802373654508,"score_gpt":0.25096703790566904,"score_spread":0.23762323553201453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410518910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25928295,0.00015437149,0.7359163,0.000085620304,0.0019096702,0.00021393693,6.206636e-7,0.00012806075,0.0023084378],"genre_scores_gemma":[0.9588646,0.00003677607,0.040058255,0.00016222318,0.00007511891,0.00001154462,5.6971305e-7,0.000011222895,0.000779665],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896604,0.00009832796,0.00021437094,0.00033003849,0.00012799264,0.0002632039],"domain_scores_gemma":[0.9995093,0.00011799253,0.0000759924,0.00022639144,0.000037447622,0.00003291002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032985563,0.00010424064,0.00013316263,0.00020558939,0.000109214074,0.00011701437,0.00031311516,0.00006288181,0.000010452316],"category_scores_gemma":[0.000025537604,0.0001114404,0.000034773857,0.0006856094,0.000022796277,0.00025136198,0.00015153327,0.00024848687,0.00004570166],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023433342,0.000054283882,0.0021796736,0.00015770577,0.000018122293,0.000037568378,0.0032280558,0.039362144,0.5968286,0.0003577263,0.00013925062,0.35761344],"study_design_scores_gemma":[0.00043968135,0.000046652665,0.0003655559,0.00012188531,0.00000697318,0.0000029015055,0.000088635956,0.48804542,0.5049179,0.0017741156,0.0040117037,0.00017855043],"about_ca_topic_score_codex":0.000080685306,"about_ca_topic_score_gemma":0.000031236083,"teacher_disagreement_score":0.6995817,"about_ca_system_score_codex":0.00019600827,"about_ca_system_score_gemma":0.0000858301,"threshold_uncertainty_score":0.45444074},"labels":[],"label_agreement":null},{"id":"W4410727859","doi":"10.1038/s41598-025-01920-4","title":"MobNas ensembled model for breast cancer prediction","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Breast cancer; Computational biology; Cancer; Computer science; Bioinformatics; Oncology; Medicine; Internal medicine; Biology","score_opus":0.015433344607978084,"score_gpt":0.27206579358721145,"score_spread":0.2566324489792334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410727859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0111975055,0.00011291042,0.96278465,0.0011588671,0.02261743,0.0004971027,0.000015113319,0.00032551982,0.0012909153],"genre_scores_gemma":[0.9657473,0.000007308837,0.01207853,0.00014287171,0.000118277334,0.0004013699,0.0000067110936,0.000010222402,0.021487439],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803674,0.00001756109,0.00037254023,0.00092891185,0.00035649553,0.00028776407],"domain_scores_gemma":[0.99830776,0.000024300285,0.00018388679,0.0010517334,0.00036698705,0.00006534054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090782915,0.00011583779,0.00012871347,0.00023853662,0.00047123362,0.00042886502,0.00031938194,0.000071543946,0.0000120392715],"category_scores_gemma":[0.000034998626,0.00011202019,0.00009210087,0.00085297227,0.00007909857,0.0005827294,0.00013721989,0.000077879755,0.0000033900842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059379978,0.00018969669,0.0037969686,0.00022590533,0.00011613474,0.000042481726,0.0015596134,0.16675964,0.076998346,0.011722209,0.39112827,0.34740135],"study_design_scores_gemma":[0.00012932731,0.000008535291,0.000803066,0.000046742764,0.0000144347,0.00006559126,0.000007374323,0.9129846,0.014146479,0.061772488,0.009915975,0.00010537834],"about_ca_topic_score_codex":0.000034390792,"about_ca_topic_score_gemma":0.00005353946,"teacher_disagreement_score":0.9545498,"about_ca_system_score_codex":0.00025521402,"about_ca_system_score_gemma":0.00058406324,"threshold_uncertainty_score":0.45680508},"labels":[],"label_agreement":null},{"id":"W4410758277","doi":"10.22541/au.174824300.06594852/v1","title":"Development and Validation of an Automated Pediatric Cancer Staging Calculator Using the Toronto Pediatric Cancer Stage Guidelines","year":2025,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Calculator; Stage (stratigraphy); Cancer; Pediatric cancer; Medical physics; Medicine; Computer science; Internal medicine; Biology","score_opus":0.06611532257245331,"score_gpt":0.38294581629846025,"score_spread":0.3168304937260069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410758277","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76306957,0.0050681666,0.22753353,0.00021167152,0.0026833348,0.0006961071,0.0000544486,0.0005999459,0.000083238476],"genre_scores_gemma":[0.39442956,0.007958969,0.5923662,0.0005352937,0.0025579617,0.00069306575,0.00003446945,0.00008462656,0.0013398355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715686,0.00013838013,0.0008914298,0.00086652406,0.0006201289,0.00032665866],"domain_scores_gemma":[0.99764097,0.000066730594,0.00069558434,0.0008043475,0.00069717737,0.000095186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074369175,0.00036657747,0.00038039702,0.00021621841,0.00025500686,0.00023727007,0.000926943,0.00022501458,0.000050047292],"category_scores_gemma":[0.000036913134,0.00029166025,0.000065705026,0.0005204004,0.00002615228,0.00059429184,0.0014750562,0.00025299698,3.4911503e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004758748,0.00015104446,0.07948648,0.0044775726,0.0004131494,0.000007916542,0.012417268,0.774697,0.0009173022,0.0009510951,0.0023109668,0.12412258],"study_design_scores_gemma":[0.00027942096,0.000015097653,0.0072439713,0.00011141988,0.00018561711,0.0000011840681,0.00019621915,0.98047566,0.010023083,0.00005774435,0.00088326994,0.00052729045],"about_ca_topic_score_codex":0.028706271,"about_ca_topic_score_gemma":0.003966363,"teacher_disagreement_score":0.36863998,"about_ca_system_score_codex":0.0012897884,"about_ca_system_score_gemma":0.0027469685,"threshold_uncertainty_score":0.99995357},"labels":[],"label_agreement":null},{"id":"W4410781874","doi":"10.1016/j.media.2025.103648","title":"Corrigendum to “LESS: Label-efficient multi-scale learning for cytological whole slide image screening” [Medical Image Analysis 94 (2024): 103109]","year":2025,"lang":"en","type":"erratum","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vector Institute; University of British Columbia","funders":"","keywords":"Artificial intelligence; Image (mathematics); Computer science; Scale (ratio); Computer vision; Pattern recognition (psychology); Machine learning; Cartography; Geography","score_opus":0.025653145658127943,"score_gpt":0.31852275399436714,"score_spread":0.2928696083362392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410781874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009672951,0.0008760659,0.9752681,0.008030218,0.010073361,0.00088743947,0.00021432474,0.0008221586,0.0037315506],"genre_scores_gemma":[0.0015953437,0.00059188186,0.5285827,0.005332885,0.003827901,0.0013624362,0.0027013475,0.00022417225,0.45578134],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9834783,0.0012495054,0.0025400526,0.004312833,0.0061299354,0.002289354],"domain_scores_gemma":[0.9911166,0.0010174644,0.0010495598,0.0028903377,0.0015493174,0.0023767615],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0051152594,0.0014528579,0.0039688926,0.0047251824,0.0010920365,0.0012460224,0.0062361658,0.0023820975,0.00401367],"category_scores_gemma":[0.009030796,0.0013185039,0.003423665,0.018364402,0.00090566033,0.0005234094,0.0033440671,0.005095349,0.00034798257],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097276,0.0009002704,0.0006877482,0.00031531684,0.009797978,0.0011786347,0.00045808533,0.0015693841,0.00021364652,0.000026513662,0.915964,0.06879116],"study_design_scores_gemma":[0.0010836675,0.0002490311,0.00095769524,0.00026636914,0.008894736,0.000018204431,0.000239849,0.8201726,0.00014513453,0.000024984032,0.16678038,0.0011673361],"about_ca_topic_score_codex":0.0011913538,"about_ca_topic_score_gemma":0.0028628767,"teacher_disagreement_score":0.8186032,"about_ca_system_score_codex":0.000872092,"about_ca_system_score_gemma":0.0017109143,"threshold_uncertainty_score":0.9998221},"labels":[],"label_agreement":null},{"id":"W4410803506","doi":"10.1200/jco.2025.43.16_suppl.11572","title":"Moving beyond the traditional two-step approach for prognosis prediction: The BayeSarc model.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; Mount Sinai Hospital","funders":"","keywords":"Medicine; Internal medicine; Artificial intelligence; Computer science","score_opus":0.15999101279492334,"score_gpt":0.41896592669256294,"score_spread":0.2589749138976396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410803506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015448837,0.00019163385,0.94154376,0.045067515,0.0033020861,0.00035179153,0.0000053400604,0.000022445452,0.007970565],"genre_scores_gemma":[0.671088,0.00011037575,0.31485412,0.0104052555,0.003007043,0.00015481847,0.00000129079,0.000010434604,0.00036867146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972756,0.0004671005,0.0014396423,0.0002370249,0.00038358758,0.00019702893],"domain_scores_gemma":[0.9935718,0.004660805,0.00096631615,0.00029700747,0.0004221933,0.00008186889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061580683,0.00010380393,0.00043180477,0.00007741632,0.0003092261,0.00007088694,0.0012242843,0.00019022072,0.0000059456875],"category_scores_gemma":[0.00095216464,0.000055595934,0.0004480212,0.0003040284,0.00025144493,0.0003531798,0.0001399106,0.0009095019,7.989533e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055312144,0.00095529424,0.0017240153,0.000028693868,0.0004722928,0.000005963013,0.0002595176,0.05502083,0.000028478098,0.14401716,0.119878314,0.6770563],"study_design_scores_gemma":[0.0015596625,0.0013731597,0.0033544467,0.000013264214,0.00010166217,0.000081698534,0.00005335095,0.8999659,0.000030028832,0.0605586,0.03285266,0.00005556749],"about_ca_topic_score_codex":0.0000026149273,"about_ca_topic_score_gemma":0.0000061100836,"teacher_disagreement_score":0.8449451,"about_ca_system_score_codex":0.00018262536,"about_ca_system_score_gemma":0.001573518,"threshold_uncertainty_score":0.39513838},"labels":[],"label_agreement":null},{"id":"W4411037799","doi":"10.1007/s10791-025-09619-w","title":"Medicine image classification using deep learning: highlighting the MedNet-MoBiL hybrid model","year":2025,"lang":"en","type":"article","venue":"Discover Computing","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Strong","keywords":"Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology)","score_opus":0.02607325318491194,"score_gpt":0.2983110197901346,"score_spread":0.27223776660522264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411037799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05606017,0.0002931679,0.9324982,0.0026938976,0.0009140643,0.00019211556,3.0703148e-7,0.00027210164,0.0070759873],"genre_scores_gemma":[0.97334695,0.0000133689355,0.025594875,0.0005027207,0.00025632634,0.000006289464,0.0000031499399,0.000016236741,0.000260066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802935,0.00018039093,0.0004380139,0.00059038406,0.0003885833,0.00037326437],"domain_scores_gemma":[0.998566,0.00032172824,0.00029826004,0.0006282924,0.00013884014,0.000046910947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008533425,0.00020603329,0.0002149541,0.00016252902,0.00082685385,0.0002770636,0.0009861179,0.00004767349,0.0000037521474],"category_scores_gemma":[0.0001767334,0.00015473513,0.00007532548,0.00075602886,0.00014318916,0.0005829042,0.0005455867,0.00041352934,0.000008832721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016373668,0.000050733004,0.0014217203,0.00009207035,0.00008742796,0.000009485608,0.0043485556,0.68891656,0.044072464,0.11171773,0.0010333922,0.1482335],"study_design_scores_gemma":[0.0002543096,0.000020701085,0.0008076351,0.00012735475,0.000023328601,0.000011304188,0.0003668639,0.99211484,0.00247442,0.0029342247,0.0007047601,0.00016024025],"about_ca_topic_score_codex":0.0001486632,"about_ca_topic_score_gemma":0.000007707418,"teacher_disagreement_score":0.9172868,"about_ca_system_score_codex":0.0003790018,"about_ca_system_score_gemma":0.00018847926,"threshold_uncertainty_score":0.6359575},"labels":[],"label_agreement":null},{"id":"W4411080389","doi":"10.1101/2025.06.04.25328900","title":"PICASA: Decomposing patient heterogeneity of single-cell cancer data by cross-attention neural networks","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Provincial Health Services Authority; University of British Columbia","funders":"","keywords":"Artificial neural network; Cancer; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.048766315296239315,"score_gpt":0.3191312585860868,"score_spread":0.2703649432898475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411080389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55387294,0.0028408496,0.43720087,0.00015897455,0.0052105268,0.00032169293,0.00015969506,0.00013228589,0.00010215292],"genre_scores_gemma":[0.9937541,0.00022157961,0.0054079425,0.00016073533,0.0001916833,0.000059903774,0.00012355275,0.00002178259,0.0000587155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675846,0.00023500483,0.00074053503,0.0013813326,0.00048294925,0.00040173475],"domain_scores_gemma":[0.996042,0.000109188775,0.00074856856,0.0027782416,0.00022357029,0.00009844287],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038772012,0.0003590713,0.00044135406,0.00013433181,0.00015497813,0.0002936172,0.0028965927,0.00030957427,0.000009350002],"category_scores_gemma":[0.000029498351,0.0003811534,0.00015684683,0.0003611138,0.000113252616,0.00041670416,0.005869924,0.0006326708,0.0000016885091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101446494,0.00075520016,0.32676455,0.0011249968,0.00027761154,0.000019359628,0.00033254744,0.30499178,0.025639288,0.000030859625,0.005273621,0.33468875],"study_design_scores_gemma":[0.0003298927,0.00011641131,0.007848062,0.00032821155,0.00006557804,0.0000045119455,0.000003103325,0.9449185,0.043704152,0.000096094904,0.0021064756,0.0004789678],"about_ca_topic_score_codex":0.00049134286,"about_ca_topic_score_gemma":0.00013122318,"teacher_disagreement_score":0.63992673,"about_ca_system_score_codex":0.0003068186,"about_ca_system_score_gemma":0.00013401685,"threshold_uncertainty_score":0.99986404},"labels":[],"label_agreement":null},{"id":"W4411224062","doi":"10.1093/mam/ozaf044","title":"Enhanced Prognostication of Early Breast Cancer Outcomes Using Deep Learning on Merged Multistain and Multicolor-Depth Tumor Histopathology","year":2025,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Histopathology; Breast cancer; Medicine; Cancer; Artificial intelligence; Oncology; Pathology; Internal medicine; Computer science","score_opus":0.009796978951691971,"score_gpt":0.2936892233822711,"score_spread":0.28389224443057914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411224062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7184433,0.0006767777,0.2803632,0.00019249084,0.00011311458,0.00014753736,0.0000053428835,0.000037424146,0.000020840609],"genre_scores_gemma":[0.97944415,0.000117366595,0.020072272,0.00013576266,0.0000106945545,0.000022498973,0.0000016863702,0.000009235509,0.00018636046],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986815,0.0001439364,0.00032851318,0.0005217803,0.00009814065,0.00022614855],"domain_scores_gemma":[0.9991842,0.00012478657,0.00024066333,0.00026052573,0.00014343511,0.000046380548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022266427,0.00017854008,0.00037279582,0.00033989787,0.00023892726,0.000066324785,0.00019752054,0.0000738019,0.0000060528223],"category_scores_gemma":[0.00006136165,0.00017143198,0.00007105448,0.0005301343,0.00015596882,0.00016363733,0.00013532944,0.00016760423,0.0000011249797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006661103,0.000050648305,0.08176921,0.00006065427,0.00009462735,0.0000024768456,0.0010314654,0.00040417266,0.87004215,0.00014325242,0.0000036973133,0.046331037],"study_design_scores_gemma":[0.001073395,0.00014740732,0.4688692,0.00014706093,0.000401945,0.00001617739,0.0002326693,0.054566145,0.47398657,0.00011297131,0.00009996592,0.00034648392],"about_ca_topic_score_codex":0.00092518044,"about_ca_topic_score_gemma":0.00028468226,"teacher_disagreement_score":0.39605558,"about_ca_system_score_codex":0.00016463529,"about_ca_system_score_gemma":0.00006075824,"threshold_uncertainty_score":0.69907933},"labels":[],"label_agreement":null},{"id":"W4411329939","doi":"10.3390/bioengineering12060655","title":"AI-Powered Spectral Imaging for Virtual Pathology Staining","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Israel Science Foundation","keywords":"Staining; Digital pathology; Pathology; Computer science; Spectral imaging; Biomedical engineering; Computer graphics (images); Medicine; Geology; Remote sensing","score_opus":0.00628838652928189,"score_gpt":0.24740681245089655,"score_spread":0.24111842592161464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411329939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047945213,0.0002958745,0.99044013,0.0013367983,0.0022653616,0.00013375087,0.0000019138351,0.0004324817,0.00029917437],"genre_scores_gemma":[0.9486347,0.0000078104285,0.050715853,0.00036215823,0.0001352087,0.0000428535,0.0000010983143,0.000011446287,0.00008886328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991715,0.0000096929925,0.00015127996,0.0002922293,0.00007114523,0.00030415264],"domain_scores_gemma":[0.99956614,0.00006015206,0.00002677934,0.00027342176,0.000039984865,0.00003352223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016368809,0.00011010122,0.000113899485,0.00019327897,0.00007837442,0.00008597461,0.0003441605,0.000038008242,0.0000022809868],"category_scores_gemma":[0.000042216867,0.00012505596,0.00005366646,0.0002981829,0.000016986985,0.00025910372,0.00011863078,0.00010740681,0.0000035367239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003449581,0.000033307446,0.0009918455,0.00011677398,0.00006918334,0.00005616926,0.001017564,0.022252753,0.098168515,0.48055375,0.0023402912,0.39436534],"study_design_scores_gemma":[0.0006052186,0.00010110323,0.0015565697,0.000057680252,0.000008854103,0.000028147851,0.00007054916,0.9443861,0.032533213,0.0047782552,0.015591726,0.00028257936],"about_ca_topic_score_codex":0.000004230366,"about_ca_topic_score_gemma":0.0000016017111,"teacher_disagreement_score":0.9438402,"about_ca_system_score_codex":0.00014337453,"about_ca_system_score_gemma":0.000054527445,"threshold_uncertainty_score":0.5099634},"labels":[],"label_agreement":null},{"id":"W4411487526","doi":"10.2196/70709","title":"Stacked Deep Learning Ensemble for Multiomics Cancer Type Classification: Development and Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Ensemble learning; Artificial intelligence; Computer science; Machine learning; World Wide Web","score_opus":0.02609775852585585,"score_gpt":0.30311019571007886,"score_spread":0.277012437184223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411487526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38062048,0.00011812981,0.6168966,0.0012211275,0.00022165097,0.0006789341,6.9459054e-7,0.00016803383,0.00007435232],"genre_scores_gemma":[0.87706274,0.0002203507,0.12226607,0.0000918925,0.000011477347,0.00021479171,0.0000051695665,0.000004577377,0.00012295104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993532,0.000010974971,0.0002529694,0.0001752955,0.00006730632,0.0001403068],"domain_scores_gemma":[0.9995464,0.000039618666,0.00012427196,0.0001764857,0.000092744885,0.000020447871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017676201,0.00009414195,0.000115116476,0.00021408383,0.0002400963,0.00009502082,0.00016771731,0.00016295005,6.2310534e-7],"category_scores_gemma":[0.0000298227,0.00008660979,0.000009379793,0.00036373464,0.00004662475,0.00018451412,0.00016893649,0.00012270476,0.0000017812711],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016726546,0.00003646209,0.0015995229,0.00008756657,0.000034780714,1.5366246e-7,0.001790808,0.000037310947,0.0013253235,0.008746552,0.00006937783,0.9862554],"study_design_scores_gemma":[0.0014154132,0.0005223275,0.007961403,0.000044547978,0.000021829279,0.000006291354,0.0032030088,0.8811348,0.048323687,0.0011674499,0.05589714,0.0003021141],"about_ca_topic_score_codex":0.0000060348057,"about_ca_topic_score_gemma":0.00003525163,"teacher_disagreement_score":0.98595333,"about_ca_system_score_codex":0.00008092187,"about_ca_system_score_gemma":0.000069942165,"threshold_uncertainty_score":0.35318446},"labels":[],"label_agreement":null},{"id":"W4411515439","doi":"10.1016/j.inffus.2025.103399","title":"FusionSegNet: A Hierarchical Multi-Axis Attention and gated feature fusion network for breast lesion segmentation with uncertainty modeling in ultrasound imaging","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Feature (linguistics); Ultrasound; Breast ultrasound; Computer vision; Fusion; Pattern recognition (psychology); Lesion; Ultrasound imaging; Radiology; Medicine; Mammography; Breast cancer","score_opus":0.01166534889318484,"score_gpt":0.2524931694884056,"score_spread":0.24082782059522076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411515439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17724776,0.00006589222,0.8200201,0.0010442286,0.0003179786,0.0010356586,0.000014399027,0.00015810055,0.00009589756],"genre_scores_gemma":[0.9147451,0.0001572598,0.08408883,0.000513632,0.00005437999,0.00016093689,0.00021975319,0.000010277132,0.00004981466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984977,0.00009144858,0.0004530328,0.0003308644,0.00031272694,0.0003142197],"domain_scores_gemma":[0.99906236,0.00013812413,0.00019798477,0.00027045736,0.00026368603,0.00006737271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000567571,0.00021167862,0.0001810797,0.0004297812,0.0005207843,0.00028070033,0.00021094127,0.00013525112,0.000003951769],"category_scores_gemma":[0.000046353238,0.00018556416,0.000047286037,0.00094270695,0.000039094128,0.0022494197,0.00016032987,0.0002514819,0.0000033929603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006244266,0.00006394659,0.0059318393,0.00018487244,0.000015427911,0.0000013306287,0.001700701,0.22304611,0.009312177,0.0010599555,0.0006755664,0.75738364],"study_design_scores_gemma":[0.0021575224,0.00006790119,0.015600296,0.00044441212,0.000012281719,0.000047717804,0.0003206043,0.97968745,0.0001801913,0.00068773126,0.00058781245,0.0002060794],"about_ca_topic_score_codex":0.00020137276,"about_ca_topic_score_gemma":0.00021856876,"teacher_disagreement_score":0.7571776,"about_ca_system_score_codex":0.0002961421,"about_ca_system_score_gemma":0.0001065177,"threshold_uncertainty_score":0.7567087},"labels":[],"label_agreement":null},{"id":"W4411632823","doi":"10.18280/ijsse.150509","title":"A Hybrid Fuzzy System Framework for Breast Cancer Prediction via Automated Medical History Analysis","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Fuzzy logic; Computer science; Cancer; Medicine; Artificial intelligence; Internal medicine","score_opus":0.0039852539518133384,"score_gpt":0.2357273760014877,"score_spread":0.23174212204967434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411632823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038746998,0.00093398296,0.9886593,0.0018047135,0.004437991,0.000055902427,0.000041280764,0.00014975344,0.000042367985],"genre_scores_gemma":[0.99158305,0.00027234177,0.0076169884,0.00010295393,0.0004033414,0.000007191258,0.0000021398334,0.000005025523,0.000006960046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883854,0.000020651172,0.00042750954,0.00014798537,0.00045658436,0.000108749664],"domain_scores_gemma":[0.9990967,0.00016014847,0.00018567017,0.000095672076,0.00037887605,0.00008293725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046198675,0.00009346627,0.00020662246,0.00045944317,0.00003877094,0.00004162448,0.0004415634,0.00008258723,0.000012529528],"category_scores_gemma":[0.00007587861,0.0000925089,0.00013705599,0.00021414226,0.00001797383,0.00034556456,0.00007394082,0.0002480386,2.3319589e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013204361,0.00026908657,0.004100771,0.0009493326,0.014822211,0.0002878329,0.0033222947,0.4080852,0.00080052996,0.37592515,0.0032608577,0.1868563],"study_design_scores_gemma":[0.0003634762,0.00002093173,0.005948872,0.00039419052,0.000107628264,0.00026927772,0.0000119086035,0.9888113,0.000082029925,0.0009006217,0.0030177492,0.00007200174],"about_ca_topic_score_codex":0.000036087204,"about_ca_topic_score_gemma":0.000006392319,"teacher_disagreement_score":0.98770833,"about_ca_system_score_codex":0.0010426863,"about_ca_system_score_gemma":0.00016156258,"threshold_uncertainty_score":0.37724036},"labels":[],"label_agreement":null},{"id":"W4411634841","doi":"10.1016/j.jpi.2025.100459","title":"Data migration, validation and implementation of a new laboratory information system (LIS) in an academic pathology department, using Ellkay data archive, and Epic Beaker anatomic and clinical pathology modules","year":2025,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Pfizer Canada; Amgen Canada; Pfizer; Amgen","keywords":"Computer science; EPIC; Pathology; Surgical pathology; Beaker; Information retrieval; Medicine; Data science","score_opus":0.05920902124463414,"score_gpt":0.3944681400751242,"score_spread":0.3352591188304901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411634841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69087225,0.0002088463,0.30817738,0.00014065999,0.00025748325,0.00018279471,0.00014598007,0.000010539099,0.0000040588748],"genre_scores_gemma":[0.888077,0.001259258,0.110138245,0.00027740604,0.000059314087,0.0000025257264,0.00018033959,0.0000054393686,4.427457e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717075,0.00036047632,0.0019351754,0.00018917279,0.00016820552,0.00017622067],"domain_scores_gemma":[0.9972461,0.00019147692,0.001625735,0.00065760437,0.00019468322,0.00008439261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030363356,0.00014302056,0.00040551036,0.0006330839,0.000079625286,0.00007275843,0.00064579566,0.00022290964,7.6555443e-7],"category_scores_gemma":[0.00021281252,0.00013601172,0.000015967436,0.00030733674,0.00016444363,0.0056975796,0.00070465775,0.00040653447,4.292573e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022030665,0.000086390864,0.7129824,0.0009512109,0.00015814239,0.00009897432,0.020599192,0.00091415143,0.0020479152,0.007588645,0.0013869689,0.2529657],"study_design_scores_gemma":[0.0043746997,0.00081691425,0.42640233,0.00028381983,0.00026918962,0.0030921265,0.009377376,0.5502661,0.0006713365,0.0033844674,0.0007367376,0.00032493516],"about_ca_topic_score_codex":0.000019032443,"about_ca_topic_score_gemma":0.00015102202,"teacher_disagreement_score":0.54935193,"about_ca_system_score_codex":0.000076448756,"about_ca_system_score_gemma":0.0003950279,"threshold_uncertainty_score":0.5546397},"labels":[],"label_agreement":null},{"id":"W4411682666","doi":"10.1055/a-2643-9818","title":"Automated breast ultrasound features associated with diagnostic performance of a multiview convolutional neural network according to the level of experience of radiologists","year":2025,"lang":"en","type":"article","venue":"Ultraschall in der Medizin - European Journal of Ultrasound","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Medicine; Homogeneous; Ultrasound; Receiver operating characteristic; Breast ultrasound; Radiology; Nuclear medicine; Area under curve; Lesion; Diagnostic accuracy; Area under the curve; Convolutional neural network; Internal medicine; Breast cancer; Pathology; Mammography; Artificial intelligence; Mathematics; Cancer; Computer science","score_opus":0.03069882490577965,"score_gpt":0.2729425405721527,"score_spread":0.24224371566637307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411682666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704399,0.0017099775,0.026121791,0.00030253542,0.0008199544,0.00034842646,0.000030422612,0.00004726294,0.00017969316],"genre_scores_gemma":[0.99406356,0.00041541268,0.005209339,0.00014184914,0.000113725204,0.000008836624,0.0000034450593,0.000022741717,0.000021089058],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996003,0.0010473484,0.0013478317,0.00036172874,0.00077978126,0.00046033945],"domain_scores_gemma":[0.9911426,0.006052368,0.0014464266,0.00049672136,0.0007436292,0.00011829796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026252072,0.0003115953,0.00070446206,0.00032211593,0.00013225214,0.000052483036,0.0017646678,0.000074571195,0.0000074801455],"category_scores_gemma":[0.003645256,0.00021942874,0.00015553815,0.0017430977,0.00054274616,0.00052120996,0.00012711243,0.0005857933,0.0000011039552],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010131699,0.00079479546,0.51480454,0.00039738455,0.0010345541,0.00014102767,0.01671099,0.37842897,0.068166606,0.0006784709,0.0030976704,0.014731788],"study_design_scores_gemma":[0.0014857476,0.00089600985,0.98185927,0.0025699413,0.00008038103,0.0011911548,0.0009039929,0.003851344,0.0067908275,0.000043426728,0.00006374948,0.00026418015],"about_ca_topic_score_codex":0.000068244124,"about_ca_topic_score_gemma":0.00008518607,"teacher_disagreement_score":0.46705467,"about_ca_system_score_codex":0.00018298363,"about_ca_system_score_gemma":0.00028232887,"threshold_uncertainty_score":0.8948044},"labels":[],"label_agreement":null},{"id":"W4411792999","doi":"10.18280/ts.420323","title":"Pap Smear Image Classification with Efficient Weight Regularization for Cervical Cancer Diagnosis","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Regularization (linguistics); Cervical cancer; Medicine; Mathematics; Artificial intelligence; Radiology; Pattern recognition (psychology); Cancer; Computer science; Internal medicine","score_opus":0.01423214608319932,"score_gpt":0.25787402373726076,"score_spread":0.24364187765406145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010564686,0.00009027689,0.98144,0.0060529094,0.00036580974,0.0007703036,0.000014992967,0.00017111312,0.00052992685],"genre_scores_gemma":[0.96595424,0.000031106778,0.03019623,0.00059230067,0.0001937569,0.0027417664,0.00001843529,0.000016040422,0.00025613673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860257,0.000055914687,0.0002647804,0.000491476,0.0003359513,0.0002493363],"domain_scores_gemma":[0.9992007,0.000102884645,0.00012051365,0.00030486414,0.00021480734,0.000056224308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024983776,0.00015250818,0.00013874231,0.00014101346,0.00022143459,0.0001515249,0.00038692565,0.0000660416,0.00010204491],"category_scores_gemma":[0.0000096241465,0.00013217471,0.000058170408,0.0005731645,0.000054869506,0.00024090282,0.000056289395,0.00008450921,0.000006675522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006357339,0.0014733411,0.021654414,0.0006984282,0.00045633657,0.000008486767,0.0020901223,0.02425785,0.043040745,0.3556484,0.033462696,0.5165734],"study_design_scores_gemma":[0.0021376857,0.00031026173,0.051916037,0.00018708169,0.0000960983,0.0000018175504,0.000044699394,0.846373,0.0703892,0.002362289,0.025813717,0.00036809748],"about_ca_topic_score_codex":0.00002815896,"about_ca_topic_score_gemma":0.000032780772,"teacher_disagreement_score":0.95538956,"about_ca_system_score_codex":0.00033525564,"about_ca_system_score_gemma":0.00014872891,"threshold_uncertainty_score":0.5389928},"labels":[],"label_agreement":null},{"id":"W4411799315","doi":"10.1109/tmi.2025.3583974","title":"Improving Robustness and Reliability in Medical Image Classification With Latent-Guided Diffusion and Nested-Ensembles","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Alliance de recherche numérique du Canada; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Reliability (semiconductor); Pattern recognition (psychology); Physics","score_opus":0.010347312520266409,"score_gpt":0.2671102496100362,"score_spread":0.2567629370897698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411799315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17588356,0.0000616706,0.81276506,0.01050274,0.00036563585,0.00018463648,6.452958e-7,0.00015169803,0.00008435857],"genre_scores_gemma":[0.9893594,0.00018754715,0.009800549,0.00052330806,0.000023808434,0.000055511988,5.6061555e-7,0.000010959088,0.00003839614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979163,0.00016031785,0.00036359124,0.00063010876,0.00066439406,0.00026530933],"domain_scores_gemma":[0.99893445,0.00033307695,0.000066649765,0.00036325617,0.00008669691,0.00021589427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008551892,0.00016994424,0.00020471061,0.0002781895,0.00022674318,0.00012883061,0.0002945261,0.0001361278,0.000019580357],"category_scores_gemma":[0.000110128145,0.00014301222,0.000027104647,0.000605431,0.0003358205,0.0005851205,0.000015555563,0.00061462575,0.0000011625943],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057222136,0.00019159418,0.00346484,0.00017167196,0.000009977851,0.00006917434,0.0002838282,0.0006752152,0.0030426746,0.00017012721,0.000056495053,0.99180716],"study_design_scores_gemma":[0.0011305162,0.00003129282,0.011080687,0.0004108454,0.000016304015,0.00011788724,0.00010028715,0.98445445,0.002276781,0.00018471482,0.000038190046,0.00015805807],"about_ca_topic_score_codex":0.00035329044,"about_ca_topic_score_gemma":0.00020975897,"teacher_disagreement_score":0.99164915,"about_ca_system_score_codex":0.00015473171,"about_ca_system_score_gemma":0.0002602848,"threshold_uncertainty_score":0.5831869},"labels":[],"label_agreement":null},{"id":"W4411799550","doi":"10.1109/tfuzz.2025.3583819","title":"FCAformer: Fuzzy-Enhanced Class-Aware Attention Based Transformer for Weakly Supervised Histopathology Image Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Natural Science Foundation of Nantong City","keywords":"Image segmentation; Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Computer vision; Fuzzy logic; Class (philosophy); Scale-space segmentation; Transformer; Engineering","score_opus":0.014257721906577607,"score_gpt":0.2641116513675389,"score_spread":0.24985392946096127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411799550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006237085,0.000075782234,0.97975993,0.0012204526,0.007914634,0.0019915719,0.0000958382,0.0005671869,0.0021375127],"genre_scores_gemma":[0.9884907,0.000023226556,0.0069018635,0.0003731957,0.0000937937,0.0019609877,0.000024519162,0.000038429698,0.0020932695],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973,0.00022232575,0.00072190916,0.0008407252,0.00040371183,0.0005112936],"domain_scores_gemma":[0.9984264,0.00021480877,0.0001828529,0.0007180706,0.00035066283,0.0001072326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004874903,0.0003601615,0.000418586,0.00064623845,0.00059640856,0.00021316856,0.00053495786,0.00035711672,0.000014826013],"category_scores_gemma":[0.000005403121,0.00038001355,0.00034545333,0.00086429995,0.00008681003,0.0009809464,0.0000016103072,0.000392575,0.00007233802],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065445265,0.0006014363,0.000023719802,0.0013833884,0.00017541711,0.000008116429,0.0015325927,0.025322996,0.8138294,0.0014962427,0.002155553,0.15281668],"study_design_scores_gemma":[0.007704942,0.0016205121,0.00043394143,0.000657152,0.0003318236,0.000041468586,0.0010572246,0.45290938,0.5275172,0.0011528096,0.0052790768,0.0012944802],"about_ca_topic_score_codex":0.00011909992,"about_ca_topic_score_gemma":0.00013810226,"teacher_disagreement_score":0.9822536,"about_ca_system_score_codex":0.001108748,"about_ca_system_score_gemma":0.00036874003,"threshold_uncertainty_score":0.9998652},"labels":[],"label_agreement":null},{"id":"W4411855123","doi":"10.1038/s41598-025-03268-1","title":"CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Qatar University; McGill University","keywords":"Segmentation; Differential diagnosis; Artificial intelligence; Computer science; Differential (mechanical device); Deep learning; Medicine; Computational biology; Pathology; Biology; Engineering","score_opus":0.02998114596194854,"score_gpt":0.31579403857094,"score_spread":0.28581289260899145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411855123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43556094,0.00006159691,0.5615063,0.00006669466,0.0024721436,0.00027075468,4.1613552e-7,0.00004039233,0.000020759971],"genre_scores_gemma":[0.93242913,0.000009341449,0.06724006,0.000006357124,0.000010820316,0.000091606475,0.000009397426,0.00000483266,0.00019842932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866825,0.00004899349,0.0003653775,0.00054794684,0.0002176797,0.00015174628],"domain_scores_gemma":[0.99896103,0.00009562588,0.00032810122,0.00037244614,0.0002045527,0.000038271366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046619502,0.000084616324,0.0001246052,0.00022411741,0.00043319404,0.00019088456,0.00011742222,0.000045038796,0.000004488616],"category_scores_gemma":[0.0001883729,0.00008536439,0.00004873678,0.0005259486,0.00011154326,0.00043847814,0.000097328186,0.00006018127,3.0073002e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015409065,0.00008091512,0.013988892,0.0000991459,0.000022971653,0.0000039827873,0.000598599,0.0060207793,0.42439237,0.0011014624,0.00013903379,0.5535365],"study_design_scores_gemma":[0.00038226377,0.000054288208,0.00873847,0.00009116426,0.000042203705,0.0000148141,0.00019606938,0.5459815,0.4352475,0.0069033653,0.0022008233,0.00014752906],"about_ca_topic_score_codex":0.000021279799,"about_ca_topic_score_gemma":0.000020661872,"teacher_disagreement_score":0.5533889,"about_ca_system_score_codex":0.00010114664,"about_ca_system_score_gemma":0.00007752896,"threshold_uncertainty_score":0.34810585},"labels":[],"label_agreement":null},{"id":"W4411966292","doi":"10.1007/978-981-96-3250-3_40","title":"Advancements in Digital Pathology: A Comprehensive Survey of Predictive Models for Cancer Diagnosis","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Digital pathology; Data science; Medicine; Computer science; Medical physics; Pathology","score_opus":0.03169909423969267,"score_gpt":0.26950091465354403,"score_spread":0.23780182041385137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411966292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018603691,0.033265594,0.9621615,0.000031667907,0.0017095451,0.0013125222,0.00043796393,0.000027375623,0.0008678308],"genre_scores_gemma":[0.9912951,0.006064639,0.0004352557,0.00011195137,0.00020705957,0.0011735682,0.0000789741,0.000036053363,0.0005974202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824303,0.000059543778,0.0005696128,0.0006661328,0.0001837881,0.00027786702],"domain_scores_gemma":[0.9975668,0.0013880864,0.00036205986,0.00036295608,0.00028225363,0.00003783917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023641145,0.00032040852,0.00077072537,0.00023923893,0.000040620307,0.00007355123,0.000332579,0.00049430993,0.0000010903349],"category_scores_gemma":[0.00005147595,0.00030363223,0.00006841669,0.0001770307,0.0000783893,0.00022113732,0.00019335008,0.000375729,9.041658e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101624806,0.000016816777,0.008331744,0.00029052634,0.00008021035,0.000009313248,0.00021908026,0.90072834,4.144596e-7,0.0016098783,0.00017169514,0.088440366],"study_design_scores_gemma":[0.0006296491,0.00021022854,0.001216755,0.0024690097,0.000017325217,0.0000043547384,0.0000023182947,0.9786403,0.00000382283,0.015121527,0.001387287,0.0002974273],"about_ca_topic_score_codex":0.0006935341,"about_ca_topic_score_gemma":0.0023047165,"teacher_disagreement_score":0.991109,"about_ca_system_score_codex":0.00023639649,"about_ca_system_score_gemma":0.00010066803,"threshold_uncertainty_score":0.9999416},"labels":[],"label_agreement":null},{"id":"W4411975814","doi":"10.3390/diagnostics15131699","title":"Simplified Artificial Intelligence Terminology for Pathologists","year":2025,"lang":"en","type":"review","venue":"Diagnostics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Terminology; Computer science; GRASP; Digital pathology; Artificial intelligence; Applications of artificial intelligence; Data science; Management science; Engineering","score_opus":0.13074389056254754,"score_gpt":0.4030477277064994,"score_spread":0.27230383714395184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411975814","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9286152e-8,0.5081344,0.48872295,0.0000771149,0.002161549,0.00060989463,0.00004985673,0.00012473737,0.00011946179],"genre_scores_gemma":[0.0000037112684,0.97939223,0.019096768,0.00015469214,0.00036121425,0.000821095,0.000043736458,0.000020544758,0.00010602138],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979303,0.00011996971,0.00066264684,0.00074559735,0.00013714284,0.00040437648],"domain_scores_gemma":[0.99315906,0.0053672763,0.0003369936,0.00095033227,0.00012761717,0.00005870532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025765478,0.0003497698,0.00096267345,0.00027294084,0.00012287413,0.00012796461,0.0015578745,0.0005039344,0.0000047773297],"category_scores_gemma":[0.0027540224,0.00032505946,0.00032247422,0.00052806234,0.000099044344,0.00008420586,0.00047189594,0.00033975806,0.00009110373],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.9927077e-7,0.00002589304,3.0867466e-7,0.0036230434,0.00001681871,0.000022436465,0.000017750524,0.000005913459,2.3663953e-8,0.04661716,0.0013080514,0.9483618],"study_design_scores_gemma":[0.000016909937,0.0001250815,7.1167125e-7,0.0026442097,0.00017093551,0.00002909851,0.0000024901717,0.000497025,0.000021668946,0.04677018,0.94938165,0.00034001126],"about_ca_topic_score_codex":0.000003720725,"about_ca_topic_score_gemma":0.000009093007,"teacher_disagreement_score":0.9480736,"about_ca_system_score_codex":0.00018127097,"about_ca_system_score_gemma":0.0005347883,"threshold_uncertainty_score":0.9999201},"labels":[],"label_agreement":null},{"id":"W4411991803","doi":"10.1016/j.compbiomed.2025.110634","title":"Self-supervised deep metric learning for prototypical zero-shot lesion retrieval in placenta whole-slide images","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal","funders":"Institut TransMedTech; Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; Canada First Research Excellence Fund","keywords":"Metric (unit); Artificial intelligence; Computer science; Pattern recognition (psychology); Placenta; Zero (linguistics); Lesion; Computer vision; Medicine; Pathology; Biology; Pregnancy","score_opus":0.02356154124519938,"score_gpt":0.33009804624648736,"score_spread":0.306536505001288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411991803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036419064,0.0019316626,0.95512396,0.0041080266,0.0011942596,0.0008877205,4.0970042e-7,0.000112514674,0.00022240385],"genre_scores_gemma":[0.91835785,0.00038371154,0.07987743,0.001080268,0.0001462853,0.00008113702,0.00001159971,0.000007834334,0.00005387203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985897,0.00020594525,0.00032827133,0.0005082207,0.00007873632,0.00028911524],"domain_scores_gemma":[0.99891776,0.0007112663,0.00006734681,0.00020204521,0.00004725924,0.00005434552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081521727,0.00014878361,0.00032748346,0.0006330206,0.00010248725,0.000014937166,0.00036629336,0.00018133558,0.0000016952778],"category_scores_gemma":[0.00027357085,0.00012418367,0.00002708701,0.0009938559,0.00014154604,0.00011415774,0.00022238097,0.00035808454,0.0000010101702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016573466,0.00029978273,0.13662899,0.00073285284,0.00010415579,0.00005214361,0.0030465252,0.0007870147,0.016112007,0.022691285,0.0025202895,0.8153676],"study_design_scores_gemma":[0.0118692,0.0028675576,0.056772936,0.0008035323,0.00003415332,0.000043791602,0.00017280808,0.8784628,0.0049076756,0.022485241,0.021118334,0.0004619602],"about_ca_topic_score_codex":0.000021492895,"about_ca_topic_score_gemma":0.000011821331,"teacher_disagreement_score":0.8819388,"about_ca_system_score_codex":0.00014556637,"about_ca_system_score_gemma":0.00005874402,"threshold_uncertainty_score":0.50640637},"labels":[],"label_agreement":null},{"id":"W4412054439","doi":"10.1101/2025.07.02.662608","title":"OMIDIENT: Multiomics Integration for Cancer by Dirichlet Auto-Encoder Networks","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ottawa Mental Health Centre","funders":"Horizon 2020 Framework Programme; Finnish Center for Artificial Intelligence; Academy of Finland","keywords":"Computer science","score_opus":0.013546208530341768,"score_gpt":0.24380662889141164,"score_spread":0.23026042036106986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412054439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059723086,0.0028479886,0.9790749,0.00080949854,0.0084252935,0.0014878551,0.0004356988,0.0009360574,0.000010388021],"genre_scores_gemma":[0.8791452,0.0019013484,0.11222248,0.0012518637,0.0013786968,0.003864328,0.0000023148073,0.00014089145,0.0000928702],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996433,0.00013475037,0.0006871155,0.001652681,0.00038990102,0.0007025046],"domain_scores_gemma":[0.99635047,0.00017747363,0.00062542333,0.0017567577,0.00088770007,0.00020219921],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006671636,0.00065460446,0.0005989285,0.0003302937,0.00032929852,0.000602679,0.0016833927,0.00081918086,0.000009359531],"category_scores_gemma":[0.00015973327,0.00072478596,0.00023590671,0.00088996516,0.00008736161,0.00049877004,0.0009340487,0.0009184816,0.000008197459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048007874,0.0013646812,0.0054073134,0.0036598323,0.0023312778,0.000033441782,0.00040178414,0.14709498,0.6330772,0.035843723,0.16582079,0.0044848807],"study_design_scores_gemma":[0.000634317,0.00005498678,0.00145671,0.00058738334,0.00010978581,5.683922e-9,0.0000014552403,0.83566284,0.12266153,0.000023952076,0.03782387,0.0009831663],"about_ca_topic_score_codex":0.0002494397,"about_ca_topic_score_gemma":0.000031918335,"teacher_disagreement_score":0.8731729,"about_ca_system_score_codex":0.0014112125,"about_ca_system_score_gemma":0.0009282052,"threshold_uncertainty_score":0.9995203},"labels":[],"label_agreement":null},{"id":"W4412138693","doi":"10.2196/62996","title":"Deep Learning for the Early Detection of Invasive Ductal Carcinoma in Histopathological Images: Convolutional Neural Network Approach With Transfer Learning","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Transfer of learning; Preprint; Artificial intelligence; Deep learning; Computer science","score_opus":0.03813608939123301,"score_gpt":0.3116527715674264,"score_spread":0.27351668217619335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412138693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42495036,0.00022095584,0.5734476,0.00013623395,0.00008447647,0.0006419033,5.294009e-7,0.000033350632,0.00048461687],"genre_scores_gemma":[0.99787205,0.000016808228,0.0011498048,0.0000137336865,0.00005996521,0.00077934633,0.00000270175,0.0000082963725,0.000097292854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763644,0.0007244035,0.0002846888,0.00034070344,0.00051445473,0.000499292],"domain_scores_gemma":[0.99804807,0.0012228797,0.00006456333,0.00020129168,0.0004242113,0.000038986826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016636066,0.00013127175,0.00019460624,0.00029347467,0.00064262917,0.000087683526,0.00052902394,0.000095360185,0.0000028359216],"category_scores_gemma":[0.00013642511,0.00009202799,0.000075157805,0.0014341818,0.0004114445,0.00061573385,0.00017768372,0.001216546,0.0000020317216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027209178,0.00037966808,0.08675471,0.0007066241,0.0001307206,0.00002922029,0.05021994,0.7048116,0.00957426,0.020061795,0.00019338359,0.12441719],"study_design_scores_gemma":[0.0009800073,0.0015172089,0.3191455,0.00005144736,0.0000052865275,0.00003177833,0.0018483393,0.6725425,0.0027476489,0.0008482597,0.00015238624,0.0001296165],"about_ca_topic_score_codex":0.00009038761,"about_ca_topic_score_gemma":0.0000564243,"teacher_disagreement_score":0.5729217,"about_ca_system_score_codex":0.000367868,"about_ca_system_score_gemma":0.00016376769,"threshold_uncertainty_score":0.5285355},"labels":[],"label_agreement":null},{"id":"W4412163728","doi":"10.1158/1557-3265.aimachine-b048","title":"Abstract B048: Large Scale, AI-Enabled, Spatial Signal Processing of Breast Cancer Pathology Identifies Consensus Tissue Structures Related to Biology and Outcomes","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Cancer; Scale (ratio); Pathology; Medicine; Biology; Computational biology; Internal medicine; Cartography","score_opus":0.06175049177618674,"score_gpt":0.4973120765686493,"score_spread":0.43556158479246254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9602091,0.0026235431,0.017619286,0.016438544,0.0016909838,0.00076807814,0.00017187312,0.00011624655,0.00036237572],"genre_scores_gemma":[0.9977189,0.00023663974,0.00080894417,0.0005398951,0.00014666276,0.00012831712,0.000002307168,0.000015903328,0.0004024666],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963413,0.0005965296,0.00093689066,0.0009734888,0.0004499743,0.00070180534],"domain_scores_gemma":[0.9970775,0.0011005239,0.00020129576,0.0005155221,0.00091131165,0.0001938006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026824053,0.00020185621,0.0005962315,0.00042139518,0.00032355174,0.00013360658,0.0008260754,0.00037863248,0.00022301692],"category_scores_gemma":[0.00035280292,0.00017135574,0.00008180149,0.0010217952,0.0008758902,0.00016303992,0.00087293616,0.0010826667,0.000009594184],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005130066,0.00013909643,0.2933252,0.00035291334,0.00012918073,0.000044324403,0.00056070444,0.00019208268,0.011292993,0.0021480946,0.0036355173,0.6876669],"study_design_scores_gemma":[0.0013830883,0.00022875867,0.96660817,0.00023774692,0.000022463653,0.000018170073,0.00012010067,0.0024729485,0.005859796,0.020834893,0.0019638368,0.00025000644],"about_ca_topic_score_codex":0.0031074684,"about_ca_topic_score_gemma":0.0034127466,"teacher_disagreement_score":0.6874169,"about_ca_system_score_codex":0.00017594488,"about_ca_system_score_gemma":0.0010440783,"threshold_uncertainty_score":0.69876844},"labels":[],"label_agreement":null},{"id":"W4412163734","doi":"10.1158/1557-3265.aimachine-a031","title":"Abstract A031: Unsupervised graph-based visualization of variational autoencoder latent spaces reveals hidden multiple myeloma subtypes","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Autoencoder; Visualization; Multiple myeloma; Artificial intelligence; Graph; Pattern recognition (psychology); Computer science; Computational biology; Medicine; Biology; Theoretical computer science; Artificial neural network; Internal medicine","score_opus":0.1465657502516099,"score_gpt":0.46955915706531387,"score_spread":0.322993406813704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30409005,0.0014984467,0.6764293,0.011092744,0.0029472206,0.0015566908,0.000053545762,0.0003720475,0.0019599542],"genre_scores_gemma":[0.9896218,0.0002415676,0.009018279,0.00035409213,0.00020991518,0.00017062061,0.000011861427,0.000016679336,0.0003551824],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99598527,0.0007740408,0.0008925524,0.00074051105,0.0011599157,0.00044769832],"domain_scores_gemma":[0.9945739,0.0031098202,0.00022448739,0.00073553174,0.0012159629,0.00014028931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004772923,0.00015927614,0.0003514724,0.0004929678,0.00023883935,0.00015320569,0.0010709666,0.0002408524,0.00019739266],"category_scores_gemma":[0.0015267059,0.00014928206,0.00017859232,0.002020993,0.00033537683,0.00034538997,0.0002902362,0.00051907677,0.000028664297],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010547754,0.0011448998,0.7670034,0.00082239276,0.00035078195,0.000013905596,0.0004367408,0.013538443,0.0068632937,0.049288772,0.02285629,0.13662627],"study_design_scores_gemma":[0.0015154172,0.00023973951,0.7378676,0.00030276246,0.000014950857,3.1575007e-7,0.000019061446,0.23781145,0.0047414,0.014995469,0.0022850586,0.00020676055],"about_ca_topic_score_codex":0.00078232517,"about_ca_topic_score_gemma":0.00036300984,"teacher_disagreement_score":0.68553174,"about_ca_system_score_codex":0.0002714486,"about_ca_system_score_gemma":0.0013492707,"threshold_uncertainty_score":0.6087546},"labels":[],"label_agreement":null},{"id":"W4412163875","doi":"10.1158/1557-3265.aimachine-a058","title":"Abstract A058: Multimodal generative AI jointly learns pathology and clinical data to synthesize a multinational lung cancer cohort","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lung cancer; Cohort; Cancer; Medicine; Multinational corporation; Pathology; Generative grammar; Computer science; Artificial intelligence; Internal medicine; Business","score_opus":0.2597887378410895,"score_gpt":0.5770479330291616,"score_spread":0.31725919518807205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75377035,0.003605172,0.14693709,0.08285351,0.0072313407,0.0034716479,0.0004559689,0.00035672553,0.0013182171],"genre_scores_gemma":[0.9681366,0.003282736,0.01890047,0.0056677647,0.0017396584,0.0008781418,0.0000193791,0.000040177543,0.0013350876],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99317616,0.0015241049,0.001272606,0.0022141393,0.0010149487,0.00079805875],"domain_scores_gemma":[0.99072754,0.005749094,0.00017943676,0.0018117616,0.0010857595,0.0004464052],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011069645,0.0002552581,0.00062897505,0.00033398232,0.00048434275,0.0003391234,0.0024490561,0.00041352585,0.00024563583],"category_scores_gemma":[0.005834694,0.00023819764,0.00013381925,0.0010371353,0.0007268926,0.00059270527,0.0034152672,0.0023224142,0.000056666915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047733798,0.00045012755,0.35456195,0.00009784075,0.00039479666,0.000106685904,0.00022902235,0.00044275567,0.00039106605,0.00143681,0.06652631,0.5748853],"study_design_scores_gemma":[0.00123071,0.00021703576,0.8049307,0.00019352045,0.000037805443,0.0000053529748,0.00004197336,0.17702423,0.00026296524,0.0006794537,0.015076725,0.00029953584],"about_ca_topic_score_codex":0.0013833569,"about_ca_topic_score_gemma":0.0028605033,"teacher_disagreement_score":0.57458574,"about_ca_system_score_codex":0.0004964137,"about_ca_system_score_gemma":0.002323196,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W4412163909","doi":"10.1158/1557-3265.aimachine-a041","title":"Abstract A041: A Hybrid Active Learning (AL) Random Forest Model with KNN Imputation to Predict Recurrence in Ductal Carcinoma In Situ (DCIS) of the Breast","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ductal carcinoma; In situ; Random forest; Medicine; Carcinoma in situ; Oncology; Breast cancer; Carcinoma; Internal medicine; Artificial intelligence; Cancer; Computer science; Chemistry","score_opus":0.07290023780787054,"score_gpt":0.4324860707928705,"score_spread":0.35958583298499996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97019655,0.00008377329,0.024573509,0.0032032845,0.0002818932,0.0009061018,0.00001193873,0.000025350993,0.000717594],"genre_scores_gemma":[0.9989345,0.00007638297,0.00046916216,0.000098998775,0.000059766677,0.00028130118,0.000001298529,0.000011099336,0.000067501875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99677724,0.0005761381,0.00063233334,0.00071957207,0.00081978814,0.00047492207],"domain_scores_gemma":[0.9974852,0.0012959889,0.0001520994,0.00052854064,0.00043158807,0.00010658243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031364427,0.00013924837,0.00032338887,0.0003722018,0.0001288304,0.000069403126,0.0010543946,0.0000869447,0.000005003231],"category_scores_gemma":[0.0008391233,0.00010556809,0.00008469812,0.002049868,0.00028946815,0.00040871475,0.00056913367,0.0016026127,0.000003820169],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052578896,0.00028404815,0.44918314,0.00012470786,0.000035228506,0.00003305126,0.0014196474,0.29537818,0.00080550025,0.00047562586,0.0006960539,0.24630694],"study_design_scores_gemma":[0.0024718344,0.00027364757,0.70149827,0.0004982045,0.0000039749716,0.000006582507,0.00010559052,0.29176947,0.0013703838,0.001832836,0.00005329516,0.00011586893],"about_ca_topic_score_codex":0.0018303175,"about_ca_topic_score_gemma":0.0059831277,"teacher_disagreement_score":0.25231516,"about_ca_system_score_codex":0.0006436812,"about_ca_system_score_gemma":0.0017418239,"threshold_uncertainty_score":0.6962644},"labels":[],"label_agreement":null},{"id":"W4412187495","doi":"10.1007/s13721-025-00560-y","title":"Semantic segmentation of human blastocyst images using deep CNNs and vision transformers","year":2025,"lang":"en","type":"article","venue":"Network Modeling Analysis in Health Informatics and Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Segmentation; Computer science; Computer vision; Natural language processing","score_opus":0.017942413270598676,"score_gpt":0.3276066989244615,"score_spread":0.3096642856538628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412187495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0785108,0.0003734397,0.92044616,0.0001014955,0.000084461106,0.00026899495,0.0000024209976,0.00003274451,0.00017950164],"genre_scores_gemma":[0.6666857,0.0011207231,0.3319144,0.00024685013,0.000011299643,0.000005117189,0.000009190065,0.0000037824711,0.0000029521334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727654,0.000047454552,0.0019218082,0.00012319675,0.00028915482,0.00034183104],"domain_scores_gemma":[0.99887335,0.00008336154,0.00059888826,0.0002522406,0.000107960834,0.0000842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014628314,0.00017733546,0.0004813974,0.0008347652,0.00034015995,0.00015173934,0.00019003052,0.000094734205,7.8924387e-7],"category_scores_gemma":[0.00001264781,0.00016596913,0.00007643176,0.00194128,0.00006188296,0.00093601656,0.00011746821,0.00018896937,2.2170997e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006246743,0.000012043248,0.0011758336,0.001146001,0.00009432113,8.399769e-8,0.0038737252,0.9132039,0.0000071739537,0.00053225853,0.0000086504015,0.07993976],"study_design_scores_gemma":[0.00036887007,0.00010662859,0.0001324675,0.00034598715,0.00009977749,0.0000022544766,0.0011606558,0.99670166,0.00002566398,0.0009139952,0.000008897598,0.00013311852],"about_ca_topic_score_codex":0.00026457888,"about_ca_topic_score_gemma":0.00020802836,"teacher_disagreement_score":0.58853173,"about_ca_system_score_codex":0.00014832547,"about_ca_system_score_gemma":0.000105449464,"threshold_uncertainty_score":0.67680246},"labels":[],"label_agreement":null},{"id":"W4412398359","doi":"10.1007/978-981-96-3287-9_24","title":"Segmentation of Nuclei from H&amp;E Stained Histopathological Images Using Deep Learning Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Deep learning; Segmentation; Computer science; Pattern recognition (psychology); Anatomy; Biology","score_opus":0.021909711424785577,"score_gpt":0.24236608148523786,"score_spread":0.2204563700604523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412398359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037041784,0.013799415,0.9805042,0.00001532592,0.00087585644,0.000355594,0.0000045830143,0.000072293114,0.0040022973],"genre_scores_gemma":[0.8972824,0.001044206,0.09706903,0.0001020431,0.0010564643,0.00003794808,0.00010058087,0.000063280946,0.0032440054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983169,0.00015445608,0.0004812695,0.00060260657,0.00023914318,0.0002056229],"domain_scores_gemma":[0.9987833,0.00033517613,0.00042548377,0.00034020017,0.00007851329,0.000037313126],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034073196,0.00028482245,0.0005480475,0.00017575352,0.00010950291,0.0001235971,0.00028190098,0.00052899396,0.000005105721],"category_scores_gemma":[0.000040475763,0.00025759527,0.00007696938,0.00011864068,0.00007608126,0.000104454455,0.00018048081,0.0006534053,3.7857987e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029508703,0.0000113234355,0.0005264759,0.00020983185,0.000044140685,0.000013511023,0.0006131094,0.8827388,0.00035920698,0.0030280186,0.000027424529,0.11239863],"study_design_scores_gemma":[0.00024920554,0.00006640606,0.00009029464,0.000544279,0.00003949448,0.00002058677,0.000008394889,0.9929382,0.000023824878,0.0040764865,0.0016362797,0.00030654445],"about_ca_topic_score_codex":0.0002430309,"about_ca_topic_score_gemma":0.00003610546,"teacher_disagreement_score":0.89691204,"about_ca_system_score_codex":0.00026105763,"about_ca_system_score_gemma":0.000034709115,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W4412433844","doi":"10.1016/j.media.2025.103711","title":"CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; ARUP Laboratories; National Institutes of Health; Huntsman Cancer Institute; University of Utah","keywords":"Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Stain; Computer science; Computer vision; Image (mathematics); Mathematics; Pathology; Medicine; Staining","score_opus":0.014088078634863782,"score_gpt":0.3105851636818431,"score_spread":0.2964970850469793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412433844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004119258,0.000067980356,0.9898545,0.004315848,0.00009068211,0.00030659212,0.000005376753,0.00023295118,0.001006799],"genre_scores_gemma":[0.787241,0.000010551944,0.21097314,0.00087556784,0.000068469715,0.00027349434,0.00004385531,0.0000106626185,0.0005032998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974774,0.00032941625,0.00042785687,0.00076559675,0.0006596661,0.0003400499],"domain_scores_gemma":[0.99766845,0.0008966859,0.0002389128,0.00040484115,0.0006432987,0.00014779565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011971564,0.00020376737,0.0004221316,0.000460003,0.00035986013,0.0001833596,0.0005250771,0.00016512975,0.00007076859],"category_scores_gemma":[0.0011920377,0.00016694918,0.00020556162,0.002252685,0.0002912201,0.00041240492,0.00006905846,0.00043045974,0.000012476123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033809326,0.0024531856,0.037418794,0.0004379345,0.0075075873,0.00081187196,0.0035051059,0.065293975,0.108870886,0.085202694,0.014416727,0.6707003],"study_design_scores_gemma":[0.00081683806,0.00026372494,0.0023677882,0.000032870244,0.00051580084,0.0000021619562,0.00018405438,0.9924109,0.0017754378,0.00051088084,0.0009302427,0.00018932218],"about_ca_topic_score_codex":0.0000504801,"about_ca_topic_score_gemma":0.000104529914,"teacher_disagreement_score":0.92711693,"about_ca_system_score_codex":0.00040985332,"about_ca_system_score_gemma":0.0005057902,"threshold_uncertainty_score":0.680799},"labels":[],"label_agreement":null},{"id":"W4412446698","doi":"10.1109/dsp65409.2025.11075027","title":"Learning Beyond Generated Targets: A Modified SFNet for CBCT Image Enhancement","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Computer vision; Image enhancement; Artificial intelligence; Image (mathematics)","score_opus":0.01185725199177786,"score_gpt":0.2661715184589592,"score_spread":0.25431426646718136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412446698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028860488,0.00012450614,0.9785119,0.0009483735,0.0007188541,0.00033940858,7.893339e-7,0.00027665283,0.01619343],"genre_scores_gemma":[0.6312158,0.000040064904,0.33886293,0.0015008675,0.00012813493,0.00038472773,0.000011596548,0.000014658683,0.027841201],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896425,0.000039885654,0.00019991247,0.00040164814,0.00013566912,0.0002586219],"domain_scores_gemma":[0.9994135,0.00006377274,0.000059026064,0.0002929923,0.0001335876,0.000037130816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024757138,0.000116620875,0.00012422369,0.00011166078,0.00020006525,0.00016064454,0.00038304628,0.000049718667,0.000044166296],"category_scores_gemma":[0.000038658065,0.000110746005,0.00005266099,0.00039384945,0.000020497151,0.0003060033,0.00015324308,0.000106874526,0.00002030844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012127085,0.00017818355,0.000082253246,0.00015744717,0.00020394602,0.000005706851,0.0010319825,0.013537254,0.40273488,0.123571895,0.09275558,0.3656196],"study_design_scores_gemma":[0.0004961004,0.00016973652,0.0000446311,0.00001013136,0.0000066394655,6.6327726e-7,0.000021136546,0.6328642,0.32964298,0.0055207214,0.031080687,0.00014235848],"about_ca_topic_score_codex":0.00003935028,"about_ca_topic_score_gemma":0.000013065295,"teacher_disagreement_score":0.63964903,"about_ca_system_score_codex":0.0001483036,"about_ca_system_score_gemma":0.00009444583,"threshold_uncertainty_score":0.45160908},"labels":[],"label_agreement":null},{"id":"W4412587288","doi":"10.1101/2025.07.20.665804","title":"Deep-learning triage of 3D pathology datasets for comprehensive and efficient pathologist assessments","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Digital pathology; Triage; Medical diagnosis; Computer science; Context (archaeology); Pathology; Risk stratification; Surgical pathology; Histopathology; Deep learning; Barrett's esophagus; Biopsy; Dysplasia; Medicine; Artificial intelligence; Cancer; Adenocarcinoma; Medical emergency; Biology","score_opus":0.026589940294244926,"score_gpt":0.2878122084044346,"score_spread":0.26122226811018967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412587288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1533763,0.0016416876,0.840178,0.00008794233,0.0022516658,0.0013090263,0.0007082859,0.00044045754,0.000006651513],"genre_scores_gemma":[0.8413969,0.00029249338,0.1576432,0.00013812163,0.00011225975,0.00037558688,0.0000024921203,0.000036825553,0.0000020687091],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674714,0.00038171283,0.0006506658,0.0014209393,0.00032125274,0.00047830262],"domain_scores_gemma":[0.9965589,0.0004107396,0.000801013,0.0015508092,0.00055089896,0.00012760494],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00085818133,0.0004607544,0.0007436025,0.00038387722,0.00022215035,0.00017803459,0.0010827663,0.00048605478,0.0000028410216],"category_scores_gemma":[0.00030981132,0.00051052356,0.000111475696,0.00047561142,0.00020667845,0.00013930755,0.0020168333,0.0007202292,0.0000032821013],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006641415,0.0015324471,0.013076634,0.012282422,0.0013317993,0.00067510724,0.0002979135,0.05450005,0.89587814,0.015723538,0.0020485327,0.0019893],"study_design_scores_gemma":[0.005443697,0.0012544111,0.13409914,0.0017358052,0.0005247854,4.769587e-7,0.00002393432,0.6560312,0.18378855,0.0000438389,0.014325953,0.0027282261],"about_ca_topic_score_codex":0.000021450413,"about_ca_topic_score_gemma":0.0000012679521,"teacher_disagreement_score":0.71208954,"about_ca_system_score_codex":0.00024757496,"about_ca_system_score_gemma":0.00040078635,"threshold_uncertainty_score":0.99973464},"labels":[],"label_agreement":null},{"id":"W4412610790","doi":"10.1109/aaicv66571.2025.00060","title":"Optimizing MCMC-Driven Bayesian Neural Networks for High-Precision Medical Image Classification in Small Sample Sizes","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Artificial intelligence; Bayesian probability; Sample (material); Pattern recognition (psychology); Artificial neural network; Sample size determination; Machine learning; Statistics; Mathematics","score_opus":0.022263812246298833,"score_gpt":0.28402034580869073,"score_spread":0.2617565335623919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412610790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025026072,0.000049913255,0.98934877,0.0058379527,0.001087664,0.00038460185,0.000001370635,0.0002167708,0.0005703767],"genre_scores_gemma":[0.58390915,0.000024698094,0.41527283,0.00050905533,0.00010395047,0.00009670755,0.0000065359036,0.000008003345,0.00006906846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849397,0.00009430281,0.00037358876,0.000521901,0.00020895303,0.00030729198],"domain_scores_gemma":[0.99829334,0.0009852049,0.0000830919,0.00046986068,0.00008787873,0.00008060753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049028907,0.00013574878,0.00018447604,0.00019217235,0.00013029648,0.00016374866,0.0008241773,0.00017030656,0.000042589876],"category_scores_gemma":[0.0003391604,0.00012695786,0.00006039992,0.000627393,0.000046074805,0.0003987554,0.00026179999,0.00022403446,0.0000022953475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006970664,0.00007143037,0.0006639547,0.000029453915,0.000014368087,0.0000038681446,0.00017553386,0.026607277,0.0006755099,0.044221498,0.0019222816,0.9255451],"study_design_scores_gemma":[0.0005683545,0.000060485083,0.003133544,0.000046352077,0.0000042119395,0.0000014359047,0.00002621439,0.98655176,0.0006644301,0.008475336,0.0003439729,0.00012392421],"about_ca_topic_score_codex":0.0002922869,"about_ca_topic_score_gemma":0.0010292928,"teacher_disagreement_score":0.9599445,"about_ca_system_score_codex":0.0001953176,"about_ca_system_score_gemma":0.00009822638,"threshold_uncertainty_score":0.5177191},"labels":[],"label_agreement":null},{"id":"W4412616832","doi":"10.32768/abc.6520237689199","title":"Image-Guided Pre-Operative Magnetic Seed Localization of Breast Lesions: Experience of a Northern Ontario Hospital with the Magnetic Occult Lesion Localization Instrument (MOLLI)","year":2025,"lang":"en","type":"article","venue":"Archives of Breast Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences North; NOSM University","funders":"","keywords":"Occult; Lesion; Medicine; Radiology; Magnetic resonance imaging; Pathology","score_opus":0.006933717805809009,"score_gpt":0.23981907455049492,"score_spread":0.2328853567446859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412616832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41332337,0.0003383117,0.5840715,0.0008349832,0.000165947,0.0007350788,0.000040211624,0.000035883742,0.00045467712],"genre_scores_gemma":[0.9952155,0.00008338968,0.0042124176,0.00007656932,0.00001954063,0.00014894958,0.0000059478816,0.000014332232,0.00022336477],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99817634,0.00014699566,0.0005154097,0.00046672893,0.00046126646,0.00023328807],"domain_scores_gemma":[0.99849045,0.00008943557,0.00039026284,0.00060578756,0.00036849387,0.0000555615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093973955,0.00023356044,0.0003044948,0.00017874512,0.00015914967,0.00004163402,0.0006835398,0.000050833063,0.00004910925],"category_scores_gemma":[0.00001190486,0.00016975318,0.00008243612,0.0007459736,0.0006401039,0.00040438777,0.00026682593,0.0001305134,0.0000010139808],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014322596,0.00086807064,0.3326239,0.00062064675,0.00024085905,0.0000054918905,0.10989596,0.08566118,0.027366227,0.0018902511,0.00019306093,0.4392021],"study_design_scores_gemma":[0.0017973575,0.0009580604,0.8283469,0.0012651343,0.000090678346,0.000045217246,0.0014986349,0.1432951,0.021679385,0.0005159846,0.00015838837,0.00034913654],"about_ca_topic_score_codex":0.020396588,"about_ca_topic_score_gemma":0.025544554,"teacher_disagreement_score":0.58189213,"about_ca_system_score_codex":0.00018874637,"about_ca_system_score_gemma":0.00069290196,"threshold_uncertainty_score":0.99223673},"labels":[],"label_agreement":null},{"id":"W4412631047","doi":"10.1038/s41746-025-01788-8","title":"Personalized federated learning for predicting disability progression in multiple sclerosis using real-world routine clinical data","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep de Saint Jerome; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Université de Montréal","funders":"Cliniques Universitaires Saint-Luc; Faculty of Medicine and Health, University of Sydney; Allergan; EMD Serono; Koç Üniversitesi Translasyonel Tıp Araştırma Merkezi; Szegedi Tudományegyetem; Vlaamse regering; Universiteit Hasselt; Debreceni Egyetem; Universiteit Antwerpen; Koning Boudewijnstichting; lékařská fakulta Univerzity Karlovy; Teva Pharmaceutical Industries; Università di Bologna; Razi University; Hunter Medical Research Institute; Univerzita Karlova v Praze; Karadeniz Teknik Üniversitesi; Sanofi Genzyme; Universität Basel; Agentschap Innoveren en Ondernemen; KU Leuven; Università degli Studi di Firenze; Eisai; Universidade do Porto; Fonds Wetenschappelijk Onderzoek; Všeobecná Fakultní Nemocnice v Praze; Biogen; Celgene; Koç Üniversitesi; H. Lundbeck A/S; Monash University; Alexion Pharmaceuticals; European Commission; Multiple Sclerosis International Federation; Sultan Qaboos University; Sanofi; American University of Beirut; Bristol-Myers Squibb; Università di Catania; Amgen","keywords":"Multiple sclerosis; Real world data; Computer science; Medicine; Data science; Psychiatry","score_opus":0.20644145412923182,"score_gpt":0.41874933950563153,"score_spread":0.21230788537639972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412631047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5189584,0.00016831102,0.4744191,0.002528763,0.0013856381,0.0009839521,0.000016571656,0.0003934552,0.0011458143],"genre_scores_gemma":[0.9923364,0.000022444015,0.00688647,0.0001029591,0.00032016446,0.000036919784,0.0000830405,0.000014526315,0.00019707161],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747306,0.00015447443,0.0007960891,0.0008799201,0.00035008832,0.00034636317],"domain_scores_gemma":[0.99734324,0.001549955,0.00023655304,0.00064559537,0.00012464651,0.00009998537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017965656,0.0001858093,0.00042162882,0.00012684439,0.00027023983,0.00018274362,0.00067723484,0.00009644715,0.000005113815],"category_scores_gemma":[0.004726878,0.00015484258,0.000053864416,0.0010341895,0.00033209767,0.0010937611,0.0006607891,0.0003797954,0.0000010808064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019059269,0.00012808121,0.6312663,0.00007596549,0.00002161698,0.0000018152543,0.00015684075,0.00013423632,0.0002545909,0.000117636955,0.0002466159,0.3674057],"study_design_scores_gemma":[0.0034219294,0.00027663633,0.10777698,0.0015557288,0.000020657953,0.000001939283,0.0001773213,0.8843067,0.00013826817,0.0002227066,0.0019469243,0.00015417262],"about_ca_topic_score_codex":0.000310257,"about_ca_topic_score_gemma":0.000318564,"teacher_disagreement_score":0.8841725,"about_ca_system_score_codex":0.0003136073,"about_ca_system_score_gemma":0.00014483366,"threshold_uncertainty_score":0.63142973},"labels":[],"label_agreement":null},{"id":"W4412739692","doi":"10.21203/rs.3.rs-6768159/v1","title":"Lightweight U-Net for Breast Ultrasound Image Segmentation","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Breast ultrasound; Segmentation; Computer science; Net (polyhedron); Image (mathematics); Artificial intelligence; Ultrasound; Computer vision; Image segmentation; Medicine; Mathematics; Radiology; Breast cancer; Internal medicine; Mammography; Geometry","score_opus":0.041825596806554226,"score_gpt":0.397585156555221,"score_spread":0.35575955974866674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412739692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012291748,0.00052495045,0.9824885,0.0033680864,0.0018101353,0.0030964406,0.00086518575,0.0004039869,0.0062135314],"genre_scores_gemma":[0.40256128,0.00223593,0.5507455,0.00043521408,0.004887972,0.011588613,0.0011687374,0.00019026393,0.026186468],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962316,0.0004147843,0.00034671128,0.0011287548,0.0011881205,0.00069001864],"domain_scores_gemma":[0.9960147,0.0010613073,0.00012725842,0.0014009756,0.0012465949,0.00014912216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001746545,0.0002618904,0.00027491432,0.00065688073,0.0004366864,0.0009319789,0.0018204673,0.0003246975,0.00007160232],"category_scores_gemma":[0.00022580645,0.00026378935,0.00019353695,0.00080443406,0.00011779569,0.00044934094,0.0016627783,0.001077785,0.00007559084],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004525663,0.0007240532,0.0013805422,0.014414368,0.00059641746,0.00006239422,0.0062380433,0.0016964395,0.02560054,0.050117005,0.29108036,0.6076373],"study_design_scores_gemma":[0.004836127,0.0018432505,0.023121174,0.0069114007,0.00013101869,0.00021979454,0.0012051438,0.15130053,0.2735004,0.40341252,0.12978634,0.0037322836],"about_ca_topic_score_codex":0.00020522729,"about_ca_topic_score_gemma":0.00007111811,"teacher_disagreement_score":0.60390496,"about_ca_system_score_codex":0.001052635,"about_ca_system_score_gemma":0.00097401714,"threshold_uncertainty_score":0.9999814},"labels":[],"label_agreement":null},{"id":"W4412785360","doi":"10.2196/71974","title":"K-Means Clustering and Classification of Breast Cancer Images Using Histogram of Oriented Gradients Features and Convolutional Neural Network Models: Diagnostic Image Analysis Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Cluster analysis; Computer science; Histogram; Breast cancer; Feature extraction; Artificial neural network; k-means clustering; Cancer; Image (mathematics); Medicine; Internal medicine","score_opus":0.047330970817786304,"score_gpt":0.38488589064273304,"score_spread":0.33755491982494673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412785360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69085467,0.00042431362,0.30786893,0.00013557954,0.0001052685,0.00047341202,0.000037508624,0.000021329417,0.00007902396],"genre_scores_gemma":[0.9975161,0.00008413393,0.0022509354,0.0000046533182,0.000017888395,0.00009981841,0.0000035596029,0.0000044134204,0.000018505214],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983361,0.00031730055,0.00030310152,0.0002925975,0.00048741067,0.00026349255],"domain_scores_gemma":[0.9984774,0.00040569363,0.00015854104,0.0002580005,0.0006462782,0.00005408375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066881516,0.0001058312,0.00023782627,0.0006003195,0.00026376572,0.000069775386,0.00024942544,0.00004146682,0.0000021573956],"category_scores_gemma":[0.000039684368,0.00009715332,0.00004457948,0.0022856677,0.00035186266,0.00083603297,0.0004234285,0.00022891045,1.0905633e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007197779,0.0014387366,0.64209247,0.0012298833,0.002266264,0.000008463017,0.039583918,0.19500521,0.006033868,0.009137488,0.0018246593,0.10065928],"study_design_scores_gemma":[0.0002325267,0.0000735115,0.4785448,0.000049519567,0.00003084276,0.0000020455611,0.00039537143,0.52018905,0.000044114615,0.00039430766,0.0000022531792,0.00004164704],"about_ca_topic_score_codex":0.0008867317,"about_ca_topic_score_gemma":0.00032571563,"teacher_disagreement_score":0.32518387,"about_ca_system_score_codex":0.00026282528,"about_ca_system_score_gemma":0.00008935021,"threshold_uncertainty_score":0.39617977},"labels":[],"label_agreement":null},{"id":"W4412788639","doi":"10.2196/75022","title":"Deep Learning and Image Generator Health Tabular Data (IGHT) for Predicting Overall Survival in Patients With Colorectal Cancer: Retrospective Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Colorectal cancer; Medicine; Computer science; Cancer; Artificial intelligence; World Wide Web; Internal medicine","score_opus":0.010358786814447194,"score_gpt":0.30003083174071804,"score_spread":0.28967204492627086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412788639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7520756,0.00007804239,0.24531692,0.0002615064,0.000455363,0.0015507522,0.000019279065,0.000113883354,0.00012864025],"genre_scores_gemma":[0.9841202,0.000049822163,0.015082892,0.00034708454,0.00008875544,0.00024524084,0.000039137652,0.000011777687,0.00001510449],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801993,0.000092802795,0.0005460875,0.00027863792,0.00072796445,0.0003345559],"domain_scores_gemma":[0.9990132,0.00011519552,0.00025527232,0.00032255033,0.00014596175,0.00014782044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009817376,0.00015504741,0.00031032323,0.00013100244,0.00022371576,0.00013746507,0.0006177634,0.00008363723,0.000005376832],"category_scores_gemma":[0.00021882987,0.00012926935,0.000014229032,0.0004292233,0.00006985941,0.000960936,0.0006456223,0.00045309766,6.198058e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015595036,0.00022793877,0.94449717,0.0002151647,0.00007645693,0.0000019311017,0.00834154,0.000114071685,6.529694e-7,0.00033371997,0.00048464615,0.04555077],"study_design_scores_gemma":[0.003597086,0.001124556,0.31081665,0.00015159331,0.000009169886,6.684369e-7,0.001024924,0.6823674,0.000008336521,0.00005929656,0.0006841313,0.00015623824],"about_ca_topic_score_codex":0.0001216873,"about_ca_topic_score_gemma":0.0012608891,"teacher_disagreement_score":0.6822533,"about_ca_system_score_codex":0.00041770577,"about_ca_system_score_gemma":0.00046382388,"threshold_uncertainty_score":0.5271451},"labels":[],"label_agreement":null},{"id":"W4412852478","doi":"10.1007/978-3-031-96628-6_3","title":"PathTTT: Test-Time Training with Meta-auxiliary Learning for Pathology Image Classification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Contextual image classification; Test (biology); Pattern recognition (psychology); Image (mathematics); Training (meteorology); Machine learning; Natural language processing","score_opus":0.0358980018059981,"score_gpt":0.2631283829052097,"score_spread":0.22723038109921156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412852478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019594454,0.00024329108,0.9931738,0.0016753686,0.0008152391,0.00078529905,0.000011088365,0.0003740499,0.002902298],"genre_scores_gemma":[0.03944636,0.00003660416,0.9557286,0.0015897017,0.0004442602,0.00019707248,0.000016559388,0.00006608612,0.0024747571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99563074,0.00007999777,0.00060163136,0.002195868,0.000761273,0.00073047885],"domain_scores_gemma":[0.9954256,0.0021356158,0.00053569657,0.0012938225,0.00048839947,0.0001208929],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016489419,0.00063090876,0.0008925198,0.0009432852,0.0004760064,0.00048939616,0.0023962737,0.00041273527,0.00001956363],"category_scores_gemma":[0.00042596683,0.0005342684,0.00025286333,0.0007721984,0.0007349037,0.00080233684,0.00063138496,0.0010996341,0.000021595819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024551413,0.000025471154,0.0000133811345,0.000085118794,0.00010039933,0.00006541316,0.0011106947,0.014190177,0.0032391392,0.005548598,0.00005720424,0.97553986],"study_design_scores_gemma":[0.0004408003,0.00079476484,0.00010770362,0.0002361141,0.00020051411,0.00016288097,9.3325804e-7,0.9502208,0.0037730667,0.03980473,0.0034134663,0.00084417145],"about_ca_topic_score_codex":0.000006411952,"about_ca_topic_score_gemma":0.000024142266,"teacher_disagreement_score":0.9746957,"about_ca_system_score_codex":0.00045082511,"about_ca_system_score_gemma":0.0010689398,"threshold_uncertainty_score":0.99971086},"labels":[],"label_agreement":null},{"id":"W4413147061","doi":"10.1109/sas65169.2025.11105127","title":"Improved Breast Cancer Classification Using Prior Information and Decentralized Training Approach","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cancer; Training (meteorology); Breast cancer; Artificial intelligence; Machine learning; Medicine; Internal medicine","score_opus":0.03448584583492557,"score_gpt":0.28464634289916085,"score_spread":0.25016049706423527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413147061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019934516,0.00005771317,0.9767449,0.0007721354,0.00028856008,0.0002251755,0.0000019625145,0.0001533081,0.0018217372],"genre_scores_gemma":[0.87209964,0.00005499872,0.12730213,0.0004111182,0.000023027771,0.00004210349,0.000001994231,0.0000030702442,0.000061948434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993437,0.000024648118,0.00019863063,0.00018062184,0.00009867645,0.00015374602],"domain_scores_gemma":[0.9995807,0.000017717171,0.000090712376,0.00019190786,0.00008236255,0.00003661403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016689366,0.00008013081,0.00008714709,0.00012188937,0.00014150483,0.0002168621,0.0001780415,0.00005626024,0.0000063191324],"category_scores_gemma":[0.000010027164,0.000074160474,0.000018499912,0.00041566778,0.00002636472,0.0014720667,0.00006838711,0.00007263799,8.52289e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017971397,0.000010260214,0.000594736,0.000045210607,0.00001804424,3.46787e-8,0.0012730375,0.00024100745,0.006750931,0.014383204,0.00008145263,0.97658414],"study_design_scores_gemma":[0.00043400598,0.0000052996193,0.014948731,0.000018084855,0.000008559014,0.000009896506,0.00025898815,0.9821441,0.00095383177,0.0002800555,0.00084962806,0.00008882015],"about_ca_topic_score_codex":0.00021324056,"about_ca_topic_score_gemma":0.000014721215,"teacher_disagreement_score":0.9819031,"about_ca_system_score_codex":0.0001918898,"about_ca_system_score_gemma":0.00019876627,"threshold_uncertainty_score":0.30241764},"labels":[],"label_agreement":null},{"id":"W4413147113","doi":"10.1109/cvpr52734.2025.02857","title":"Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Queen's University; Queen's University Belfast; Department for the Economy","keywords":"Discriminator; Computer science; Training (meteorology); Sampling (signal processing); Quality (philosophy); Training set; Artificial intelligence; Computer vision; Detector; Telecommunications","score_opus":0.09434456230474401,"score_gpt":0.3671695660295568,"score_spread":0.2728250037248128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413147113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021867936,0.000047658672,0.97553587,0.0007022861,0.00091588765,0.0001857356,0.0000070897677,0.00016570048,0.0005718393],"genre_scores_gemma":[0.97519404,0.0000028520153,0.024518922,0.00011581761,0.000024582414,0.000012108912,0.000005762665,0.000005536966,0.000120369135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985945,0.000112558446,0.00035564083,0.0004836419,0.0002534436,0.00020021216],"domain_scores_gemma":[0.99819916,0.0002537956,0.00017000259,0.0012669923,0.00008550321,0.000024539624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012504542,0.000105781204,0.00014390507,0.00009869021,0.00025716537,0.00008494516,0.00116433,0.00004904208,0.0000051788256],"category_scores_gemma":[0.00010130572,0.00007749938,0.00004798925,0.00058999803,0.00006269912,0.00035357152,0.00063490326,0.00017054514,0.0000015303449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014296265,0.00005115466,0.00009284346,0.00013817765,0.00003390471,5.1449337e-7,0.0029241545,0.005409183,0.019421156,0.013705033,0.000057965237,0.95815164],"study_design_scores_gemma":[0.00012264565,0.000026292555,0.0023662455,0.000038570644,0.000014977582,0.0000036386386,0.0015182842,0.9904895,0.0040144906,0.0011104994,0.00019223649,0.000102632235],"about_ca_topic_score_codex":0.001000614,"about_ca_topic_score_gemma":0.00042594387,"teacher_disagreement_score":0.9850803,"about_ca_system_score_codex":0.0001821923,"about_ca_system_score_gemma":0.00015922285,"threshold_uncertainty_score":0.3160333},"labels":[],"label_agreement":null},{"id":"W4413174753","doi":"10.18280/ts.420416","title":"Early Diagnosis of Mammogram Images Using Hybird Deep and Machine Learning Algorithm","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Algorithm; Deep learning; Pattern recognition (psychology)","score_opus":0.014083500965581747,"score_gpt":0.244013649789575,"score_spread":0.22993014882399324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413174753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12167009,0.000689037,0.8769379,0.00016746987,0.00014920863,0.00014831536,0.0000038972094,0.0000951863,0.00013885628],"genre_scores_gemma":[0.89846617,0.00007671566,0.10126286,0.00007251291,0.000044018074,0.000027877166,0.0000011790886,0.000007976715,0.00004070366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989819,0.00007520965,0.00023971022,0.00028896163,0.00022217337,0.00019202412],"domain_scores_gemma":[0.99954367,0.00010369922,0.00010369844,0.00014319677,0.00006154294,0.000044218355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026215534,0.00012280818,0.00015855303,0.00017269929,0.00013591288,0.00010379459,0.00025196662,0.00003888393,0.00003487551],"category_scores_gemma":[0.000011045681,0.00012419016,0.00004936088,0.00036689048,0.000062132385,0.00030554348,0.00016511978,0.00013752522,0.0000014822616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010577385,0.00006913502,0.037099473,0.00005089383,0.000063659696,0.0000072109906,0.0004263885,0.0009570599,0.003418927,0.00055578677,0.000052887564,0.957288],"study_design_scores_gemma":[0.0011115619,0.00046775283,0.04971572,0.00014494601,0.00006695261,0.0000120700915,0.000050311017,0.8893769,0.05501151,0.0017945375,0.0019507693,0.00029696448],"about_ca_topic_score_codex":0.0003111181,"about_ca_topic_score_gemma":0.000011509526,"teacher_disagreement_score":0.956991,"about_ca_system_score_codex":0.00006188658,"about_ca_system_score_gemma":0.00002847601,"threshold_uncertainty_score":0.50643283},"labels":[],"label_agreement":null},{"id":"W4413195264","doi":"10.1089/ipm.12.04.06","title":"From Microscopes to Computers: Reaching an Inflection Point in Digital Pathology","year":2025,"lang":"en","type":"article","venue":"Inside Precision Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Inflection point; Digital pathology; Inflection; Point (geometry); Digital microscope; Microscope; Computer science; Computer graphics (images); Pathology; Artificial intelligence; Medicine; Mathematics; Geometry","score_opus":0.018981939263758605,"score_gpt":0.3157595855315894,"score_spread":0.29677764626783076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413195264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39675122,0.00013029088,0.59740245,0.0028874918,0.0018765001,0.0001813605,0.0000013135211,0.00012980298,0.00063955307],"genre_scores_gemma":[0.9488449,0.000020056817,0.04765397,0.0030984743,0.00029508112,0.000021031527,0.000007573733,0.000009266559,0.000049629074],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831,0.000112506845,0.0004687271,0.0006361694,0.00025573364,0.00021683342],"domain_scores_gemma":[0.99862,0.00044281103,0.00008572774,0.00065631414,0.00009440857,0.00010076877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005431404,0.00015574085,0.00027595597,0.00064378185,0.00007827261,0.000120189674,0.0005944266,0.00010120572,0.000010027366],"category_scores_gemma":[0.0005668094,0.00013717383,0.00002553221,0.00089673913,0.00004589093,0.0009759743,0.00040445614,0.00027858565,0.000026997002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009023657,0.00005668551,0.001867315,0.000006316407,0.000008146121,0.000053374042,0.006840653,0.00095092604,0.054296482,0.00034070815,0.0032077632,0.9322814],"study_design_scores_gemma":[0.009699197,0.005151421,0.19273028,0.0071390294,0.000046431218,0.00027632155,0.002323719,0.15075451,0.108673744,0.466785,0.054789133,0.0016311827],"about_ca_topic_score_codex":0.0008713794,"about_ca_topic_score_gemma":0.00041148395,"teacher_disagreement_score":0.93065023,"about_ca_system_score_codex":0.00026760722,"about_ca_system_score_gemma":0.000061498555,"threshold_uncertainty_score":0.5593787},"labels":[],"label_agreement":null},{"id":"W4413205920","doi":"10.1109/iccai66501.2025.00009","title":"Rel-UNet: Reliable Tumor Segmentation via Uncertainty Quantification in nnU-Net","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Reliability engineering; Net (polyhedron); Segmentation; Risk analysis (engineering); Environmental science; Artificial intelligence; Business; Mathematics; Engineering","score_opus":0.011795533344941404,"score_gpt":0.2694359190072657,"score_spread":0.25764038566232433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413205920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017014686,0.00006594037,0.97329664,0.0020683084,0.0009341153,0.0003136626,6.018008e-7,0.00035786428,0.005948205],"genre_scores_gemma":[0.9481679,0.000024261295,0.047659803,0.000958254,0.00003357823,0.00010807901,0.000007170256,0.000009507684,0.0030314212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887943,0.00005514885,0.0002878669,0.00041055464,0.00018174764,0.0001852401],"domain_scores_gemma":[0.999277,0.000059048518,0.00008446543,0.00048118367,0.00007184399,0.000026465457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037791886,0.000096097785,0.000102644495,0.00021983974,0.00008335645,0.000098397264,0.0003800566,0.000047066333,0.000019011999],"category_scores_gemma":[0.000025522306,0.00009639627,0.000026107457,0.0010716481,0.000022206126,0.0005163197,0.00008421822,0.000114083625,0.00009305808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016385048,0.00042046714,0.02296993,0.00023678772,0.00005556564,0.000018172934,0.002156358,0.12071755,0.09029381,0.20659238,0.060588762,0.49578637],"study_design_scores_gemma":[0.0006839679,0.000080424,0.013226966,0.00006686916,0.0000059978756,0.000004725618,0.00014555796,0.85772747,0.093544655,0.021620486,0.012646517,0.00024637938],"about_ca_topic_score_codex":0.001704893,"about_ca_topic_score_gemma":0.0007617843,"teacher_disagreement_score":0.93115324,"about_ca_system_score_codex":0.00037058294,"about_ca_system_score_gemma":0.00010093179,"threshold_uncertainty_score":0.39309257},"labels":[],"label_agreement":null},{"id":"W4413251653","doi":"10.3390/diagnostics15161983","title":"From Microscopes to Monitors: Unique Opportunities and Challenges in Digital Pathology Implementation in Remote Canadian Regions","year":2025,"lang":"en","type":"article","venue":"Diagnostics","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Northern College; University Health Network","funders":"","keywords":"Telepathology; Digital pathology; Workflow; Virtual microscopy; Computer science; Health care; Economic shortage; Workforce; Data science; Telemedicine; Pathology; Medicine; Artificial intelligence","score_opus":0.05317098313799944,"score_gpt":0.3069486994195405,"score_spread":0.25377771628154105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413251653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8970458,0.004713764,0.037884437,0.057101082,0.0011644756,0.0006131332,0.00014970037,0.00008487168,0.001242725],"genre_scores_gemma":[0.9808325,0.013083796,0.0052167997,0.00074256404,0.000049114547,0.000030512876,0.000017378194,0.000006901678,0.000020444655],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99931675,0.00003741654,0.00016172841,0.00024489858,0.000049458682,0.0001897616],"domain_scores_gemma":[0.9993356,0.00032006312,0.000026276639,0.00020490553,0.000035463127,0.000077699115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093928225,0.00008043534,0.000099302044,0.00038222663,0.000039527975,0.00009177827,0.00018776876,0.0000622228,0.0000012588785],"category_scores_gemma":[0.0001539294,0.00009648558,0.000008208657,0.00022379066,0.00002766391,0.00023108617,0.000104672894,0.00008410772,0.0000021733238],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054035672,0.000026326274,0.04040338,0.000024976198,0.000009277079,0.00032041883,0.008820111,0.000071185335,0.00007497474,0.018747289,0.0022367695,0.9292599],"study_design_scores_gemma":[0.0014339577,0.00040154313,0.6904322,0.0010292752,0.000016924627,0.0000271487,0.018741272,0.0027900473,0.006008456,0.15328784,0.12496686,0.00086448167],"about_ca_topic_score_codex":0.07482109,"about_ca_topic_score_gemma":0.43565702,"teacher_disagreement_score":0.9283954,"about_ca_system_score_codex":0.00021872699,"about_ca_system_score_gemma":0.00022012963,"threshold_uncertainty_score":0.93133974},"labels":[],"label_agreement":null},{"id":"W4413270899","doi":"10.1016/j.patrec.2025.06.016","title":"MAMBO-NET: Multi-causal aware modeling backdoor-intervention optimization for medical image segmentation network","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Backdoor; Image (mathematics); Artificial intelligence; Computer science; Segmentation; Image segmentation; Intervention (counseling); Pattern recognition (psychology); Computer vision; Psychology; Computer security","score_opus":0.02589340498463851,"score_gpt":0.2960952029256575,"score_spread":0.270201797941019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413270899","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011499638,0.000030634517,0.98124105,0.0043729995,0.0017909189,0.00070719724,0.000024572848,0.00029787282,0.0000351065],"genre_scores_gemma":[0.47051603,0.000107707914,0.5082834,0.01761981,0.0010875505,0.0011899568,0.0010524829,0.00007151732,0.000071590126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979828,0.000172246,0.00053416006,0.00058459974,0.00036779264,0.0003584241],"domain_scores_gemma":[0.99913096,0.00012099159,0.00019121087,0.00026838353,0.0002041541,0.00008427384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878388,0.00020981547,0.0001838691,0.00020500131,0.0002482535,0.00023017218,0.0003585983,0.00013624772,0.00016726705],"category_scores_gemma":[0.00006240183,0.00024005634,0.00015905255,0.00037059368,0.000033432243,0.0010291073,0.0001157191,0.00019383359,0.000047757443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007200633,0.00016154737,0.00076694565,0.00032943874,0.00014150087,0.000010820588,0.0001594672,0.29323155,0.001038975,0.000024254012,0.0059899273,0.69807357],"study_design_scores_gemma":[0.0017654891,0.000050295635,0.00016213681,0.00036436922,0.00003705127,0.0000069284692,0.000030696836,0.99559605,0.0014401386,0.00025576967,0.000054615266,0.00023644294],"about_ca_topic_score_codex":0.00006652402,"about_ca_topic_score_gemma":0.00004545086,"teacher_disagreement_score":0.7023645,"about_ca_system_score_codex":0.00025318202,"about_ca_system_score_gemma":0.00004504687,"threshold_uncertainty_score":0.97892135},"labels":[],"label_agreement":null},{"id":"W4413334194","doi":"10.1101/2025.08.14.670178","title":"Genomic Characterization of Lung Cancer in Never-Smokers Using Deep Learning","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"National Institutes of Health; U.S. Department of Health and Human Services","keywords":"CDKN2A; KRAS; Receiver operating characteristic; Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Digital pathology; Computational biology; Pattern recognition (psychology); Biology; Cancer; Machine learning; Colorectal cancer; Genetics","score_opus":0.011436629086722404,"score_gpt":0.23731018484536492,"score_spread":0.2258735557586425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413334194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7514546,0.0006828753,0.24480897,0.00008245262,0.0021932018,0.00050446927,0.000036788202,0.00023284188,0.0000038186695],"genre_scores_gemma":[0.98972106,0.0005318663,0.009270778,0.00008984095,0.00020637357,0.00012614057,1.7323508e-7,0.000048744067,0.0000050201756],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973234,0.00021259811,0.0006636186,0.0010087808,0.00034184154,0.00044977866],"domain_scores_gemma":[0.9977696,0.00004520185,0.00076069066,0.00097625254,0.00035348057,0.00009477335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052707485,0.00040231785,0.000533591,0.0006932739,0.00011933568,0.00016640451,0.0010341977,0.00043659596,0.000016303899],"category_scores_gemma":[0.00006443474,0.0005166145,0.000113252594,0.0012448587,0.00005840743,0.00057440373,0.0009925036,0.00086284225,0.000002340646],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014685453,0.000033474444,0.060035173,0.00057937624,0.000082216146,0.000008671806,0.000054762397,0.021654097,0.9171729,0.0003042945,0.0000021541978,0.00005819526],"study_design_scores_gemma":[0.0003506599,0.0000180558,0.33955204,0.0010812505,0.000060931958,8.42095e-9,0.0000012494238,0.4631166,0.19486956,0.0000017619827,0.00036253285,0.00058534415],"about_ca_topic_score_codex":0.00044133872,"about_ca_topic_score_gemma":0.000011599707,"teacher_disagreement_score":0.72230333,"about_ca_system_score_codex":0.001571287,"about_ca_system_score_gemma":0.0011411029,"threshold_uncertainty_score":0.99972856},"labels":[],"label_agreement":null},{"id":"W4413334920","doi":"10.1101/2025.08.11.669726","title":"Detection of prostate cancer in 3D pathology datasets via generative immunolabeling","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Immunolabeling; Prostate cancer; Generative grammar; Generative model; Pathology; Medicine; Cancer detection; Cancer; Prostate; Artificial intelligence; Computer science; Computational biology; Internal medicine; Biology; Immunohistochemistry","score_opus":0.010917385789075303,"score_gpt":0.240465801191294,"score_spread":0.22954841540221868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413334920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48726797,0.0058186376,0.49739474,0.000218153,0.0060491785,0.001471028,0.0013156575,0.00046031474,0.00000433402],"genre_scores_gemma":[0.97537816,0.00095150934,0.022761922,0.00010703226,0.00015171937,0.00060837675,5.845087e-7,0.000038159884,0.0000025421507],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967936,0.00033247916,0.0007567947,0.0012994976,0.00032910163,0.0004884972],"domain_scores_gemma":[0.99700475,0.00007314403,0.00067844,0.0017032499,0.00046116568,0.00007927445],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007580727,0.00045996293,0.00059829286,0.0006532463,0.00012404197,0.000120263314,0.0011311165,0.0004941029,0.000006739134],"category_scores_gemma":[0.00009909189,0.0005337732,0.000086841304,0.0012495625,0.00010611909,0.00041933896,0.0013361843,0.0009724941,0.0000067138685],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038522343,0.00007866866,0.0017940853,0.00039325678,0.000092931434,0.000040030103,0.00007316464,0.0037538263,0.99315065,0.00010487877,0.000020868049,0.00045914113],"study_design_scores_gemma":[0.00051800057,0.00007232854,0.021636229,0.00064860773,0.00004227302,3.46366e-8,0.0000015394545,0.04114939,0.9348383,0.000014796919,0.00051413104,0.0005643916],"about_ca_topic_score_codex":0.0005961815,"about_ca_topic_score_gemma":0.000112461676,"teacher_disagreement_score":0.48811018,"about_ca_system_score_codex":0.0008516969,"about_ca_system_score_gemma":0.00094442867,"threshold_uncertainty_score":0.9997114},"labels":[],"label_agreement":null},{"id":"W4413367346","doi":"10.1007/978-3-032-04228-6_12","title":"Human Papillomavirus Detection Using Novel Machine Learning Algorithm Based on Cytology Images","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Human papillomavirus; Computer science; Cytology; Artificial intelligence; Pattern recognition (psychology); Medicine; Pathology; Internal medicine","score_opus":0.03893539171720457,"score_gpt":0.30820964479284635,"score_spread":0.2692742530756418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413367346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014176843,0.00013007341,0.9419307,0.00026077346,0.0004384496,0.00029378565,0.000015918558,0.00016409498,0.056752026],"genre_scores_gemma":[0.09194801,0.0006815399,0.90322256,0.0021017215,0.000101195736,0.000063057516,0.000073763906,0.000026088159,0.0017820331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815845,0.000061388884,0.00065881835,0.00041150284,0.00045151365,0.00025835086],"domain_scores_gemma":[0.9971327,0.00021268943,0.00046380653,0.0017502797,0.00036723175,0.00007327258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010064238,0.00027672717,0.00029371644,0.0018839389,0.0012162824,0.00052995357,0.0023254745,0.00019093273,0.000006460655],"category_scores_gemma":[0.000045654957,0.00030050622,0.000060126018,0.0006812252,0.0006557153,0.0036013988,0.0015820648,0.0008691809,0.000013335748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036928543,0.000028888111,0.000028057824,0.00003583068,0.000007672307,4.901335e-7,0.00028987636,0.010539293,0.00017406854,0.0703664,0.000024789817,0.91850096],"study_design_scores_gemma":[0.0003402711,0.00011737967,0.0002613588,0.00019173659,0.0000068751247,0.000018404151,0.000004021143,0.9632659,0.00019651631,0.0014835303,0.03384208,0.00027192966],"about_ca_topic_score_codex":0.000087942804,"about_ca_topic_score_gemma":0.000021956048,"teacher_disagreement_score":0.9527266,"about_ca_system_score_codex":0.0005127321,"about_ca_system_score_gemma":0.00029811496,"threshold_uncertainty_score":0.9999447},"labels":[],"label_agreement":null},{"id":"W4413419002","doi":"10.1182/blood.2025029876","title":"Artificial intelligence in hematology","year":2025,"lang":"en","type":"article","venue":"Blood","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"U.S. Food and Drug Administration; National Cancer Institute; National Institutes of Health; Incyte; Swedish Orphan Biovitrum; CSL Behring; Novo Nordisk; Sanofi; Genentech; AstraZeneca","keywords":"Workflow; Artificial intelligence; Personalized medicine; Pace; Medical physics; Computer science; Medicine; Data science; Bioinformatics","score_opus":0.017645548277878977,"score_gpt":0.27660179170183574,"score_spread":0.2589562434239568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413419002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034047194,0.00021739496,0.9580234,0.0012651839,0.0006119553,0.000078235666,1.4780363e-7,0.000103251674,0.0056531886],"genre_scores_gemma":[0.98752177,0.000007134016,0.0121946605,0.00018331241,0.000021115444,0.000016863922,8.747816e-8,0.0000016176317,0.000053457283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945325,0.000026386311,0.000144658,0.00019483008,0.000056902223,0.00012395404],"domain_scores_gemma":[0.99965197,0.000050456016,0.00002132246,0.00024734344,0.000015954736,0.00001296547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000111564645,0.000044852688,0.00007227618,0.00012799054,0.000026343525,0.00002608301,0.00035396207,0.000042653024,0.000006515582],"category_scores_gemma":[0.00003340672,0.00004757706,0.00001659273,0.00055058947,0.000021270822,0.000094150164,0.00011297442,0.00008433528,0.000043637196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003621824,0.00017636867,0.002260966,0.000014309765,0.000008447787,0.00002486415,0.00021020719,0.000084494415,0.00078442245,0.7788781,0.0000973249,0.21745688],"study_design_scores_gemma":[0.00014516692,0.00007411396,0.0028822229,0.000057154746,0.000007668015,0.000040907104,0.000044801338,0.026929094,0.48434246,0.4839346,0.001365823,0.00017600048],"about_ca_topic_score_codex":0.000026615044,"about_ca_topic_score_gemma":0.000107054315,"teacher_disagreement_score":0.9534746,"about_ca_system_score_codex":0.000020427644,"about_ca_system_score_gemma":0.000054484768,"threshold_uncertainty_score":0.19401363},"labels":[],"label_agreement":null},{"id":"W4413438262","doi":"10.62051/p44xjf14","title":"Dynamic Feature Engineering for Breast Cancer Risk Stratification: A Machine Learning System Integrating Clinical Guidelines","year":2025,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Risk stratification; Breast cancer; Stratification (seeds); Feature (linguistics); Computer science; Feature engineering; Artificial intelligence; Machine learning; Medicine; Medical physics; Cancer; Internal medicine; Biology; Deep learning","score_opus":0.07515410590438526,"score_gpt":0.4162538166870503,"score_spread":0.34109971078266504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413438262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014793687,0.0007890042,0.99170977,0.0018415073,0.0029439752,0.00089858205,0.00002886407,0.0002588572,0.000050067356],"genre_scores_gemma":[0.9487545,0.0007305793,0.04925092,0.000045515095,0.00020491738,0.00042126462,0.0000013355881,0.000016268374,0.0005746879],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661815,0.00029422774,0.00067350385,0.0009883496,0.00090247724,0.00052326254],"domain_scores_gemma":[0.9961519,0.0006867127,0.00014032905,0.00060298666,0.0022484306,0.00016961429],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0067505958,0.00021018139,0.00029419697,0.0009170118,0.0014846342,0.0010349753,0.0011249579,0.00012966366,0.0000022913985],"category_scores_gemma":[0.00012162148,0.00017717219,0.000098323944,0.0024921005,0.0002433743,0.0006074597,0.000059501413,0.000999488,0.0000070716133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037074482,0.000057687816,0.0002403446,0.00033519775,0.000066628505,0.0000015119141,0.00030223696,0.12652032,0.00038109746,0.007312093,0.00032903958,0.8644168],"study_design_scores_gemma":[0.00017019968,0.00021480344,0.00038862554,0.0006968768,0.0000101927735,0.000032738702,0.00024836743,0.9946206,0.00058878114,0.000032471286,0.002842102,0.00015424192],"about_ca_topic_score_codex":0.00048065538,"about_ca_topic_score_gemma":0.00008498497,"teacher_disagreement_score":0.94727516,"about_ca_system_score_codex":0.0007265221,"about_ca_system_score_gemma":0.00061330583,"threshold_uncertainty_score":0.9998153},"labels":[],"label_agreement":null},{"id":"W4413481029","doi":"10.3390/app15179276","title":"Automated Segmentation and Quantification of Histology Fragments for Enhanced Macroscopic Reporting","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vitalité Health Network; Université de Moncton","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.03127235523181817,"score_gpt":0.34892669497449885,"score_spread":0.3176543397426807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413481029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3035644,0.000042951397,0.69443345,0.00018168462,0.00032719277,0.0002488647,4.2510896e-7,0.0001114146,0.0010896303],"genre_scores_gemma":[0.9159875,0.0000047327617,0.083798006,0.00006834212,0.000005356941,0.00009137357,0.0000010280411,0.0000013320164,0.00004236318],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990068,0.000013948832,0.0004037164,0.00033307393,0.00012302145,0.000119444005],"domain_scores_gemma":[0.99912137,0.00009735901,0.00056637055,0.00015091029,0.0000506601,0.000013323689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062957266,0.00005474677,0.00011022311,0.000119283686,0.00022074279,0.00004675747,0.00023481435,0.00003460428,0.0000010254255],"category_scores_gemma":[0.00007495117,0.000052478703,0.000013080735,0.0004881994,0.00016275427,0.00016032081,0.000055708962,0.000025320254,6.99703e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055658916,0.000012397486,0.00060692086,0.000048666698,0.0000057584793,5.4895786e-8,0.0003497904,0.0003212749,0.92083365,0.03856889,0.00011779747,0.039129235],"study_design_scores_gemma":[0.00019427497,0.000051914616,0.0044447873,0.000017359851,0.0000051389316,7.739243e-7,0.00012720865,0.05831062,0.92754966,0.009166545,0.00007370147,0.000058006593],"about_ca_topic_score_codex":0.000017868308,"about_ca_topic_score_gemma":0.0000093593435,"teacher_disagreement_score":0.61242306,"about_ca_system_score_codex":0.00004386141,"about_ca_system_score_gemma":0.00008595408,"threshold_uncertainty_score":0.21400194},"labels":[],"label_agreement":null},{"id":"W4413494925","doi":"10.1038/s41597-025-05866-0","title":"Full Field Digital Mammography Dataset from a Population Screening Program","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. John’s Health Sciences Centre; Newfoundland and Labrador Centre for Applied Health Research; Memorial University of Newfoundland","funders":"Memorial University of Newfoundland","keywords":"Mammography; Field (mathematics); Population; Digital mammography; Mammography screening; Data science; Computer science; Medical physics; Medicine; Environmental health; Mathematics; Breast cancer; Internal medicine; Cancer","score_opus":0.03314364068906861,"score_gpt":0.3164268363211404,"score_spread":0.28328319563207177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413494925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062026507,0.00016584483,0.96846485,0.0012108614,0.004623555,0.00043410223,0.017676786,0.0005257687,0.00069557526],"genre_scores_gemma":[0.57830596,0.0000056172844,0.2589408,0.00059884647,0.00026536183,0.000069559,0.16098075,0.000017555152,0.0008155547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998037,0.000029190544,0.0002220891,0.0010907005,0.00037584396,0.00024517457],"domain_scores_gemma":[0.9961559,0.00008858781,0.00008209547,0.003568927,0.000043868018,0.00006061106],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042776891,0.00010969905,0.00009979219,0.00026297267,0.0003255818,0.0027725063,0.0032371625,0.000052606054,0.000025642403],"category_scores_gemma":[0.00012742852,0.000109592605,0.000031334912,0.0015628515,0.000074797405,0.0029957716,0.0023677498,0.00012872808,0.000051236944],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010505273,0.00003953295,0.0015002136,0.000006475723,0.000016506474,0.0000023016244,0.000019913576,0.000013752397,0.00006165675,0.00033513003,0.29901826,0.69897574],"study_design_scores_gemma":[0.00027113696,0.00007354476,0.0064625,0.00008243545,0.000019007955,0.0000026436212,0.00002820922,0.17356075,0.00035670918,0.005900313,0.812998,0.00024474048],"about_ca_topic_score_codex":0.00034683052,"about_ca_topic_score_gemma":0.00026642045,"teacher_disagreement_score":0.7095241,"about_ca_system_score_codex":0.0000225506,"about_ca_system_score_gemma":0.000050376813,"threshold_uncertainty_score":0.9982627},"labels":[],"label_agreement":null},{"id":"W4413800665","doi":"10.1101/2025.08.26.25334483","title":"The African Breast Imaging Dataset for Equitable Cancer Care: Protocol for an Open Mammogram and Ultrasound Breast Cancer Detection Dataset","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Breast cancer; Mammography; Outreach; Breast examination; Cancer; Incidence (geometry); Breast ultrasound; Family medicine; Radiology; Medical physics; Internal medicine","score_opus":0.041303223398612594,"score_gpt":0.3791196600181018,"score_spread":0.33781643661948924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413800665","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016132588,0.00027135396,0.36585745,0.002554679,0.0022205662,0.22340366,0.405244,0.0002274684,0.00005952433],"genre_scores_gemma":[0.012113084,0.00006923491,0.006790577,0.0003935759,0.00077607535,0.97423744,0.005451527,0.000067513116,0.000100947895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963358,0.00018670759,0.00052721996,0.0017387633,0.000373994,0.00083749596],"domain_scores_gemma":[0.99623895,0.000391894,0.0005195453,0.0022459473,0.00040635685,0.00019728424],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011791484,0.0005121963,0.00044627194,0.00014876215,0.0013415127,0.0025089034,0.0040370463,0.00017590987,0.0000123065865],"category_scores_gemma":[0.000055504104,0.00041983425,0.000077885314,0.0003953052,0.00018181605,0.0012092724,0.003692178,0.00047546558,9.175199e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011300719,0.00013683485,0.0052047726,0.0022104676,0.0002643821,0.0000025460029,0.0006297531,0.0012760048,0.0013402676,0.00030532246,0.08261372,0.9048858],"study_design_scores_gemma":[0.002475518,0.00022500903,0.004382322,0.00060778856,0.00021878886,0.00013138991,0.00025308845,0.034049705,0.00314773,0.003387029,0.94996566,0.001156004],"about_ca_topic_score_codex":0.014969768,"about_ca_topic_score_gemma":0.024933368,"teacher_disagreement_score":0.90372986,"about_ca_system_score_codex":0.0007240621,"about_ca_system_score_gemma":0.00094961864,"threshold_uncertainty_score":0.99995863},"labels":[],"label_agreement":null},{"id":"W4413940286","doi":"10.1007/s10549-025-07801-8","title":"Natural language processing for local, regional, and distant breast cancer relapse identification in pathology reports","year":2025,"lang":"en","type":"article","venue":"Breast Cancer Research and Treatment","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Breast cancer; Medicine; Cancer; Cohort; Oncology; Receiver operating characteristic; Pathology; Internal medicine","score_opus":0.02888630840797602,"score_gpt":0.37336620953311966,"score_spread":0.34447990112514365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413940286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8146558,0.085874476,0.04486317,0.049801577,0.0010661689,0.0031405762,0.00024494974,0.00021258922,0.00014070257],"genre_scores_gemma":[0.9956962,0.0017586027,0.00030269742,0.00005560739,0.000067123845,0.0014992496,0.000009326052,0.000009633352,0.0006015516],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983839,0.00007735576,0.00024381284,0.00068290456,0.00023888798,0.00037316966],"domain_scores_gemma":[0.9992224,0.0000769029,0.00008356457,0.0003152281,0.0002182913,0.000083640145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032704708,0.00013969862,0.00017391425,0.00025624107,0.00027904293,0.00018061417,0.00013175445,0.00006387587,0.0000038057715],"category_scores_gemma":[0.000009384667,0.0001132704,0.000026646312,0.0005304238,0.00022313018,0.00032546525,0.00010690193,0.00014259211,4.2025337e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034952653,0.00014068712,0.007058659,0.00012475913,0.0000356228,0.00016322402,0.0008905894,0.00002599173,0.0013145658,0.0007049667,0.00041195107,0.9887795],"study_design_scores_gemma":[0.0063465796,0.00063867075,0.8919528,0.0017412561,0.00008141629,0.0042733666,0.0021626852,0.06631862,0.0060170447,0.013967288,0.0056731044,0.00082714035],"about_ca_topic_score_codex":0.004499455,"about_ca_topic_score_gemma":0.0048897984,"teacher_disagreement_score":0.9879523,"about_ca_system_score_codex":0.0010293322,"about_ca_system_score_gemma":0.00045818524,"threshold_uncertainty_score":0.680186},"labels":[],"label_agreement":null},{"id":"W4413971657","doi":"10.1093/ajcp/aqaf083","title":"Selecting high-throughput scanners for clinical use: A multicenter institution experience","year":2025,"lang":"en","type":"article","venue":"American Journal of Clinical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Throughput; Multicenter study; Medicine; Computer science; Medical physics; Pathology","score_opus":0.09131896349793185,"score_gpt":0.4737302279056982,"score_spread":0.38241126440776635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413971657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45152587,0.000042344083,0.5420102,0.0015584235,0.004663272,0.00011887276,0.0000010833539,0.000030832984,0.00004909302],"genre_scores_gemma":[0.8211079,0.00022513271,0.17484595,0.0032235559,0.00053390476,0.00001328741,3.486141e-7,0.000008306091,0.000041604202],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99566895,0.00088294497,0.0023069414,0.00054049655,0.00023242403,0.00036822417],"domain_scores_gemma":[0.9934755,0.003473,0.0018071582,0.0004672887,0.000609095,0.00016793858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032642807,0.00016528575,0.00086559664,0.00019361569,0.00015621286,0.0000795162,0.00089514075,0.00016000003,0.0000031590005],"category_scores_gemma":[0.0061497604,0.00014708618,0.00042523653,0.00066276244,0.0010642051,0.0007590386,0.0002055256,0.0007609604,0.000005003323],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081983116,0.00035520046,0.1563917,0.000012702863,0.00013229495,0.00011231156,0.00048597268,0.00034012843,0.00015684988,0.0034371356,0.0018833841,0.8358725],"study_design_scores_gemma":[0.013666869,0.018714983,0.8236517,0.00054772984,0.0003146996,0.0011612431,0.0012990035,0.032230735,0.0013278007,0.008297027,0.09765401,0.0011342154],"about_ca_topic_score_codex":0.0000391615,"about_ca_topic_score_gemma":0.000017026277,"teacher_disagreement_score":0.83473825,"about_ca_system_score_codex":0.00011062645,"about_ca_system_score_gemma":0.0005527198,"threshold_uncertainty_score":0.73622817},"labels":[],"label_agreement":null},{"id":"W4413979894","doi":"10.1109/tnnls.2025.3600443","title":"Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the Seven-Point Checklist","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Checklist; Point (geometry); Melanoma diagnosis; Computer science; Artificial neural network; Melanoma; Artificial intelligence; Medicine; Medical physics; Psychology; Natural language processing; Mathematics; Cognitive psychology; Cancer research","score_opus":0.01796228811516171,"score_gpt":0.2815856936904686,"score_spread":0.2636234055753069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413979894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06443879,0.0033404166,0.92353964,0.00041914135,0.0070163608,0.00094427884,0.00000320738,0.00025524825,0.000042916134],"genre_scores_gemma":[0.99808383,0.00023300429,0.00019108139,0.00012393227,0.0001832069,0.0008226945,0.0000015952637,0.000023698189,0.0003369722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972374,0.0008763252,0.000665058,0.00067601854,0.00015328075,0.00039191192],"domain_scores_gemma":[0.99681205,0.0023071817,0.00025620536,0.000376511,0.00013253851,0.00011552191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011487436,0.000296819,0.00042953325,0.00016424301,0.0012300146,0.0005234014,0.00034677453,0.0001859061,8.134771e-7],"category_scores_gemma":[0.000032815846,0.00022122779,0.00019726071,0.00057580427,0.00015051526,0.00024325712,0.0000085605225,0.0009826449,8.0774885e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009272848,0.0000787584,0.00059425796,0.00019966398,0.00009996013,0.0000021345895,0.00042452794,0.8506836,0.00006454219,0.0007917534,0.00028697748,0.14668106],"study_design_scores_gemma":[0.00068940985,0.00059011515,0.00031419314,0.00031449657,0.000060232458,0.000021912478,0.00028988378,0.99617535,0.00012562849,0.00002449133,0.0011758778,0.00021838739],"about_ca_topic_score_codex":0.00027555303,"about_ca_topic_score_gemma":0.00013819135,"teacher_disagreement_score":0.933645,"about_ca_system_score_codex":0.00007485882,"about_ca_system_score_gemma":0.000034965295,"threshold_uncertainty_score":0.9460402},"labels":[],"label_agreement":null},{"id":"W4413986381","doi":"10.1080/10408363.2025.2549309","title":"Large scale implementation of DP for clinical diagnoses: experience, challenges, and lessons learned","year":2025,"lang":"en","type":"review","venue":"Critical Reviews in Clinical Laboratory Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Scale (ratio); Medical diagnosis; Data science; Computer science; Medical physics; Medicine; Geography; Cartography; Pathology","score_opus":0.4443458344913378,"score_gpt":0.6195860533763532,"score_spread":0.1752402188850154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413986381","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013108934,0.9863232,0.007962902,0.0011259842,0.0023419035,0.0018571864,0.00013311517,0.000049467497,0.00019315345],"genre_scores_gemma":[0.00004330951,0.982153,0.01601729,0.00042739345,0.00027572413,0.0010491943,0.000005043857,0.000015403126,0.000013632102],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98889244,0.0031258743,0.004666175,0.0020815437,0.0005331032,0.00070086075],"domain_scores_gemma":[0.97672653,0.020630213,0.00095351017,0.0010508186,0.00033441262,0.00030451038],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020703658,0.00047374016,0.003511285,0.00033558608,0.0002492486,0.00015671353,0.0021244432,0.00061216636,0.000023242332],"category_scores_gemma":[0.0207946,0.00037286134,0.00072735106,0.0018271218,0.0019336356,0.0007723699,0.0007592273,0.0008042826,0.00001323889],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020374814,0.00016317557,0.00014207212,0.009070165,0.000009069214,0.0000018261323,0.00013236095,2.2794975e-8,2.126152e-8,0.042987674,0.00050813,0.94698346],"study_design_scores_gemma":[0.0003308939,0.00051017257,0.00019918791,0.013562042,0.00013004371,0.0000014679514,0.0003282487,0.000050036982,9.633519e-7,0.004563554,0.9799527,0.00037070867],"about_ca_topic_score_codex":0.0000040529762,"about_ca_topic_score_gemma":0.00013559351,"teacher_disagreement_score":0.97944456,"about_ca_system_score_codex":0.00008598782,"about_ca_system_score_gemma":0.0019267618,"threshold_uncertainty_score":0.9998723},"labels":[],"label_agreement":null},{"id":"W4414114177","doi":"10.1016/j.bspc.2025.108638","title":"Adaptive deep Q-GAN framework for enhanced breast cancer detection in medical imaging","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Preprocessor; Feature (linguistics); Mammography; Medical imaging; Breast cancer; Segmentation; Pattern recognition (psychology); Feature engineering","score_opus":0.00542007798914244,"score_gpt":0.26881321060421626,"score_spread":0.2633931326150738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414114177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009851488,0.0018901001,0.98929465,0.007009358,0.00039228404,0.00023896122,0.0000042413994,0.00012338755,0.00006188984],"genre_scores_gemma":[0.994239,0.000029328798,0.0035070032,0.0016136273,0.00031051235,0.00028091887,5.413466e-7,0.000008145856,0.000010959292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839914,0.00006479296,0.00029917184,0.00048729786,0.0003968705,0.00035272603],"domain_scores_gemma":[0.9992158,0.00030225946,0.00009676436,0.000107127686,0.00011374389,0.00016432196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004695668,0.0001514458,0.00023195716,0.00019038001,0.00021661045,0.00012652199,0.00032103818,0.00019084748,0.000018796683],"category_scores_gemma":[0.00009907072,0.00013195927,0.00004470026,0.00064082805,0.00018924772,0.00026958,0.000050844454,0.00032413815,9.131766e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015780226,0.000041631978,0.00010104733,0.00005729071,0.000014522745,0.0000038430076,0.0001352831,0.000012352154,0.003123357,0.00050127425,0.000012328443,0.99583924],"study_design_scores_gemma":[0.0020123369,0.000074927244,0.0018498348,0.0006881374,0.000021306423,0.000017829594,0.00009072943,0.9672001,0.0031544778,0.024214363,0.00048425834,0.0001916785],"about_ca_topic_score_codex":0.0000996109,"about_ca_topic_score_gemma":0.000062463216,"teacher_disagreement_score":0.9956476,"about_ca_system_score_codex":0.00016760951,"about_ca_system_score_gemma":0.000369465,"threshold_uncertainty_score":0.5381143},"labels":[],"label_agreement":null},{"id":"W4414156394","doi":"10.3390/biomedinformatics5030053","title":"High-Precision, Automatic, and Fast Segmentation Method of Hepatic Vessels and Liver Tumors from CT Images Using a Fusion Decision-Based Stacking Deep Learning Model","year":2025,"lang":"en","type":"article","venue":"BioMedInformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Deep learning; Segmentation; Robustness (evolution); Stacking; Liver tumor; Flexibility (engineering); Image segmentation; Pattern recognition (psychology)","score_opus":0.013303542469609905,"score_gpt":0.2859272044504051,"score_spread":0.2726236619807952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414156394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3456503,0.000115856026,0.6538139,0.000024000812,0.00014634783,0.00016904873,0.0000062963263,0.00006210205,0.000012191289],"genre_scores_gemma":[0.40229222,0.000054756594,0.59757656,0.000048261867,0.000008302948,0.000005613017,0.000005127693,0.000005580184,0.0000035484286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843115,0.00008065076,0.00064541836,0.00022503066,0.00043642457,0.00018134069],"domain_scores_gemma":[0.9981489,0.0009309687,0.0004201064,0.00027894144,0.00015081833,0.00007023467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063480175,0.00017560659,0.0002932979,0.0004834913,0.00022403667,0.0001997312,0.0002636318,0.000057739515,0.000005660453],"category_scores_gemma":[0.00021420802,0.00016114362,0.000034018714,0.0006001136,0.0000746929,0.0009966027,0.0003225971,0.00012825629,0.0000011937799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000151635195,0.000019786024,0.0005472851,0.0002789386,0.000025828931,0.000002205172,0.0034469925,0.04962363,0.010359373,0.00012227258,0.00002286783,0.93553567],"study_design_scores_gemma":[0.0005760563,0.00005718711,0.001389422,0.00051231286,0.000037991504,0.000005223724,0.00040637457,0.96285766,0.031300787,0.002707454,0.000007656382,0.0001418697],"about_ca_topic_score_codex":0.0001318576,"about_ca_topic_score_gemma":0.0000058555584,"teacher_disagreement_score":0.9353938,"about_ca_system_score_codex":0.00013906002,"about_ca_system_score_gemma":0.00011329186,"threshold_uncertainty_score":0.6571246},"labels":[],"label_agreement":null},{"id":"W4414197358","doi":"10.1109/cvprw67362.2025.00475","title":"Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Tree traversal; Trajectory; Image (mathematics); Key (lock); Space (punctuation); Medical imaging; Generative model; Scale (ratio); Factorization","score_opus":0.01862059473908766,"score_gpt":0.292096718681559,"score_spread":0.27347612394247134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414197358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1805692,0.00006187456,0.81504756,0.0016930191,0.0010970281,0.00042681867,0.0000028597522,0.0001608853,0.00094077253],"genre_scores_gemma":[0.96185863,0.00004012617,0.034224194,0.0004229592,0.00018792172,0.0001193383,0.000017435332,0.000012515045,0.0031168964],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986924,0.0000765035,0.00026046787,0.00038337384,0.00033943704,0.00024780026],"domain_scores_gemma":[0.99942523,0.000107395965,0.000048544487,0.00029177684,0.000051217103,0.00007582507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033516245,0.00012569323,0.000170389,0.00016689213,0.000080009064,0.00008832556,0.0003375797,0.000109190805,0.00011804247],"category_scores_gemma":[0.000103774124,0.00011078225,0.000069287766,0.00037059945,0.000024902205,0.00032232446,0.00010058065,0.00011984752,0.000006138514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001835674,0.00047833825,0.0030971195,0.00015133535,0.000067080604,0.00004891155,0.0043289852,0.0003509159,0.86442196,0.019960873,0.032164987,0.07474591],"study_design_scores_gemma":[0.0040664747,0.00010096573,0.0055824895,0.000048119997,0.000012933062,0.0000037984485,0.00019851427,0.8362488,0.15101527,0.0005308096,0.0019214799,0.00027031873],"about_ca_topic_score_codex":0.00046090252,"about_ca_topic_score_gemma":0.0010824527,"teacher_disagreement_score":0.8358979,"about_ca_system_score_codex":0.00034564798,"about_ca_system_score_gemma":0.00019869962,"threshold_uncertainty_score":0.45175692},"labels":[],"label_agreement":null},{"id":"W4414208331","doi":"10.3390/cancers17182991","title":"A Deep Learning Framework for Classification of Neuroendocrine Neoplasm Whole Slide Images","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Royal Jubilee Hospital; University of British Columbia","funders":"BC Cancer Foundation","keywords":"Grading (engineering); Neuroendocrine tumors; Survival analysis; Deep learning; Tumor grade; Multivariate analysis; Overall survival; Multivariate statistics","score_opus":0.015791194978969778,"score_gpt":0.2891659667071627,"score_spread":0.2733747717281929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414208331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004367206,0.0003259578,0.99153256,0.0013720045,0.001080645,0.00020253786,0.0000016938174,0.00012313334,0.0009942509],"genre_scores_gemma":[0.9330731,0.000081652775,0.06553766,0.00028820927,0.00008143256,0.00015326236,0.0000019179226,0.000010458089,0.00077232224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991872,0.00003462926,0.0001819351,0.00029979966,0.00011182086,0.00018463265],"domain_scores_gemma":[0.99916375,0.00023171358,0.00013669468,0.0003320626,0.00010459538,0.000031167536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008056669,0.00008701983,0.00012751199,0.00011293448,0.0001063952,0.00004564662,0.00038090695,0.00003021012,0.0000036140923],"category_scores_gemma":[0.0002113343,0.000095394396,0.000059508962,0.0004972213,0.000047746595,0.00020836169,0.00006887792,0.0001682744,0.000003946961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108810076,0.000015560645,0.001760075,0.00028662742,0.00006797484,0.000003576935,0.0006194802,0.06672021,0.035327382,0.09391433,0.005328751,0.79584724],"study_design_scores_gemma":[0.00071849755,0.00024339206,0.010767615,0.0002093714,0.000033677952,0.0000062565878,0.0002847513,0.74544793,0.08500151,0.026915712,0.13010485,0.00026640977],"about_ca_topic_score_codex":0.00004930528,"about_ca_topic_score_gemma":0.000020191364,"teacher_disagreement_score":0.9287059,"about_ca_system_score_codex":0.00049550127,"about_ca_system_score_gemma":0.0002446047,"threshold_uncertainty_score":0.38900706},"labels":[],"label_agreement":null},{"id":"W4414301659","doi":"10.1016/j.rineng.2025.107174","title":"TransfusionNet: Framework for cervical cancer detection using deep learning with multi-level fusion","year":2025,"lang":"en","type":"article","venue":"Results in Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Pattern recognition (psychology); Robustness (evolution); Overfitting; Preprocessor; Feature (linguistics); Concatenation (mathematics); Thresholding; Histogram; Image fusion","score_opus":0.023363894114322787,"score_gpt":0.27803321513940576,"score_spread":0.254669321025083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414301659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04769356,0.0002202194,0.9506174,0.00012085663,0.00081310514,0.0002921713,0.0000026216758,0.00021971838,0.000020387757],"genre_scores_gemma":[0.6955287,0.00004641883,0.3042216,0.000019757981,0.00007659323,0.00007161413,7.0671643e-7,0.000015543654,0.000019068979],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988109,0.000024572935,0.00026577554,0.00043102712,0.00015887897,0.0003088846],"domain_scores_gemma":[0.99937236,0.00022448735,0.000056510326,0.00023752576,0.00006590938,0.000043201726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002533314,0.00016133978,0.0001628867,0.00028833645,0.00013967318,0.000062127074,0.00025586286,0.00015860752,0.0000013070913],"category_scores_gemma":[0.00014925643,0.00015896645,0.0000432436,0.00093404157,0.000011383849,0.00023979957,0.00006180693,0.000412258,5.065689e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100395104,0.00001589342,0.0001736918,0.00009206889,0.000012385513,0.0000021530286,0.0005688866,0.83293694,0.007888007,0.00034012465,3.3153378e-7,0.15786913],"study_design_scores_gemma":[0.0010875906,0.000062162275,0.0052748104,0.0005529688,0.000008609968,0.00000417159,0.000040783605,0.97659963,0.015721897,0.00011541354,0.0003484541,0.00018352293],"about_ca_topic_score_codex":0.0002053646,"about_ca_topic_score_gemma":0.00054231664,"teacher_disagreement_score":0.64783514,"about_ca_system_score_codex":0.0004103553,"about_ca_system_score_gemma":0.00004877716,"threshold_uncertainty_score":0.64824635},"labels":[],"label_agreement":null},{"id":"W4414372291","doi":"10.1007/s00521-025-11631-6","title":"MammoSegNet: a convolutional network analysis for segmenting tumor tissue masses in digital mammograms of breast cancer patients","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Lakehead University","funders":"University of Southern Queensland","keywords":"Preprocessor; Convolutional neural network; Pattern recognition (psychology); Segmentation; Normalization (sociology); Feature extraction; Breast cancer; Robustness (evolution); Mammography; Pixel","score_opus":0.007587469216668794,"score_gpt":0.26842020712259207,"score_spread":0.26083273790592326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414372291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.251938,0.00015016756,0.746939,0.0002533839,0.00009598258,0.00041158375,0.00005162377,0.00005952454,0.00010073376],"genre_scores_gemma":[0.99311554,0.0000034074785,0.006547171,0.000081558544,0.00007225785,0.00012974357,0.000019322706,0.0000040603277,0.000026934238],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991025,0.00001332537,0.00027399295,0.000315808,0.0001023135,0.00019208857],"domain_scores_gemma":[0.9993738,0.00015801811,0.00014620373,0.00016292231,0.00012922083,0.000029855759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009082588,0.00009100654,0.00016565026,0.00013402279,0.00017292592,0.000094303075,0.00021972255,0.00002639666,0.0000013613053],"category_scores_gemma":[0.0000070675687,0.000095345466,0.000050958475,0.0013962736,0.00004336624,0.00013593894,0.00014564637,0.000069740876,3.0159563e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011272522,0.000102521844,0.6392525,0.00006985152,0.00009163688,1.5406624e-7,0.000057985617,0.042234942,0.00010439954,0.0062473826,0.0001459319,0.31168145],"study_design_scores_gemma":[0.00042132818,0.00003334582,0.4654672,0.00005221811,0.00005818873,0.0000017952935,0.000017657852,0.5305787,0.00013201372,0.002030626,0.0010673254,0.00013962932],"about_ca_topic_score_codex":0.00008068754,"about_ca_topic_score_gemma":0.000041349926,"teacher_disagreement_score":0.74117756,"about_ca_system_score_codex":0.000051147366,"about_ca_system_score_gemma":0.00003427391,"threshold_uncertainty_score":0.3888075},"labels":[],"label_agreement":null},{"id":"W4414424103","doi":"10.1002/mp.18119","title":"A deep learning framework for accurate mammographic mass classification using local context attention module","year":2025,"lang":"en","type":"article","venue":"Medical Physics","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"Princess Nourah Bint Abdulrahman University","keywords":"Deep learning; Context (archaeology); Consistency (knowledge bases); Mammography; Pattern recognition (psychology); Medical imaging","score_opus":0.03440808163158842,"score_gpt":0.3116002836259476,"score_spread":0.2771922019943592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414424103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004565879,0.00011309388,0.99252707,0.001227796,0.001069207,0.00022567526,5.082971e-7,0.00017867326,0.000092100236],"genre_scores_gemma":[0.971609,0.000021026057,0.02752687,0.00046424556,0.00025956772,0.00006429648,0.0000054872776,0.000011243393,0.000038244896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859655,0.00008479663,0.00024627088,0.00039309057,0.00042259248,0.0002567162],"domain_scores_gemma":[0.9990632,0.0002664248,0.00013501545,0.000310638,0.00013671412,0.000088008856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036118377,0.00012340215,0.0001620956,0.000072164825,0.00025279837,0.00009445942,0.00044509684,0.00018921989,0.00000620245],"category_scores_gemma":[0.0002224704,0.00012565905,0.000110497866,0.0007725508,0.00012959297,0.00031380044,0.000091318245,0.0004343936,0.000009465413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015868736,0.000041516287,0.00081592397,0.000057740013,0.000031444713,0.0000011016455,0.00007899745,0.0020002997,0.00042621398,0.103085384,0.00006793434,0.89337754],"study_design_scores_gemma":[0.00027349114,0.00004087917,0.0009283117,0.00013736461,0.00001613176,9.515637e-7,0.00005368568,0.83850676,0.0012601343,0.15786117,0.0008138802,0.000107234046],"about_ca_topic_score_codex":0.000019089304,"about_ca_topic_score_gemma":0.000007612048,"teacher_disagreement_score":0.96704316,"about_ca_system_score_codex":0.00015900374,"about_ca_system_score_gemma":0.000119124576,"threshold_uncertainty_score":0.51242274},"labels":[],"label_agreement":null},{"id":"W4414449407","doi":"10.1007/978-3-032-05825-6_1","title":"LesionGen: A Concept-Guided Diffusion Model for Dermatology Image Synthesis","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of British Columbia; University of Victoria","funders":"","keywords":"Probabilistic logic; Image (mathematics); Skin lesion; Annotation; Deep learning; Code (set theory); Pattern recognition (psychology)","score_opus":0.022337215498309568,"score_gpt":0.2696632690694883,"score_spread":0.2473260535711787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414449407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018923558,0.00039106925,0.9922637,0.0023782721,0.002212135,0.0008867884,0.000022697934,0.000280973,0.0015454502],"genre_scores_gemma":[0.03769243,0.00008456554,0.9583583,0.002149171,0.0003255218,0.00014335,0.0000053372673,0.000048575544,0.0011927544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567544,0.000048724854,0.00070633506,0.0020315577,0.0007484465,0.0007894823],"domain_scores_gemma":[0.9959687,0.0013584978,0.00037317444,0.001684969,0.00045799345,0.0001566636],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005154192,0.0006298243,0.00076714874,0.0010190948,0.00047257886,0.0003998314,0.0036666244,0.0005659219,0.000013725673],"category_scores_gemma":[0.0003062874,0.00060453505,0.00025178012,0.0005614365,0.0008019551,0.00063647435,0.0017281331,0.00062351883,0.000014924231],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020923942,0.000039720333,0.000007912616,0.00017197405,0.000024666755,0.000050918406,0.0008124956,0.055700123,0.0010067788,0.0343581,0.0010890652,0.9067173],"study_design_scores_gemma":[0.00025356893,0.00005035002,0.000004513778,0.00034504524,0.000017309998,0.00008230859,1.12941805e-7,0.8360917,0.008859023,0.15310441,0.0006832405,0.00050839904],"about_ca_topic_score_codex":0.000019137104,"about_ca_topic_score_gemma":0.000063367625,"teacher_disagreement_score":0.90620893,"about_ca_system_score_codex":0.00065796875,"about_ca_system_score_gemma":0.0011995535,"threshold_uncertainty_score":0.9996406},"labels":[],"label_agreement":null},{"id":"W4414478100","doi":"10.1007/978-3-032-05472-2_27","title":"Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Pixel; Encoder; Generative grammar; Context (archaeology); Key (lock); Terminology; Transformer; Image (mathematics)","score_opus":0.011207072310807793,"score_gpt":0.2765376953058719,"score_spread":0.2653306229950641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414478100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011883236,0.0005225308,0.9922121,0.0019891413,0.0031214058,0.0008597726,0.000015266138,0.0003251632,0.00083577546],"genre_scores_gemma":[0.06403343,0.00008492634,0.93096787,0.0018940395,0.0012213108,0.0001104106,0.000031229745,0.000052338564,0.0016044787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943456,0.000082173705,0.00079553487,0.002165695,0.0018287732,0.0007822003],"domain_scores_gemma":[0.99656194,0.0009005978,0.00041545156,0.0014398127,0.00046397487,0.00021819945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021804257,0.0006155869,0.00062461785,0.001025731,0.0006977228,0.0008075703,0.0028898548,0.00061799167,0.000023834533],"category_scores_gemma":[0.00047972435,0.00059304695,0.00021496655,0.00072536163,0.0005999448,0.0011129506,0.0014137223,0.0009723538,0.000012852125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017597718,0.000025813137,0.0000018198936,0.00009137232,0.0000127757185,0.000009512995,0.00079705915,0.1656274,0.0020056958,0.004633647,0.00021353648,0.8265638],"study_design_scores_gemma":[0.00047152193,0.00021521428,0.0000072648663,0.0005708736,0.000017856586,0.000035724344,4.017872e-7,0.9516495,0.002819058,0.043182705,0.00047281283,0.0005570711],"about_ca_topic_score_codex":0.00008405952,"about_ca_topic_score_gemma":0.00044036226,"teacher_disagreement_score":0.8260067,"about_ca_system_score_codex":0.0011539288,"about_ca_system_score_gemma":0.0018950563,"threshold_uncertainty_score":0.9996521},"labels":[],"label_agreement":null},{"id":"W4414486758","doi":"10.1007/978-3-032-05559-0_29","title":"Bridging the Gap: A Community Driven and AI-Enabled Approach to Early Breast Cancer Detection in Black African Women","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Breast cancer; Breast ultrasound; Breast cancer screening; Black women; Incidence (geometry); Black african; Breast imaging; Mammography","score_opus":0.014956808640933447,"score_gpt":0.23656427058192275,"score_spread":0.2216074619409893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414486758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009348266,0.00008475913,0.98487705,0.0019491615,0.00080480793,0.0008112584,0.000009410322,0.00013678608,0.0019785047],"genre_scores_gemma":[0.9803199,0.000031645613,0.016895762,0.002134114,0.00027172212,0.00012352815,6.471313e-7,0.000026104964,0.00019657667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99658585,0.00021376982,0.00045385803,0.0012299358,0.00072726165,0.000789326],"domain_scores_gemma":[0.997524,0.00040184704,0.00021566164,0.0014581515,0.00022355134,0.00017674768],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015923271,0.0004875558,0.0005079299,0.0010858979,0.000614164,0.00082622794,0.0030157024,0.0002511802,0.0000035788084],"category_scores_gemma":[0.000056261615,0.0004115496,0.00006622294,0.0019169394,0.00071766414,0.0006269224,0.0022333555,0.0020257728,0.000004518455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034197095,0.000038999504,0.00041906736,0.000089419336,0.00001957816,0.000007077097,0.015670158,0.06727446,0.00019812453,0.0008985811,0.000018496488,0.91533184],"study_design_scores_gemma":[0.00042536785,0.00020589933,0.011875957,0.0005952193,0.00001065134,0.00007439859,0.0000098240425,0.95993733,0.0005048205,0.025287122,0.0003356988,0.0007377202],"about_ca_topic_score_codex":0.002434436,"about_ca_topic_score_gemma":0.0022965842,"teacher_disagreement_score":0.97097164,"about_ca_system_score_codex":0.0018138435,"about_ca_system_score_gemma":0.0005400298,"threshold_uncertainty_score":0.99983364},"labels":[],"label_agreement":null},{"id":"W4414486781","doi":"10.1007/978-3-032-05559-0_10","title":"Breast Cancer Detection from Multi-view Screening Mammograms with Visual Prompt Tuning","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Robustness (evolution); Breast cancer; Mammography; Scalability; Feature (linguistics); Medical imaging; Data set; Pattern recognition (psychology)","score_opus":0.01574486416068844,"score_gpt":0.2615335562261875,"score_spread":0.24578869206549908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414486781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017006959,0.0010555626,0.9945748,0.00047295587,0.0023064932,0.00070289476,0.00002190159,0.0004642177,0.0002311358],"genre_scores_gemma":[0.24713166,0.0001468201,0.74992114,0.0010727622,0.001092154,0.000115713156,0.000010625817,0.000088452274,0.00042066307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948533,0.00006717572,0.0005847047,0.0024332684,0.0012331079,0.0008284029],"domain_scores_gemma":[0.99732804,0.0003175654,0.00047685578,0.0012405924,0.00043397438,0.00020294116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057168683,0.0007807844,0.0006904832,0.00095759734,0.00054191094,0.0008844312,0.0025619445,0.00042853446,0.000028668923],"category_scores_gemma":[0.0000226927,0.0006947504,0.00014327603,0.0014614951,0.0005890261,0.0010964872,0.0012844526,0.0013757279,0.000012461584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027352933,0.000022151251,0.00021203906,0.000049373786,0.000043356806,0.00003898843,0.0002776126,0.023581076,0.00027272504,0.00010855104,0.0000032623366,0.9753635],"study_design_scores_gemma":[0.000615915,0.00021168144,0.0011034874,0.002791664,0.000045152374,0.0001458052,4.8357236e-7,0.9871394,0.0031745883,0.0030249595,0.0007591256,0.0009877252],"about_ca_topic_score_codex":0.0011808015,"about_ca_topic_score_gemma":0.002982186,"teacher_disagreement_score":0.9743758,"about_ca_system_score_codex":0.00089774973,"about_ca_system_score_gemma":0.000831128,"threshold_uncertainty_score":0.99955034},"labels":[],"label_agreement":null},{"id":"W4414499593","doi":"10.1109/icscsa66339.2025.11171231","title":"Optimizing Hyperparameters with Pelican Algorithm for Deep Learning–based Oral Cancer Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hyperparameter; Segmentation; Context (archaeology); Deep learning; Ground truth; Generalization; Artificial neural network; Feature (linguistics)","score_opus":0.012322787088543102,"score_gpt":0.26677779152755987,"score_spread":0.25445500443901675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414499593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021814106,0.00007621935,0.9953058,0.00055192277,0.00055586547,0.00034715794,7.5930564e-7,0.00043845898,0.0005424474],"genre_scores_gemma":[0.321595,0.000008420275,0.6766297,0.0006320632,0.000046328754,0.00037124706,0.0000010053265,0.000014526621,0.0007016778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887526,0.00004606336,0.00015173102,0.00046643201,0.00017090402,0.00028961015],"domain_scores_gemma":[0.99930614,0.00012639989,0.000077915414,0.0002819293,0.00015274392,0.000054846125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017682808,0.00015020854,0.0001563647,0.00019156838,0.0002593504,0.00015714548,0.0003289705,0.000065566026,0.000011951501],"category_scores_gemma":[0.000019149178,0.00013002528,0.00006379567,0.0006750343,0.000044608816,0.00031522964,0.00005431418,0.0001691985,0.000002940741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028075143,0.0000132868745,0.00008543097,0.000012568149,0.000028658817,6.6308377e-7,0.00006603888,0.050341398,0.0006280204,0.00009467075,0.00004566798,0.94865555],"study_design_scores_gemma":[0.00069434464,0.00029973005,0.00016622864,0.000024647063,0.000021747124,0.0000024512608,0.000049841237,0.9401526,0.052213404,0.000109872715,0.0060946955,0.00017045838],"about_ca_topic_score_codex":0.00045845087,"about_ca_topic_score_gemma":0.0006539638,"teacher_disagreement_score":0.9484851,"about_ca_system_score_codex":0.00031169562,"about_ca_system_score_gemma":0.00013544095,"threshold_uncertainty_score":0.53022766},"labels":[],"label_agreement":null},{"id":"W4414510733","doi":"10.1038/s41598-025-15772-5","title":"End-to-end CNN-based deep learning enhances breast lesion characterization using quantitative ultrasound (QUS) spectral parametric images","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Foundation","keywords":"Parametric statistics; Deep learning; Pattern recognition (psychology); Convolutional neural network; Transfer of learning; Parametric model; Breast imaging; Radiomics","score_opus":0.019506856964055557,"score_gpt":0.2903000502185931,"score_spread":0.27079319325453755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414510733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42505673,0.000059806305,0.56853724,0.00012950254,0.005547077,0.00024139298,0.0000019867584,0.00016912614,0.00025712504],"genre_scores_gemma":[0.96627516,0.0000050985745,0.032650188,0.000051858136,0.000065226726,0.000022770002,0.000040176987,0.000014043231,0.00087549456],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965798,0.00020197571,0.00060350535,0.0013550118,0.0007861208,0.0004735761],"domain_scores_gemma":[0.9978779,0.00025406262,0.0005419013,0.00082028634,0.00038308304,0.0001227542],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017280835,0.00023382522,0.00025584362,0.0011692491,0.0009221473,0.0014247205,0.0004256995,0.00008334723,0.000071374445],"category_scores_gemma":[0.0005206808,0.00023606695,0.00010915966,0.0049433834,0.0002187441,0.0011098757,0.0001342493,0.00023975983,0.000029970159],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017003538,0.00006667106,0.006732778,0.00003891947,0.000018462302,0.00007200719,0.0004307273,0.01158207,0.9441503,0.00030398433,0.000094670875,0.036492378],"study_design_scores_gemma":[0.00019210993,0.00012831131,0.054100502,0.00025192898,0.00003812051,0.00027522605,0.00015661852,0.12996866,0.8085831,0.0028767744,0.0028928514,0.00053580303],"about_ca_topic_score_codex":0.000099794546,"about_ca_topic_score_gemma":0.000029275598,"teacher_disagreement_score":0.5412184,"about_ca_system_score_codex":0.00038752262,"about_ca_system_score_gemma":0.0004104777,"threshold_uncertainty_score":0.9996119},"labels":[],"label_agreement":null},{"id":"W4414556207","doi":"10.6000/1929-6029.2025.14.54","title":"Transforming Breast Cancer Prediction: Advanced Machine Learning Models for Accurate Prediction and Personalized Care","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Random forest; Support vector machine; Breast cancer; Gradient boosting; Artificial neural network; Logistic regression; Preprocessor; Lasso (programming language)","score_opus":0.04821177731210035,"score_gpt":0.4215333976759396,"score_spread":0.37332162036383926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414556207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029079253,0.0016438945,0.9886043,0.004752848,0.0013146799,0.00020169096,0.00033419157,0.0000150781625,0.00022535889],"genre_scores_gemma":[0.9586432,0.009027981,0.031496856,0.00014027455,0.000394839,0.000083978935,0.00001787543,0.00001251342,0.00018248607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969865,0.00016762804,0.0005202263,0.00022192478,0.0018722145,0.00023150981],"domain_scores_gemma":[0.9965718,0.0010257991,0.00012530504,0.00007486895,0.002069926,0.00013232607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019091582,0.00009001485,0.00017160871,0.00056208053,0.00014446968,0.00012209109,0.0006633797,0.00009548213,0.000042267653],"category_scores_gemma":[0.00096085656,0.00008197369,0.000039911287,0.00032678654,0.00016039106,0.00057576044,0.00012262462,0.0009127419,2.6113636e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007014054,0.000052874042,0.001981421,0.00012663848,0.00011499404,0.000074009,0.0019815946,0.010225427,0.000203438,0.04528851,0.0005325538,0.9387171],"study_design_scores_gemma":[0.0028935794,0.0002326849,0.0018479626,0.0008608503,0.000010249478,0.00014316126,0.00052851345,0.9575435,0.00018227888,0.028676922,0.007007926,0.00007238257],"about_ca_topic_score_codex":0.00009781211,"about_ca_topic_score_gemma":0.00012221694,"teacher_disagreement_score":0.9571075,"about_ca_system_score_codex":0.00065869413,"about_ca_system_score_gemma":0.00091293716,"threshold_uncertainty_score":0.396546},"labels":[],"label_agreement":null},{"id":"W4414605173","doi":"10.1109/icdsns65743.2025.11168652","title":"Integration of Enhanced Feature Selection with Explainable Deep Learning Models for Predicting Breast Cancer","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature selection; Preprocessor; Generalizability theory; Deep learning; Benchmark (surveying); Breast cancer; Feature (linguistics); Data pre-processing","score_opus":0.009467942924183098,"score_gpt":0.2450331895188844,"score_spread":0.2355652465947013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414605173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0101738265,0.000055172255,0.9862931,0.00045639896,0.0001923085,0.00030201327,0.0000010110898,0.00019893287,0.0023272457],"genre_scores_gemma":[0.91733146,0.000017376771,0.0802179,0.000047504058,0.0000512749,0.00021724685,0.0000015143269,0.0000069649964,0.0021087548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992497,0.000027664055,0.00013051963,0.00029033428,0.00013618972,0.0001656153],"domain_scores_gemma":[0.9993043,0.000058509057,0.00011577299,0.00012844134,0.00037299164,0.00002000764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015364778,0.000097319054,0.00011860103,0.00012584844,0.00018155301,0.000056919955,0.00017212478,0.000069600006,0.000005355221],"category_scores_gemma":[0.000014900445,0.00007986354,0.000030974526,0.00065904617,0.000015230398,0.0008143975,0.00003699336,0.00015103334,1.9004356e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023400143,0.000033705983,0.0007838172,0.00014612796,0.000069978734,1.2787223e-7,0.0015778076,0.531827,0.06840246,0.01883204,0.00034471313,0.37774825],"study_design_scores_gemma":[0.00028578495,0.00011795032,0.00046100744,0.000112291455,0.000011500249,0.0000035474964,0.00022492987,0.83993566,0.15714432,0.0015533294,0.000077118595,0.00007253908],"about_ca_topic_score_codex":0.00028423837,"about_ca_topic_score_gemma":0.00069318985,"teacher_disagreement_score":0.90715766,"about_ca_system_score_codex":0.00021835713,"about_ca_system_score_gemma":0.00011472352,"threshold_uncertainty_score":0.32567406},"labels":[],"label_agreement":null},{"id":"W4414644965","doi":"10.2196/70256","title":"Effectiveness of a 5G Local Area Network–Based Digital Microscopy Interactive System: Quasi-Experimental Design","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Microscopy; Microscope; Digital holographic microscopy; Key (lock)","score_opus":0.007492537704453817,"score_gpt":0.31989371049931314,"score_spread":0.31240117279485935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414644965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027966099,0.0002138908,0.9672243,0.00021600872,0.0027287814,0.0006436321,0.0000011174868,0.0001201567,0.00088602334],"genre_scores_gemma":[0.9960459,9.1761774e-7,0.0031308355,0.00016799173,0.00009598564,0.00051151984,0.000008683003,0.000008370714,0.000029797653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838424,0.0003177958,0.00029894695,0.0003846462,0.00040987853,0.00020447743],"domain_scores_gemma":[0.99864906,0.0005843165,0.00014283997,0.00034955892,0.00014839521,0.00012585222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005128559,0.00014552266,0.00022776308,0.00013385326,0.00007760637,0.0000836095,0.0004890233,0.00013774024,0.000016626891],"category_scores_gemma":[0.00014393813,0.00013817551,0.00007110856,0.0006097714,0.00014404289,0.00041460522,0.00008091688,0.00019864514,0.000012666362],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058111628,0.025809953,0.008952023,0.00742023,0.00070171105,0.000040606883,0.0074702557,0.008461137,0.0338734,0.06193722,0.04061856,0.79890376],"study_design_scores_gemma":[0.0026964017,0.0020633924,0.0066647534,0.008771027,0.00003808108,0.000048401373,0.0016082188,0.56290096,0.41121802,0.001811406,0.001584709,0.0005946226],"about_ca_topic_score_codex":0.000053580923,"about_ca_topic_score_gemma":0.0000013162505,"teacher_disagreement_score":0.9680798,"about_ca_system_score_codex":0.0008353981,"about_ca_system_score_gemma":0.0021913566,"threshold_uncertainty_score":0.5634634},"labels":[],"label_agreement":null},{"id":"W4414902551","doi":"10.48550/arxiv.2503.15008","title":"A Novel Channel Boosted Residual CNN-Transformer with Regional-Boundary Learning for Breast Cancer Detection","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Residual; Pattern recognition (psychology); Redundancy (engineering); Convolutional neural network; Block (permutation group theory); Pixel; Deep learning; Feature extraction; Digital mammography","score_opus":0.042263708810198454,"score_gpt":0.28012835942511544,"score_spread":0.237864650614917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414902551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07794759,0.0004799813,0.91284573,0.0042579174,0.0022696168,0.0011862576,0.00009695256,0.0005920481,0.0003238931],"genre_scores_gemma":[0.9876231,0.00028336543,0.005285231,0.0007759293,0.001127004,0.0016431889,0.00004042829,0.00007489528,0.0031468903],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99706805,0.00008045076,0.00043692856,0.0013434449,0.00049261365,0.00057849905],"domain_scores_gemma":[0.99804264,0.00014599426,0.00038660166,0.0007683068,0.0005362816,0.000120181554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038867953,0.00049612916,0.00044612747,0.00036347492,0.0006089755,0.0002190408,0.0009050537,0.00044796028,0.000013978357],"category_scores_gemma":[0.000027154982,0.00048170754,0.00019126697,0.0005930105,0.00012968604,0.0004975657,0.00026160647,0.0012314842,0.000010180997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060210894,0.00082719274,0.046900485,0.0061670165,0.0037497208,0.00005706651,0.012746884,0.19667877,0.060066357,0.0009616273,0.00494532,0.6608785],"study_design_scores_gemma":[0.011299388,0.0021214022,0.5798796,0.008336893,0.0010966401,0.00091234,0.0007106747,0.19963929,0.10964547,0.0038185362,0.07611953,0.0064202663],"about_ca_topic_score_codex":0.0019101491,"about_ca_topic_score_gemma":0.0022188246,"teacher_disagreement_score":0.9096755,"about_ca_system_score_codex":0.0007674279,"about_ca_system_score_gemma":0.0012374853,"threshold_uncertainty_score":0.9997635},"labels":[],"label_agreement":null},{"id":"W4414909173","doi":"10.1101/2025.10.01.25336172","title":"Glomerular Segmentation, Classification, and Pathomic Feature-based Prediction of Clinical Outcomes in Minimal Change Disease and Focal Segmental Glomerulosclerosis","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of North Carolina at Chapel Hill; Temple University; National Institute of Diabetes and Digestive and Kidney Diseases; Anschutz Medical Campus, University of Colorado; Johns Hopkins University; University of Washington; Washington University in St. Louis; University of South Carolina; University of Minnesota; Wake Forest University; Texas Children's Hospital; Harvard University; Northwestern University; National Cancer Institute; Emory University; Cleveland Clinic; National Center for Research Resources; University of Pennsylvania; National Institutes of Health; Ohio State University; York University; University of Miami","keywords":"Minimal change disease; Disease; Glomerulosclerosis; Focal segmental glomerulosclerosis; Outcome (game theory); MEDLINE","score_opus":0.07333725684980164,"score_gpt":0.3317164761075262,"score_spread":0.25837921925772456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414909173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94355375,0.0009086678,0.050471436,0.002150809,0.0013996412,0.0010356882,0.0003599764,0.000105196596,0.000014858212],"genre_scores_gemma":[0.9837036,0.00078395393,0.014596072,0.00026978028,0.00012431598,0.00041419768,0.00006787866,0.000014215898,0.0000259651],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99714166,0.0003563299,0.00083217904,0.0010265629,0.00042378184,0.00021950327],"domain_scores_gemma":[0.99829704,0.00023602536,0.00048037514,0.00069423794,0.00011010811,0.00018224292],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083662494,0.00030233365,0.0005567268,0.00037050687,0.00007769392,0.00008656929,0.00041602828,0.00030358287,0.0000031637496],"category_scores_gemma":[0.00014804894,0.0003061756,0.00012394266,0.00034081622,0.00020293989,0.00027952634,0.00056055846,0.00045524072,8.9158556e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006844839,0.00015347266,0.97527134,0.0003038864,0.00005025661,0.0000033263289,0.00021974927,0.000026363732,0.00025888797,0.000114162496,0.00006561792,0.023464466],"study_design_scores_gemma":[0.0009800757,0.00010321105,0.9385516,0.00025787528,0.00007510047,6.113026e-7,0.000031088406,0.059154503,0.000342086,0.00024991418,0.00006926663,0.00018468231],"about_ca_topic_score_codex":0.000098352015,"about_ca_topic_score_gemma":0.00006024603,"teacher_disagreement_score":0.05912814,"about_ca_system_score_codex":0.00017040421,"about_ca_system_score_gemma":0.0002602307,"threshold_uncertainty_score":0.999939},"labels":[],"label_agreement":null},{"id":"W4414924630","doi":"10.1101/2025.10.07.675857","title":"Artificial Intelligence-enabled Histological Analysis in Preclinical Respiratory Disease Models: A Scoping Review","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Ottawa; McMaster University; Carleton University; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"H&E stain; Digital pathology; Interstitial lung disease; MEDLINE; Deep learning; Data extraction","score_opus":0.09676086972202431,"score_gpt":0.3315203738854691,"score_spread":0.23475950416344482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414924630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008230602,0.06721074,0.9172267,0.0013007359,0.0021355944,0.0028038064,0.000069258575,0.000987272,0.000035293222],"genre_scores_gemma":[0.94523555,0.013481116,0.035674587,0.0029921648,0.0004950468,0.0020447532,4.7676738e-7,0.00006997268,0.0000063455163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929821,0.0009176775,0.001998689,0.0025820017,0.0007682049,0.0007513432],"domain_scores_gemma":[0.99447143,0.0003831094,0.00083771866,0.003315981,0.0005448065,0.00044692843],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002846911,0.00068311224,0.001536932,0.0011671813,0.00018023884,0.00031800984,0.0024820575,0.0006427249,0.00004074611],"category_scores_gemma":[0.001331079,0.0007386272,0.00060965726,0.0044471617,0.0001832569,0.0005148536,0.0020713054,0.0015475771,0.000031304913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018470082,0.008643627,0.05185054,0.17451736,0.0091775935,0.004432021,0.0002963464,0.5199057,0.009369922,0.2117537,0.0036292907,0.0045769163],"study_design_scores_gemma":[0.00045648904,0.00025453488,0.019438975,0.12960924,0.0036020742,2.3675899e-8,0.000002748593,0.82841134,0.010283344,0.002082415,0.0009741339,0.00488466],"about_ca_topic_score_codex":0.000055042572,"about_ca_topic_score_gemma":0.000045210607,"teacher_disagreement_score":0.9370049,"about_ca_system_score_codex":0.0011476267,"about_ca_system_score_gemma":0.0033639618,"threshold_uncertainty_score":0.9995065},"labels":[],"label_agreement":null},{"id":"W4414932958","doi":"10.1038/s41467-025-64712-4","title":"Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Rockyview General Hospital","funders":"National Cancer Institute; HORIZON EUROPE Framework Programme; National Institutes of Health; Gemeinsame Bundesausschuss; Deutsche Forschungsgemeinschaft; Leeds Biomedical Research Centre; Eisai; Deutscher Akademischer Austauschdienst; Deutsche Krebshilfe; Pfizer; Daiichi Sankyo Europe; European Commission; Department of Health and Social Care; National Institute for Health and Care Research; AstraZeneca","keywords":"Prostate cancer; Segmentation; Grading (engineering); Prostatectomy; Terminology; Prostate","score_opus":0.016233741859206955,"score_gpt":0.3436827575506779,"score_spread":0.32744901569147095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414932958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048372825,0.07204491,0.8044169,0.09762801,0.004322311,0.0030617975,0.00006117784,0.0008503626,0.012777257],"genre_scores_gemma":[0.9465142,0.0011210946,0.04796622,0.002104593,0.00001529549,0.0013147321,0.0000106663865,0.00000890135,0.0009442998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999041,0.00010573832,0.00021461608,0.00029927777,0.000090551555,0.00024877506],"domain_scores_gemma":[0.99766856,0.00028871186,0.00008310246,0.0017507232,0.00018210622,0.000026794252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003816837,0.00011144813,0.00014445909,0.00022423867,0.00031887734,0.00012849833,0.0020716179,0.00015388029,0.0000023679381],"category_scores_gemma":[0.00015382264,0.00011487607,0.00005242857,0.0010069602,0.00006778642,0.00050867384,0.00067018514,0.000768707,0.0000027166898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010653238,0.00041666432,0.03286915,0.00024134206,0.000092126145,0.0000050416784,0.004714469,0.0022791445,0.0034749329,0.6255416,0.12060882,0.20965013],"study_design_scores_gemma":[0.00089472637,0.000074633856,0.0059747673,0.00041374285,0.000022526006,0.000005961693,0.00025272233,0.21934387,0.0029583995,0.04049834,0.72919554,0.00036478078],"about_ca_topic_score_codex":0.0002418013,"about_ca_topic_score_gemma":0.0022211499,"teacher_disagreement_score":0.9416769,"about_ca_system_score_codex":0.00043404833,"about_ca_system_score_gemma":0.00019391495,"threshold_uncertainty_score":0.46845102},"labels":[],"label_agreement":null},{"id":"W4415053651","doi":"10.1016/j.neucom.2025.131792","title":"Dynamic complementary dual-teacher: A novel framework for semi-supervised thyroid nodule segmentation","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Department of Science and Technology of Liaoning Province","keywords":"Segmentation; Consistency (knowledge bases); Semantics (computer science); Representation (politics); Asynchronous communication; Exploit; Boundary (topology); A priori and a posteriori","score_opus":0.019939261120870386,"score_gpt":0.30151804592539844,"score_spread":0.281578784804528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415053651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057248507,0.00007033975,0.9375757,0.0020799723,0.0015001692,0.00076387,0.0000073379206,0.00045172838,0.00030238595],"genre_scores_gemma":[0.50632477,0.000004330786,0.49120378,0.002153158,0.00013264052,0.0000763279,0.000014409588,0.000021475016,0.00006908158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813807,0.00006849023,0.00040919823,0.00070881407,0.00025524944,0.00042017762],"domain_scores_gemma":[0.9987412,0.00043411797,0.00016435115,0.00051110686,0.000091949165,0.000057262674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031709182,0.00021950013,0.00020917265,0.00018408895,0.00044350172,0.00020698519,0.0006056329,0.000084508654,0.000008647029],"category_scores_gemma":[0.000058897404,0.00025114365,0.000111907655,0.00066280353,0.000027993625,0.0003229711,0.0004261684,0.00029943016,0.000008821903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012257426,0.0006097644,0.0034008445,0.0005670942,0.00022793129,0.000014110362,0.0039121634,0.033180326,0.23247094,0.04930214,0.005820015,0.67037207],"study_design_scores_gemma":[0.001075139,0.00014496676,0.0021780992,0.00010698591,0.000019421008,0.000011617789,0.00012315625,0.98099256,0.006304666,0.0068613435,0.0019427903,0.00023922922],"about_ca_topic_score_codex":0.000032378877,"about_ca_topic_score_gemma":0.000014196584,"teacher_disagreement_score":0.94781226,"about_ca_system_score_codex":0.00023487912,"about_ca_system_score_gemma":0.00008050782,"threshold_uncertainty_score":0.9999941},"labels":[],"label_agreement":null},{"id":"W4415104312","doi":"10.30683/1929-2279.2025.14.20","title":"A Sisters Similarity Neural Network SSNN Model for Generalization and Detection of Mammographic Breast Cancer Lesion Abnormalities","year":2025,"lang":"en","type":"article","venue":"Journal of cancer research updates","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Preprocessor; Generalization; Artificial neural network; Similarity (geometry); Segmentation; Discriminative model; Deep learning; Mammography","score_opus":0.05699549791103678,"score_gpt":0.3811213001421099,"score_spread":0.3241258022310731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415104312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40115392,0.008598972,0.58347636,0.0053994553,0.00088929577,0.0003956495,0.000037662183,0.000026989042,0.000021670108],"genre_scores_gemma":[0.99184704,0.0047246986,0.0028257219,0.00015993846,0.0002795724,0.000066879846,8.770002e-7,0.000010967128,0.000084293264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998152,0.00020351277,0.00047977408,0.00023204242,0.00057675457,0.00035591252],"domain_scores_gemma":[0.99790066,0.0001723139,0.0003273843,0.00020987421,0.0013022171,0.000087564316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001506839,0.00012340271,0.00025804478,0.00053130067,0.00029658008,0.00015830742,0.00044650486,0.00009052655,0.000004152618],"category_scores_gemma":[0.000043166692,0.00010822226,0.000109845336,0.0009921663,0.00016572043,0.000906438,0.0001690449,0.00032659416,4.709749e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018584176,0.0000938633,0.031141698,0.0009091431,0.00036283315,0.00000410856,0.00088884245,0.65649086,0.0346746,0.004362602,0.0057594217,0.26345363],"study_design_scores_gemma":[0.0007536343,0.0001972075,0.012535772,0.00034073065,0.000041330466,0.000018959023,0.00006126167,0.95735335,0.015872678,0.012033778,0.00066732336,0.00012399767],"about_ca_topic_score_codex":0.0005966525,"about_ca_topic_score_gemma":0.0013447971,"teacher_disagreement_score":0.5906931,"about_ca_system_score_codex":0.00027533597,"about_ca_system_score_gemma":0.00040827878,"threshold_uncertainty_score":0.4413176},"labels":[],"label_agreement":null},{"id":"W4415158575","doi":"10.1097/spc.0000000000000780","title":"Survival prediction in metastatic breast cancer using artificial intelligence: a scoping review","year":2025,"lang":"en","type":"review","venue":"Current Opinion in Supportive and Palliative Care","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Health Sciences Centre; BC Cancer Agency; Ottawa Hospital; Princess Margaret Cancer Centre; University of Toronto; Sunnybrook Health Science Centre; Western University","funders":"","keywords":"Metastatic breast cancer; Focus (optics); Overall survival; Prognostic model; MEDLINE; Predictive modelling; Breast cancer","score_opus":0.295051089761543,"score_gpt":0.5025133000043703,"score_spread":0.20746221024282735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415158575","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011106265,0.9311623,0.059199966,0.00003717084,0.006699625,0.0023753822,0.0004706438,0.000035896086,0.000017925704],"genre_scores_gemma":[0.000017400835,0.99841017,0.00032075864,0.000014637812,0.0002502527,0.0008014132,0.00016447536,0.000018276443,0.0000026445537],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99609506,0.00069780997,0.0014134818,0.0010155187,0.00038516556,0.00039298437],"domain_scores_gemma":[0.9981963,0.00032949197,0.00072386896,0.0003482057,0.00031422105,0.00008790857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052899926,0.00050131377,0.0016043579,0.0005951107,0.00009495846,0.0000920527,0.0004301533,0.00014561178,0.000049219114],"category_scores_gemma":[0.00011854368,0.00046516443,0.00023639339,0.0019887346,0.00008509693,0.0003998656,0.00030934255,0.0006897359,0.000005087298],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032297032,0.000026859088,0.00036135878,0.2139975,0.000023829763,0.0000017366536,0.00037251555,0.000018191613,1.2088623e-8,0.000593811,0.000022996986,0.78457797],"study_design_scores_gemma":[0.00009542692,0.000045202523,0.00014556709,0.98109233,0.0001584746,0.000005145802,0.00019994473,0.0009816973,9.4037125e-7,0.00039677022,0.016397107,0.00048136798],"about_ca_topic_score_codex":0.00006278162,"about_ca_topic_score_gemma":0.00009616663,"teacher_disagreement_score":0.7840966,"about_ca_system_score_codex":0.0010074863,"about_ca_system_score_gemma":0.0019151118,"threshold_uncertainty_score":0.99978},"labels":[],"label_agreement":null},{"id":"W4415205382","doi":"10.3390/curroncol32100571","title":"Automated Software Evaluation in Screening Mammography: A Scoping Review of Image Quality and Technique Assessment","year":2025,"lang":"en","type":"review","venue":"Current Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Software; Breast cancer; Quality (philosophy); Image quality; Software tool; Quality assessment","score_opus":0.26594859927534215,"score_gpt":0.5797910239646025,"score_spread":0.3138424246892603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415205382","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6591761e-7,0.669445,0.32648382,0.000038102917,0.00048695196,0.0032694717,0.0000086538585,0.00018360857,0.00008427544],"genre_scores_gemma":[6.299943e-7,0.90061843,0.09694248,0.000027814343,0.000025920544,0.0023297507,0.000044246586,0.000009954381,7.5867257e-7],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9946664,0.0025276153,0.0014172866,0.0007174821,0.00042413734,0.000247067],"domain_scores_gemma":[0.9969655,0.00080477836,0.0012273004,0.00061903085,0.0003334825,0.000049879247],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0054499274,0.0003048482,0.0019267647,0.0006968498,0.00005340739,0.000029460647,0.000595957,0.00027049784,0.000011570494],"category_scores_gemma":[0.000634162,0.000291933,0.00024055243,0.001587907,0.000089662615,0.00021904761,0.00053057284,0.00058086123,7.912248e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.4435577e-7,0.00003644729,0.000023610732,0.2845857,0.00001335129,9.831697e-7,0.000006615491,3.7920515e-7,2.3830697e-7,0.000055392666,0.00008579016,0.71519095],"study_design_scores_gemma":[0.00025008078,0.00011297209,0.00013025403,0.94273907,0.00027705217,0.000019211131,0.0000017172824,0.0012100197,0.0000019154024,0.00022554016,0.054748073,0.00028409238],"about_ca_topic_score_codex":0.000019241315,"about_ca_topic_score_gemma":0.00002514276,"teacher_disagreement_score":0.7149068,"about_ca_system_score_codex":0.00078079617,"about_ca_system_score_gemma":0.0028453174,"threshold_uncertainty_score":0.99995327},"labels":[],"label_agreement":null},{"id":"W4415218161","doi":"10.1016/j.fraope.2025.100385","title":"A combined UNet++ and LSTM approach for breast ultrasound image segmentation","year":2025,"lang":"en","type":"article","venue":"Franklin Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Zoo","funders":"","keywords":"Segmentation; Pipeline (software); Pattern recognition (psychology); Ground truth; Feature (linguistics); Breast ultrasound; Feature extraction; Deep learning; Artificial neural network","score_opus":0.01174547518244128,"score_gpt":0.283422305787283,"score_spread":0.2716768306048417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415218161","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035588832,0.00005181535,0.9874263,0.00088447344,0.0003208067,0.0011730038,0.00002011207,0.000071599075,0.0064930297],"genre_scores_gemma":[0.37440753,0.000022914162,0.6208777,0.0011183027,0.00008019139,0.0005672225,0.000035800524,0.000015142402,0.0028752263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918693,0.000042201675,0.00015643412,0.00036425106,0.00010031761,0.00014983425],"domain_scores_gemma":[0.999405,0.000121282945,0.000059026155,0.0003093939,0.00006929033,0.000035972236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003229353,0.00009778627,0.00013331183,0.00006684387,0.00017740187,0.00053823844,0.0007016154,0.000049630286,0.000010854154],"category_scores_gemma":[0.000021396529,0.000097338154,0.00002645072,0.0003047857,0.000042905493,0.0006675517,0.00029204978,0.00006939045,0.000004411494],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009081488,0.00075516605,0.0123892715,0.0008080064,0.00045051228,0.0000045900833,0.0046735993,0.0007892158,0.04985298,0.08637079,0.07226535,0.7707324],"study_design_scores_gemma":[0.022831803,0.0011596011,0.12096488,0.00025994415,0.00020526747,0.00014786168,0.0011988479,0.6392424,0.069307774,0.117455475,0.02540067,0.00182544],"about_ca_topic_score_codex":0.000135119,"about_ca_topic_score_gemma":0.000011479136,"teacher_disagreement_score":0.76890695,"about_ca_system_score_codex":0.00006261114,"about_ca_system_score_gemma":0.000063832,"threshold_uncertainty_score":0.5190246},"labels":[],"label_agreement":null},{"id":"W4415384710","doi":"10.1038/s41598-025-20411-0","title":"Lightweight self supervised learning framework for domain generalization in histopathology","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Vector Institute; Baycrest Hospital; University Health Network; Toronto Metropolitan University; University of Toronto","funders":"Mitacs","keywords":"Robustness (evolution); Representation (politics); Domain (mathematical analysis); Software deployment; Generalization; Graphics; Labeled data; Pattern recognition (psychology); Generalizability theory","score_opus":0.009460592356901828,"score_gpt":0.25884502528849074,"score_spread":0.2493844329315889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415384710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08047834,0.00020974176,0.9021039,0.0008601593,0.014946749,0.0003618495,1.5706424e-7,0.00024916723,0.0007899622],"genre_scores_gemma":[0.5095317,0.000008649943,0.4864319,0.00021566139,0.000115945055,0.0002151116,0.000015105552,0.000014775579,0.0034511976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979784,0.00011525588,0.00045126275,0.0009111791,0.00023952305,0.00030441786],"domain_scores_gemma":[0.998742,0.000082257015,0.00018873242,0.0007938872,0.00015112788,0.00004201367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017584808,0.000113776296,0.00016425292,0.00046726153,0.00037425745,0.00028464478,0.0003249099,0.00013470402,0.000011244459],"category_scores_gemma":[0.00022690945,0.00011732262,0.00006541213,0.0014983958,0.00006655255,0.00033054707,0.00014006378,0.00016400925,0.000005275104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050462346,0.00048747423,0.09120733,0.00040722298,0.000043902302,0.0009082485,0.01770682,0.014433887,0.08982268,0.65954846,0.038555007,0.0868285],"study_design_scores_gemma":[0.0002359637,0.00004998346,0.0020942057,0.000089377645,0.000008010816,0.00007690431,0.000041228777,0.055950493,0.018811401,0.68255997,0.23983671,0.00024578648],"about_ca_topic_score_codex":0.0000106672405,"about_ca_topic_score_gemma":0.000027024507,"teacher_disagreement_score":0.4290533,"about_ca_system_score_codex":0.00030711584,"about_ca_system_score_gemma":0.00024468714,"threshold_uncertainty_score":0.47842777},"labels":[],"label_agreement":null},{"id":"W4415515884","doi":"10.1007/978-3-032-07373-0_11","title":"Computer-Aided Diagnosis in Uterus Imaging","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Feature (linguistics); MATLAB; Pattern recognition (psychology); Process (computing); Principal component analysis; Image (mathematics); Interface (matter); Artificial neural network","score_opus":0.026755272656608018,"score_gpt":0.2908461129273004,"score_spread":0.26409084027069235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415515884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043667,0.00080422347,0.8423016,0.0028546865,0.0011674622,0.0005982499,0.000011723069,0.00019333638,0.15202503],"genre_scores_gemma":[0.088755734,0.017682297,0.8820423,0.008387722,0.00022830702,0.00043599625,0.00008510703,0.000036154484,0.002346387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762964,0.000056125038,0.0009820835,0.00049257383,0.00049546803,0.00034411516],"domain_scores_gemma":[0.9960685,0.0004227245,0.00037997088,0.0026944513,0.0003382096,0.00009619179],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012279894,0.00030288476,0.00035096137,0.0024779479,0.00040171936,0.00091660034,0.0046009496,0.00013339656,0.000007140994],"category_scores_gemma":[0.000038606326,0.0003399743,0.000061534556,0.0010821582,0.00068766956,0.008796072,0.0045235553,0.00066732476,0.000039699724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014516079,0.000015444783,0.00044916203,0.000034486435,0.0000032511218,0.0000011707237,0.00091628655,0.00042302354,5.150424e-7,0.24753787,0.00075165374,0.7498657],"study_design_scores_gemma":[0.00039660127,0.000036479534,0.003689404,0.0006534969,0.0000041028043,0.000022598655,0.000009565166,0.829448,0.000016119599,0.012065911,0.15325545,0.00040229023],"about_ca_topic_score_codex":0.00007548726,"about_ca_topic_score_gemma":0.00005652922,"teacher_disagreement_score":0.829025,"about_ca_system_score_codex":0.000582249,"about_ca_system_score_gemma":0.00047696315,"threshold_uncertainty_score":0.9999052},"labels":[],"label_agreement":null},{"id":"W4415610459","doi":"10.1016/j.csbj.2025.10.052","title":"Leveraging AutoML to optimize dataset selection for improved breast cancer variants pathogenicity prediction","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"United Arab Emirates University","keywords":"Interpretability; Pathogenicity; Overfitting; Prioritization; Selection (genetic algorithm); Benchmarking; Feature selection; Ranking (information retrieval); Precision medicine","score_opus":0.009242350494047672,"score_gpt":0.26721178438077064,"score_spread":0.257969433886723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415610459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05723258,0.000092983246,0.922217,0.018404847,0.0011707372,0.00023436829,0.00049912004,0.00014569207,0.0000026798948],"genre_scores_gemma":[0.78316027,0.00003939393,0.21542527,0.001051796,0.0001958337,0.000034868463,0.00006350127,0.000007180564,0.000021876918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894947,0.000036219946,0.0002794294,0.00038707422,0.00010948312,0.00023834393],"domain_scores_gemma":[0.999412,0.00005978049,0.0001308854,0.00011687807,0.00020869108,0.00007178183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019084431,0.00014325415,0.00015692477,0.00032865544,0.00065083255,0.00017612861,0.0003389689,0.0001695946,0.000008772799],"category_scores_gemma":[0.000032407952,0.0001296369,0.000040482395,0.00046958466,0.00005679801,0.00038891664,0.00017028354,0.00032721317,6.5065655e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026508336,0.000022303355,0.0015351952,0.000039036433,0.00025629616,0.0000031756683,0.00015338992,0.24554397,0.023093266,0.0098846145,0.009424949,0.7097787],"study_design_scores_gemma":[0.0007146573,0.00009328674,0.027762357,0.000028903172,0.000020304939,0.0009389817,0.000011444377,0.934921,0.0012106714,0.033308007,0.00086232275,0.00012801784],"about_ca_topic_score_codex":0.000026925862,"about_ca_topic_score_gemma":0.0000067541237,"teacher_disagreement_score":0.7259277,"about_ca_system_score_codex":0.00023757938,"about_ca_system_score_gemma":0.00019462625,"threshold_uncertainty_score":0.5286439},"labels":[],"label_agreement":null},{"id":"W4415655898","doi":"10.21037/qims-2024-2903","title":"Deep learning in multi-modal breast cancer data fusion: a literature review","year":2025,"lang":"en","type":"review","venue":"Quantitative Imaging in Medicine and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Deep learning; Breast cancer; Focus (optics); Scarcity; Cancer; Resource (disambiguation)","score_opus":0.10873471396190748,"score_gpt":0.4232574601129732,"score_spread":0.31452274615106574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415655898","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.073406e-7,0.97053856,0.024210306,0.003728646,0.00088916067,0.00048022377,0.000023346165,0.000067415014,0.000062026855],"genre_scores_gemma":[0.000002434224,0.9953259,0.0030095724,0.0011462998,0.00012028794,0.00014029091,0.00015143002,0.000023248358,0.000080540354],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9960446,0.0010131338,0.0010339118,0.0011610806,0.00035131598,0.00039599172],"domain_scores_gemma":[0.99564487,0.0028367226,0.00046395586,0.00081816706,0.00015427012,0.00008198971],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002970116,0.0004660411,0.0022545282,0.0012106166,0.000092122704,0.00008533475,0.00085307896,0.00012663685,0.000020103302],"category_scores_gemma":[0.0013379147,0.00035828215,0.00012443328,0.003122946,0.00015637261,0.0007993772,0.00062327867,0.0012455977,0.0000035622259],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029836026,0.000016701399,0.0007335548,0.04483947,0.000018475988,0.00025570282,0.0003515191,0.0000019802205,9.780942e-8,0.00007431169,0.0041939444,0.94951123],"study_design_scores_gemma":[0.00016012545,0.000008826256,0.0002815372,0.5329543,0.000092507194,0.00016916006,0.000052385032,0.012280378,1.34596245e-8,0.000027413083,0.45366165,0.0003117579],"about_ca_topic_score_codex":0.0003273978,"about_ca_topic_score_gemma":0.00019426923,"teacher_disagreement_score":0.9491995,"about_ca_system_score_codex":0.00019344779,"about_ca_system_score_gemma":0.0005813022,"threshold_uncertainty_score":0.99988693},"labels":[],"label_agreement":null},{"id":"W4415667207","doi":"10.1038/s41598-025-21787-9","title":"Detection, localization, and staging of breast cancer lymph node metastasis in digital pathology whole slide images using selective neighborhood attention-based deep learning","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities; Terry Fox Foundation; Lotte and John Hecht Memorial Foundation","keywords":"Jaccard index; Deep learning; Receiver operating characteristic; Breast cancer; Digital pathology; Lymph node; Concordance; Biopsy; Feature (linguistics)","score_opus":0.0063545499239354925,"score_gpt":0.24420342889314917,"score_spread":0.23784887896921367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415667207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19425875,0.00025581807,0.8035077,0.00010252375,0.001569618,0.00015135497,0.0000052199834,0.00007461962,0.00007440754],"genre_scores_gemma":[0.99771667,0.0000044907215,0.002104999,0.000028126069,0.000016349537,0.000025702877,0.0000068186555,0.000010892797,0.00008597439],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978407,0.000100286474,0.0005558636,0.00088472955,0.00032833507,0.00029007267],"domain_scores_gemma":[0.9984168,0.00006450655,0.0004373317,0.00043574645,0.00059388106,0.000051742107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085935136,0.0001561026,0.00023429155,0.0006937317,0.0004013945,0.0004444878,0.00016513318,0.00006521196,0.000005352098],"category_scores_gemma":[0.00017432055,0.00016622918,0.000059114038,0.0024315706,0.00022776444,0.0009390034,0.00014906217,0.00013127009,5.99525e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015693542,0.00007803122,0.6784557,0.000109541026,0.000043948883,0.000085646534,0.00045676905,0.1593913,0.073515244,0.000049457907,0.00003090399,0.08776775],"study_design_scores_gemma":[0.00056896347,0.000025581474,0.12148544,0.00034299958,0.000059630416,0.00030993661,0.00028688423,0.77354205,0.09458497,0.00821009,0.00020853498,0.000374887],"about_ca_topic_score_codex":0.00024919,"about_ca_topic_score_gemma":0.000093122304,"teacher_disagreement_score":0.8034579,"about_ca_system_score_codex":0.00036009232,"about_ca_system_score_gemma":0.00038493605,"threshold_uncertainty_score":0.6778629},"labels":[],"label_agreement":null},{"id":"W4415688800","doi":"10.1007/978-3-032-04339-9_17","title":"Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Concordia University","funders":"","keywords":"Context (archaeology); Domain (mathematical analysis); Task (project management); Digital pathology; Computational model; Clinical Practice; Computational Science and Engineering","score_opus":0.0419747694207174,"score_gpt":0.29572737156089596,"score_spread":0.2537526021401786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415688800","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020985412,0.000421865,0.9568287,0.00057025685,0.0001973035,0.00079861336,0.0000049192245,0.000101460755,0.040867038],"genre_scores_gemma":[0.25611684,0.0010051607,0.7408213,0.0013413619,0.000022069487,0.00022098754,0.000026481284,0.000015417729,0.00043038683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788904,0.00010162205,0.0007575027,0.00045266168,0.0004937037,0.0003054636],"domain_scores_gemma":[0.99612844,0.001009909,0.00037955574,0.0020870683,0.00030283313,0.000092202004],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016464918,0.00026756772,0.0003013634,0.0015465062,0.000394001,0.00048594334,0.0029167605,0.00015183748,0.0000018168842],"category_scores_gemma":[0.00015336067,0.00025253685,0.000026962729,0.0010211833,0.00096319773,0.004018753,0.002224984,0.00062678044,0.000011314223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050178173,0.000042224237,0.00005313288,0.00008281743,0.0000058625697,0.000004685829,0.0111105535,0.22262067,0.000012578492,0.45170328,0.00015575804,0.3142034],"study_design_scores_gemma":[0.00033772393,0.00011787738,0.00041652756,0.00080717896,0.0000041543467,0.00003726765,0.000028625851,0.9848402,0.000028763208,0.012313134,0.0007894443,0.0002790634],"about_ca_topic_score_codex":0.000028328017,"about_ca_topic_score_gemma":0.000024784962,"teacher_disagreement_score":0.76221955,"about_ca_system_score_codex":0.00036502082,"about_ca_system_score_gemma":0.0007191742,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W4415719589","doi":"10.18280/ts.420504","title":"A Hybrid Mobile Net-Active Learning Framework for Breast Cancer Detection Using Ultrasound Images","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ultrasound; Breast cancer; Breast ultrasound; Cancer detection; Pattern recognition (psychology); Cancer","score_opus":0.014874158546952733,"score_gpt":0.29099492136116256,"score_spread":0.27612076281420983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415719589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14040683,0.00087704865,0.8528859,0.00022512856,0.0032689974,0.0018142725,0.00020985989,0.00021932278,0.00009265167],"genre_scores_gemma":[0.981095,0.000252246,0.015748296,0.00031949522,0.0013091787,0.0010060703,0.0000056845606,0.000059708702,0.00020430288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958122,0.0003186499,0.0008278554,0.0014056346,0.0006257147,0.0010099622],"domain_scores_gemma":[0.9973793,0.0008295494,0.00061317376,0.00045404374,0.00054401136,0.00017994308],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00067976024,0.00062016386,0.00055537163,0.00042314042,0.0014767852,0.0007709221,0.0007109172,0.00024237923,0.00070534134],"category_scores_gemma":[0.00007383972,0.00072064507,0.0003658663,0.0010563751,0.00023949689,0.0012447429,0.00021264677,0.0009191269,0.000010597818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076989736,0.00023436123,0.0005928219,0.0003017233,0.0004888107,0.000006423547,0.0012996113,0.13415691,0.07713109,0.0004865095,0.00011251325,0.7844193],"study_design_scores_gemma":[0.0023239772,0.0011840245,0.009506974,0.0014102379,0.0005336121,0.00013457285,0.00076751807,0.6789182,0.29254666,0.0077032186,0.003765536,0.0012054833],"about_ca_topic_score_codex":0.00058104837,"about_ca_topic_score_gemma":0.00004248818,"teacher_disagreement_score":0.84068817,"about_ca_system_score_codex":0.0019034462,"about_ca_system_score_gemma":0.0006308149,"threshold_uncertainty_score":0.99982315},"labels":[],"label_agreement":null},{"id":"W4415902225","doi":"10.1016/j.mlwa.2025.100789","title":"Beyond single-run metrics with CP-fuse: A rigorous multi-cohort evaluation of clinico-pathological fusion for improved survival prediction in TCGA","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University; Jewish General Hospital","funders":"Canada Research Chairs","keywords":"Benchmark (surveying); Fusion; Survival analysis; Calibration; Pattern recognition (psychology); Feature (linguistics)","score_opus":0.0315292332960606,"score_gpt":0.31455197407066415,"score_spread":0.28302274077460354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415902225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067253955,0.00014544501,0.9287612,0.0003593193,0.000120990844,0.0024017848,0.00001679486,0.00021273733,0.0007277829],"genre_scores_gemma":[0.84903437,0.000016439184,0.1484609,0.0000464943,0.000042268992,0.0021473328,0.000072356765,0.00001804654,0.00016178806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978832,0.00025814096,0.0004813747,0.00068955,0.0004445581,0.00024317401],"domain_scores_gemma":[0.99800265,0.0004130289,0.00037694196,0.0005618305,0.0005953477,0.00005021502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022149766,0.00019010532,0.00028882577,0.00045110373,0.00025781384,0.00006287893,0.00040298782,0.00014212985,0.0000041799426],"category_scores_gemma":[0.0003429455,0.00015650927,0.000051879524,0.0021477034,0.000086075685,0.00021759268,0.00011516613,0.00040673773,0.0000018206412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004243917,0.0012214103,0.4431386,0.00011776798,0.00010661489,8.4950017e-7,0.0004690502,0.074355386,0.0097289765,0.005052253,0.000033681183,0.46535102],"study_design_scores_gemma":[0.002890867,0.0008271174,0.13320006,0.000042743246,0.00013118298,0.000005578946,0.000046758374,0.85950553,0.0010875624,0.0010199603,0.0010649341,0.00017770584],"about_ca_topic_score_codex":0.00017879109,"about_ca_topic_score_gemma":0.00054357713,"teacher_disagreement_score":0.7851501,"about_ca_system_score_codex":0.00032796484,"about_ca_system_score_gemma":0.0002201907,"threshold_uncertainty_score":0.6382263},"labels":[],"label_agreement":null},{"id":"W4415973317","doi":"10.2196/73605","title":"Large Language Model Versus Manual Review for Clinical Data Curation in Breast Cancer: Retrospective Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data curation; Data extraction; Data quality; Scalability; MEDLINE; Quality (philosophy); Information extraction","score_opus":0.10572829371582713,"score_gpt":0.49519443938524915,"score_spread":0.389466145669422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415973317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03655125,0.0016685014,0.9472128,0.005371972,0.0021663636,0.0043935827,0.00041090464,0.00025377146,0.0019708385],"genre_scores_gemma":[0.96685797,0.0060158656,0.017643875,0.007147189,0.0004210023,0.0015094642,0.00021581438,0.000017589997,0.00017124937],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976715,0.00011550469,0.0010158289,0.00027781926,0.0006519362,0.00026745317],"domain_scores_gemma":[0.9982709,0.00028147936,0.00026475516,0.00091638014,0.0001585621,0.000107912034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019917355,0.00015057839,0.0004454745,0.00010109031,0.000089308174,0.000059270104,0.0013939199,0.0001271851,0.000020630532],"category_scores_gemma":[0.00022253598,0.00013035674,0.000052775966,0.00060650724,0.00006207224,0.0014133025,0.0007590873,0.00048547005,0.000011798276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012163679,0.0041032117,0.01908991,0.0043396787,0.00067443255,0.000020206351,0.07959337,0.00047889873,0.0000014154093,0.031145327,0.5594976,0.29983956],"study_design_scores_gemma":[0.0030469506,0.00017186232,0.0039033494,0.00072120375,0.00003119343,0.0000021768599,0.0026304598,0.9872611,0.0000020303942,0.00021786074,0.0018642915,0.00014748987],"about_ca_topic_score_codex":0.000024185905,"about_ca_topic_score_gemma":0.00044525272,"teacher_disagreement_score":0.98678225,"about_ca_system_score_codex":0.0002867009,"about_ca_system_score_gemma":0.00056264084,"threshold_uncertainty_score":0.5315794},"labels":[],"label_agreement":null},{"id":"W4415988651","doi":"10.1002/alz.70775","title":"Digital neuropathology of neurodegenerative disorders: Foundations, research advances, and future directions","year":2025,"lang":"en","type":"review","venue":"Alzheimer s & Dementia","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs","funders":"National Institute of Neurological Disorders and Stroke; National Institute on Aging; National Institutes of Health","keywords":"Neuropathology; Digital pathology; Disease; Neurodegeneration; Workflow; Digital image analysis","score_opus":0.051722837993784326,"score_gpt":0.37084668291352474,"score_spread":0.31912384491974044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415988651","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6338451e-7,0.9831616,0.010708773,0.00022427055,0.0019859914,0.0006659716,0.000041745254,0.00008559475,0.0031258906],"genre_scores_gemma":[0.00003666357,0.9965,0.0028486657,0.000020030173,0.00027806772,0.00020626144,0.00003987987,0.000024313662,0.000046086454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973603,0.00058865815,0.00053079275,0.0008613112,0.00033348,0.0003254582],"domain_scores_gemma":[0.9982338,0.0004278078,0.000280571,0.00079022057,0.00020296272,0.000064662345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003327116,0.00030351753,0.0006422234,0.0005637185,0.000353217,0.00023232013,0.0007961064,0.00016347681,0.000012317245],"category_scores_gemma":[0.00006234537,0.00028585954,0.0001742859,0.0015451666,0.0002331992,0.0008672277,0.0007618101,0.00052835536,0.000016241898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010969994,0.000044942342,0.0000047550934,0.00042595193,0.00072651624,0.0000019633394,0.00004282941,5.5914524e-7,1.5916807e-7,0.0029758338,0.00040511283,0.99537027],"study_design_scores_gemma":[0.00006682146,0.0001348137,0.000007877819,0.00033587895,0.0021269305,0.000020368165,0.000009141619,0.000034392906,0.000005996456,0.000610968,0.99645364,0.00019319728],"about_ca_topic_score_codex":0.000010571642,"about_ca_topic_score_gemma":0.000056278008,"teacher_disagreement_score":0.9960485,"about_ca_system_score_codex":0.000015669588,"about_ca_system_score_gemma":0.00044997648,"threshold_uncertainty_score":0.99995935},"labels":[],"label_agreement":null},{"id":"W4416019033","doi":"10.1016/j.ijgc.2025.102190","title":"MULTICOHORT DEVELOPMENT AND VALIDATION OF A REPRODUCIBLE VAGINAL MICROBIOME MODEL FOR ENDOMETRIAL CANCER DETECTION","year":2025,"lang":"en","type":"article","venue":"International Journal of Gynecological Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Endometrial cancer; Microbiome; Vaginal cancer; Vagina; MEDLINE","score_opus":0.04019977965437519,"score_gpt":0.3443785331204776,"score_spread":0.3041787534661024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416019033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38094956,0.00045339996,0.6148187,0.0010322535,0.0025100664,0.00018166975,0.000007943879,0.000012698647,0.00003372124],"genre_scores_gemma":[0.95744973,0.00021992363,0.04170507,0.00017075008,0.00020293974,0.000089532725,8.378602e-7,0.000004495554,0.0001567274],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986114,0.000038374223,0.0005968583,0.00028667197,0.00033151158,0.00013521491],"domain_scores_gemma":[0.9979382,0.0002733241,0.00052016875,0.00011685802,0.0011085754,0.000042860644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072879146,0.00010723609,0.00023058112,0.00044205552,0.000065602064,0.00006488359,0.00048708802,0.00008517512,0.000020034999],"category_scores_gemma":[0.00047132012,0.000090602305,0.0000877784,0.0002959649,0.00005152249,0.00036525854,0.00013284256,0.00013746847,3.031429e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001211464,0.00028460438,0.008382551,0.000077482386,0.0007223913,0.000006887778,0.000653579,0.041438296,0.1512404,0.0014224303,0.00054513686,0.79401475],"study_design_scores_gemma":[0.0034259963,0.00032433972,0.013622341,0.00015238767,0.00007106957,0.000028919214,0.000020644313,0.12347181,0.8469931,0.004247413,0.007436994,0.00020501614],"about_ca_topic_score_codex":0.000037655915,"about_ca_topic_score_gemma":0.000055182638,"teacher_disagreement_score":0.7938098,"about_ca_system_score_codex":0.0006882521,"about_ca_system_score_gemma":0.0004777062,"threshold_uncertainty_score":0.3694655},"labels":[],"label_agreement":null},{"id":"W4416029571","doi":"10.1016/b978-0-443-33012-4.00024-0","title":"Predictive detection of breast cancer with artificial neural network and support vector machine","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mohawk College","funders":"","keywords":"Breast cancer; Artificial neural network; Support vector machine; Benchmark (surveying); Receiver operating characteristic; Key (lock)","score_opus":0.008290767930907142,"score_gpt":0.21939306575122464,"score_spread":0.2111022978203175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416029571","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024834336,0.0020745683,0.029595684,0.00039426074,0.0041673714,0.0018336019,0.00038936362,0.0004410136,0.9608558],"genre_scores_gemma":[0.18163922,0.00022158779,0.0016132717,0.00038818986,0.0019992653,0.00024276563,0.000014157085,0.00011913843,0.8137624],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825436,0.000036617086,0.00039757547,0.00065611064,0.0003764023,0.00027891796],"domain_scores_gemma":[0.99873585,0.000056119472,0.00039808938,0.0005198618,0.00019794809,0.000092146685],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016502009,0.00037235118,0.00047290607,0.00015966075,0.00014269467,0.000060990693,0.00034520432,0.00023534475,0.000034523677],"category_scores_gemma":[0.0000029749735,0.00033020074,0.00009843866,0.000063830455,0.00018417684,0.00013746785,0.00023769289,0.00048581563,0.0000026567757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016647062,0.000004285702,0.00003810619,0.00008623687,0.00013064832,0.0000095857595,0.00010980005,0.00013094755,0.00008213312,0.0013939618,0.000036523783,0.9978113],"study_design_scores_gemma":[0.0037559138,0.006701683,0.014728678,0.0066676964,0.00261196,0.0015759281,0.000029203467,0.11817656,0.0074415905,0.05230094,0.7804338,0.0055760634],"about_ca_topic_score_codex":0.000014396885,"about_ca_topic_score_gemma":0.00047444718,"teacher_disagreement_score":0.99223524,"about_ca_system_score_codex":0.00018793414,"about_ca_system_score_gemma":0.00027101568,"threshold_uncertainty_score":0.999915},"labels":[],"label_agreement":null},{"id":"W4416085464","doi":"10.1093/neuonc/noaf201.1022","title":"PATH-70. Neuropath-IHC: a deep neural network for virtual immunohistochemistry from digital whole slide images of CNS tumors","year":2025,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Immunohistochemistry; Interpretability; OLIG2; Glioblastoma; Sensitivity (control systems); Gene expression; Lineage markers","score_opus":0.008345121883805378,"score_gpt":0.2592310332279975,"score_spread":0.25088591134419214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416085464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38050923,0.00066224433,0.60245836,0.0030088525,0.008019616,0.0008959692,0.0001840113,0.00052659685,0.0037351395],"genre_scores_gemma":[0.9923065,0.00001680965,0.0054277414,0.0014084534,0.00047490041,0.00015236823,0.000027013532,0.00003487042,0.0001513881],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976573,0.00015120815,0.00062111765,0.0008121657,0.00022501351,0.0005332206],"domain_scores_gemma":[0.9972101,0.0012917796,0.00037452328,0.00085310475,0.00016911543,0.00010139712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017326519,0.00028826742,0.0005131082,0.00009801813,0.00018622457,0.00011864865,0.0012412345,0.0001879312,0.000008947355],"category_scores_gemma":[0.00038258565,0.0003136288,0.00021717035,0.0005059136,0.00022242682,0.00045462025,0.00064048654,0.00043169456,0.000013232256],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028578565,0.00016111591,0.00075618806,0.00004346318,0.000041126066,0.00011798833,0.000292138,0.0033692964,0.8071122,0.0006316438,0.01060568,0.17658335],"study_design_scores_gemma":[0.0075443457,0.0082119275,0.0082297465,0.00021573712,0.00022766297,0.00041138873,0.0004132664,0.31769827,0.44279823,0.016392868,0.19609655,0.0017599876],"about_ca_topic_score_codex":0.000040244853,"about_ca_topic_score_gemma":0.0000059529043,"teacher_disagreement_score":0.6117972,"about_ca_system_score_codex":0.00026212877,"about_ca_system_score_gemma":0.0003477479,"threshold_uncertainty_score":0.9999316},"labels":[],"label_agreement":null},{"id":"W4416094033","doi":"10.1016/j.modpat.2025.100934","title":"Clinical-Grade Interpretable Artificial Intelligence Tool for Automated Detection of Lymph Node Metastasis in Prostate Cancer","year":2025,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; St. Michael's Hospital; University Health Network","funders":"Institute of Cancer Research; Canadian Institutes of Health Research","keywords":"Prostate cancer; Data set; Micrometastasis; Lymph node; Receiver operating characteristic; Training set; Test set; Deep learning","score_opus":0.03979989582514221,"score_gpt":0.36051716079902235,"score_spread":0.32071726497388015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416094033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20295699,0.00025239337,0.79450893,0.00037769324,0.0012420558,0.00039820728,0.000018496434,0.00021880135,0.000026436832],"genre_scores_gemma":[0.9653079,0.00007927477,0.033874683,0.00023603979,0.000027956108,0.0004160066,0.0000017743057,0.000011572305,0.00004477828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978781,0.00024262657,0.00081320596,0.0006245755,0.0001138452,0.00032766475],"domain_scores_gemma":[0.9988261,0.00025094862,0.00024063246,0.0005098849,0.0001449385,0.000027512737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009446462,0.00015404982,0.0003863054,0.00031268154,0.00007896898,0.00004509561,0.00048357513,0.00014955239,0.000003197778],"category_scores_gemma":[0.0001932903,0.0001580702,0.000116796466,0.0006251877,0.0001440838,0.00025113556,0.00020094264,0.0001641666,0.0000030003378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018980402,0.00015231047,0.0038857262,0.00010811097,0.000043630575,0.000009809655,0.0006881596,0.028935812,0.030111916,0.0019644257,0.000017596749,0.9338927],"study_design_scores_gemma":[0.00020944359,0.000096997,0.0035077601,0.000057378456,0.00002204005,0.000007339652,0.00001836967,0.87183946,0.09013969,0.03389203,0.00008223098,0.00012727041],"about_ca_topic_score_codex":0.00016944631,"about_ca_topic_score_gemma":0.0003272136,"teacher_disagreement_score":0.9337654,"about_ca_system_score_codex":0.00019886627,"about_ca_system_score_gemma":0.0002245188,"threshold_uncertainty_score":0.64459157},"labels":[],"label_agreement":null},{"id":"W4416217346","doi":"10.1016/j.landig.2025.100933","title":"Application of artificial intelligence and digital tools in cancer pathology","year":2025,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Digital pathology; Workflow; Applications of artificial intelligence; Precision medicine; Deep learning; Radiomics; Cancer","score_opus":0.06412705673087551,"score_gpt":0.35747661020142485,"score_spread":0.29334955347054936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416217346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07552329,0.00074683735,0.90895444,0.012137008,0.0002521022,0.0003789476,0.000043342752,0.00007180239,0.0018922257],"genre_scores_gemma":[0.998633,0.00014323645,0.00044011587,0.00065171154,0.000058571593,0.000045327604,0.0000022706884,0.0000029286332,0.00002283722],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991973,0.000025649431,0.00026205007,0.00022189465,0.000091589776,0.0002014975],"domain_scores_gemma":[0.9993418,0.0001633647,0.000104911305,0.00033590713,0.000029203584,0.000024814448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023850826,0.000068076966,0.00018716873,0.000067070236,0.00004632863,0.00013311111,0.00037529378,0.00003101209,4.7491818e-7],"category_scores_gemma":[0.00004479706,0.000053815125,0.00001570015,0.00046094172,0.00009563132,0.0005054385,0.00015562493,0.00011535634,0.0000035106718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016099382,0.000020885034,0.003507551,0.000038481856,0.0000020036066,3.9068075e-7,0.00026731179,0.00012718218,0.000013288764,0.055741176,0.0000610571,0.94020456],"study_design_scores_gemma":[0.00039124436,0.0004678667,0.11044021,0.00030361483,0.0000042119514,0.000031438998,0.00040767234,0.11429806,0.0026651423,0.7618886,0.008727844,0.00037408638],"about_ca_topic_score_codex":0.000112366324,"about_ca_topic_score_gemma":0.00014133388,"teacher_disagreement_score":0.9398305,"about_ca_system_score_codex":0.00008217027,"about_ca_system_score_gemma":0.00014070014,"threshold_uncertainty_score":0.21945171},"labels":[],"label_agreement":null},{"id":"W4416221296","doi":"10.1097/pas.0000000000002481","title":"Performance Assessment of a Deep Learning–based Algorithm for Ovarian Cancer Histotyping in an Independent Data Set","year":2025,"lang":"en","type":"article","venue":"The American Journal of Surgical Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ovarian cancer; Voting; Serous fluid; Data set; Domain (mathematical analysis); Domain adaptation; Diagnostic accuracy","score_opus":0.031977820851810154,"score_gpt":0.3495695417127254,"score_spread":0.31759172086091525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416221296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29596636,0.00018255813,0.7020848,0.0012627948,0.00034131433,0.00010148598,0.00000488675,0.000009881516,0.000045936984],"genre_scores_gemma":[0.9366078,0.00018769545,0.06290107,0.00020039985,0.00007154295,0.000014545443,0.000002115566,0.0000065032195,0.000008321123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982859,0.00050327566,0.00050025096,0.00025647442,0.00022934105,0.00022479519],"domain_scores_gemma":[0.9981721,0.0003641853,0.00073180784,0.00050474406,0.00017754317,0.000049609553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020242808,0.00010567766,0.00040895148,0.00024102378,0.0000849318,0.000020777807,0.0014006039,0.000038520764,0.0000075122875],"category_scores_gemma":[0.000023831413,0.00007824053,0.00006165116,0.0005630438,0.00024509794,0.0002869565,0.0002240092,0.0004733601,1.9933653e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014135384,0.00007055817,0.011578876,0.000013146716,0.000023449098,0.000055746223,0.00022751212,0.012203395,0.00022684033,0.00012765841,0.000010491256,0.975321],"study_design_scores_gemma":[0.0010960306,0.0012109412,0.06471194,0.00005784085,0.000024839333,0.0001563682,0.0001272735,0.930526,0.00011004733,0.00017320742,0.0017104959,0.00009497552],"about_ca_topic_score_codex":0.000057361314,"about_ca_topic_score_gemma":0.00002986935,"teacher_disagreement_score":0.975226,"about_ca_system_score_codex":0.00022653297,"about_ca_system_score_gemma":0.0003263127,"threshold_uncertainty_score":0.31905565},"labels":[],"label_agreement":null},{"id":"W4416412042","doi":"10.1080/1354750x.2025.2591717","title":"Emerging biomarkers in breast cancer: translational and multi-omics perspectives in precision oncology","year":2025,"lang":"en","type":"article","venue":"Biomarkers","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research","funders":"","keywords":"Biomarker; Precision medicine; Breast cancer; Liquid biopsy; Biomarker discovery; Translational research; Extracellular vesicles; Standardization; Harmonization","score_opus":0.01759147204653635,"score_gpt":0.315943726080586,"score_spread":0.2983522540340497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416412042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67771125,0.011524284,0.26464275,0.039292473,0.0026055072,0.0013420302,0.000044473316,0.00025929877,0.002577939],"genre_scores_gemma":[0.9775366,0.00094067527,0.021296104,0.00010108725,0.00002278472,0.000066479755,0.0000015849649,0.00000837854,0.00002630843],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99868107,0.00013579802,0.00027955818,0.00052518636,0.00013834523,0.00024007172],"domain_scores_gemma":[0.9995043,0.00014368443,0.00006778649,0.00019393375,0.00004577971,0.00004448938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047996355,0.00013527749,0.00016973088,0.0006571445,0.00007142738,0.00004508413,0.00028774294,0.0001239818,0.000010121843],"category_scores_gemma":[0.000023420209,0.00014545092,0.00003937019,0.0011255228,0.00010592091,0.0003598638,0.00010075432,0.00012662366,0.0000011356786],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033697434,0.000129198,0.1729431,0.000031209045,0.00010203668,0.000013442374,0.0032704684,0.00029866508,0.004023797,0.001142789,0.00031454372,0.8173938],"study_design_scores_gemma":[0.0022813273,0.000032127235,0.6870475,0.00016383282,0.000007774043,0.000017464115,0.0011411929,0.3064481,0.0003470314,0.0009259765,0.0013669217,0.00022080271],"about_ca_topic_score_codex":0.0012967407,"about_ca_topic_score_gemma":0.0019865243,"teacher_disagreement_score":0.81717294,"about_ca_system_score_codex":0.0006688426,"about_ca_system_score_gemma":0.00029389677,"threshold_uncertainty_score":0.5931316},"labels":[],"label_agreement":null},{"id":"W4416552516","doi":"10.1038/s41598-025-26789-1","title":"BoxCell: Leveraging SAM for Cell Segmentation with Box Supervision","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Minimum bounding box; Segmentation; Bounding overwatch; Scale-space segmentation; Dice; Image segmentation; Segmentation-based object categorization; Object (grammar); Point (geometry)","score_opus":0.012444745170305948,"score_gpt":0.25118154380130314,"score_spread":0.2387367986309972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416552516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07856669,0.0001207244,0.90810317,0.00044447105,0.009456942,0.0005501113,4.956685e-7,0.00019079294,0.0025665797],"genre_scores_gemma":[0.8947252,0.0000028389015,0.09561838,0.00014538688,0.000050534567,0.00010658007,0.000015720389,0.000011237394,0.009324141],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980867,0.000026912725,0.00031308256,0.0008973765,0.00041178495,0.0002641358],"domain_scores_gemma":[0.9985821,0.000047868376,0.00017601295,0.00091565785,0.00022470824,0.000053624917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966065,0.00011953202,0.00011475945,0.00024572556,0.0005216501,0.00068038603,0.00028534053,0.00004127354,0.00001006512],"category_scores_gemma":[0.00002256981,0.00010469566,0.00005555277,0.00090014713,0.00006635408,0.0006507095,0.000121666235,0.00007106616,0.0000067588658],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094990646,0.0005533295,0.0093556745,0.00069507473,0.00007869937,0.00034495248,0.005623576,0.007398572,0.42074138,0.002096931,0.21382847,0.33918837],"study_design_scores_gemma":[0.000573428,0.00011917939,0.00045297138,0.000110990375,0.000022508313,0.00009320535,0.00018215072,0.032679748,0.8574162,0.02058136,0.08748103,0.00028719916],"about_ca_topic_score_codex":0.000028423929,"about_ca_topic_score_gemma":0.00001595897,"teacher_disagreement_score":0.8161585,"about_ca_system_score_codex":0.00016531404,"about_ca_system_score_gemma":0.00027065337,"threshold_uncertainty_score":0.65609777},"labels":[],"label_agreement":null},{"id":"W4416588311","doi":"10.2196/66931","title":"Impact of AI on Breast Cancer Detection Rates in Mammography by Radiologists of Varying Experience Levels in Singapore: Preliminary Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Mammography; Breast cancer; Breast cancer screening; Mammography screening; Screening mammography","score_opus":0.07915726736223347,"score_gpt":0.47367294209183325,"score_spread":0.3945156747295998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416588311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907507,0.00014014059,0.0076692277,0.000098611505,0.00010164091,0.0010032988,0.000029028524,0.00002058833,0.00018679965],"genre_scores_gemma":[0.9993274,0.000019745616,0.000057273526,0.0000090538215,0.0000069548814,0.0005657882,9.933249e-7,0.00000468135,0.000008085079],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99732566,0.00084215606,0.00050569605,0.00037609137,0.0005486731,0.0004017229],"domain_scores_gemma":[0.9985569,0.00050198985,0.00017351705,0.00036944705,0.00035420328,0.000043921416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011132637,0.00016237951,0.00036145907,0.0013627809,0.000114197814,0.000042881362,0.00063714664,0.000079078134,0.00000841702],"category_scores_gemma":[0.000035245648,0.00013668457,0.00007205877,0.0040887063,0.00031783237,0.0011546208,0.00026460286,0.00066165556,0.000001159788],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035518415,0.003963867,0.6544176,0.00031199295,0.00020632969,0.000014605833,0.17982014,0.010383158,0.06340437,0.00039521724,0.00081149524,0.082719415],"study_design_scores_gemma":[0.0009909506,0.0026904612,0.8948064,0.00030203327,0.0000011600085,0.0000029301602,0.00263694,0.023891822,0.07408938,0.00046942866,0.00000256191,0.00011592757],"about_ca_topic_score_codex":0.0023900864,"about_ca_topic_score_gemma":0.00018791787,"teacher_disagreement_score":0.24038883,"about_ca_system_score_codex":0.00082344655,"about_ca_system_score_gemma":0.00025096853,"threshold_uncertainty_score":0.5573835},"labels":[],"label_agreement":null},{"id":"W4416590576","doi":"10.1038/s41746-025-02095-y","title":"Multimodal analysis of whole slide images in colorectal cancer","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Leeds Biomedical Research Centre; National Health and Medical Research Council; Medical Research Council; National Institutes of Health; Gemeinsame Bundesausschuss; Deutsche Forschungsgemeinschaft; Deutsche Krebshilfe; European Commission; HORIZON EUROPE Framework Programme; Department of Health and Social Care; National Institute for Health and Care Research; Deutscher Akademischer Austauschdienst; University of New South Wales; Nvidia","keywords":"Multimodal therapy; Modality (human–computer interaction); Modalities; Colorectal cancer; Digital pathology; Treatment modality; MEDLINE","score_opus":0.007855304520056427,"score_gpt":0.2872012234811282,"score_spread":0.27934591896107175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416590576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8486759,0.0007419739,0.122591116,0.004839109,0.0009054545,0.00022724974,0.00003634541,0.00011688318,0.021865984],"genre_scores_gemma":[0.9989295,0.000019886,0.00047285773,0.00015142177,0.00004120316,0.00002564014,0.0000055899163,0.0000035579617,0.00035033087],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99898565,0.000017644476,0.0002962608,0.0002862062,0.00024899747,0.00016524173],"domain_scores_gemma":[0.9993945,0.00015580619,0.00008731017,0.00023257262,0.00008905111,0.000040786093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013515126,0.00010077674,0.00032407165,0.0006606937,0.000021274856,0.000028572533,0.00037552632,0.000045709985,0.00002095846],"category_scores_gemma":[0.00015352787,0.000084806365,0.000060459803,0.0028342812,0.00012515775,0.00041977043,0.00012348135,0.00010482936,0.000003057846],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103701794,0.00018947454,0.21294917,0.00008848481,0.0007183327,0.000033733333,0.001756295,0.0054999883,0.050995763,0.0023568461,0.0040069064,0.7213013],"study_design_scores_gemma":[0.0021243547,0.0003905323,0.7811526,0.00040778873,0.00028609278,0.0000026000253,0.00029930004,0.15831265,0.05077588,0.002196595,0.003747398,0.0003042078],"about_ca_topic_score_codex":0.00061130873,"about_ca_topic_score_gemma":0.00036306458,"teacher_disagreement_score":0.7209971,"about_ca_system_score_codex":0.00015198608,"about_ca_system_score_gemma":0.000082266204,"threshold_uncertainty_score":0.34583032},"labels":[],"label_agreement":null},{"id":"W4416739914","doi":"10.3390/cancers17233797","title":"Tissue Microarray-Based Digital Spatial Profiling of Benign Breast Lobules and Breast Cancers: Feasibility, Biological Coherence, and Cross-Platform Benchmarks","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute","keywords":"Profiling (computer programming); Risk stratification; Breast tissue; Digital pathology; Sampling (signal processing); Breast imaging; Breast tumours; Breast cancer","score_opus":0.018565284909670063,"score_gpt":0.28160673404454245,"score_spread":0.2630414491348724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416739914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9035356,0.0009051268,0.09208603,0.00021003521,0.00069728197,0.0006276843,0.00034466363,0.000105026746,0.0014885188],"genre_scores_gemma":[0.9961731,0.00003681553,0.0035184675,0.00009357949,0.00007670075,0.000041792904,0.000021423153,0.00000794793,0.000030170191],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99834037,0.00002846704,0.000354308,0.000731699,0.00020097592,0.00034419398],"domain_scores_gemma":[0.99900573,0.00011570887,0.00017239948,0.00040477718,0.00017669908,0.00012467365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020520481,0.00023883063,0.00032469112,0.00013096862,0.0001730017,0.00028900642,0.00043225626,0.00016937779,0.000028508342],"category_scores_gemma":[0.000031294778,0.00021825863,0.000050229082,0.0004153574,0.0007014817,0.0005482317,0.0002446275,0.00019497226,8.943795e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006381268,0.000052535514,0.4538469,0.00050822773,0.00011885083,0.00001372179,0.00044220767,0.0027422663,0.017702729,0.0022017444,0.00042346137,0.52130926],"study_design_scores_gemma":[0.008748257,0.0020750188,0.6074931,0.0016209815,0.00011457842,0.000528174,0.0008224667,0.11649246,0.24270746,0.014362133,0.0024981191,0.0025372826],"about_ca_topic_score_codex":0.0018920413,"about_ca_topic_score_gemma":0.00048212183,"teacher_disagreement_score":0.51877195,"about_ca_system_score_codex":0.0011233232,"about_ca_system_score_gemma":0.0011967974,"threshold_uncertainty_score":0.8900329},"labels":[],"label_agreement":null},{"id":"W4416780876","doi":"10.1016/j.esmorw.2025.100548","title":"352P Pathomic embeddings improve prediction of clinically actionable breast cancer related mutations from whole slide images","year":2025,"lang":"en","type":"article","venue":"ESMO Real World Data and Digital Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Breast cancer; Mutation; Cancer; Feature (linguistics)","score_opus":0.018376915422445485,"score_gpt":0.3267523096492561,"score_spread":0.30837539422681065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416780876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5805412,0.00069063494,0.22094479,0.02572238,0.012057761,0.0017814245,0.042285852,0.0017190172,0.11425694],"genre_scores_gemma":[0.99086094,0.000267528,0.0058825877,0.00018631064,0.000123454,0.000037998456,0.0006102181,0.0000103689945,0.0020206205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984337,0.00005260608,0.0005763479,0.0006124135,0.0001339297,0.00019096714],"domain_scores_gemma":[0.99832237,0.0005019009,0.0003334136,0.0006496711,0.00011896533,0.00007369737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024090812,0.000128307,0.0002764895,0.00017488966,0.000121795994,0.00014722321,0.0005664334,0.000100078876,0.000016803693],"category_scores_gemma":[0.000083030885,0.00012583281,0.000040085804,0.0005517157,0.0001846417,0.0018654106,0.0006834625,0.00022580205,0.000011207761],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023735927,0.00036519428,0.07851564,0.00003534274,0.00027037074,0.000018251596,0.0003039561,0.00011223796,0.0033554127,0.0031237944,0.019016122,0.89464635],"study_design_scores_gemma":[0.0039037392,0.00087433273,0.69489384,0.00022574022,0.00029088333,0.00006980393,0.00033671205,0.0913186,0.0016510846,0.042105258,0.16378051,0.0005494637],"about_ca_topic_score_codex":0.0013930461,"about_ca_topic_score_gemma":0.00053280033,"teacher_disagreement_score":0.89409685,"about_ca_system_score_codex":0.0002296935,"about_ca_system_score_gemma":0.00045020867,"threshold_uncertainty_score":0.5131313},"labels":[],"label_agreement":null},{"id":"W4416786470","doi":"10.2196/72665","title":"Comparison of Machine Learning Models for Colon Cancer Survival: Predictive Modeling Approach","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Colorectal cancer; Predictive modelling; Cancer; Clinical Practice; MEDLINE","score_opus":0.10407284683720595,"score_gpt":0.3836249451323374,"score_spread":0.27955209829513145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416786470","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008312409,0.003052043,0.9841564,0.00033640667,0.0009924986,0.00087258255,0.000037268186,0.0001986214,0.0020417154],"genre_scores_gemma":[0.98576146,0.00018746848,0.010996852,0.00007980517,0.000121143625,0.0022388212,0.0000064201354,0.000021398193,0.0005866553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840045,0.00007419286,0.00037957897,0.0005346477,0.0003035607,0.0003075601],"domain_scores_gemma":[0.9989871,0.00009970853,0.00021449916,0.00034029467,0.0003088344,0.000049592072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026518304,0.00018583846,0.00040207416,0.0001646244,0.00018446824,0.00004782448,0.00056558265,0.00012438754,0.0000066367456],"category_scores_gemma":[0.000016417283,0.00018636377,0.0001087729,0.00059038535,0.00004514462,0.00040252614,0.0001898954,0.00029308983,3.8882672e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013387443,0.000066521745,0.0026574754,0.00018444401,0.00008062122,6.9103415e-8,0.0013136275,0.96851957,0.00046609828,0.0036025832,0.00048378934,0.02249133],"study_design_scores_gemma":[0.0006348244,0.00010813405,0.000100951635,0.00011763321,0.000030477018,1.7130812e-7,0.00011809267,0.99236995,0.0024648432,0.0022819284,0.0016091209,0.00016386877],"about_ca_topic_score_codex":0.0013224178,"about_ca_topic_score_gemma":0.00031512688,"teacher_disagreement_score":0.977449,"about_ca_system_score_codex":0.00046304238,"about_ca_system_score_gemma":0.0003156354,"threshold_uncertainty_score":0.7599694},"labels":[],"label_agreement":null},{"id":"W4416799376","doi":"10.1109/icriset64803.2025.11253735","title":"Hybrid Ensemble DL Model for Breast Cancer Detection and Classification with Enhanced Breast Lesion Segmentation using U-Net Model","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Segmentation; Pattern recognition (psychology); Breast cancer; Mammography; Deep learning; Image segmentation; Masking (illustration); Breast ultrasound; Medical imaging","score_opus":0.04168465454664711,"score_gpt":0.30182034448735634,"score_spread":0.26013568994070924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416799376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13995408,0.00012273288,0.85637873,0.00081841595,0.00061704713,0.0015806516,0.0001347441,0.00017850495,0.00021509203],"genre_scores_gemma":[0.91769934,0.00036464614,0.079959996,0.00027904872,0.00012824044,0.00041523148,0.0000090120975,0.00004809157,0.0010963752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965144,0.000098734665,0.00070246664,0.0015477999,0.00051318767,0.0006234079],"domain_scores_gemma":[0.997738,0.00007524483,0.0005204484,0.0006658792,0.0008371434,0.00016330571],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041849777,0.00053284125,0.000415923,0.00044817422,0.0009773293,0.0005357741,0.00035189666,0.00022324515,0.000009562471],"category_scores_gemma":[0.00000773907,0.0005299402,0.00010077396,0.00076582603,0.00015980878,0.0022242353,0.00018020852,0.0002732681,0.000002266096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055102585,0.00005580932,0.000028366709,0.00015941534,0.00004704016,1.684676e-7,0.0003144169,0.35040456,0.28280595,0.00041778845,0.000034057575,0.36518142],"study_design_scores_gemma":[0.0016172522,0.00012236601,0.000826167,0.0003491503,0.00020035252,0.00008645708,0.00013179515,0.8436191,0.1501507,0.0024101287,0.000003095939,0.0004834338],"about_ca_topic_score_codex":0.0004378201,"about_ca_topic_score_gemma":0.00081103656,"teacher_disagreement_score":0.7777453,"about_ca_system_score_codex":0.0016109401,"about_ca_system_score_gemma":0.0009925843,"threshold_uncertainty_score":0.9997152},"labels":[],"label_agreement":null},{"id":"W4416944430","doi":"10.3390/cancers17233853","title":"Identification of Potential Biomarkers in Prostate Cancer Microarray Gene Expression Leveraging Explainable Machine Learning Classifiers","year":2025,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Random forest; Prostate cancer; Naive Bayes classifier; Decision tree; Support vector machine; Oversampling; Biomarker discovery; Logistic regression; Identification (biology)","score_opus":0.010589176148577255,"score_gpt":0.2519342481018011,"score_spread":0.24134507195322383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416944430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4690032,0.004060512,0.5219372,0.00083191,0.0029069583,0.0005742543,0.000010415782,0.00017210304,0.0005034775],"genre_scores_gemma":[0.99608046,0.0005286906,0.002441086,0.00007091655,0.00002892844,0.00014335461,0.0000046327104,0.000012410292,0.0006895258],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984248,0.00011276435,0.00041591612,0.0005187458,0.00022173556,0.00030600352],"domain_scores_gemma":[0.99919355,0.000029119235,0.00027257332,0.00035892488,0.00010080602,0.00004503637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042072518,0.00014772579,0.00018520173,0.0004061261,0.00016457231,0.00007379933,0.00045508903,0.00006554783,0.000015823376],"category_scores_gemma":[0.000033428987,0.00016011382,0.000058051955,0.0010037714,0.00007824605,0.0005057226,0.00013549636,0.00021860914,0.0000017201165],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008558413,0.000008028181,0.0048464686,0.00010471329,0.00004010096,0.00000631302,0.0011588833,0.118690364,0.8437359,0.000054575157,0.0004744795,0.030794596],"study_design_scores_gemma":[0.00073143264,0.000023805633,0.0022351535,0.00022765512,0.000011330891,0.0000021704348,0.00037930682,0.20423813,0.79027057,0.00026428315,0.0014339575,0.00018220098],"about_ca_topic_score_codex":0.0016715595,"about_ca_topic_score_gemma":0.00008101101,"teacher_disagreement_score":0.52707726,"about_ca_system_score_codex":0.0022784024,"about_ca_system_score_gemma":0.0006570161,"threshold_uncertainty_score":0.6529252},"labels":[],"label_agreement":null},{"id":"W4416960891","doi":"10.1109/embc58623.2025.11252716","title":"Tri-Model Integration: Advancing Breast Cancer Immunohistochemical Image Generation through Multi-Method Fusion","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Convolutional neural network; Immunohistochemistry; Reliability (semiconductor); Pattern recognition (psychology); Digital pathology; Similarity (geometry); Image quality; Expression (computer science)","score_opus":0.022035674414038132,"score_gpt":0.34972599066587506,"score_spread":0.3276903162518369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416960891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013555485,0.0002463971,0.9911357,0.003435005,0.0011102246,0.00024532474,0.0000049909536,0.00030493358,0.0021618647],"genre_scores_gemma":[0.06793466,0.000105173756,0.9282814,0.0012867706,0.00016457673,0.00012724099,0.000006444947,0.000011147355,0.0020825404],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985498,0.000075867814,0.0003416496,0.0005625161,0.00022409366,0.0002460523],"domain_scores_gemma":[0.99901056,0.000052837866,0.00010005163,0.00053347705,0.0002633718,0.000039678645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002960158,0.00018037292,0.00017840517,0.00010006136,0.00025215797,0.0001464486,0.00046447176,0.00011885429,0.00005835478],"category_scores_gemma":[0.0000357899,0.00016310545,0.00008441004,0.00058607303,0.000036192818,0.0012884119,0.00023075525,0.00023616612,0.000012608818],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016908942,0.000042382148,0.000012692524,0.000011309408,0.000010829073,7.336832e-7,0.00038704756,0.0040147062,0.8179936,0.0058930106,0.005640883,0.16597594],"study_design_scores_gemma":[0.00038255146,0.00001064344,0.00007997792,0.000034768887,0.000008273241,0.000009749376,0.00002445064,0.7585473,0.23935045,0.0010171174,0.00039732357,0.00013741049],"about_ca_topic_score_codex":0.00049681426,"about_ca_topic_score_gemma":0.00018459308,"teacher_disagreement_score":0.7545326,"about_ca_system_score_codex":0.00073139515,"about_ca_system_score_gemma":0.00027739638,"threshold_uncertainty_score":0.6651247},"labels":[],"label_agreement":null},{"id":"W4416960960","doi":"10.1109/embc58623.2025.11253497","title":"TexSegNet: An Attention-Guided Feedback-Driven Texture-Aware Deep Learning Model for Nuclei Segmentation and Classification in Digital Pathology Images of Breast Tissues*","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Digital pathology; Segmentation; Pattern recognition (psychology); Deep learning; Representation (politics); Breast cancer; Data set; Feature extraction","score_opus":0.0182194975108375,"score_gpt":0.28863901905194367,"score_spread":0.27041952154110616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416960960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10829519,0.00003178675,0.8903922,0.00037517803,0.0000745319,0.0002953345,0.000008448469,0.00008130124,0.00044601774],"genre_scores_gemma":[0.96819454,0.00002024575,0.031130169,0.000046408448,0.000014204296,0.00005354471,0.00003123335,0.000008155386,0.0005015021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990598,0.000036311758,0.00027689594,0.00037953007,0.00010488998,0.00014255608],"domain_scores_gemma":[0.9994332,0.00005005405,0.00012887867,0.00020506087,0.00015309422,0.000029721177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013643385,0.000102671474,0.00013705158,0.00016029592,0.00008273637,0.00011287658,0.0001988805,0.00008176879,0.000003286039],"category_scores_gemma":[0.000020193427,0.00010557308,0.000029003933,0.00025973265,0.000054653483,0.0010482542,0.0000819634,0.00008471997,0.0000020694372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045273962,0.000121269404,0.03436594,0.000107461754,0.000018849563,0.000001686781,0.0011620021,0.019524863,0.043462012,0.0059551937,0.00015824715,0.89507717],"study_design_scores_gemma":[0.00050748914,0.000078257784,0.07033029,0.00002844632,0.000006423518,0.000015411595,0.0002922663,0.9251074,0.0008150512,0.002707933,0.00001579469,0.00009521645],"about_ca_topic_score_codex":0.000020250454,"about_ca_topic_score_gemma":0.000068311456,"teacher_disagreement_score":0.90558255,"about_ca_system_score_codex":0.00009068399,"about_ca_system_score_gemma":0.00003526293,"threshold_uncertainty_score":0.43051454},"labels":[],"label_agreement":null},{"id":"W4416987187","doi":"10.2196/79011","title":"FHIR Standard–Based Oncology Data Model for Cancer Screening: Design and Implementation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interoperability; Cancer; Data sharing; Health data; Work (physics); Data exchange; Focus (optics); Patient data; Survivorship curve","score_opus":0.14827943294016796,"score_gpt":0.4809391055522493,"score_spread":0.3326596726120813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416987187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032095518,0.00043047004,0.9903013,0.0029241072,0.00046739457,0.002366132,0.00015161038,0.00011108064,0.000038347785],"genre_scores_gemma":[0.71705276,0.00012745752,0.2718595,0.0021528732,0.00018712367,0.0081569515,0.000022828735,0.000029214629,0.00041131375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985038,0.0000916497,0.00024671675,0.0006729641,0.00021975195,0.00026509893],"domain_scores_gemma":[0.99883306,0.00014412122,0.00013082135,0.0006790235,0.00015979235,0.000053167445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055959314,0.00014580425,0.00020741718,0.0001335946,0.00021684567,0.00011090469,0.000692372,0.000061442996,0.000020911912],"category_scores_gemma":[0.0000109129505,0.00014473674,0.000023378114,0.00033896408,0.00003614002,0.00050960714,0.00032315464,0.000103169565,3.3394153e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041417842,0.00008296156,0.0028178631,0.00006039859,0.00011745863,0.0000014786847,0.0012462977,0.056425665,0.00036320664,0.0005056519,0.036461767,0.9015031],"study_design_scores_gemma":[0.002458732,0.00035618464,0.0014182357,0.000028257084,0.000048021913,2.7549405e-7,0.00017944214,0.965839,0.0011171044,0.0007384641,0.027658984,0.00015729028],"about_ca_topic_score_codex":0.0005300987,"about_ca_topic_score_gemma":0.0033572312,"teacher_disagreement_score":0.90941334,"about_ca_system_score_codex":0.0005457999,"about_ca_system_score_gemma":0.0012276989,"threshold_uncertainty_score":0.59021926},"labels":[],"label_agreement":null},{"id":"W4417102935","doi":"10.1038/s41746-025-02196-8","title":"Self-supervised stain normalization empowers privacy-preserving and model generalization in digital pathology","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Zhejiang University; Hangzhou Science and Technology Bureau; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Normalization (sociology); Stain; Digital pathology; Database normalization; Pattern recognition (psychology); Generalization","score_opus":0.009580765354644742,"score_gpt":0.25238780492241375,"score_spread":0.242807039567769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417102935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16551821,0.00026430344,0.8230569,0.0020495874,0.00027874252,0.00025448063,0.000004044606,0.00021090226,0.008362863],"genre_scores_gemma":[0.9935376,0.000092290225,0.005508697,0.00053232437,0.00005315769,0.000022295515,0.000030109748,0.000011572199,0.0002119361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987172,0.000023616316,0.00034446878,0.0004236638,0.00024764132,0.00024342838],"domain_scores_gemma":[0.9992612,0.00007188076,0.00007590387,0.00041051954,0.00011206327,0.00006841013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001796786,0.00015778844,0.0002011733,0.00035295202,0.000065125285,0.00019149482,0.0004408091,0.00009416526,0.000003149384],"category_scores_gemma":[0.00035118798,0.00014790852,0.000019083924,0.000808958,0.00007033442,0.0021760538,0.0004444615,0.000111562,0.0000021473302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019191201,0.0005020255,0.1336716,0.00095840567,0.00012559173,0.00018326416,0.025867429,0.04337595,0.0038051754,0.13946043,0.0073813363,0.6444769],"study_design_scores_gemma":[0.0009927766,0.000120408054,0.0016378806,0.00012232743,0.0000057207308,0.000013596091,0.00010553779,0.9739406,0.00014327753,0.021641845,0.0011285242,0.00014750673],"about_ca_topic_score_codex":0.000012595221,"about_ca_topic_score_gemma":0.00001010161,"teacher_disagreement_score":0.93056464,"about_ca_system_score_codex":0.0001640942,"about_ca_system_score_gemma":0.00009322312,"threshold_uncertainty_score":0.6031534},"labels":[],"label_agreement":null},{"id":"W4417214487","doi":"10.1016/j.knosys.2025.115096","title":"Mix-domain contrastive learning with Mamba generator for unpaired H&amp;E-to-IHC stain translation","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"China Postdoctoral Science Foundation; Beijing University of Posts and Telecommunications; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Purdue University","keywords":"Generator (circuit theory); Translation (biology); Perspective (graphical); Stain; Pattern recognition (psychology); Contrastive analysis; Matching (statistics)","score_opus":0.022604110867275533,"score_gpt":0.27332931061415544,"score_spread":0.2507251997468799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417214487","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011592746,0.001024685,0.98128384,0.0004801771,0.0016209115,0.0019188358,0.000018899203,0.00044914367,0.0016107731],"genre_scores_gemma":[0.9646114,0.0000011993242,0.031828847,0.00012615198,0.00032435605,0.0011582131,0.00002187089,0.000038273436,0.0018896573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976444,0.00045146214,0.0004434101,0.0007279907,0.00027152506,0.00046115776],"domain_scores_gemma":[0.9980116,0.00056568126,0.00016626104,0.0004941373,0.00061232917,0.00015001952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009807164,0.00029063632,0.0003883847,0.00041199595,0.000397236,0.00026600226,0.0004551329,0.00013815565,0.0000038247636],"category_scores_gemma":[0.00009802704,0.00027033052,0.00010560396,0.0011994794,0.000050821694,0.00022853729,0.00003217011,0.00019234615,0.000041466614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041008554,0.0011360827,0.006647453,0.005452995,0.0012506491,0.000037460337,0.018502386,0.4010581,0.12098118,0.06938932,0.037560977,0.33388254],"study_design_scores_gemma":[0.0058257557,0.0010370499,0.000435776,0.00085639354,0.00007454652,0.0000058364744,0.0005458549,0.6679163,0.019918097,0.00040220458,0.30216506,0.00081714714],"about_ca_topic_score_codex":0.000058476588,"about_ca_topic_score_gemma":0.0004537356,"teacher_disagreement_score":0.95301867,"about_ca_system_score_codex":0.00056265056,"about_ca_system_score_gemma":0.0007135122,"threshold_uncertainty_score":0.9999749},"labels":[],"label_agreement":null},{"id":"W4417250807","doi":"10.1109/bibe66822.2025.00057","title":"Delaunay Triangulations: A New Avenue for Classification of Biomedical Images Using Graph Neural Networks","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Delaunay triangulation; Convolutional neural network; Bowyer–Watson algorithm; Graph; Voronoi diagram; Pattern recognition (psychology); Context (archaeology); Node (physics)","score_opus":0.048936571788896946,"score_gpt":0.3307639364457929,"score_spread":0.28182736465689595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417250807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027930334,0.0016970335,0.9873187,0.0029619827,0.004118965,0.00089469226,0.000010437358,0.0000773466,0.00012780936],"genre_scores_gemma":[0.8897581,0.00006955683,0.10869015,0.0002116298,0.0005450007,0.000041677,0.000009922576,0.000016127782,0.0006577946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766123,0.00012233363,0.0008851199,0.0006329721,0.0003117998,0.00038655754],"domain_scores_gemma":[0.9980609,0.00037741484,0.00044402006,0.0006709432,0.000309917,0.0001367978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000551739,0.00022327034,0.00034029665,0.0005495108,0.00029651262,0.00017829004,0.0006254184,0.0002777445,0.00003363536],"category_scores_gemma":[0.0001734851,0.00023491509,0.0002635662,0.0024808866,0.00025978548,0.0005491541,0.00016340415,0.00021262348,0.0000011388034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020383614,0.00016685063,0.0006446718,0.00015717601,0.00015207165,9.740035e-7,0.0003192219,0.026042698,0.0091874,0.018814594,0.010154502,0.934156],"study_design_scores_gemma":[0.0011688955,0.00017042729,0.00487049,0.00014306058,0.00011909837,0.00000535391,0.000036502763,0.97911465,0.0015811466,0.011341212,0.0012685055,0.00018062619],"about_ca_topic_score_codex":0.00027157276,"about_ca_topic_score_gemma":0.000035780078,"teacher_disagreement_score":0.95307195,"about_ca_system_score_codex":0.0002118275,"about_ca_system_score_gemma":0.00063358655,"threshold_uncertainty_score":0.9579559},"labels":[],"label_agreement":null},{"id":"W4417282532","doi":"10.1109/icce-berlin67488.2025.11277969","title":"Classifying histological images using cell counting estimators","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Digital pathology; Grading (engineering); Pattern recognition (psychology); Cluster analysis; Estimator; H&E stain; Gaussian process; Support vector machine","score_opus":0.03583113918498127,"score_gpt":0.2995882925793104,"score_spread":0.26375715339432915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417282532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018537203,0.001939336,0.9192965,0.0009463309,0.005631381,0.00024675883,0.0000010989341,0.000363302,0.053038083],"genre_scores_gemma":[0.77367383,0.000049141385,0.22239876,0.00068384997,0.00012719083,0.0000073383053,2.3665265e-7,0.000014754897,0.0030449003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673724,0.00017413095,0.00072517357,0.0011366204,0.00045970018,0.0007671427],"domain_scores_gemma":[0.9982322,0.0003076877,0.0003436126,0.0007668832,0.00023018972,0.000119417185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006745876,0.00039033478,0.00042851947,0.00035424347,0.0009249247,0.0007663622,0.0010695234,0.00031197676,0.00021043475],"category_scores_gemma":[0.00013739309,0.00039508936,0.00017880341,0.0014982098,0.00031660782,0.0009805799,0.0009902919,0.00060843065,0.00007661359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012396507,0.00081515836,0.050940666,0.0021186967,0.00026584291,0.00032107395,0.0015400633,0.025543319,0.12532765,0.05747988,0.027049607,0.7084741],"study_design_scores_gemma":[0.0003886143,0.000065908134,0.0011001535,0.00022516375,0.00007380017,0.000029658328,0.0000947297,0.9437561,0.046048474,0.0021208934,0.005642073,0.00045440946],"about_ca_topic_score_codex":0.0003476044,"about_ca_topic_score_gemma":0.000010921928,"teacher_disagreement_score":0.91821283,"about_ca_system_score_codex":0.0012881284,"about_ca_system_score_gemma":0.0008340288,"threshold_uncertainty_score":0.9998501},"labels":[],"label_agreement":null},{"id":"W4417292933","doi":"10.1016/j.jpi.2025.100507","title":"Digital pathology implementation in a multi-site hospital network: the devil is in the details","year":2025,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Digital pathology; MEDLINE; Digital health; Quality (philosophy)","score_opus":0.014174105390318383,"score_gpt":0.3007397860105377,"score_spread":0.2865656806202193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417292933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54122025,0.00022484848,0.45264593,0.0042884545,0.00093738956,0.0002575701,0.000003552688,0.000009876819,0.00041210084],"genre_scores_gemma":[0.9812687,0.000111973015,0.014723914,0.0038041184,0.00005889003,0.000015025912,0.0000011972644,0.0000033769247,0.000012771993],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998289,0.00016829412,0.0009851594,0.00007231681,0.00020250966,0.00028272948],"domain_scores_gemma":[0.99870163,0.00024419342,0.0006191202,0.0003016754,0.000114280054,0.000019098623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017660508,0.00011151007,0.00020154649,0.00023466074,0.000092128794,0.00015559352,0.00086501683,0.000096734126,0.0000031451887],"category_scores_gemma":[0.000094003626,0.000067783105,0.000078095705,0.00068043167,0.00008578908,0.0011238802,0.00018758168,0.0005193356,0.000009166566],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004951663,0.0002448531,0.3381068,0.00006725813,0.00006652695,0.0008069592,0.14878473,0.0063050035,0.000054199743,0.0049567623,0.008912628,0.49164477],"study_design_scores_gemma":[0.006937987,0.0017498101,0.804117,0.0002881474,0.000080249076,0.00593636,0.030873237,0.113099195,0.0003406083,0.020394435,0.01560209,0.0005808311],"about_ca_topic_score_codex":0.0000030608203,"about_ca_topic_score_gemma":0.000104826155,"teacher_disagreement_score":0.49106392,"about_ca_system_score_codex":0.0001244351,"about_ca_system_score_gemma":0.00015174421,"threshold_uncertainty_score":0.27641147},"labels":[],"label_agreement":null},{"id":"W4417308935","doi":"10.1093/jnci/djaf358","title":"Modernizing pathology and oncology education: integrating genomics, artificial intelligence, and clinical relevance into medical training","year":2025,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Accreditation; Operationalization; Curriculum; Health informatics; Graduate medical education; Informatics; Health informatics tools; Resource (disambiguation); Milestone","score_opus":0.12066069622991257,"score_gpt":0.43095590528073313,"score_spread":0.31029520905082053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417308935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13993767,0.0033685104,0.78660166,0.048363693,0.019582655,0.00019516381,0.0000026304676,0.000025293248,0.001922735],"genre_scores_gemma":[0.9379495,0.0014754373,0.05453774,0.0042390735,0.0017222397,0.000012469347,2.8605177e-7,0.0000056510144,0.00005763237],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823827,0.00017054265,0.0007841972,0.00023882318,0.00043928408,0.00012887108],"domain_scores_gemma":[0.9983025,0.0004437161,0.0004998146,0.00010763972,0.0005562349,0.000090064015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019073366,0.0001036612,0.00024120967,0.0001796289,0.0002702257,0.000075908436,0.0006190492,0.00015590247,0.0000049647124],"category_scores_gemma":[0.0020473641,0.00007954547,0.00007193215,0.00032450844,0.00039175892,0.0005013705,0.00026640177,0.0007095526,5.9501787e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033232216,0.000036714868,0.00043650463,0.000013129378,0.000043296594,0.000005814372,0.0010269014,0.0008163426,0.00016084152,0.08872417,0.00044597517,0.90825707],"study_design_scores_gemma":[0.00063590746,0.00034680424,0.0047148266,0.00087210356,0.00008910456,0.0018684572,0.0008372425,0.16480546,0.0014121567,0.68164945,0.14241329,0.0003552039],"about_ca_topic_score_codex":0.000040849347,"about_ca_topic_score_gemma":0.00063396996,"teacher_disagreement_score":0.9079019,"about_ca_system_score_codex":0.0007297178,"about_ca_system_score_gemma":0.005708295,"threshold_uncertainty_score":0.9999284},"labels":[],"label_agreement":null},{"id":"W4417343483","doi":"10.64898/2025.12.14.25342223","title":"OMOP CDM for breast cancer research: transforming the Breast Cancer Now Biobank data","year":2025,"lang":"","type":"article","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Barts Health NHS Trust; McMaster University","keywords":"Biobank; Interoperability; Breast cancer; Translational research; General partnership; Process (computing); Data quality; Quality (philosophy)","score_opus":0.1260531515446123,"score_gpt":0.39929008307460323,"score_spread":0.27323693152999096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417343483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051645588,0.020265602,0.45907852,0.4221361,0.026607536,0.006205985,0.011948842,0.00045435884,0.001657464],"genre_scores_gemma":[0.9817055,0.008445631,0.000758566,0.0016747037,0.0025761449,0.0014366783,0.00001425743,0.000089656474,0.0032988929],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275094,0.0006083724,0.00093219354,0.0023308871,0.0014935641,0.0018840175],"domain_scores_gemma":[0.9929481,0.0009304393,0.0002615373,0.004347917,0.001230317,0.0002816805],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0054883254,0.00059095334,0.0005827337,0.00053812185,0.002337376,0.00094981375,0.008263285,0.00033216816,0.0004138069],"category_scores_gemma":[0.00009363703,0.00046438485,0.00024359708,0.0045129606,0.0009562722,0.0018494683,0.0018981752,0.0013559524,0.00005364552],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047035396,0.00015438409,0.02044778,0.00061613065,0.00037589518,0.000009787261,0.0014512896,0.000324257,0.0030085354,0.0020391378,0.036298525,0.9348039],"study_design_scores_gemma":[0.0036286784,0.00025512476,0.13439809,0.0037955893,0.0005740584,0.00030209933,0.0006938779,0.37261057,0.015539769,0.0044474364,0.46200794,0.0017467614],"about_ca_topic_score_codex":0.004595759,"about_ca_topic_score_gemma":0.01281852,"teacher_disagreement_score":0.9330572,"about_ca_system_score_codex":0.0011491092,"about_ca_system_score_gemma":0.0033167375,"threshold_uncertainty_score":0.9997808},"labels":[],"label_agreement":null},{"id":"W4417348244","doi":"10.1117/1.jmi.12.6.061401","title":"Introduction to the JMI Special Section on Computational Pathology","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Special section; Section (typography); Medical imaging; Computed tomography","score_opus":0.006878304536962735,"score_gpt":0.2903145322760559,"score_spread":0.28343622773909316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417348244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025850392,0.00003769788,0.6989479,0.28316653,0.014712277,0.00003812511,1.11496206e-7,0.000014453355,0.00049782987],"genre_scores_gemma":[0.7802842,0.00007622106,0.023823623,0.03512745,0.16021273,0.000011797719,0.0000011231596,0.000017403638,0.00044541206],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847513,0.00013868307,0.000307951,0.000151493,0.0008058148,0.00012094735],"domain_scores_gemma":[0.9992959,0.00015924871,0.00014446206,0.00014495623,0.00017998175,0.000075448406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014871088,0.00006221,0.000106321975,0.00024232155,0.0001329109,0.000087382316,0.0005409243,0.00004000988,0.00007228563],"category_scores_gemma":[0.00049812277,0.00004334866,0.000055928325,0.00044290238,0.00004682447,0.00022807246,0.00010657405,0.00050471193,0.000021519521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029199398,0.000033781685,0.00010391721,0.0000035835048,0.000012979279,0.0000431754,0.00026567874,0.007189257,0.000087205335,0.007289044,0.38186458,0.6030776],"study_design_scores_gemma":[0.00085432484,0.00016084746,0.008596378,0.00013959267,0.000017926208,0.0017969969,0.00015765449,0.23699212,0.00061422563,0.01431724,0.7362286,0.00012411785],"about_ca_topic_score_codex":0.0000034766738,"about_ca_topic_score_gemma":0.000004182162,"teacher_disagreement_score":0.77769923,"about_ca_system_score_codex":0.00019973393,"about_ca_system_score_gemma":0.00020564113,"threshold_uncertainty_score":0.21927503},"labels":[],"label_agreement":null},{"id":"W4417509627","doi":"10.1109/icsit65336.2025.11294287","title":"Multi-Scale Hematological Image Analysis for WBC Classification via GNNs","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Pattern recognition (psychology); Artificial neural network; Robustness (evolution); Deep learning; Confusion; Graph; Training set","score_opus":0.045859993003712074,"score_gpt":0.3303297002870644,"score_spread":0.2844697072833523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417509627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015854251,0.00021158518,0.986762,0.0057000527,0.0013503395,0.0008798299,0.000012921172,0.00030284253,0.0031950278],"genre_scores_gemma":[0.6248362,0.000044387616,0.36989015,0.00043482933,0.000057780686,0.00023128584,0.000008041445,0.000008583439,0.0044887154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966731,0.00016861867,0.0008563673,0.0014001277,0.0003326624,0.00056910055],"domain_scores_gemma":[0.9973135,0.00036992537,0.00030671616,0.0013389672,0.00053377723,0.00013712213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064846507,0.0003377234,0.00062192284,0.00065946684,0.00053516834,0.00046517237,0.0011423874,0.00034821394,0.0002534918],"category_scores_gemma":[0.00012118163,0.0003183597,0.0006416758,0.004320666,0.00026420166,0.00051314704,0.000382149,0.00025453448,0.00010669027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053465925,0.002981345,0.054055095,0.00113628,0.0060751834,0.000015122531,0.0026289744,0.0038355342,0.17168862,0.0824048,0.019792277,0.6548521],"study_design_scores_gemma":[0.0006393613,0.00010676354,0.033729758,0.000018682576,0.00062062615,0.000003295042,0.0001380644,0.94173867,0.018652068,0.0020179506,0.0020220876,0.000312655],"about_ca_topic_score_codex":0.00010778356,"about_ca_topic_score_gemma":0.00045584427,"teacher_disagreement_score":0.93790317,"about_ca_system_score_codex":0.0004086265,"about_ca_system_score_gemma":0.0001858746,"threshold_uncertainty_score":0.99992687},"labels":[],"label_agreement":null},{"id":"W4417509867","doi":"10.1109/aibthings66987.2025.11296160","title":"Interpretable Deep Transfer Learning Framework for Breast Cancer Histopathology Classification","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Deep learning; Breast cancer; Transfer of learning; Clinical Practice; Magnification; Relevance (law); Focus (optics)","score_opus":0.01830488432617562,"score_gpt":0.29950244473182197,"score_spread":0.28119756040564636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417509867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011808423,0.0017752597,0.9713828,0.011925489,0.0077633564,0.00077765225,0.000015890357,0.0002879853,0.0048907436],"genre_scores_gemma":[0.9453009,0.000588153,0.042353794,0.001607133,0.00032566508,0.0006488202,0.0000022531042,0.000031422005,0.009141901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969479,0.00022728302,0.0006673471,0.0012354918,0.00023320364,0.00068877207],"domain_scores_gemma":[0.9981449,0.00043586036,0.00013090725,0.00074400706,0.0004367327,0.00010755154],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058389624,0.0003569398,0.00045299053,0.00033378205,0.0006116922,0.00028992273,0.0009586418,0.00054318085,0.00091808365],"category_scores_gemma":[0.00010455197,0.00038610116,0.00023854799,0.0010986578,0.00020473082,0.00066735054,0.00015979844,0.0008529735,0.000030995165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020747824,0.00007736677,0.0015540754,0.00017088106,0.00005353777,0.0000010969618,0.0016461876,0.0033542712,0.0025047294,0.20137225,0.00048506696,0.788573],"study_design_scores_gemma":[0.0006173945,0.00023138733,0.013659807,0.00046396896,0.00015126712,0.000027262193,0.00029710654,0.9311582,0.0021118715,0.026019225,0.024771273,0.0004912573],"about_ca_topic_score_codex":0.00017134543,"about_ca_topic_score_gemma":0.00020445918,"teacher_disagreement_score":0.94412,"about_ca_system_score_codex":0.0011906073,"about_ca_system_score_gemma":0.0005390276,"threshold_uncertainty_score":0.99999523},"labels":[],"label_agreement":null},{"id":"W53864427","doi":"","title":"A robust automatic nuclei segmentation technique for quantitative histopathological image analysis.","year":2012,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Image segmentation; Pattern recognition (psychology); Computer vision","score_opus":0.06248067866189234,"score_gpt":0.2812895216788442,"score_spread":0.21880884301695186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W53864427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007610015,0.00006621464,0.9896727,0.00029834823,0.00029310642,0.0012646867,0.0000041925164,0.00028794468,0.00050276594],"genre_scores_gemma":[0.5135692,0.0000019850631,0.47958273,0.000102596074,0.000042823853,0.006632692,0.0000035765695,0.000006487216,0.000057974252],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988907,0.00010134294,0.00021003606,0.00026336688,0.00017223618,0.0003622927],"domain_scores_gemma":[0.99926484,0.00013363364,0.00015159353,0.00028714372,0.000069659865,0.0000931138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009645639,0.000103667175,0.00017152965,0.000216083,0.00010431764,0.00007036514,0.0002969613,0.0000613051,0.000008681216],"category_scores_gemma":[0.00013402078,0.00009392297,0.0001179749,0.00075315713,0.00004612443,0.0008336935,0.000074572206,0.00007451542,0.000010718037],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012217376,0.0011861299,0.020141756,0.00034291646,0.00090395403,0.000017888753,0.0075354893,0.0017877142,0.041363873,0.07762269,0.008553971,0.84042144],"study_design_scores_gemma":[0.0007623042,0.00019862677,0.81113404,0.000008225061,0.00048471757,0.00003873898,0.00017717954,0.12772296,0.052313965,0.005218388,0.0012527369,0.0006880989],"about_ca_topic_score_codex":0.0000083276345,"about_ca_topic_score_gemma":0.0000042267857,"teacher_disagreement_score":0.83973336,"about_ca_system_score_codex":0.0003095551,"about_ca_system_score_gemma":0.000011922261,"threshold_uncertainty_score":0.38300675},"labels":[],"label_agreement":null},{"id":"W54396154","doi":"10.1096/fasebj.22.1_supplement.385.7","title":"A new paradigm for teaching histology in Canada's first distributed medical school","year":2008,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Curriculum; Interactivity; The Internet; Internet access; Computer science; Virtual microscopy; Videoconferencing; Quality (philosophy); Medical education; Multimedia; Medicine; World Wide Web; Psychology; Pathology; Pedagogy","score_opus":0.01526968298157963,"score_gpt":0.23491105527178163,"score_spread":0.219641372290202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W54396154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060222406,0.00027086269,0.9077531,0.030385295,0.0011426798,0.00010603864,0.000003549825,0.000023044477,0.000093003524],"genre_scores_gemma":[0.9938595,0.00004376581,0.0047279806,0.00085975585,0.00041789017,0.000007973373,0.0000010356507,0.0000063088573,0.000075756034],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877226,0.0001144373,0.00026446974,0.00014858703,0.000387738,0.00031252403],"domain_scores_gemma":[0.9990063,0.00026746103,0.0001244828,0.00023618477,0.000020856256,0.00034473967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056068844,0.000088253415,0.00013958373,0.00005523782,0.00051086175,0.000031995725,0.00095479394,0.00004793154,0.000069016765],"category_scores_gemma":[0.00044309068,0.000064283704,0.000046528276,0.00014145918,0.000042190783,0.00017239805,0.00007679298,0.0007029416,0.0000043001887],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028242715,0.0001043137,0.041657798,0.000027456284,0.00014763509,0.0021095606,0.00365372,0.008553706,0.00045206284,0.011323932,0.7848368,0.14685056],"study_design_scores_gemma":[0.008820931,0.00070353603,0.08542094,0.00034169893,0.00004845804,0.052437343,0.00038586793,0.44850716,0.0032561084,0.029782245,0.36910388,0.0011918558],"about_ca_topic_score_codex":0.28684345,"about_ca_topic_score_gemma":0.6385799,"teacher_disagreement_score":0.93363714,"about_ca_system_score_codex":0.0016255387,"about_ca_system_score_gemma":0.005908859,"threshold_uncertainty_score":0.9997267},"labels":[],"label_agreement":null},{"id":"W6887395092","doi":"10.15562/tcp.76","title":"Machine learning application in cancer research: Mini Review","year":2019,"lang":"en","type":"article","venue":"The Cancer Press","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cancer; Feature (linguistics); Process (computing); Field (mathematics); Training set","score_opus":0.09652963668837547,"score_gpt":0.3908739109914948,"score_spread":0.2943442743031194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887395092","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026675148,0.8523015,0.04613153,0.04777866,0.002833671,0.005761531,0.000019679494,0.00055542565,0.017942855],"genre_scores_gemma":[0.84187615,0.14789551,0.00050842157,0.0018864168,0.0003863945,0.0032052577,0.0000029966573,0.000039332248,0.00419949],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826705,0.00036298213,0.00020003693,0.00042990377,0.00043114528,0.00030885593],"domain_scores_gemma":[0.99875015,0.00016025886,0.00010751768,0.0008231851,0.00011967904,0.00003919955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001525414,0.00009979081,0.00015951096,0.00006014274,0.000105524836,0.000054739387,0.0013225599,0.00004250355,0.00008434362],"category_scores_gemma":[0.000034174052,0.00007411715,0.000032326843,0.0006703385,0.000049270933,0.00026910016,0.00036899606,0.0005487562,0.000070532435],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050175993,0.000050252358,0.009027005,0.0013913682,0.000042798685,0.0000022551744,0.0021097981,0.012486091,0.003765277,0.005944696,0.009648007,0.9554823],"study_design_scores_gemma":[0.00049908395,0.00008379462,0.0035188398,0.0017965973,0.000015620923,0.0000050698104,0.000020464568,0.1591652,0.0062567443,0.0016819763,0.8266449,0.00031171856],"about_ca_topic_score_codex":0.008793292,"about_ca_topic_score_gemma":0.0010006097,"teacher_disagreement_score":0.9551706,"about_ca_system_score_codex":0.0003420864,"about_ca_system_score_gemma":0.000111699526,"threshold_uncertainty_score":0.99780726},"labels":[],"label_agreement":null},{"id":"W6887833115","doi":"10.17632/bk45c9yxb9.1","title":"CRICVA Database","year":2019,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pixel; Eye tracking; Image processing; Fixation (population genetics); Tracking (education); Notice","score_opus":0.0283349011813571,"score_gpt":0.27274200238257384,"score_spread":0.24440710120121675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887833115","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000111356676,0.0010054142,0.040286,0.00010611664,0.0023167059,0.00030007836,0.9555489,0.00017231959,0.00015313797],"genre_scores_gemma":[0.00015209404,0.002874121,0.0053096428,0.0007227932,0.0010165442,0.00002023848,0.98977864,0.000034006694,0.00009190197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996231,0.00027176974,0.00045326076,0.0018341162,0.0005512799,0.00065858103],"domain_scores_gemma":[0.9918883,0.000431081,0.00037469857,0.0070528067,0.000034266755,0.00021884032],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00075800164,0.0005412166,0.00051439734,0.00022193708,0.00034533304,0.00060579245,0.008848096,0.00019623895,0.000024466459],"category_scores_gemma":[0.000013954815,0.000499807,0.000054960445,0.0004750833,0.00008610724,0.001461388,0.00900429,0.0008471805,0.00023876768],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001799965,0.00003076642,0.00005277551,0.0007838999,0.00006770317,0.000030511294,0.00017554981,0.00018446184,0.000014980722,0.00001616245,0.9885574,0.010067785],"study_design_scores_gemma":[0.00018961841,0.00005462604,0.0002701343,0.0005691345,0.0000728717,0.000055781624,0.000030927396,0.18339191,0.000003853354,0.00010844263,0.8147544,0.0004982593],"about_ca_topic_score_codex":0.0023247066,"about_ca_topic_score_gemma":0.0028083303,"teacher_disagreement_score":0.18320745,"about_ca_system_score_codex":0.00005253227,"about_ca_system_score_gemma":0.00011476123,"threshold_uncertainty_score":0.99974537},"labels":[],"label_agreement":null},{"id":"W6889352121","doi":"10.25446/oxford.25806148.v1","title":"55708: Canadian Memorial","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.025089190676388717,"score_gpt":0.24542186011506867,"score_spread":0.22033266943867996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889352121","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4514595e-9,0.001260985,0.00003942535,0.00018750574,0.00391362,0.00015446241,0.12746084,0.00066803,0.8663151],"genre_scores_gemma":[0.000015796404,0.0000037684122,0.00066882797,0.00032781367,0.00462448,0.00016275173,0.011866976,0.00035091906,0.98197865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990392,0.000013686651,0.000079524296,0.00042767375,0.00019172308,0.00024819677],"domain_scores_gemma":[0.9991982,0.00001033095,0.000051247636,0.0005592174,0.00002123106,0.00015977472],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000018109213,0.00016465309,0.00012100078,0.00031665724,0.000024665283,0.00021336474,0.00082712,0.00027808224,0.4467361],"category_scores_gemma":[0.00006261926,0.00016918642,0.000063664666,0.00028555037,0.0000023109926,0.00006515816,0.00016444788,0.00024212652,0.11150062],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.4761454e-8,6.228867e-7,2.5171813e-8,0.000092979186,0.000012405332,0.000047170553,0.000020324796,4.0953395e-7,1.13345244e-7,0.00007566635,0.9942095,0.0055406806],"study_design_scores_gemma":[0.00003164931,0.000010535583,0.0000010982562,0.0014742007,0.0000031221136,0.0000093592125,6.9083785e-7,0.00023183576,0.0000144949945,0.00022054237,0.9978104,0.00019204969],"about_ca_topic_score_codex":0.019933535,"about_ca_topic_score_gemma":0.15942046,"teacher_disagreement_score":0.33523548,"about_ca_system_score_codex":0.00025452542,"about_ca_system_score_gemma":0.000537138,"threshold_uncertainty_score":0.9865928},"labels":[],"label_agreement":null},{"id":"W6889934769","doi":"10.3389/fpsyg.2020.02230.s002","title":"Data_Sheet_10_International Comparative Study on PISA Mathematics Achievement Test Based on Cognitive Diagnostic Models.CSV","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Cognition; Process (computing); Achievement test; Item response theory; Metacognition; Cognitive development; Cognitive skill","score_opus":0.13857252019597088,"score_gpt":0.33658069145015057,"score_spread":0.1980081712541797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889934769","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001899369,0.000010465674,0.0029683176,0.00013228288,0.00029228622,0.0016555208,0.99434525,0.00014462991,0.00044936157],"genre_scores_gemma":[0.0030980655,0.0000020087775,0.0003957197,0.0014007982,0.0002892582,0.0016177489,0.9931472,0.000027898775,0.0000213248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99664766,0.00013081133,0.00046723185,0.0010818882,0.0013731678,0.000299235],"domain_scores_gemma":[0.9928611,0.0051819095,0.0005009722,0.0010172001,0.0002839625,0.00015483589],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0000919235,0.0005527454,0.00048424743,0.00024504712,0.00016832384,0.00037030687,0.0020687908,0.00015770626,0.009614785],"category_scores_gemma":[0.002390606,0.0005335631,0.000108257285,0.00038602576,0.000013773492,0.00033986737,0.00071399735,0.0008167108,0.01035342],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019359917,0.0015429505,0.0000011236775,0.0001744757,0.000078479396,0.00009156534,0.00021914575,0.0025162513,1.4887003e-7,0.000012412768,0.9951964,0.00014768606],"study_design_scores_gemma":[0.0018786025,0.005609708,0.0002650152,0.0110159805,0.000114058355,0.0000064245396,0.00024779528,0.4249679,0.0001487383,0.00023653389,0.5542194,0.0012898004],"about_ca_topic_score_codex":0.000018156878,"about_ca_topic_score_gemma":0.00007087002,"teacher_disagreement_score":0.44097698,"about_ca_system_score_codex":0.00038047877,"about_ca_system_score_gemma":0.00025921862,"threshold_uncertainty_score":0.9997116},"labels":[],"label_agreement":null},{"id":"W6892197726","doi":"10.5061/dryad.167d5","title":"Data from: Sex-specific graphs: Relating group-specific topology to demographic and landscape data","year":2017,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Trent University","funders":"","keywords":"Metapopulation; Biological dispersal; Network topology; Population; Topology (electrical circuits); Graph; Limiting; Partition (number theory); Vertebrate","score_opus":0.05079847545593012,"score_gpt":0.29030230142732383,"score_spread":0.2395038259713937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892197726","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016114806,0.00951119,0.0242808,0.00027478125,0.0022251627,0.0004682136,0.9613043,0.00022498259,0.000099063596],"genre_scores_gemma":[0.0011383718,0.022065265,0.015147054,0.00031976923,0.0015910743,0.000021230713,0.95963824,0.000059053975,0.000019946492],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924639,0.0005392309,0.0008069611,0.0046399194,0.00060568395,0.0009442955],"domain_scores_gemma":[0.9739948,0.0010707293,0.0007174027,0.02375599,0.000035684105,0.00042538065],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019992392,0.0008094367,0.0009183173,0.000473312,0.0014492787,0.0017355449,0.02738193,0.0004110941,0.00002784956],"category_scores_gemma":[0.000037499714,0.00078305486,0.00004326173,0.00056615734,0.0003207265,0.0028941466,0.040457714,0.0013353757,0.00005367345],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054124546,0.00003901365,0.0022466704,0.00020028386,0.00017641408,0.00006557185,0.0003396649,0.000020346302,0.000020483494,0.000036491703,0.9446043,0.052196685],"study_design_scores_gemma":[0.00038977148,0.00008899527,0.0057929247,0.0006844162,0.00010525501,0.00008317667,0.00012385072,0.09831934,4.2879915e-7,0.00088867825,0.89271694,0.00080624555],"about_ca_topic_score_codex":0.0030697288,"about_ca_topic_score_gemma":0.025772357,"teacher_disagreement_score":0.098299,"about_ca_system_score_codex":0.000024829566,"about_ca_system_score_gemma":0.000057609166,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W6901570721","doi":"10.60692/dg8nr-ant75","title":"Bias Reduction in Representation of Histopathology Images Using Deep Feature Selection","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University; Brock University; Ontario Tech University","funders":"","keywords":"Pattern recognition (psychology); Feature extraction; Feature selection; Representation (politics); Feature (linguistics); Artificial neural network; Deep neural networks; Set (abstract data type)","score_opus":0.048678255503543856,"score_gpt":0.24684769522973418,"score_spread":0.19816943972619033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901570721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4782083,0.0000058545397,0.5198648,0.00005831022,0.0011097575,0.00026348018,0.0000068268805,0.00014327212,0.0003394128],"genre_scores_gemma":[0.99175847,1.2576264e-7,0.008033959,0.000021121108,0.000046603065,0.000078870304,0.0000061633145,0.0000057070233,0.000048989627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852216,0.00027974756,0.00049202266,0.00020052363,0.00034799165,0.00015755517],"domain_scores_gemma":[0.9989444,0.000006388929,0.0005764397,0.00030206257,0.00014634941,0.000024331976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516867,0.000104864506,0.00017495836,0.00071536284,0.00019359187,0.00006068481,0.0002383511,0.000064722226,0.000008092234],"category_scores_gemma":[0.000017331186,0.00011399759,0.000051341198,0.0012661279,0.000019965386,0.0014905507,0.00013406067,0.00017528638,0.000009835892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036052373,0.000021448985,0.29049882,0.000669483,0.00004265192,0.000015278622,0.33861876,0.34440035,0.0039231936,0.0020262077,0.0004901329,0.018933147],"study_design_scores_gemma":[0.0019297281,0.00033658987,0.13901284,0.00009322678,0.000032806634,0.002470573,0.027959432,0.7891563,0.038100187,0.000057091536,0.00032727892,0.0005239548],"about_ca_topic_score_codex":0.00006388965,"about_ca_topic_score_gemma":6.3492547e-7,"teacher_disagreement_score":0.51355016,"about_ca_system_score_codex":0.0009231911,"about_ca_system_score_gemma":0.00005769098,"threshold_uncertainty_score":0.46486866},"labels":[],"label_agreement":null},{"id":"W6901625362","doi":"10.60692/9cch1-cwe76","title":"A deep learning approach for the detection and counting of colon cancer cells (HT-29 cells) bunches and impurities","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Colorectal cancer; Cancer; Colon adenocarcinoma; Cancer cell; Pattern recognition (psychology)","score_opus":0.02625694109635405,"score_gpt":0.20914072420875215,"score_spread":0.1828837831123981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901625362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22456598,0.000043289143,0.7741617,0.00001740461,0.0004244839,0.0004696121,0.000008695248,0.0002034834,0.00010532371],"genre_scores_gemma":[0.99817115,0.0000073571337,0.001428648,0.000019080151,0.0000657572,0.00025756785,0.0000012237541,0.0000069964594,0.000042239342],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990985,0.000045430726,0.00032528435,0.00015048153,0.00020234125,0.00017797586],"domain_scores_gemma":[0.99929464,0.000057427944,0.00031288448,0.00016418388,0.00014202845,0.000028808769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063402037,0.000112268026,0.00014835561,0.00016849913,0.00034814395,0.0002569756,0.00015273406,0.00007359491,4.37389e-7],"category_scores_gemma":[0.0000097505845,0.00008589041,0.000032825563,0.0003221652,0.000045681627,0.00073076366,0.000107397485,0.00008884661,0.000004778323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002315397,0.0000045063393,0.023155496,0.009413426,0.00027949546,9.338616e-7,0.64421546,0.12885216,0.0034054557,0.0005915259,0.00012727239,0.18972275],"study_design_scores_gemma":[0.00037598755,0.000059298396,0.0032813884,0.000055103326,0.00001941479,0.000009643873,0.014607205,0.96449804,0.016731704,0.0000028123552,0.000249472,0.00010994989],"about_ca_topic_score_codex":0.00005800174,"about_ca_topic_score_gemma":0.0000022400247,"teacher_disagreement_score":0.83564585,"about_ca_system_score_codex":0.000075831296,"about_ca_system_score_gemma":0.000019022295,"threshold_uncertainty_score":0.35025093},"labels":[],"label_agreement":null},{"id":"W6901658333","doi":"10.60692/4k7hr-88809","title":"Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Spinal Cord Injury BC","funders":"","keywords":"Social media; Classifier (UML); Deep learning; Disease; Digital pathology; MEDLINE","score_opus":0.03851976129112783,"score_gpt":0.25261889087430994,"score_spread":0.2140991295831821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901658333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12321941,0.000003094394,0.8726066,0.0007760858,0.00070453796,0.0007567274,0.00005576065,0.0008857207,0.0009920861],"genre_scores_gemma":[0.99584347,3.805774e-7,0.0030928964,0.00048637204,0.00028723056,0.00018864563,0.000031021173,0.000017564109,0.000052414136],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805367,0.00019561754,0.0005495428,0.000354033,0.00043704332,0.000410092],"domain_scores_gemma":[0.9989314,0.000070221446,0.00027204276,0.0002989576,0.0002336135,0.00019377665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046264534,0.00021850655,0.00029414575,0.00019263942,0.00033305134,0.00030870247,0.0005250858,0.00013020184,0.000018353945],"category_scores_gemma":[0.00012009791,0.00020795943,0.00010212379,0.00031443906,0.000037629638,0.001131616,0.00019511032,0.00021952906,0.001307909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012945959,0.000012856542,0.005348023,0.0012313804,0.00011218831,0.00004620104,0.8057097,0.010556261,0.00030589657,0.0014143556,0.0019716285,0.17199692],"study_design_scores_gemma":[0.001800948,0.0003365454,0.01372099,0.000097358716,0.0000275132,0.00002003509,0.0048527257,0.9746932,0.0023114157,0.000007556828,0.0016504296,0.0004812808],"about_ca_topic_score_codex":0.0000056930658,"about_ca_topic_score_gemma":1.8524594e-7,"teacher_disagreement_score":0.96413696,"about_ca_system_score_codex":0.00023658514,"about_ca_system_score_gemma":0.000077988145,"threshold_uncertainty_score":0.9994697},"labels":[],"label_agreement":null},{"id":"W6901676203","doi":"10.60692/29pyd-jx366","title":"Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Waterloo; McMaster University","funders":"","keywords":"Digital pathology; Deep learning; Demographics; Scope (computer science); Pattern recognition (psychology); Profiling (computer programming); Precision medicine","score_opus":0.030431446735364576,"score_gpt":0.22331909903376687,"score_spread":0.1928876522984023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901676203","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023377234,0.000025388661,0.9740417,0.00024861595,0.0010105874,0.0002941814,0.000152437,0.00027559712,0.0005742748],"genre_scores_gemma":[0.9972161,8.8213056e-7,0.0018917088,0.0005072112,0.00017359265,0.000037420952,0.00013739301,0.000008038861,0.000027650378],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980869,0.0002049183,0.00069365365,0.0002702585,0.0005007672,0.00024349357],"domain_scores_gemma":[0.99720126,0.000040522515,0.0004881697,0.0017721212,0.00043340275,0.00006449756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072369055,0.00016743546,0.00021338172,0.00015230245,0.00020421993,0.00043387318,0.00080607424,0.00010887589,0.000017922865],"category_scores_gemma":[0.000031603096,0.00012655286,0.00007256734,0.0007500706,0.000046779674,0.002752736,0.0004324119,0.00014767115,0.0001376109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054484076,0.000056208188,0.27051318,0.0037006966,0.0009690793,0.00010381883,0.23780786,0.38009068,0.00034989492,0.0029121134,0.02190787,0.08104379],"study_design_scores_gemma":[0.0007245972,0.000044558823,0.037194602,0.00018172241,0.00003464778,0.000074578886,0.0016236239,0.95560557,0.0039234445,0.0000038321523,0.00040383622,0.00018497996],"about_ca_topic_score_codex":0.000015584967,"about_ca_topic_score_gemma":0.0000010560826,"teacher_disagreement_score":0.97383887,"about_ca_system_score_codex":0.00011337542,"about_ca_system_score_gemma":0.0000943591,"threshold_uncertainty_score":0.51606756},"labels":[],"label_agreement":null},{"id":"W6901682040","doi":"10.60692/zfnz7-z3v11","title":"Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"","keywords":"Grading (engineering); Prostate cancer; Prostate; Prostate biopsy; Applications of artificial intelligence; Classifier (UML)","score_opus":0.03433825213271046,"score_gpt":0.2265304661374261,"score_spread":0.19219221400471564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901682040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22104488,0.00002592532,0.77705,0.00009134061,0.0007515522,0.00022751566,0.00006456388,0.0002492254,0.0004949888],"genre_scores_gemma":[0.9938347,0.000001106043,0.0059604095,0.000047901653,0.00003477768,0.000053280088,0.000008519995,0.000006920595,0.000052382755],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812347,0.00010178909,0.0008234344,0.00028440624,0.0003985401,0.00026834582],"domain_scores_gemma":[0.9984259,0.000019261204,0.00059850706,0.0005553591,0.0003349604,0.00006602681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439819,0.00017748815,0.00024675703,0.00014880052,0.00013952299,0.0003381603,0.0004057852,0.000097875614,0.000003718286],"category_scores_gemma":[0.000048857648,0.00016317458,0.00007475795,0.00058150943,0.00007111326,0.0014541397,0.00012915887,0.00011388209,0.000094357194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041729995,0.000060206985,0.0508825,0.0055540795,0.0002817224,0.0001131036,0.38701317,0.002559005,0.024639191,0.03171793,0.0013659832,0.4953958],"study_design_scores_gemma":[0.00014622632,0.00014181987,0.005249335,0.00029790797,0.000016332888,0.000095156945,0.013821366,0.053435262,0.9259171,0.00013355516,0.00030989794,0.0004360666],"about_ca_topic_score_codex":0.000009247953,"about_ca_topic_score_gemma":5.6590807e-7,"teacher_disagreement_score":0.9012779,"about_ca_system_score_codex":0.00016819853,"about_ca_system_score_gemma":0.00009090781,"threshold_uncertainty_score":0.66540664},"labels":[],"label_agreement":null},{"id":"W6901702367","doi":"10.60692/9faf1-58474","title":"Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Spinal Cord Injury BC","funders":"","keywords":"Social media; Classifier (UML); Deep learning; Disease; Digital pathology; MEDLINE","score_opus":0.03851976129112783,"score_gpt":0.25261889087430994,"score_spread":0.2140991295831821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901702367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12321941,0.000003094394,0.8726066,0.0007760858,0.00070453796,0.0007567274,0.00005576065,0.0008857207,0.0009920861],"genre_scores_gemma":[0.99584347,3.805774e-7,0.0030928964,0.00048637204,0.00028723056,0.00018864563,0.000031021173,0.000017564109,0.000052414136],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805367,0.00019561754,0.0005495428,0.000354033,0.00043704332,0.000410092],"domain_scores_gemma":[0.9989314,0.000070221446,0.00027204276,0.0002989576,0.0002336135,0.00019377665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046264534,0.00021850655,0.00029414575,0.00019263942,0.00033305134,0.00030870247,0.0005250858,0.00013020184,0.000018353945],"category_scores_gemma":[0.00012009791,0.00020795943,0.00010212379,0.00031443906,0.000037629638,0.001131616,0.00019511032,0.00021952906,0.001307909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012945959,0.000012856542,0.005348023,0.0012313804,0.00011218831,0.00004620104,0.8057097,0.010556261,0.00030589657,0.0014143556,0.0019716285,0.17199692],"study_design_scores_gemma":[0.001800948,0.0003365454,0.01372099,0.000097358716,0.0000275132,0.00002003509,0.0048527257,0.9746932,0.0023114157,0.000007556828,0.0016504296,0.0004812808],"about_ca_topic_score_codex":0.0000056930658,"about_ca_topic_score_gemma":1.8524594e-7,"teacher_disagreement_score":0.96413696,"about_ca_system_score_codex":0.00023658514,"about_ca_system_score_gemma":0.000077988145,"threshold_uncertainty_score":0.9994697},"labels":[],"label_agreement":null},{"id":"W6901740934","doi":"10.60692/nzsw9-kgh76","title":"Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"","keywords":"Grading (engineering); Prostate cancer; Prostate; Prostate biopsy; Applications of artificial intelligence; Classifier (UML)","score_opus":0.03433825213271046,"score_gpt":0.2265304661374261,"score_spread":0.19219221400471564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901740934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22104488,0.00002592532,0.77705,0.00009134061,0.0007515522,0.00022751566,0.00006456388,0.0002492254,0.0004949888],"genre_scores_gemma":[0.9938347,0.000001106043,0.0059604095,0.000047901653,0.00003477768,0.000053280088,0.000008519995,0.000006920595,0.000052382755],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812347,0.00010178909,0.0008234344,0.00028440624,0.0003985401,0.00026834582],"domain_scores_gemma":[0.9984259,0.000019261204,0.00059850706,0.0005553591,0.0003349604,0.00006602681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439819,0.00017748815,0.00024675703,0.00014880052,0.00013952299,0.0003381603,0.0004057852,0.000097875614,0.000003718286],"category_scores_gemma":[0.000048857648,0.00016317458,0.00007475795,0.00058150943,0.00007111326,0.0014541397,0.00012915887,0.00011388209,0.000094357194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041729995,0.000060206985,0.0508825,0.0055540795,0.0002817224,0.0001131036,0.38701317,0.002559005,0.024639191,0.03171793,0.0013659832,0.4953958],"study_design_scores_gemma":[0.00014622632,0.00014181987,0.005249335,0.00029790797,0.000016332888,0.000095156945,0.013821366,0.053435262,0.9259171,0.00013355516,0.00030989794,0.0004360666],"about_ca_topic_score_codex":0.000009247953,"about_ca_topic_score_gemma":5.6590807e-7,"teacher_disagreement_score":0.9012779,"about_ca_system_score_codex":0.00016819853,"about_ca_system_score_gemma":0.00009090781,"threshold_uncertainty_score":0.66540664},"labels":[],"label_agreement":null},{"id":"W6901829842","doi":"10.60692/7382v-tz037","title":"Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Robustness (evolution); Breast cancer; Segmentation; Breast ultrasound; Pattern recognition (psychology); Speckle pattern; Hyperparameter; Image segmentation; Image quality","score_opus":0.034999216613801974,"score_gpt":0.23471830584544073,"score_spread":0.19971908923163875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901829842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47144777,4.7389682e-7,0.52647364,0.00004104313,0.00013539907,0.00029686856,0.00005606146,0.0013810024,0.00016770752],"genre_scores_gemma":[0.9826334,1.403957e-7,0.017111093,0.00005083559,0.00003304554,0.000073711846,0.000051871608,0.000013910954,0.00003195105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985158,0.00006172622,0.0004821838,0.00026980852,0.00041064675,0.0002598466],"domain_scores_gemma":[0.99884504,0.00001371481,0.00041570893,0.0004116962,0.00022896477,0.000084844876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034892937,0.00019679677,0.0001719501,0.00039249676,0.0002617367,0.0006088673,0.00022130027,0.000046720383,0.0000019801123],"category_scores_gemma":[0.0000077284985,0.00017068212,0.000027899634,0.0007478093,0.0000422275,0.003110452,0.00006918981,0.000080437436,0.00022685554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009483257,0.000035956462,0.15204185,0.0056510125,0.0006254899,0.00009862701,0.3239796,0.46588704,0.025426164,0.004046553,0.0046473313,0.016612072],"study_design_scores_gemma":[0.00067550543,0.000029849265,0.023361754,0.00009374649,0.000016600521,0.0004927612,0.0017554081,0.97046566,0.0028937433,0.000005872036,0.000005068677,0.00020401162],"about_ca_topic_score_codex":0.000013166618,"about_ca_topic_score_gemma":4.5225042e-7,"teacher_disagreement_score":0.51118565,"about_ca_system_score_codex":0.00028954438,"about_ca_system_score_gemma":0.00008574759,"threshold_uncertainty_score":0.6960215},"labels":[],"label_agreement":null},{"id":"W6902175400","doi":"10.6084/m9.figshare.26589999","title":"Additional file 1 of Biased data, biased AI: deep networks predict the acquisition site of TCGA images","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Ontario Tech University; Brock University; William Osler Health System; Laurentian University; McMaster University; University Health Network","funders":"","keywords":"Table (database); Deep learning; Source code; Deep neural networks; File format","score_opus":0.031811152055972944,"score_gpt":0.2887079528766788,"score_spread":0.2568968008207058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902175400","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006174092,0.00033450744,0.48393753,0.0009600228,0.000787595,0.0007539177,0.50666976,0.000027671393,0.0059115803],"genre_scores_gemma":[0.5642406,0.00005922096,0.2386588,0.00086355634,0.0019324452,0.0007465142,0.18937092,0.00008627421,0.0040416955],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988333,0.000090424655,0.0002534538,0.00039700588,0.00028656705,0.00013925317],"domain_scores_gemma":[0.9976108,0.0012778391,0.00012959153,0.0008565733,0.00008987795,0.0000353217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031227653,0.000096188545,0.00012868886,0.00007114393,0.00007897047,0.00025373063,0.0013768262,0.00005618611,0.30241445],"category_scores_gemma":[0.000094894065,0.00007507644,0.000046525143,0.0005289614,0.00010408006,0.0010591241,0.0007243707,0.00013905094,0.0001820712],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012731927,0.000020613074,0.000003875659,0.00000864197,0.000025989366,0.0000051098846,0.00009487508,0.0016108273,0.00017153712,0.000009134747,0.8597765,0.13826014],"study_design_scores_gemma":[0.00012703285,0.00010077916,0.00120457,0.00031059858,0.000019584571,0.000011536277,0.000021712432,0.7200186,0.0021753882,0.0001366653,0.2757747,0.00009884827],"about_ca_topic_score_codex":0.000040112078,"about_ca_topic_score_gemma":0.00003976725,"teacher_disagreement_score":0.7184078,"about_ca_system_score_codex":0.00003543274,"about_ca_system_score_gemma":0.00017861981,"threshold_uncertainty_score":0.69822323},"labels":[],"label_agreement":null},{"id":"W6905828715","doi":"10.15468/dl.mank2g","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Arctic; The arctic","score_opus":0.011640177569269399,"score_gpt":0.22126077720356976,"score_spread":0.20962059963430035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6905828715","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008167373,0.000024202945,0.0031799425,0.00034275898,0.0020658816,0.0002845257,0.9935965,0.0002438858,0.00025415758],"genre_scores_gemma":[0.0000031446566,0.00006947963,0.000026632786,0.0008553282,0.0000016094031,0.0000061627206,0.9990374,3.660014e-9,2.5550153e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983193,0.00007330656,0.00038781075,0.00035392056,0.0005652178,0.00030043427],"domain_scores_gemma":[0.99808216,0.000028210887,0.00031350114,0.001131926,0.00032513367,0.000119077726],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002659426,0.00028045263,0.00025348237,0.00015846177,0.00032630644,0.00036015233,0.0018318297,0.00036919158,0.00020847595],"category_scores_gemma":[0.00012016688,0.00030732824,0.00014718845,0.000812539,0.00010383667,0.0022997786,0.001131248,0.00034598843,0.029425897],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011989989,0.000015887195,0.00008385149,0.00013628781,0.000020627527,0.0000011957651,0.000023175951,0.000018025783,1.2461972e-8,9.2624964e-7,0.9899657,0.009722325],"study_design_scores_gemma":[0.00021824588,0.00003170942,0.000023377901,0.000004561395,0.00002115157,0.000003977982,0.000016164406,0.0000037989553,0.000007259044,0.000004894312,0.9993989,0.00026596637],"about_ca_topic_score_codex":0.00047300165,"about_ca_topic_score_gemma":0.000014888082,"teacher_disagreement_score":0.02921742,"about_ca_system_score_codex":0.0007845331,"about_ca_system_score_gemma":0.00041186795,"threshold_uncertainty_score":0.9999379},"labels":[],"label_agreement":null},{"id":"W6907980578","doi":"10.25549/examiner-c44-28170","title":"Canadian cruiser, HMCS Ontario, arrives at Terminal Island, 1951","year":2021,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cruise; Stern; Terminal (telecommunication); Port (circuit theory); Section (typography)","score_opus":0.005275700201398701,"score_gpt":0.14901060665520452,"score_spread":0.14373490645380582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907980578","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008746254,0.00010283273,0.0003294925,0.0002711387,0.0002051138,0.00012876505,0.9957016,0.000079181526,0.002307265],"genre_scores_gemma":[0.00027262792,0.000044420583,0.0005652675,0.00020738135,0.00011906235,4.1169835e-7,0.9885012,0.000025692421,0.010263922],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983215,0.00004270889,0.00021651613,0.0006333808,0.00037735127,0.0004085654],"domain_scores_gemma":[0.9983758,0.0000499652,0.00024721932,0.0008668937,0.000048855072,0.00041128302],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00003702505,0.0003272272,0.00037497925,0.00033014826,0.00026511698,0.0003051776,0.0016969544,0.00033777187,0.0044395416],"category_scores_gemma":[0.000008987224,0.00038132258,0.0002443908,0.00029795177,0.0001592067,0.0007397759,0.0011778327,0.00040421635,0.005734839],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030529067,0.000029583276,0.0015589898,0.000058149304,0.00005875769,0.0006582828,0.00014733583,0.000008758787,5.966535e-7,0.0000014418798,0.9961645,0.0012830897],"study_design_scores_gemma":[0.00024207744,0.00004265181,0.000031365278,0.00011915842,0.000032156502,0.000062505445,0.00022156484,0.0000437142,0.000016412898,0.0001353985,0.99866194,0.00039105595],"about_ca_topic_score_codex":0.1890642,"about_ca_topic_score_gemma":0.6456244,"teacher_disagreement_score":0.45656016,"about_ca_system_score_codex":0.0007548962,"about_ca_system_score_gemma":0.0022085698,"threshold_uncertainty_score":0.99986386},"labels":[],"label_agreement":null},{"id":"W6920405387","doi":"10.60692/gt1vf-xy892","title":"Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"Engineering and Physical Sciences Research Council","keywords":"Colorectal cancer; Grading (engineering); Deep learning; Random forest; Tumour heterogeneity; Transcriptome; Precision medicine; Correlation; Convolutional neural network","score_opus":0.04272459765940327,"score_gpt":0.23863253463724834,"score_spread":0.1959079369778451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920405387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.429127,0.000004904245,0.569936,0.00012289631,0.00018849697,0.00017810686,0.0000068805566,0.00018383616,0.00025192587],"genre_scores_gemma":[0.98373693,8.8411326e-8,0.016059145,0.00012583051,0.000032753753,0.000030341065,0.0000040993577,0.000009511436,0.0000013115546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985859,0.00012218895,0.0005428616,0.00019508443,0.0003708637,0.00018310819],"domain_scores_gemma":[0.9986622,0.0000128471,0.0006197033,0.00022012803,0.0003964702,0.000088652676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022109268,0.00014427029,0.0002019083,0.00015932693,0.00011387393,0.00014447876,0.0002907369,0.00009319528,0.000007963625],"category_scores_gemma":[0.000041354037,0.00014379797,0.0000706319,0.00059921696,0.00004411799,0.00052990613,0.000062902975,0.0001344335,0.00007015912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082592387,0.000013132257,0.26274756,0.004173667,0.0003268503,0.000031664702,0.21488136,0.43363446,0.06371918,0.0023773545,0.00010192508,0.017166924],"study_design_scores_gemma":[0.00050125696,0.00006398667,0.00765921,0.000061669336,0.000017865663,0.000009510814,0.0014683298,0.9529329,0.03709431,6.2836705e-7,0.000042924057,0.00014740771],"about_ca_topic_score_codex":0.000025543739,"about_ca_topic_score_gemma":3.0247665e-7,"teacher_disagreement_score":0.5546099,"about_ca_system_score_codex":0.0002459106,"about_ca_system_score_gemma":0.00014649796,"threshold_uncertainty_score":0.5863911},"labels":[],"label_agreement":null},{"id":"W6920809413","doi":"10.6084/m9.figshare.19728292","title":"Additional file 1 of Cost-effectiveness of using artificial intelligence versus polygenic risk score to guide breast cancer screening","year":2022,"lang":"en","type":"article","venue":"Open MIND","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Polygenic risk score; Risk assessment; Breast cancer; Breast cancer screening; Cancer screening; Mammography","score_opus":0.12506524390288212,"score_gpt":0.36439318245773666,"score_spread":0.23932793855485454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920809413","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03699602,0.000034842535,0.46472475,0.000076655815,0.001121137,0.0014957468,0.49416712,0.000008953417,0.0013747603],"genre_scores_gemma":[0.6304667,0.0000030119088,0.3655502,0.00003639059,0.00025267596,0.0016653574,0.0018123846,0.00003842193,0.00017487833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985584,0.00021396982,0.00028651505,0.00038627876,0.00037601433,0.0001788283],"domain_scores_gemma":[0.9982618,0.00090682256,0.00027929977,0.00033814923,0.00015312868,0.000060781338],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041949915,0.00010075553,0.00017913185,0.0001248975,0.00022731515,0.00005404868,0.0010221942,0.000026225394,0.32058665],"category_scores_gemma":[0.00013716429,0.00011721771,0.000060455313,0.0008242767,0.000053739215,0.00032214963,0.0011253289,0.00014459754,0.000024347803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064599013,0.00006036053,0.00006022173,0.000007883733,0.000053869215,0.000003596066,0.00021868652,0.0796002,0.0012279681,0.000070815266,0.01216743,0.90588295],"study_design_scores_gemma":[0.001354533,0.0019481028,0.022822887,0.0018748632,0.00016763451,0.0001926845,0.0021892923,0.54448825,0.18039294,0.0017080404,0.24117516,0.0016856343],"about_ca_topic_score_codex":0.001521543,"about_ca_topic_score_gemma":0.00025657492,"teacher_disagreement_score":0.90419734,"about_ca_system_score_codex":0.00034881354,"about_ca_system_score_gemma":0.0004950607,"threshold_uncertainty_score":0.6800344},"labels":[],"label_agreement":null},{"id":"W6929091277","doi":"10.3932/ethz-a-000595959","title":"Kanada, Hydro Quebec, Snell","year":2001,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.00902472885967718,"score_gpt":0.21738380205611035,"score_spread":0.20835907319643318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929091277","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4204171e-7,0.00026262473,0.40920162,0.00023303286,0.0009875079,0.00007533781,7.478209e-7,0.0005780546,0.58866096],"genre_scores_gemma":[0.000041433577,0.00010607559,0.016552214,0.0005505406,0.00053014635,0.000011369099,0.0000015875893,0.0001417323,0.9820649],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989342,0.000022487888,0.00011505039,0.0004447242,0.00026154908,0.0002219688],"domain_scores_gemma":[0.9989827,0.000015014256,0.000098713805,0.00082181854,0.000012983099,0.00006876981],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000052843305,0.00018214848,0.00016337397,0.0001844948,0.000027979655,0.00008300963,0.00085008895,0.00021091351,0.008064007],"category_scores_gemma":[0.000003172246,0.000168486,0.000055586308,0.0002710989,0.000026297306,0.00009296936,0.00014788171,0.0001495841,0.0014361567],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.8720017e-7,0.000005580627,0.000007063475,0.000007310865,0.000011815262,0.000011132029,0.0000090565445,0.0000040630566,0.000003853797,0.002638478,0.9497843,0.047517177],"study_design_scores_gemma":[0.00007336785,0.000013071518,0.000008677564,0.000027002352,0.000003499284,0.000010295292,0.0000019386505,0.001578655,0.00014128446,0.00043860695,0.9974868,0.00021678313],"about_ca_topic_score_codex":0.14528567,"about_ca_topic_score_gemma":0.23006053,"teacher_disagreement_score":0.39340395,"about_ca_system_score_codex":0.0001598249,"about_ca_system_score_gemma":0.0001129719,"threshold_uncertainty_score":0.99934137},"labels":[],"label_agreement":null},{"id":"W6931338264","doi":"10.5281/zenodo.5683922","title":"Nomada tiftonensis Cockerell","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"DNA barcoding; Type (biology); Labrum; Taxonomy (biology); Adult male; Genetic divergence","score_opus":0.021786595790732017,"score_gpt":0.22946959134620218,"score_spread":0.20768299555547015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931338264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10858929,0.00007530537,0.4694608,0.0050324313,0.0023080797,0.00083390035,0.000075000076,0.006065862,0.40755934],"genre_scores_gemma":[0.98999524,0.000023415721,0.0074283467,0.0002871502,0.0002834477,3.709288e-8,0.000099543315,0.00079562276,0.0010871888],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985531,0.00012942005,0.00018055788,0.00045790183,0.00035998152,0.00031906393],"domain_scores_gemma":[0.99846905,0.000018670118,0.00008491586,0.0008336158,0.00042836645,0.00016535966],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004947316,0.00011626947,0.00009911323,0.00017906731,0.0016322744,0.00095508096,0.0018254106,0.00007266523,0.0044311234],"category_scores_gemma":[0.00024789988,0.00012551852,0.000044090968,0.000645866,0.000117058626,0.00050468795,0.0014089475,0.00040953822,0.012155263],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023589377,0.000120615194,0.000005561897,0.00003071765,0.000031935702,0.000022222543,0.0011081926,0.00003980441,0.06382162,0.03384341,0.22818638,0.672766],"study_design_scores_gemma":[0.00023447993,0.00011256906,0.0006577919,0.000005963952,0.000003637105,0.00018346567,0.000026146385,0.0037801606,0.0063085128,0.0007344238,0.98779273,0.00016010026],"about_ca_topic_score_codex":0.000028999068,"about_ca_topic_score_gemma":0.0000012669683,"teacher_disagreement_score":0.88140595,"about_ca_system_score_codex":0.00008858734,"about_ca_system_score_gemma":0.0000049283753,"threshold_uncertainty_score":0.99966747},"labels":[],"label_agreement":null},{"id":"W6931971975","doi":"10.56105/cjsae.v30i2.5440","title":"Stitching Together an Arts-based Inquiry with Indigenous Communities in Canada and Chile","year":2018,"lang":"en","type":"article","venue":"Canadian Journal for the Study of Adult Education","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"","keywords":"Indigenous; Image stitching; Traditional knowledge; Participant observation; Informal learning; Point (geometry); Ethnography; Research methodology","score_opus":0.032601924832559526,"score_gpt":0.29814050079158333,"score_spread":0.2655385759590238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931971975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99123394,0.00006018393,0.0068351743,0.0003990925,0.0010787818,0.00035817068,0.000002742212,0.000003281895,0.000028602193],"genre_scores_gemma":[0.99855256,0.0000020330858,0.0008762475,0.00033067205,0.00018094873,0.000039759085,9.2449477e-7,0.000007702042,0.000009175024],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9993799,0.00007257863,0.00014960073,0.00008778523,0.00011789624,0.00019227629],"domain_scores_gemma":[0.9991164,0.00007586104,0.00011792591,0.00026973122,0.0002740399,0.00014602934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028671042,0.000072084295,0.00008077318,0.00015347605,0.0007571757,0.00009833569,0.00039674327,0.000014899888,0.00000612451],"category_scores_gemma":[0.000020594292,0.000054706787,0.000007829616,0.00017624274,0.000075350545,0.00024233073,0.00000907083,0.00014495483,1.0412479e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062576364,0.00015528018,0.31007168,0.000021264343,0.000060159902,0.00000287099,0.4527273,0.0025340093,0.000011019596,0.00035082083,0.00059019396,0.23341282],"study_design_scores_gemma":[0.0014170675,0.003352573,0.5490006,0.00022249392,0.000037813123,0.00012121127,0.43230644,0.00956479,0.00022981477,0.0012051549,0.002190737,0.000351259],"about_ca_topic_score_codex":0.98975927,"about_ca_topic_score_gemma":0.99986774,"teacher_disagreement_score":0.23892896,"about_ca_system_score_codex":0.00053941685,"about_ca_system_score_gemma":0.008247363,"threshold_uncertainty_score":0.99737495},"labels":[],"label_agreement":null},{"id":"W6938874353","doi":"10.60692/8w8sb-dj544","title":"Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI","year":2024,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Context (archaeology); Breast cancer; Random forest; Logistic regression; Decision tree; Supervised learning","score_opus":0.03726994436018144,"score_gpt":0.2187443033581686,"score_spread":0.18147435899798717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6938874353","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120292224,0.000012774184,0.87841916,0.000058093494,0.00010774857,0.0006699564,0.00029903173,0.00006929356,0.00007170435],"genre_scores_gemma":[0.99865985,5.2025433e-7,0.00085429766,0.000035307803,0.000014644169,0.00038373788,0.000032164244,0.0000072414646,0.000012219453],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988642,0.0000772312,0.000455105,0.00015567896,0.0003139904,0.00013379574],"domain_scores_gemma":[0.9991622,0.000023353772,0.00025007193,0.00021959776,0.00032527253,0.000019529343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036745062,0.000109125576,0.00015112227,0.00019858648,0.0000691423,0.00016492451,0.0002311901,0.00005788519,6.174136e-7],"category_scores_gemma":[0.000007934691,0.00007176936,0.000035715668,0.00042387785,0.00002072869,0.0020833404,0.000030378465,0.000119051714,0.0000014547652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006451671,0.000028838524,0.15576047,0.004458909,0.00016265844,3.6970283e-7,0.49882805,0.31546852,0.000014883353,0.0030650739,0.00026685803,0.021300187],"study_design_scores_gemma":[0.00048016643,0.00009455196,0.0028952777,0.0002949225,0.000013367809,0.0000054589905,0.0071844347,0.9887333,0.00015619418,0.0000012978352,0.00006618284,0.000074848984],"about_ca_topic_score_codex":0.00013915371,"about_ca_topic_score_gemma":0.0000014839384,"teacher_disagreement_score":0.87836766,"about_ca_system_score_codex":0.00019634902,"about_ca_system_score_gemma":0.000055478864,"threshold_uncertainty_score":0.29266694},"labels":[],"label_agreement":null},{"id":"W6939063096","doi":"10.60692/pgwg9-j7b59","title":"Telepathology in Nigeria for Global Health Collaboration","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Telepathology; Telemedicine; Software deployment; Quality assurance; Quality (philosophy); Global health; Health services","score_opus":0.0220789131181505,"score_gpt":0.25847911818615943,"score_spread":0.23640020506800893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939063096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082786895,0.0000055423257,0.9126482,0.00088063156,0.0018859567,0.00086561724,0.0001312203,0.00026683556,0.0005291038],"genre_scores_gemma":[0.9941222,5.4639187e-8,0.0045668036,0.00057739386,0.000040378,0.00065347226,0.000015279955,0.0000033768486,0.000021016704],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986916,0.00014954267,0.00051473797,0.0001707475,0.0002439192,0.00022941375],"domain_scores_gemma":[0.99920267,0.000005784235,0.0003390155,0.00030707786,0.00010153202,0.000043893288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074352697,0.00009369786,0.0001611519,0.00018611221,0.0002717269,0.00013916043,0.00032276165,0.000038959253,0.000003626254],"category_scores_gemma":[0.0000102925915,0.00010008525,0.000031840147,0.000813705,0.000008624429,0.00090653566,0.00013384035,0.000065201195,0.000032697535],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004701295,0.000020279906,0.23211262,0.0010945922,0.000050058727,0.000011610244,0.59643996,0.04747408,0.0000059925987,0.07255264,0.004887504,0.044880554],"study_design_scores_gemma":[0.011193489,0.0027541476,0.16018815,0.00014448837,0.000012145145,0.00090704317,0.12203741,0.6666871,0.0004939227,0.00080744276,0.03327569,0.0014989979],"about_ca_topic_score_codex":0.000010443535,"about_ca_topic_score_gemma":0.00000603077,"teacher_disagreement_score":0.91133535,"about_ca_system_score_codex":0.0016616439,"about_ca_system_score_gemma":0.00026733865,"threshold_uncertainty_score":0.4345141},"labels":[],"label_agreement":null},{"id":"W6939147731","doi":"10.60692/zwb80-wqg15","title":"Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Waterloo; McMaster University","funders":"","keywords":"Digital pathology; Deep learning; Demographics; Scope (computer science); Pattern recognition (psychology); Profiling (computer programming); Precision medicine","score_opus":0.030431446735364576,"score_gpt":0.22331909903376687,"score_spread":0.1928876522984023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939147731","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023377234,0.000025388661,0.9740417,0.00024861595,0.0010105874,0.0002941814,0.000152437,0.00027559712,0.0005742748],"genre_scores_gemma":[0.9972161,8.8213056e-7,0.0018917088,0.0005072112,0.00017359265,0.000037420952,0.00013739301,0.000008038861,0.000027650378],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980869,0.0002049183,0.00069365365,0.0002702585,0.0005007672,0.00024349357],"domain_scores_gemma":[0.99720126,0.000040522515,0.0004881697,0.0017721212,0.00043340275,0.00006449756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072369055,0.00016743546,0.00021338172,0.00015230245,0.00020421993,0.00043387318,0.00080607424,0.00010887589,0.000017922865],"category_scores_gemma":[0.000031603096,0.00012655286,0.00007256734,0.0007500706,0.000046779674,0.002752736,0.0004324119,0.00014767115,0.0001376109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054484076,0.000056208188,0.27051318,0.0037006966,0.0009690793,0.00010381883,0.23780786,0.38009068,0.00034989492,0.0029121134,0.02190787,0.08104379],"study_design_scores_gemma":[0.0007245972,0.000044558823,0.037194602,0.00018172241,0.00003464778,0.000074578886,0.0016236239,0.95560557,0.0039234445,0.0000038321523,0.00040383622,0.00018497996],"about_ca_topic_score_codex":0.000015584967,"about_ca_topic_score_gemma":0.0000010560826,"teacher_disagreement_score":0.97383887,"about_ca_system_score_codex":0.00011337542,"about_ca_system_score_gemma":0.0000943591,"threshold_uncertainty_score":0.51606756},"labels":[],"label_agreement":null},{"id":"W6939378386","doi":"10.60692/vyte2-wvs43","title":"Bias Reduction in Representation of Histopathology Images Using Deep Feature Selection","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University; Brock University; Ontario Tech University","funders":"","keywords":"Pattern recognition (psychology); Feature extraction; Feature selection; Representation (politics); Feature (linguistics); Artificial neural network; Deep neural networks; Set (abstract data type)","score_opus":0.048678255503543856,"score_gpt":0.24684769522973418,"score_spread":0.19816943972619033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939378386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4782083,0.0000058545397,0.5198648,0.00005831022,0.0011097575,0.00026348018,0.0000068268805,0.00014327212,0.0003394128],"genre_scores_gemma":[0.99175847,1.2576264e-7,0.008033959,0.000021121108,0.000046603065,0.000078870304,0.0000061633145,0.0000057070233,0.000048989627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852216,0.00027974756,0.00049202266,0.00020052363,0.00034799165,0.00015755517],"domain_scores_gemma":[0.9989444,0.000006388929,0.0005764397,0.00030206257,0.00014634941,0.000024331976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516867,0.000104864506,0.00017495836,0.00071536284,0.00019359187,0.00006068481,0.0002383511,0.000064722226,0.000008092234],"category_scores_gemma":[0.000017331186,0.00011399759,0.000051341198,0.0012661279,0.000019965386,0.0014905507,0.00013406067,0.00017528638,0.000009835892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036052373,0.000021448985,0.29049882,0.000669483,0.00004265192,0.000015278622,0.33861876,0.34440035,0.0039231936,0.0020262077,0.0004901329,0.018933147],"study_design_scores_gemma":[0.0019297281,0.00033658987,0.13901284,0.00009322678,0.000032806634,0.002470573,0.027959432,0.7891563,0.038100187,0.000057091536,0.00032727892,0.0005239548],"about_ca_topic_score_codex":0.00006388965,"about_ca_topic_score_gemma":6.3492547e-7,"teacher_disagreement_score":0.51355016,"about_ca_system_score_codex":0.0009231911,"about_ca_system_score_gemma":0.00005769098,"threshold_uncertainty_score":0.46486866},"labels":[],"label_agreement":null},{"id":"W6945415356","doi":"10.25384/sage.21579472","title":"sj-pdf-1-vet-10.1177_03009858221137582 – Supplemental material for Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cytology; Human Pathology; Human animal; Human physiology","score_opus":0.04523845990757133,"score_gpt":0.30637958922745867,"score_spread":0.2611411293198873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945415356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8428061,0.0050354637,0.14738385,0.0003203999,0.0014445989,0.0011358073,0.001686537,0.0001279056,0.00005932748],"genre_scores_gemma":[0.97273415,0.00025916842,0.026235186,0.000037798032,0.00017397474,0.00011092928,0.00035226005,0.000026746333,0.00006977329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975951,0.00016326255,0.0006779174,0.00057871785,0.0005839549,0.00040104784],"domain_scores_gemma":[0.9983026,0.000086385364,0.00052374764,0.0008977238,0.00009226238,0.00009730275],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013486763,0.00022111529,0.00042870492,0.00026348804,0.0006076957,0.00010476107,0.0016972091,0.000059149766,0.0039057434],"category_scores_gemma":[0.00003073067,0.00022772797,0.00007173919,0.00035867156,0.00006795355,0.0009920516,0.002003861,0.00027799967,0.0000016435498],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002695323,0.00022438963,0.000993904,0.00025431387,0.00004182463,0.00007626314,0.00035779751,0.0005564734,0.24533823,0.0000015237773,0.00037713558,0.7515086],"study_design_scores_gemma":[0.0022690562,0.0036766601,0.0008035919,0.00032842744,0.00007315086,0.0004266392,0.0006086192,0.7511057,0.23918405,0.00010954479,0.00095898757,0.00045556156],"about_ca_topic_score_codex":0.000057442205,"about_ca_topic_score_gemma":0.000006685277,"teacher_disagreement_score":0.75105304,"about_ca_system_score_codex":0.00013024194,"about_ca_system_score_gemma":0.000092335,"threshold_uncertainty_score":0.9970048},"labels":[],"label_agreement":null},{"id":"W6950505923","doi":"10.5281/zenodo.8083819","title":"Ceratoculicoides confusus Fasbender 2023, sp. nov.","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Aedeagus; Apex (geometry); Holotype; Dorsum; Sternum","score_opus":0.048389150164623196,"score_gpt":0.2574990306963434,"score_spread":0.2091098805317202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950505923","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016121939,0.00021124238,0.39446214,0.00920077,0.0017962828,0.0013894384,0.00019046958,0.014125236,0.5625025],"genre_scores_gemma":[0.9886241,0.00021893503,0.002063367,0.0006857524,0.0005140027,2.4593535e-7,0.0005400769,0.0016312798,0.0057222242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980372,0.00021459271,0.00023316599,0.0005566148,0.00049720873,0.00046122773],"domain_scores_gemma":[0.99853665,0.000033805154,0.00008943005,0.00073149224,0.00043677576,0.00017182596],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00066154473,0.00014621165,0.00012872733,0.00034986736,0.0018499757,0.0013084838,0.0018046463,0.00006993892,0.0034494495],"category_scores_gemma":[0.00027896016,0.000159609,0.000056279063,0.0018616103,0.00011142193,0.0006056727,0.0019004713,0.0002656115,0.033839416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020429417,0.000051574316,0.0000035084406,0.000043095723,0.000042801068,0.00004041669,0.0011060095,0.0003055951,0.007760396,0.02892005,0.64020455,0.32150158],"study_design_scores_gemma":[0.0003580911,0.00012969632,0.00078553986,0.000014373531,0.0000041033177,0.00009205219,0.00013807655,0.007934259,0.0020263104,0.0010695839,0.98724735,0.00020058636],"about_ca_topic_score_codex":0.000024120753,"about_ca_topic_score_gemma":6.03762e-7,"teacher_disagreement_score":0.9725022,"about_ca_system_score_codex":0.000182966,"about_ca_system_score_gemma":0.0000077242385,"threshold_uncertainty_score":0.99972826},"labels":[],"label_agreement":null},{"id":"W6957694299","doi":"10.60692/v89d5-jwh64","title":"A deep learning approach for the detection and counting of colon cancer cells (HT-29 cells) bunches and impurities","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Colorectal cancer; Cancer; Colon adenocarcinoma; Cancer cell; Pattern recognition (psychology)","score_opus":0.02625694109635405,"score_gpt":0.20914072420875215,"score_spread":0.1828837831123981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957694299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22456598,0.000043289143,0.7741617,0.00001740461,0.0004244839,0.0004696121,0.000008695248,0.0002034834,0.00010532371],"genre_scores_gemma":[0.99817115,0.0000073571337,0.001428648,0.000019080151,0.0000657572,0.00025756785,0.0000012237541,0.0000069964594,0.000042239342],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990985,0.000045430726,0.00032528435,0.00015048153,0.00020234125,0.00017797586],"domain_scores_gemma":[0.99929464,0.000057427944,0.00031288448,0.00016418388,0.00014202845,0.000028808769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063402037,0.000112268026,0.00014835561,0.00016849913,0.00034814395,0.0002569756,0.00015273406,0.00007359491,4.37389e-7],"category_scores_gemma":[0.0000097505845,0.00008589041,0.000032825563,0.0003221652,0.000045681627,0.00073076366,0.000107397485,0.00008884661,0.000004778323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002315397,0.0000045063393,0.023155496,0.009413426,0.00027949546,9.338616e-7,0.64421546,0.12885216,0.0034054557,0.0005915259,0.00012727239,0.18972275],"study_design_scores_gemma":[0.00037598755,0.000059298396,0.0032813884,0.000055103326,0.00001941479,0.000009643873,0.014607205,0.96449804,0.016731704,0.0000028123552,0.000249472,0.00010994989],"about_ca_topic_score_codex":0.00005800174,"about_ca_topic_score_gemma":0.0000022400247,"teacher_disagreement_score":0.83564585,"about_ca_system_score_codex":0.000075831296,"about_ca_system_score_gemma":0.000019022295,"threshold_uncertainty_score":0.35025093},"labels":[],"label_agreement":null},{"id":"W6957977880","doi":"10.60692/rtt22-kb812","title":"IoMT Cloud-Based Intelligent Prediction of Breast Cancer Stages Empowered With Deep Learning","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Breast cancer; Cancer; The Internet; Mammography","score_opus":0.019850869477950575,"score_gpt":0.21117356550404726,"score_spread":0.1913226960260967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957977880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14236398,0.000013158892,0.85573846,0.00008493792,0.00080053805,0.00019570049,0.00006683865,0.0003094428,0.00042693462],"genre_scores_gemma":[0.99760884,8.148802e-7,0.0021042025,0.000056686375,0.000080129736,0.000069661524,0.0000128140255,0.0000093080025,0.00005753131],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984458,0.00010635408,0.00053698773,0.000214047,0.00049102434,0.000205762],"domain_scores_gemma":[0.99839115,0.00001087592,0.00047181358,0.0004362579,0.000615776,0.00007414852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025852863,0.00016066004,0.00020720504,0.00021281658,0.00013176819,0.00018644774,0.00024803565,0.00008503433,0.00003049561],"category_scores_gemma":[0.000008204359,0.00013553131,0.000060017857,0.0006268857,0.000030416631,0.0010124008,0.00007561652,0.00013954546,0.00004531807],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032661424,0.000016652642,0.66408014,0.0019866796,0.0002782925,0.000018061828,0.11962765,0.18107481,0.00012022171,0.0006946034,0.00010616442,0.031670086],"study_design_scores_gemma":[0.0026176875,0.0003881576,0.2531764,0.0014021725,0.00008186479,0.00034144463,0.01740898,0.65798604,0.06473266,0.0000030943017,0.0012513956,0.000610126],"about_ca_topic_score_codex":0.000028795661,"about_ca_topic_score_gemma":0.000002269302,"teacher_disagreement_score":0.8552449,"about_ca_system_score_codex":0.00031853878,"about_ca_system_score_gemma":0.00017593017,"threshold_uncertainty_score":0.5526807},"labels":[],"label_agreement":null},{"id":"W6958282275","doi":"10.60692/qw9ay-fph30","title":"IoMT Cloud-Based Intelligent Prediction of Breast Cancer Stages Empowered With Deep Learning","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Breast cancer; Cancer; The Internet; Mammography","score_opus":0.019850869477950575,"score_gpt":0.21117356550404726,"score_spread":0.1913226960260967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958282275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14236398,0.000013158892,0.85573846,0.00008493792,0.00080053805,0.00019570049,0.00006683865,0.0003094428,0.00042693462],"genre_scores_gemma":[0.99760884,8.148802e-7,0.0021042025,0.000056686375,0.000080129736,0.000069661524,0.0000128140255,0.0000093080025,0.00005753131],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984458,0.00010635408,0.00053698773,0.000214047,0.00049102434,0.000205762],"domain_scores_gemma":[0.99839115,0.00001087592,0.00047181358,0.0004362579,0.000615776,0.00007414852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025852863,0.00016066004,0.00020720504,0.00021281658,0.00013176819,0.00018644774,0.00024803565,0.00008503433,0.00003049561],"category_scores_gemma":[0.000008204359,0.00013553131,0.000060017857,0.0006268857,0.000030416631,0.0010124008,0.00007561652,0.00013954546,0.00004531807],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032661424,0.000016652642,0.66408014,0.0019866796,0.0002782925,0.000018061828,0.11962765,0.18107481,0.00012022171,0.0006946034,0.00010616442,0.031670086],"study_design_scores_gemma":[0.0026176875,0.0003881576,0.2531764,0.0014021725,0.00008186479,0.00034144463,0.01740898,0.65798604,0.06473266,0.0000030943017,0.0012513956,0.000610126],"about_ca_topic_score_codex":0.000028795661,"about_ca_topic_score_gemma":0.000002269302,"teacher_disagreement_score":0.8552449,"about_ca_system_score_codex":0.00031853878,"about_ca_system_score_gemma":0.00017593017,"threshold_uncertainty_score":0.5526807},"labels":[],"label_agreement":null},{"id":"W6958447620","doi":"10.6084/m9.figshare.19728292.v1","title":"Additional file 1 of Cost-effectiveness of using artificial intelligence versus polygenic risk score to guide breast cancer screening","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Polygenic risk score; Risk assessment; Breast cancer; Breast cancer screening; Cancer screening; Mammography","score_opus":0.12445265594886783,"score_gpt":0.33205765351015554,"score_spread":0.2076049975612877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958447620","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018509633,0.000028463919,0.011830769,0.000012275871,0.00019778573,0.0003168476,0.9872792,0.000041882904,0.00010768344],"genre_scores_gemma":[0.3493346,0.0000022797958,0.05151253,0.00014683607,0.0007777911,0.011045123,0.5869993,0.00009847148,0.00008306634],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985912,0.00016361824,0.00025686974,0.0003437151,0.00044507958,0.00019955353],"domain_scores_gemma":[0.997702,0.001373907,0.00028610762,0.00032187722,0.0002510039,0.00006512339],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010539355,0.00011356381,0.00015978394,0.00015094569,0.00020965075,0.000023709617,0.00063442654,0.000033555854,0.88820094],"category_scores_gemma":[0.0006817,0.00013559655,0.00009182884,0.0009303796,0.000012763861,0.00021529057,0.0006620785,0.00017950451,0.00006164077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028723117,0.000043994663,0.000013517658,0.00008312491,0.00005016219,0.00000473918,0.0001009411,0.11070749,0.00023692742,0.00005305518,0.7159182,0.17250067],"study_design_scores_gemma":[0.0006719927,0.0011029788,0.02773129,0.010351077,0.000062893894,0.00014123606,0.00051083684,0.5821922,0.039728135,0.0009851312,0.33504924,0.0014730053],"about_ca_topic_score_codex":0.00029197277,"about_ca_topic_score_gemma":0.000060908184,"teacher_disagreement_score":0.88813925,"about_ca_system_score_codex":0.00037810922,"about_ca_system_score_gemma":0.00039592863,"threshold_uncertainty_score":0.5529467},"labels":[],"label_agreement":null},{"id":"W6966819763","doi":"10.48550/arxiv.1007.5129","title":"An Efficient Automatic Mass Classification Method In Digitized Mammograms Using Artificial Neural Network","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial neural network; Pattern recognition (psychology); Sensitivity (control systems); Kurtosis; Contextual image classification; Process (computing)","score_opus":0.11207855786486219,"score_gpt":0.2504665224484962,"score_spread":0.138387964583634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966819763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44118544,0.000006906642,0.5567007,0.00003220932,0.0013332381,0.00031274572,0.000002493583,0.00032837296,0.000097917466],"genre_scores_gemma":[0.9162722,0.000005148293,0.08338559,0.000035704034,0.00023983816,0.0000033915287,0.00001209251,0.000026854514,0.000019178764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693227,0.0005362995,0.00040660644,0.0014071183,0.00017818544,0.00053951517],"domain_scores_gemma":[0.9974524,0.00014934345,0.0004898283,0.001594685,0.00013335067,0.00018039107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008333367,0.00035684335,0.0004069238,0.0003854349,0.00021248753,0.0003629352,0.0016443346,0.00051242224,0.000013325599],"category_scores_gemma":[0.000028389206,0.000439407,0.00017616004,0.001326141,0.000107953114,0.00042819272,0.0006204532,0.0011506573,0.00001583567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024633473,0.000080752536,0.00080541,0.00003202303,0.000016402548,0.000058799473,0.0001133006,0.96415704,0.000984439,0.023344308,0.0000036819251,0.010379219],"study_design_scores_gemma":[0.0002445848,0.000041536106,0.0026288964,0.00006337153,0.000041142812,0.0000065125755,0.000044962846,0.9485854,0.0002214534,0.04769286,0.000017731609,0.00041158425],"about_ca_topic_score_codex":0.0002822319,"about_ca_topic_score_gemma":0.00021674369,"teacher_disagreement_score":0.47508678,"about_ca_system_score_codex":0.0006628482,"about_ca_system_score_gemma":0.00025319672,"threshold_uncertainty_score":0.99980575},"labels":[],"label_agreement":null},{"id":"W6967807798","doi":"10.5281/zenodo.13361538","title":"100m climate and heat stress information up to 2100 for 142 cities around the globe","year":2024,"lang":"en","type":"dataset","venue":"Open MIND","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"European Commission","keywords":"Montenegro; Curitiba; Conurbation; Almeria; Climate change","score_opus":0.03148503244756937,"score_gpt":0.3166088600471909,"score_spread":0.2851238275996215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6967807798","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017077371,0.00011926553,0.004892812,0.0011481517,0.0023195485,0.0012508043,0.9895752,0.000006680391,0.0005167803],"genre_scores_gemma":[0.00024460597,0.0004276488,0.010373844,0.0013688958,0.0010893812,0.0009028918,0.98469293,0.00002811849,0.0008716817],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988835,0.000031272975,0.00027648237,0.0003444108,0.00021435496,0.00024998953],"domain_scores_gemma":[0.9989636,0.00011464359,0.00009031959,0.0007005433,0.00006828003,0.000062591156],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004325641,0.00019679537,0.00019112315,0.00011422387,0.000249446,0.00344847,0.0015667381,0.0001239145,0.000061907296],"category_scores_gemma":[0.000026365844,0.00014779044,0.000039461025,0.00022042112,0.00004273361,0.0014193926,0.0015764361,0.00018522929,0.0010552189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018684228,0.0000023328314,7.63736e-7,0.000099541496,0.000018265955,7.47064e-7,0.0006163,0.000047033645,7.2124953e-7,0.00003231309,0.93842703,0.060736276],"study_design_scores_gemma":[0.00013770393,0.0001224415,0.0000069427715,0.00016990918,0.00003263078,0.000015299172,0.00037802878,0.001819563,0.00016817926,0.00021786169,0.99673826,0.00019318405],"about_ca_topic_score_codex":0.0003897696,"about_ca_topic_score_gemma":0.0010515476,"teacher_disagreement_score":0.060543094,"about_ca_system_score_codex":0.00012788274,"about_ca_system_score_gemma":0.00013653633,"threshold_uncertainty_score":0.9997226},"labels":[],"label_agreement":null},{"id":"W6977074463","doi":"10.60692/2zznn-dtx41","title":"Function tissue unit segmentation based on UNext model","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Segmentation; Pyramid (geometry); Pooling; Pattern recognition (psychology); Image segmentation; Inference; Feature (linguistics); Human Protein Atlas","score_opus":0.0543086363533391,"score_gpt":0.23923004298573178,"score_spread":0.18492140663239268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977074463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030058622,3.0285779e-7,0.9625704,0.00014563145,0.0010267168,0.00036050173,0.000018616882,0.0014239802,0.0043952046],"genre_scores_gemma":[0.99630004,5.4487444e-8,0.0027175997,0.00039110964,0.00006225354,0.00014255976,0.000032685184,0.000009792992,0.00034387578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998586,0.00006203482,0.0004024198,0.00020548966,0.00051679154,0.00022727819],"domain_scores_gemma":[0.99901426,0.0000112744465,0.00023193113,0.0005260099,0.00014723612,0.000069303234],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039981492,0.00015617211,0.00012159238,0.00059522106,0.0002118713,0.0002974449,0.00028236923,0.00009512048,0.000008457312],"category_scores_gemma":[0.000008270864,0.00014596128,0.00004218422,0.0010279467,0.000011499185,0.0016743359,0.000057302692,0.00009161685,0.0037627432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009094034,0.0000028473025,0.00303409,0.00031229568,0.000022268881,0.0000026127186,0.023929259,0.94705254,0.000058780803,0.0033227766,0.0013270817,0.020844508],"study_design_scores_gemma":[0.0005503636,0.00010381999,0.004101503,0.000056810946,0.000007212114,0.0000035121348,0.0010364098,0.9907304,0.0029401623,0.000018318595,0.00029418129,0.00015731624],"about_ca_topic_score_codex":0.0000054214247,"about_ca_topic_score_gemma":1.918111e-7,"teacher_disagreement_score":0.9662414,"about_ca_system_score_codex":0.00023462994,"about_ca_system_score_gemma":0.000059956667,"threshold_uncertainty_score":0.9970129},"labels":[],"label_agreement":null},{"id":"W6977245106","doi":"10.6084/m9.figshare.26727847","title":"Additional file 5 of Extensive remodeling of sugar metabolism through gene loss and horizontal gene transfer in a eukaryotic lineage","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Horizontal gene transfer; Sugar; Gene; Lineage (genetic); Sugar consumption; Consumption (sociology); Carbohydrate metabolism","score_opus":0.025409573504766046,"score_gpt":0.2377802947316109,"score_spread":0.21237072122684483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977245106","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008129748,0.001553011,0.0038979053,0.000031462365,0.00008525415,0.00013630895,0.9932809,0.000050963834,0.00015123184],"genre_scores_gemma":[0.31868997,0.00010398262,0.09592584,0.00023726751,0.0007924486,0.0007929793,0.5831864,0.00007559627,0.00019551096],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905366,0.000028405471,0.00024216679,0.0003209788,0.00021386985,0.00014091212],"domain_scores_gemma":[0.9992065,0.0003983893,0.000035438043,0.00019525623,0.00013396064,0.00003048312],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002910057,0.000109457236,0.00018448778,0.00009669154,0.00002415079,0.000028909146,0.00020714337,0.00007267847,0.3652951],"category_scores_gemma":[0.00019028746,0.00010973566,0.00006731989,0.0003715729,0.000014629171,0.0004109336,0.000092856506,0.00014133431,0.00006094341],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017598277,0.000036659345,6.5729995e-7,0.00042434377,0.000046349593,0.00010957964,0.0012899591,0.00062953803,0.0021949047,0.0001615212,0.9839173,0.011171567],"study_design_scores_gemma":[0.00092367956,0.00036566105,0.00450955,0.010652759,0.000043601725,0.00047176477,0.00010456347,0.5312242,0.18016104,0.0022788637,0.26838368,0.0008806289],"about_ca_topic_score_codex":0.000018039918,"about_ca_topic_score_gemma":0.000016866481,"teacher_disagreement_score":0.7155337,"about_ca_system_score_codex":0.000035689674,"about_ca_system_score_gemma":0.00013581825,"threshold_uncertainty_score":0.6352851},"labels":[],"label_agreement":null},{"id":"W6977592522","doi":"10.6084/m9.figshare.c.7042244","title":"Predictors of social intermediate factors associated with sexual quality of life of women: systematic review and meta-analysis","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Checklist; Affect (linguistics); Reproductive health; Observational study; Quality of life (healthcare); Sexual function; Systematic review; Marital status","score_opus":0.10107755104464297,"score_gpt":0.3153204532392965,"score_spread":0.21424290219465356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977592522","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003761757,0.10173618,0.00026236454,0.00009427636,0.00023008585,0.003651332,0.88768625,0.0004995364,0.0054637743],"genre_scores_gemma":[0.6238357,0.00043539557,0.00035768675,0.0008629914,0.00043775287,0.0057618637,0.059219252,0.0017552415,0.30733413],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9976298,0.00038554077,0.00083702424,0.00038449044,0.00059855817,0.00016459316],"domain_scores_gemma":[0.99665385,0.0002075937,0.0023906387,0.0004972593,0.00018007358,0.0000705914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004294204,0.00026289583,0.0032305722,0.0003230211,0.000011467136,0.000019881632,0.0005369417,0.00019141758,0.019044546],"category_scores_gemma":[0.0011413046,0.00017849424,0.00043115008,0.0010384567,0.00003125356,0.00007160779,0.00021855185,0.0001577381,0.000011210126],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020729613,0.000033540367,0.000029868357,0.65850675,0.16165389,6.6763687e-7,0.0017648457,0.0000015095973,9.253842e-7,0.000009579829,0.17799343,0.0000029230864],"study_design_scores_gemma":[0.0008511374,0.0012193072,0.0037250677,0.14106943,0.8451482,0.0000013656662,0.0010466246,0.00035374134,0.00016233833,0.00006187032,0.0040699826,0.0022909064],"about_ca_topic_score_codex":0.000043198168,"about_ca_topic_score_gemma":0.00011329059,"teacher_disagreement_score":0.828467,"about_ca_system_score_codex":0.0001277041,"about_ca_system_score_gemma":0.00013386583,"threshold_uncertainty_score":0.9818522},"labels":[],"label_agreement":null},{"id":"W6987794177","doi":"","title":"Transfer learning for focal pathology segmentation across neuro-degenerative diseases","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Transfer of learning; Pattern recognition (psychology); Constant (computer programming)","score_opus":0.020118144501503225,"score_gpt":0.27427065482809365,"score_spread":0.2541525103265904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987794177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704504,0.00060725317,0.010318359,0.00034842666,0.008542083,0.0034697696,0.0018911302,0.0018699578,0.0025026477],"genre_scores_gemma":[0.98791903,0.00017744096,0.005689697,0.0012177925,0.0002464472,0.0013927671,0.0016888111,0.00025148602,0.0014165494],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99494404,0.00064433174,0.0008449551,0.001963349,0.00074544357,0.0008578559],"domain_scores_gemma":[0.99772674,0.00043594075,0.00038162316,0.00060156285,0.00048498734,0.00036916372],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00042373582,0.0007964224,0.0007500446,0.00015964513,0.0019150147,0.0002978448,0.001154273,0.0006504242,0.000030969157],"category_scores_gemma":[0.0005924458,0.0009027213,0.0005049268,0.00072093285,0.00006841828,0.0019845702,0.00015931213,0.001481048,0.00009210905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006345792,0.00016458941,0.000025262962,0.0005350541,0.00022306587,0.00013577237,0.00026667406,0.002360061,0.20262186,0.047849808,0.000019962363,0.7451633],"study_design_scores_gemma":[0.0035804957,0.0024207905,0.0010922536,0.00026059075,0.00040804103,0.000082764076,0.0010559842,0.010075638,0.88801533,0.018073179,0.072292544,0.0026423617],"about_ca_topic_score_codex":0.000034126297,"about_ca_topic_score_gemma":0.0003319564,"teacher_disagreement_score":0.7425209,"about_ca_system_score_codex":0.0006697081,"about_ca_system_score_gemma":0.000092734066,"threshold_uncertainty_score":0.99938434},"labels":[],"label_agreement":null},{"id":"W6989481664","doi":"","title":"An automated approach for segmenting regions containing invasive ductal breast carcinomas in whole digital slides","year":2015,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Detector; Local binary patterns; Histogram; Pattern recognition (psychology); Ductal carcinoma; Binary number; Breast tissue","score_opus":0.02588411254503933,"score_gpt":0.26987998364459787,"score_spread":0.24399587109955853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6989481664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782525,0.0001686301,0.00031059096,0.00002575822,0.0016112132,0.0019475968,0.0012957788,0.0019289348,0.014459011],"genre_scores_gemma":[0.98433053,0.0000066003286,0.011396565,0.00006691193,0.00011445596,0.0006112512,0.002574929,0.00019011271,0.00070864015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99470735,0.00029762258,0.001065975,0.0019544694,0.0009132663,0.0010613373],"domain_scores_gemma":[0.9962641,0.0002728231,0.0009130225,0.0012100248,0.0008909893,0.00044904574],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011834487,0.0008497422,0.0008540989,0.00082405604,0.0010063385,0.00079761667,0.0017944009,0.0007620153,0.0000035585422],"category_scores_gemma":[0.0005676194,0.0009867202,0.0002932811,0.0012063051,0.00006857995,0.0051785195,0.00027592416,0.001178625,0.000028828372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025170548,0.0029822162,0.0033145838,0.003516601,0.0014401594,0.0006879435,0.002132969,0.00998842,0.16904055,0.14267114,0.000226664,0.6614817],"study_design_scores_gemma":[0.030035283,0.008637693,0.030864127,0.007534259,0.001337995,0.00555621,0.044006016,0.42537493,0.19385184,0.2119621,0.017125081,0.023714462],"about_ca_topic_score_codex":0.00040398218,"about_ca_topic_score_gemma":0.001277081,"teacher_disagreement_score":0.63776726,"about_ca_system_score_codex":0.0020006937,"about_ca_system_score_gemma":0.0003789409,"threshold_uncertainty_score":0.99925834},"labels":[],"label_agreement":null},{"id":"W6992572893","doi":"","title":"#6598 - #maghanandharry #theroyals #canada \"🔥🔥🔥🔥🔥🔥🔥Is Racism The Reason Meghan Flew Out Of Britain Like a Bat Out Of Hell?🔥🔥🔥🔥🔥🔥🔥\" With Organic The Prime Minister","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prime minister; Racism; Prime (order theory); Prime time","score_opus":0.006268380541105755,"score_gpt":0.1762998600221797,"score_spread":0.17003147948107394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992572893","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038238366,0.0010188067,0.00030912305,0.003545531,0.0010860933,0.0012960554,0.00019654034,0.0001521209,0.9923575],"genre_scores_gemma":[0.004186317,0.00032414828,0.0023255097,0.002286132,0.0002764522,0.00004708438,0.00003227193,0.00019135898,0.9903307],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99575734,0.0003199121,0.001322513,0.0005493609,0.0015379947,0.000512854],"domain_scores_gemma":[0.9950164,0.00041528096,0.002305819,0.0017097808,0.0003775436,0.00017519918],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059901533,0.0006682458,0.00095566997,0.00009471753,0.00015635848,0.0001213378,0.0023469692,0.00040788483,0.03698639],"category_scores_gemma":[0.00012832916,0.0004488369,0.00027422872,0.000069746115,0.0004136653,0.0000024773717,0.00046892365,0.0005889626,0.00071064994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013865033,0.000036655652,0.0000033417455,0.00052860915,0.00026484238,0.000014164198,0.0017025906,0.000062040766,0.000009933706,0.000034195855,0.991343,0.005861945],"study_design_scores_gemma":[0.00068462564,0.00043941874,0.000015887494,0.00057465746,0.00014721426,0.0000584216,0.0003088859,0.0002494068,0.0008681652,0.000020446987,0.99614775,0.00048509787],"about_ca_topic_score_codex":0.06326864,"about_ca_topic_score_gemma":0.14636849,"teacher_disagreement_score":0.08309985,"about_ca_system_score_codex":0.00018782518,"about_ca_system_score_gemma":0.0006018355,"threshold_uncertainty_score":0.99979633},"labels":[],"label_agreement":null},{"id":"W6996112791","doi":"","title":"Recovering from Hail","year":2021,"lang":"en","type":"other","venue":"University Library (University of Saskatchewan)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Crop; Yield (engineering); Canopy; Agriculture; Crop yield; Fungicide; Nutrient","score_opus":0.0076477632423621504,"score_gpt":0.15386268869071454,"score_spread":0.14621492544835238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996112791","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021154487,0.0011769773,0.25691855,0.0012548324,0.0018511735,0.0003332764,0.00052968366,0.0018589991,0.73396105],"genre_scores_gemma":[0.0039446885,0.0006398332,0.10805149,0.000073694835,0.00015785845,1.911263e-8,0.00014125365,0.000114111754,0.88687706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984996,0.00011298982,0.000090819405,0.0007475014,0.0002944093,0.00025470502],"domain_scores_gemma":[0.99848235,0.00006273825,0.00031918634,0.00094838545,0.000029048118,0.00015827648],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000334825,0.00026838158,0.0004358697,0.00047738277,0.00014498,0.000044835513,0.0019589325,0.00043342187,0.008347205],"category_scores_gemma":[0.0000023368777,0.00042356818,0.00024847913,0.0007444666,0.00014450461,0.0012768292,0.0015008519,0.00033312643,0.00009753202],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001393861,0.00021472394,0.001987611,0.00044340582,0.0010639527,0.0022311285,0.024494397,0.00006839657,0.00049005495,0.00094467646,0.92221355,0.04570872],"study_design_scores_gemma":[0.0007571471,0.000054021682,0.0004382751,0.00046783817,0.00008569144,0.0000044315293,0.021731168,0.0004891332,0.00037186264,0.0003810322,0.9746267,0.00059264887],"about_ca_topic_score_codex":0.009881679,"about_ca_topic_score_gemma":0.005216833,"teacher_disagreement_score":0.152916,"about_ca_system_score_codex":0.00013587698,"about_ca_system_score_gemma":0.0005227486,"threshold_uncertainty_score":0.9998216},"labels":[],"label_agreement":null},{"id":"W6996558241","doi":"","title":"Search for single-top-quark production in <i>pp</i> collisions at √s =1.8 TeV","year":2002,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Istituto Nazionale di Fisica Nucleare; Korea Science and Engineering Foundation; National Science Council; Alfred P. Sloan Foundation; Fermilab; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Fusion; Collider; Production (economics); Standard Model (mathematical formulation); Detector; Limit (mathematics); Cross section (physics)","score_opus":0.03713328745087082,"score_gpt":0.22359494055111057,"score_spread":0.18646165310023974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996558241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8784477,0.00024542332,0.10692967,0.00826433,0.00096971577,0.0009847782,0.000017965169,0.00020092519,0.0039394996],"genre_scores_gemma":[0.9678176,0.00008570657,0.028905125,0.00004513995,0.00010265704,0.0000025705926,0.0000029865225,0.000010357812,0.0030278487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878514,0.000065038286,0.00012895593,0.00046926882,0.00029291463,0.00025868244],"domain_scores_gemma":[0.99911535,0.000119905526,0.00010040316,0.00043937252,0.00014768874,0.00007730076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025253984,0.000102184735,0.00017093883,0.00023720236,0.0003012441,0.000023059043,0.0005817239,0.00010511512,0.000054689102],"category_scores_gemma":[0.00003089078,0.00013595009,0.00008672434,0.0010069433,0.00009954753,0.00060510956,0.00028174729,0.00012974982,0.000050635394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000851479,0.0034683084,0.07403012,0.0007347771,0.00019547391,0.00017979654,0.034648504,0.036264636,0.1870398,0.012023297,0.12358788,0.5269759],"study_design_scores_gemma":[0.006534493,0.0026181247,0.021813262,0.0004000515,0.00007292428,0.0001412654,0.0035160931,0.5901104,0.18054214,0.0021643585,0.1906162,0.0014706777],"about_ca_topic_score_codex":0.00016807052,"about_ca_topic_score_gemma":0.00033097682,"teacher_disagreement_score":0.55384576,"about_ca_system_score_codex":0.0004591721,"about_ca_system_score_gemma":0.000045652378,"threshold_uncertainty_score":0.5543884},"labels":[],"label_agreement":null},{"id":"W7000650813","doi":"","title":"FactSet Reports Strong Revenue Growth in Second Quarter 2018","year":2018,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Revenue; Payment; Work (physics)","score_opus":0.01144114484445648,"score_gpt":0.2385042089717601,"score_spread":0.22706306412730362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000650813","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000335965,0.00008185759,0.0919952,0.00013578647,0.0030074078,0.00024245672,0.000011569427,0.0002479383,0.9042442],"genre_scores_gemma":[0.0029885946,0.000010592123,0.010885802,0.00016618837,0.00071704027,0.000028025614,0.000005806538,0.00012737174,0.9850706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986004,0.000049104226,0.0002621958,0.0006103996,0.00022381944,0.00025405467],"domain_scores_gemma":[0.9988214,0.000014992203,0.00026904326,0.0008162051,0.000024019433,0.00005435891],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020949254,0.00019661494,0.0002212397,0.0002776786,0.000021565427,0.00007831885,0.00042237132,0.00025039734,0.005206673],"category_scores_gemma":[0.0000113743645,0.00018787081,0.000047805763,0.00021424075,0.00004317858,0.00018901333,0.00013115385,0.00016759793,0.0006612608],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.9741217e-7,0.000007639111,0.00022842787,0.000025377414,0.0000093718945,0.0000425474,0.000056207515,9.9120825e-8,0.00000570875,0.00019892145,0.99811625,0.0013088228],"study_design_scores_gemma":[0.000105430576,0.00008334081,0.0006193211,0.00012980691,0.0000029211558,0.00006698133,0.0000069315033,0.000118689386,0.0002968491,0.0017453505,0.9965293,0.00029511575],"about_ca_topic_score_codex":0.0008058895,"about_ca_topic_score_gemma":0.0055949967,"teacher_disagreement_score":0.081109405,"about_ca_system_score_codex":0.0001379202,"about_ca_system_score_gemma":0.00008666521,"threshold_uncertainty_score":0.9957027},"labels":[],"label_agreement":null},{"id":"W7000734358","doi":"","title":"Gmina Polkowice w opisie Friedricha Alberta Zimmermanna [Dokument elektroniczny]","year":2024,"lang":"pl","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Natural (archaeology); Identification (biology); Context (archaeology)","score_opus":0.010637562511920032,"score_gpt":0.2555543156286721,"score_spread":0.24491675311675207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000734358","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016243797,0.01040571,0.08990483,0.0067888754,0.016491784,0.0010879908,0.000026012513,0.00063750835,0.87464106],"genre_scores_gemma":[0.004881831,0.00094634347,0.004681734,0.0019416641,0.0027529846,0.00016794934,0.000018634268,0.0006791754,0.9839297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930727,0.00020313363,0.0009874349,0.0028831973,0.0013144139,0.0015391236],"domain_scores_gemma":[0.99595624,0.00019897883,0.0004928848,0.0027626,0.00013536609,0.00045390349],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0004982671,0.0012933421,0.0009460181,0.000754098,0.000201667,0.0009645895,0.0027948793,0.00095769495,0.021387331],"category_scores_gemma":[0.00003609154,0.0012281021,0.0005363321,0.0014225414,0.0002126354,0.00052666874,0.0016952727,0.0013588597,0.09238818],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020917912,0.00014812204,0.000015733352,0.00056367915,0.0006031526,0.00007300666,0.0015822189,0.000029963707,0.000102646976,0.04149566,0.8917402,0.063624695],"study_design_scores_gemma":[0.00040590562,0.00041365923,0.000043277323,0.0007702963,0.00022328347,0.0001027791,0.00010087759,0.009099883,0.0007748037,0.0018660311,0.9847961,0.0014030833],"about_ca_topic_score_codex":0.011903846,"about_ca_topic_score_gemma":0.004722614,"teacher_disagreement_score":0.10928864,"about_ca_system_score_codex":0.0013212524,"about_ca_system_score_gemma":0.00065677636,"threshold_uncertainty_score":0.9999818},"labels":[],"label_agreement":null},{"id":"W7000852425","doi":"","title":"IDACORP, Inc. Announces Second Quarter 2020 Results, Reaffirms 2020 Earnings Guidance - Commodities (COMMODIT) News","year":2020,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Earnings; Quarter (Canadian coin); Payment; Revenue","score_opus":0.013145692541991797,"score_gpt":0.23105434078029646,"score_spread":0.21790864823830466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000852425","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001894458,0.0016333961,0.061684713,0.010613222,0.004084915,0.0007102752,0.0005290681,0.0027135874,0.9180119],"genre_scores_gemma":[0.0017293546,0.0008727003,0.052051403,0.006506922,0.0064524417,0.00020537464,0.00035039458,0.0006397007,0.9311917],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953073,0.00031480993,0.00093409495,0.0018194469,0.0009244364,0.0006998953],"domain_scores_gemma":[0.9963126,0.00021636125,0.0010884848,0.0019536028,0.00011160181,0.0003173216],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00037936622,0.000848822,0.0009345624,0.00022932235,0.00022680953,0.00062911963,0.003094806,0.000639503,0.0028024495],"category_scores_gemma":[0.000089161455,0.0007926836,0.00022012251,0.00087591197,0.00026878674,0.00071135006,0.00085441436,0.0011011248,0.0017502692],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000418519,0.000025367854,0.000064041174,0.00012418375,0.00009124609,0.00005198489,0.00089284754,0.00001433646,0.000036551,0.0006096925,0.9928931,0.005154811],"study_design_scores_gemma":[0.0006789942,0.00040820608,0.00018198558,0.00022318959,0.000020000729,0.00003749315,0.00016984563,0.0039846906,0.00013402308,0.00059357815,0.9926034,0.0009645903],"about_ca_topic_score_codex":0.002310663,"about_ca_topic_score_gemma":0.006806801,"teacher_disagreement_score":0.013179827,"about_ca_system_score_codex":0.00022047342,"about_ca_system_score_gemma":0.00029620796,"threshold_uncertainty_score":0.9994524},"labels":[],"label_agreement":null},{"id":"W7000978245","doi":"","title":"+91-9829791419^% How Can I Kill, Remove, Destroy Enemy Without Any Evidence In Kolkata, Durgapur","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mantra; Spell; MAGIC (telescope); nobody; Curse; Unicorn","score_opus":0.025835673322275612,"score_gpt":0.26762557777851115,"score_spread":0.24178990445623555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000978245","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017125229,0.00014803882,0.06886781,0.0020827258,0.00290142,0.002259769,0.000029841569,0.0010658539,0.920932],"genre_scores_gemma":[0.02423633,0.0015527459,0.03050144,0.00036650695,0.0004731646,0.0005553779,0.00001948668,0.00046890366,0.94182605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9892429,0.0013927326,0.00087990705,0.0060071396,0.0013002512,0.0011770701],"domain_scores_gemma":[0.9872244,0.00055259356,0.000979647,0.010534329,0.0002312805,0.00047772806],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038626147,0.0009978978,0.0012062306,0.0008374352,0.00017521143,0.00071730494,0.0053095235,0.0010028398,0.15055203],"category_scores_gemma":[0.0030528426,0.0011904823,0.00036975503,0.0012913015,0.00029240965,0.0006697564,0.004982363,0.001616674,0.11469093],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018948184,0.0008997673,0.07856161,0.0022135596,0.00086640235,0.0013322367,0.0033613397,0.0016616129,0.011746622,0.0034685498,0.7152238,0.18047501],"study_design_scores_gemma":[0.0015268703,0.000009082081,0.021025123,0.0069508213,0.00013198113,0.0005033072,0.00014407736,0.0054213405,0.016071722,0.0027941708,0.9424244,0.002997103],"about_ca_topic_score_codex":0.0043457495,"about_ca_topic_score_gemma":0.0062242704,"teacher_disagreement_score":0.2272006,"about_ca_system_score_codex":0.0017737929,"about_ca_system_score_gemma":0.0012823542,"threshold_uncertainty_score":0.9990545},"labels":[],"label_agreement":null},{"id":"W7002173374","doi":"","title":"Montreal's BrainBox AI among Canadian companies working with MaRS Discovery District in order to scale Cleantech across Canada - Energy (ENERGY01) News","year":2019,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mars Exploration Program; Order (exchange); Scale (ratio); Energy (signal processing); Sustainability; Renewable energy; Sustainable energy","score_opus":0.005700544468664043,"score_gpt":0.19664744188206626,"score_spread":0.1909468974134022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002173374","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033140602,0.00039980796,0.42587012,0.0026969742,0.0038289586,0.0009997298,0.00023176154,0.00054175104,0.56211686],"genre_scores_gemma":[0.38348174,0.000068299036,0.003084641,0.003982125,0.0003583017,0.0001088097,0.00005258952,0.0004360814,0.6084274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968034,0.00007175127,0.0003484524,0.0011155731,0.0005931973,0.0010676234],"domain_scores_gemma":[0.998017,0.00005702186,0.000199807,0.0012348951,0.000084604035,0.0004066856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009467218,0.0005475625,0.0005869393,0.00036799037,0.00013326798,0.0005790134,0.0014515226,0.0002853457,0.000063114676],"category_scores_gemma":[0.000012968155,0.0004831309,0.000045330125,0.002443162,0.00008128632,0.0003748457,0.0003381395,0.00035428305,0.000009495682],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003500847,0.00002977331,0.030873714,0.000045978602,0.000115726245,0.00020985738,0.00035703563,0.012481846,0.0000022598106,0.00078723434,0.77804446,0.17701708],"study_design_scores_gemma":[0.0006026008,0.000102927974,0.020546833,0.00069764024,0.000011485167,0.000021894846,0.00036032216,0.008759528,0.00005906951,0.000026380627,0.9674116,0.0013997101],"about_ca_topic_score_codex":0.9998809,"about_ca_topic_score_gemma":0.9999985,"teacher_disagreement_score":0.4227855,"about_ca_system_score_codex":0.002089353,"about_ca_system_score_gemma":0.0026967619,"threshold_uncertainty_score":0.99976206},"labels":[],"label_agreement":null},{"id":"W7008615601","doi":"","title":"Canadian Gender Wage Gap","year":2023,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wage; Quantile regression; Quantile; Selection bias; Matching (statistics); Robustness (evolution); Selection (genetic algorithm); Workforce","score_opus":0.017701471487546704,"score_gpt":0.1583123319063233,"score_spread":0.1406108604187766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008615601","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025753581,0.00010320708,0.004428918,0.0004094793,0.0010816253,0.00030659203,0.0011037908,0.0049921535,0.9875485],"genre_scores_gemma":[0.0035290848,0.00019199135,0.0012987135,0.00015114101,0.00023826306,1.1697126e-7,0.00014945258,0.0004718301,0.9939694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99758255,0.000081652055,0.00012955276,0.0010720296,0.00037244207,0.0007617468],"domain_scores_gemma":[0.997863,0.00007923084,0.00021201564,0.0010706576,0.000023401213,0.00075169373],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000278568,0.0004957444,0.00038686793,0.0028074884,0.00035268045,0.00052389025,0.0031774468,0.00060464063,0.0008218257],"category_scores_gemma":[0.0000067280853,0.0006807788,0.0002897904,0.0033599013,0.00016951992,0.0033079442,0.0011022902,0.00049026264,0.0022775063],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018456254,0.000026544469,0.0009998747,0.000031036976,0.00017967916,0.0018426885,0.00011811357,0.000021572494,3.6401383e-7,0.035804063,0.9562507,0.0047068894],"study_design_scores_gemma":[0.00038290644,0.000047360074,0.00016465971,0.00010416732,0.000036724014,0.000012048619,0.00049486425,0.00008911848,0.000005451626,0.00026871442,0.99766624,0.0007277608],"about_ca_topic_score_codex":0.014355653,"about_ca_topic_score_gemma":0.026694886,"teacher_disagreement_score":0.041415505,"about_ca_system_score_codex":0.0010263316,"about_ca_system_score_gemma":0.0012954192,"threshold_uncertainty_score":0.99956435},"labels":[],"label_agreement":null},{"id":"W7023740763","doi":"","title":"Patrick Decostre Before the CCI Française au Canada - Encouraging first steps and award for Boralex's CSR strategy","year":2021,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate social responsibility; Government (linguistics); Work (physics)","score_opus":0.00888294555807954,"score_gpt":0.21982736633847247,"score_spread":0.21094442078039294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023740763","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009793096,0.011940317,0.6199273,0.01320926,0.009886953,0.0033507713,0.0002655469,0.0008391575,0.3396014],"genre_scores_gemma":[0.16520284,0.0008075401,0.032745156,0.0020585717,0.005241258,0.0007033863,0.00011844043,0.0009049605,0.79221785],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983366,0.000036117934,0.00022548079,0.0006431926,0.00034636987,0.0004121991],"domain_scores_gemma":[0.99873173,0.00014497402,0.00018499127,0.00074426335,0.000074077034,0.00011993214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013428117,0.00031221093,0.00028413767,0.00009160703,0.00027992408,0.00021290116,0.0007711246,0.00018232726,0.00037260432],"category_scores_gemma":[0.00002474853,0.00022926633,0.000074218995,0.00031876625,0.000047469344,0.000108534914,0.000215487,0.00024016111,0.000002619452],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031910333,0.000011995501,0.0013999455,0.0002941775,0.00010149095,0.000031258325,0.00034971756,0.00015544072,9.25409e-7,0.00083551224,0.8447984,0.15201798],"study_design_scores_gemma":[0.00029036633,0.000065541804,0.00071756076,0.00015141744,0.000026056035,0.000017794435,0.00021937085,0.008532968,0.00003298703,0.00016156756,0.98948175,0.0003026021],"about_ca_topic_score_codex":0.784962,"about_ca_topic_score_gemma":0.9939579,"teacher_disagreement_score":0.58718216,"about_ca_system_score_codex":0.00035501842,"about_ca_system_score_gemma":0.0017869705,"threshold_uncertainty_score":0.9349209},"labels":[],"label_agreement":null},{"id":"W7030206018","doi":"","title":"Multicultural and Intercultural Education : Building Canada : Proceedings of the November, 1987 CCMIE National Conference, Edmonton, Alberta /","year":2015,"lang":"en","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multiculturalism; Multicultural education; Work (physics); Cultural diversity; Curriculum","score_opus":0.00826843070242849,"score_gpt":0.21442067954904404,"score_spread":0.20615224884661554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030206018","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033861145,0.0039409837,0.00039758152,0.01675427,0.0011510224,0.0011719394,0.00024143401,0.00016544464,0.9423162],"genre_scores_gemma":[0.550865,0.00014414535,0.0036778103,0.0010513668,0.00045774598,0.00016593486,0.000014534514,0.0001206593,0.4435028],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972431,0.000049385526,0.00043155436,0.0005720144,0.0014719265,0.00023203154],"domain_scores_gemma":[0.9976383,0.0008771678,0.0007693265,0.00021864021,0.00035488687,0.00014167129],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015466775,0.00038086917,0.00030997186,0.00037177556,0.00013260693,0.00029940592,0.0012058809,0.000096431635,0.00022922183],"category_scores_gemma":[0.0010590705,0.0002867976,0.00009322447,0.0006755633,0.00021939562,0.0005810251,0.00066265475,0.000309642,0.000005895127],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002109379,0.00008264874,0.001857212,0.00013045475,0.000118668315,2.7941337e-7,0.002441217,0.000016921973,0.0007980113,0.015932271,0.9781205,0.00048068786],"study_design_scores_gemma":[0.0006716309,0.0000673322,0.018928697,0.0006785032,0.000044837936,0.0000747749,0.00035704882,0.002807027,0.0006522703,0.0005782981,0.9745299,0.00060963654],"about_ca_topic_score_codex":0.91172874,"about_ca_topic_score_gemma":0.99898213,"teacher_disagreement_score":0.51700383,"about_ca_system_score_codex":0.005023157,"about_ca_system_score_gemma":0.066120945,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W7034456777","doi":"","title":"Turkish Exporters to Forge Partnerships in Toronto: Exclusive B2B Event Unveils Opportunities for Canadian Businesses","year":2024,"lang":"en","type":"other","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Forge; Turkish; Event (particle physics)","score_opus":0.09093126886915669,"score_gpt":0.31558075860220797,"score_spread":0.22464948973305127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034456777","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007743126,0.0015718098,0.14025466,0.00901633,0.0061660977,0.001754336,0.000118559234,0.00058452756,0.8405259],"genre_scores_gemma":[0.0053955545,0.00018419753,0.009085778,0.0029296116,0.00074176927,0.00089187635,0.00002995512,0.00036433715,0.9803769],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803424,0.000032480006,0.0003273861,0.0007483704,0.0002601095,0.0005974168],"domain_scores_gemma":[0.9987682,0.00004274371,0.000109514156,0.00065202365,0.000057728925,0.00036975378],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021179096,0.00035972093,0.00035273435,0.00053153257,0.00004930075,0.00022471606,0.000796976,0.0002676971,0.0009233212],"category_scores_gemma":[0.000025205916,0.00035541406,0.000103369974,0.00031246213,0.000030230696,0.0002956877,0.0001725926,0.00011007877,0.000055950135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038720505,0.000009047457,0.000005261368,0.00017913515,0.000037414797,0.00006354692,0.0004529503,0.000005954382,0.0000028261684,0.010100095,0.9674786,0.021661315],"study_design_scores_gemma":[0.00013143929,0.00007775674,0.000015481537,0.0003823329,0.000013970856,0.000009334699,0.0012871237,0.0005032681,0.000058822083,0.0012793888,0.9957638,0.00047729132],"about_ca_topic_score_codex":0.23405175,"about_ca_topic_score_gemma":0.95519143,"teacher_disagreement_score":0.72113967,"about_ca_system_score_codex":0.0015845381,"about_ca_system_score_gemma":0.0011026099,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W7036192545","doi":"","title":"The angel story : a study of the interpretation of Genesis 6:1-4 in the Jewish literature of the Second Temple period","year":2005,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mythology; Interpretation (philosophy); Judaism; Period (music); Character (mathematics); Second Temple period","score_opus":0.0114890663024388,"score_gpt":0.24161443355174733,"score_spread":0.23012536724930854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036192545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905421,0.0017053632,0.0000022025845,0.000073144285,0.0019145769,0.0016042991,0.00021913415,0.000031399315,0.0039077504],"genre_scores_gemma":[0.99823743,0.00005599811,0.00012963114,0.00011596924,0.00004079372,0.00022501619,0.00001134974,0.000047787646,0.0011360133],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99469614,0.0020036546,0.0010144837,0.000676623,0.0012573051,0.00035181217],"domain_scores_gemma":[0.9949886,0.0005993807,0.0015729414,0.0022086662,0.0005891249,0.000041240888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002228817,0.00044089294,0.000510679,0.00023055689,0.0010241459,0.00012806237,0.0040250374,0.0003680993,0.000014230369],"category_scores_gemma":[0.0004648052,0.00024017834,0.00040416117,0.0018073476,0.0001350622,0.0006996225,0.00036929696,0.0015698167,0.0000021600656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007199596,0.0018089283,0.0021369786,0.0014868326,0.0008267664,0.000012423302,0.023171717,0.0011513644,0.056567997,0.029541204,0.00008854716,0.8824873],"study_design_scores_gemma":[0.006587407,0.0033476443,0.50891906,0.0059790113,0.0011277933,0.00016805032,0.07220532,0.005361048,0.29883313,0.03706592,0.05709925,0.0033063453],"about_ca_topic_score_codex":0.00014913332,"about_ca_topic_score_gemma":0.018147308,"teacher_disagreement_score":0.87918097,"about_ca_system_score_codex":0.00041755693,"about_ca_system_score_gemma":0.00013520806,"threshold_uncertainty_score":0.999769},"labels":[],"label_agreement":null},{"id":"W7066362866","doi":"","title":"Histopathology Classification of Colorectal Cancer Whole Slide Images Using Color Features with Deep Residual Transfer Learning","year":2022,"lang":"en","type":"dissertation","venue":"Scholarship at UWindsor (University of Windsor)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Deep learning; Residual; Transfer of learning; Cancer; Histopathology; Pattern recognition (psychology)","score_opus":0.01616819761168677,"score_gpt":0.24778172023931097,"score_spread":0.2316135226276242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066362866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99294156,0.00082095916,0.0037631097,0.00023201297,0.0006553067,0.0004737491,0.00008208006,0.00012850124,0.0009027325],"genre_scores_gemma":[0.9876537,0.00009143498,0.006884083,0.000019978123,0.000057778867,0.000008725029,0.00028864216,0.000062019775,0.004933656],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9967173,0.0005842311,0.0003470139,0.0009810573,0.000938558,0.00043185375],"domain_scores_gemma":[0.997988,0.00014767834,0.0007258079,0.0005207585,0.0004965846,0.00012117013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006231085,0.00040391178,0.0006797077,0.0007251935,0.0009539615,0.000050053837,0.0013877678,0.0005345037,0.0002957238],"category_scores_gemma":[0.000054663462,0.00050414616,0.0002235308,0.001003514,0.00026448525,0.0010683038,0.00020524982,0.0014703231,0.000006131624],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004615378,0.00024929523,0.03462265,0.00070987595,0.00035555396,0.00017868483,0.02710319,0.008676245,0.91106045,0.00073773094,0.0002363141,0.011454656],"study_design_scores_gemma":[0.0022566523,0.001332679,0.89795727,0.00035603516,0.0006064278,0.00010525791,0.010146334,0.0017246754,0.08204411,0.00017231851,0.002229841,0.0010684179],"about_ca_topic_score_codex":0.00071645575,"about_ca_topic_score_gemma":0.0058618183,"teacher_disagreement_score":0.8633346,"about_ca_system_score_codex":0.0010922456,"about_ca_system_score_gemma":0.00071020896,"threshold_uncertainty_score":0.999741},"labels":[],"label_agreement":null},{"id":"W7083866290","doi":"","title":"Fairfax bids $300 million for Toys R Us's Canada business","year":2018,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stalking; Bidding; Set (abstract data type); Government (linguistics)","score_opus":0.011324782002372084,"score_gpt":0.22719950561429983,"score_spread":0.21587472361192775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083866290","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010400492,0.00015795036,0.6056039,0.0003521746,0.0056891595,0.0009995278,0.000532687,0.00047684758,0.38608375],"genre_scores_gemma":[0.0042135813,0.00010991524,0.03632867,0.00078832917,0.0025993676,0.0003669869,0.00039246472,0.00067953713,0.9545211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99503016,0.00025104667,0.0008032079,0.0019808195,0.0008082779,0.0011264563],"domain_scores_gemma":[0.99662566,0.0004188932,0.0007357178,0.0016564459,0.0001792408,0.0003840555],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023046228,0.0010428794,0.0009105886,0.0008760042,0.00007646658,0.00033641004,0.004052334,0.00027694725,0.0023270508],"category_scores_gemma":[0.00011110993,0.001017342,0.00037002168,0.00040642533,0.00041913483,0.00023102255,0.0016357399,0.0005641961,0.000789335],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000125159,0.000055227018,0.00012116044,0.00024902838,0.00030192154,0.000055202057,0.00048336652,0.000021071524,0.000121546465,0.0026965302,0.99312055,0.0026492556],"study_design_scores_gemma":[0.00077773526,0.00042388216,0.0005393135,0.0011272022,0.000055819437,0.00008517209,0.0000127971525,0.01599302,0.0009993826,0.0027743503,0.9761196,0.0010917194],"about_ca_topic_score_codex":0.7562911,"about_ca_topic_score_gemma":0.93932486,"teacher_disagreement_score":0.5692752,"about_ca_system_score_codex":0.00043692015,"about_ca_system_score_gemma":0.00094996224,"threshold_uncertainty_score":0.9999887},"labels":[],"label_agreement":null},{"id":"W7084399024","doi":"10.5281/zenodo.17251206","title":"CANADA 🇨🇦, AUSTRALIA 🇦🇺,UK 🇬🇧 WORK VISAS AVAILABLE CALL OR WHATSAPP MR PETER OBENDE ON ☎(08143870581).","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Confidentiality","score_opus":0.04018357200838084,"score_gpt":0.24891656963546255,"score_spread":0.2087329976270817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084399024","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015541958,0.000117033516,0.013649708,0.0008133883,0.0013718938,0.0007201416,0.0003212998,0.0015342301,0.98145676],"genre_scores_gemma":[0.0033096354,0.00013680334,0.0013783788,0.00071917236,0.00046446943,2.5074058e-7,0.00035890762,0.0031876403,0.9904447],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965984,0.0003497674,0.00035515885,0.001107733,0.00089691085,0.00069202617],"domain_scores_gemma":[0.99755436,0.000047366237,0.00025510445,0.0015052045,0.00036303786,0.0002749034],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003928574,0.00040454135,0.0003329909,0.00050497986,0.0009955247,0.0014202892,0.0031811637,0.00024215809,0.11220241],"category_scores_gemma":[0.0002929598,0.00039813764,0.000076730095,0.0012581772,0.000110984154,0.00020441266,0.0017723999,0.00069618627,0.02715099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004754931,0.00003926627,0.0000013244293,0.00008951629,0.00007485495,0.00005813608,0.000064610314,0.000034488843,0.000032303393,0.001261725,0.98011184,0.01818441],"study_design_scores_gemma":[0.00035000104,0.00019515296,0.00004015146,0.00030572826,0.000017615468,0.000031910553,0.0000107758,0.0001445566,0.00020029985,0.00003851408,0.99825084,0.0004144493],"about_ca_topic_score_codex":0.035764445,"about_ca_topic_score_gemma":0.0044445954,"teacher_disagreement_score":0.085051425,"about_ca_system_score_codex":0.0011215189,"about_ca_system_score_gemma":0.00012822347,"threshold_uncertainty_score":0.99984705},"labels":[],"label_agreement":null},{"id":"W7084750974","doi":"10.7202/1120271ar","title":"Experimenting Hybrid Justice in the Central African Republic: The Special Criminal Court, an Embodiment of Retributive Justice?","year":2024,"lang":"en","type":"article","venue":"Revue québécoise de droit international","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Retributive justice; Mandate; Restorative justice; Opposition (politics); Criminal justice; Transitional justice","score_opus":0.02191260366684475,"score_gpt":0.2856673659422427,"score_spread":0.26375476227539796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084750974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56027377,0.00081088615,0.30418417,0.020444969,0.017904408,0.001124533,0.00015806276,0.00032483248,0.09477439],"genre_scores_gemma":[0.9944566,0.000033506072,0.0015312845,0.00042992362,0.0033406285,0.00005437828,0.000013556943,0.000013006198,0.00012710864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806243,0.00016469703,0.0004141365,0.00043138745,0.00058622647,0.00034114413],"domain_scores_gemma":[0.99880874,0.00035324873,0.00016433954,0.00045500882,0.00015524172,0.00006341459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000897195,0.00014424711,0.00013827483,0.00018360966,0.00012875721,0.00036671158,0.0015302614,0.00004227025,0.000074691765],"category_scores_gemma":[0.00019886182,0.00011686973,0.00010720684,0.00041361013,0.00008762493,0.0005837604,0.00014862057,0.00034967446,0.000010254523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088797584,0.0002430784,0.00010705599,0.00014488833,0.00009726165,0.0002119419,0.031731855,0.0013962574,0.0007092779,0.9283223,0.0054804194,0.03146688],"study_design_scores_gemma":[0.0008876369,0.0006416584,0.021226618,0.0006704127,0.00053338695,0.001852744,0.015256573,0.7656415,0.013741321,0.042501803,0.1362283,0.00081806816],"about_ca_topic_score_codex":0.0006270789,"about_ca_topic_score_gemma":0.00034251297,"teacher_disagreement_score":0.8858205,"about_ca_system_score_codex":0.0009243433,"about_ca_system_score_gemma":0.0003220365,"threshold_uncertainty_score":0.4765809},"labels":[],"label_agreement":null},{"id":"W7087156948","doi":"10.6084/m9.figshare.c.8078704.v1","title":"Understanding cholera dynamics in African countries with persistent outbreaks: a mathematical modeling approach","year":2025,"lang":"en","type":"other","venue":"Figshare","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University; University of Toronto; York University","funders":"","keywords":"Outbreak; Cholera; Basic reproduction number; Transmission (telecommunications); Socioeconomic status; Public health; Pandemic; Cholera vaccine; Epidemiology","score_opus":0.08576378600095498,"score_gpt":0.2463002078499366,"score_spread":0.1605364218489816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7087156948","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.050188e-8,0.00018256728,0.3732457,0.000136931,0.000038306178,0.0003567613,0.010547711,0.00027934602,0.6152126],"genre_scores_gemma":[0.03074195,0.000067700814,0.12151641,0.0010118125,0.00092709245,0.003366305,0.042029884,0.0016938495,0.798645],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853927,0.000028603901,0.00019309839,0.0005540813,0.0003889729,0.0002959992],"domain_scores_gemma":[0.9991835,0.00004807197,0.00013357289,0.0005383807,0.000041323394,0.00005514593],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000059098104,0.00027198438,0.0003189046,0.00038258813,0.00005984065,0.00023015017,0.0006887369,0.00023625598,0.010559008],"category_scores_gemma":[0.000045467576,0.00024487107,0.00007941501,0.00044440394,0.000012543436,0.00012837394,0.00024351051,0.00033454035,0.00020300315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008203328,0.0003138647,0.000010173117,0.00955014,0.00060727366,0.00011462015,0.0050693876,0.06944466,9.8672075e-8,0.058629293,0.853121,0.0030574778],"study_design_scores_gemma":[0.00020979864,0.00003870527,2.5043107e-7,0.0058566583,0.000012525193,0.000013375763,0.00046593763,0.9713691,2.7864368e-7,0.00038571647,0.021352652,0.0002950307],"about_ca_topic_score_codex":0.000042967702,"about_ca_topic_score_gemma":0.00013617516,"teacher_disagreement_score":0.90192443,"about_ca_system_score_codex":0.0018218332,"about_ca_system_score_gemma":0.0002745791,"threshold_uncertainty_score":0.9985552},"labels":[],"label_agreement":null},{"id":"W7095557794","doi":"","title":"Abstracts of the 1st Congress of the International Academy of Digital Pathology","year":2011,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Telepathology; Digital pathology; Digital imaging; Telemedicine","score_opus":0.04467568398213358,"score_gpt":0.2581519895115455,"score_spread":0.21347630552941194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095557794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93712646,0.000018674871,0.009858742,0.0013511436,0.0018154938,0.00013499794,0.000012816526,0.000020465704,0.049661234],"genre_scores_gemma":[0.9989144,0.0000024650803,0.00068447355,0.000082580365,0.000014840414,0.0000016065964,4.7647195e-8,0.0000018348453,0.00029772922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994519,0.000015540498,0.00019752244,0.00009290502,0.0001868651,0.000055273882],"domain_scores_gemma":[0.9994596,0.000034868557,0.00024000475,0.00019984042,0.000056444725,0.000009227804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010787562,0.000037895104,0.00006303481,0.000021644575,0.0000132618015,0.00000608109,0.00113894,0.000041587075,0.000031018128],"category_scores_gemma":[0.0000356461,0.000020515112,0.00005054894,0.00009971643,0.00016432618,0.00019543774,0.00036508133,0.00007839908,0.0000021317448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109448876,0.00077478675,0.23214597,0.00012421467,0.00030199415,0.0000043022246,0.01017129,0.0007213585,0.14666677,0.46322468,0.009863313,0.13589187],"study_design_scores_gemma":[0.00014118162,0.00003073163,0.3087782,0.000020044454,0.000003339219,0.000017437367,0.000033283963,0.0006923604,0.6818875,0.007838633,0.00051825086,0.00003902897],"about_ca_topic_score_codex":0.000023183673,"about_ca_topic_score_gemma":0.000006513836,"teacher_disagreement_score":0.53522074,"about_ca_system_score_codex":0.000012224958,"about_ca_system_score_gemma":0.000027838618,"threshold_uncertainty_score":0.21164529},"labels":[],"label_agreement":null},{"id":"W7098994132","doi":"","title":"23 Copyright © Canadian Academy of Oriental and Occidental Culture The Political Hero Figure in Egyptian Songs: A Linguistic Reading-- With","year":2012,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; HERO; Government (linguistics); Linguistic analysis","score_opus":0.009799844927113263,"score_gpt":0.2565883521317535,"score_spread":0.24678850720464024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098994132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87818205,0.0011504142,0.014164956,0.025363494,0.0017728455,0.0015701337,0.000052918367,0.00029575883,0.07744744],"genre_scores_gemma":[0.99632746,0.0000032901075,0.0020961137,0.0010449683,0.00017990665,0.000010416333,0.0000014335121,0.0000073017573,0.0003291166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989112,0.00004209187,0.00015014435,0.00021026398,0.00020157648,0.0004846917],"domain_scores_gemma":[0.99942917,0.00004607086,0.000042813645,0.00014868764,0.000026214262,0.0003070482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015452542,0.000117053176,0.000117921234,0.000085487845,0.00010287007,0.000053101463,0.0003164282,0.000104726336,0.000030958585],"category_scores_gemma":[0.000033148248,0.00007157961,0.00001972151,0.00031067044,0.00013561966,0.00027762924,0.000066981585,0.00027264684,0.000012838062],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046440364,0.000091414135,0.21178508,0.000056616427,0.000054633754,0.000029509449,0.01979621,0.000013059793,0.00032194392,0.7551657,0.011191309,0.0014481223],"study_design_scores_gemma":[0.0056488197,0.001992478,0.58750063,0.00090013037,0.00019551806,0.0032812958,0.025513358,0.032678064,0.05702608,0.025881045,0.25616202,0.0032205652],"about_ca_topic_score_codex":0.029598748,"about_ca_topic_score_gemma":0.038274493,"teacher_disagreement_score":0.72928464,"about_ca_system_score_codex":0.0002748617,"about_ca_system_score_gemma":0.00010605114,"threshold_uncertainty_score":0.9792745},"labels":[],"label_agreement":null},{"id":"W7103143665","doi":"10.70251/hyjr2348.365360","title":"Hybrid Supervised-Unsupervised CycleGAN for Virtual HER2 Immunohistochemistry from Hematoxylin and Eosin Stains","year":2025,"lang":"","type":"article","venue":"American journal of student research.","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brantford Energy (Canada)","funders":"","keywords":"H&E stain; Pattern recognition (psychology); Immunohistochemistry; Digital pathology; Fidelity; Breast cancer; Categorization","score_opus":0.03977468107641352,"score_gpt":0.3878409918000749,"score_spread":0.3480663107236614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103143665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8797798,0.005951719,0.10784081,0.0042429,0.0011706669,0.0007478435,0.00006901784,0.00002992357,0.00016730899],"genre_scores_gemma":[0.99024487,0.003447706,0.00497451,0.00033188728,0.0006146608,0.00006160867,0.0000040581294,0.000053072807,0.00026762538],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.992682,0.00090761913,0.0016865474,0.0010343754,0.002451595,0.0012378874],"domain_scores_gemma":[0.9932154,0.0019799056,0.0008291806,0.0011383017,0.0022337192,0.00060349336],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003936831,0.00052269315,0.0012206705,0.0008753804,0.0009399882,0.0010836268,0.003183599,0.00011662237,0.000041815536],"category_scores_gemma":[0.00045573062,0.00052805536,0.00043485654,0.0015139346,0.0021619902,0.00085094164,0.0015624913,0.0018643116,0.000007895623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022602642,0.0012685667,0.0048008002,0.00025001023,0.0017574735,0.000282626,0.007961777,0.00019130949,0.12533171,0.0010040796,0.0064980937,0.84839326],"study_design_scores_gemma":[0.03323155,0.049754225,0.09662922,0.0103239035,0.0012542332,0.0010126788,0.114770986,0.06896932,0.5719592,0.020241823,0.027006287,0.0048466013],"about_ca_topic_score_codex":0.0007335585,"about_ca_topic_score_gemma":0.000018100573,"teacher_disagreement_score":0.8435467,"about_ca_system_score_codex":0.00156326,"about_ca_system_score_gemma":0.0021973306,"threshold_uncertainty_score":0.9999533},"labels":[],"label_agreement":null},{"id":"W7114779469","doi":"10.48550/arxiv.2512.08243","title":"Residual-SwinCA-Net: A Channel-Aware Integrated Residual CNN-Swin Transformer for Malignant Lesion Segmentation in BUSI","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Discriminative model; Robustness (evolution); Encoder; Residual; Pattern recognition (psychology); Pixel","score_opus":0.08994713190645673,"score_gpt":0.22913005510070744,"score_spread":0.1391829231942507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114779469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09894153,0.00016974683,0.89177644,0.0007781183,0.0028215875,0.0038897132,0.00039065554,0.00031382983,0.0009183751],"genre_scores_gemma":[0.987395,0.002189201,0.0020801332,0.00024689373,0.00030759463,0.0000697877,0.00028357207,0.00007577445,0.0073520457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99212307,0.0009867075,0.001278235,0.0038146973,0.0004366356,0.0013606353],"domain_scores_gemma":[0.9955886,0.0005587904,0.00085595984,0.001721112,0.0009489801,0.0003265747],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017356733,0.00122161,0.0011573664,0.0021553454,0.00082025834,0.00034281335,0.0025514315,0.0013254777,0.00009821611],"category_scores_gemma":[0.00010082098,0.0014868289,0.00053515984,0.003911555,0.0003298218,0.0015788298,0.0008863331,0.0017711283,0.000058207163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004634581,0.0009819808,0.0012002102,0.0024181567,0.00064696046,0.0005802296,0.009288919,0.9289226,0.0026171135,0.012603365,0.0023528473,0.03375304],"study_design_scores_gemma":[0.0076625184,0.0012307948,0.0025227373,0.00400802,0.000571998,0.000019423198,0.0041381055,0.9112557,0.037094247,0.026493508,0.0023839357,0.002618994],"about_ca_topic_score_codex":0.0027601141,"about_ca_topic_score_gemma":0.0038396385,"teacher_disagreement_score":0.8896963,"about_ca_system_score_codex":0.0033283453,"about_ca_system_score_gemma":0.0021537123,"threshold_uncertainty_score":0.99997103},"labels":[],"label_agreement":null},{"id":"W7115164551","doi":"10.18280/isi.301011","title":"Learning Framework Designed for Early Prediction of Breast Cancer Metastasis Consuming Genomic, Transcriptomic, and Epigenomic Profiles","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Epigenomics; Metastasis; Cancer","score_opus":0.01510023406752941,"score_gpt":0.24377375479734262,"score_spread":0.2286735207298132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115164551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35033503,0.0020114728,0.6440817,0.00013410095,0.001278523,0.0014692091,0.0004187291,0.00013360585,0.00013760242],"genre_scores_gemma":[0.9716861,0.0011269297,0.026298083,0.000090779744,0.00012396128,0.00055939396,0.000028507096,0.000028809627,0.000057425073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966018,0.0002537465,0.0017015709,0.0004939408,0.00033217485,0.000616764],"domain_scores_gemma":[0.9969822,0.0004043212,0.0012098681,0.00042824485,0.0008498906,0.00012547779],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012695976,0.0004649682,0.00069133413,0.000848977,0.0009954149,0.0006987885,0.00050418905,0.00042845102,0.000032160584],"category_scores_gemma":[0.0002345223,0.00053330784,0.0002126081,0.0009334912,0.00047720372,0.0048873136,0.00016255723,0.00044182755,0.0000060899215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085565646,0.000047933565,0.016397657,0.005805754,0.0007959253,5.584236e-7,0.04226159,0.0057806955,0.015457406,0.0052898885,0.00009813392,0.9072088],"study_design_scores_gemma":[0.005162747,0.0016462456,0.28635278,0.007746245,0.0015501722,0.00012660933,0.006603973,0.58165216,0.083471045,0.020524103,0.0034999538,0.00166398],"about_ca_topic_score_codex":0.0005308256,"about_ca_topic_score_gemma":0.000016883732,"teacher_disagreement_score":0.9055448,"about_ca_system_score_codex":0.0012174197,"about_ca_system_score_gemma":0.00075117406,"threshold_uncertainty_score":0.9997119},"labels":[],"label_agreement":null},{"id":"W7116735645","doi":"10.1007/978-3-032-13509-4_8","title":"Fuzzy Consensus Clustering for Deep Learning Tuning. Taking Breast Cancer for Medical Diagnosis as a Case","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université du Québec à Rimouski; HEC Montréal","funders":"","keywords":"Deep learning; Artificial neural network; Cluster analysis; Initialization; Fuzzy logic; Medical diagnosis; Supervised learning; Scheme (mathematics)","score_opus":0.018182226762266246,"score_gpt":0.29700454285639305,"score_spread":0.2788223160941268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116735645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016881238,0.0030219858,0.9836353,0.0034607092,0.0031184792,0.0010958634,0.000033784185,0.00024803772,0.005368926],"genre_scores_gemma":[0.878944,0.0024059212,0.061705817,0.010164689,0.034274127,0.00520915,0.00012183714,0.00060261716,0.006571868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972505,0.00008584486,0.00058728096,0.00094594917,0.00041870773,0.0007117022],"domain_scores_gemma":[0.99524367,0.0035125888,0.00058091484,0.00028703987,0.00024948866,0.00012632892],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00058898295,0.0005251373,0.0007188223,0.00022918075,0.0008157979,0.00019261037,0.00063155475,0.0016094582,0.0000660127],"category_scores_gemma":[0.0005902938,0.00058466126,0.00036586207,0.00023174455,0.00016700015,0.00007742071,0.00042073912,0.0016646408,0.0000010712663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114908056,0.000009021006,0.00006532434,0.00017549383,0.0001386924,0.0002791809,0.00082815514,0.059100635,5.104125e-7,0.005974125,0.00063637947,0.93267757],"study_design_scores_gemma":[0.0013492154,0.00014869974,0.000015700643,0.0017017884,0.00016920916,0.00072227616,0.00001598642,0.9187756,0.0000072036187,0.043474726,0.032641362,0.0009782367],"about_ca_topic_score_codex":0.00047818682,"about_ca_topic_score_gemma":0.008146229,"teacher_disagreement_score":0.93169934,"about_ca_system_score_codex":0.00082855084,"about_ca_system_score_gemma":0.00044669272,"threshold_uncertainty_score":0.99968666},"labels":[],"label_agreement":null},{"id":"W7116986978","doi":"10.1109/picc67314.2025.11291491","title":"Optimizing Breast Cancer Classification: A Comparative Study of Filter Pruning, Neuron Pruning, and Knowledge Distillation","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Context (archaeology); Deep learning; Distillation; Breast cancer; Filter (signal processing); Inference; Computational model","score_opus":0.05972236635334169,"score_gpt":0.34341033531652443,"score_spread":0.2836879689631827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116986978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50923705,0.0027637074,0.45921233,0.0016842238,0.0030240216,0.0027762395,0.000025396575,0.00022112837,0.02105592],"genre_scores_gemma":[0.9941579,0.0001436222,0.0025681017,0.00004584776,0.000119944954,0.00014119435,0.0000015515225,0.000016192547,0.0028056584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679685,0.0004737366,0.00086651905,0.0011411852,0.00036065333,0.0003610709],"domain_scores_gemma":[0.99755144,0.00022530506,0.00060157146,0.0008240076,0.00068342796,0.00011424315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039269746,0.00040234308,0.00056913885,0.00041761334,0.00049327716,0.00032197358,0.0005911417,0.00013721312,0.00010500633],"category_scores_gemma":[0.000018744842,0.00040384114,0.00006707872,0.0017006901,0.00026839616,0.00088464905,0.00067144807,0.00037540024,0.00000585488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078137784,0.0043417322,0.14013687,0.0011143545,0.0011277389,0.0000066305884,0.21336293,0.027479034,0.004672268,0.02081429,0.0069070654,0.5792557],"study_design_scores_gemma":[0.0011847604,0.00046091265,0.30917397,0.0003495449,0.00012383946,0.0000071827685,0.0030046338,0.68370336,0.00048931595,0.000071592505,0.0011401685,0.00029074482],"about_ca_topic_score_codex":0.0005855411,"about_ca_topic_score_gemma":0.001141721,"teacher_disagreement_score":0.6562243,"about_ca_system_score_codex":0.0003535059,"about_ca_system_score_gemma":0.00046944266,"threshold_uncertainty_score":0.99984133},"labels":[],"label_agreement":null},{"id":"W7117111041","doi":"10.1016/j.jpi.2025.100537","title":"ADPv2: A hierarchical histological tissue type-annotated dataset for potential biomarker discovery of colorectal disease","year":2025,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Sunnybrook Health Science Centre; Centre Hospitalier de l’Université de Montréal; Institute for Research in Immunology and Cancer; Cegep Edouard Montpetit; Canada Research Chairs; University of Toronto; Université de Montréal; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Economic Development, Job Creation and Trade","keywords":"Digital pathology; Biomarker discovery; Annotation; Colorectal cancer; Biomarker; Biopsy","score_opus":0.015450695761174282,"score_gpt":0.2988720792633532,"score_spread":0.2834213835021789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117111041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17708927,0.00013697064,0.81984913,0.0007625416,0.0016089489,0.00017543818,0.00030037246,0.000013152756,0.00006414542],"genre_scores_gemma":[0.8985279,0.000066440356,0.100602336,0.00055433874,0.00006066797,0.000008815556,0.00010971517,0.000005933939,0.00006382236],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855477,0.00008809648,0.00086977816,0.000086785665,0.00021038487,0.00019019666],"domain_scores_gemma":[0.99856144,0.00019130674,0.00065139827,0.0002578607,0.0002595861,0.00007842889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005230928,0.00011366691,0.00031024907,0.00027977797,0.00007036046,0.000044584813,0.0006001654,0.000119084936,0.000005500885],"category_scores_gemma":[0.00036075443,0.00008899953,0.00010039391,0.0003202996,0.00019803265,0.00073122943,0.00021339062,0.00023516957,0.0000032067326],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020210681,0.003005194,0.011480419,0.00286049,0.0018432279,0.004128882,0.0065610157,0.010727187,0.07551253,0.056731287,0.5695006,0.23743846],"study_design_scores_gemma":[0.015892634,0.012222942,0.1249788,0.000710177,0.0012721898,0.008682436,0.00071519706,0.6148423,0.020865893,0.06368913,0.13442096,0.0017073281],"about_ca_topic_score_codex":8.716561e-7,"about_ca_topic_score_gemma":8.007732e-7,"teacher_disagreement_score":0.72143865,"about_ca_system_score_codex":0.00008869699,"about_ca_system_score_gemma":0.0003744071,"threshold_uncertainty_score":0.36292955},"labels":[],"label_agreement":null},{"id":"W7117360372","doi":"10.71146/kjmr777","title":"A HYBRID DATASET-BASED ENSEMBLE STRATEGY FOR EFFICIENT BREAST CANCER DETECTION","year":2025,"lang":"","type":"article","venue":"Kashf Journal of Multidisciplinary Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Breast cancer; Support vector machine; Cancer; Mammography; Random forest; Feature (linguistics); Breast cancer awareness; Focus (optics)","score_opus":0.08854667192971007,"score_gpt":0.42518389353758873,"score_spread":0.3366372216078787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117360372","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13527192,0.004811777,0.8412651,0.008765001,0.0057498026,0.0020357938,0.001885331,0.000044169163,0.00017110266],"genre_scores_gemma":[0.9929049,0.00038527636,0.004887978,0.00005076346,0.0011335263,0.00019191937,0.000026302861,0.000054485645,0.00036485118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915013,0.0013520743,0.0018165342,0.0011932246,0.0024916946,0.0016452034],"domain_scores_gemma":[0.991194,0.001530399,0.0009572219,0.0013529955,0.0044143056,0.00055109157],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009511979,0.00053513586,0.00081971276,0.0024308055,0.0020170845,0.0008382119,0.0027626378,0.00029284795,0.00008700115],"category_scores_gemma":[0.00032549465,0.0005041546,0.0005034083,0.0026567678,0.00064837054,0.00096023374,0.0011886059,0.0023829695,0.000027811495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008429347,0.0020859889,0.0005352845,0.0014055835,0.00048336998,0.0002839585,0.0004471922,0.34245837,0.06318906,0.00038067487,0.013337774,0.5669634],"study_design_scores_gemma":[0.00475566,0.0027315377,0.0038596052,0.0014410049,0.0001338994,0.00042535667,0.0004564192,0.8737335,0.108050846,0.0016961913,0.0022534705,0.00046251353],"about_ca_topic_score_codex":0.00020864133,"about_ca_topic_score_gemma":0.00017337615,"teacher_disagreement_score":0.857633,"about_ca_system_score_codex":0.0026595504,"about_ca_system_score_gemma":0.006349528,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W7117463490","doi":"10.1016/j.media.2025.103927","title":"Multi-cancer framework with cancer-aware attention and adversarial mutual-information minimization for whole slide image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Israel Innovation Authority; Technion-Israel Institute of Technology; Ministry of Science and Technology, Israel; Israel Science Foundation; University of Toronto; Israel Cancer Association; Israel Cancer Association USA","keywords":"Leverage (statistics); Generalizability theory; Adversarial system; Regularization (linguistics); Scalability; Focus (optics); Construct (python library); Minification","score_opus":0.01122081343523291,"score_gpt":0.30923430122183787,"score_spread":0.29801348778660497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117463490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029382503,0.00010700744,0.98878455,0.007218103,0.00033043002,0.00036622133,0.00003526164,0.00015343181,0.00006675361],"genre_scores_gemma":[0.52147704,0.0006792091,0.47263852,0.002163391,0.0004389001,0.0012795489,0.00039179073,0.000025434563,0.00090617675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982291,0.000081268074,0.00043202142,0.00045436277,0.0005602931,0.00024293987],"domain_scores_gemma":[0.9985404,0.00017312975,0.00027861472,0.000402696,0.0004817386,0.00012340539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039145487,0.00017394837,0.00028965058,0.00047739566,0.00026222307,0.00030231656,0.00036888695,0.00019911263,0.00008561709],"category_scores_gemma":[0.00035132494,0.00015317467,0.00012655352,0.0020837875,0.00013513325,0.0018229235,0.00010036275,0.0002052484,0.000009381133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005782098,0.00038893626,0.025990121,0.0007453057,0.0035733308,0.0000094239695,0.0028693916,0.0035928967,0.0056878603,0.0028395222,0.020415166,0.93330985],"study_design_scores_gemma":[0.0011607965,0.000043728352,0.01783955,0.00012430071,0.0007552353,7.2939775e-7,0.00019209248,0.97496927,0.00071639026,0.00022236138,0.0037917907,0.00018375958],"about_ca_topic_score_codex":0.00037092163,"about_ca_topic_score_gemma":0.00044718536,"teacher_disagreement_score":0.97137636,"about_ca_system_score_codex":0.0002489673,"about_ca_system_score_gemma":0.00024464508,"threshold_uncertainty_score":0.6246282},"labels":[],"label_agreement":null},{"id":"W7117658980","doi":"10.18280/ts.420647","title":"Enhancing Breast Cancer Detection Using Squeeze and Excitation Networks (SENet) with DenseNet Features Extraction","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Extraction (chemistry); Breast cancer; Pattern recognition (psychology); Excitation; Feature extraction","score_opus":0.009446715733300162,"score_gpt":0.2605631389468631,"score_spread":0.251116423213563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117658980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30906722,0.0013843514,0.68705636,0.0003569511,0.0013350182,0.00061071373,0.00000720846,0.000111927926,0.000070286624],"genre_scores_gemma":[0.99351466,0.00044546177,0.004356668,0.00033669267,0.0010626639,0.000110248664,0.000003917145,0.000038917493,0.0001307651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659264,0.00030249186,0.0006704271,0.0011403136,0.00062754325,0.0006665824],"domain_scores_gemma":[0.9984086,0.00017641186,0.00051664835,0.00034423394,0.00039177958,0.00016230639],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060162373,0.00053522666,0.000384164,0.00045569616,0.0009525535,0.0007718335,0.00026994865,0.00030142916,0.00010713798],"category_scores_gemma":[0.000008214088,0.0005485966,0.000092979455,0.0012714554,0.00017481101,0.0014167265,0.00012274215,0.0005835325,0.0000016282752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012655382,0.0001489919,0.0032640335,0.00031924294,0.0003932808,0.000022974342,0.001266781,0.35987654,0.10507043,0.00035224372,0.0001108737,0.5279091],"study_design_scores_gemma":[0.0014900041,0.00035336282,0.17311038,0.00097563915,0.00033003,0.00029376923,0.00023074204,0.7998932,0.022348158,0.00026710882,0.00013948357,0.0005681222],"about_ca_topic_score_codex":0.00153888,"about_ca_topic_score_gemma":0.0043079066,"teacher_disagreement_score":0.68444747,"about_ca_system_score_codex":0.001212773,"about_ca_system_score_gemma":0.00040012112,"threshold_uncertainty_score":0.99969655},"labels":[],"label_agreement":null},{"id":"W7117759112","doi":"10.23950/jcmk/17449","title":"Classification of Combined MLO and CC Mammographic Views Using Vision–Language Models","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Medicine of Kazakhstan","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Preprocessor; Mammography; Digital mammography; Breast cancer screening; Adaptability; Breast cancer; Screening mammography; Recall","score_opus":0.11061802811028439,"score_gpt":0.454633052733089,"score_spread":0.34401502462280464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117759112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5491579,0.0019273438,0.44262403,0.0037204917,0.0014111832,0.00014588596,0.0000010029214,0.000011808087,0.001000354],"genre_scores_gemma":[0.9821032,0.00075709587,0.016708544,0.00022126971,0.0001759516,6.5474035e-7,2.3276333e-7,0.0000060744132,0.000026958594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655604,0.00028694764,0.002284792,0.0002085492,0.00053881994,0.00012482158],"domain_scores_gemma":[0.9960759,0.0009293465,0.0019367739,0.00042254044,0.0005045395,0.00013086434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003508063,0.00011879582,0.0008053651,0.00045295054,0.00004013144,0.000012032309,0.000519838,0.00012844142,0.000006524906],"category_scores_gemma":[0.00083598174,0.00008675792,0.00017358491,0.00074966415,0.00036730067,0.00038072257,0.00009830979,0.00039177886,1.485433e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017242993,0.002409985,0.031929515,0.0009887767,0.0006314448,0.000053620366,0.0027706719,0.00073523447,0.04121804,0.05047277,0.0057023666,0.8613633],"study_design_scores_gemma":[0.02847922,0.013679527,0.16093022,0.008753832,0.00075501297,0.00015830275,0.0020956725,0.6707064,0.004420938,0.10667446,0.0028122903,0.00053414697],"about_ca_topic_score_codex":0.000019704992,"about_ca_topic_score_gemma":0.000009581568,"teacher_disagreement_score":0.8608291,"about_ca_system_score_codex":0.00003471746,"about_ca_system_score_gemma":0.00020376948,"threshold_uncertainty_score":0.35378855},"labels":[],"label_agreement":null},{"id":"W7125592653","doi":"10.1109/ssitcon66133.2025.11342278","title":"Multi-Class Classification of Cervical Pre-Cancerous Lesions using Deep Learning on Brown Multicellular ThinPrep Pap Smear Images","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Colposcopy; Feature (linguistics); Pattern recognition (psychology); Cervical cancer","score_opus":0.04475890881283412,"score_gpt":0.31154029375118564,"score_spread":0.2667813849383515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125592653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09638261,0.0011022441,0.89590585,0.00084172416,0.0022043458,0.00096304587,0.0000054510197,0.00033130366,0.0022634193],"genre_scores_gemma":[0.9162701,0.00037629242,0.08015568,0.00023551987,0.00016533579,0.000048779664,0.000004151066,0.000050198785,0.002693979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994019,0.00094246643,0.0014291686,0.0017805356,0.0009901191,0.00083873066],"domain_scores_gemma":[0.99572563,0.0007425831,0.00089126494,0.0017017076,0.00070995174,0.00022885119],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010000316,0.00061885535,0.0007052577,0.0005934113,0.0009713273,0.00040782872,0.0015083986,0.0005681564,0.00018711375],"category_scores_gemma":[0.00046572014,0.0006457613,0.00033787696,0.0019270238,0.0004584075,0.0009171569,0.00082449516,0.0013465094,0.00006939858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003294056,0.0010412553,0.0065081487,0.0006244404,0.00026240086,0.000012727961,0.0033834635,0.29350618,0.25262767,0.0028761206,0.00009714705,0.43873104],"study_design_scores_gemma":[0.0012631408,0.00034970653,0.031683978,0.0006237391,0.00015476074,0.000006994564,0.0006604878,0.90806484,0.05573701,0.00015196319,0.0007986305,0.00050476537],"about_ca_topic_score_codex":0.0014162643,"about_ca_topic_score_gemma":0.0003030336,"teacher_disagreement_score":0.81988746,"about_ca_system_score_codex":0.0012022645,"about_ca_system_score_gemma":0.0006111951,"threshold_uncertainty_score":0.99959934},"labels":[],"label_agreement":null},{"id":"W7125927771","doi":"10.1109/smc58881.2025.11342812","title":"Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Transformer; Feature (linguistics); Mammography; Architecture; CAD; Feature extraction; Feature learning","score_opus":0.014204633849904478,"score_gpt":0.26594723195691,"score_spread":0.2517425981070055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125927771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02155121,0.0067689535,0.96478057,0.0028182254,0.000967134,0.0024325328,0.00010746598,0.00012288323,0.00045105448],"genre_scores_gemma":[0.7691045,0.0016236771,0.22569855,0.0007784959,0.00009167437,0.00034943692,0.0000073509264,0.00005823376,0.0022881147],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99653864,0.0001487649,0.00070222793,0.0013281237,0.0004899455,0.0007923033],"domain_scores_gemma":[0.998167,0.00016249414,0.00027152605,0.0008080993,0.0003702283,0.00022067226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036447754,0.00065464526,0.00078317826,0.0005944353,0.00031831782,0.00025053654,0.00068266125,0.00019052939,0.00004155859],"category_scores_gemma":[0.00001679111,0.000522369,0.00034034447,0.0013306744,0.0005654516,0.0005161528,0.00012386635,0.00037810783,7.699275e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020075438,0.00043469958,0.00063296664,0.0030942457,0.0010478093,0.000030423493,0.006963599,0.0011802026,0.011589227,0.0027687035,0.0023355589,0.967915],"study_design_scores_gemma":[0.0154132545,0.0050183684,0.0010170004,0.0032556476,0.0008570502,0.00037457867,0.0008472176,0.11671125,0.74318284,0.0072299466,0.103485025,0.0026078376],"about_ca_topic_score_codex":0.00027920757,"about_ca_topic_score_gemma":0.0010025072,"teacher_disagreement_score":0.9653072,"about_ca_system_score_codex":0.00010097447,"about_ca_system_score_gemma":0.0004652174,"threshold_uncertainty_score":0.9997228},"labels":[],"label_agreement":null},{"id":"W7125973950","doi":"10.1109/smc58881.2025.11343070","title":"Capsule-ConvKAN: A Hybrid Neural Approach for Medical Image Classification","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Pattern recognition (psychology); Image (mathematics); Contextual image classification; Representation (politics); Hierarchy; Feature (linguistics); Feature extraction","score_opus":0.025561587535220413,"score_gpt":0.2940115216184269,"score_spread":0.2684499340832065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125973950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009816835,0.0003767503,0.9468588,0.015531777,0.003901934,0.0013663893,0.000012434838,0.00031837082,0.030651834],"genre_scores_gemma":[0.86332196,0.00009072521,0.12439793,0.003074489,0.00065656146,0.00065172743,0.000023870709,0.00003091239,0.0077518257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958065,0.00020908819,0.00090246194,0.0014849139,0.0008662905,0.0007307376],"domain_scores_gemma":[0.99751145,0.00023848837,0.00024459697,0.0012752974,0.000442042,0.00028811273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013137094,0.00038602194,0.00042440192,0.00031115988,0.00047921413,0.0005834635,0.0018695362,0.00028271283,0.0002321318],"category_scores_gemma":[0.00046474673,0.00038340435,0.0002830995,0.0010258429,0.00036176972,0.00094305264,0.0005102219,0.0005338631,0.000047402435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011426529,0.00043034877,0.00006362466,0.0005305955,0.00012826428,0.000008007051,0.0002966568,0.00012264677,0.0031953193,0.06931443,0.06843836,0.8573575],"study_design_scores_gemma":[0.0013319529,0.00017438881,0.00061179756,0.000045937442,0.00005380325,0.000045871617,0.00009896713,0.97623247,0.011358863,0.0021596444,0.007537097,0.00034918147],"about_ca_topic_score_codex":0.00009942275,"about_ca_topic_score_gemma":0.000011882353,"teacher_disagreement_score":0.97610986,"about_ca_system_score_codex":0.00044962997,"about_ca_system_score_gemma":0.001102417,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W7126080695","doi":"10.1109/bibm66473.2025.11356986","title":"Active Learning for Lesion Segmentation Using Contrastive Learning with Strong Augmentation","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Segmentation; Active learning (machine learning); Pattern recognition (psychology); Annotation; Selection (genetic algorithm); Image segmentation; Sampling (signal processing)","score_opus":0.0337395359083766,"score_gpt":0.32979163853781324,"score_spread":0.29605210262943665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126080695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089448966,0.00008427704,0.9057719,0.00023778116,0.0009717399,0.0016328961,0.0000023575246,0.00018842936,0.001661634],"genre_scores_gemma":[0.93593234,0.00004914604,0.061262522,0.00009399434,0.0001368634,0.00013830606,0.00001999224,0.000032285818,0.0023345465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970545,0.00038135043,0.0005136174,0.0010097037,0.00047179166,0.00056899025],"domain_scores_gemma":[0.997971,0.0005015644,0.0006219374,0.0002076322,0.000609384,0.00008846272],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00050432933,0.00039227167,0.0003553919,0.0004080163,0.0015158192,0.00052243215,0.0002715816,0.00017226256,0.000044517205],"category_scores_gemma":[0.00010159541,0.00039879774,0.00010828295,0.0010345622,0.00012545015,0.0020806792,0.00015555903,0.0005855821,0.0000061317537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011569947,0.00006478337,0.0018632944,0.00013656753,0.00025573178,0.0000017805477,0.003522858,0.395298,0.03025867,0.002250235,0.000024285642,0.5651668],"study_design_scores_gemma":[0.0032932432,0.0013746974,0.0021997117,0.0004983007,0.00021423245,0.0000057158413,0.009793171,0.86951786,0.11224893,0.00023531892,0.00023745386,0.0003813748],"about_ca_topic_score_codex":0.00027874322,"about_ca_topic_score_gemma":0.00008609828,"teacher_disagreement_score":0.8464834,"about_ca_system_score_codex":0.001788154,"about_ca_system_score_gemma":0.00061539473,"threshold_uncertainty_score":0.9998464},"labels":[],"label_agreement":null},{"id":"W7126159215","doi":"10.18280/isi.301217","title":"Automated Breast Cancer Detection in Mammograms Using Optimized Radial Basis Function Neural Network","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Breast cancer; Pattern recognition (psychology); Radial basis function; Function (biology); Mammography","score_opus":0.012872322324759376,"score_gpt":0.24538678959729465,"score_spread":0.23251446727253527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126159215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19526708,0.00077492814,0.7849073,0.00022026013,0.015214423,0.001505456,0.000042370066,0.0013137021,0.00075451535],"genre_scores_gemma":[0.99292654,0.00022990025,0.0053480454,0.0004947753,0.00059366843,0.00030335627,0.000031931155,0.000034875393,0.000036920126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99471825,0.0005670706,0.0021440082,0.000664537,0.0006820634,0.001224074],"domain_scores_gemma":[0.9969918,0.00013697994,0.0012106159,0.00074146595,0.0007389158,0.000180224],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001356651,0.00069005915,0.0007409888,0.0014719741,0.0011610339,0.0017180023,0.00068582,0.0006748205,0.00008657343],"category_scores_gemma":[0.00011709258,0.00080751104,0.0002741225,0.006673306,0.00029494308,0.011580165,0.0003602736,0.0007410629,0.000035280937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006776124,0.00002979839,0.001685582,0.00033003965,0.00009919179,0.0000022702254,0.0011341494,0.49181244,0.00015872889,0.00011987616,0.00016254514,0.50378776],"study_design_scores_gemma":[0.0023165531,0.00015506844,0.046949517,0.0012065361,0.00015561005,0.00010804933,0.0002867822,0.9462934,0.00061163417,0.0007953803,0.00048226464,0.00063919043],"about_ca_topic_score_codex":0.004907865,"about_ca_topic_score_gemma":0.0007677114,"teacher_disagreement_score":0.79765946,"about_ca_system_score_codex":0.0054655396,"about_ca_system_score_gemma":0.0008070921,"threshold_uncertainty_score":0.9994376},"labels":[],"label_agreement":null},{"id":"W7127336508","doi":"10.1109/ccece64018.2025.11364431","title":"Deep Learning Model for Invasive Ductal Carcinoma Detection in Histopathology Images","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Convolutional neural network; Oversampling; Histopathology; Class (philosophy); Invasive ductal carcinoma; Ductal carcinoma; Pattern recognition (psychology); Artificial neural network","score_opus":0.015632246571292863,"score_gpt":0.2531688304669452,"score_spread":0.23753658389565235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127336508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09595188,0.0009645808,0.8966775,0.0007463976,0.002559834,0.0007301066,0.0000012427935,0.00013936454,0.0022291115],"genre_scores_gemma":[0.96687585,0.000116834526,0.026374672,0.00029497067,0.00011376987,0.00028056995,0.0000013240685,0.000022451813,0.0059195715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970931,0.00023765252,0.000630128,0.0011841239,0.00019492627,0.0006600966],"domain_scores_gemma":[0.99855846,0.0003359167,0.00022583104,0.00051317253,0.00029246288,0.00007417995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006155815,0.00033180817,0.00039857483,0.00078623905,0.00043589604,0.00015712908,0.00062626036,0.000321135,0.000017531156],"category_scores_gemma":[0.00042117652,0.00039681557,0.00017175633,0.0010104193,0.00017476706,0.00080881437,0.00044846896,0.0006245381,0.00001562679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000340692,0.00014905592,0.010467623,0.00039242083,0.000025546182,0.00005841434,0.0054608774,0.32674602,0.059708342,0.0043985466,0.00019362211,0.59205884],"study_design_scores_gemma":[0.0009992523,0.0003776838,0.010192525,0.000043713655,0.000029581319,0.000050154842,0.00023386136,0.92742777,0.052032914,0.008215338,0.000078213176,0.0003190046],"about_ca_topic_score_codex":0.00029302918,"about_ca_topic_score_gemma":0.003656249,"teacher_disagreement_score":0.87092394,"about_ca_system_score_codex":0.0014172596,"about_ca_system_score_gemma":0.0005390798,"threshold_uncertainty_score":0.99984837},"labels":[],"label_agreement":null},{"id":"W7127423665","doi":"10.1109/icodt269104.2025.11360745","title":"Cross-Attention Patch Fusion for Few-Shot Colorectal Tissue Generation","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"","keywords":"Pattern recognition (psychology); Classifier (UML); Fusion; Stromal cell; Feature vector; Feature (linguistics); Feature extraction","score_opus":0.03285814838115081,"score_gpt":0.3380748282317676,"score_spread":0.3052166798506168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127423665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18266518,0.00028329343,0.7968223,0.001987775,0.01269971,0.0015276194,0.000015151068,0.00020638257,0.003792583],"genre_scores_gemma":[0.9477699,0.00012699777,0.021121297,0.0005451778,0.0010719213,0.0003647668,0.00004506332,0.000024831128,0.028930046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967431,0.00014167154,0.0007902429,0.0012730563,0.0004640389,0.0005879251],"domain_scores_gemma":[0.9980449,0.00013329276,0.00027062252,0.00068683963,0.0007535239,0.00011080034],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008293185,0.00036561367,0.0003238021,0.00030003546,0.0011281073,0.0012485386,0.0006837212,0.00041640515,0.00043166045],"category_scores_gemma":[0.00010290252,0.000393783,0.00019854605,0.0011362056,0.00013391553,0.0012409673,0.0004137701,0.0002358369,0.00011329375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017573722,0.00019036498,0.0021434592,0.00017791589,0.0000622558,0.0000023038137,0.0003181493,0.0010305062,0.2937921,0.0116865495,0.012495634,0.67792505],"study_design_scores_gemma":[0.0011618114,0.0007259403,0.007860438,0.00006899321,0.000046404344,0.000007281811,0.00002437595,0.65932894,0.3104732,0.001417403,0.018519519,0.00036567808],"about_ca_topic_score_codex":0.00041241094,"about_ca_topic_score_gemma":0.00080122025,"teacher_disagreement_score":0.775701,"about_ca_system_score_codex":0.0006963057,"about_ca_system_score_gemma":0.0004227348,"threshold_uncertainty_score":0.9998514},"labels":[],"label_agreement":null},{"id":"W7130676010","doi":"10.1109/isriti68345.2025.11393356","title":"Enhancing Clinical Interpretability in BI-RADS Classification: Segmentation-Assisted Approach Using U-Net and ResNet50 for Mammography","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Mammography; Segmentation; Pattern recognition (psychology); Confusion; Digital mammography; Breast cancer; Feature (linguistics); Precision and recall","score_opus":0.0845205680795132,"score_gpt":0.38730705736577853,"score_spread":0.30278648928626534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130676010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118282676,0.0007272764,0.8753818,0.00070651603,0.0020908392,0.0016509942,0.0000072487883,0.000096949014,0.0010556926],"genre_scores_gemma":[0.72010434,0.000101769736,0.27907082,0.00032504316,0.00010446723,0.00017013364,0.000004946711,0.000013603062,0.000104878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99441665,0.0009055621,0.0020140558,0.0018089144,0.00033211708,0.0005227042],"domain_scores_gemma":[0.9969421,0.0010857718,0.00045628467,0.0010614338,0.0003038159,0.00015061584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0045072394,0.0003700715,0.00061086024,0.00069109944,0.0003650072,0.00051331456,0.00065500825,0.00040282423,0.000015387735],"category_scores_gemma":[0.00037612178,0.00039816895,0.00025456707,0.0026051188,0.0004747828,0.000883744,0.00042237222,0.0005089705,0.0000012624413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005825347,0.0010236334,0.2708313,0.0014235139,0.00027958117,0.000001391177,0.0028816778,0.00046368196,0.006974218,0.009267329,0.00020406807,0.7060671],"study_design_scores_gemma":[0.0014730821,0.00022001563,0.14738789,0.0003024516,0.00008650943,0.000006709474,0.0012044739,0.84464294,0.0025529112,0.0015257036,0.00023002001,0.0003673103],"about_ca_topic_score_codex":0.00021871575,"about_ca_topic_score_gemma":0.00055480446,"teacher_disagreement_score":0.8441792,"about_ca_system_score_codex":0.0005452543,"about_ca_system_score_gemma":0.000584971,"threshold_uncertainty_score":0.999847},"labels":[],"label_agreement":null},{"id":"W7131067922","doi":"10.1109/iccvw69036.2025.00104","title":"TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Pancreatic Tumor in Endoscopic Ultrasound","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Concordia University","funders":"","keywords":"Endoscopic ultrasound; Segmentation; Dice; Ground truth; Pancreatic cancer; Pancreatic tumor; Encoder; Image segmentation; Biopsy","score_opus":0.025892175952233764,"score_gpt":0.3091220691108667,"score_spread":0.28322989315863295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131067922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12891917,0.000826925,0.8554284,0.0024119383,0.0027685624,0.004736017,0.0000061907826,0.0002861796,0.0046165995],"genre_scores_gemma":[0.9496951,0.00010203377,0.034127157,0.0015978562,0.00021050543,0.0014622529,0.0000036664792,0.000041976375,0.012759435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99496496,0.00031926917,0.00118784,0.0017292115,0.00053873926,0.0012599599],"domain_scores_gemma":[0.99668956,0.0015249014,0.0002960804,0.00097202754,0.00026480932,0.00025264532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010555702,0.00060648884,0.00075481815,0.00078209763,0.00053159136,0.0009132603,0.001365994,0.00017739966,0.0003029071],"category_scores_gemma":[0.0010490565,0.00062569964,0.00018362766,0.0027056898,0.00009851431,0.0008307704,0.00055129844,0.0006435591,0.0002237652],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073101296,0.0011158918,0.040128868,0.0027443462,0.00046685635,0.00004970692,0.010689275,0.04749835,0.043806076,0.012012586,0.008808338,0.8319487],"study_design_scores_gemma":[0.011466389,0.008160604,0.10280352,0.007503495,0.0003917284,0.00009244457,0.004339854,0.48680133,0.26146355,0.014224017,0.09908954,0.003663513],"about_ca_topic_score_codex":0.00055043725,"about_ca_topic_score_gemma":0.0006566717,"teacher_disagreement_score":0.82828516,"about_ca_system_score_codex":0.0015944679,"about_ca_system_score_gemma":0.0010602467,"threshold_uncertainty_score":0.9996194},"labels":[],"label_agreement":null},{"id":"W7132930524","doi":"","title":"Nonparametric methods for receiver operating characteristic (ROC) curve analysis in genomic studies and diagnostic medicine","year":2006,"lang":"","type":"dissertation","venue":"TSpace","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Receiver operating characteristic; Gold standard (test); Logistic regression; Nonparametric regression; Pattern recognition (psychology); Inference; Statistical hypothesis testing","score_opus":0.052320674204446846,"score_gpt":0.4439457529746763,"score_spread":0.39162507877022945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132930524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29612583,0.040999524,0.65758634,0.0005505954,0.0026885446,0.0018345453,0.00000931628,0.00007016536,0.0001351853],"genre_scores_gemma":[0.6829847,0.01881755,0.28982955,0.00024151547,0.0011306091,0.0015078918,0.00034322488,0.00015383058,0.0049911095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99460846,0.0008986005,0.0014181286,0.0018932124,0.00043167514,0.0007499274],"domain_scores_gemma":[0.985693,0.011342058,0.0012705283,0.00078908884,0.0007493284,0.00015599273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031602704,0.00083014066,0.002122941,0.0029051655,0.0005075441,0.0002471178,0.0006980105,0.00042061528,0.000038749316],"category_scores_gemma":[0.007943649,0.000822058,0.0002492003,0.0065147085,0.00024515044,0.00038413535,0.00021324882,0.0006586391,0.0000073369984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003229447,0.0002390385,0.021687208,0.0046374323,0.005130655,0.00005877502,0.13396001,0.017288882,0.0128672505,0.00040156386,0.0005830541,0.8028232],"study_design_scores_gemma":[0.002317781,0.0013098238,0.40442148,0.001796848,0.005651227,0.000017185788,0.009849319,0.56906325,0.0017179966,0.0011919698,0.0008441008,0.0018190013],"about_ca_topic_score_codex":0.002685221,"about_ca_topic_score_gemma":0.0021724848,"teacher_disagreement_score":0.8010042,"about_ca_system_score_codex":0.0010331778,"about_ca_system_score_gemma":0.00022468637,"threshold_uncertainty_score":0.999423},"labels":[],"label_agreement":null},{"id":"W7133019661","doi":"","title":"Automated Morphological Grading of Human Blastocysts from Multi-focus Images","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Blastocyst; Grading (engineering); Inner cell mass; In vitro fertilisation; Live birth","score_opus":0.038101182057343454,"score_gpt":0.37251169583166577,"score_spread":0.3344105137743223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133019661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92612606,0.003645779,0.058119122,0.00031936096,0.0068782787,0.00096844183,0.00006595216,0.002376947,0.0015000538],"genre_scores_gemma":[0.97841096,0.00011321031,0.015845876,0.000021377644,0.00034703966,0.000097261356,0.00013027003,0.00010708573,0.004926914],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9950718,0.00031497708,0.0010643617,0.0019049522,0.000941581,0.0007022825],"domain_scores_gemma":[0.9969843,0.00027308642,0.0009866807,0.0012048895,0.00032654713,0.00022447997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042716533,0.00084647024,0.0010409679,0.00057218806,0.00036441174,0.0004345847,0.0016027249,0.0008796056,0.00039895033],"category_scores_gemma":[0.000103772894,0.00086703995,0.00043861527,0.0011178397,0.00026885624,0.0004064629,0.00043520334,0.0012196007,0.00045766265],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013878407,0.00040758264,0.0001570933,0.0006957061,0.0004999275,0.0006095335,0.04132794,0.0007740913,0.9309832,0.0004173242,0.004785824,0.019203035],"study_design_scores_gemma":[0.0011050878,0.0008309415,0.010238753,0.0019120221,0.00036165016,0.000054711974,0.0034617106,0.3550501,0.6240029,0.0015450172,0.0001962226,0.0012409327],"about_ca_topic_score_codex":0.0059653227,"about_ca_topic_score_gemma":0.0004683604,"teacher_disagreement_score":0.354276,"about_ca_system_score_codex":0.00051643304,"about_ca_system_score_gemma":0.00026605386,"threshold_uncertainty_score":0.999378},"labels":[],"label_agreement":null},{"id":"W7133559933","doi":"10.1109/apcit65661.2025.11411228","title":"An Enhanced Architectural Model for Graph based Multiple Instance Learning for Re-Identification of Histopathology Data","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Graph; Data modeling; Feature (linguistics); Graph theory; Pattern recognition (psychology)","score_opus":0.05243623807789964,"score_gpt":0.32988915012708997,"score_spread":0.2774529120491903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133559933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01908014,0.0002377577,0.9760922,0.00081950385,0.0015952919,0.0018081551,0.00013154895,0.00015870831,0.00007666591],"genre_scores_gemma":[0.7519342,0.000012240797,0.24652402,0.00023788963,0.0000414115,0.00031490953,0.00011559734,0.000019522415,0.00080021436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636906,0.00020817287,0.0010628703,0.0016233003,0.00025037827,0.00048624256],"domain_scores_gemma":[0.99538946,0.000678003,0.0007310734,0.0025212679,0.0006055183,0.00007468956],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015082748,0.00029065832,0.0004371713,0.0004761382,0.00048865675,0.000120240264,0.0023873472,0.00020060157,0.0000049885725],"category_scores_gemma":[0.0007867791,0.00032853932,0.00015530823,0.00075488817,0.0002474771,0.00095142715,0.0002968238,0.00026279953,8.471406e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005710414,0.00012896667,0.00010941377,0.0003663422,0.000017043827,1.3210423e-7,0.0009208843,0.56384945,0.21501936,0.0019959165,0.000176318,0.21684512],"study_design_scores_gemma":[0.0014575585,0.00036280783,0.00034866162,0.00007388181,0.000049766735,7.0388796e-7,0.000069171794,0.85414046,0.13749324,0.00538467,0.00036580645,0.00025327678],"about_ca_topic_score_codex":0.00006023933,"about_ca_topic_score_gemma":0.0007804903,"teacher_disagreement_score":0.73285407,"about_ca_system_score_codex":0.00022571678,"about_ca_system_score_gemma":0.0005866677,"threshold_uncertainty_score":0.9999167},"labels":[],"label_agreement":null},{"id":"W7135059285","doi":"10.5376/cge.2024.12.0022","title":"Multi-Modal Data Fusion Using AI for Colon Cancer Prediction","year":2024,"lang":"","type":"article","venue":"Cancer Genetics and Epigenetics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Sensor fusion; Fusion; Cancer","score_opus":0.13175558351043754,"score_gpt":0.38840323209361477,"score_spread":0.25664764858317723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135059285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04787041,0.21175593,0.7169887,0.0013767054,0.016941534,0.0012055106,0.0037281597,0.00012503081,0.000008055606],"genre_scores_gemma":[0.57033515,0.31518883,0.10668875,0.0007691001,0.0057438654,0.0003812248,0.00013537145,0.00023231868,0.0005253876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952776,0.00010595954,0.00087293045,0.0022169265,0.0005814133,0.0009452137],"domain_scores_gemma":[0.99717057,0.00011793804,0.00023799621,0.0016112276,0.00047719755,0.00038506725],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00059171766,0.0006170535,0.0004948329,0.0002620259,0.0007399388,0.0011618152,0.0012820837,0.00052906,0.0000632616],"category_scores_gemma":[0.000031588963,0.0006827244,0.00012922201,0.00081382063,0.00031919763,0.0004840417,0.0014893755,0.00049867306,0.0000051115153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009411462,0.00010137845,0.0026824644,0.0015046466,0.00035812205,0.000010987706,0.0016778352,0.06768152,0.032430552,0.00013542015,0.0050292374,0.88829374],"study_design_scores_gemma":[0.00069983734,0.00039464908,0.0015856688,0.00070520386,0.00052974484,0.00001566342,0.000035755358,0.8392043,0.009387751,0.0005120563,0.14633206,0.0005972799],"about_ca_topic_score_codex":0.0007698047,"about_ca_topic_score_gemma":0.0011539737,"teacher_disagreement_score":0.88769644,"about_ca_system_score_codex":0.00073434913,"about_ca_system_score_gemma":0.0018475172,"threshold_uncertainty_score":0.99987507},"labels":[],"label_agreement":null},{"id":"W7139931300","doi":"10.1109/acoit66109.2025.11436564","title":"Prostate Cancer Detection Using Deep Learning with Clinical-Structural Data Integration in an EfficientNetV2B3 Framework","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Deep learning; Prostate cancer; Data integration; Cancer; Deep integration; Artificial neural network","score_opus":0.059207499828270144,"score_gpt":0.40128915651643365,"score_spread":0.3420816566881635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139931300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42949468,0.0004055888,0.566149,0.0001684978,0.0030081708,0.0005720837,0.0000030410822,0.00013541819,0.0000635183],"genre_scores_gemma":[0.93730426,0.0002434163,0.061613787,0.0002559566,0.0003334917,0.00003647392,0.000013557873,0.000032947897,0.00016608162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943336,0.0009522898,0.0012540993,0.0021658547,0.0005703516,0.00072378095],"domain_scores_gemma":[0.9965354,0.0003355112,0.00060671865,0.0019420201,0.00042109776,0.00015925817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017396971,0.00047799383,0.00052201,0.0005530014,0.000682804,0.0010156328,0.0016229344,0.00046373476,0.00006689591],"category_scores_gemma":[0.00037685886,0.00042309915,0.00006618383,0.0037048615,0.00030806958,0.003199959,0.0009225044,0.0021792834,0.000006446364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003402451,0.00005318108,0.06637151,0.00004524684,0.00003545661,0.000005606542,0.0012987332,0.15732267,0.00039023004,0.00024541104,0.000002100027,0.7738896],"study_design_scores_gemma":[0.00078103255,0.000598842,0.04923241,0.00096843473,0.00007731578,0.000010977775,0.0006166584,0.9443862,0.002022921,0.00069428905,0.00014576825,0.00046518786],"about_ca_topic_score_codex":0.002623871,"about_ca_topic_score_gemma":0.01942203,"teacher_disagreement_score":0.7870635,"about_ca_system_score_codex":0.00093862554,"about_ca_system_score_gemma":0.0006569628,"threshold_uncertainty_score":0.9998221},"labels":[],"label_agreement":null},{"id":"W7140012299","doi":"","title":"Deep learning for breast cancer diagnosis","year":2013,"lang":"en","type":"dissertation","venue":"DeustoTeka","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Histopathology; Mammography; Malignancy; Deep learning; Breast cancer; Breast imaging; Convolutional neural network; Magnetic resonance imaging","score_opus":0.011259233603099748,"score_gpt":0.2710075837343116,"score_spread":0.25974835013121184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140012299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048921887,0.009427769,0.89902014,0.0023400255,0.026260551,0.0038768752,0.00009980003,0.002104534,0.007948411],"genre_scores_gemma":[0.813123,0.005590724,0.042796806,0.0011365283,0.005521699,0.040923733,0.0008017573,0.0005425725,0.089563206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983229,0.00004334628,0.00027226526,0.0006570048,0.0003132927,0.0003911922],"domain_scores_gemma":[0.9986684,0.00014244088,0.00031648573,0.00042959122,0.000342731,0.00010038931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012252745,0.00029531142,0.00029001865,0.00019227715,0.0002718434,0.00024260186,0.0007968403,0.00035197055,0.00034452553],"category_scores_gemma":[0.00004708927,0.0003087449,0.00017086828,0.00030856556,0.000015243556,0.00046331654,0.00005760121,0.00042103,0.00014751106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002067358,0.000022790977,0.0005945225,0.00019329661,0.00006552341,0.0000017622868,0.0009134657,0.0011468263,0.00010161598,0.000649219,0.009097419,0.98719287],"study_design_scores_gemma":[0.0022490604,0.0005760176,0.14256239,0.0013510812,0.0004184976,0.00007665263,0.0011048095,0.45506766,0.017602323,0.006031557,0.36889642,0.00406353],"about_ca_topic_score_codex":0.0005717806,"about_ca_topic_score_gemma":0.0006400867,"teacher_disagreement_score":0.9831294,"about_ca_system_score_codex":0.0003152563,"about_ca_system_score_gemma":0.00014343814,"threshold_uncertainty_score":0.99993646},"labels":[],"label_agreement":null},{"id":"W7140093891","doi":"10.1109/iconscept66142.2025.11436939","title":"An Explainable Deep Learning Framework for Breast Cancer Diagnosis using GAN-based Augmentation","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Breast cancer; Cancer; Mammography; MEDLINE","score_opus":0.02516342726657442,"score_gpt":0.3450329635736732,"score_spread":0.31986953630709875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140093891","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018000778,0.0006275701,0.9739419,0.0023317232,0.0035558196,0.0010222612,0.00002218943,0.00027750994,0.00022019942],"genre_scores_gemma":[0.8386254,0.00016281226,0.15781194,0.0013696033,0.0003975714,0.0013348025,0.000004504104,0.000038221042,0.00025515215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675304,0.00027113725,0.00057635724,0.0011852364,0.00042277583,0.0007914682],"domain_scores_gemma":[0.997532,0.0007161415,0.00035980737,0.0006907194,0.0005247903,0.0001765296],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006077673,0.0003962306,0.00035874452,0.00041668254,0.0014605862,0.0009403731,0.00075232954,0.0003344628,0.0009324218],"category_scores_gemma":[0.00010637133,0.00045859773,0.00017693525,0.0018024746,0.000102123595,0.0016254764,0.00007042524,0.00046092735,0.0000074638183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015107385,0.00016123014,0.014937386,0.0002609441,0.00006861971,0.0000018421072,0.0006930021,0.45030954,0.00073724467,0.0052024294,0.0001088096,0.5273679],"study_design_scores_gemma":[0.00088619726,0.00027488804,0.0034211995,0.0006844228,0.00013590141,0.0000026213006,0.00060407614,0.9362715,0.051469523,0.004902834,0.0008866291,0.0004602276],"about_ca_topic_score_codex":0.0019225483,"about_ca_topic_score_gemma":0.00035850506,"teacher_disagreement_score":0.8206246,"about_ca_system_score_codex":0.0018511501,"about_ca_system_score_gemma":0.00078735687,"threshold_uncertainty_score":0.99998087},"labels":[],"label_agreement":null},{"id":"W7160019347","doi":"10.1109/iccv51701.2025.02217","title":"Modaltune: Fine-Tuning Slide-Level Foundation Models with Multi-Modal Information for Multi-Task Learning in Digital Pathology","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Foundation (evidence); Digital pathology; Information system; Key (lock)","score_opus":0.049099432101830515,"score_gpt":0.2897281009137557,"score_spread":0.2406286688119252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160019347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01831205,0.00006549281,0.976992,0.00063689664,0.0010620283,0.001615371,0.000021677168,0.00029411982,0.0010003678],"genre_scores_gemma":[0.75960475,0.000026796242,0.2379593,0.00024369711,0.000045448436,0.00030306264,0.00007430315,0.000023246414,0.0017193768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965379,0.00011124835,0.0012029023,0.00089388323,0.00042080003,0.0008332507],"domain_scores_gemma":[0.9976854,0.0002892325,0.00057237054,0.00058006827,0.0007580542,0.00011490805],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00082405243,0.0005111286,0.00051301875,0.0010227795,0.00058196427,0.0012133562,0.00071151863,0.0003787975,0.00001082526],"category_scores_gemma":[0.00039364523,0.0005194247,0.00013087066,0.0014970931,0.00015810328,0.012535808,0.00047132373,0.0007310631,0.0000396312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022546477,0.00012553562,0.0015589466,0.00015778437,0.000038480743,0.0000038760013,0.0033912545,0.4637149,0.00017281802,0.008078332,0.00002285039,0.52250975],"study_design_scores_gemma":[0.005282074,0.00050750724,0.0025384391,0.0003126286,0.000026214142,0.000024463901,0.0006327825,0.986927,0.00050442305,0.0020092875,0.0006854747,0.00054975244],"about_ca_topic_score_codex":0.00026740585,"about_ca_topic_score_gemma":0.0007569533,"teacher_disagreement_score":0.7412927,"about_ca_system_score_codex":0.0008518957,"about_ca_system_score_gemma":0.0008857936,"threshold_uncertainty_score":0.99982345},"labels":[],"label_agreement":null},{"id":"W7160137672","doi":"10.1109/iccv51701.2025.02166","title":"Unsupervised Histopathological Image Semantic Segmentation with Overlapping Patches Consistency Constraint","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Constraint (computer-aided design); Consistency (knowledge bases); Pattern recognition (psychology); Image (mathematics); Image segmentation","score_opus":0.01675153630037865,"score_gpt":0.25165716492773116,"score_spread":0.2349056286273525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160137672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066115975,0.00049137045,0.8951393,0.0034635928,0.0014178928,0.00089051254,0.0000060447283,0.000356634,0.0321187],"genre_scores_gemma":[0.9092494,0.00013123748,0.08730209,0.0015480693,0.000061222345,0.00007368065,0.0000037786979,0.000015553267,0.0016149296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99638975,0.00033129065,0.00080036774,0.0013047607,0.00054253475,0.0006313222],"domain_scores_gemma":[0.9980184,0.000281626,0.00027688817,0.00089051225,0.0003863812,0.0001461949],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006215969,0.00048054164,0.0005468278,0.0003001194,0.00057543936,0.0005474291,0.00064921775,0.00022512548,0.00040273467],"category_scores_gemma":[0.00008725959,0.00041480604,0.00015989947,0.0012267368,0.0010000787,0.00088591664,0.00034945025,0.0004470214,0.00007730451],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004774491,0.0009805795,0.0194691,0.001538336,0.0004676226,0.0008630257,0.007090487,0.0006075214,0.18608871,0.0915283,0.0021382007,0.6887507],"study_design_scores_gemma":[0.014318203,0.00509894,0.107928745,0.0043197167,0.0012110021,0.001414733,0.017062925,0.68478626,0.13425416,0.022015627,0.0027469234,0.0048427884],"about_ca_topic_score_codex":0.00018008368,"about_ca_topic_score_gemma":0.00008991692,"teacher_disagreement_score":0.84313345,"about_ca_system_score_codex":0.0007746134,"about_ca_system_score_gemma":0.00092570693,"threshold_uncertainty_score":0.99983037},"labels":[],"label_agreement":null},{"id":"W7160449095","doi":"10.1109/iccit68739.2025.11490333","title":"Impact of Stain Normalization and Background Filtering on Deep Learning &amp; Transformer Based Models for Ovarian Cancer Histopathology Classification","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Normalization (sociology); Deep learning; Pattern recognition (psychology); Ovarian cancer; Histopathology","score_opus":0.05890978803688779,"score_gpt":0.34085666667341596,"score_spread":0.2819468786365282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160449095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052147098,0.0003095958,0.9440402,0.0005747895,0.0005912522,0.0008063759,0.00001730773,0.00006883824,0.0014445801],"genre_scores_gemma":[0.9767274,0.00026681717,0.021834252,0.00014823396,0.000051900148,0.0001989794,0.000019819043,0.000024560617,0.0007279932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770224,0.00022128825,0.0006569292,0.0007600298,0.0002288012,0.0004306994],"domain_scores_gemma":[0.9985526,0.00020535583,0.000341255,0.00043324844,0.0003825278,0.00008497931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066281855,0.00030957515,0.00038029364,0.0005133178,0.00036479245,0.00014185594,0.00029693788,0.00025225026,0.00011038248],"category_scores_gemma":[0.000040212177,0.0003157531,0.00017327153,0.0007124329,0.00012974696,0.00086431176,0.0000374954,0.00024857637,0.0000012132143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064865645,0.00011381151,0.0020606788,0.00043816073,0.0000622351,3.728327e-7,0.0015301574,0.65889597,0.023811478,0.019587383,0.000056300876,0.2927948],"study_design_scores_gemma":[0.0013382282,0.00068692793,0.019182496,0.00017030477,0.00006941213,0.0000022331458,0.000069758746,0.97392607,0.001958786,0.0017440177,0.0005845926,0.00026718792],"about_ca_topic_score_codex":0.0008495875,"about_ca_topic_score_gemma":0.0006232456,"teacher_disagreement_score":0.92458034,"about_ca_system_score_codex":0.0011863676,"about_ca_system_score_gemma":0.00053465384,"threshold_uncertainty_score":0.9999294},"labels":[],"label_agreement":null},{"id":"W7160598019","doi":"10.1109/becithcon69222.2025.11504035","title":"Robust Dual-Site Cancer Screening via Multi-Scale Vision Transformer and Rapid Recognition Pipeline","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Pipeline (software); Transformer; Cancer screening; Pattern recognition (psychology); Pipeline transport","score_opus":0.03922805073386172,"score_gpt":0.2864807539172852,"score_spread":0.24725270318342352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160598019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065336935,0.00477373,0.9776242,0.004789776,0.0027144814,0.0008650214,0.000040394803,0.00026356662,0.002395138],"genre_scores_gemma":[0.5766314,0.013519642,0.3925434,0.0038919474,0.0008176971,0.00024122419,0.00003913936,0.000088671855,0.012226822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620956,0.00021063807,0.0008953206,0.0014681183,0.0005018973,0.0007144924],"domain_scores_gemma":[0.99836755,0.00014597965,0.00022118584,0.0005843523,0.00044499474,0.00023592984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008343725,0.00051850034,0.0004905211,0.0005175385,0.00073698297,0.0004914063,0.00033540474,0.0003776948,0.00084307767],"category_scores_gemma":[0.00002169927,0.000526724,0.00018110024,0.001590792,0.0002319589,0.0019364281,0.00022081578,0.0005958473,0.000064307984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015656815,0.00014188433,0.0004355349,0.0001638783,0.00005548044,0.0000043165055,0.0008339248,0.0014607995,0.011143075,0.000012581171,0.0013842974,0.98420763],"study_design_scores_gemma":[0.0028801798,0.00028633315,0.0051126713,0.0009054549,0.00015708293,0.00002653235,0.00010778047,0.938962,0.04371184,0.0001805369,0.0070401295,0.0006294831],"about_ca_topic_score_codex":0.0020940185,"about_ca_topic_score_gemma":0.0038041875,"teacher_disagreement_score":0.9835782,"about_ca_system_score_codex":0.00026814034,"about_ca_system_score_gemma":0.00019119783,"threshold_uncertainty_score":0.9997184},"labels":[],"label_agreement":null},{"id":"W7160640516","doi":"10.1109/becithcon69222.2025.11504068","title":"Lightweight Hybrid Transformer System for Robust and Explainable Multi-Modality Breast Cancer Recognition","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Breast cancer; Pattern recognition (psychology); Transformer; Robustness (evolution); Key (lock)","score_opus":0.03005948691535709,"score_gpt":0.26502470953558555,"score_spread":0.23496522262022845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160640516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035593437,0.0015220356,0.97682,0.008113994,0.0046587773,0.0022342163,0.00040121007,0.0003326074,0.0023577947],"genre_scores_gemma":[0.96325094,0.00093428185,0.028861482,0.00044140147,0.00040354652,0.001425683,0.000013744976,0.000040951738,0.0046279863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963944,0.00016184495,0.00083452096,0.0014490716,0.00033004215,0.0008301137],"domain_scores_gemma":[0.9980353,0.00017631102,0.00023073288,0.0006195166,0.000718681,0.00021941798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008497318,0.00050307426,0.0005752327,0.00031829343,0.0009669381,0.0005699959,0.0005223899,0.00024074226,0.000116377734],"category_scores_gemma":[0.000015801943,0.00049000315,0.00021676184,0.0007886535,0.00015726686,0.0017017446,0.00011167359,0.00028763677,0.000018357397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000573324,0.0003059339,0.00031662293,0.0054898355,0.00036489652,0.000009273293,0.00077034754,0.0010627855,0.0012014526,0.0042782817,0.0038220056,0.98180526],"study_design_scores_gemma":[0.004425771,0.00021267559,0.0019844836,0.0015404164,0.0003456485,0.00016958691,0.00059012976,0.8907625,0.091874234,0.0013393641,0.0058001825,0.000954972],"about_ca_topic_score_codex":0.0018887921,"about_ca_topic_score_gemma":0.0006830868,"teacher_disagreement_score":0.9808503,"about_ca_system_score_codex":0.0012513626,"about_ca_system_score_gemma":0.00058308634,"threshold_uncertainty_score":0.99975514},"labels":[],"label_agreement":null},{"id":"W7160662978","doi":"10.1109/icscss64956.2025.11500988","title":"Ovarian Cancer Detection: A Systematic Review of Deep Learning Models","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Ovarian cancer; Deep learning; Cancer; MEDLINE; Disease","score_opus":0.02332762806050621,"score_gpt":0.2762077904541135,"score_spread":0.2528801623936073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160662978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011896509,0.2109587,0.772648,0.00090357265,0.0019186902,0.0014034654,7.211741e-7,0.0001402204,0.012014777],"genre_scores_gemma":[0.8766935,0.10631262,0.0057116747,0.0022821154,0.00013860111,0.0008851569,4.08357e-7,0.000032564945,0.007943351],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588424,0.0006947421,0.0015660309,0.0007896838,0.0006415147,0.00042377718],"domain_scores_gemma":[0.996916,0.0002229321,0.0008482032,0.001169581,0.0007439036,0.00009939449],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015162836,0.00035221185,0.001194787,0.0003236812,0.00032499604,0.00014727238,0.0010366644,0.00018440804,0.0003215606],"category_scores_gemma":[0.00028055388,0.00033162624,0.00032742153,0.0028879035,0.00008941816,0.0008366516,0.00043637576,0.00050953217,0.000028754086],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010950127,0.00003588113,0.0000065075196,0.90758,0.00028627794,0.0000022429226,0.00041470284,0.011037001,0.0001237097,0.008720216,0.00005033193,0.071732156],"study_design_scores_gemma":[0.00019437616,0.00008794879,0.0000073128203,0.31708655,0.00046455246,0.0000124405,0.0000568913,0.67799115,0.0022830819,0.001527417,0.00007603614,0.00021222307],"about_ca_topic_score_codex":0.00065572746,"about_ca_topic_score_gemma":0.00026523188,"teacher_disagreement_score":0.8766816,"about_ca_system_score_codex":0.000665624,"about_ca_system_score_gemma":0.00041623274,"threshold_uncertainty_score":0.9999136},"labels":[],"label_agreement":null},{"id":"W7161975338","doi":"10.82308/18624","title":"An automated approach for segmenting regions containing invasive ductal breast carcinomas in whole digital slides","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Breast tumor; Open source","score_opus":0.027217594423106232,"score_gpt":0.29407658488545246,"score_spread":0.26685899046234623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161975338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5826093,0.00021369448,0.3864487,0.00017406768,0.0019025425,0.0026084578,0.00013809127,0.0030938562,0.022811292],"genre_scores_gemma":[0.97172123,0.0000010267923,0.024636902,0.000027590502,0.0001689904,0.0002863011,0.0018692758,0.000048150625,0.0012405139],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979123,0.000051031824,0.00043484778,0.00083136506,0.00034849453,0.00042196302],"domain_scores_gemma":[0.9985619,0.00008955836,0.00032569462,0.00050851697,0.0003778593,0.00013648055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031068595,0.00031877527,0.00035617957,0.00036744642,0.00016252814,0.0006812578,0.0007499444,0.0002630871,0.0000015450809],"category_scores_gemma":[0.00007551831,0.00033220949,0.00009507555,0.0004930086,0.000026275082,0.0019245853,0.00007653356,0.0002476943,0.0000056230965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034013824,0.004473831,0.06991493,0.0063676885,0.001863696,0.00047589105,0.250942,0.039418597,0.05751848,0.05524663,0.059230458,0.45114642],"study_design_scores_gemma":[0.0020735636,0.000727109,0.009894529,0.0003463783,0.000051767456,0.0003249181,0.028730085,0.94926494,0.0033801738,0.003591629,0.00018048297,0.0014343929],"about_ca_topic_score_codex":0.0003297756,"about_ca_topic_score_gemma":0.0008734431,"teacher_disagreement_score":0.90984637,"about_ca_system_score_codex":0.000430143,"about_ca_system_score_gemma":0.0006404018,"threshold_uncertainty_score":0.999913},"labels":[],"label_agreement":null},{"id":"W7163753538","doi":"10.2196/86278","title":"Intra-System Repeatability of S-Detect for Breast Ultrasound Classification on Identical Static Images: A Single-Center Retrospective Repeatability Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Repeatability; Ultrasound; Retrospective cohort study; Breast MRI; Reproducibility","score_opus":0.019061644292273385,"score_gpt":0.30532333810763557,"score_spread":0.2862616938153622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163753538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37006912,0.0000033452884,0.62385076,0.00036685774,0.000634025,0.0029899075,0.000070241986,0.0002910167,0.0017247102],"genre_scores_gemma":[0.99063116,0.0000021582193,0.008527832,0.00014713264,0.00005347238,0.0006007931,0.000008544184,0.000010214329,0.000018676576],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956977,0.00027942634,0.0018659345,0.00051480223,0.0012753304,0.00036683696],"domain_scores_gemma":[0.99570256,0.0011384538,0.00058192725,0.0018077999,0.0005786929,0.00019054729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003031758,0.00025593303,0.0005339607,0.0002086076,0.00015731207,0.00015572764,0.0010457403,0.00019746147,0.000022883904],"category_scores_gemma":[0.002301641,0.00022377836,0.00016836921,0.00075762154,0.00030904845,0.00068722764,0.0003150484,0.0004930941,0.000014142823],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027899335,0.016433096,0.30504024,0.013826122,0.0011377677,0.00002183594,0.05855214,0.000124748,0.0014269021,0.05848948,0.0039300085,0.53822774],"study_design_scores_gemma":[0.010195393,0.005697761,0.66770744,0.0023441652,0.00018866899,0.0002757446,0.027774516,0.25902036,0.008824553,0.016301595,0.00048291378,0.0011869112],"about_ca_topic_score_codex":0.000022155133,"about_ca_topic_score_gemma":0.000023134295,"teacher_disagreement_score":0.6205621,"about_ca_system_score_codex":0.0013966076,"about_ca_system_score_gemma":0.00031752026,"threshold_uncertainty_score":0.9125417},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W767089542","doi":"10.1007/978-3-642-59327-7_59","title":"A model for nonrigid mammogram registration using mutual information","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mutual information; Centroid; Artificial intelligence; Similarity (geometry); Image registration; Similarity measure; Computer vision; Computer science; Pattern recognition (psychology); Point (geometry); Mathematics; Image (mathematics)","score_opus":0.06273049849350364,"score_gpt":0.2681507355187877,"score_spread":0.20542023702528406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W767089542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020207053,0.000015980106,0.7631818,0.00010876691,0.00043669456,0.0004715138,0.0000097322045,0.0001599742,0.23561354],"genre_scores_gemma":[0.0011025727,0.00003296577,0.7170428,0.0011691347,0.00020290742,0.00006163307,0.00006262563,0.000038531227,0.28028682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875504,0.0000058219985,0.00041707265,0.00029560307,0.0003328341,0.00019360702],"domain_scores_gemma":[0.99877137,0.000025597816,0.00038668577,0.000517706,0.0002421998,0.000056460627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020866557,0.00023581756,0.00018262894,0.00019758451,0.00013045079,0.00026993768,0.00033809082,0.00032205088,0.000015972006],"category_scores_gemma":[0.000013572242,0.0002468911,0.00012911262,0.000046326983,0.00003060001,0.0016737761,0.00005486655,0.00016434696,0.000034218927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016083994,0.0000054256243,2.3662417e-7,0.00007045638,0.000027380669,5.1389355e-7,0.00021719017,0.013665604,0.000025185609,0.9142493,0.009717578,0.062005036],"study_design_scores_gemma":[0.00016339676,0.00006301983,1.0714096e-7,0.000028397966,0.00001535351,0.000019221237,0.0000020719217,0.8244292,0.000077146986,0.05505519,0.119900644,0.0002462651],"about_ca_topic_score_codex":0.0000139159065,"about_ca_topic_score_gemma":0.000045139812,"teacher_disagreement_score":0.8591941,"about_ca_system_score_codex":0.00034217013,"about_ca_system_score_gemma":0.0002335425,"threshold_uncertainty_score":0.99999833},"labels":[],"label_agreement":null},{"id":"W812606030","doi":"10.1515/jaiscr-2015-0005","title":"Web–Based Framework For Breast Cancer Classification","year":2014,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Soft Computing Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Support vector machine; Breast cancer; Feature vector; Malignancy; Feature (linguistics); Feature extraction; Fuzzy logic; Cancer; Medicine; Pathology; Internal medicine","score_opus":0.1701775737704979,"score_gpt":0.43462374791236885,"score_spread":0.264446174141871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W812606030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035443053,0.00013115456,0.95778704,0.0056806104,0.0007547779,0.00014108533,0.000001842023,0.000029682697,0.00003076329],"genre_scores_gemma":[0.92324364,0.000044587137,0.07546544,0.00014481053,0.0010791468,0.000005392127,1.4106412e-7,0.0000102819495,0.0000065859545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792665,0.00024890623,0.0005375916,0.00027690936,0.00064187223,0.00036804067],"domain_scores_gemma":[0.9956908,0.002249973,0.00029435407,0.00026054794,0.0013595514,0.00014475778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046311263,0.0001020098,0.000198127,0.00036341057,0.00045450605,0.00037208982,0.00069395563,0.00011000722,0.000010751586],"category_scores_gemma":[0.00079827773,0.000089644345,0.000085836466,0.00065303803,0.0001668706,0.00028534466,0.00010562195,0.00062109885,0.00000679535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007495253,0.000052142903,0.00048977917,0.00003518468,0.000011338394,0.0000011201589,0.0003495189,0.0039786776,0.0019656483,0.061506614,0.00020266752,0.93133235],"study_design_scores_gemma":[0.00004669304,0.0003199404,0.0013901194,0.00018834393,0.0000046305436,0.000021020294,0.00016000401,0.8703969,0.005861871,0.120676756,0.0008371091,0.00009660668],"about_ca_topic_score_codex":0.000020829899,"about_ca_topic_score_gemma":0.000011077174,"teacher_disagreement_score":0.93123573,"about_ca_system_score_codex":0.00013326803,"about_ca_system_score_gemma":0.00033242657,"threshold_uncertainty_score":0.36555904},"labels":[],"label_agreement":null},{"id":"W89051845","doi":"10.4018/978-1-59904-849-9.ch176","title":"Neural Network-Based Visual Data Mining for Cancer Data","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Cancer; Medicine; Breast cancer; Lung cancer; Colorectal cancer; Stomach cancer; Oncology; Internal medicine","score_opus":0.08437902227365873,"score_gpt":0.3351798944940671,"score_spread":0.25080087222040837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W89051845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016120192,0.0032732908,0.5165245,0.0009177522,0.0075675924,0.0016363701,0.0028050886,0.0009679179,0.4662914],"genre_scores_gemma":[0.06537787,0.00015502307,0.62871677,0.041450586,0.04363896,0.00053526496,0.003706661,0.00089364103,0.2155252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636674,0.000028828292,0.0005047567,0.0018505687,0.0005872193,0.00066187815],"domain_scores_gemma":[0.99473304,0.00011932561,0.00044902152,0.004376979,0.00013963279,0.00018199583],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00036726633,0.0005404727,0.00052018196,0.00006058795,0.00023323114,0.0003510256,0.006163794,0.0003973311,0.000012464953],"category_scores_gemma":[0.000025935109,0.00057779055,0.00011288639,0.0000515303,0.00008821028,0.00043792636,0.0022090683,0.0003163513,0.00001668715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078919176,0.0000088790275,0.000011550168,0.000045141744,0.00009723978,0.00003244814,0.000009568967,0.0014814843,0.0000032417151,0.12471444,0.081695765,0.7918213],"study_design_scores_gemma":[0.00065042335,0.0002756134,0.000017977025,0.00032332202,0.00014238879,0.000025580015,9.2688083e-7,0.55272746,0.000013791395,0.03245869,0.41253725,0.0008266069],"about_ca_topic_score_codex":0.00016103842,"about_ca_topic_score_gemma":0.0011171665,"teacher_disagreement_score":0.7909947,"about_ca_system_score_codex":0.000414187,"about_ca_system_score_gemma":0.00085265696,"threshold_uncertainty_score":0.99966735},"labels":[],"label_agreement":null},{"id":"W899273498","doi":"10.1007/978-3-319-18305-3_8","title":"Classification of Malignant and Benign Tumors","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine","score_opus":0.0585317790347011,"score_gpt":0.25657762816176277,"score_spread":0.19804584912706166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W899273498","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045082925,0.0004700775,0.14763938,0.00031693923,0.0003186629,0.00017654263,0.0000042982483,0.00010696722,0.85092205],"genre_scores_gemma":[0.10354851,0.00026917458,0.029965054,0.00010703849,0.00022849008,0.000016378684,0.0000082551815,0.000049304115,0.8658078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907506,0.0000083059285,0.00022855969,0.00032997545,0.00027588237,0.00008221014],"domain_scores_gemma":[0.99906737,0.000023423194,0.00021942772,0.00047678797,0.00015388044,0.000059117738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001889437,0.00012945243,0.00018121485,0.00011438016,0.000022129825,0.000027486383,0.0003069145,0.00013531138,0.000041729647],"category_scores_gemma":[0.000005992223,0.00011527031,0.000033532888,0.000028055767,0.00006344644,0.00014674128,0.000138568,0.00010354793,0.000028433815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023873445,0.0000023060056,0.000006371097,0.000020045436,0.000009181059,0.0000016238001,0.00005720625,0.0000018204507,0.00019792965,0.95038635,0.0033867068,0.045928065],"study_design_scores_gemma":[0.00038764995,0.0005013701,0.0010607574,0.0003302958,0.000042491505,0.00009561404,0.00002603973,0.014528508,0.0022108206,0.6512796,0.32876676,0.0007700255],"about_ca_topic_score_codex":0.000020922851,"about_ca_topic_score_gemma":0.00001580028,"teacher_disagreement_score":0.32538006,"about_ca_system_score_codex":0.00008255668,"about_ca_system_score_gemma":0.00010916162,"threshold_uncertainty_score":0.47005868},"labels":[],"label_agreement":null},{"id":"W9776825","doi":"","title":"Diagnostic accuracy of commercial system for computer-assisted detection (CADx) as an adjunct to interpretation of mammograms.","year":2005,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Mammography; Radiology; Biopsy; Ultrasound; Asymptomatic; Breast cancer; Concordance; Breast cancer screening; Cancer; Pathology; Internal medicine","score_opus":0.020138631624027646,"score_gpt":0.2573913566510993,"score_spread":0.23725272502707165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9776825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2612163,0.000021995169,0.7359635,0.00018199673,0.0010599354,0.0013492284,0.000007442572,0.00012498457,0.000074583644],"genre_scores_gemma":[0.97494054,0.0000021071123,0.023100141,0.00010853303,0.00029306102,0.0015304196,0.000004554924,0.000015211442,0.0000054272077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984873,0.00011950782,0.00049021386,0.00035313633,0.0002757715,0.00027408195],"domain_scores_gemma":[0.9981556,0.0006317245,0.00035985472,0.00045349062,0.00026658105,0.00013274967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048617163,0.00014063314,0.00026360754,0.00023297615,0.00007050281,0.000061397215,0.0005385042,0.0000839851,9.122203e-7],"category_scores_gemma":[0.00036025172,0.00014671449,0.00010255568,0.0005033334,0.000031442196,0.00064900424,0.00011153261,0.00007876838,0.0000049429254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011819069,0.000084309824,0.00022395253,0.0001117146,0.000022396285,4.0185517e-7,0.0005693377,0.0021273359,0.00031453327,0.00023079025,0.00004629168,0.99615073],"study_design_scores_gemma":[0.0017964811,0.0014206846,0.3932811,0.00018565296,0.00008701661,0.000053406064,0.00014698524,0.459917,0.1408249,0.0002165033,0.0016024536,0.00046779934],"about_ca_topic_score_codex":0.00020654831,"about_ca_topic_score_gemma":0.00045535294,"teacher_disagreement_score":0.99568295,"about_ca_system_score_codex":0.00029777642,"about_ca_system_score_gemma":0.0000354525,"threshold_uncertainty_score":0.59828436},"labels":[],"label_agreement":null}]}