{"meta":{"query_hash":"8f8a0ffd912f","filters":{"topic":"Multimodal Machine Learning Applications"},"cohort_total":476,"direct_labels_cover":3,"predictions_cover":476,"exported":476,"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/8f8a0ffd912f","api":"https://metacan.xera.ac/api/v1/cohort?topic=Multimodal+Machine+Learning+Applications"},"results":[{"id":"W1479686495","doi":"10.1109/crv.2015.33","title":"Latent SVM for Object Localization in Weakly Labeled Videos","year":2015,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba; Nvidia","keywords":"Computer science; Object (grammar); Artificial intelligence; Support vector machine; The Internet; Computer vision; Class (philosophy); Pattern recognition (psychology); Information retrieval; World Wide Web","score_opus":0.03551878154791596,"score_gpt":0.3047090166105915,"score_spread":0.2691902350626756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1479686495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017460622,0.000016693379,0.97671527,0.0031600585,0.00008023136,0.00040400756,7.282898e-7,0.00022164195,0.0019407326],"genre_scores_gemma":[0.89199686,8.757071e-7,0.10696577,0.0005130284,0.00002462089,0.00013249484,0.0000070634674,0.0000072398275,0.00035204252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924046,0.00004270146,0.00016639437,0.00025144388,0.00013644302,0.00016255591],"domain_scores_gemma":[0.9993652,0.00008094522,0.00004505315,0.0003233212,0.00010737579,0.000078085686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033774183,0.000073238276,0.0000897091,0.00008969987,0.00004066613,0.000064552136,0.0003779018,0.00003983391,0.000006765078],"category_scores_gemma":[0.00015854854,0.00006529202,0.000022915096,0.00037648194,0.000010406184,0.00017854529,0.00008975205,0.000064643966,0.00010379165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033976426,0.00044268914,0.08843295,0.000041913892,0.000020908843,0.0000034733814,0.003051212,0.19712554,0.002377469,0.6325072,0.013203378,0.062759265],"study_design_scores_gemma":[0.00051797245,0.000047311896,0.007353975,0.0000052964806,0.0000014202388,0.0000013187688,0.000009914116,0.98028415,0.0005945592,0.006063374,0.005026675,0.00009403514],"about_ca_topic_score_codex":0.0008607797,"about_ca_topic_score_gemma":0.00017254746,"teacher_disagreement_score":0.8745362,"about_ca_system_score_codex":0.00006549902,"about_ca_system_score_gemma":0.000073038864,"threshold_uncertainty_score":0.26625314},"labels":[],"label_agreement":null},{"id":"W1492731187","doi":"","title":"Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":47,"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; Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Computer science; Recurrent neural network; Mechanism (biology); Artificial intelligence; Frame (networking); Motion (physics); Long short term memory; Artificial neural network; Speech recognition; Machine learning; Natural language processing","score_opus":0.07850502296318435,"score_gpt":0.21182208747209735,"score_spread":0.133317064508913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492731187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41862088,0.00002682246,0.58023965,0.00023001754,0.00022775125,0.00027971534,0.000006046132,0.00023347222,0.00013564655],"genre_scores_gemma":[0.96861124,0.000014703696,0.030474061,0.00007697416,0.00016152386,0.0000068636646,0.00022626758,0.000020118483,0.00040824604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980934,0.00024801306,0.00022784233,0.0010774105,0.00014056487,0.00021273863],"domain_scores_gemma":[0.998232,0.000036274683,0.0004551001,0.0007968558,0.0003084214,0.00017137048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051770976,0.00028907086,0.00024347549,0.00028478669,0.00030135427,0.00038016407,0.0006890387,0.00030309716,0.000004704346],"category_scores_gemma":[0.00007694855,0.00034590025,0.00008487258,0.00038576027,0.00006141107,0.0006804498,0.0011837061,0.00060651253,0.000032485656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027289512,0.00013255523,0.0231298,0.00010600937,0.00008458197,0.000055022156,0.00084332185,0.25190702,0.0030884042,0.7150034,0.0010903688,0.0045322343],"study_design_scores_gemma":[0.00029983715,0.00003913091,0.007332553,0.000038009024,0.000038817907,0.000010014844,0.000033767643,0.8631957,0.00007234571,0.12858896,0.000043838572,0.000306987],"about_ca_topic_score_codex":0.0018310867,"about_ca_topic_score_gemma":0.00043247067,"teacher_disagreement_score":0.6112887,"about_ca_system_score_codex":0.00026012032,"about_ca_system_score_gemma":0.00018384214,"threshold_uncertainty_score":0.9998993},"labels":[],"label_agreement":null},{"id":"W1508012366","doi":"10.1007/11414353_17","title":"Visual Capabilities in an Interactive Autonomous Robot","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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; Robot; Human–computer interaction; Variety (cybernetics); Mobile robot; Embodied cognition; Gesture; Social robot; Context (archaeology); Artificial intelligence; Robot control","score_opus":0.011979985489256283,"score_gpt":0.28657387203121354,"score_spread":0.27459388654195727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508012366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046677017,0.00008713475,0.9897487,0.0007087399,0.0006548096,0.0005092055,0.0000045456113,0.00029343148,0.003325691],"genre_scores_gemma":[0.7730001,0.0000021773903,0.22595678,0.00048722068,0.00026803615,0.000035851812,0.000012770802,0.000035861533,0.00020117567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995945,0.00008741338,0.00064146775,0.0019369789,0.00069877,0.00069041346],"domain_scores_gemma":[0.9972053,0.0006579116,0.00030640312,0.0014579763,0.00021192884,0.00016043546],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071196334,0.0005648549,0.0005527443,0.0012297902,0.00020727831,0.00064927415,0.0033817075,0.0003065452,0.000022694801],"category_scores_gemma":[0.0000954246,0.0005651048,0.000103831604,0.00065610296,0.0006793162,0.0010396505,0.0011553717,0.0014274103,0.000061185725],"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":[0.0000062006443,0.00013485634,0.0015115214,0.000024036539,0.0000048987777,0.000049352784,0.0020953405,0.5029235,0.00021529626,0.0133248875,0.000005869331,0.47970423],"study_design_scores_gemma":[0.00021511833,0.00019834857,0.01006773,0.00014310036,0.0000030525694,0.000030640535,4.168335e-7,0.9266145,0.00030598466,0.06155525,0.00024396915,0.0006218484],"about_ca_topic_score_codex":0.0013655142,"about_ca_topic_score_gemma":0.0011123555,"teacher_disagreement_score":0.7683324,"about_ca_system_score_codex":0.0007955766,"about_ca_system_score_gemma":0.0005837839,"threshold_uncertainty_score":0.99968004},"labels":[],"label_agreement":null},{"id":"W1514535095","doi":"10.48550/arxiv.1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7525,"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; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Visualization; Gaze; Object (grammar); Backpropagation; Salient; Sequence (biology); Object detection; Machine translation; Image (mathematics); Artificial neural network; Machine learning; Computer vision; Pattern recognition (psychology)","score_opus":0.06664802413473758,"score_gpt":0.20829710166008256,"score_spread":0.14164907752534497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514535095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5765283,0.000003825287,0.42278194,0.00017023664,0.00003051764,0.00008192445,5.614042e-7,0.00009355377,0.00030913553],"genre_scores_gemma":[0.9933254,0.0000034502477,0.0062612994,0.000052333617,0.000051898132,9.563591e-7,0.00001289173,0.000008030492,0.00028371587],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991837,0.00008010042,0.00007481401,0.00043778837,0.00007375015,0.0001498543],"domain_scores_gemma":[0.99937713,0.000020666499,0.00007385798,0.0002710008,0.00012124987,0.00013607212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013680047,0.00010826122,0.00008155902,0.00009946906,0.00014220257,0.00010403552,0.00022224092,0.000042093154,0.000004290949],"category_scores_gemma":[0.0000135803,0.0001083492,0.000021744185,0.0003659019,0.000067433946,0.00077178667,0.00011759835,0.00011777642,0.00005563188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014719277,0.0005047251,0.40636647,0.000040646126,0.00010327438,0.00029567053,0.0014399445,0.2617693,0.05902739,0.25144026,0.0007745034,0.018090619],"study_design_scores_gemma":[0.00048896205,0.00010676858,0.052330166,0.000003246952,0.000014978267,0.000023004397,0.000043287637,0.94628364,0.00012256167,0.0004003482,0.000047159254,0.00013588986],"about_ca_topic_score_codex":0.00029118662,"about_ca_topic_score_gemma":0.000052651663,"teacher_disagreement_score":0.68451434,"about_ca_system_score_codex":0.000062730775,"about_ca_system_score_gemma":0.00003012166,"threshold_uncertainty_score":0.44183522},"labels":[],"label_agreement":null},{"id":"W1566289585","doi":"10.1109/iccv.2015.11","title":"Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2068,"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; University of Toronto","funders":"","keywords":"Computer science; Reading (process); Context (archaeology); Semantics (computer science); Sentence; Embedding; Object (grammar); Artificial intelligence; Feeling; Natural language processing; Character (mathematics); Linguistics; Psychology; History","score_opus":0.024420724676901304,"score_gpt":0.3090277660838301,"score_spread":0.2846070414069288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566289585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120354794,0.0021745295,0.84476733,0.006594077,0.0006695795,0.0010190053,0.000053715536,0.0014194427,0.022947527],"genre_scores_gemma":[0.87112963,0.000152503,0.12343534,0.00073606,0.0001755393,0.0002914602,0.00008987161,0.00006028272,0.003929331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731475,0.00022400837,0.00041803974,0.0011606583,0.00048011725,0.00040239556],"domain_scores_gemma":[0.998151,0.00029267304,0.0002892672,0.00077265594,0.00017829756,0.00031610267],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010235427,0.00045582006,0.00047078548,0.00027997268,0.0005583891,0.000858435,0.0008490751,0.00026189163,0.0000093571625],"category_scores_gemma":[0.00017083062,0.00044572228,0.00006360257,0.000107676344,0.00013409296,0.00040828553,0.0027421368,0.0010686829,0.000011887476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003278217,0.0003801357,0.010736843,0.0012685218,0.0008519614,0.000044789173,0.11640099,0.008964827,0.00820666,0.21229142,0.12909101,0.5117301],"study_design_scores_gemma":[0.0007954944,0.00012130501,0.0037490872,0.00039816136,0.00009660522,0.00006788321,0.0018372613,0.92682767,0.0006957258,0.020715248,0.042895585,0.0017999754],"about_ca_topic_score_codex":0.003569749,"about_ca_topic_score_gemma":0.000054533935,"teacher_disagreement_score":0.91786283,"about_ca_system_score_codex":0.00014497577,"about_ca_system_score_gemma":0.00022475312,"threshold_uncertainty_score":0.99979943},"labels":[],"label_agreement":null},{"id":"W1575833922","doi":"10.48550/arxiv.1505.02074","title":"Exploring Models and Data for Image Question Answering","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":390,"is_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; Image (mathematics); Question answering; Suite; Artificial intelligence; Segmentation; Image segmentation; Simple (philosophy); Object (grammar); Baseline (sea); Information retrieval; Pattern recognition (psychology); Machine learning; Data mining","score_opus":0.4143372677061843,"score_gpt":0.2670283867265147,"score_spread":0.1473088809796696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1575833922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24512102,0.00000989836,0.754043,0.00015781855,0.00004465641,0.00010608096,0.000005056726,0.00014598534,0.0003665392],"genre_scores_gemma":[0.93428123,0.000017418082,0.065571904,0.000020179754,0.000026600552,0.0000019094336,0.000010715545,0.000006677922,0.00006334646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992381,0.000033020828,0.00006261292,0.0004899461,0.000035542715,0.00014082303],"domain_scores_gemma":[0.99887276,0.00006626145,0.000042933785,0.0008240041,0.00007390001,0.00012015222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029637528,0.00007613286,0.0000737406,0.00007188523,0.00010408173,0.00006881995,0.00079829467,0.000021871194,4.3984875e-7],"category_scores_gemma":[0.00006297644,0.00008982278,0.000013939852,0.00022822853,0.00003062182,0.0023542338,0.00057214056,0.00007490896,0.000010663997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000152110015,0.00003762898,0.0014577103,0.000017676703,0.000013730737,0.00001318548,0.0004711199,0.2112447,0.00032212338,0.77983767,0.00011043613,0.0064588143],"study_design_scores_gemma":[0.00029568723,0.000021315456,0.00089130574,0.0000074934205,0.000007883396,0.000002769667,0.000051798972,0.9743403,0.000042710584,0.023840511,0.0003950604,0.000103157574],"about_ca_topic_score_codex":0.00031354433,"about_ca_topic_score_gemma":0.000014076748,"teacher_disagreement_score":0.7630956,"about_ca_system_score_codex":0.000039037866,"about_ca_system_score_gemma":0.000030415145,"threshold_uncertainty_score":0.3662867},"labels":[],"label_agreement":null},{"id":"W1581862991","doi":"10.1109/tpami.2015.2505297","title":"Saying What You're Looking For: Linguistics Meets Video Search","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","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":"Army Research Laboratory; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology; University of Waterloo; Purdue University","keywords":"Computer science; Natural language processing; Parsing; Sentence; Artificial intelligence; Meaning (existential); Semantics (computer science); Noun; Natural language; Object (grammar); Information retrieval; Linguistics; Psychology","score_opus":0.049082483547532654,"score_gpt":0.33033742457999854,"score_spread":0.2812549410324659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581862991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022086068,0.00023797498,0.9951988,0.0014147584,0.00037106554,0.00024789374,0.000024389607,0.00016206873,0.00013447888],"genre_scores_gemma":[0.9792982,0.00021756998,0.019745298,0.0004634784,0.0000741506,0.00006620416,0.000010088393,0.000021038202,0.00010399543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798554,0.00011369284,0.00042491322,0.0007171892,0.00041028438,0.000348401],"domain_scores_gemma":[0.99810076,0.0003795654,0.000116405834,0.0007583804,0.00036120877,0.0002836974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069636153,0.00025483203,0.00033859332,0.0005626563,0.00036845086,0.0005613812,0.00069706526,0.000085738495,0.00002891836],"category_scores_gemma":[0.00006661414,0.00024039482,0.00023711706,0.0010807912,0.000067670284,0.00027705726,0.000016209526,0.00039437975,0.000038071987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010619949,0.00012212641,0.0011212631,0.000021678154,0.0002843542,0.0000034482628,0.001327683,0.19996825,0.000089348,0.0006708187,0.000011484095,0.7963689],"study_design_scores_gemma":[0.00015398761,0.00012040043,0.0003496317,0.000042038195,0.0003126093,0.000004883569,0.00024360046,0.9798831,0.016908636,0.0006522698,0.0010133612,0.0003155201],"about_ca_topic_score_codex":0.0025064175,"about_ca_topic_score_gemma":0.0008831087,"teacher_disagreement_score":0.9770896,"about_ca_system_score_codex":0.00007481202,"about_ca_system_score_gemma":0.000050584575,"threshold_uncertainty_score":0.9803016},"labels":[],"label_agreement":null},{"id":"W1586939924","doi":"10.1109/iccv.2015.512","title":"Describing Videos by Exploiting Temporal Structure","year":2015,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":956,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal; Université de Sherbrooke","funders":"Compute Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Representation (politics); Convolutional neural network; Context (archaeology); Motion (physics); Natural language; Pattern recognition (psychology); Artificial neural network; Machine learning","score_opus":0.05364504113686984,"score_gpt":0.2721015833326518,"score_spread":0.21845654219578192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586939924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15265027,0.000036059777,0.8389517,0.0029936903,0.00009229914,0.0001130836,0.0000023060813,0.00056338584,0.0045972066],"genre_scores_gemma":[0.7728828,1.4964583e-7,0.22631723,0.0005680012,0.000040498795,0.000008729146,0.0000066986518,0.000007490547,0.00016835851],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908406,0.000046637466,0.00014687752,0.00029898703,0.00021945585,0.00020398611],"domain_scores_gemma":[0.9991681,0.000045958895,0.000060697792,0.0004357616,0.00007060624,0.00021888917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017375177,0.00009927893,0.00008602525,0.00004359493,0.00010067705,0.00017009677,0.00065142254,0.000040119154,0.00003102961],"category_scores_gemma":[0.00015733858,0.000087096145,0.00002263113,0.00024338604,0.000017159464,0.00040487168,0.00022057265,0.00016522233,0.0000841919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008782599,0.00016647116,0.14333244,0.00001951631,0.000046572575,0.000016250227,0.0063664326,0.00602422,0.0639423,0.274059,0.14154682,0.36447123],"study_design_scores_gemma":[0.0008543529,0.00008275752,0.002639114,0.000025304327,0.0000058122505,0.000045663768,0.00036281228,0.94244856,0.013567764,0.012233024,0.027096698,0.0006381651],"about_ca_topic_score_codex":0.0008014744,"about_ca_topic_score_gemma":0.0000137326215,"teacher_disagreement_score":0.9364243,"about_ca_system_score_codex":0.000042781503,"about_ca_system_score_gemma":0.000060808048,"threshold_uncertainty_score":0.35516778},"labels":[],"label_agreement":null},{"id":"W1794939664","doi":"10.48550/arxiv.1312.6171","title":"Learning Paired-associate Images with An Unsupervised Deep Learning Architecture","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Acadia University","funders":"","keywords":"MNIST database; Computer science; Associative property; Artificial intelligence; Restricted Boltzmann machine; Unsupervised learning; Content-addressable memory; Representation (politics); Boltzmann machine; Deep learning; Pattern recognition (psychology); Modal; Artificial neural network; Machine learning; Mathematics","score_opus":0.028708464196324054,"score_gpt":0.185583910849351,"score_spread":0.15687544665302694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794939664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54616886,0.000028135542,0.45093244,0.00022543992,0.000064106935,0.0003456681,0.0000024434628,0.0010241811,0.0012087267],"genre_scores_gemma":[0.9761603,0.00004450591,0.021786358,0.00007608337,0.000092348404,0.00001094818,0.000070684124,0.000070400485,0.0016884117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961564,0.00084848667,0.00025328077,0.0018479726,0.00021535749,0.0006784833],"domain_scores_gemma":[0.9970712,0.00026691073,0.0005098971,0.00147625,0.0003075715,0.00036813613],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00041172426,0.00058587716,0.0005067327,0.0003764386,0.0007681412,0.0004896958,0.002658081,0.00039242947,0.00006855734],"category_scores_gemma":[0.00011579515,0.0006022309,0.00020062584,0.00080177333,0.000173193,0.0005663688,0.0018424437,0.0032573377,0.00023304894],"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":[0.000019952653,0.00009282762,0.03231915,0.000050753813,0.00010956607,0.000080209036,0.0013069973,0.9459107,0.000090110574,0.0066066906,0.00001147348,0.013401596],"study_design_scores_gemma":[0.0006104625,0.00027505154,0.03665684,0.00009095549,0.000078825,0.000009716071,0.00021065402,0.95190847,0.000049576534,0.008908043,0.0003817735,0.0008196086],"about_ca_topic_score_codex":0.0020380358,"about_ca_topic_score_gemma":0.000097824755,"teacher_disagreement_score":0.42999142,"about_ca_system_score_codex":0.00024204457,"about_ca_system_score_gemma":0.00016779637,"threshold_uncertainty_score":0.9996429},"labels":[],"label_agreement":null},{"id":"W1956526898","doi":"10.48550/arxiv.1509.06812","title":"Learning Wake-Sleep Recurrent Attention Models","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Inference; Convolutional neural network; Artificial intelligence; Machine learning; Stochastic gradient descent; Deep learning; Variance (accounting); Stochastic process; Artificial neural network; Mathematics; Statistics","score_opus":0.09991577746164898,"score_gpt":0.20594045657521004,"score_spread":0.10602467911356106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1956526898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37743887,0.000012939462,0.6172929,0.00018041073,0.0001014796,0.00008478475,4.402278e-7,0.00029018355,0.004598043],"genre_scores_gemma":[0.9943163,0.000009460888,0.004567131,0.00003829692,0.000035104604,0.0000011530183,0.0000066419293,0.000009989415,0.0010159313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988573,0.00014456021,0.0001141982,0.00053976517,0.00009800847,0.00024612012],"domain_scores_gemma":[0.99894726,0.00005066582,0.00010905623,0.000525079,0.0001535273,0.00021441071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028222575,0.00012911482,0.00011472844,0.00013611294,0.00017877857,0.00006935267,0.0007706586,0.00006210134,0.000008236301],"category_scores_gemma":[0.000049574035,0.0001484563,0.00007198701,0.00067519135,0.000039997838,0.00070334395,0.00031454163,0.0002972284,0.00041052874],"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":[0.000007843072,0.000057103458,0.0073946523,0.0000033565127,0.000011286433,0.000014325307,0.00026057853,0.6950545,0.000045652672,0.2921572,0.00009725092,0.004896311],"study_design_scores_gemma":[0.00039626565,0.00007666717,0.0037775561,0.000007953544,0.000011017211,0.0000036960473,0.00006330951,0.97065365,0.000014776531,0.024024328,0.00080076564,0.0001699999],"about_ca_topic_score_codex":0.00020974613,"about_ca_topic_score_gemma":0.000011618456,"teacher_disagreement_score":0.61687744,"about_ca_system_score_codex":0.00013942581,"about_ca_system_score_gemma":0.000048240607,"threshold_uncertainty_score":0.6053872},"labels":[],"label_agreement":null},{"id":"W1982527966","doi":"10.1145/1054972.1055042","title":"A visual recipe book for persons with language impairments","year":2005,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Recipe; Computer science; Presentation (obstetrics); Aphasia; Visual language; Natural language processing; Modal; Artificial intelligence; Human–computer interaction; Linguistics; Psychology; Cognitive psychology; Medicine","score_opus":0.006463165865420177,"score_gpt":0.29848421595249364,"score_spread":0.29202105008707346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982527966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0930007,0.000046481964,0.89220625,0.0066386345,0.00001806874,0.00041844288,0.0000027084252,0.00039910566,0.007269602],"genre_scores_gemma":[0.6583471,4.0072092e-7,0.33362037,0.0012621386,0.00006445709,0.00013218746,0.000003625295,0.0000084838,0.006561302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933165,0.00001536546,0.00008216951,0.00025548763,0.000119666896,0.00019563329],"domain_scores_gemma":[0.99950266,0.0000645971,0.00003639355,0.00029466584,0.000027647422,0.00007403737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009817255,0.000083902014,0.000072114715,0.000047980448,0.000112982634,0.00006825077,0.00034843737,0.00002353307,0.00007421085],"category_scores_gemma":[0.000013307368,0.00006353815,0.000032663767,0.00012672959,0.00001587907,0.0002338807,0.00006309493,0.00007123359,0.00012975962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012170552,0.0017172644,0.016000573,0.00006665991,0.00019024046,0.00001864491,0.042430084,0.004588469,0.012425448,0.07701148,0.05388595,0.7915435],"study_design_scores_gemma":[0.0011183381,0.00039598433,0.012094684,0.000011057248,0.000009511613,0.000032760567,0.00015618838,0.9162984,0.0016030782,0.00005917285,0.06793625,0.0002846104],"about_ca_topic_score_codex":0.00012824663,"about_ca_topic_score_gemma":0.000042325537,"teacher_disagreement_score":0.9117099,"about_ca_system_score_codex":0.000048613867,"about_ca_system_score_gemma":0.000053837397,"threshold_uncertainty_score":0.25910106},"labels":[],"label_agreement":null},{"id":"W1995820507","doi":"10.1109/cvpr.2013.340","title":"A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching","year":2013,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":294,"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":"Interior Business Center; Defense Advanced Research Projects Agency; U.S. Department of the Interior; Simon Fraser University; National Science Foundation","keywords":"Computer science; Image stitching; Artificial intelligence; Natural language processing; Natural language; Object (grammar); Probabilistic logic; Image (mathematics); Language model; Annotation; Natural language generation; Information retrieval; Pattern recognition (psychology)","score_opus":0.03467305324326582,"score_gpt":0.29148073092247134,"score_spread":0.25680767767920554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995820507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7551668,0.00009424034,0.24234475,0.0011478898,0.000060856837,0.0002490835,3.3095418e-7,0.000077550714,0.0008584856],"genre_scores_gemma":[0.8276151,0.000023416385,0.17198971,0.00016636902,0.000038416794,0.000031099098,6.8033717e-7,0.000005287536,0.00012992363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991281,0.000059517006,0.00023866995,0.00027162064,0.00013523325,0.00016684647],"domain_scores_gemma":[0.9994229,0.00009264296,0.000082946,0.00031176428,0.000047683185,0.000042067866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015985566,0.000101338606,0.00015035401,0.0000778757,0.00005827844,0.00013413382,0.0002637617,0.00005863995,0.000023719975],"category_scores_gemma":[0.00009292857,0.00008621168,0.000025342768,0.00024566596,0.000034361477,0.00045370118,0.00018073767,0.00019745519,0.000017795172],"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":[0.000012829461,0.0004414339,0.3448424,0.00015160911,0.000043894655,0.000008452717,0.043849964,0.007412512,0.012075477,0.06864105,0.0004542721,0.5220661],"study_design_scores_gemma":[0.0005080694,0.00007846687,0.64986366,0.00010122922,0.00000763195,0.000010092899,0.0003554249,0.33618343,0.0013941338,0.010881203,0.00038607005,0.00023061063],"about_ca_topic_score_codex":0.013183299,"about_ca_topic_score_gemma":0.00032935967,"teacher_disagreement_score":0.5218355,"about_ca_system_score_codex":0.00002386241,"about_ca_system_score_gemma":0.000031746025,"threshold_uncertainty_score":0.993388},"labels":[],"label_agreement":null},{"id":"W1999830516","doi":"10.4000/lettre-cdf.86","title":"Modèles computationnels du mouvement humain","year":2009,"lang":"fr","type":"article","venue":"La lettre du Collège de France","topic":"Multimodal Machine Learning Applications","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":"Humanities; Art","score_opus":0.01060716546016197,"score_gpt":0.2507894383769145,"score_spread":0.2401822729167525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999830516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11443404,0.0015487612,0.7393572,0.13797215,0.0005436965,0.00051961164,0.00003115554,0.00034206585,0.005251342],"genre_scores_gemma":[0.87008995,0.00009553575,0.11587562,0.009235192,0.0007358118,0.00008262219,0.000016178616,0.000028875176,0.0038402197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703807,0.0005019444,0.00050402223,0.0007867688,0.0004647501,0.00070447696],"domain_scores_gemma":[0.9979205,0.00049743295,0.00027434653,0.00081418373,0.00023979698,0.00025371584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007052226,0.00038191615,0.0003635807,0.00013160403,0.0005870769,0.0005302058,0.0012312995,0.00021832097,0.00013283413],"category_scores_gemma":[0.00017373185,0.0004550034,0.00015717167,0.0009454231,0.00019087654,0.00046833622,0.00016105072,0.00056904927,0.00040040252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013086113,0.00087457575,0.02206409,0.0000646879,0.00004883577,0.00022417062,0.0044121654,0.347819,0.0009828445,0.43890148,0.023935577,0.16065948],"study_design_scores_gemma":[0.0006751201,0.0000893025,0.17034478,0.000096937794,0.00001383613,0.00008725734,0.000018412522,0.6286835,0.00013433337,0.007705719,0.1918036,0.0003472092],"about_ca_topic_score_codex":0.0011826294,"about_ca_topic_score_gemma":0.000031598684,"teacher_disagreement_score":0.7556559,"about_ca_system_score_codex":0.00020644655,"about_ca_system_score_gemma":0.00018019316,"threshold_uncertainty_score":0.9997902},"labels":[],"label_agreement":null},{"id":"W2048343491","doi":"10.1109/cvpr.2014.455","title":"What Are You Talking About? Text-to-Image Coreference","year":2014,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":205,"is_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":"Coreference; Computer science; Artificial intelligence; Parsing; Natural language processing; Exploit; Object (grammar); Image (mathematics); Noun; Resolution (logic)","score_opus":0.014036303612288489,"score_gpt":0.27823979989435704,"score_spread":0.2642034962820686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048343491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048647773,0.000017907072,0.9250543,0.008688069,0.0002621109,0.000176019,6.261333e-7,0.00053567905,0.016617488],"genre_scores_gemma":[0.8285489,0.000004854735,0.16840182,0.0019013557,0.00006736811,0.000039755512,0.0000018431729,0.000010536432,0.0010235326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871516,0.00006484717,0.00017668119,0.00051318645,0.00024337639,0.000286729],"domain_scores_gemma":[0.9985259,0.0001454573,0.00009071299,0.0009662744,0.000100824356,0.00017080839],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002863624,0.00013979565,0.0001404137,0.0000969527,0.00017892364,0.00074447645,0.0012669375,0.000044797573,0.00008534519],"category_scores_gemma":[0.0001759498,0.00012324702,0.000039597064,0.0004199969,0.000031340125,0.0007604406,0.00043599794,0.00018912028,0.0020186382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032583077,0.000108915454,0.01374765,0.000025185607,0.000011288819,0.000003116602,0.0016294747,0.0012761563,0.007295511,0.36832598,0.0030651602,0.60450834],"study_design_scores_gemma":[0.00026210086,0.00006691987,0.42178312,0.00010177383,0.0000044256913,0.000010218407,0.00010492276,0.5208066,0.0015347227,0.0055166185,0.04933788,0.000470692],"about_ca_topic_score_codex":0.00023590807,"about_ca_topic_score_gemma":0.000042598054,"teacher_disagreement_score":0.77990115,"about_ca_system_score_codex":0.000026790845,"about_ca_system_score_gemma":0.000017188348,"threshold_uncertainty_score":0.99875844},"labels":[],"label_agreement":null},{"id":"W2110380922","doi":"10.1109/icra.2014.6906913","title":"Curiosity based exploration for learning terrain models","year":2014,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Terrain; Perplexity; Discriminative model; Path (computing); Visualization; Plan (archaeology)","score_opus":0.030668714280670105,"score_gpt":0.28077977677587596,"score_spread":0.25011106249520587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110380922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004146209,0.0000016919804,0.9857109,0.005375429,0.000039684033,0.00022687421,3.238554e-7,0.00047617854,0.004022662],"genre_scores_gemma":[0.65454227,1.4504197e-7,0.34470907,0.00044382404,0.000030459893,0.000102559374,0.000007062968,0.000005661584,0.00015894571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923766,0.000085948064,0.00012251097,0.00028425624,0.00011814737,0.00015147636],"domain_scores_gemma":[0.99923104,0.00023471376,0.000060341525,0.00035050392,0.0000683472,0.000055078093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044446177,0.00007923358,0.00007989156,0.000059772447,0.00021880819,0.00010539582,0.00038854842,0.000035275636,0.000007613486],"category_scores_gemma":[0.00014228493,0.0000744345,0.000043557146,0.00013508882,0.000011384696,0.000507057,0.000061006944,0.00010599981,0.000038428614],"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":[0.0000027737074,0.00003986698,0.00047433045,0.000009775755,0.0000025318807,3.314902e-8,0.00041509263,0.5033538,0.0010352687,0.4235332,0.00026814634,0.07086522],"study_design_scores_gemma":[0.00022419338,0.000049101538,0.000592954,0.0000032204289,0.0000015806833,2.0762322e-7,0.0000052166456,0.9583841,0.0005514819,0.0362252,0.0038676055,0.00009516204],"about_ca_topic_score_codex":0.000122010235,"about_ca_topic_score_gemma":0.000012179331,"teacher_disagreement_score":0.65039605,"about_ca_system_score_codex":0.000018489036,"about_ca_system_score_gemma":0.000020996893,"threshold_uncertainty_score":0.3035351},"labels":[],"label_agreement":null},{"id":"W2111141593","doi":"10.1109/iccv.2007.4408877","title":"Learning Structured Appearance Models from Captioned Images of Cluttered Scenes","year":2007,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Computer science; Artificial intelligence; Feature (linguistics); ENCODE; Computer vision; Object (grammar); Graph; Pattern recognition (psychology)","score_opus":0.012134812412102477,"score_gpt":0.26091229373609864,"score_spread":0.24877748132399616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111141593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32935134,0.00006847508,0.66843605,0.00030815625,0.000045531466,0.00009005769,0.0000018211512,0.00020736839,0.0014912082],"genre_scores_gemma":[0.769229,0.000003897381,0.23054647,0.000057229063,0.00003719566,0.000004261898,0.0000048470315,0.000008496112,0.00010862565],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880874,0.00005675187,0.00028990884,0.0003656775,0.0002505851,0.00022833423],"domain_scores_gemma":[0.99903935,0.00011353143,0.00016025348,0.0005046763,0.000108314845,0.00007387584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028289785,0.00012403075,0.00016752687,0.000102252096,0.00012316434,0.00005356361,0.00066017837,0.000060862567,0.000026876387],"category_scores_gemma":[0.00004474822,0.00011484824,0.000054608194,0.00030506015,0.000052136587,0.00033375004,0.0001580357,0.00021084772,0.000029786941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047072863,0.0001301605,0.038807705,0.000037069407,0.00007280022,0.0000062538547,0.0037640396,0.29273418,0.3578676,0.09129555,0.0001132574,0.21512431],"study_design_scores_gemma":[0.00037830044,0.00002280361,0.23830311,0.000020389769,0.000005040743,0.0000025378722,0.000059216614,0.71411264,0.027384099,0.01945952,0.00006539067,0.00018694841],"about_ca_topic_score_codex":0.0025575077,"about_ca_topic_score_gemma":0.0000528558,"teacher_disagreement_score":0.43987763,"about_ca_system_score_codex":0.000020722313,"about_ca_system_score_gemma":0.000022262257,"threshold_uncertainty_score":0.46833754},"labels":[],"label_agreement":null},{"id":"W2111407473","doi":"10.1109/crv.2012.37","title":"Learning Categorical Shape from Captioned Images","year":2012,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Minimum bounding box; Object (grammar); Bounding overwatch; Computer vision; Boundary (topology); Active appearance model; Annotation; Set (abstract data type); Categorical variable; Pattern recognition (psychology); Image (mathematics); Class (philosophy); Cognitive neuroscience of visual object recognition; Mathematics; Machine learning","score_opus":0.014716694765619813,"score_gpt":0.26916058934433645,"score_spread":0.25444389457871663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111407473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19997223,0.0000767326,0.78748864,0.0020860939,0.00012670968,0.00007442571,5.458931e-7,0.00063711585,0.009537531],"genre_scores_gemma":[0.88822544,0.0000028605455,0.11095121,0.00014985233,0.00016429761,0.0000226167,0.000008437068,0.000007874118,0.0004674018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991164,0.00008032979,0.00012903042,0.00023312474,0.00016935306,0.00027175073],"domain_scores_gemma":[0.9992529,0.00017358712,0.00004891634,0.0003418412,0.000035549965,0.00014720912],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017404597,0.00009429244,0.000091046924,0.00004863194,0.00017394606,0.00009480817,0.00046902837,0.000045056804,0.00040902884],"category_scores_gemma":[0.00008184688,0.00008259979,0.00003784467,0.00021632001,0.000020258973,0.00046722862,0.00020794389,0.00024996398,0.0019539346],"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":[0.0000044145754,0.00034578567,0.37502995,0.000005670443,0.000042342876,0.0000032645673,0.0035722782,0.0018166163,0.029695436,0.30828288,0.0023306597,0.2788707],"study_design_scores_gemma":[0.00017406365,0.000016003924,0.60241884,0.0000014653131,0.0000056826784,0.0000068512345,0.000043132393,0.3882287,0.0011385025,0.002223593,0.0055288086,0.00021434975],"about_ca_topic_score_codex":0.0017747559,"about_ca_topic_score_gemma":0.0000024889775,"teacher_disagreement_score":0.6882532,"about_ca_system_score_codex":0.00003136038,"about_ca_system_score_gemma":0.00001426318,"threshold_uncertainty_score":0.99882317},"labels":[],"label_agreement":null},{"id":"W2113005879","doi":"10.1109/iccv.2013.462","title":"Handling Uncertain Tags in Visual Recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Training set; Artificial intelligence; Noise (video); Set (abstract data type); Noisy data; Pattern recognition (psychology); Data set; Computer vision; Machine learning; Image (mathematics)","score_opus":0.019587749397098838,"score_gpt":0.2892064570180142,"score_spread":0.26961870762091533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113005879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55239564,0.000006216659,0.43863094,0.0023922967,0.0000384931,0.00018884962,1.4092177e-7,0.00018692728,0.006160512],"genre_scores_gemma":[0.88988864,0.0000012308954,0.10946529,0.00034976684,0.000021590913,0.00009601382,0.0000035908497,0.000003777176,0.00017009981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937075,0.00004124807,0.00013007312,0.00021540569,0.00009341215,0.00014909492],"domain_scores_gemma":[0.99960893,0.00009251885,0.00003073985,0.00017994322,0.000043490807,0.000044390476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014094898,0.00005915623,0.000060426384,0.000093809285,0.000048772774,0.00011160083,0.00026109008,0.00003143181,0.00020191782],"category_scores_gemma":[0.00005582153,0.000053681615,0.000016593574,0.00030664328,0.000010473622,0.00033477938,0.00008045842,0.000116875366,0.0016005158],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012441052,0.0001464905,0.026567033,0.0000091354805,0.0000043322525,0.0000020377524,0.00063608406,0.001532965,0.006511895,0.012340162,0.00052583596,0.9517228],"study_design_scores_gemma":[0.00017791417,0.00001957203,0.09098473,0.0000094286,4.950721e-7,0.0000023609684,0.000020830623,0.8975663,0.0007147647,0.01020352,0.0001956674,0.0001044021],"about_ca_topic_score_codex":0.0052275234,"about_ca_topic_score_gemma":0.0000646336,"teacher_disagreement_score":0.9516184,"about_ca_system_score_codex":0.000027501817,"about_ca_system_score_gemma":0.000018167299,"threshold_uncertainty_score":0.99917686},"labels":[],"label_agreement":null},{"id":"W2130844143","doi":"10.13140/2.1.1135.8081","title":"Unsupervised Disambiguation of Image Captions","year":2012,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Set (abstract data type); sort; Natural language processing; Construct (python library); Context (archaeology); Word (group theory); Word-sense disambiguation; Image (mathematics); Topic model; Pattern recognition (psychology); Information retrieval","score_opus":0.01478172752583834,"score_gpt":0.28339435324562423,"score_spread":0.2686126257197859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130844143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15936089,0.000015269,0.82620716,0.0011216798,0.000048904298,0.00008295733,0.000001007071,0.00012739739,0.013034719],"genre_scores_gemma":[0.78521746,9.173806e-7,0.21456347,0.00005072261,0.000023549155,0.0000158656,0.0000032627797,0.0000029231533,0.00012181392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999512,0.000032612283,0.000120024364,0.000095510055,0.000113891576,0.00012592909],"domain_scores_gemma":[0.9994163,0.000056632067,0.000041385625,0.00037582807,0.000050463415,0.000059393486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015887938,0.00004713692,0.000056126028,0.000051210613,0.00005228585,0.000018228317,0.00028991047,0.000019491143,0.000100291145],"category_scores_gemma":[0.000043949898,0.000041763295,0.000029268742,0.00023944104,0.000023152104,0.0004314306,0.00007737361,0.00005159621,0.00021832659],"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":[8.513608e-7,0.0002665871,0.04510538,0.000011719295,0.000009360283,6.2351646e-8,0.001627621,0.0002059786,0.067213826,0.8533613,0.00041272974,0.031784575],"study_design_scores_gemma":[0.00019307723,0.000015638514,0.80245954,0.0000037952582,0.000005885696,0.00000286928,0.000036098925,0.1863057,0.007763231,0.0022466436,0.000844217,0.00012327454],"about_ca_topic_score_codex":0.00042456193,"about_ca_topic_score_gemma":0.000003831383,"teacher_disagreement_score":0.8511147,"about_ca_system_score_codex":0.000012403754,"about_ca_system_score_gemma":0.000012164422,"threshold_uncertainty_score":0.28062195},"labels":[],"label_agreement":null},{"id":"W2155292833","doi":"10.48550/arxiv.1511.02793","title":"Generating Images from Captions with Attention","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":75,"is_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":"Generative grammar; Computer science; Artificial intelligence; Generative model; Baseline (sea); Image (mathematics); Natural language processing; Training set; Natural (archaeology); Natural language generation; Machine learning; Natural language; Geography","score_opus":0.06370869466700849,"score_gpt":0.20355322829454486,"score_spread":0.13984453362753638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155292833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4405344,0.000020986463,0.5578642,0.00017617457,0.00009452077,0.0001468002,0.00002522364,0.00026965234,0.0008680313],"genre_scores_gemma":[0.9408504,0.000011542783,0.058169857,0.00004471229,0.00010871483,0.000003817993,0.00010996238,0.00001807437,0.0006829158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983744,0.0001438181,0.0001426572,0.0010126183,0.000103554165,0.0002229545],"domain_scores_gemma":[0.9979794,0.00006961229,0.0002503272,0.0012779658,0.0002613375,0.00016137522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016194134,0.0002417709,0.0002095029,0.00015483104,0.0002258811,0.00020359631,0.0012544424,0.00015638181,0.000019341258],"category_scores_gemma":[0.00002702244,0.00025758607,0.000086941356,0.0003863338,0.00007491822,0.00031349476,0.0011757219,0.00059963367,0.00018214458],"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":[0.000005532394,0.00006166842,0.014170322,0.00001042478,0.0000666783,0.000047262034,0.00016915705,0.96107435,0.00045656005,0.022952082,0.00023362064,0.00075233844],"study_design_scores_gemma":[0.00031276388,0.000022549559,0.0164797,0.000046382338,0.00005938028,0.000002646532,0.00003807092,0.96955305,0.000030934352,0.013016154,0.00011273406,0.0003256115],"about_ca_topic_score_codex":0.0045339474,"about_ca_topic_score_gemma":0.0001712272,"teacher_disagreement_score":0.500316,"about_ca_system_score_codex":0.00019018647,"about_ca_system_score_gemma":0.0002017059,"threshold_uncertainty_score":0.99998766},"labels":[],"label_agreement":null},{"id":"W2160257818","doi":"10.3115/1119212.1119220","title":"Why can't José read?","year":2003,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Set (abstract data type); Process (computing); Context (archaeology); Mobile robot; Robot; Image (mathematics); Computer vision; Cognitive neuroscience of visual object recognition; Spatial contextual awareness; Pattern recognition (psychology)","score_opus":0.012240741510052246,"score_gpt":0.2586873306050244,"score_spread":0.24644658909497216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160257818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004237589,0.00001361952,0.8107935,0.011238261,0.00007464385,0.00008337119,3.271809e-7,0.0003409032,0.17321777],"genre_scores_gemma":[0.71786785,0.0000014049415,0.27283195,0.006577862,0.000014695274,0.000023833487,8.001691e-7,0.0000060753505,0.0026755407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99937874,0.000049018705,0.000085035805,0.0002236961,0.00011356735,0.00014994318],"domain_scores_gemma":[0.99926275,0.000053175783,0.000024748855,0.00055478927,0.00003378851,0.00007074822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012214358,0.00006222114,0.000055199285,0.000040610983,0.000087646484,0.00006768245,0.00043016142,0.00002443295,0.00024442124],"category_scores_gemma":[0.00007507874,0.00005414322,0.000023014243,0.0002660376,0.000014041256,0.00008789342,0.000052793697,0.000093420334,0.00026940196],"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":[1.4148874e-7,0.00002796419,0.002650793,0.0000015516985,0.0000032438456,0.000001295613,0.00013516971,0.00022004585,0.0003739655,0.97314966,0.015190611,0.008245575],"study_design_scores_gemma":[0.0002961674,0.000037281803,0.02643984,0.0000045412603,0.000003398125,0.000035810877,0.000016573396,0.07361807,0.0024614832,0.021366086,0.87539643,0.00032432465],"about_ca_topic_score_codex":0.0013122798,"about_ca_topic_score_gemma":0.000077127406,"teacher_disagreement_score":0.95178354,"about_ca_system_score_codex":0.000017810476,"about_ca_system_score_gemma":0.000031716936,"threshold_uncertainty_score":0.34627068},"labels":[],"label_agreement":null},{"id":"W2171361956","doi":"","title":"Multimodal Neural Language Models","year":2014,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":568,"is_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; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Natural language processing; Modalities; Focus (optics); Sentence; Phrase; Natural language; Image (mathematics); Artificial neural network; Language model; Word (group theory); Speech recognition; Linguistics","score_opus":0.010895750074746786,"score_gpt":0.26624760043780255,"score_spread":0.25535185036305574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171361956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09422432,0.000007836963,0.8721488,0.001838371,0.000055548084,0.00007592882,3.4302508e-7,0.00053998013,0.031108836],"genre_scores_gemma":[0.81011856,1.8864154e-7,0.18877152,0.0006362746,0.000045533536,0.000015695256,0.0000016125902,0.0000061047194,0.0004045282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924505,0.00005451794,0.00010567274,0.00027164564,0.00014169606,0.00018142375],"domain_scores_gemma":[0.9991466,0.00009147134,0.000031598338,0.0006228224,0.000026382977,0.00008115872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015009122,0.00008428649,0.000078933765,0.00004892536,0.00008259195,0.00008399296,0.00071691116,0.00003029439,0.000030321768],"category_scores_gemma":[0.000036348683,0.000071455135,0.00003743605,0.00015413851,0.000017132861,0.00028596865,0.00018323956,0.00012294945,0.00027058966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010696418,0.00004994291,0.00093445,0.000004032237,0.000004287358,0.0000011320755,0.00095395424,0.06250409,0.002272264,0.72281414,0.00030936618,0.21015127],"study_design_scores_gemma":[0.00014475027,0.000014374341,0.006258309,9.4703887e-7,9.1980166e-7,0.0000040271993,0.0000068419577,0.98857266,0.0002587165,0.0042887633,0.00035429452,0.000095383395],"about_ca_topic_score_codex":0.00082350575,"about_ca_topic_score_gemma":0.000014104812,"teacher_disagreement_score":0.9260686,"about_ca_system_score_codex":0.000010185372,"about_ca_system_score_gemma":0.000007926905,"threshold_uncertainty_score":0.34779727},"labels":[],"label_agreement":null},{"id":"W2172888184","doi":"10.48550/arxiv.1511.06361","title":"Order-Embeddings of Images and Language","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":87,"is_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":"Closed captioning; Hierarchy; Computer science; Natural language processing; Variety (cybernetics); Artificial intelligence; Image (mathematics); Logical consequence; Textual entailment; Order (exchange)","score_opus":0.04293762358184849,"score_gpt":0.21878959671675857,"score_spread":0.17585197313491008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172888184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64013904,0.00010494243,0.3554484,0.00017235441,0.000069924135,0.00015933893,0.00001498758,0.00017126676,0.0037197296],"genre_scores_gemma":[0.9840917,0.000035567733,0.0151493,0.000027008517,0.00002194725,7.5359435e-7,0.000008479735,0.0000106303,0.00065459614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998952,0.000073715986,0.00012301875,0.0006256586,0.00006663814,0.00015902339],"domain_scores_gemma":[0.99849826,0.00008302104,0.00021365921,0.0008853775,0.00020031293,0.00011936962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021754557,0.00016864638,0.00022878822,0.00016756283,0.000053695177,0.000052103318,0.001067853,0.00013250156,0.000010614327],"category_scores_gemma":[0.0000854295,0.0001918049,0.000053711596,0.00038357824,0.00011041331,0.00015964547,0.0019736537,0.00037463434,0.000026388463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044447865,0.0003764197,0.049473118,0.0005757859,0.0002709498,0.00026145158,0.007324167,0.35234275,0.002649399,0.5705364,0.0023208451,0.013824278],"study_design_scores_gemma":[0.00049881235,0.000044855547,0.012058906,0.00007255447,0.000054454275,0.0000067998103,0.00017502012,0.9543968,0.00049574394,0.031452265,0.00032044135,0.0004233553],"about_ca_topic_score_codex":0.0014283303,"about_ca_topic_score_gemma":0.000015237482,"teacher_disagreement_score":0.60205406,"about_ca_system_score_codex":0.000051357852,"about_ca_system_score_gemma":0.000116681884,"threshold_uncertainty_score":0.78215766},"labels":[],"label_agreement":null},{"id":"W2174492417","doi":"10.48550/arxiv.1511.05960","title":"ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":278,"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":"Convolutional neural network; Question answering; Computer science; Artificial intelligence; Visual attention; Natural language processing; Pattern recognition (psychology); Psychology; Neuroscience; Cognition","score_opus":0.07866269093093313,"score_gpt":0.2518239291440776,"score_spread":0.17316123821314444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174492417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34183577,0.000014758834,0.6566499,0.00018291014,0.00043769064,0.00040534788,0.000015572454,0.00035943024,0.000098634075],"genre_scores_gemma":[0.96852857,0.00000262812,0.030455599,0.000094864525,0.000343492,0.000012637587,0.00036006165,0.000023739842,0.00017840028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979219,0.00025497426,0.00021882061,0.0011007641,0.00012727128,0.0003762988],"domain_scores_gemma":[0.99811846,0.00013227628,0.00030269573,0.00080209784,0.00040758046,0.00023689608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060724834,0.0002829709,0.00024859235,0.00017702847,0.0003264047,0.00015608173,0.0011144493,0.0002593742,0.000009537492],"category_scores_gemma":[0.000053934924,0.00036161416,0.00017236239,0.0003976646,0.00008414117,0.00046560037,0.00057046185,0.0004974554,0.000033654185],"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":[0.00003530966,0.000088010434,0.012094031,0.000031506803,0.000020165959,0.0000064451506,0.000024125993,0.9044352,0.00005246185,0.08226984,0.00015451924,0.0007883992],"study_design_scores_gemma":[0.0005545948,0.00010582371,0.03855866,0.00004512476,0.00004234132,0.0000018104331,0.000007294917,0.94052297,0.000005287149,0.019564888,0.00024563214,0.00034560368],"about_ca_topic_score_codex":0.00054701715,"about_ca_topic_score_gemma":0.000067556146,"teacher_disagreement_score":0.62669283,"about_ca_system_score_codex":0.0003264789,"about_ca_system_score_gemma":0.00027382787,"threshold_uncertainty_score":0.9998836},"labels":[],"label_agreement":null},{"id":"W2176212817","doi":"10.48550/arxiv.1511.06973","title":"Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":47,"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":"Question answering; Computer science; Image (mathematics); Ask price; Information retrieval; Knowledge base; Representation (politics); Questions and answers; Artificial intelligence; Knowledge representation and reasoning; Natural language processing","score_opus":0.04890827163354747,"score_gpt":0.23881712332946559,"score_spread":0.18990885169591812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176212817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45917988,0.00003728416,0.53790873,0.000111405076,0.00031822888,0.0001864077,0.000017255512,0.00045710366,0.0017837085],"genre_scores_gemma":[0.9869058,0.000008321658,0.012331662,0.00008452408,0.0002499643,0.0000039779625,0.00004606746,0.000033932745,0.0003357364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974448,0.00028999857,0.00025548838,0.0014263073,0.0002092539,0.00037411676],"domain_scores_gemma":[0.99699926,0.0002721571,0.00035922998,0.0018098693,0.00024344597,0.00031604528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053185556,0.00042593537,0.00035599453,0.00040344917,0.00025702108,0.00027845617,0.0028834578,0.00035208216,0.000031080624],"category_scores_gemma":[0.00012439297,0.0004954129,0.00018895826,0.0004725363,0.00009395617,0.0003689821,0.0021508546,0.001147461,0.000265708],"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":[0.00008541639,0.00038850727,0.02069524,0.000050196348,0.00006112593,0.00008170998,0.001249172,0.93442243,0.0002816444,0.038936548,0.00014664383,0.0036013485],"study_design_scores_gemma":[0.0006564971,0.00010098749,0.017610064,0.00022386419,0.000043051004,0.000001123398,0.000028687879,0.94920045,0.00017290011,0.03120828,0.00027162326,0.00048248144],"about_ca_topic_score_codex":0.0035969515,"about_ca_topic_score_gemma":0.00012482337,"teacher_disagreement_score":0.52772593,"about_ca_system_score_codex":0.00049988,"about_ca_system_score_gemma":0.00033581443,"threshold_uncertainty_score":0.9997498},"labels":[],"label_agreement":null},{"id":"W2190067570","doi":"10.1109/cvpr.2016.501","title":"MovieQA: Understanding Stories in Movies through Question-Answering","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"Karlsruhe House of Young Scientists; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Question answering; Scripting language; Set (abstract data type); Benchmark (surveying); Comprehension; Semantics (computer science); Information retrieval; Natural language processing; Domain (mathematical analysis); CLIPS; Range (aeronautics); Artificial intelligence; Programming language","score_opus":0.06700293859533554,"score_gpt":0.34423839817472807,"score_spread":0.27723545957939255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190067570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048186933,0.00020022735,0.95817953,0.007230123,0.00060444436,0.00034367177,0.000004882517,0.00067442196,0.027944004],"genre_scores_gemma":[0.8392356,0.00007596705,0.15979733,0.00012784431,0.00012026803,0.00015724546,0.0000053141357,0.000023064753,0.0004573595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794334,0.0001401944,0.0004036775,0.0008402628,0.00031795714,0.00035455273],"domain_scores_gemma":[0.998193,0.0002932828,0.00019704616,0.0011950922,0.000059536134,0.000062030704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042432436,0.0003068807,0.00033743877,0.00019717557,0.000157916,0.00029674897,0.0013993123,0.00022367216,0.000033090673],"category_scores_gemma":[0.00014078215,0.00025703752,0.00008808001,0.00027682201,0.000082741404,0.0004656917,0.001870189,0.0006787761,0.000074473435],"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":[0.0000014626145,0.000023069691,0.005675936,0.00005665001,0.000014369902,0.000003869693,0.0020704095,0.0034319789,0.00006396157,0.98693264,0.00011124481,0.001614388],"study_design_scores_gemma":[0.00026213683,0.000016647751,0.010343168,0.000500086,0.000006872469,0.0000050108647,0.00022888088,0.07070447,0.0002023983,0.9157521,0.0013616048,0.0006166389],"about_ca_topic_score_codex":0.002884282,"about_ca_topic_score_gemma":0.00030977497,"teacher_disagreement_score":0.8344169,"about_ca_system_score_codex":0.00069900363,"about_ca_system_score_gemma":0.0001696244,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"id":"W2467945436","doi":"10.1145/2932710","title":"Visualizing Natural Language Descriptions","year":2016,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Multimodal Machine Learning Applications","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 Ottawa","funders":"","keywords":"Exploit; Natural language user interface; Naturalness; Natural language programming; Natural language; Visualization; Simplicity; Natural language understanding; Language identification","score_opus":0.02202513094967928,"score_gpt":0.3171835668698234,"score_spread":0.2951584359201441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467945436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37080106,0.00008392786,0.62610394,0.0016779804,0.00030989823,0.000075768614,0.0000016462944,0.0006248569,0.00032093743],"genre_scores_gemma":[0.89434206,0.0000014489708,0.10509951,0.00018029936,0.00011287696,0.0000031044328,0.0000038994363,0.000015191811,0.00024157956],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99809116,0.0006301134,0.00023453409,0.0004542254,0.00022440565,0.00036555654],"domain_scores_gemma":[0.9973473,0.0011448914,0.00011300949,0.0012123226,0.0000920122,0.000090456735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015577598,0.00014983323,0.00014368845,0.00011718085,0.0002935439,0.00014312474,0.0016730822,0.000044719385,0.000015423873],"category_scores_gemma":[0.0011728166,0.00011098312,0.00006797419,0.0004478401,0.000047858943,0.00027393096,0.00087998895,0.00017803386,0.0003929172],"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":[9.5029753e-7,0.000068279056,0.104147024,0.000009510676,0.000028544639,0.000010826388,0.0015094392,0.00013640367,0.040087953,0.024925612,0.00068800326,0.82838744],"study_design_scores_gemma":[0.00038662978,0.00002440859,0.89882696,0.00006327745,0.0000038913004,0.00002586518,0.000026055175,0.09719495,0.0012691551,0.0012299911,0.0006168462,0.0003319484],"about_ca_topic_score_codex":0.0005840237,"about_ca_topic_score_gemma":0.000034685905,"teacher_disagreement_score":0.8280555,"about_ca_system_score_codex":0.00006289203,"about_ca_system_score_gemma":0.000036646135,"threshold_uncertainty_score":0.50502867},"labels":[],"label_agreement":null},{"id":"W2524766041","doi":"10.5244/c.30.141","title":"Oracle Performance for Visual Captioning","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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 de Montréal","funders":"","keywords":"Closed captioning; Computer science; Oracle; Task (project management); Artificial intelligence; Natural language; Process (computing); Natural language processing; Image (mathematics); Simplicity; Imperfect; Upper and lower bounds; Machine learning; Programming language; Mathematics; Linguistics","score_opus":0.021510436132043273,"score_gpt":0.3232858661331357,"score_spread":0.3017754300010924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2524766041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046439927,0.000021866193,0.94441897,0.0024790938,0.0003264411,0.00045925044,0.000004932602,0.0005435519,0.005305984],"genre_scores_gemma":[0.74250954,0.000005443713,0.25556234,0.00011924808,0.00017033906,0.00039448336,0.000010553731,0.000014576279,0.0012134666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877805,0.000025550486,0.00021403511,0.00057698484,0.00016158308,0.00024382156],"domain_scores_gemma":[0.99877757,0.00014566834,0.00015207333,0.0007174419,0.00013737704,0.00006986995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026935973,0.0001675504,0.00016053364,0.00009206334,0.0001924551,0.00018758676,0.0010685866,0.00013226001,0.000031045336],"category_scores_gemma":[0.000052841056,0.00013334483,0.00008526306,0.00007931531,0.000024771956,0.00017199309,0.0011042837,0.00025946304,0.00023787563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011462233,0.0001392146,0.010157884,0.00031782067,0.00006488797,6.5087465e-7,0.0005391709,0.009557547,0.0013919174,0.26181263,0.0019095885,0.7140972],"study_design_scores_gemma":[0.00018924885,0.00003602021,0.016509397,0.00006726209,0.0000052286264,0.0000023003686,0.0000018720154,0.968852,0.0007899394,0.008906207,0.0043686675,0.00027188836],"about_ca_topic_score_codex":0.00009016036,"about_ca_topic_score_gemma":0.0000029009059,"teacher_disagreement_score":0.95929444,"about_ca_system_score_codex":0.00006755337,"about_ca_system_score_gemma":0.00012166334,"threshold_uncertainty_score":0.5437644},"labels":[],"label_agreement":null},{"id":"W2557264465","doi":"10.1109/cvpr.2017.339","title":"Hierarchical Boundary-Aware Neural Encoder for Video Captioning","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":141,"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":"Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Closed captioning; ENCODE; Encoding (memory); Leverage (statistics); Encoder; Recurrent neural network; Artificial neural network; Scheme (mathematics); Annotation","score_opus":0.02768488918146487,"score_gpt":0.32825486747151345,"score_spread":0.30056997829004856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557264465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034001216,0.000008598921,0.94797593,0.012778188,0.00020274971,0.0002354243,0.0000028386721,0.00026790836,0.004527127],"genre_scores_gemma":[0.82286495,3.3374874e-7,0.17578976,0.00054028956,0.00011362641,0.00010118178,0.000003303623,0.00000881838,0.0005777269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990401,0.000026226642,0.00014646053,0.00038194188,0.00015256112,0.00025266607],"domain_scores_gemma":[0.9984697,0.00015151594,0.00010213035,0.0010960136,0.00007748668,0.00010313018],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00020173995,0.00010254517,0.000106139385,0.000044205633,0.0014964361,0.0009013761,0.0014186708,0.000039039063,0.000033429296],"category_scores_gemma":[0.00020827356,0.00009137729,0.000072038,0.000041443676,0.00009413022,0.00050133164,0.00035044798,0.00018675964,0.00007610101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001175183,0.00012261952,0.038751207,0.000035396573,0.000032335254,0.000005471302,0.00083054294,0.0032283987,0.0014515021,0.6891409,0.004046845,0.26234302],"study_design_scores_gemma":[0.0002864368,0.00003062767,0.08705708,0.0000047547974,0.0000028014454,0.000010152812,0.000004375968,0.8919718,0.000102747435,0.011198412,0.0091980975,0.00013269826],"about_ca_topic_score_codex":0.00051079364,"about_ca_topic_score_gemma":0.00005821522,"teacher_disagreement_score":0.8887434,"about_ca_system_score_codex":0.000023702145,"about_ca_system_score_gemma":0.00005780723,"threshold_uncertainty_score":0.9998035},"labels":[],"label_agreement":null},{"id":"W2560645892","doi":"10.1109/iccv.2017.140","title":"Areas of Attention for Image Captioning","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":218,"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":"Agence Nationale de la Recherche","keywords":"Closed captioning; Computer science; Pairwise comparison; Transformer; Artificial intelligence; Convolutional neural network; Image (mathematics); Language model; Pattern recognition (psychology); Computer vision","score_opus":0.030481745100812682,"score_gpt":0.3389131894072359,"score_spread":0.3084314443064232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560645892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017789055,0.000019172254,0.9722703,0.0016934637,0.00023386508,0.00047615878,0.0000111671025,0.00016344734,0.007343364],"genre_scores_gemma":[0.5884904,0.0000025878608,0.41064748,0.000012796225,0.000051620354,0.00015412024,0.000032545366,0.000007499466,0.0006009349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990524,0.000025098776,0.00022550099,0.0004270556,0.00014235952,0.00012756084],"domain_scores_gemma":[0.9978032,0.00007690203,0.00045178575,0.0013893995,0.00023902561,0.00003967511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003059074,0.00012141649,0.00018705966,0.00008671702,0.00016657918,0.00021397589,0.0013683233,0.00010965933,0.00001136339],"category_scores_gemma":[0.00015806509,0.00012005296,0.00014842759,0.000029313669,0.00004137576,0.0001399677,0.0009683971,0.00021642566,0.000025843921],"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":[0.000012956938,0.00032356547,0.019673577,0.0012034724,0.00019500792,0.0000021925002,0.00083856494,0.010694468,0.017663075,0.77240336,0.0034049593,0.17358479],"study_design_scores_gemma":[0.00024325402,0.000020568239,0.14065884,0.000119720884,0.00002120667,0.000002924102,0.0000051032202,0.80451703,0.00076462555,0.052862775,0.0005458796,0.00023806175],"about_ca_topic_score_codex":0.00100949,"about_ca_topic_score_gemma":0.0000147565615,"teacher_disagreement_score":0.7938226,"about_ca_system_score_codex":0.000029266896,"about_ca_system_score_gemma":0.00007789709,"threshold_uncertainty_score":0.48956177},"labels":[],"label_agreement":null},{"id":"W2562029256","doi":"10.1109/crv.2016.39","title":"Learning Neural Networks with Ranking-Based Losses for Action Retrieval","year":2016,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Manitoba","funders":"","keywords":"Softmax function; Hinge loss; Artificial neural network; Computer science; Ranking (information retrieval); Artificial intelligence; Machine learning; Pattern recognition (psychology); Function (biology); Support vector machine","score_opus":0.019387711974587274,"score_gpt":0.28219914199966795,"score_spread":0.2628114300250807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562029256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07917261,0.000005810171,0.91572076,0.0041072927,0.000073650495,0.00023084151,3.1656387e-7,0.00048350904,0.00020522252],"genre_scores_gemma":[0.93344814,8.4169653e-7,0.06581989,0.00020221848,0.00009586524,0.000036091184,0.0000023488176,0.00001360534,0.00038100468],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990933,0.00005459753,0.0001206852,0.0003372037,0.00015573445,0.00023847111],"domain_scores_gemma":[0.9988749,0.0005411661,0.00009515746,0.00032122605,0.0001065257,0.000061031955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002062606,0.00010861318,0.000096700285,0.000060455128,0.00022723193,0.0001038771,0.00036724092,0.000046885034,0.000022074071],"category_scores_gemma":[0.000112605536,0.000064777036,0.000042894735,0.00026543223,0.000037123493,0.00026011496,0.000043164553,0.00012937281,0.000013533216],"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":[0.00031781595,0.00007657665,0.03215146,0.000020077596,0.000026356529,0.00000194506,0.00007829021,0.61918426,0.0048312237,0.014039701,0.00029287965,0.32897943],"study_design_scores_gemma":[0.0008841004,0.00023447062,0.008825272,0.000013551081,0.000005160147,0.000004149255,0.0000032683877,0.9871287,0.0013939106,0.00014553379,0.0012297829,0.00013211124],"about_ca_topic_score_codex":0.000045539913,"about_ca_topic_score_gemma":0.000014073203,"teacher_disagreement_score":0.8542755,"about_ca_system_score_codex":0.000036344456,"about_ca_system_score_gemma":0.00003399432,"threshold_uncertainty_score":0.2641531},"labels":[],"label_agreement":null},{"id":"W2575068822","doi":"","title":"A Scalable Unsupervised Deep Multimodal Learning System.","year":2016,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Multimodal Machine Learning Applications","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; Acadia University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Scalability; Unsupervised learning; Machine learning; Database","score_opus":0.03201505997780801,"score_gpt":0.33672308778766696,"score_spread":0.30470802780985895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575068822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16552201,0.00022026917,0.7871827,0.04009955,0.0003373842,0.0011340096,0.000005468806,0.0013927604,0.0041058343],"genre_scores_gemma":[0.9834515,0.000043811004,0.0137572475,0.00019490866,0.00040411332,0.00034787736,0.0000021593953,0.000034190267,0.0017642366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956274,0.0010128635,0.000296229,0.0007108275,0.001308126,0.0010445791],"domain_scores_gemma":[0.9957858,0.0018092134,0.00007243363,0.0015186463,0.0005604153,0.00025352268],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048122494,0.0002086299,0.00021815687,0.00007972931,0.0018488909,0.00039134445,0.00285965,0.00013200108,0.00006535609],"category_scores_gemma":[0.00054282835,0.00011611613,0.00023187937,0.0013001072,0.00040304172,0.0004930166,0.0012598351,0.0012474455,0.0015532546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010572696,0.00044639048,0.039435707,0.0005214364,0.00054447807,0.00003686426,0.030755633,0.011927145,0.120733604,0.44561523,0.037749887,0.3121279],"study_design_scores_gemma":[0.0009854543,0.00009918631,0.012255443,0.00010406211,0.000006899729,0.000018589348,0.0006883631,0.96676403,0.0014396983,0.0013637497,0.015985874,0.00028861835],"about_ca_topic_score_codex":0.0010258724,"about_ca_topic_score_gemma":0.000009869916,"teacher_disagreement_score":0.9548369,"about_ca_system_score_codex":0.000406177,"about_ca_system_score_gemma":0.00021739483,"threshold_uncertainty_score":0.99945056},"labels":[],"label_agreement":null},{"id":"W2587335008","doi":"10.29173/cais427","title":"Task-Based Representation of Moving Images","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Multimodal Machine Learning Applications","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":"Task (project management); Representation (politics); Computer science; Construct (python library); Congruence (geometry); Artificial intelligence; Computer vision; Image (mathematics); Psychology","score_opus":0.01778663194423156,"score_gpt":0.2627378118163914,"score_spread":0.24495117987215984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587335008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844321,0.000031223073,0.005529655,0.0047635217,0.000056155168,0.0004505264,0.000027537537,0.00007852513,0.0046307277],"genre_scores_gemma":[0.98156697,0.000008010914,0.018070467,0.00011658605,0.000028421844,0.000069560876,0.000002322993,0.000013703699,0.00012395016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838084,0.000033203396,0.0005072118,0.00035223077,0.00045591025,0.00027060907],"domain_scores_gemma":[0.96938044,0.0002642762,0.0010235015,0.00040860786,0.02883048,0.000092722745],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00036768278,0.00018609052,0.0003492313,0.0001769611,0.00010096828,0.0012756498,0.00255416,0.000088261826,0.000022924196],"category_scores_gemma":[0.010073541,0.0001503218,0.00014329588,0.0006587989,0.00028513573,0.007098847,0.00061318866,0.00022529409,0.000008912536],"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":[0.00003167278,0.0002772841,0.47457907,0.00041825173,0.000074256604,3.2500023e-7,0.01556225,0.00038550817,0.44355142,0.035172097,0.0024969499,0.027450904],"study_design_scores_gemma":[0.0004907291,0.0001542681,0.6766968,0.00019908226,0.000034069617,0.0000069012135,0.00048196755,0.054112107,0.25809437,0.008514196,0.0009596816,0.00025584787],"about_ca_topic_score_codex":0.0018123294,"about_ca_topic_score_gemma":0.0000030373983,"teacher_disagreement_score":0.20211771,"about_ca_system_score_codex":0.00002971555,"about_ca_system_score_gemma":0.00016223209,"threshold_uncertainty_score":0.9997611},"labels":[],"label_agreement":null},{"id":"W2599940792","doi":"10.24963/ijcai.2017/385","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":89,"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","funders":"Agence Nationale de la Recherche; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Task (project management); Utterance; Artificial intelligence; Reinforcement learning; Sequence (biology); Object (grammar); Human–computer interaction; Engineering","score_opus":0.017686626201186408,"score_gpt":0.29341083613172203,"score_spread":0.27572420993053565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599940792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03874923,0.000009674429,0.95287,0.001055582,0.000119067954,0.00029337447,0.0000035544144,0.00010377222,0.0067957416],"genre_scores_gemma":[0.8526888,0.000004306224,0.14698485,0.000045163677,0.00003351991,0.000030844367,0.0000046457576,0.000006606255,0.00020130475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915326,0.000050226,0.00019033512,0.00029834177,0.00017496693,0.00013289826],"domain_scores_gemma":[0.9987137,0.00008758599,0.00018363693,0.00081891177,0.00010035119,0.00009584566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020204483,0.000091081056,0.00014688849,0.00007495482,0.00026906203,0.00035679393,0.00080444815,0.000045539284,0.000010886296],"category_scores_gemma":[0.000117983895,0.000082111794,0.000021551641,0.00008188362,0.000056194895,0.00034289726,0.00037176572,0.000069084046,0.000022611819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000927416,0.00012927486,0.026435252,0.000067368484,0.000042759835,0.000002649314,0.0012735965,0.37020546,0.0047622696,0.5719841,0.0002447258,0.024843229],"study_design_scores_gemma":[0.00020341965,0.000048800408,0.10910697,0.000014725846,0.000004263599,0.0000040494665,0.000009353226,0.8900375,0.00011888625,0.00015470992,0.00019954906,0.000097760516],"about_ca_topic_score_codex":0.0038606506,"about_ca_topic_score_gemma":0.00006977852,"teacher_disagreement_score":0.8139395,"about_ca_system_score_codex":0.000019043346,"about_ca_system_score_gemma":0.00002873353,"threshold_uncertainty_score":0.58361745},"labels":[],"label_agreement":null},{"id":"W2608022654","doi":"10.1109/icpr.2016.7900081","title":"Automatic video description generation via LSTM with joint two-stream encoding","year":2016,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Computer science; Encoding (memory); Artificial intelligence; Convolutional neural network; Closed captioning; Recurrent neural network; RGB color model; Decoding methods; Deep learning; Component (thermodynamics); Feature extraction; Pattern recognition (psychology); Artificial neural network; Image (mathematics); Algorithm","score_opus":0.02855375016983549,"score_gpt":0.2545483060394659,"score_spread":0.22599455586963038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608022654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24962194,0.0000046116975,0.7457481,0.002298009,0.000060710736,0.00016099811,3.4604872e-7,0.00047718518,0.0016280822],"genre_scores_gemma":[0.7567941,0.0000012378096,0.24258071,0.00015985014,0.000072170864,0.00006209978,0.00000192648,0.000008508765,0.00031941812],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890685,0.00007089278,0.000212627,0.00037534864,0.0002315494,0.00020275083],"domain_scores_gemma":[0.9991021,0.00005759316,0.00010797717,0.0005672513,0.00007997086,0.00008508854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023544821,0.00012700862,0.00010882716,0.000105335326,0.00016660847,0.00015594615,0.00031608058,0.000031833726,0.000113180235],"category_scores_gemma":[0.000041036023,0.0000755236,0.000030511625,0.00024217032,0.000029526975,0.00067293993,0.00008693263,0.00007023571,0.000349149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001320587,0.000060317685,0.004089032,0.0000074251125,0.000013700777,0.0000021115832,0.00027955038,0.0007966318,0.54106224,0.051816013,0.00034061618,0.40153107],"study_design_scores_gemma":[0.0004001661,0.00006812809,0.022684108,0.000031514366,0.0000060904313,0.000029043129,0.0000038835524,0.95612884,0.019004442,0.0013190871,0.00015341923,0.00017126635],"about_ca_topic_score_codex":0.00036588134,"about_ca_topic_score_gemma":0.00008888156,"teacher_disagreement_score":0.9553322,"about_ca_system_score_codex":0.0001007725,"about_ca_system_score_gemma":0.000039900853,"threshold_uncertainty_score":0.44877204},"labels":[],"label_agreement":null},{"id":"W2617136920","doi":"10.24963/ijcai.2017/178","title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Comisión Nacional de Investigación Científica y Tecnológica","keywords":"Commonsense knowledge; Computer science; Ontology; Exploit; Commonsense reasoning; Artificial intelligence; Information retrieval; Natural language processing; Question answering; Testbed; Sentence; Visualization; Knowledge retrieval; Benchmark (surveying); Knowledge representation and reasoning; Knowledge extraction; World Wide Web","score_opus":0.014062946221605574,"score_gpt":0.269845979589982,"score_spread":0.25578303336837643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617136920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8764413,0.000009941485,0.1072592,0.014217959,0.00012137083,0.00024585586,0.0000040700006,0.0001878275,0.0015124666],"genre_scores_gemma":[0.9080482,0.000002811162,0.08976924,0.00013738629,0.00004221755,0.000014528465,0.000004365429,0.0000129358705,0.001968293],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986991,0.00012426285,0.00021033692,0.00042367246,0.00022633767,0.00031629042],"domain_scores_gemma":[0.99741,0.00013392205,0.00041329482,0.0017417413,0.00018428976,0.00011673236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034671513,0.00016923473,0.0002565535,0.000094069284,0.00056329963,0.00030926312,0.0015644782,0.00009033712,0.000012568916],"category_scores_gemma":[0.00043020042,0.00015274466,0.00008098491,0.00011098894,0.0002595642,0.0002943865,0.0003536538,0.0004028697,0.000021227701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025847892,0.0005040837,0.24806966,0.00020717537,0.00008272056,0.000044001477,0.0010853383,0.0032073276,0.6384877,0.03800906,0.00046751925,0.06957694],"study_design_scores_gemma":[0.0006977375,0.00031533922,0.11265388,0.0000092529735,0.00000818648,0.000010716705,0.000007973726,0.7799831,0.10481468,0.00010789828,0.0011799576,0.00021130209],"about_ca_topic_score_codex":0.0019504405,"about_ca_topic_score_gemma":0.00022714242,"teacher_disagreement_score":0.7767758,"about_ca_system_score_codex":0.000039874638,"about_ca_system_score_gemma":0.00014224391,"threshold_uncertainty_score":0.6228746},"labels":[],"label_agreement":null},{"id":"W2734498959","doi":"10.48550/arxiv.1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":189,"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":"Affine transformation; Computer science; Benchmark (surveying); Feature (linguistics); Artificial intelligence; Transformation (genetics); Computation; Simple (philosophy); Artificial neural network; Layer (electronics); Image (mathematics); Task (project management); Process (computing); Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Engineering","score_opus":0.05285417320652501,"score_gpt":0.23371162585806823,"score_spread":0.18085745265154324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734498959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44171238,0.000011961099,0.5522514,0.00014922117,0.00011948948,0.00019179478,0.000010613013,0.000313867,0.005239246],"genre_scores_gemma":[0.9759834,0.000012769175,0.021266388,0.00008607025,0.0001253247,0.0000056296726,0.00006141516,0.000027369852,0.0024316534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980289,0.0001232294,0.00014571709,0.0012107425,0.00012246407,0.00036897158],"domain_scores_gemma":[0.997435,0.00007984824,0.00044969472,0.0016685384,0.00018018803,0.00018673138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020068459,0.0003216632,0.00029916796,0.00019795474,0.0006893737,0.00043910916,0.0021173994,0.00022015,0.000042645926],"category_scores_gemma":[0.000053888758,0.00034864526,0.00012337533,0.00022987711,0.0001453016,0.00043864842,0.0017656997,0.0008925571,0.00014780134],"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":[0.000020002566,0.00008283249,0.030172676,0.000035784382,0.00012587414,0.00027399138,0.0002814419,0.69085896,0.00009063642,0.27703,0.00024505626,0.0007827737],"study_design_scores_gemma":[0.00043049437,0.00004510262,0.03615764,0.00013466287,0.000051434752,0.000015729305,0.000016535818,0.9560599,0.000068281945,0.006033161,0.00052157004,0.0004655364],"about_ca_topic_score_codex":0.0014549749,"about_ca_topic_score_gemma":0.00006614381,"teacher_disagreement_score":0.534271,"about_ca_system_score_codex":0.00015661912,"about_ca_system_score_gemma":0.00027061263,"threshold_uncertainty_score":0.9998965},"labels":[],"label_agreement":null},{"id":"W2741237521","doi":"10.24963/ijcai.2017/479","title":"Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Parsing; Residual; Computer science; Boundary (topology); Artificial intelligence; Convolutional neural network; Object (grammar); Cascade; Iterative refinement; Machine learning; Data mining; Pattern recognition (psychology); Algorithm; Mathematics","score_opus":0.026982535933759544,"score_gpt":0.32188678243282126,"score_spread":0.2949042464990617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741237521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00680629,0.00012107116,0.98130417,0.0064383834,0.00026573418,0.00030802784,0.0000048527386,0.00025443803,0.004497022],"genre_scores_gemma":[0.782725,0.000014133667,0.21673547,0.00018465375,0.00012458077,0.00007796542,0.0000041841276,0.0000062909958,0.00012772689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999004,0.000026517124,0.00017471786,0.00040884686,0.00012766857,0.00025826856],"domain_scores_gemma":[0.9987628,0.00009279582,0.00012204276,0.0008438514,0.00007162957,0.00010690686],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00031475167,0.00011259886,0.0001128007,0.000029677738,0.0019460049,0.0006998675,0.00058412354,0.000057640296,0.0000060764078],"category_scores_gemma":[0.000095871124,0.00010719045,0.00003229448,0.00008049729,0.00012083137,0.0003161785,0.00037707115,0.00010478798,0.0000041456024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012720476,0.00007513505,0.03176641,0.000023961562,0.0000423925,0.0000014172113,0.000120354816,0.03069766,0.000039463688,0.07178075,0.0043920935,0.8610476],"study_design_scores_gemma":[0.00030788445,0.000042882566,0.16967943,0.000022355327,0.000010243747,0.000010040811,0.0000113941405,0.82152885,0.000018010105,0.002599072,0.005658024,0.00011178889],"about_ca_topic_score_codex":0.001179554,"about_ca_topic_score_gemma":0.00027262277,"teacher_disagreement_score":0.86093587,"about_ca_system_score_codex":0.00007763218,"about_ca_system_score_gemma":0.00005135885,"threshold_uncertainty_score":0.99935335},"labels":[],"label_agreement":null},{"id":"W2748195089","doi":"10.48550/arxiv.1708.04320","title":"Situation Recognition with Graph Neural Networks","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Salient; Graph; Artificial intelligence; Artificial neural network; Action (physics); Verb; Noun; Task (project management); Machine learning; Natural language processing; Pattern recognition (psychology); Theoretical computer science","score_opus":0.07201039835022935,"score_gpt":0.20474852014659253,"score_spread":0.13273812179636318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748195089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23993926,0.0000141632745,0.7575838,0.00025632442,0.00019870375,0.00029406502,0.000005273532,0.00032217885,0.0013862196],"genre_scores_gemma":[0.9938417,0.00003978615,0.0056312806,0.000067426416,0.00010180253,0.000004863211,0.00009453394,0.000018700151,0.00019987959],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837476,0.00013132229,0.00013231282,0.0010081056,0.000084886145,0.00026858647],"domain_scores_gemma":[0.9974461,0.000083820065,0.0004501399,0.0016799022,0.00020979314,0.00013024974],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019168679,0.00026326822,0.00021647433,0.00020297375,0.00043616618,0.00028992834,0.0017490886,0.00022907201,0.000012648877],"category_scores_gemma":[0.000031993848,0.0002832422,0.00011452605,0.00029867695,0.000108192886,0.0004716887,0.0009220919,0.0007885898,0.00006333571],"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":[0.000020899866,0.00005097728,0.0063270037,0.000018093493,0.000045607776,0.000050516064,0.00009362588,0.9673151,0.000004641324,0.013742166,0.00005545367,0.012275923],"study_design_scores_gemma":[0.00031386496,0.00004164541,0.021834224,0.0000518341,0.000053018564,0.0000057727443,0.000006438674,0.9495686,0.0000072446937,0.027751291,0.000029567083,0.00033649403],"about_ca_topic_score_codex":0.00085699226,"about_ca_topic_score_gemma":0.0001341136,"teacher_disagreement_score":0.75390244,"about_ca_system_score_codex":0.00009081222,"about_ca_system_score_gemma":0.00007418852,"threshold_uncertainty_score":0.999962},"labels":[],"label_agreement":null},{"id":"W2760103357","doi":"10.1609/aaai.v32i1.11671","title":"FiLM: Visual Reasoning with a General Conditioning Layer","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1633,"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 Institute for Advanced Research; Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; CHIST-ERA; Nvidia","keywords":"Affine transformation; Computer science; Benchmark (surveying); Artificial intelligence; Feature (linguistics); Computation; Transformation (genetics); Artificial neural network; Simple (philosophy); Layer (electronics); Visual reasoning; Image (mathematics); Task (project management); Process (computing); Pattern recognition (psychology); Machine learning; Algorithm; Mathematics","score_opus":0.04609872896526987,"score_gpt":0.3260767922855972,"score_spread":0.2799780633203274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760103357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79100204,0.00000525676,0.17647173,0.0035431995,0.00019374285,0.00041501375,0.0000040059776,0.00023350051,0.028131524],"genre_scores_gemma":[0.9699196,0.0000021134451,0.029276734,0.0003045298,0.00015818322,0.00005089476,9.2074714e-7,0.000015317819,0.00027166284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998299,0.000020432397,0.00035550268,0.0005274765,0.00045578732,0.00034180543],"domain_scores_gemma":[0.99832207,0.00007173513,0.0003638454,0.00030944988,0.0008377718,0.00009513875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003468585,0.00020679974,0.00019636878,0.000115263145,0.00044811118,0.0003173928,0.0015250774,0.0000685353,0.00011888668],"category_scores_gemma":[0.00026408088,0.00014790824,0.000063082094,0.0007622186,0.0004312138,0.00038601315,0.00031948692,0.00032974847,0.00019896084],"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":[0.000035144552,0.000084464875,0.001604464,0.000009754689,0.000014368564,2.925658e-7,0.0011574526,0.00013477761,0.04061963,0.9385958,0.00009859842,0.017645305],"study_design_scores_gemma":[0.000045152156,0.00045746396,0.004813696,0.00023803361,0.000013917366,0.000015832587,0.0002458824,0.5578782,0.3977966,0.037987515,0.00020962139,0.00029805608],"about_ca_topic_score_codex":0.0001916777,"about_ca_topic_score_gemma":0.000018149167,"teacher_disagreement_score":0.90060824,"about_ca_system_score_codex":0.000039281756,"about_ca_system_score_gemma":0.00010518274,"threshold_uncertainty_score":0.6031523},"labels":[],"label_agreement":null},{"id":"W2766520430","doi":"10.1145/3123266.3123327","title":"Catching the Temporal Regions-of-Interest for Video Captioning","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":80,"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 Natural Science Foundation of China","keywords":"Closed captioning; Computer science; Focus (optics); Representation (politics); Frame (networking); Artificial intelligence; Region of interest; Image (mathematics); Telecommunications","score_opus":0.1113495865189584,"score_gpt":0.3552552529180734,"score_spread":0.243905666399115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766520430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060626023,0.000010406508,0.91890806,0.017051172,0.00011923696,0.00022783817,0.0000010366792,0.00008518566,0.0029710322],"genre_scores_gemma":[0.8784928,4.508827e-7,0.12089055,0.00015790736,0.000052529263,0.00005498311,0.0000010256341,0.0000053336826,0.00034444954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994282,0.000025564103,0.00015355647,0.00019946464,0.000067802044,0.00012540401],"domain_scores_gemma":[0.9982496,0.0002276908,0.00022192857,0.0011978052,0.00006975943,0.000033224704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037442928,0.0000656692,0.000080467624,0.000028024353,0.0009009818,0.00026003894,0.001615726,0.00002022406,0.0000043604027],"category_scores_gemma":[0.00028564507,0.000044263903,0.000061806786,0.00003776593,0.00007204304,0.0002648079,0.00027715357,0.00010715508,0.000016010335],"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":[0.0000022192085,0.000018632298,0.013574557,0.000008156625,0.000009831423,2.9335573e-7,0.00046106346,0.00030342155,0.0005751383,0.9693827,0.0009176383,0.014746367],"study_design_scores_gemma":[0.0004952208,0.000060784438,0.13605073,0.000054637534,0.000012000186,0.000018440043,0.00010484964,0.7720634,0.0014918636,0.07114102,0.018260282,0.0002468245],"about_ca_topic_score_codex":0.0037083146,"about_ca_topic_score_gemma":0.0003734181,"teacher_disagreement_score":0.89824164,"about_ca_system_score_codex":0.000012468152,"about_ca_system_score_gemma":0.00003592113,"threshold_uncertainty_score":0.6929714},"labels":[],"label_agreement":null},{"id":"W2767290858","doi":"10.1109/msp.2017.2738401","title":"Deep Multimodal Learning: A Survey on Recent Advances and Trends","year":2017,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1067,"is_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":"Deep learning; Computer science; Artificial intelligence; Modalities; Multimodal learning; Field (mathematics); Machine learning; Data science","score_opus":0.027873629156456387,"score_gpt":0.3174627048172625,"score_spread":0.28958907566080616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767290858","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079838745,0.0020770233,0.88946813,0.0058241184,0.00038788567,0.00032020727,0.000008739545,0.000881897,0.021193225],"genre_scores_gemma":[0.98293525,0.00011625097,0.015715549,0.00013378622,0.000121412835,0.000022808726,0.000010768092,0.000025482199,0.0009186745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981601,0.00015493855,0.00025192348,0.0007103377,0.00035538187,0.00036728894],"domain_scores_gemma":[0.9984518,0.0001834392,0.0003805966,0.0006169328,0.00019432619,0.00017289826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062633597,0.0002520614,0.00024635793,0.00016344195,0.0012444635,0.00085966685,0.0010620917,0.00007984553,0.000028922745],"category_scores_gemma":[0.00027954596,0.00022751329,0.0000366057,0.0002524838,0.0001778479,0.0007444028,0.00018786808,0.00049663684,0.000107576656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031735144,0.00008369167,0.013168806,0.000025428877,0.000006593769,0.0000061320657,0.00018133098,0.006134303,0.0009051012,0.00013972318,0.000100567304,0.9792166],"study_design_scores_gemma":[0.00048326654,0.00014876275,0.4356905,0.0000413508,0.000005365518,0.000008241107,0.0000020778039,0.5535587,0.00024600615,0.00034381673,0.009217295,0.00025461003],"about_ca_topic_score_codex":0.00013242537,"about_ca_topic_score_gemma":0.00013885941,"teacher_disagreement_score":0.978962,"about_ca_system_score_codex":0.000036309244,"about_ca_system_score_gemma":0.00006321509,"threshold_uncertainty_score":0.9571533},"labels":[],"label_agreement":null},{"id":"W2775835662","doi":"","title":"IC Decamouaging:: Reverse Engineering Camouflaged ICs within Minutes.","year":2015,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Reverse engineering; Engineering; Forensic engineering; Computer science; Operating system","score_opus":0.02502063523506517,"score_gpt":0.24901010794289805,"score_spread":0.22398947270783287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775835662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066730805,0.000052486263,0.92392176,0.0028760366,0.0002861255,0.00017107715,6.33286e-7,0.00090943556,0.0050516427],"genre_scores_gemma":[0.66467905,4.5285339e-7,0.33367473,0.00038612259,0.00004617938,0.000021544467,0.0000021542915,0.0000126310815,0.001177101],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998859,0.00003841726,0.00021253478,0.0003608396,0.00027702187,0.00025216877],"domain_scores_gemma":[0.99882907,0.000088076406,0.000067701636,0.0006510933,0.00010128746,0.00026278617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004898019,0.00014655481,0.00012957033,0.00011644218,0.00006828502,0.00013259097,0.0007830997,0.000055266206,0.0000128727315],"category_scores_gemma":[0.00024872008,0.00013926245,0.00003957022,0.0004897366,0.00001891532,0.00031710113,0.00026519733,0.00025610084,0.0003649797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018269402,0.00046377684,0.029414756,0.00011168645,0.00013268473,0.00013138767,0.021389857,0.22934712,0.026797535,0.5797532,0.074031234,0.03840845],"study_design_scores_gemma":[0.00036214798,0.000024082836,0.0029515321,0.000009159177,0.000005375105,0.000027978693,0.00005039121,0.98466605,0.002283847,0.0005697506,0.008793801,0.00025587896],"about_ca_topic_score_codex":0.0005860268,"about_ca_topic_score_gemma":0.000025307188,"teacher_disagreement_score":0.75531894,"about_ca_system_score_codex":0.00008071125,"about_ca_system_score_gemma":0.00010072492,"threshold_uncertainty_score":0.5678958},"labels":[],"label_agreement":null},{"id":"W2788713610","doi":"10.1109/wacv.2019.00048","title":"Joint Event Detection and Description in Continuous Video Streams","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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 British Columbia","funders":"","keywords":"Closed captioning; Computer science; Event (particle physics); Context (archaeology); Pooling; Feature (linguistics); Joint (building); Artificial intelligence; Task (project management); Feature extraction; Encoding (memory); Image (mathematics)","score_opus":0.018053724091964162,"score_gpt":0.2600056807491931,"score_spread":0.24195195665722896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788713610","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39380088,0.0000562222,0.60390526,0.00051766576,0.000257839,0.0004782506,0.0000011272267,0.00016614851,0.000816574],"genre_scores_gemma":[0.9747777,0.000024956029,0.02464577,0.0000819311,0.00003851969,0.00013997212,0.0000065649674,0.000012115068,0.00027246962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847656,0.00011404931,0.0003329395,0.0007037815,0.0001830187,0.00018965894],"domain_scores_gemma":[0.9988619,0.00005053261,0.00018642178,0.0007806658,0.00005881423,0.00006163566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038954368,0.0001927078,0.00025573611,0.00022545143,0.000045132765,0.0002399679,0.00038986065,0.00019381563,0.000011162938],"category_scores_gemma":[0.000060451533,0.00018766176,0.000056482124,0.00014128537,0.000019955993,0.00015699593,0.0010045443,0.00063715584,0.00007640595],"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":[0.000009711159,0.00019597917,0.035574157,0.00018856523,0.000029933724,0.0000047028634,0.0012331187,0.047397617,0.01057197,0.009257749,0.00008282678,0.8954537],"study_design_scores_gemma":[0.00021143738,0.000034593777,0.26665044,0.000065776876,0.000004462899,0.000007532965,0.000016571514,0.72681,0.00065760064,0.005180909,0.0001669458,0.00019375561],"about_ca_topic_score_codex":0.006778374,"about_ca_topic_score_gemma":0.0004949809,"teacher_disagreement_score":0.8952599,"about_ca_system_score_codex":0.00015323487,"about_ca_system_score_gemma":0.000053720596,"threshold_uncertainty_score":0.99983555},"labels":[],"label_agreement":null},{"id":"W2789177853","doi":"10.1609/aaai.v32i1.12274","title":"Visual Relationship Detection With Deep Structural Ranking","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Carleton University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence; Complement (music); Representation (politics); Relevance (law); Object (grammar); Machine learning; Pattern recognition (psychology); Function (biology); Image (mathematics)","score_opus":0.047743937746706655,"score_gpt":0.31674477158315684,"score_spread":0.2690008338364502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789177853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70758307,0.0000033850185,0.28609997,0.0011907662,0.00017365933,0.00030758756,5.2252045e-7,0.00014891716,0.004492107],"genre_scores_gemma":[0.98879683,7.539192e-7,0.010918125,0.00008588975,0.000113805494,0.00002940811,2.606652e-7,0.000011854098,0.00004307351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851984,0.000022525352,0.00033682238,0.0004463032,0.00041873645,0.0002557656],"domain_scores_gemma":[0.99847484,0.00012206714,0.00034500993,0.00027647725,0.00071719586,0.00006441605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003300525,0.0001734391,0.00014728431,0.00012977043,0.00052536797,0.00024097446,0.0012342015,0.000070833674,0.000036297966],"category_scores_gemma":[0.00039237415,0.00012170277,0.000053967367,0.0008920235,0.000351119,0.00041022213,0.00020622494,0.00035095247,0.00010620495],"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":[0.000070174035,0.00003736128,0.006326217,0.000013566597,0.000010668618,1.0275799e-7,0.0016823472,0.00013805514,0.03518647,0.8257719,0.0000029282814,0.13076018],"study_design_scores_gemma":[0.000033537108,0.000329199,0.025375286,0.00007713203,0.000010973158,0.00001023555,0.00016731124,0.5554467,0.30689523,0.111442305,0.000016813652,0.00019530783],"about_ca_topic_score_codex":0.00011944346,"about_ca_topic_score_gemma":0.00006991549,"teacher_disagreement_score":0.71432966,"about_ca_system_score_codex":0.000046638495,"about_ca_system_score_gemma":0.000051265102,"threshold_uncertainty_score":0.4962895},"labels":[],"label_agreement":null},{"id":"W2798338993","doi":"10.1109/cvpr.2018.00743","title":"A Face-to-Face Neural Conversation Model","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Conversation; Gesture; Computer science; Dialog box; Avatar; Speech recognition; Face (sociological concept); Natural (archaeology); Artificial intelligence; Human–computer interaction; Natural language processing; Communication; Psychology; Linguistics","score_opus":0.022569612808113572,"score_gpt":0.2964864715879034,"score_spread":0.27391685877978983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798338993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12638877,0.0000011823927,0.8562654,0.011032848,0.000065116365,0.0001636008,6.743028e-7,0.0003386698,0.005743725],"genre_scores_gemma":[0.82517236,1.2379377e-7,0.17241469,0.0015321176,0.0000364945,0.000019557157,0.0000010382608,0.000004889042,0.00081874325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992775,0.000022936469,0.000100695914,0.00028969074,0.00014680326,0.00016241574],"domain_scores_gemma":[0.99926275,0.000030979772,0.00003107951,0.0005023707,0.00007431089,0.00009849375],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000101138176,0.000075372205,0.000060475235,0.00006097668,0.00010347918,0.00008476684,0.00060832227,0.0000279156,0.000034174023],"category_scores_gemma":[0.000037442824,0.00006909064,0.000021612614,0.00027396387,0.000027895112,0.00021825943,0.00020584988,0.00007634531,0.0014670858],"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":[0.000013443536,0.00011784776,0.0034318308,0.000008895657,0.000018053024,0.0000010265225,0.016966239,0.51580614,0.019118274,0.32546493,0.008118758,0.11093457],"study_design_scores_gemma":[0.00009996309,0.00003649629,0.0072135893,0.000001120846,0.0000011141194,0.0000014659346,0.00001787338,0.9898797,0.0009862367,0.0012036953,0.00046944144,0.00008926194],"about_ca_topic_score_codex":0.0002218184,"about_ca_topic_score_gemma":0.000014680938,"teacher_disagreement_score":0.6987836,"about_ca_system_score_codex":0.000025543834,"about_ca_system_score_gemma":0.000025429139,"threshold_uncertainty_score":0.9993104},"labels":[],"label_agreement":null},{"id":"W2798881773","doi":"10.18653/v1/p18-1085","title":"Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Google (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Sentence; Word (group theory); Embedding; Image (mathematics); Semantics (computer science); Inference; Vocabulary; Speech recognition; Linguistics","score_opus":0.02645762873014901,"score_gpt":0.3338192082293743,"score_spread":0.30736157949922527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798881773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2166141,0.0000030666697,0.7548577,0.0007527534,0.000027420248,0.00014688674,0.0000013407126,0.0002842276,0.02731249],"genre_scores_gemma":[0.88843215,3.1762158e-7,0.11053949,0.00015283827,0.00010495966,0.000012505524,0.0000040783425,0.000012526732,0.000741149],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871993,0.00007485694,0.00011575935,0.00041627223,0.00030190896,0.0003712679],"domain_scores_gemma":[0.99929374,0.000119222605,0.00004213957,0.00034521634,0.00008282599,0.00011687301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033358112,0.00012648612,0.000107240645,0.00010612711,0.00039130167,0.0002653838,0.00046578856,0.00004002467,0.00028870397],"category_scores_gemma":[0.000018643868,0.000097209515,0.000026410093,0.0005684016,0.0001668995,0.0004016343,0.00021121632,0.00021261367,0.00040956217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005500515,0.00045642297,0.022088183,0.000034384317,0.00008608816,0.00004062745,0.05414434,0.000056362012,0.016775671,0.8995905,0.0006970308,0.005975399],"study_design_scores_gemma":[0.0016591186,0.0009819575,0.038892414,0.00006151213,0.00001628801,0.00006643925,0.023029435,0.921223,0.011090255,0.0019603213,0.00031957007,0.0006997074],"about_ca_topic_score_codex":0.00032977853,"about_ca_topic_score_gemma":0.00025635256,"teacher_disagreement_score":0.9211666,"about_ca_system_score_codex":0.00011149418,"about_ca_system_score_gemma":0.000058993053,"threshold_uncertainty_score":0.526423},"labels":[],"label_agreement":null},{"id":"W2799002257","doi":"10.1109/cvpr.2018.00886","title":"VirtualHome: Simulating Household Activities Via Programs","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":350,"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; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Intelligence Advanced Research Projects Activity; Samsung; Nvidia","keywords":"Computer science; Task (project management); Representation (politics); Variety (cybernetics); Human–computer interaction; Interface (matter); Code (set theory); Game engine; Natural language; Artificial intelligence; Programming language","score_opus":0.02535626076205967,"score_gpt":0.2773558627617337,"score_spread":0.251999601999674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799002257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.255824,0.0000034900222,0.7325773,0.00056991394,0.00008702365,0.00015167736,2.7876783e-7,0.0010009105,0.009785373],"genre_scores_gemma":[0.85860103,2.225498e-7,0.14052564,0.00021193392,0.00014353126,0.000032490556,0.0000012264129,0.0000121284675,0.0004717753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902374,0.000040106857,0.00014480189,0.0003360452,0.00019987798,0.00025541085],"domain_scores_gemma":[0.9990783,0.00011182769,0.00006653936,0.0006240971,0.00004234955,0.00007689294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013189371,0.00011283926,0.000098196484,0.000067022745,0.00025124179,0.00020367918,0.00065561937,0.000043187047,0.00003243295],"category_scores_gemma":[0.000029545376,0.00009913033,0.000038101953,0.0003737005,0.000092323506,0.0003804652,0.0002759082,0.00013619754,0.0001912764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036793176,0.00021057947,0.023413563,0.000010661793,0.00002290794,0.0000026331545,0.0018254549,0.0011266307,0.008126544,0.085642755,0.00022779455,0.8793868],"study_design_scores_gemma":[0.00019455966,0.00018216186,0.016840156,0.000009617223,0.0000030641008,0.000011853396,0.00003634639,0.9718024,0.0035682155,0.0028026523,0.0042935824,0.0002554047],"about_ca_topic_score_codex":0.0003555948,"about_ca_topic_score_gemma":0.00002476698,"teacher_disagreement_score":0.97067577,"about_ca_system_score_codex":0.000024348343,"about_ca_system_score_gemma":0.000021654985,"threshold_uncertainty_score":0.40424177},"labels":[],"label_agreement":null},{"id":"W2801004733","doi":"10.1109/wacv.2018.00181","title":"Scaling Human-Object Interaction Recognition Through Zero-Shot Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":163,"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 intelligence; Object (grammar); Object detection; Cognitive neuroscience of visual object recognition; Variety (cybernetics); Pattern recognition (psychology); Machine learning; Scaling; Action (physics); Histogram; Computer vision; Image (mathematics); Mathematics","score_opus":0.0710747672886309,"score_gpt":0.3634047171561183,"score_spread":0.2923299498674874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801004733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20225161,0.000004648016,0.7369472,0.0004939369,0.00020611467,0.00011880737,2.4582945e-7,0.0006881724,0.059289273],"genre_scores_gemma":[0.8975622,0.000002460417,0.10138075,0.00032657597,0.00022846574,0.000028221397,0.00001400951,0.000013367779,0.00044395062],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987851,0.00012150909,0.00023166437,0.00044107842,0.00018850809,0.00023216948],"domain_scores_gemma":[0.99912876,0.00014965158,0.00012932862,0.00037733038,0.00016485435,0.00005008341],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000287964,0.00012748863,0.000108528395,0.00009282581,0.000582697,0.00022638316,0.00041428406,0.00006306942,0.00026990758],"category_scores_gemma":[0.00015462366,0.00012385345,0.000054672568,0.00038195832,0.00004399486,0.00079004065,0.00017522342,0.0003531706,0.0017480378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028069204,0.00038189927,0.009094944,0.000044573317,0.0000891814,0.0000061286146,0.011973821,0.003149186,0.11783134,0.10031464,0.0029242334,0.75416195],"study_design_scores_gemma":[0.0009875519,0.0006357144,0.02402682,0.00015983537,0.000029447416,0.0000888283,0.00037657862,0.80444694,0.078698,0.05607014,0.033431813,0.001048301],"about_ca_topic_score_codex":0.0010572262,"about_ca_topic_score_gemma":0.000028767616,"teacher_disagreement_score":0.8012978,"about_ca_system_score_codex":0.00005827864,"about_ca_system_score_gemma":0.000018198392,"threshold_uncertainty_score":0.9990292},"labels":[],"label_agreement":null},{"id":"W2803461564","doi":"10.18653/v1/n18-2122","title":"The Emergence of Semantics in Neural Network Representations of Visual Information","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Victoria","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Semantics (computer science); Computational semantics; Computational linguistics; Artificial intelligence; Artificial neural network; Volume (thermodynamics); Natural language processing; Cognitive science; Association (psychology); Linguistics; Programming language; Operational semantics; Psychology; Epistemology; Philosophy","score_opus":0.01069177315046837,"score_gpt":0.31955754322869806,"score_spread":0.3088657700782297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803461564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2779234,0.000013521554,0.71402746,0.0025575603,0.00017067355,0.00019456206,4.3914122e-7,0.000042910873,0.0050694984],"genre_scores_gemma":[0.97966117,0.0000047470035,0.020231077,0.000038064136,0.000024360785,0.000008328746,0.0000012288119,0.000001274462,0.00002973172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935836,0.00004421659,0.00029510373,0.00006789482,0.00013564869,0.000098769364],"domain_scores_gemma":[0.9992211,0.00015478628,0.00014900364,0.00031712055,0.00014203809,0.000015950254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024513973,0.000037002563,0.000055100005,0.00004113572,0.00008644243,0.000019807185,0.0004181859,0.000016191323,0.000013165497],"category_scores_gemma":[0.00010752285,0.00002713425,0.000018804107,0.0006009246,0.00008037007,0.00030790936,0.00014000136,0.000057235848,0.0000145637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012490029,0.00009497596,0.26481822,0.00002136104,0.000014943009,1.3329594e-7,0.0039305943,0.12492792,0.00086167053,0.5147746,0.0042343773,0.086308695],"study_design_scores_gemma":[0.000049485265,0.00002955529,0.19466537,0.000003089042,8.207805e-7,4.3090847e-7,0.00006171847,0.80347484,0.00039958154,0.0011130704,0.00017772995,0.00002433304],"about_ca_topic_score_codex":0.0005777552,"about_ca_topic_score_gemma":0.00015250573,"teacher_disagreement_score":0.7017378,"about_ca_system_score_codex":0.0000030999092,"about_ca_system_score_gemma":0.00002101832,"threshold_uncertainty_score":0.11065026},"labels":[],"label_agreement":null},{"id":"W2808873503","doi":"10.1109/taslp.2019.2943018","title":"BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation","year":2019,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Multimodal Machine Learning Applications","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":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Generator (circuit theory); Discriminator; Process (computing); Sentence; Adversarial system; Generative grammar; Encoder; Joint (building)","score_opus":0.012741270686931429,"score_gpt":0.2707468446229923,"score_spread":0.2580055739360609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808873503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10281656,0.00026368798,0.8944892,0.001372852,0.00021356967,0.00055024395,0.000014322098,0.0001549779,0.00012454561],"genre_scores_gemma":[0.7315705,0.000023441533,0.26749596,0.00047536864,0.00015692587,0.0000628491,0.000011336305,0.0000149679545,0.00018865762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867165,0.00005331181,0.00023406104,0.0005821617,0.00017320992,0.00028559047],"domain_scores_gemma":[0.99915427,0.00014503668,0.0001136354,0.00034388795,0.00011052463,0.00013265318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002230149,0.00020817085,0.00021596685,0.000106770945,0.00041281918,0.00029929797,0.0002682651,0.00011693554,0.000022038852],"category_scores_gemma":[0.000035809957,0.00019543037,0.00005944648,0.00022975387,0.00008056873,0.00039581937,0.000012570013,0.00027405765,0.000008683194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055541277,0.000074812655,0.00012987913,0.00007162697,0.000038910905,0.0000046760892,0.0019252931,0.014581529,0.03761536,0.00033153212,0.00003757914,0.94513327],"study_design_scores_gemma":[0.001156343,0.00018065564,0.00026689292,0.000050890136,0.00003077919,0.000054664237,0.00020680053,0.9852209,0.012141069,0.0002208975,0.0001842767,0.0002858114],"about_ca_topic_score_codex":0.000068362235,"about_ca_topic_score_gemma":0.00005484265,"teacher_disagreement_score":0.9706394,"about_ca_system_score_codex":0.000035193516,"about_ca_system_score_gemma":0.00008566307,"threshold_uncertainty_score":0.79694194},"labels":[],"label_agreement":null},{"id":"W2882995289","doi":"","title":"Joint Embeddings of Scene Graphs and Images","year":2017,"lang":"en","type":"preprint","venue":"Lirias (KU Leuven)","topic":"Multimodal Machine Learning Applications","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":"Canada Research Chairs; University of Toronto","funders":"Mitacs; KU Leuven","keywords":"Computer science; Representation (politics); Joint (building); Task (project management); Artificial intelligence; Scene graph; Pattern recognition (psychology); Computer vision; Natural language processing","score_opus":0.030922476231541648,"score_gpt":0.30460035726814105,"score_spread":0.2736778810365994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2882995289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73699814,0.0022503925,0.21877025,0.020245597,0.0022906223,0.0016949276,0.0001409012,0.0011753732,0.016433775],"genre_scores_gemma":[0.8918446,0.00011145119,0.107332736,0.00010122802,0.00008150392,0.0000766456,0.000015355065,0.000028160124,0.00040835308],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978683,0.00010285984,0.0004563843,0.0009100266,0.00035698712,0.00030542834],"domain_scores_gemma":[0.9963243,0.00011992524,0.00080225314,0.0024299333,0.00017187258,0.00015171086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005587462,0.00033566516,0.0005567263,0.00025698243,0.00024088977,0.00038131775,0.0019512568,0.00026341222,0.000018489123],"category_scores_gemma":[0.00030648,0.00033362562,0.00018586098,0.000116500174,0.0002340162,0.0002457325,0.0032651867,0.0008431595,0.00004262266],"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":[0.00004610352,0.0007504558,0.026661268,0.00250194,0.00062638026,0.00007459527,0.008753858,0.0069914795,0.020717638,0.32531044,0.0107602,0.59680563],"study_design_scores_gemma":[0.0013366264,0.00017273282,0.40196973,0.0012148252,0.00013413416,0.00006478458,0.00003676545,0.22586088,0.0105848955,0.35117635,0.005784924,0.0016633496],"about_ca_topic_score_codex":0.0018542914,"about_ca_topic_score_gemma":0.000010977284,"teacher_disagreement_score":0.5951423,"about_ca_system_score_codex":0.00003775634,"about_ca_system_score_gemma":0.00013134138,"threshold_uncertainty_score":0.9999116},"labels":[],"label_agreement":null},{"id":"W2884007780","doi":"10.71781/10727","title":"Learning visual representations with neural networks for video captioning and image generation","year":2017,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Multimodal Machine Learning Applications","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":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Closed captioning; Computer science; Artificial intelligence; Artificial neural network; Image (mathematics); Natural language processing; Speech recognition; Computer vision","score_opus":0.03202932803664612,"score_gpt":0.3788374465242605,"score_spread":0.3468081184876144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884007780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47517508,0.00009540771,0.51266205,0.0004872958,0.00035589197,0.0021906348,0.000008931585,0.000027589997,0.008997108],"genre_scores_gemma":[0.80768883,0.0000067133183,0.1825315,0.000020370111,0.00026971303,0.0005163849,0.0015153628,0.00004031852,0.007410797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847496,0.000086147855,0.00025472537,0.0007861363,0.00017089119,0.0002271358],"domain_scores_gemma":[0.9984903,0.00014371777,0.00054322754,0.0005112938,0.00022446238,0.00008703476],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033235605,0.00022314621,0.00023861788,0.00009943969,0.0013558879,0.0027346474,0.0008445887,0.0001175838,0.000047283615],"category_scores_gemma":[0.00017794273,0.00021865025,0.0000427274,0.00010784805,0.000039082883,0.000994187,0.00013239114,0.00040723657,0.000016026635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007678983,0.00006433954,0.0018482823,0.000032068438,0.00008472213,0.000008594551,0.0036904442,0.074789084,0.004510912,0.0005719369,0.00023556461,0.91408724],"study_design_scores_gemma":[0.00045391708,0.00013115969,0.009482702,0.000049890838,0.00004886799,0.000012748619,0.0001812487,0.98740035,0.00042774904,0.000035072437,0.0014922962,0.00028401305],"about_ca_topic_score_codex":0.00061814376,"about_ca_topic_score_gemma":0.0008925091,"teacher_disagreement_score":0.9138033,"about_ca_system_score_codex":0.000030169485,"about_ca_system_score_gemma":0.00010818447,"threshold_uncertainty_score":0.9999442},"labels":[],"label_agreement":null},{"id":"W2886247548","doi":"10.1007/978-3-030-01228-1_48","title":"Visual Reasoning with Multi-hop Feature Modulation","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Computation; Feature (linguistics); Question answering; Natural language processing; Hierarchy; Algorithm","score_opus":0.013293937599181143,"score_gpt":0.279478282932439,"score_spread":0.26618434533325785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886247548","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":[0.0012072027,0.00008135548,0.9952227,0.0009923312,0.00047758888,0.0005233495,0.0000028087047,0.00038265862,0.0011100026],"genre_scores_gemma":[0.29074144,0.000004276257,0.70778024,0.0004910571,0.00041734235,0.000017082235,0.000010851858,0.00004310263,0.0004946007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607176,0.000045290857,0.00034018335,0.0019021892,0.001008905,0.0006316951],"domain_scores_gemma":[0.997177,0.0002706276,0.0003843753,0.0015340853,0.0004348512,0.00019903471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063464756,0.00058053277,0.0004406066,0.0007114352,0.0004659877,0.0006538442,0.002672942,0.00037635755,0.000028166029],"category_scores_gemma":[0.00011344956,0.0004900991,0.000086468965,0.0008517205,0.00067506783,0.00063397316,0.00097872,0.0011721783,0.0001234202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001736493,0.000082856604,0.001829718,0.00004323194,0.000027630538,0.000053270713,0.002126597,0.18161017,0.0004365497,0.012565649,0.00004353847,0.80116343],"study_design_scores_gemma":[0.00031892362,0.00018764495,0.0067715426,0.0003370807,0.000007497288,0.00007212345,1.371872e-7,0.98255897,0.0002582878,0.008096712,0.0007711795,0.00061988557],"about_ca_topic_score_codex":0.00008185491,"about_ca_topic_score_gemma":0.00013770249,"teacher_disagreement_score":0.8009488,"about_ca_system_score_codex":0.00030613336,"about_ca_system_score_gemma":0.00041865694,"threshold_uncertainty_score":0.9997551},"labels":[],"label_agreement":null},{"id":"W2891997820","doi":"10.48550/arxiv.1810.11735","title":"Middle-Out Decoding","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Decoding methods; Computer science; Sequence (biology); Task (project management); Word (group theory); Process (computing); Speech recognition; Dual (grammatical number); Artificial intelligence; Algorithm; Linguistics; Image (mathematics); Engineering; Programming language","score_opus":0.12850826277725302,"score_gpt":0.21877874903884442,"score_spread":0.0902704862615914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891997820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25961328,0.00001920927,0.72892433,0.00021148425,0.0005030675,0.00021303292,0.0000061235346,0.0005296529,0.009979826],"genre_scores_gemma":[0.97688216,0.000025903691,0.021063508,0.0001239107,0.00017018264,0.0000020968516,0.00001279389,0.000021695534,0.0016977687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979496,0.00012943558,0.00018403846,0.0012802243,0.000091518166,0.0003651684],"domain_scores_gemma":[0.99729,0.00013429127,0.0002619965,0.0019519851,0.00017004689,0.00019164821],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000257916,0.00029156962,0.00025745967,0.0002501068,0.00026169053,0.00017942514,0.0029744396,0.00026509777,0.000068999856],"category_scores_gemma":[0.00006935988,0.00035343872,0.00018412816,0.00041802274,0.000121418634,0.00024162658,0.0031906443,0.00070314447,0.0012806786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021510241,0.00023720345,0.033143923,0.0001659594,0.00021344885,0.00019673932,0.0016107307,0.19649473,0.00015414001,0.7609161,0.0018253027,0.005020192],"study_design_scores_gemma":[0.00022284982,0.000024586505,0.0050363797,0.00007760048,0.000033755194,0.0000034190214,0.000013605185,0.9407764,0.00009285387,0.051793676,0.0014875712,0.00043729146],"about_ca_topic_score_codex":0.0003398086,"about_ca_topic_score_gemma":0.000049765065,"teacher_disagreement_score":0.7442817,"about_ca_system_score_codex":0.00019841737,"about_ca_system_score_gemma":0.00015826015,"threshold_uncertainty_score":0.99989176},"labels":[],"label_agreement":null},{"id":"W2894280539","doi":"10.1609/aaai.v33i01.33019062","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":332,"is_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":"Intelligence Advanced Research Projects Activity","keywords":"Computer science; Task (project management); CLIPS; Matching (statistics); Metric (unit); Natural language processing; Artificial intelligence; Sentence; Similarity (geometry); Word (group theory); Recurrent neural network; Artificial neural network; Information retrieval; Image (mathematics)","score_opus":0.04201553110016543,"score_gpt":0.34819292535200913,"score_spread":0.3061773942518437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894280539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8068361,0.000007464449,0.18262063,0.006686264,0.00021389048,0.0012101762,0.0000076920505,0.00009591871,0.002321842],"genre_scores_gemma":[0.9749306,0.0000032081969,0.02439341,0.00025317853,0.00003751437,0.00003596656,8.660089e-7,0.00001114255,0.00033415388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986644,0.000011911237,0.00033367737,0.0004887627,0.00028533884,0.0002159507],"domain_scores_gemma":[0.9987778,0.0001916451,0.00022036974,0.0002936944,0.0004355276,0.000080935424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047352925,0.00015866087,0.00018219177,0.00012449877,0.00013665984,0.00022116306,0.0010796664,0.0000724551,0.00002521988],"category_scores_gemma":[0.0007166441,0.00011846361,0.00006216276,0.0003865473,0.00007435679,0.00027875978,0.00029993404,0.000213129,0.00013030382],"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":[0.00006673208,0.000053095628,0.00024812066,0.000027048727,0.0000037392824,1.9054447e-8,0.0023592515,0.000044132295,0.29089308,0.5551559,0.00004714804,0.15110177],"study_design_scores_gemma":[0.000051873827,0.00034293876,0.0039037785,0.00017722328,0.0000061652863,0.0000016711381,0.00043795464,0.530439,0.4277703,0.036570136,0.00011049203,0.00018847571],"about_ca_topic_score_codex":0.000071697,"about_ca_topic_score_gemma":0.000005881065,"teacher_disagreement_score":0.53039485,"about_ca_system_score_codex":0.000031686155,"about_ca_system_score_gemma":0.000037544683,"threshold_uncertainty_score":0.4830806},"labels":[],"label_agreement":null},{"id":"W2894405212","doi":"10.1167/18.10.136","title":"Totally-Looks-Like: A Dataset and Benchmark of Semantic Image Similarity","year":2018,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Multimodal Machine Learning Applications","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; Similarity (geometry); Artificial intelligence; Representation (politics); Perception; Sketch; Image (mathematics); Semantics (computer science); Pattern recognition (psychology); Information retrieval; Psychology","score_opus":0.009170502743326061,"score_gpt":0.3133320988807346,"score_spread":0.30416159613740856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894405212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80351394,0.00013097384,0.19252865,0.002890479,0.00021412874,0.000114149014,0.00003852725,0.000017324817,0.0005517946],"genre_scores_gemma":[0.8893421,0.0000178141,0.110417895,0.00012561092,0.00007923516,3.4417064e-7,0.0000057376906,0.0000038765374,0.000007359143],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99906725,0.0000697447,0.00033113873,0.00014302597,0.0002833839,0.00010547238],"domain_scores_gemma":[0.9988427,0.00011511242,0.00037183287,0.00037259,0.00020759752,0.00009017581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006328996,0.000075028154,0.00016404936,0.00011371451,0.00008546358,0.0000686785,0.0005010592,0.000036181973,0.000028381466],"category_scores_gemma":[0.00013402678,0.000059398975,0.000039074537,0.00017254909,0.000093661576,0.00043689812,0.00027822604,0.0001912758,0.0000111582085],"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":[0.00023955673,0.001534748,0.022602817,0.00031616393,0.00018194837,0.00012900273,0.0036000654,0.00023442888,0.6322266,0.012331757,0.12426657,0.20233633],"study_design_scores_gemma":[0.0012860295,0.0016857131,0.7794735,0.00025525122,0.000049466475,0.00043913297,0.0000285523,0.19335796,0.0041146763,0.0059215263,0.013125686,0.00026254938],"about_ca_topic_score_codex":0.00006473507,"about_ca_topic_score_gemma":0.0000053877484,"teacher_disagreement_score":0.7568706,"about_ca_system_score_codex":0.000013371552,"about_ca_system_score_gemma":0.000043121752,"threshold_uncertainty_score":0.242222},"labels":[],"label_agreement":null},{"id":"W2900379270","doi":"10.18653/v1/w18-6240","title":"EmojiGAN: learning emojis distributions with a generative model","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Generative grammar; Adversarial system; Emoji; Artificial intelligence; Popularity; Machine learning; Image (mathematics); Set (abstract data type); Task (project management); Generative model; Natural language processing; Social media","score_opus":0.012900485235033779,"score_gpt":0.2699766042742528,"score_spread":0.257076119039219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900379270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06290285,0.0000043887435,0.9183089,0.0031111555,0.000019883359,0.00012611317,0.0000024212457,0.00048364492,0.0150406035],"genre_scores_gemma":[0.65655756,5.856134e-7,0.34169742,0.00017927855,0.000052312396,0.000032554875,0.0000067542837,0.000006885626,0.0014666627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989935,0.000049319406,0.00012535215,0.00039784808,0.00018537047,0.0002485788],"domain_scores_gemma":[0.99908656,0.000049662805,0.000062325395,0.00049014646,0.00020405055,0.0001072766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011892991,0.00012684915,0.00010353477,0.00005623918,0.0005504161,0.00015133877,0.00051488855,0.00003832486,0.00004258541],"category_scores_gemma":[0.000046793768,0.00009736757,0.000029570028,0.00048142156,0.00012004897,0.00027087302,0.00018590176,0.00022399817,0.00031035455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008512961,0.000120476005,0.005862401,0.0000039810843,0.000040797804,0.0000025885786,0.002707139,0.07307916,0.0045575737,0.8942687,0.0016897902,0.017658867],"study_design_scores_gemma":[0.00016151892,0.00011395393,0.0029426268,0.000004377924,0.000004337183,0.0000105514755,0.000020148764,0.9898608,0.0028919731,0.00243936,0.001395306,0.00015505483],"about_ca_topic_score_codex":0.0002035329,"about_ca_topic_score_gemma":0.000059652382,"teacher_disagreement_score":0.9167816,"about_ca_system_score_codex":0.000039789404,"about_ca_system_score_gemma":0.00008854975,"threshold_uncertainty_score":0.42334113},"labels":[],"label_agreement":null},{"id":"W2900626451","doi":"10.1109/cvprw.2018.00260","title":"Image Caption Generation with Hierarchical Contextual Visual Spatial Attention","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Grid; Word (group theory); Context (archaeology); Spatial contextual awareness; Layer (electronics); Context model; Image (mathematics); Object (grammar); Pattern recognition (psychology); Computer vision; Natural language processing; Linguistics; Geography","score_opus":0.013829384278467263,"score_gpt":0.28997068423961525,"score_spread":0.276141299961148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900626451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.361023,9.270647e-7,0.63570046,0.0010783017,0.00006665953,0.00012794299,5.2401265e-7,0.0001874651,0.0018147285],"genre_scores_gemma":[0.83589125,3.1492291e-7,0.16324164,0.00019007103,0.00044294744,0.00002954991,0.000022886132,0.00000773046,0.0001735977],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895716,0.00008719231,0.00015588189,0.00037372444,0.00025025688,0.00017580052],"domain_scores_gemma":[0.99935436,0.000029355588,0.000064035536,0.00029651023,0.00017793382,0.0000777753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016989319,0.00010501995,0.00008261977,0.00007582853,0.00023574513,0.00017789357,0.00025480156,0.000046834957,0.000097081625],"category_scores_gemma":[0.000021806694,0.000083772014,0.000026491876,0.00019563461,0.00012046435,0.00038423613,0.0000863719,0.00013292643,0.00050366356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006287966,0.00040888533,0.010860069,0.000009477723,0.000040256138,0.000007816746,0.00096114015,0.00012743725,0.4941874,0.18708156,0.0011752023,0.30507788],"study_design_scores_gemma":[0.0003877399,0.00033672235,0.07980654,0.0000034817374,0.0000042694633,0.000022608641,0.0000067578544,0.9164748,0.0023565833,0.00026080373,0.0002091841,0.00013047307],"about_ca_topic_score_codex":0.0009659691,"about_ca_topic_score_gemma":0.00034284036,"teacher_disagreement_score":0.9163474,"about_ca_system_score_codex":0.000035073816,"about_ca_system_score_gemma":0.000042352163,"threshold_uncertainty_score":0.6473744},"labels":[],"label_agreement":null},{"id":"W2901786679","doi":"","title":"Keep Drawing It: Iterative language-based image generation and editing.","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal; University of Guelph","funders":"","keywords":"Computer science; Focus (optics); Image (mathematics); Extension (predicate logic); Context (archaeology); Image editing; Simple (philosophy); Artificial intelligence; Computer vision; Human–computer interaction; Programming language","score_opus":0.037735808935367036,"score_gpt":0.21462178105384494,"score_spread":0.1768859721184779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901786679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4431786,0.00000458474,0.554844,0.00046192657,0.00005921005,0.0000690001,0.0000016671219,0.00010684882,0.0012741557],"genre_scores_gemma":[0.9756518,0.0000011286179,0.023412487,0.0004245408,0.00023850966,8.396604e-7,0.000007069857,0.000007291593,0.00025634913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991671,0.00008527128,0.0000816098,0.0004496263,0.000049203496,0.00016722156],"domain_scores_gemma":[0.99927324,0.000074054944,0.00007544895,0.0003779723,0.00011628822,0.00008297787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014179878,0.00010576429,0.00008333899,0.00011000487,0.00032862148,0.00013786538,0.00034156896,0.000043257907,0.000034550983],"category_scores_gemma":[0.000056825607,0.00011852848,0.000029750683,0.00040318744,0.00012187355,0.00047740788,0.00013846852,0.000119555,0.00011051592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063800144,0.00046828177,0.056286532,0.00007983126,0.00014691091,0.00040367234,0.023134612,0.040286865,0.21163657,0.62855196,0.003505614,0.035435323],"study_design_scores_gemma":[0.00032672012,0.000052086834,0.0042800875,0.000009276653,0.000008456103,0.000002354793,0.00008334141,0.9891283,0.0051301997,0.0005522995,0.00029087457,0.00013602046],"about_ca_topic_score_codex":0.00018850616,"about_ca_topic_score_gemma":0.00006266388,"teacher_disagreement_score":0.9488414,"about_ca_system_score_codex":0.00004333822,"about_ca_system_score_gemma":0.000033382606,"threshold_uncertainty_score":0.4833451},"labels":[],"label_agreement":null},{"id":"W2903711666","doi":"10.1109/tpami.2018.2886192","title":"Deep Neural Network Compression by In-Parallel Pruning-Quantization","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":138,"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","keywords":"Computer science; Pruning; Quantization (signal processing); Convolutional neural network; Deep learning; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Computer vision","score_opus":0.01616013985227046,"score_gpt":0.2839327377264118,"score_spread":0.26777259787414137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903711666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010552698,0.00009691096,0.9881208,0.00067511195,0.00016936864,0.0001687701,0.0000049127657,0.00012080298,0.00009060722],"genre_scores_gemma":[0.9909095,0.0000852666,0.008346792,0.0004950365,0.00003537604,0.000036416255,0.0000131412735,0.000012984266,0.00006546466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982785,0.00016299018,0.0004051382,0.0006089643,0.00024583944,0.0002985589],"domain_scores_gemma":[0.99897265,0.00014518829,0.00013953942,0.0005465619,0.0000776681,0.0001183878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024177223,0.00021740819,0.0002733742,0.00036511643,0.00033596155,0.00014428153,0.0005433855,0.00007487475,0.00010744755],"category_scores_gemma":[0.0000053847752,0.00019883139,0.00011420725,0.0017209728,0.00009437478,0.00023926015,0.000012229809,0.00034202044,0.00004674466],"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":[0.000010840322,0.0001415441,0.009928109,0.0000054187185,0.00008394192,0.0000016045553,0.000324743,0.5291747,0.00025612983,0.00022074464,0.000022126784,0.4598301],"study_design_scores_gemma":[0.00009952492,0.000095571304,0.012201124,0.000015072052,0.00007392499,0.0000036569465,0.000009011502,0.984057,0.0029313585,0.00022434478,0.00008551925,0.00020387155],"about_ca_topic_score_codex":0.0027795618,"about_ca_topic_score_gemma":0.0023093875,"teacher_disagreement_score":0.9803568,"about_ca_system_score_codex":0.000029732513,"about_ca_system_score_gemma":0.00000858589,"threshold_uncertainty_score":0.8108109},"labels":[],"label_agreement":null},{"id":"W2905288264","doi":"10.1609/aaai.v33i01.33018885","title":"Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Science and Technology Planning Project of Guangdong Province; National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China","keywords":"Closed captioning; Bounding overwatch; Computer science; Benchmark (surveying); Artificial intelligence; Image (mathematics); Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology)","score_opus":0.030288974158012197,"score_gpt":0.3297025353385947,"score_spread":0.29941356118058254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905288264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8573007,0.00003727442,0.13751484,0.002425926,0.00018712548,0.0013467899,0.000007238001,0.00015116239,0.00102896],"genre_scores_gemma":[0.93381774,0.000002097466,0.065635785,0.00016215531,0.00010006758,0.000105672516,0.0000017563666,0.000019283778,0.00015544456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983677,0.000019935886,0.00039385614,0.00057648454,0.00026854454,0.00037342537],"domain_scores_gemma":[0.9983289,0.00043412542,0.00036787518,0.0002925555,0.00046461227,0.00011188141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005729635,0.00019895098,0.00022995826,0.00009954707,0.0003312401,0.00046053668,0.0009828554,0.00005268254,0.0000249389],"category_scores_gemma":[0.0013231403,0.00016691319,0.000080423015,0.00047190176,0.000068480156,0.00030939028,0.0003710881,0.00023778758,0.00006728993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007693418,0.000083542385,0.0017490707,0.00018632917,0.0000296945,0.0000020077225,0.010834585,0.003596854,0.32986972,0.5658741,0.00006019247,0.08763698],"study_design_scores_gemma":[0.000118150754,0.00028286263,0.0016854458,0.00088587176,0.000030502817,0.000022024009,0.0055292123,0.8895777,0.07674012,0.02454995,0.000052551124,0.0005256294],"about_ca_topic_score_codex":0.00016071224,"about_ca_topic_score_gemma":0.000008769976,"teacher_disagreement_score":0.88598084,"about_ca_system_score_codex":0.00004695094,"about_ca_system_score_gemma":0.000037915946,"threshold_uncertainty_score":0.6806522},"labels":[],"label_agreement":null},{"id":"W2913694129","doi":"10.1145/3279952","title":"Deep Learning–Based Multimedia Analytics","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Multimodal Machine Learning Applications","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 Ottawa","funders":"National Laboratory of Pattern Recognition; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Analytics; Closed captioning; Multimedia; Milestone; Domain (mathematical analysis); Visual analytics; Learning analytics; Data science; Artificial intelligence; Visualization; Image (mathematics)","score_opus":0.017483534786770713,"score_gpt":0.2872168292985619,"score_spread":0.2697332945117912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913694129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031304285,0.00019971245,0.98858106,0.0047544255,0.00008974052,0.0012191714,0.000010761503,0.00091150834,0.0011031802],"genre_scores_gemma":[0.5818354,0.00012350407,0.41721755,0.00028328053,0.000029838147,0.00028914734,0.000055665023,0.000030959356,0.00013467431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974463,0.00027251724,0.000599344,0.00085455703,0.00036553826,0.00046174153],"domain_scores_gemma":[0.9909934,0.0028738906,0.00029937938,0.0052695256,0.0002709331,0.00029286364],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004626168,0.00037061176,0.00035590547,0.0004529027,0.001328339,0.00025784623,0.0035936357,0.00018014312,0.0000619888],"category_scores_gemma":[0.000095377094,0.00039988238,0.00016406717,0.0013415586,0.00026678768,0.00025948064,0.00025411518,0.0011844666,0.00074834697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064995365,0.00076029997,0.0039438535,0.000035454486,0.00007514754,3.9579052e-7,0.000649704,0.104376286,0.00076448073,0.0051276237,0.00001623584,0.884244],"study_design_scores_gemma":[0.00077619246,0.000090515634,0.0077269375,0.00003325712,0.000039467242,0.000007328463,0.000093942086,0.9766108,0.00016216807,0.00080984546,0.013241261,0.00040833198],"about_ca_topic_score_codex":0.00014065909,"about_ca_topic_score_gemma":0.000024627117,"teacher_disagreement_score":0.8838357,"about_ca_system_score_codex":0.000099818,"about_ca_system_score_gemma":0.00009968692,"threshold_uncertainty_score":0.9999718},"labels":[],"label_agreement":null},{"id":"W2933890497","doi":"10.1109/iccv.2019.01040","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Université de Montréal; University of Guelph; Vector Institute","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Extension (predicate logic); Image (mathematics); Code (set theory); Simple (philosophy); Code generation; Artificial intelligence; Natural language processing; Computer vision; Programming language; Key (lock)","score_opus":0.013444786845761662,"score_gpt":0.27378596282388734,"score_spread":0.26034117597812567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2933890497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34246412,0.00008428683,0.6518039,0.00049390085,0.0003494089,0.00040738602,0.000006265688,0.00031318542,0.004077523],"genre_scores_gemma":[0.73544383,0.000009071653,0.2640319,0.00019066477,0.0001456167,0.000032908145,0.00001305937,0.00001550462,0.000117446754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982178,0.00010843637,0.0002917752,0.0009653581,0.00021923332,0.0001973625],"domain_scores_gemma":[0.99844116,0.00028350664,0.00022652849,0.00084644783,0.000114782124,0.00008756053],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034676038,0.00026138316,0.00026952158,0.00017665364,0.00022531995,0.00061244646,0.00036889984,0.000168002,0.000005916333],"category_scores_gemma":[0.00037120003,0.00024978834,0.000040600615,0.00008987547,0.00006209143,0.000079727484,0.0008218282,0.0006775601,0.000010778791],"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":[0.000027942606,0.00014160758,0.059571017,0.00085470435,0.00007172439,0.000017710163,0.0023540116,0.53909725,0.0066845748,0.029128825,0.00023702663,0.3618136],"study_design_scores_gemma":[0.00033728543,0.000037363738,0.018491557,0.00010146643,0.00001102474,0.000008771739,0.0000080278705,0.9794162,0.000474584,0.00072568486,0.00012181235,0.00026624632],"about_ca_topic_score_codex":0.00084307685,"about_ca_topic_score_gemma":0.000007111334,"teacher_disagreement_score":0.4403189,"about_ca_system_score_codex":0.000040941777,"about_ca_system_score_gemma":0.00008156297,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W2944195906","doi":"10.1109/ipas.2018.8708893","title":"A Hierarchical Quasi-Recurrent approach to Video Captioning","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":20,"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":"Closed captioning; Computer science; Encoding (memory); Encoder; Recurrent neural network; Exploit; Representation (politics); Decoding methods; Artificial intelligence; Layer (electronics); Detector; Artificial neural network; Computer vision; Image (mathematics); Algorithm; Telecommunications","score_opus":0.022680602477925558,"score_gpt":0.2990787251192561,"score_spread":0.2763981226413305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944195906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023040943,0.0000055372516,0.92592067,0.0034066136,0.00011621977,0.0002019958,5.246398e-7,0.0003956692,0.046911802],"genre_scores_gemma":[0.5915882,1.702503e-7,0.40744764,0.0005341997,0.00012630486,0.00006211906,0.0000014643254,0.0000051154984,0.00023476913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987875,0.000066674715,0.0001662445,0.00048168754,0.00023335581,0.00026452035],"domain_scores_gemma":[0.9989823,0.000069943686,0.000032658645,0.0006299218,0.0000849854,0.00020019381],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002611614,0.000105649626,0.000100668214,0.00011644604,0.00022549753,0.00015430823,0.00084594503,0.00003713949,0.0000391777],"category_scores_gemma":[0.00010001568,0.0000921016,0.000038993156,0.00052615424,0.00005247851,0.00013819576,0.0003583063,0.00018447683,0.001366346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004906648,0.0002871606,0.0008998524,0.0000055699365,0.000008360726,4.2737543e-7,0.0021727146,0.0003260122,0.00058864726,0.81876194,0.0024521984,0.17449221],"study_design_scores_gemma":[0.00016390091,0.00019389353,0.021594724,0.0000081230355,0.0000024258238,0.000016101945,0.000017378596,0.95693165,0.00019893276,0.0036232236,0.017029528,0.00022014588],"about_ca_topic_score_codex":0.00033767996,"about_ca_topic_score_gemma":0.000015324538,"teacher_disagreement_score":0.9566056,"about_ca_system_score_codex":0.000039122846,"about_ca_system_score_gemma":0.000039307768,"threshold_uncertainty_score":0.9994112},"labels":[],"label_agreement":null},{"id":"W2945922950","doi":"10.1007/978-3-030-20876-9_42","title":"Dynamic Gated Graph Neural Networks for Scene Graph Generation","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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; Graph; Artificial neural network; Artificial intelligence; Theoretical computer science","score_opus":0.014895537652651124,"score_gpt":0.26298440261584144,"score_spread":0.24808886496319033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945922950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048670406,0.00033853212,0.9940907,0.0011436978,0.0021543268,0.0012279566,0.000009421685,0.00030692565,0.0002417692],"genre_scores_gemma":[0.5031593,0.0000254317,0.49493617,0.001204687,0.00034117093,0.00003733726,0.00007399124,0.00005417006,0.00016776955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606717,0.000048682297,0.0005662243,0.0019186939,0.0006548935,0.00074432185],"domain_scores_gemma":[0.9968169,0.0004820023,0.00040645894,0.0017713514,0.0003567183,0.00016662458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007298182,0.000582425,0.00051456346,0.00092558016,0.00043233536,0.00061083125,0.0031985901,0.00039702308,0.000009040521],"category_scores_gemma":[0.00007083414,0.00056016824,0.00022328847,0.0009211121,0.00038603254,0.00046967715,0.0007177775,0.0009413975,0.000023531553],"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":[0.0000032110029,0.00001544621,0.00006948378,0.000016146,0.000008379896,0.0000029386504,0.00007751391,0.68620795,0.00022981981,0.011375175,0.000017384793,0.30197656],"study_design_scores_gemma":[0.00031560045,0.00014088793,0.00048504476,0.000073307245,0.000010805153,0.000023766419,2.7312112e-8,0.9688277,0.00009502723,0.029199187,0.0002475683,0.00058106874],"about_ca_topic_score_codex":0.000081193015,"about_ca_topic_score_gemma":0.00013453381,"teacher_disagreement_score":0.50267255,"about_ca_system_score_codex":0.000216798,"about_ca_system_score_gemma":0.0002802751,"threshold_uncertainty_score":0.999685},"labels":[],"label_agreement":null},{"id":"W2947973444","doi":"10.18653/v1/d19-6401","title":"Structure Learning for Neural Module Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Polytechnique Montréal","funders":"","keywords":"Artificial neural network; Task (project management); Class (philosophy); Simple (philosophy); Sensitivity (control systems); Deep learning","score_opus":0.006695838380215307,"score_gpt":0.24943788624816196,"score_spread":0.24274204786794665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947973444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22632074,0.000012075256,0.77104795,0.0008308781,0.00016099837,0.00025958198,3.4731616e-7,0.0002732808,0.001094145],"genre_scores_gemma":[0.91558284,3.3930561e-7,0.08270051,0.00031621844,0.00006909545,0.000018394354,0.00000710467,0.000009374654,0.0012961429],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992882,0.000026584925,0.000097755255,0.0002944553,0.00008808745,0.00020489107],"domain_scores_gemma":[0.99936634,0.00011915457,0.00004805997,0.00037506118,0.0000428467,0.000048550584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000078427634,0.00008396805,0.0000884574,0.000033980927,0.00010547468,0.000100309575,0.0005215801,0.000047973048,0.000077276345],"category_scores_gemma":[0.000024602661,0.00007196105,0.000043646993,0.00015941267,0.000007802733,0.00016837993,0.00012807087,0.0002135592,0.00005467222],"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":[0.0000015298115,0.000005748857,0.017301934,0.000004013166,0.0000042630822,8.8841965e-8,0.00006147546,0.89503175,0.00082336226,0.0600482,0.00017645814,0.026541166],"study_design_scores_gemma":[0.00017566474,0.00003789459,0.034876518,0.0000014289465,0.0000012252709,0.0000025431234,0.0000031925654,0.96116954,0.000104961895,0.0010451075,0.0024878671,0.000094049836],"about_ca_topic_score_codex":0.00005892152,"about_ca_topic_score_gemma":0.0000040582536,"teacher_disagreement_score":0.6892621,"about_ca_system_score_codex":0.000012493041,"about_ca_system_score_gemma":0.0000099790905,"threshold_uncertainty_score":0.29344863},"labels":[],"label_agreement":null},{"id":"W2949833607","doi":"10.48550/arxiv.1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"","keywords":"Representation (politics); Computer science; Artificial intelligence; Learning to learn; Feature learning; Active learning (machine learning); Data science; Machine learning; Mathematics education; Psychology; Political science","score_opus":0.1648509459164146,"score_gpt":0.25149987939107327,"score_spread":0.08664893347465866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949833607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7718166,0.00027661514,0.20361832,0.0019156069,0.00030426183,0.0009852329,0.0000019649256,0.0010009131,0.0200805],"genre_scores_gemma":[0.9959579,0.00042607228,0.0017510874,0.00003212019,0.00006425404,0.000018375491,0.00005558328,0.00003785294,0.0016567309],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964796,0.00048822747,0.00040900637,0.0020073978,0.00019554024,0.00042026135],"domain_scores_gemma":[0.99673736,0.00045814275,0.0006993539,0.0017431412,0.00019124294,0.00017076982],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006548253,0.00041226056,0.00047537603,0.00055862474,0.00021057474,0.00015597249,0.0015684244,0.0003380669,0.00003263798],"category_scores_gemma":[0.0006125689,0.00048302193,0.00017826643,0.0006204281,0.000078874735,0.0003464748,0.001625415,0.0025190206,0.0003169868],"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":[0.000018525689,0.00014094038,0.15242581,0.00004285411,0.00004178154,0.0005796374,0.00042161424,0.7417468,0.00002837796,0.09458916,0.000014214788,0.009950292],"study_design_scores_gemma":[0.00045432188,0.000088505,0.16599421,0.000121056924,0.000016151598,0.000027553997,0.00004633778,0.81342953,0.000019062232,0.018777188,0.0006203203,0.00040573275],"about_ca_topic_score_codex":0.004433926,"about_ca_topic_score_gemma":0.0007317598,"teacher_disagreement_score":0.22414133,"about_ca_system_score_codex":0.000277364,"about_ca_system_score_gemma":0.00012086649,"threshold_uncertainty_score":0.9997822},"labels":[],"label_agreement":null},{"id":"W2949906242","doi":"10.48550/arxiv.1612.01033","title":"Areas of Attention for Image Captioning","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Pairwise comparison; Transformer; Artificial intelligence; Language model; Image (mathematics); Convolutional neural network; Natural language processing; Pattern recognition (psychology); Machine learning","score_opus":0.05277417207380759,"score_gpt":0.21515213246116632,"score_spread":0.16237796038735874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949906242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20070936,0.000008022538,0.797076,0.00023756507,0.0001444347,0.00030980055,0.000023346885,0.00014231393,0.0013491893],"genre_scores_gemma":[0.97895813,0.0000104006995,0.020195113,0.000013473997,0.00005161402,0.0000053081903,0.00002066146,0.000013184492,0.0007321006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988246,0.00006538667,0.00017162066,0.0006895528,0.00005802907,0.0001908387],"domain_scores_gemma":[0.9982199,0.00014849425,0.00035848658,0.00093803916,0.000262053,0.00007303515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002085587,0.00016280854,0.00020418125,0.00018675879,0.00011826292,0.000044944154,0.0011193934,0.00014264093,0.000012573305],"category_scores_gemma":[0.00006274775,0.0001727449,0.00020032564,0.00020917793,0.00007663613,0.00022640947,0.000816871,0.00020445642,0.000045806504],"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":[0.000023312892,0.00011578139,0.015972663,0.00019693002,0.0001026433,0.000010813432,0.00014347285,0.037911367,0.0036903245,0.9387003,0.00021634575,0.0029160185],"study_design_scores_gemma":[0.00063501985,0.000038469232,0.03914961,0.00017429485,0.000062755935,0.0000023997084,0.000015782998,0.7945886,0.00040006946,0.16435827,0.00022597298,0.00034874113],"about_ca_topic_score_codex":0.00017793821,"about_ca_topic_score_gemma":0.000007747568,"teacher_disagreement_score":0.7782488,"about_ca_system_score_codex":0.00010862965,"about_ca_system_score_gemma":0.00009096106,"threshold_uncertainty_score":0.70443326},"labels":[],"label_agreement":null},{"id":"W2950120176","doi":"10.48550/arxiv.1705.08844","title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Commonsense knowledge; Computer science; Exploit; Ontology; Commonsense reasoning; Artificial intelligence; Information retrieval; Natural language processing; Question answering; Testbed; Benchmark (surveying); Sentence; Knowledge retrieval; Knowledge representation and reasoning; Knowledge extraction; World Wide Web","score_opus":0.04332595075993373,"score_gpt":0.2097428559751148,"score_spread":0.16641690521518107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950120176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7972599,0.000021270283,0.200138,0.0012053703,0.00025149412,0.00040762316,0.000027993483,0.00023384573,0.00045446627],"genre_scores_gemma":[0.9875904,0.000036991278,0.009892225,0.00004644589,0.000064224,0.0000025647223,0.000037782585,0.000029279303,0.002300129],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997586,0.00035655638,0.00024296997,0.0012188631,0.00014492401,0.00045070416],"domain_scores_gemma":[0.9954514,0.00019833243,0.0009978451,0.002780558,0.00036941504,0.00020246272],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003891926,0.00040150547,0.0005654384,0.000319196,0.00044394354,0.00022063393,0.003079822,0.00038706703,0.000007796012],"category_scores_gemma":[0.0002563198,0.00047044505,0.00025653068,0.0003009273,0.0004335939,0.0002551225,0.0018177392,0.0015355371,0.000021745478],"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":[0.00071252434,0.00074758934,0.13163386,0.0010409892,0.00040690156,0.00066509354,0.0011487734,0.76989764,0.0252497,0.062746786,0.00019711815,0.005553026],"study_design_scores_gemma":[0.0007842291,0.00021587386,0.014567789,0.00006225059,0.00006793396,0.0000064757405,0.000013675046,0.97645223,0.0056844796,0.0012408702,0.0004283488,0.00047583977],"about_ca_topic_score_codex":0.0019925684,"about_ca_topic_score_gemma":0.00019540476,"teacher_disagreement_score":0.20655459,"about_ca_system_score_codex":0.00021311904,"about_ca_system_score_gemma":0.00053004845,"threshold_uncertainty_score":0.99977475},"labels":[],"label_agreement":null},{"id":"W2950788030","doi":"10.48550/arxiv.1701.04693","title":"Incremental Learning for Robot Perception through HRI","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Artificial intelligence; Convolutional neural network; Robot; Computer science; Perception; Robot learning; Task (project management); Deep learning; Robotics; Object (grammar); Computer vision; Cognitive neuroscience of visual object recognition; Object detection; Human–robot interaction; Human–computer interaction; Mobile robot; Pattern recognition (psychology); Engineering","score_opus":0.11343942762562877,"score_gpt":0.2520223980097026,"score_spread":0.13858297038407386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950788030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17425011,0.000013328068,0.8213264,0.0003827304,0.00027959328,0.00051527703,0.0000068033805,0.00036919548,0.002856599],"genre_scores_gemma":[0.96199733,0.000042868414,0.036266837,0.00007409242,0.00014287664,0.000010320323,0.00006244513,0.000025396626,0.001377811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980896,0.00012676932,0.00017184373,0.0011818983,0.00009376134,0.0003361135],"domain_scores_gemma":[0.99775857,0.00011562525,0.00042718256,0.0014490648,0.00015081483,0.000098729135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002855003,0.00028892042,0.00027678473,0.00012206135,0.00084481295,0.0002881154,0.0023929963,0.00026379662,0.000031913016],"category_scores_gemma":[0.00010183778,0.0003564092,0.0002395859,0.00013495347,0.00009897485,0.000530599,0.0021095609,0.0008274777,0.00016688506],"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":[0.000028705206,0.00016484005,0.010368138,0.00011680795,0.00010820563,0.000020352658,0.0011875455,0.83260447,0.0006448449,0.14720748,0.0003863176,0.0071622757],"study_design_scores_gemma":[0.0005120124,0.000061582294,0.020926315,0.00006058452,0.00005304959,0.000002878785,0.000084103114,0.95336354,0.000050468905,0.022578431,0.0018722304,0.0004348074],"about_ca_topic_score_codex":0.001452291,"about_ca_topic_score_gemma":0.000038488823,"teacher_disagreement_score":0.78774726,"about_ca_system_score_codex":0.00028091355,"about_ca_system_score_gemma":0.00012281701,"threshold_uncertainty_score":0.9998888},"labels":[],"label_agreement":null},{"id":"W2950895666","doi":"","title":"Visual Reasoning with Multi-hop Feature Modulation","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Hop (telecommunications); Feature (linguistics); Telecommunications","score_opus":0.00956658975243875,"score_gpt":0.25293620468830846,"score_spread":0.24336961493586973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950895666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14543422,0.000049675036,0.8347662,0.008806834,0.000051350635,0.00023218375,0.0000024271953,0.0004691834,0.010187887],"genre_scores_gemma":[0.6004395,0.000005350875,0.3972771,0.000090025205,0.000020836189,0.000028451077,0.00002853484,0.000017447293,0.002092791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968526,0.0015842501,0.00021726839,0.0006639375,0.00036292468,0.0003190413],"domain_scores_gemma":[0.99589604,0.00048721526,0.0002503464,0.0015280979,0.001676414,0.00016186536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019701356,0.00020455573,0.00016503519,0.00014369919,0.00064690225,0.0004072542,0.0011554444,0.000107601285,0.000035808298],"category_scores_gemma":[0.00068012706,0.00019150307,0.000058934467,0.0008624482,0.00020067513,0.0004287711,0.00039814328,0.00031838412,0.00013483659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026561685,0.0010830888,0.049206387,0.000041754593,0.00008620571,0.000006436848,0.021248538,0.00057742454,0.023650758,0.53341407,0.0009640739,0.36969468],"study_design_scores_gemma":[0.00057115534,0.0000013954269,0.13668525,0.00022958968,0.000008579544,0.000019111805,0.00003201212,0.8412803,0.015161955,0.00039879564,0.005329644,0.00028223477],"about_ca_topic_score_codex":0.00086720975,"about_ca_topic_score_gemma":0.0008144855,"teacher_disagreement_score":0.84070283,"about_ca_system_score_codex":0.000067901805,"about_ca_system_score_gemma":0.00010846807,"threshold_uncertainty_score":0.7809268},"labels":[],"label_agreement":null},{"id":"W2952059673","doi":"10.48550/arxiv.1611.07810","title":"A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Automatic summarization; Benchmark (surveying); Artificial intelligence; Task (project management); Vocabulary; Question answering; Machine learning; Language model; Blank; Field (mathematics); Convolutional neural network; Natural language processing; Information retrieval","score_opus":0.3574155743804664,"score_gpt":0.29138193558292586,"score_spread":0.06603363879754054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952059673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046254164,0.000029625377,0.99247205,0.0009158203,0.00006944562,0.0005286279,0.0011101365,0.000048047285,0.0002008408],"genre_scores_gemma":[0.9832369,0.00010963584,0.015626982,0.00004728217,0.000029955494,0.0000066384146,0.00091947056,0.000010032793,0.000013113244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985446,0.00013670175,0.00020402101,0.00085765735,0.00008089749,0.00017616738],"domain_scores_gemma":[0.99726677,0.00048263493,0.0002471149,0.0019176243,0.000049522434,0.00003632246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005829459,0.00016698345,0.00019888482,0.0001310482,0.00013758523,0.000086280896,0.002061284,0.000111015055,0.0000016823517],"category_scores_gemma":[0.00007808473,0.00015106678,0.000034589684,0.0002508446,0.00008482178,0.0016674418,0.0016564905,0.00022753407,0.0000025065563],"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":[0.000014867502,0.00003202908,0.00030248627,0.000083771774,0.000022636963,0.0000047748044,0.0007120647,0.17220552,0.000021556387,0.82607037,0.00033900177,0.00019091966],"study_design_scores_gemma":[0.00022746538,0.000012209688,0.0000870312,0.00008723183,0.000019952327,0.000001004216,0.00009628431,0.5973624,0.0000067319834,0.40186492,0.00012405643,0.00011074701],"about_ca_topic_score_codex":0.0005861498,"about_ca_topic_score_gemma":0.00013233829,"teacher_disagreement_score":0.97861147,"about_ca_system_score_codex":0.00010921726,"about_ca_system_score_gemma":0.00007996379,"threshold_uncertainty_score":0.6160324},"labels":[],"label_agreement":null},{"id":"W2952769376","doi":"10.48550/arxiv.1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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 Toronto; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Intelligence Advanced Research Projects Activity; Samsung; Nvidia","keywords":"Computer science; Task (project management); Variety (cybernetics); Representation (politics); Human–computer interaction; Interface (matter); Code (set theory); Game engine; Artificial intelligence; Programming language","score_opus":0.0827059822227267,"score_gpt":0.21093085153611998,"score_spread":0.12822486931339327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952769376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46049845,0.000008922174,0.5367246,0.00007284093,0.00022768059,0.00031948206,0.0000056581002,0.0008222294,0.0013201148],"genre_scores_gemma":[0.98717356,0.000010262483,0.011829274,0.000059654503,0.00018452725,0.0000060565408,0.00002376118,0.000042106763,0.0006707837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975629,0.00018093962,0.00023040922,0.0014081862,0.00014706302,0.00047048958],"domain_scores_gemma":[0.99711967,0.00019815461,0.00039329613,0.0019794982,0.00011609294,0.00019330216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022983667,0.00040148015,0.00035303537,0.00027171633,0.00036293743,0.00029349356,0.002506396,0.00032662728,0.000019603107],"category_scores_gemma":[0.000042005337,0.00047707913,0.0002141588,0.00068890245,0.00021770575,0.0004446304,0.0031969876,0.0009286389,0.0001363531],"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":[0.000023502547,0.00040390933,0.03633821,0.0001429299,0.00019344273,0.00012972177,0.0010527119,0.86667705,0.00021915293,0.07543692,0.00012913569,0.019253332],"study_design_scores_gemma":[0.00026117414,0.000075534765,0.004788926,0.00007715503,0.000038837064,0.000005168748,0.00003452593,0.973366,0.00010219275,0.020246211,0.00045766935,0.0005466051],"about_ca_topic_score_codex":0.0007280677,"about_ca_topic_score_gemma":0.000034465796,"teacher_disagreement_score":0.5266751,"about_ca_system_score_codex":0.00022001109,"about_ca_system_score_gemma":0.00014189108,"threshold_uncertainty_score":0.9997681},"labels":[],"label_agreement":null},{"id":"W2960202457","doi":"10.1145/3306346.3322941","title":"PlanIT","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":207,"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":"FP7 Ideas: European Research Council; National Science Foundation","keywords":"Computer science; Scene graph; Graph; Relation (database); Generative model; Artificial intelligence; Spatial relation; Representation (politics); Theoretical computer science; Set (abstract data type); Generative grammar; Data mining; Rendering (computer graphics); Programming language","score_opus":0.01302205938873805,"score_gpt":0.2537439968164512,"score_spread":0.24072193742771317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960202457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05737826,0.000010589797,0.93531877,0.004316165,0.00024253232,0.00019812945,0.000005811386,0.00041863654,0.0021110813],"genre_scores_gemma":[0.9571373,0.000014084695,0.041618127,0.0008827762,0.000011490272,0.000033155702,0.0000024030828,0.0000109426155,0.00028975078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914867,0.000036445814,0.00012519483,0.00030909316,0.00020724858,0.00017332735],"domain_scores_gemma":[0.9982659,0.00021550419,0.000038439655,0.0013702133,0.00004065158,0.00006925305],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010922457,0.00010561663,0.00009000828,0.00019650807,0.00015701381,0.00006506983,0.0010649584,0.00006687192,0.000115121875],"category_scores_gemma":[0.000012952557,0.00010408102,0.00007970755,0.00063656626,0.000023627981,0.00018644282,0.000011390375,0.00036597907,0.0012334572],"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":[0.000030341449,0.000979653,0.016688189,0.00005754883,0.00016700769,0.000008001141,0.0014011812,0.026941588,0.0033663088,0.67879516,0.00060520926,0.2709598],"study_design_scores_gemma":[0.0027632432,0.0009527609,0.2585534,0.000097674594,0.000066771914,0.00010502997,0.00009541184,0.47571948,0.005804475,0.15144268,0.10259676,0.0018023365],"about_ca_topic_score_codex":0.0000976817,"about_ca_topic_score_gemma":0.000014765679,"teacher_disagreement_score":0.899759,"about_ca_system_score_codex":0.000015389096,"about_ca_system_score_gemma":0.000025969499,"threshold_uncertainty_score":0.9995442},"labels":[],"label_agreement":null},{"id":"W2962849532","doi":"","title":"Teaching Machines to Describe Images with Natural Language Feedback","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Closed captioning; Computer science; Natural language; Focus (optics); Artificial intelligence; Sentence; Point (geometry); Natural (archaeology); Quality (philosophy); Phrase; Natural language processing; SIGNAL (programming language); Robot; Human–computer interaction; Machine learning; Image (mathematics)","score_opus":0.010935333915803007,"score_gpt":0.28775438830282307,"score_spread":0.2768190543870201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962849532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4898584,0.00025280533,0.4823173,0.010249061,0.0008288963,0.0010901361,0.000012838252,0.0014169947,0.013973565],"genre_scores_gemma":[0.97885436,2.413934e-7,0.019974565,0.00047141887,0.00011744681,0.0000799722,0.000012376479,0.000011339768,0.00047827017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873835,0.00005429094,0.00033521728,0.00022340652,0.00037325974,0.0002754882],"domain_scores_gemma":[0.9984029,0.00003363966,0.00047663265,0.00078541826,0.00018601649,0.00011542778],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033224458,0.00019169967,0.00017617257,0.00015340926,0.0013822416,0.0038662076,0.0013749581,0.000042881795,0.0000013281252],"category_scores_gemma":[0.00017995322,0.00014255011,0.000029939914,0.00013125285,0.000041080642,0.0064504896,0.00024518176,0.00035434705,0.00012436278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025091354,0.00002930847,0.0068464666,0.00045371565,0.00001624234,0.0000059815,0.01595459,0.0122071365,0.0022650543,0.0043273056,0.0009602955,0.9569088],"study_design_scores_gemma":[0.00034518828,0.00004760069,0.03526272,0.00017610723,0.0000055833298,0.00010795004,0.00033837763,0.9607921,0.0002278743,0.00001559467,0.0023836228,0.00029726495],"about_ca_topic_score_codex":0.0024376402,"about_ca_topic_score_gemma":0.000017547753,"teacher_disagreement_score":0.9566116,"about_ca_system_score_codex":0.000050048846,"about_ca_system_score_gemma":0.000046105462,"threshold_uncertainty_score":0.9999178},"labels":[],"label_agreement":null},{"id":"W2962860923","doi":"10.1109/iccv.2019.00285","title":"Lifelong GAN: Continual Learning for Conditional Image Generation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Forgetting; Lifelong learning; Computer science; Artificial intelligence; Artificial neural network; Generative grammar; Machine learning; Image (mathematics); Task (project management); Generative model; Cognitive psychology; Engineering; Psychology","score_opus":0.025556129044986057,"score_gpt":0.31175500620246316,"score_spread":0.2861988771574771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962860923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017464394,0.000029998482,0.9748027,0.002763093,0.00048429344,0.0010250768,0.000026089372,0.00050959503,0.002894774],"genre_scores_gemma":[0.67885303,0.000003375304,0.3160829,0.00037404272,0.0005998739,0.00042356623,0.0012348397,0.000024372963,0.0024040274],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809235,0.000113882095,0.0003588308,0.0008630769,0.00029676303,0.0002750874],"domain_scores_gemma":[0.9982374,0.0002855801,0.00031501843,0.0007119533,0.00036508215,0.00008501432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044737328,0.00025681808,0.00028426904,0.00013831384,0.00023388723,0.00053770316,0.0009377452,0.00023204522,0.00009872669],"category_scores_gemma":[0.00024382678,0.00026550516,0.00017139623,0.00009477812,0.00003773739,0.00024564523,0.00062711345,0.0007467192,0.00035956968],"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":[0.000011716176,0.00018343958,0.005972005,0.00024960734,0.00016599882,0.0000030179503,0.0011938553,0.68428606,0.017381288,0.22284473,0.04409026,0.023618001],"study_design_scores_gemma":[0.00033310853,0.000036745674,0.010812608,0.000013081271,0.000011817455,0.0000042688985,0.000006563098,0.97755593,0.0009476944,0.002866882,0.007090305,0.00032100512],"about_ca_topic_score_codex":0.00018244219,"about_ca_topic_score_gemma":0.000011462624,"teacher_disagreement_score":0.66138864,"about_ca_system_score_codex":0.00007681033,"about_ca_system_score_gemma":0.00022107757,"threshold_uncertainty_score":0.99997973},"labels":[],"label_agreement":null},{"id":"W2962879739","doi":"10.1007/978-3-319-18356-5_22","title":"Learning Paired-Associate Images with an Unsupervised Deep Learning Architecture","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Acadia University","funders":"","keywords":"Computer science; MNIST database; Artificial intelligence; Associative property; Restricted Boltzmann machine; Content-addressable memory; Unsupervised learning; Deep learning; Pattern recognition (psychology); Representation (politics); Boltzmann machine; Modal; Artificial neural network; Machine learning; Mathematics","score_opus":0.01598576285133331,"score_gpt":0.25674946916856856,"score_spread":0.24076370631723526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962879739","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":[0.001656631,0.0003596328,0.99166715,0.0011642305,0.00028809402,0.00053117785,0.0000027795027,0.0009519359,0.0033783917],"genre_scores_gemma":[0.49447995,0.000016810049,0.5038659,0.00041225873,0.0004076814,0.00003290312,0.000031820644,0.00011130356,0.0006413482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939128,0.0002791411,0.0005682864,0.0024407464,0.0017036514,0.0010953848],"domain_scores_gemma":[0.9959734,0.000675042,0.00056650775,0.0016711514,0.0006153887,0.0004985213],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018569162,0.00089111144,0.0007869523,0.0009690173,0.0008317595,0.0010776547,0.004337818,0.000442441,0.000027600696],"category_scores_gemma":[0.00035028296,0.0007672975,0.00013803769,0.0010658447,0.0007491455,0.000813634,0.001378023,0.003783666,0.000083829706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009480142,0.000026051606,0.00074805046,0.000017770444,0.0000138236655,0.00004524261,0.0017516027,0.49241522,0.00007277543,0.0012869872,0.0000021086773,0.5036109],"study_design_scores_gemma":[0.00064204616,0.0010771129,0.0017775476,0.00029006423,0.000022565888,0.0001283121,0.0000020298319,0.95164055,0.00016460387,0.04086651,0.0021171204,0.0012715657],"about_ca_topic_score_codex":0.00023882686,"about_ca_topic_score_gemma":0.0001997927,"teacher_disagreement_score":0.5023393,"about_ca_system_score_codex":0.0004950558,"about_ca_system_score_gemma":0.00068090163,"threshold_uncertainty_score":0.99995935},"labels":[],"label_agreement":null},{"id":"W2963062932","doi":"10.1609/aaai.v30i1.10475","title":"SentiCap: Generating Image Descriptions with Sentiments","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":214,"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":"Australian Research Council; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Australian Government; Institute for Catastrophic Loss Reduction; Nvidia","keywords":"Closed captioning; Computer science; Natural language processing; Stylized fact; Artificial intelligence; Image (mathematics); Vocabulary; Sentiment analysis; Regularization (linguistics); Quality (philosophy); Linguistics","score_opus":0.05085603367949731,"score_gpt":0.29375943901469953,"score_spread":0.24290340533520222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963062932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41940162,0.000004246828,0.5598478,0.012025181,0.00016078963,0.00045070003,0.0000055291875,0.00019175436,0.007912401],"genre_scores_gemma":[0.9397037,0.0000053680865,0.059681393,0.00012390992,0.000044168894,0.0000516675,2.2681293e-7,0.000012731348,0.00037681323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983716,0.000019788291,0.00037575953,0.00048888184,0.00043419888,0.00030976994],"domain_scores_gemma":[0.9985126,0.000085418695,0.00031647604,0.00040079077,0.0005941935,0.000090521266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029578526,0.0001885012,0.00016542443,0.00010004875,0.0002923767,0.00025871216,0.001541168,0.00004763782,0.00007672366],"category_scores_gemma":[0.0002455769,0.00010537715,0.000069664595,0.0005313052,0.00027996392,0.00049385347,0.00033214886,0.00018287599,0.00024103536],"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":[0.000009600783,0.00008342704,0.00082551775,0.000007732024,0.000011061228,2.0665328e-7,0.00027406486,0.00001889268,0.4297092,0.53327614,0.000053587206,0.035730597],"study_design_scores_gemma":[0.00006760168,0.00015672507,0.0021499684,0.0003224641,0.00001953539,0.000011883723,0.0001509321,0.12559877,0.8098933,0.061212502,0.00009694558,0.00031935828],"about_ca_topic_score_codex":0.00006174154,"about_ca_topic_score_gemma":0.0000068983745,"teacher_disagreement_score":0.5203021,"about_ca_system_score_codex":0.000047101697,"about_ca_system_score_gemma":0.00006829986,"threshold_uncertainty_score":0.42971554},"labels":[],"label_agreement":null},{"id":"W2963202404","doi":"","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Plot (graphics); Visual reasoning; Artificial intelligence; Task (project management); Intersection (aeronautics); Bar chart; Scatter plot; Bounding overwatch; Minimum bounding box; Natural language processing; Smoothness; Baseline (sea); Machine learning; Line (geometry); Image (mathematics); Mathematics","score_opus":0.07102971897405239,"score_gpt":0.44039492234294464,"score_spread":0.3693652033688922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963202404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2190443,0.00000939625,0.69070774,0.039500576,0.0013969627,0.0012871212,0.0009371951,0.00086714915,0.04624958],"genre_scores_gemma":[0.9740696,0.0000062763706,0.020351157,0.00019872717,0.00020628508,0.0002615113,0.0031358493,0.000020479483,0.0017501244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981803,0.00012016045,0.00028579668,0.0007332156,0.0004147912,0.0002657225],"domain_scores_gemma":[0.99757487,0.0002649681,0.0004320012,0.0010982217,0.00048436972,0.00014556714],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034573182,0.00018694285,0.00015517557,0.00017652108,0.0014764948,0.0015582578,0.0023045058,0.00007969995,0.00023130665],"category_scores_gemma":[0.0018609014,0.00019709878,0.00007019724,0.00009035876,0.000097819044,0.0013144641,0.0002846577,0.00043972261,0.00020582163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105752915,0.0005289077,0.042169616,0.00001534549,0.0001772226,0.000022415208,0.0023045668,0.021828309,0.008557227,0.8562774,0.0056559485,0.062357273],"study_design_scores_gemma":[0.0005948783,0.00015790132,0.114010684,0.000040308038,0.000009454819,0.0000082522565,0.00011492965,0.8674757,0.00038065534,0.003798467,0.0131649,0.0002438993],"about_ca_topic_score_codex":0.00070076785,"about_ca_topic_score_gemma":0.000044334793,"teacher_disagreement_score":0.8524789,"about_ca_system_score_codex":0.000053515592,"about_ca_system_score_gemma":0.0001124493,"threshold_uncertainty_score":0.99982345},"labels":[],"label_agreement":null},{"id":"W2963245493","doi":"","title":"Modulating early visual processing by language","year":2017,"lang":"en","type":"article","venue":"LillOA (Université de Lille (University Of Lille))","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":147,"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":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research; Nvidia","keywords":"Computer science; Natural language processing; Visual language; Artificial intelligence; Linguistics; Philosophy","score_opus":0.004933358070285787,"score_gpt":0.21979079856117845,"score_spread":0.21485744049089267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963245493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87914675,0.00010258193,0.09786056,0.0022765764,0.000053904532,0.00017183892,0.00001528169,0.00025862458,0.020113848],"genre_scores_gemma":[0.96413845,0.00001681191,0.03131691,0.00005249636,0.000028408405,3.2476567e-7,0.000010842702,0.000018077972,0.00441767],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984644,0.000073798255,0.00012370393,0.0005644919,0.00034425227,0.00042935536],"domain_scores_gemma":[0.99806774,0.00006504744,0.0005153177,0.0010058676,0.00011236712,0.00023365178],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00021591531,0.00020726956,0.00029131575,0.00019923985,0.0025190096,0.00013920618,0.0024717697,0.0001617163,0.00012559949],"category_scores_gemma":[0.00004920734,0.00027911272,0.00015165917,0.00027771236,0.00023495434,0.0013093812,0.0015525585,0.0002876486,0.000076548546],"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":[0.0002293473,0.0007099233,0.1412209,0.0002963029,0.00034880757,0.0005105957,0.106542565,0.0012309991,0.15546496,0.026057493,0.0052989577,0.56208915],"study_design_scores_gemma":[0.0032101148,0.00029752756,0.4960124,0.00016087726,0.00009991091,0.00004916498,0.00701933,0.47904727,0.0023871523,0.00038023494,0.010209645,0.0011263699],"about_ca_topic_score_codex":0.00702558,"about_ca_topic_score_gemma":0.00020919452,"teacher_disagreement_score":0.5609628,"about_ca_system_score_codex":0.0002241393,"about_ca_system_score_gemma":0.00008072499,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W2963299217","doi":"","title":"A Neural Compositional Paradigm for Image Captioning","year":2018,"lang":"en","type":"article","venue":"The HKU Scholars Hub (University of Hong Kong)","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Closed captioning; Computer science; Semantics (computer science); Generalization; Natural language processing; Artificial intelligence; Syntax; Representation (politics); Image (mathematics); Programming language; Mathematics","score_opus":0.01437617044879723,"score_gpt":0.2468396403155849,"score_spread":0.23246346986678768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963299217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5770375,0.0000149787975,0.41609916,0.0058207167,0.00007117462,0.00019056248,0.000011833495,0.00009707839,0.0006569696],"genre_scores_gemma":[0.8925865,0.0000011970355,0.107068546,0.00012660888,0.000055875225,0.0000010945748,0.000009545963,0.0000060364296,0.00014457149],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991811,0.00009086001,0.00008789243,0.0002561096,0.00019258283,0.00019143571],"domain_scores_gemma":[0.99901366,0.00016120172,0.00012654721,0.00047645936,0.00015770638,0.00006442293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034456624,0.000091049056,0.0001139149,0.000084566556,0.0010334722,0.00009680158,0.0012123529,0.000039654085,0.0000439338],"category_scores_gemma":[0.00003015173,0.000092498594,0.000095214236,0.0002738655,0.0003019018,0.0007188755,0.00026561233,0.00021142038,0.00009930932],"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":[0.00030041917,0.00056148745,0.017178005,0.000091836446,0.00032364478,0.000030508356,0.015336234,0.004582933,0.12447823,0.7916766,0.009643005,0.035797108],"study_design_scores_gemma":[0.0012884481,0.00023285719,0.38821405,0.00003624249,0.000051341583,0.000052100015,0.0003140042,0.5917244,0.00079117075,0.014365033,0.0026078133,0.0003225382],"about_ca_topic_score_codex":0.0003155461,"about_ca_topic_score_gemma":0.000029116873,"teacher_disagreement_score":0.77731156,"about_ca_system_score_codex":0.000035403267,"about_ca_system_score_gemma":0.00003967282,"threshold_uncertainty_score":0.7948737},"labels":[],"label_agreement":null},{"id":"W2963398599","doi":"10.1109/cvpr.2016.500","title":"Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":368,"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":"Question answering; Computer science; Image (mathematics); Information retrieval; Knowledge base; Ask price; Representation (politics); Artificial intelligence; Knowledge representation and reasoning; Natural language; Questions and answers; Natural language processing","score_opus":0.015678643470038032,"score_gpt":0.30608828207007777,"score_spread":0.2904096386000397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963398599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11268692,0.000084612795,0.87418854,0.00188644,0.0007044218,0.00035018235,0.000024344665,0.0011447908,0.008929728],"genre_scores_gemma":[0.860045,0.0000042565734,0.1383842,0.00024789752,0.00062176347,0.00013210664,0.000028460025,0.00004149052,0.0004948179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997022,0.00023482725,0.00047598107,0.0013069651,0.00055154966,0.0004086853],"domain_scores_gemma":[0.9966599,0.0005544597,0.00035229398,0.002057219,0.00015207032,0.00022409932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063227955,0.00047443193,0.00037952312,0.00031561157,0.00024391741,0.0005556248,0.0028836327,0.00036247415,0.00014500813],"category_scores_gemma":[0.00017912517,0.0003840553,0.0001947671,0.0001644786,0.00006288561,0.0002613806,0.002280578,0.0010072079,0.0004917232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014443033,0.002154664,0.06905757,0.00040828556,0.00027139878,0.00004278789,0.007818857,0.064433366,0.028507886,0.17770225,0.0018849302,0.6475736],"study_design_scores_gemma":[0.00042790285,0.00006800256,0.052631658,0.00056600355,0.000013888758,0.0000014030866,0.0000054671586,0.91422194,0.002644395,0.028224397,0.00068137376,0.0005135887],"about_ca_topic_score_codex":0.0031629542,"about_ca_topic_score_gemma":0.0000816303,"teacher_disagreement_score":0.84978855,"about_ca_system_score_codex":0.00024909154,"about_ca_system_score_gemma":0.00022664605,"threshold_uncertainty_score":0.9998611},"labels":[],"label_agreement":null},{"id":"W2963499204","doi":"","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives.","year":2018,"lang":"en","type":"article","venue":"British Machine Vision Conference","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"","keywords":"Computer science; Modal; Ranking (information retrieval); Information retrieval; Learning to rank; Artificial intelligence; Simple (philosophy); Image retrieval; Image (mathematics); Machine learning; Data mining; Pattern recognition (psychology)","score_opus":0.010031982784397351,"score_gpt":0.28159681845750656,"score_spread":0.2715648356731092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963499204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24231774,0.0000848574,0.7523491,0.0013681905,0.00014245219,0.000364636,0.00000825354,0.0006299616,0.0027348544],"genre_scores_gemma":[0.90703064,0.000020581912,0.09171885,0.00045896438,0.00012982631,0.00005221535,0.000011912067,0.000033971504,0.00054305105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736243,0.00012693675,0.00038495293,0.0010657669,0.0005393709,0.0005205125],"domain_scores_gemma":[0.99804395,0.00014857428,0.0002608821,0.0007912835,0.00050751807,0.00024778652],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003694295,0.0002931294,0.0003222998,0.0001604899,0.00057780877,0.0012373698,0.0013572602,0.00009239544,0.00028012646],"category_scores_gemma":[0.00022794651,0.00030025735,0.00006668489,0.00073577213,0.00031456546,0.0008504343,0.00063799095,0.00042696318,0.00039798574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025138355,0.00023860631,0.008211326,0.000053929583,0.00002939594,0.000056519057,0.0006470091,0.00004335191,0.011582542,0.015566184,0.0006872564,0.96285874],"study_design_scores_gemma":[0.0008213702,0.00065662584,0.20247556,0.00027197236,0.000013710523,0.00024585647,0.000019484258,0.7900173,0.0015441685,0.0013950008,0.001980978,0.00055796944],"about_ca_topic_score_codex":0.005798887,"about_ca_topic_score_gemma":0.0006568564,"teacher_disagreement_score":0.9623008,"about_ca_system_score_codex":0.000046109642,"about_ca_system_score_gemma":0.00016726773,"threshold_uncertainty_score":0.9999449},"labels":[],"label_agreement":null},{"id":"W2963651499","doi":"10.48550/arxiv.1707.03017","title":"Learning Visual Reasoning Without Strong Priors","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Visual reasoning; Exploit; Machine learning; Normalization (sociology); Benchmark (surveying); Process (computing); Deep learning; Natural language processing","score_opus":0.013999791537374134,"score_gpt":0.282005870834834,"score_spread":0.2680060792974599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963651499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13956815,0.00030254168,0.80333644,0.007620959,0.00027596188,0.0005373049,0.0000074090635,0.0010345681,0.04731669],"genre_scores_gemma":[0.75996035,0.000092493625,0.23386173,0.000033785018,0.000042859017,0.00012126723,0.00013901603,0.00005794009,0.005690564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9914194,0.00515569,0.00059681735,0.0015248358,0.0007038993,0.000599395],"domain_scores_gemma":[0.9910973,0.0011060336,0.0013257542,0.004475157,0.0016868184,0.00030898908],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006455526,0.0005065621,0.0005271061,0.00027337973,0.0015417937,0.0021238434,0.0050203484,0.00038220492,0.000043489566],"category_scores_gemma":[0.004115289,0.0005711151,0.00026362328,0.00027721093,0.00026762325,0.00041909065,0.005625493,0.0022389614,0.00014496285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012690394,0.00081799086,0.0936287,0.00029039028,0.00023827562,0.000016179918,0.027978342,0.0071549555,0.0023187576,0.43581888,0.00040034074,0.43132448],"study_design_scores_gemma":[0.00052099075,9.3723355e-7,0.048379697,0.0019615225,0.000042621195,0.000017635377,0.00007372917,0.9332642,0.0041602966,0.0027318816,0.007990672,0.0008558309],"about_ca_topic_score_codex":0.0041897874,"about_ca_topic_score_gemma":0.00045709737,"teacher_disagreement_score":0.92610925,"about_ca_system_score_codex":0.00019007412,"about_ca_system_score_gemma":0.0005296992,"threshold_uncertainty_score":0.99975806},"labels":[],"label_agreement":null},{"id":"W2963742410","doi":"","title":"DOM-Q-NET: Grounded RL on Structured Language","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Task (project management); Machine learning; The Internet; String (physics); Graph; Natural language processing; Theoretical computer science; World Wide Web","score_opus":0.021628009855171406,"score_gpt":0.34219214213863863,"score_spread":0.32056413228346725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963742410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62262386,0.0000070784395,0.044819307,0.013972667,0.0010985447,0.0005676306,0.000016059254,0.00071843545,0.31617638],"genre_scores_gemma":[0.9865697,0.000005119861,0.004932993,0.0004285628,0.00011463829,0.00007123241,0.000098967255,0.000019612451,0.0077591776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802047,0.00016649002,0.00027144217,0.0006624539,0.0006439083,0.00023522817],"domain_scores_gemma":[0.9984275,0.0003359741,0.00020839348,0.00071092666,0.00022071833,0.00009646684],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017071687,0.0001926039,0.0001554879,0.0002977721,0.00019440973,0.0004183274,0.0012334333,0.0000751849,0.0013699309],"category_scores_gemma":[0.0002951385,0.00018916801,0.00009010274,0.00030198504,0.00005464852,0.00034296289,0.00018489323,0.00064873847,0.0025618544],"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":[0.000028582208,0.00010277187,0.01172502,0.0000045996867,0.00005831782,0.000008548047,0.0026607406,0.025638279,0.01025158,0.9303633,0.00025366124,0.0189046],"study_design_scores_gemma":[0.0012834499,0.0002845776,0.33273754,0.0000818638,0.000009285497,0.000023730763,0.0008105892,0.6405316,0.0015789767,0.017253954,0.0048898403,0.0005146061],"about_ca_topic_score_codex":0.00049764145,"about_ca_topic_score_gemma":0.000023424021,"teacher_disagreement_score":0.91310936,"about_ca_system_score_codex":0.000102150916,"about_ca_system_score_gemma":0.00007744149,"threshold_uncertainty_score":0.99954295},"labels":[],"label_agreement":null},{"id":"W2964028737","doi":"10.18653/v1/w17-2629","title":"Adversarial Generation of Natural Language","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":115,"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; Université de Montréal; Polytechnique Montréal","funders":"Nvidia","keywords":"Natural language generation; Computer science; Adversarial system; Natural language; Context (archaeology); Artificial intelligence; Generative grammar; Probabilistic logic; Natural language understanding; Natural language processing; Rule-based machine translation; Sentence; Language model; Estimator; Theoretical computer science; Mathematics","score_opus":0.02246753577189608,"score_gpt":0.31643478305866657,"score_spread":0.2939672472867705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964028737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5391355,0.000026224108,0.44209456,0.0021962256,0.00040607553,0.0000984804,8.4905014e-7,0.000101646554,0.015940396],"genre_scores_gemma":[0.9201492,3.4318504e-7,0.07928457,0.000043313317,0.00009899986,0.0000031712407,0.0000019487247,0.0000016713614,0.00041675213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966675,0.000012363599,0.00006703525,0.000112453345,0.000085455256,0.000055962322],"domain_scores_gemma":[0.9992081,0.000014236484,0.000081963175,0.0006492967,0.000029122855,0.00001728778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007806464,0.0000334236,0.000044672117,0.00001988404,0.0001447041,0.00007675336,0.00064666447,0.000016314036,0.000018371165],"category_scores_gemma":[0.00008482007,0.000028134002,0.000021245018,0.000021636017,0.000021192547,0.0002266605,0.00014437364,0.000052735788,0.00003359522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034914615,0.00005843146,0.008285578,0.0000072862113,0.000016801872,0.0000023370746,0.0015180679,0.00053073757,0.26925337,0.44137862,0.0012674801,0.2776778],"study_design_scores_gemma":[0.00021689225,0.000010541976,0.09975242,0.0000015128849,0.0000016140294,0.000001335685,0.000005742515,0.8805943,0.018900016,0.00017251901,0.00028482376,0.000058246333],"about_ca_topic_score_codex":0.0011395889,"about_ca_topic_score_gemma":0.000050867744,"teacher_disagreement_score":0.8800636,"about_ca_system_score_codex":0.0000060518523,"about_ca_system_score_gemma":0.000013857714,"threshold_uncertainty_score":0.1722725},"labels":[],"label_agreement":null},{"id":"W2964248098","doi":"10.1007/978-3-030-11018-5_21","title":"Learnable Pooling Methods for Video Classification","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"","keywords":"Pooling; Computer science; Artificial intelligence","score_opus":0.03735968409245802,"score_gpt":0.35151771802476095,"score_spread":0.3141580339323029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964248098","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":[0.000021255253,0.00027282236,0.99134314,0.0019041452,0.0011980206,0.0010313112,0.000003489128,0.00027285228,0.0039529903],"genre_scores_gemma":[0.024776619,0.000011770698,0.9727923,0.001167797,0.00032247332,0.000056863097,0.000009831078,0.00004968889,0.0008126354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632764,0.0000745898,0.0005536782,0.001881227,0.00052122853,0.0006416413],"domain_scores_gemma":[0.99513423,0.0018287491,0.00046996173,0.0020486645,0.0003737963,0.00014459685],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002200134,0.00045520675,0.00051288115,0.00076644536,0.00036677142,0.00060576777,0.003720339,0.00029490152,0.000015734655],"category_scores_gemma":[0.00042271696,0.00044393918,0.0001728632,0.00059478736,0.00029108473,0.0005210874,0.0009059838,0.0009245235,0.00012696533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003314865,0.000015136079,0.000052032756,0.000045022505,0.000007668178,0.0000011199445,0.00020342733,0.066010386,0.0011009956,0.12335434,0.000013834403,0.8091927],"study_design_scores_gemma":[0.00018608356,0.000076588294,0.00031505863,0.000113276146,0.00000784065,0.000015644202,8.795307e-8,0.8424806,0.0006686332,0.14316215,0.012545176,0.000428863],"about_ca_topic_score_codex":0.000062681065,"about_ca_topic_score_gemma":0.0000119386,"teacher_disagreement_score":0.80876386,"about_ca_system_score_codex":0.000364616,"about_ca_system_score_gemma":0.000755832,"threshold_uncertainty_score":0.9998012},"labels":[],"label_agreement":null},{"id":"W2964516821","doi":"","title":"TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Multimodal Machine Learning Applications","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":"BC Research (Canada)","funders":"","keywords":"Computer science; Closed captioning; Benchmarking; Storytelling; Matching (statistics); Videoconferencing; Artificial intelligence; Video tracking; Computer vision; Video processing; Multimedia; Narrative; Image (mathematics); Mathematics","score_opus":0.012794704856313892,"score_gpt":0.24439575751913414,"score_spread":0.23160105266282024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964516821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42966756,0.00024681847,0.5647956,0.0024305847,0.00011340262,0.00022487447,0.0000028186564,0.00028467714,0.0022336494],"genre_scores_gemma":[0.8659985,0.00013238506,0.13313055,0.00011299588,0.00009726835,0.000045738972,0.0000116834235,0.00003686492,0.0004339922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99445134,0.0029063164,0.00044703163,0.0011554222,0.00050586124,0.0005340141],"domain_scores_gemma":[0.99443054,0.0022741961,0.0003634519,0.0015545315,0.001079692,0.00029761292],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006347725,0.00032686093,0.00030854635,0.0003486471,0.0019715417,0.0010647218,0.0010224279,0.00018616162,0.000039150345],"category_scores_gemma":[0.00074813527,0.00036519198,0.0000857305,0.00079897966,0.00042386274,0.0009091378,0.0008736761,0.0007389001,0.00004417831],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023284692,0.00025487712,0.020392712,0.00012533934,0.00007811991,0.0000038129785,0.03342541,0.00041114638,0.084416606,0.033004597,0.00008388709,0.8277802],"study_design_scores_gemma":[0.0009307119,0.000006512407,0.12005142,0.0010834596,0.00004336064,0.000094030125,0.00019096959,0.7802737,0.08460226,0.004731905,0.0071347086,0.00085697876],"about_ca_topic_score_codex":0.0058380384,"about_ca_topic_score_gemma":0.002759401,"teacher_disagreement_score":0.82692325,"about_ca_system_score_codex":0.00015427341,"about_ca_system_score_gemma":0.00012439734,"threshold_uncertainty_score":0.9999723},"labels":[],"label_agreement":null},{"id":"W2968104955","doi":"10.1109/cvpr.2019.00675","title":"Streamlined Dense Video Captioning","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":153,"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 Parks and Wilderness Society","funders":"","keywords":"Closed captioning; Computer science; Event (particle physics); Context (archaeology); Dependency (UML); Task (project management); Artificial intelligence; Storytelling; Sequence (biology); Natural language processing; Image (mathematics); Narrative; Linguistics","score_opus":0.006586964800575043,"score_gpt":0.24543348210477273,"score_spread":0.23884651730419768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968104955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44855323,0.00000764057,0.52859586,0.0017278823,0.00008513165,0.00012039265,2.4205812e-7,0.00039463677,0.020514978],"genre_scores_gemma":[0.86187786,5.1094844e-7,0.13543363,0.00029774828,0.000021409121,0.000010699702,0.0000016277793,0.000004656339,0.0023518426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993631,0.000024735997,0.00010252126,0.00025179322,0.000121973906,0.0001358585],"domain_scores_gemma":[0.9992315,0.00008986589,0.000036642337,0.000549151,0.000040747273,0.00005209167],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000113923634,0.00006365353,0.00006520495,0.000050043538,0.000059951668,0.00008846414,0.00043794117,0.000026397505,0.00023010324],"category_scores_gemma":[0.00003002766,0.00005682588,0.000028480667,0.00019571857,0.000007739642,0.00019189219,0.00013111562,0.00009698366,0.0032218867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030503668,0.00007791683,0.11952795,0.000011040849,0.000017364891,0.0000026103512,0.0005393172,0.012953491,0.013076443,0.78535146,0.0009416072,0.06749777],"study_design_scores_gemma":[0.00028462423,0.00003079301,0.12731713,0.000006482419,0.0000019528748,0.000009771913,0.000014361331,0.8645836,0.00090239,0.002710887,0.0039761197,0.00016186293],"about_ca_topic_score_codex":0.00047348498,"about_ca_topic_score_gemma":0.00001104481,"teacher_disagreement_score":0.85163015,"about_ca_system_score_codex":0.000019938361,"about_ca_system_score_gemma":0.000024827745,"threshold_uncertainty_score":0.99755424},"labels":[],"label_agreement":null},{"id":"W2969127500","doi":"10.1109/cvpr.2019.00853","title":"Progressive Attention Memory Network for Movie Story Question Answering","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":90,"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":"Question answering; Computer science; Inference; Modality (human–computer interaction); Benchmark (surveying); Artificial intelligence; Fusion mechanism; Feature (linguistics); Natural language processing; Scheme (mathematics); Information retrieval; Fusion; Linguistics","score_opus":0.008055523171589318,"score_gpt":0.27657397358735764,"score_spread":0.26851845041576833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969127500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09566401,0.00011631587,0.8979897,0.00164883,0.00036573096,0.0010320625,5.1625165e-7,0.0004137666,0.0027690819],"genre_scores_gemma":[0.7321036,0.0000011166685,0.2659923,0.0001440032,0.00013032406,0.0002643103,0.000009067346,0.000009380643,0.0013458943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912214,0.000091697206,0.00013350538,0.00032432392,0.00012999558,0.00019834093],"domain_scores_gemma":[0.9991749,0.00016792743,0.00010992497,0.00041433593,0.00008729158,0.000045600467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058862416,0.00008944797,0.00012384554,0.00004327286,0.00012716945,0.00007115437,0.00034929786,0.0000453024,0.000022807864],"category_scores_gemma":[0.000045411263,0.00008082426,0.00006841204,0.00015141763,0.000024932084,0.00028462242,0.00009344351,0.000121010424,0.00018202601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005546223,0.00006780414,0.010204943,0.000079995974,0.00003315942,0.0000010041582,0.00030048177,0.049035404,0.0012645104,0.8085345,0.0014318379,0.12899089],"study_design_scores_gemma":[0.0012501735,0.0000506514,0.03448919,0.000038000315,0.0000064060414,0.00000429505,0.000011390325,0.9571294,0.00007886586,0.005313473,0.0014711171,0.00015702656],"about_ca_topic_score_codex":0.00006684647,"about_ca_topic_score_gemma":0.0000032644573,"teacher_disagreement_score":0.908094,"about_ca_system_score_codex":0.000042012944,"about_ca_system_score_gemma":0.000026735452,"threshold_uncertainty_score":0.32959178},"labels":[],"label_agreement":null},{"id":"W2973802306","doi":"10.1109/iccv.2019.00900","title":"Watch, Listen and Tell: Multi-Modal Weakly Supervised Dense Event Captioning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Closed captioning; Computer science; Event (particle physics); Modal; Focus (optics); Feature (linguistics); Representation (politics); Modalities; Ranging; Speech recognition; Audio visual; Natural language processing; Artificial intelligence; Multimedia; Image (mathematics); Linguistics","score_opus":0.023672183288163867,"score_gpt":0.29058380137952466,"score_spread":0.26691161809136077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973802306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28141272,0.00014126507,0.7107077,0.004273359,0.00041708208,0.00084341597,0.000009789968,0.0005949383,0.0015997142],"genre_scores_gemma":[0.75630623,0.000032397347,0.23990658,0.00023899817,0.00007824974,0.000116482144,0.00003371497,0.00003257192,0.0032547573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731386,0.00016455448,0.00045679157,0.0012777502,0.0003778089,0.00040924727],"domain_scores_gemma":[0.9974617,0.0001978248,0.00020859788,0.0017451954,0.00017508405,0.00021164992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044994848,0.00040836324,0.00041590387,0.00013882491,0.000201599,0.0005214847,0.0014633478,0.00031869733,0.00005764828],"category_scores_gemma":[0.00009312705,0.0003819989,0.00015490019,0.00016193824,0.0000635134,0.00019479675,0.003347923,0.0010131326,0.0003938691],"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":[0.000051907482,0.0013854076,0.23734784,0.0015700985,0.0006352888,0.000066375185,0.01711651,0.4654018,0.013553728,0.08461976,0.0028484205,0.17540285],"study_design_scores_gemma":[0.00040252108,0.000025246916,0.09148768,0.00007846658,0.000020552565,0.000020458265,0.000026850596,0.90560305,0.00015600228,0.0006318573,0.0010752755,0.00047204088],"about_ca_topic_score_codex":0.0051028132,"about_ca_topic_score_gemma":0.000115015355,"teacher_disagreement_score":0.47489354,"about_ca_system_score_codex":0.00011762717,"about_ca_system_score_gemma":0.00018199057,"threshold_uncertainty_score":0.9998632},"labels":[],"label_agreement":null},{"id":"W2982151481","doi":"10.1109/iccv.2019.00184","title":"Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive Style","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"McGill University","funders":"","keywords":"Closed captioning; Computer science; Sentence; Artificial intelligence; Encoder; ENCODE; Convolutional neural network; Salient; Natural language processing; Cognition; Speech recognition; Image (mathematics)","score_opus":0.04834636649097077,"score_gpt":0.298771803654511,"score_spread":0.2504254371635402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982151481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5212542,0.0000015452457,0.47297022,0.0001530508,0.00006017369,0.00042661044,0.000002411552,0.000115021394,0.005016801],"genre_scores_gemma":[0.9686899,8.71061e-7,0.030471012,0.00029798504,0.000018159926,0.00030106722,0.00003074885,0.000005595514,0.00018465616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925154,0.000024664638,0.0002235916,0.00018663774,0.00012617049,0.00018739718],"domain_scores_gemma":[0.999371,0.00019255007,0.000085214415,0.00019960014,0.00011530063,0.000036358193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023233326,0.00008759579,0.00010296439,0.00014565948,0.00009637197,0.0001720072,0.00025953312,0.000026218051,0.00003689014],"category_scores_gemma":[0.000064570864,0.00009023596,0.000034134766,0.00014594349,0.000013030402,0.0029223461,0.00010878254,0.00012790269,0.00031336403],"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":[0.000045217068,0.00018734125,0.02262269,0.0001281982,0.000037573784,0.0000014506663,0.02205753,0.0066089737,0.0135684535,0.83948934,0.00032409604,0.09492915],"study_design_scores_gemma":[0.0032387772,0.00016417139,0.18136723,0.00008303983,0.000004755884,0.0000041455255,0.0011891425,0.8085543,0.0016172639,0.0015933459,0.0017747288,0.00040912363],"about_ca_topic_score_codex":0.0008173627,"about_ca_topic_score_gemma":0.000030676558,"teacher_disagreement_score":0.837896,"about_ca_system_score_codex":0.000052208055,"about_ca_system_score_gemma":0.00002270175,"threshold_uncertainty_score":0.4027765},"labels":[],"label_agreement":null},{"id":"W2995439012","doi":"10.1007/978-3-030-58565-5_13","title":"ScanRefer: 3D Object Localization in RGB-D Scans Using Natural Language","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Object (grammar); Computer science; Artificial intelligence; Point cloud; Minimum bounding box; Task (project management); Computer vision; Natural language; Point (geometry); RGB color model; Bounding overwatch; Pattern recognition (psychology); Sentence; Natural language processing; Image (mathematics); Mathematics; Geometry","score_opus":0.018180355763784246,"score_gpt":0.3058155811202975,"score_spread":0.28763522535651326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995439012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06502723,0.0003655115,0.93054646,0.0018797417,0.0012585814,0.00058642036,0.0000046523733,0.00030911094,0.000022272743],"genre_scores_gemma":[0.60072684,0.000003734093,0.39799935,0.0010424305,0.00018070957,0.000019365874,0.000010588026,0.000016752661,2.272137e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99559695,0.00024480405,0.0005692252,0.0020058784,0.0008643883,0.00071876706],"domain_scores_gemma":[0.99754506,0.0003122727,0.0002949859,0.0015203817,0.00015848578,0.00016879899],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008424454,0.00046975387,0.0004964664,0.00091893063,0.00023964109,0.0008027732,0.0042071263,0.00025489178,0.0000051196866],"category_scores_gemma":[0.000410668,0.00046749527,0.00009410977,0.00396651,0.0003152638,0.00047850612,0.004125145,0.0018721927,0.000017307892],"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":[0.0000027560648,0.000035261924,0.0047287717,0.000049833572,0.0000032828705,0.000027518376,0.0035433124,0.838903,0.0010286749,0.00015585912,0.000001744966,0.15151998],"study_design_scores_gemma":[0.00023007864,0.000025445888,0.010219611,0.0002505053,0.0000042291167,0.000020860949,0.0000013581854,0.98351914,0.0012885608,0.0039501563,0.00000925461,0.0004808293],"about_ca_topic_score_codex":0.0041901595,"about_ca_topic_score_gemma":0.00075144327,"teacher_disagreement_score":0.5356996,"about_ca_system_score_codex":0.0006901138,"about_ca_system_score_gemma":0.0009248708,"threshold_uncertainty_score":0.9997777},"labels":[],"label_agreement":null},{"id":"W2996187564","doi":"","title":"Decentralized Distributed PPO: Mastering PointGoal Navigation","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Reinforcement learning; Speedup; Leverage (statistics); Robot; Task (project management); Artificial intelligence; Distributed computing; Computation; Autonomous agent; Compass; Real-time computing; Parallel computing; Algorithm","score_opus":0.059373361083821706,"score_gpt":0.1911636216772524,"score_spread":0.13179026059343069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996187564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3819372,0.0000040685363,0.61638075,0.001026124,0.000032806656,0.000087418935,0.0000056348395,0.00027601374,0.00024996034],"genre_scores_gemma":[0.994449,0.0000049802875,0.005229745,0.00021580819,0.000025920295,5.971312e-7,0.00003005953,0.000008009312,0.000035858615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990555,0.000070407164,0.000113142014,0.0004778898,0.000060729024,0.00022233912],"domain_scores_gemma":[0.99924004,0.000050521583,0.00008604687,0.00036151777,0.000055402317,0.00020645189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000065866436,0.0001172316,0.00011278151,0.00003599506,0.00014396971,0.00007378168,0.00074136665,0.0000471447,0.000035884987],"category_scores_gemma":[0.000040014183,0.00013908384,0.00006300002,0.00077031204,0.000035157493,0.0003988699,0.0002762724,0.00017090449,0.0002666744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077164674,0.00012201865,0.049669314,0.000048591668,0.00006641699,0.00021353175,0.0011615205,0.32851964,0.0066373926,0.6081917,0.00038607657,0.0049065957],"study_design_scores_gemma":[0.00056598196,0.00003300617,0.016475962,0.0000095413925,0.000010938665,0.0000038756903,0.000030201285,0.9785212,0.00039380594,0.0021593657,0.0016253951,0.00017069756],"about_ca_topic_score_codex":0.000102874445,"about_ca_topic_score_gemma":0.0000024005847,"teacher_disagreement_score":0.6500016,"about_ca_system_score_codex":0.00007275185,"about_ca_system_score_gemma":0.000030407144,"threshold_uncertainty_score":0.56716746},"labels":[],"label_agreement":null},{"id":"W2997498756","doi":"10.71781/10271","title":"Visual question answering with modules and language modeling","year":2019,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Multimodal Machine Learning Applications","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":"Question answering; Computer science; Natural language processing; Linguistics; Artificial intelligence; Information retrieval; Philosophy","score_opus":0.0147581786918676,"score_gpt":0.3420031289771181,"score_spread":0.3272449502852505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997498756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8775443,0.00010071944,0.1157502,0.000052743027,0.00006489328,0.00041673848,0.000002956868,0.000010674082,0.0060567753],"genre_scores_gemma":[0.8678582,0.000005577473,0.12962112,0.0000079689935,0.000025244688,0.000034239398,0.00019072178,0.000019612582,0.002237313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899167,0.00003723068,0.00014392598,0.00052329147,0.00016462945,0.00013927874],"domain_scores_gemma":[0.9993777,0.000028865412,0.00011876993,0.00036709127,0.00005639136,0.00005114053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018059813,0.0001664218,0.00018116558,0.00008908753,0.000103718514,0.0005331754,0.00064063305,0.00010154959,0.000028243707],"category_scores_gemma":[0.000016384383,0.0001504866,0.000016248587,0.00012304257,0.0000075175103,0.00039461974,0.000142218,0.0002409722,0.00010986549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003951658,0.000056029672,0.0005637003,0.000066307155,0.000035990888,0.0000081000835,0.010014753,0.03365798,0.0040161004,0.0010487253,0.0000037736827,0.95048904],"study_design_scores_gemma":[0.0001914871,0.000050215363,0.0022544174,0.00018393567,0.000014684946,0.000006136858,0.00049145083,0.99582154,0.0006085055,0.000039461844,0.00010426007,0.00023388311],"about_ca_topic_score_codex":0.001402859,"about_ca_topic_score_gemma":0.00037572245,"teacher_disagreement_score":0.96216357,"about_ca_system_score_codex":0.000023882221,"about_ca_system_score_gemma":0.00006908011,"threshold_uncertainty_score":0.61366653},"labels":[],"label_agreement":null},{"id":"W2997514790","doi":"10.1609/aaai.v34i07.6783","title":"Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":57,"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 intelligence; Scene graph; Probabilistic logic; Generative model; Graph; Theoretical computer science; Minimum bounding box; Pattern recognition (psychology); Generative grammar; Image (mathematics)","score_opus":0.09663262041000328,"score_gpt":0.3077191104554348,"score_spread":0.21108649004543154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997514790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037718892,0.000023864814,0.94647914,0.01339174,0.00026029465,0.001467639,0.000004490745,0.00015426593,0.00049968506],"genre_scores_gemma":[0.9661045,0.000008962849,0.032326583,0.00095282507,0.00026676556,0.00030717603,0.0000035972141,0.000017521532,0.0000120744635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980345,0.000032866283,0.0005435964,0.000695923,0.00034898042,0.00034414284],"domain_scores_gemma":[0.9982093,0.00012410781,0.0004155723,0.00029191494,0.00081189594,0.00014719866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032932972,0.00025516062,0.0002613881,0.000083009945,0.0003818216,0.0003085366,0.0017517329,0.00009285558,0.000016468892],"category_scores_gemma":[0.0006803833,0.00020149919,0.00016484164,0.0009198263,0.00021385193,0.00031304845,0.00026435664,0.0003379356,0.000014334292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042926175,0.00008360852,0.00018317168,0.000034107437,0.000015510646,9.5151385e-8,0.0011725444,0.064152814,0.026919916,0.8618849,0.00010876514,0.045401655],"study_design_scores_gemma":[0.00003516171,0.00023208659,0.00015586261,0.000022560132,0.000014504512,0.0000011983878,0.000058872272,0.88915527,0.04297586,0.06714015,0.000016717131,0.00019174989],"about_ca_topic_score_codex":0.000039739658,"about_ca_topic_score_gemma":0.000014013362,"teacher_disagreement_score":0.9283856,"about_ca_system_score_codex":0.000029529043,"about_ca_system_score_gemma":0.000053004875,"threshold_uncertainty_score":0.82168984},"labels":[],"label_agreement":null},{"id":"W2997948740","doi":"10.1609/aaai.v34i07.6893","title":"Region-Based Global Reasoning Networks","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Western University","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Focus (optics); Visual reasoning; Artificial intelligence; Pixel; Semantics (computer science); Action (physics); Machine learning; Geography; Cartography","score_opus":0.07076003573598823,"score_gpt":0.3006842134052787,"score_spread":0.22992417766929046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997948740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034580253,0.000020905249,0.9071784,0.04434573,0.00019636874,0.00045984908,0.000002573933,0.00034337808,0.012872552],"genre_scores_gemma":[0.9852633,0.000004700887,0.013017108,0.0015617799,0.00009869202,0.000029870022,4.665084e-7,0.0000099586305,0.000014162095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982907,0.000023242414,0.0004141617,0.00056282204,0.00039322753,0.00031580692],"domain_scores_gemma":[0.99860084,0.000091414586,0.00037965484,0.00033166027,0.00043148475,0.000164952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022883079,0.00020513176,0.00021587963,0.000034749886,0.00023130803,0.0002463126,0.0025872597,0.00008656694,0.000022786237],"category_scores_gemma":[0.0006992504,0.00016426256,0.00012084574,0.0011328578,0.0001860894,0.00021320881,0.00036162866,0.00038282893,0.00008412056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032536605,0.000054127868,0.0029196795,0.000015783433,0.000006911227,4.5836208e-7,0.00027878897,0.006987311,0.0009589098,0.93941456,0.00019219915,0.049138762],"study_design_scores_gemma":[0.000024660538,0.00010974645,0.0014949437,0.000097861215,0.000007534641,0.0000023107102,0.000063746156,0.9589363,0.013455164,0.02550786,0.00012261029,0.00017730244],"about_ca_topic_score_codex":0.000105393745,"about_ca_topic_score_gemma":0.0000033420963,"teacher_disagreement_score":0.95194894,"about_ca_system_score_codex":0.000049884246,"about_ca_system_score_gemma":0.00010996423,"threshold_uncertainty_score":0.66984326},"labels":[],"label_agreement":null},{"id":"W2998392846","doi":"","title":"HoME: a Household Multimodal Environment.","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Computer science; Generalization; Human–computer interaction; Robotics; Context (archaeology); Semantics (computer science); Reinforcement learning; Artificial intelligence; Transfer of learning; Multimodal interaction; Robot; Programming language","score_opus":0.011182462263243625,"score_gpt":0.21810827262158627,"score_spread":0.20692581035834265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998392846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1680132,0.000089095745,0.7974841,0.010391608,0.00008567278,0.00023608874,0.000010142508,0.0005638326,0.023126276],"genre_scores_gemma":[0.7285982,0.000029468642,0.26882115,0.00017736861,0.000028231456,0.00004849095,0.000021148831,0.000024220448,0.002251722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996275,0.0018473185,0.0003301805,0.0007511754,0.00040002514,0.0003962899],"domain_scores_gemma":[0.9957867,0.000759474,0.0002258344,0.0025610325,0.0004494103,0.00021751907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002435743,0.00022225344,0.00018706683,0.00015091868,0.0005725223,0.00034488074,0.0020715615,0.00010830364,0.00015415454],"category_scores_gemma":[0.0004386771,0.00023486215,0.00010302648,0.00050877506,0.0003255485,0.00034229472,0.0008750628,0.0003044466,0.0006181675],"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":[0.000009619565,0.0011961211,0.020691806,0.000029369736,0.00006518979,0.000006341505,0.013739276,0.00020352092,0.025208376,0.67317855,0.00202029,0.26365155],"study_design_scores_gemma":[0.0018069799,0.0000028541465,0.1813269,0.00027464805,0.000028675358,0.00004738564,0.000055358196,0.63460374,0.07871157,0.010681318,0.091342166,0.0011184389],"about_ca_topic_score_codex":0.0010892478,"about_ca_topic_score_gemma":0.00014455413,"teacher_disagreement_score":0.6624972,"about_ca_system_score_codex":0.00007876897,"about_ca_system_score_gemma":0.00007877497,"threshold_uncertainty_score":0.95774},"labels":[],"label_agreement":null},{"id":"W3000176874","doi":"10.1109/iccv.2019.00999","title":"LayoutVAE: Stochastic Scene Layout Generation From a Label Set","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":140,"is_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":"MNIST database; Computer science; Set (abstract data type); Image (mathematics); Artificial intelligence; Autoencoder; Theoretical computer science; Computer vision; Deep learning; Programming language","score_opus":0.02946545474529133,"score_gpt":0.28468178264534616,"score_spread":0.25521632790005483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000176874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42159557,0.000018383553,0.57400393,0.0016068005,0.00016691361,0.00018722749,0.000010689852,0.00026755402,0.002142948],"genre_scores_gemma":[0.870343,3.4815469e-7,0.12756783,0.00064186606,0.000105915664,0.000025689324,0.000052081552,0.000010190148,0.0012530453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998941,0.00005071438,0.00016169186,0.0004353916,0.00022254427,0.00018862511],"domain_scores_gemma":[0.998952,0.000082206105,0.00006432086,0.00076179806,0.000059002625,0.00008069291],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012162149,0.000117919815,0.00011989917,0.00005534158,0.00008135938,0.00014770753,0.00060242455,0.00005537568,0.0002555057],"category_scores_gemma":[0.00002904965,0.00010665893,0.000028631348,0.00023002824,0.000011692536,0.00024975135,0.00018790044,0.00014669009,0.0026126755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016073729,0.00048791454,0.031894516,0.000015745696,0.00011696573,0.0000056911954,0.0034197061,0.07869617,0.1717818,0.6279227,0.012902307,0.07274039],"study_design_scores_gemma":[0.0003660475,0.00002536936,0.016622135,0.000004263477,0.0000037787445,0.0000017983054,0.0000077615805,0.981055,0.00037469782,0.0009270826,0.000467238,0.0001448218],"about_ca_topic_score_codex":0.0016425526,"about_ca_topic_score_gemma":0.000038168073,"teacher_disagreement_score":0.90235883,"about_ca_system_score_codex":0.00003296661,"about_ca_system_score_gemma":0.000042456726,"threshold_uncertainty_score":0.9981639},"labels":[],"label_agreement":null},{"id":"W3003423830","doi":"10.1109/tmm.2020.2971171","title":"Dual Convolutional LSTM Network for Referring Image Segmentation","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":48,"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; National Natural Science Foundation of China","keywords":"Encoder; Focus (optics); Dual (grammatical number); Segmentation; Image segmentation; Intersection (aeronautics); Natural language; Object (grammar)","score_opus":0.02954615709882722,"score_gpt":0.2871377927065734,"score_spread":0.25759163560774617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003423830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056992564,0.000013523807,0.98794794,0.00459194,0.00047779805,0.00060073583,0.00006163355,0.00047357817,0.00013359761],"genre_scores_gemma":[0.5473573,0.000003945435,0.45133245,0.00070482877,0.00023208659,0.0002782416,0.000020889278,0.000017893051,0.000052340838],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985922,0.00006432397,0.00027722216,0.0004915754,0.00026291728,0.00031178686],"domain_scores_gemma":[0.99889946,0.00040046938,0.00009474799,0.0002922171,0.00010648238,0.0002066453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015727317,0.0001765225,0.00015718529,0.00006546501,0.00037494896,0.000087827444,0.00035407,0.00007751896,0.00006951528],"category_scores_gemma":[0.000025380383,0.00019055011,0.0001197095,0.00036585567,0.00005279952,0.0003484878,0.0000040713426,0.00030539322,0.0003039661],"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":[0.0001748564,0.00039525735,0.00023666481,0.00007565265,0.00016285149,0.000006661555,0.0032513451,0.68982285,0.06766746,0.0030980108,0.0054058935,0.22970249],"study_design_scores_gemma":[0.0009602084,0.00011839403,0.0017605877,0.000010536581,0.000020908421,0.0000040376203,0.000021375621,0.9848876,0.010516799,0.00021213364,0.0012732965,0.00021411608],"about_ca_topic_score_codex":0.00006236133,"about_ca_topic_score_gemma":0.000011588933,"teacher_disagreement_score":0.54165804,"about_ca_system_score_codex":0.00007207753,"about_ca_system_score_gemma":0.0000672161,"threshold_uncertainty_score":0.7770408},"labels":[],"label_agreement":null},{"id":"W3004831296","doi":"10.1109/bibm47256.2019.8983272","title":"Multitask and Multimodal Neural Network Model for Interpretable Analysis of X-ray Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Optech (Canada)","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Closed captioning; Artificial neural network; Pattern recognition (psychology); Natural language processing; State (computer science); Image (mathematics)","score_opus":0.008721184977760824,"score_gpt":0.27077729390256783,"score_spread":0.262056108924807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004831296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24242005,0.000030655232,0.75649124,0.00026330655,0.000035534114,0.00028351223,0.00001060355,0.000078751815,0.00038632457],"genre_scores_gemma":[0.64972806,0.0000014388513,0.3497258,0.00009730991,0.000008107905,0.000028861386,0.0000064234114,0.0000056429544,0.00039835932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899566,0.00003001419,0.00023364155,0.00039956224,0.00011620363,0.00022494291],"domain_scores_gemma":[0.99886775,0.00029686894,0.00010819213,0.0005685516,0.0000949978,0.00006362621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002324287,0.00011772538,0.0002853626,0.00015008764,0.000060652732,0.00006427692,0.0004919577,0.000042658725,0.000020478878],"category_scores_gemma":[0.00003672594,0.000101382306,0.00012363793,0.0005233906,0.000031881522,0.0002662458,0.0002374494,0.0000881237,0.0000075730977],"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":[0.0000068725462,0.000027708282,0.03287651,0.000011385558,0.00012894555,4.564591e-8,0.0002196875,0.95377934,0.001532883,0.00631913,0.00008765467,0.0050098607],"study_design_scores_gemma":[0.00025900177,0.000030028563,0.049015064,0.0000035351616,0.00008737584,2.3461772e-7,0.000007297249,0.95002806,0.00007174744,0.0003692554,0.000018321523,0.000110080226],"about_ca_topic_score_codex":0.00041351208,"about_ca_topic_score_gemma":0.000027281185,"teacher_disagreement_score":0.40730798,"about_ca_system_score_codex":0.000011217346,"about_ca_system_score_gemma":0.000016449667,"threshold_uncertainty_score":0.41342503},"labels":[],"label_agreement":null},{"id":"W3012812419","doi":"10.1109/iros45743.2020.9340914","title":"One-Shot Informed Robotic Visual Search in the Wild","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Australian Centre for Field Robotics","keywords":"Computer science; Artificial intelligence; Robot; Visual search; Computer vision; Viewpoints; Task (project management); Field (mathematics); Similarity (geometry); Human–computer interaction; Focus (optics); Flexibility (engineering); Robotics; Image (mathematics)","score_opus":0.11714171087324242,"score_gpt":0.38875510885397835,"score_spread":0.2716133979807359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012812419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03267714,0.000027280874,0.87471616,0.06557563,0.00016230613,0.0012373596,0.0000017338836,0.00044852792,0.025153842],"genre_scores_gemma":[0.93254477,0.000010407518,0.064619966,0.0024451555,0.0000945514,0.00017143143,0.000025857698,0.000012139625,0.000075745294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979058,0.000213794,0.00034394243,0.00061724114,0.00059485744,0.00032437418],"domain_scores_gemma":[0.998168,0.00044792987,0.00009026775,0.0011406795,0.000056765297,0.00009637261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052257767,0.00020402222,0.0002507443,0.0001639906,0.00009880459,0.00046803366,0.0034771482,0.00015672731,0.00003503176],"category_scores_gemma":[0.00017172766,0.00016103384,0.00008785308,0.0006309804,0.000051416722,0.0001363581,0.002724064,0.0017684643,0.00040007816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018567194,0.0007645646,0.020159421,0.00052973063,0.000104826846,0.000029007291,0.024926074,0.40071392,0.00028016977,0.41215342,0.0023078362,0.13801247],"study_design_scores_gemma":[0.00013549105,0.000035874127,0.13379297,0.000035173754,0.000004541048,0.0000026196,0.00005420351,0.8614722,0.000028625638,0.003874981,0.0003584109,0.00020491969],"about_ca_topic_score_codex":0.002741287,"about_ca_topic_score_gemma":0.00017644964,"teacher_disagreement_score":0.8998676,"about_ca_system_score_codex":0.000085579384,"about_ca_system_score_gemma":0.00041373973,"threshold_uncertainty_score":0.7683196},"labels":[],"label_agreement":null},{"id":"W3014594587","doi":"10.1007/978-3-030-58586-0_27","title":"ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 Guelph; Vector Institute","funders":"","keywords":"Pooling; Proxy (statistics); Scaling; Metric (unit); Computer science; Similarity (geometry); Recall; Precision and recall; Task (project management); Component (thermodynamics); Artificial intelligence; Algorithm; Machine learning; Pattern recognition (psychology); Mathematics; Image (mathematics); Psychology","score_opus":0.01792349795523812,"score_gpt":0.29121482040543406,"score_spread":0.27329132245019594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014594587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022231193,0.0006233417,0.96362996,0.011881341,0.00030734538,0.0008889075,0.000005317157,0.00039702147,0.000035553592],"genre_scores_gemma":[0.5730398,0.000016370046,0.42599058,0.00067549606,0.00020638667,0.0000491244,0.0000091553575,0.000012938059,1.3640854e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946683,0.00025462764,0.00073447684,0.002737457,0.0009102348,0.0006949151],"domain_scores_gemma":[0.9964653,0.00052645983,0.00053733983,0.0019301249,0.00022982806,0.0003109021],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001461721,0.00053924206,0.00085908646,0.0009770032,0.0004118241,0.0016114127,0.0037869094,0.00020758109,0.0000032094226],"category_scores_gemma":[0.00051972346,0.00051399175,0.00019907024,0.0051581953,0.00034866994,0.00042914032,0.0076165986,0.0015990908,0.000010113428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003513213,0.000061889245,0.058553647,0.00034354886,0.000104698316,0.0000360776,0.0029546265,0.40022597,0.0010054988,0.0036504427,0.0000017446451,0.53305835],"study_design_scores_gemma":[0.00013629001,0.000036665057,0.045765493,0.0002581152,0.00006204056,0.000014915748,4.8638816e-7,0.93513745,0.00035651482,0.01770965,0.000018821042,0.0005035672],"about_ca_topic_score_codex":0.00033211804,"about_ca_topic_score_gemma":0.000014534116,"teacher_disagreement_score":0.5508086,"about_ca_system_score_codex":0.00022522663,"about_ca_system_score_gemma":0.00037202987,"threshold_uncertainty_score":0.9997312},"labels":[],"label_agreement":null},{"id":"W3014867697","doi":"10.3390/sym12040511","title":"Attentive Gated Graph Neural Network for Image Scene Graph Generation","year":2020,"lang":"en","type":"article","venue":"Symmetry","topic":"Multimodal Machine Learning Applications","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":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Embedding; Graph; Artificial neural network; Scene graph; Visualization; Image (mathematics); Relation (database); Graph embedding; Computer vision; Theoretical computer science; Data mining","score_opus":0.026025546355178602,"score_gpt":0.27781754890669424,"score_spread":0.2517920025515156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014867697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09234086,0.00009509811,0.89813507,0.008003123,0.0002699562,0.00044976096,0.00001198417,0.00036955494,0.00032458353],"genre_scores_gemma":[0.77562916,0.0000031297286,0.2219858,0.0017845547,0.00044993917,0.0000534924,0.000060072878,0.000015748152,0.000018072931],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875265,0.00008295373,0.00020996922,0.00048927387,0.00016698327,0.0002981593],"domain_scores_gemma":[0.99917656,0.00008996378,0.00011203358,0.0003565263,0.00012318658,0.00014175255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016471633,0.0001455459,0.00014993969,0.00006989606,0.00026046607,0.00015138176,0.0005570685,0.00005639946,0.000009084906],"category_scores_gemma":[0.00009459271,0.00014477503,0.00011790013,0.0010832506,0.000038285823,0.00025331223,0.00013474046,0.00018579383,0.000060807986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009736546,0.000400466,0.051118724,0.00020412811,0.0003627107,0.000030003797,0.0025659169,0.062229045,0.15279417,0.35249624,0.13959962,0.23810162],"study_design_scores_gemma":[0.0003959134,0.00008489889,0.016768837,0.0000047597246,0.00001394112,0.000002953712,0.000008042451,0.97702736,0.0017791728,0.002474328,0.0012383378,0.00020148583],"about_ca_topic_score_codex":0.000081562524,"about_ca_topic_score_gemma":0.0000047188946,"teacher_disagreement_score":0.91479826,"about_ca_system_score_codex":0.000015294843,"about_ca_system_score_gemma":0.000021199145,"threshold_uncertainty_score":0.5903754},"labels":[],"label_agreement":null},{"id":"W3014973596","doi":"10.48550/arxiv.2004.00760","title":"Consistent Multiple Sequence Decoding","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Decoding methods; Computer science; Fusion mechanism; Context (archaeology); Sequential decoding; List decoding; Sequence (biology); Closed captioning; Task (project management); Algorithm; Pattern recognition (psychology); Artificial intelligence; Theoretical computer science; Fusion; Image (mathematics); Concatenated error correction code; Block code","score_opus":0.1794902213038457,"score_gpt":0.22722523727327126,"score_spread":0.04773501596942556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014973596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16998932,0.000023787366,0.8253406,0.001223606,0.00027154532,0.0003458159,0.000019457606,0.00070140295,0.0020844364],"genre_scores_gemma":[0.97069836,0.00003515351,0.028666403,0.00029923982,0.000058695787,0.0000033723154,0.00002205674,0.000019692845,0.00019701169],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978174,0.00014933062,0.00021161625,0.0013970578,0.00010092733,0.00032367403],"domain_scores_gemma":[0.9976193,0.0002658337,0.0002780113,0.0014335176,0.00013387896,0.0002694798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016076534,0.00030104842,0.00030548775,0.00014749885,0.00022690263,0.00016649991,0.002482448,0.00020010298,0.000022275442],"category_scores_gemma":[0.00018382586,0.0003726322,0.00020567518,0.00054684415,0.00010576938,0.00021509154,0.0030774677,0.0008963788,0.00040580088],"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":[0.000014142843,0.00009042346,0.030826038,0.00011193772,0.000112728834,0.00034942923,0.0004781246,0.49842557,0.00090575434,0.46566132,0.00030185035,0.002722692],"study_design_scores_gemma":[0.0002663574,0.000017959002,0.0049617304,0.000046936486,0.000031168955,0.000005573654,0.000020171938,0.97211844,0.00011719774,0.021366064,0.0006674382,0.00038093948],"about_ca_topic_score_codex":0.00077182584,"about_ca_topic_score_gemma":0.000039828366,"teacher_disagreement_score":0.80070907,"about_ca_system_score_codex":0.00023910153,"about_ca_system_score_gemma":0.00023031238,"threshold_uncertainty_score":0.99987257},"labels":[],"label_agreement":null},{"id":"W3015882298","doi":"10.36227/techrxiv.12093564.v1","title":"Image Captioning with Complementary Visual and Textual Cues","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Lakehead University","funders":"","keywords":"Closed captioning; Modality (human–computer interaction); Image (mathematics); Computer science; Artificial intelligence; Computer vision; Natural language processing","score_opus":0.021762578800096587,"score_gpt":0.31395479874815174,"score_spread":0.29219221994805517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015882298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053430587,0.000030232271,0.9317727,0.00934495,0.000036932273,0.00035951353,0.0000130311655,0.0005456431,0.004466428],"genre_scores_gemma":[0.569492,0.0000037362583,0.42990282,0.00040654634,0.000058818623,0.00004200422,0.00006002423,0.000010590173,0.000023450635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985793,0.000063393636,0.00019897011,0.0007332021,0.00023892614,0.00018619133],"domain_scores_gemma":[0.9991822,0.000081866354,0.00012121132,0.00043256208,0.00005172135,0.00013042854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011176924,0.00021982819,0.00021440757,0.00007131163,0.00016773761,0.00041129277,0.0006600063,0.00005591208,0.00006121109],"category_scores_gemma":[0.000013056456,0.00018882914,0.00003170756,0.00012211209,0.00008041718,0.00014883814,0.0023211224,0.0005606436,0.000053735064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000992336,0.0008020638,0.16577834,0.0012704969,0.0009867328,0.0001879535,0.017404787,0.009815985,0.0137699,0.5433076,0.013478201,0.2330987],"study_design_scores_gemma":[0.0003502672,0.00011713393,0.08009116,0.000053375334,0.000022597394,0.0000221269,0.00015608301,0.91468596,0.0001362769,0.003090351,0.0008380583,0.00043659634],"about_ca_topic_score_codex":0.0034863604,"about_ca_topic_score_gemma":0.0001254755,"teacher_disagreement_score":0.90487,"about_ca_system_score_codex":0.000032542834,"about_ca_system_score_gemma":0.00007961778,"threshold_uncertainty_score":0.7700229},"labels":[],"label_agreement":null},{"id":"W3031234741","doi":"10.1145/3318464.3384701","title":"SVQ++: Querying for Object Interactions in Video Streams","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Frame (networking); Object (grammar); Video tracking; Artificial intelligence; Computer vision; Video processing; Object detection; Frame rate; Pattern recognition (psychology)","score_opus":0.03883423857464274,"score_gpt":0.32772350611831785,"score_spread":0.2888892675436751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031234741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0307682,0.000007411032,0.94284964,0.020404387,0.000066094544,0.00028407428,0.0000018422459,0.0002948479,0.0053234757],"genre_scores_gemma":[0.8454751,7.2776584e-7,0.15309116,0.0011573476,0.000048436017,0.00011747897,0.0000031438988,0.000006245595,0.00010040543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928933,0.000026929605,0.00016186897,0.00029792794,0.00007314159,0.00015080185],"domain_scores_gemma":[0.9993452,0.00026556334,0.000041705098,0.0002426804,0.000030945146,0.00007391841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008813229,0.00007406242,0.00009048117,0.000060757502,0.00007200127,0.000085271924,0.00043330132,0.000015955611,0.000032304593],"category_scores_gemma":[0.00018420498,0.00007084222,0.00004483826,0.0003566385,0.000008590867,0.0002669554,0.00012036133,0.00014779597,0.000098947574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027440705,0.00027291957,0.046285674,0.00007237626,0.000037273585,0.0000057412794,0.0076394123,0.025456898,0.016660523,0.3915186,0.0060147117,0.50600845],"study_design_scores_gemma":[0.0002478368,0.000029615509,0.0096824365,0.000007616046,0.0000016545699,0.0000018135918,0.00005420908,0.9789883,0.0009574866,0.0012636844,0.008659962,0.000105379804],"about_ca_topic_score_codex":0.000911555,"about_ca_topic_score_gemma":0.00021982084,"teacher_disagreement_score":0.9535314,"about_ca_system_score_codex":0.00003210902,"about_ca_system_score_gemma":0.00003436922,"threshold_uncertainty_score":0.2888862},"labels":[],"label_agreement":null},{"id":"W3034585290","doi":"10.1109/cvpr42600.2020.00365","title":"Composed Query Image Retrieval Using Locally Bounded Features","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Manitoba","funders":"","keywords":"Computer science; Image retrieval; Image (mathematics); Margin (machine learning); Benchmark (surveying); Set (abstract data type); Visual Word; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Sentence; Machine learning","score_opus":0.025373388347400473,"score_gpt":0.28916207059125776,"score_spread":0.26378868224385726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034585290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0818961,0.000024957904,0.8997451,0.013702393,0.00006229103,0.00017856125,0.0000013849132,0.0006399483,0.0037492337],"genre_scores_gemma":[0.57111573,6.701746e-7,0.42625907,0.0024892876,0.00006741518,7.4111915e-7,0.0000025155732,0.0000090275325,0.00005556189],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988601,0.00007359175,0.00017786445,0.0004102443,0.00025805333,0.00022012195],"domain_scores_gemma":[0.9991488,0.00009133463,0.00006984823,0.00043025365,0.0000833603,0.00017641901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012345341,0.00012870952,0.0001420996,0.000040632796,0.00018108329,0.0003067927,0.0008424226,0.000054592856,0.000046774],"category_scores_gemma":[0.000116943294,0.00011861248,0.000059767837,0.00049690914,0.000056855817,0.00028202354,0.00031221172,0.00027816682,0.00017549624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006973465,0.00013773215,0.002013477,0.000050477025,0.00006376734,0.000044710687,0.0017132063,0.0040040044,0.8084535,0.17620347,0.0028563077,0.004389589],"study_design_scores_gemma":[0.00042513147,0.00005629977,0.011788246,0.0000073068413,0.000007838754,0.000018981975,0.000017878881,0.96423763,0.02023223,0.0014030853,0.0015532334,0.00025214293],"about_ca_topic_score_codex":0.00037047753,"about_ca_topic_score_gemma":0.000004326676,"teacher_disagreement_score":0.9602336,"about_ca_system_score_codex":0.000037450936,"about_ca_system_score_gemma":0.000096337586,"threshold_uncertainty_score":0.48368764},"labels":[],"label_agreement":null},{"id":"W3034733309","doi":"10.18653/v1/2020.acl-main.664","title":"Improving Image Captioning with Better Use of Caption","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":85,"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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Closed captioning; Computer science; Leverage (statistics); Artificial intelligence; Natural language processing; Semantics (computer science); Visualization; Feature learning; Representation (politics); Word (group theory); Inductive bias; Image (mathematics); Machine learning; Task (project management); Multi-task learning","score_opus":0.02151848015296971,"score_gpt":0.23068016380181638,"score_spread":0.20916168364884669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034733309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2538826,0.0000014275264,0.7418215,0.0038195439,0.0000068419577,0.00007567948,5.7438774e-7,0.00014088083,0.00025094356],"genre_scores_gemma":[0.5794617,1.2762689e-7,0.42002085,0.00047249094,0.000015481533,0.000005890048,0.0000012708507,0.0000041010367,0.000018117202],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994017,0.00002401041,0.0001202115,0.0002231324,0.00013058029,0.00010037673],"domain_scores_gemma":[0.99949497,0.000048292237,0.00008371355,0.00024447264,0.00006926609,0.00005926794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005074481,0.000065023276,0.00007512975,0.000030986423,0.000053293083,0.0000942912,0.00023523434,0.000018798055,0.000022991031],"category_scores_gemma":[0.000040052717,0.000052761035,0.000020252184,0.00022101476,0.000025417785,0.0005460928,0.0001019772,0.000104625025,0.000042924396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031599546,0.00009973404,0.07565247,0.00011261254,0.000046423676,0.000010799168,0.0042451313,0.01830934,0.70465076,0.05215101,0.0006430107,0.14404708],"study_design_scores_gemma":[0.000170175,0.00007446202,0.032756165,0.000006250559,0.0000048648035,0.0000037108823,0.000013007694,0.961164,0.0054322174,0.0000544487,0.00021765918,0.00010301826],"about_ca_topic_score_codex":0.0013262541,"about_ca_topic_score_gemma":0.000009978121,"teacher_disagreement_score":0.9428547,"about_ca_system_score_codex":0.000010367099,"about_ca_system_score_gemma":0.000020121117,"threshold_uncertainty_score":0.21515326},"labels":[],"label_agreement":null},{"id":"W3035931148","doi":"10.48550/arxiv.2006.10923","title":"Hyperparameter Analysis for Image Captioning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Hyperparameter; Computer science; Transformer; Baseline (sea); Encoder; Artificial intelligence; Image (mathematics); Sensitivity (control systems); Preprocessor; Machine learning; Speech recognition; Pattern recognition (psychology); Natural language processing; Engineering","score_opus":0.09702672678732742,"score_gpt":0.2241226351722768,"score_spread":0.12709590838494939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035931148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11552363,0.000010031605,0.8820484,0.00076507503,0.0001010586,0.00035043297,0.000029794282,0.00036750623,0.0008040415],"genre_scores_gemma":[0.8825807,0.000007724565,0.11684434,0.00014796515,0.00005730435,0.000007757708,0.00006497291,0.000015994743,0.00027324457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811023,0.00009423948,0.00018353736,0.0012756955,0.00007074728,0.00026555455],"domain_scores_gemma":[0.9979554,0.00022037307,0.00024865978,0.0012348436,0.00017250862,0.00016823865],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017064331,0.0002465996,0.00037007607,0.00035303214,0.00020572524,0.00021562118,0.0017741135,0.00017228536,0.000024864128],"category_scores_gemma":[0.00009834943,0.0003023878,0.00049717596,0.001258567,0.000061061495,0.00022257608,0.001362632,0.0005054492,0.00012918326],"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":[0.000011810566,0.000051298917,0.008302246,0.000050880335,0.0006701018,0.000030404783,0.00025678158,0.84380597,0.00020685734,0.14592318,0.00013888162,0.0005516093],"study_design_scores_gemma":[0.00020474372,0.00001913885,0.01051555,0.000008627312,0.00044904833,7.603998e-7,0.000012868929,0.96155685,0.000044290588,0.026554657,0.0003273862,0.00030605422],"about_ca_topic_score_codex":0.0005325479,"about_ca_topic_score_gemma":0.000025416226,"teacher_disagreement_score":0.76705706,"about_ca_system_score_codex":0.00012804708,"about_ca_system_score_gemma":0.00009737552,"threshold_uncertainty_score":0.99994284},"labels":[],"label_agreement":null},{"id":"W3037533539","doi":"10.1609/aaai.v34i07.6833","title":"Learning Cross-Modal Context Graph for Visual Grounding","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":84,"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","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Ground; Artificial intelligence; Phrase; Graph; Modal; Modular design; Natural language processing; Theoretical computer science; Programming language","score_opus":0.08715630185034338,"score_gpt":0.3538858751306011,"score_spread":0.2667295732802577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037533539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55751723,0.000015662808,0.42407992,0.013593252,0.00027281969,0.0009360551,0.000005160762,0.00034426397,0.0032356174],"genre_scores_gemma":[0.9925161,0.0000058506143,0.00655402,0.00057927973,0.0001390671,0.00010257591,0.0000010969552,0.000021444073,0.00008054553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979155,0.000023447845,0.00056082295,0.00067386014,0.00042775396,0.00039860889],"domain_scores_gemma":[0.998218,0.00025572712,0.0004752457,0.00019382872,0.00069721515,0.00015998163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004929177,0.00024581904,0.00028822024,0.0000954405,0.0005195398,0.00053651305,0.0021467234,0.00009639983,0.000046319627],"category_scores_gemma":[0.0014379509,0.00020375618,0.00019457379,0.00076088606,0.0002626716,0.00043415144,0.00042780134,0.00052934326,0.00011171502],"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":[0.00007289013,0.00007099651,0.0023766377,0.000051350413,0.00001519859,1.1964683e-7,0.0023694024,0.0005097835,0.037758682,0.86463726,0.000036110003,0.09210156],"study_design_scores_gemma":[0.00009037555,0.0006694672,0.0016886799,0.00010553945,0.000014994856,0.0000028125457,0.00080733706,0.7202037,0.18559375,0.089998044,0.00045905024,0.0003662363],"about_ca_topic_score_codex":0.000079482066,"about_ca_topic_score_gemma":0.0000031709365,"teacher_disagreement_score":0.77463925,"about_ca_system_score_codex":0.000037180143,"about_ca_system_score_gemma":0.00007875161,"threshold_uncertainty_score":0.8308936},"labels":[],"label_agreement":null},{"id":"W3044731091","doi":"10.48550/arxiv.1909.07459","title":"Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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; Bridging (networking); Robot; Human–computer interaction; Semantics (computer science); Perception; Tuple; Artificial intelligence; Ontology; Natural language processing; Programming language","score_opus":0.12548312163179495,"score_gpt":0.2426436539427157,"score_spread":0.11716053231092075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044731091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22243842,0.0000035040105,0.7759322,0.00022453615,0.00016978054,0.00069473544,0.0000074286886,0.00025477775,0.0002746215],"genre_scores_gemma":[0.9862279,0.0000071863647,0.013139311,0.000058258534,0.000090827925,0.0000040381797,0.00009606461,0.000032345564,0.00034405183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982736,0.00009050065,0.0001828783,0.001021734,0.000117609314,0.0003136888],"domain_scores_gemma":[0.9985234,0.00015633261,0.00032748916,0.0007452904,0.00015250199,0.00009499104],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024082899,0.00028683594,0.00028159958,0.00026021703,0.00029345107,0.00021307239,0.0007825471,0.00021821416,0.000008763715],"category_scores_gemma":[0.000023451028,0.00032527855,0.00012944818,0.000316505,0.0000654578,0.0003575595,0.0005983367,0.0004846787,0.000048312235],"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":[0.000033810302,0.000044386128,0.0088258,0.00008620406,0.000052282005,0.0000068683867,0.00029939765,0.8067787,0.00013795988,0.18301435,0.000027222548,0.0006930019],"study_design_scores_gemma":[0.00065769575,0.000094510935,0.019730533,0.00011077679,0.000074780655,0.0000047702283,0.00020533719,0.9702593,0.000011392955,0.0084419055,0.000019874324,0.0003890848],"about_ca_topic_score_codex":0.00032948874,"about_ca_topic_score_gemma":0.000059858165,"teacher_disagreement_score":0.7637895,"about_ca_system_score_codex":0.00062140875,"about_ca_system_score_gemma":0.00013486399,"threshold_uncertainty_score":0.99991995},"labels":[],"label_agreement":null},{"id":"W3080318437","doi":"10.18653/v1/2021.mrl-1.13","title":"VisualSem: a high-quality knowledge graph for vision and language","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":33,"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":"Samsung; European Commission; York University; Samsung Advanced Institute of Technology; Nvidia; Universiteit van Amsterdam; National Science Foundation","keywords":"Computer science; Pipeline (software); Modal; Artificial intelligence; Knowledge graph; Artificial neural network; Quality (philosophy); Natural language processing; Bridging (networking); Graph; Natural language; Information retrieval; Programming language; Theoretical computer science","score_opus":0.024389899715241477,"score_gpt":0.397022387454462,"score_spread":0.37263248773922053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080318437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27181542,0.0005275524,0.72400004,0.0013363676,0.00022485835,0.0005337237,0.000013553562,0.00036261222,0.001185869],"genre_scores_gemma":[0.7442757,0.000020151761,0.2546238,0.00014443258,0.000078132114,0.00025366282,0.00007939715,0.000015996451,0.00050872617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812233,0.00018340381,0.00032637897,0.00098322,0.00015941676,0.00022522997],"domain_scores_gemma":[0.9978625,0.00047435204,0.00016600131,0.0012014495,0.00017422944,0.00012142787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006492184,0.00024719638,0.00036178337,0.00013481533,0.000146408,0.0004707463,0.00080951984,0.00021213807,0.000020796457],"category_scores_gemma":[0.0001692721,0.00022072565,0.00013916501,0.00021538307,0.000042483276,0.00011919844,0.0024226073,0.0004040891,0.000016259879],"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":[0.000016604163,0.0009181557,0.0019436183,0.0017001549,0.00018264679,0.0000074765558,0.0109271705,0.0007237811,0.015764793,0.5304481,0.0024966304,0.43487087],"study_design_scores_gemma":[0.0021186764,0.00024384576,0.36050916,0.0004909056,0.00009877121,0.000018480545,0.00044981163,0.55641466,0.0076486073,0.065879606,0.003856034,0.0022714227],"about_ca_topic_score_codex":0.0020174012,"about_ca_topic_score_gemma":0.00015110969,"teacher_disagreement_score":0.5556909,"about_ca_system_score_codex":0.000033556607,"about_ca_system_score_gemma":0.00013527626,"threshold_uncertainty_score":0.9000931},"labels":[],"label_agreement":null},{"id":"W3081752373","doi":"10.5244/c.34.107","title":"Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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 Manitoba","funders":"","keywords":"Thumbnail; Computer science; Sentence; Embedding; Modulation (music); Artificial intelligence; Natural language processing; Speech recognition; Image (mathematics)","score_opus":0.06512363023925581,"score_gpt":0.3391107237255148,"score_spread":0.273987093486259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081752373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0182115,0.00002230819,0.9621407,0.016661394,0.00047800055,0.0013285467,0.000020587053,0.00075686723,0.0003801203],"genre_scores_gemma":[0.5727281,0.0000036444615,0.4257577,0.000425048,0.00015488215,0.00036374817,0.00033695,0.000018409624,0.00021150953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977796,0.00009073191,0.0004858352,0.0010999887,0.00031261347,0.00023123978],"domain_scores_gemma":[0.99803567,0.000084771505,0.00034607772,0.0011608978,0.00026053743,0.0001120737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030915605,0.00028328967,0.00027054176,0.000112034126,0.00019351211,0.0003797794,0.0012849899,0.00020421654,0.000015009374],"category_scores_gemma":[0.00017865923,0.00028371657,0.00016529192,0.00020714807,0.000025927528,0.00022711688,0.0009826152,0.00038179697,0.00007799723],"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":[0.00001326561,0.00017812286,0.003530922,0.0003488965,0.00012599929,0.0000031078316,0.0014303364,0.6647104,0.039332047,0.13460448,0.014461974,0.14126046],"study_design_scores_gemma":[0.00018956768,0.000022993376,0.006916388,0.00001665833,0.000010780128,0.0000025389504,0.0000031856803,0.9729845,0.00023037444,0.018645007,0.00068683014,0.00029118685],"about_ca_topic_score_codex":0.0009205433,"about_ca_topic_score_gemma":0.00009217908,"teacher_disagreement_score":0.5545166,"about_ca_system_score_codex":0.000144482,"about_ca_system_score_gemma":0.0001847871,"threshold_uncertainty_score":0.9999615},"labels":[],"label_agreement":null},{"id":"W3083845092","doi":"10.48550/arxiv.2009.04806","title":"SketchEmbedNet: Learning Novel Concepts by Imitating Drawings","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Sketch; Computer science; Principle of compositionality; Salient; Generative grammar; Artificial intelligence; Focus (optics); Class (philosophy); Natural (archaeology); Natural language processing; Algorithm","score_opus":0.06690291441134907,"score_gpt":0.22608206366341768,"score_spread":0.1591791492520686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083845092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17547718,0.00005362764,0.8191474,0.00097394426,0.0001751558,0.00028031375,0.000014477849,0.0008397931,0.0030381037],"genre_scores_gemma":[0.97730625,0.000028866132,0.02129312,0.0003240733,0.00008597931,0.00000377407,0.0000630929,0.000042103587,0.00085274933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728304,0.0001580138,0.00027738378,0.0016807732,0.0001521169,0.00044866957],"domain_scores_gemma":[0.9977333,0.0003372442,0.0004918999,0.0009734497,0.00016183335,0.00030230114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024840358,0.00041750586,0.00040327694,0.00013688381,0.00039851552,0.0002578595,0.0025309008,0.00029596247,0.000028960307],"category_scores_gemma":[0.00026708655,0.0005418363,0.00021529467,0.0007483281,0.00012832535,0.00032487963,0.002968285,0.0019176613,0.00021742543],"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":[0.00001711532,0.00017642294,0.010131035,0.00015878335,0.00018953506,0.00008402509,0.0036656782,0.79381883,0.010591837,0.17434017,0.001955292,0.0048712823],"study_design_scores_gemma":[0.00047845545,0.00004088034,0.0010556887,0.00007917059,0.000039829167,0.0000030663196,0.00017219808,0.9880712,0.00031128846,0.0065736864,0.002583668,0.00059086026],"about_ca_topic_score_codex":0.00078919454,"about_ca_topic_score_gemma":0.000005820697,"teacher_disagreement_score":0.80182904,"about_ca_system_score_codex":0.0001962005,"about_ca_system_score_gemma":0.00020763166,"threshold_uncertainty_score":0.9997033},"labels":[],"label_agreement":null},{"id":"W3088099248","doi":"","title":"Memory Augmented Neural Networks for Natural Language Processing","year":2017,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","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 de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Scalability; Set (abstract data type); Focus (optics); Auxiliary memory; Deep learning; Machine learning; Theoretical computer science; Programming language","score_opus":0.040286962499015484,"score_gpt":0.46035881602918827,"score_spread":0.4200718535301728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088099248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05030762,0.027200403,0.9156943,0.0040027914,0.0008103686,0.0008172406,0.0000031278241,0.0006191671,0.00054498785],"genre_scores_gemma":[0.54358995,0.0000015123286,0.4551488,0.0006434617,0.00027280077,0.00010148536,0.000010848813,0.00003107774,0.00020009685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966563,0.00044075228,0.0005958211,0.001053883,0.00038218958,0.00087107345],"domain_scores_gemma":[0.99721557,0.0007166532,0.00060530717,0.0011073457,0.00017996361,0.0001751758],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016896045,0.00043113212,0.000532785,0.00024382824,0.0011750803,0.0012144708,0.0025264472,0.00022194274,0.000007850549],"category_scores_gemma":[0.0028219798,0.00036142985,0.00017728223,0.00056348677,0.00019012355,0.0013422254,0.0007465034,0.0014469394,0.0000034576285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035662204,0.00005911157,0.00121685,0.00012840184,0.000009368355,0.00002934985,0.0035171157,0.00073933386,0.0031065175,0.000041282135,0.0000442566,0.9910728],"study_design_scores_gemma":[0.0008557303,0.000030319809,0.018324006,0.00014432459,0.000017588629,0.00003622402,0.00030098975,0.97801214,0.0014589496,0.00022157795,0.00012551312,0.00047260275],"about_ca_topic_score_codex":0.00022173747,"about_ca_topic_score_gemma":0.00004844307,"teacher_disagreement_score":0.99060017,"about_ca_system_score_codex":0.00016528214,"about_ca_system_score_gemma":0.00010897353,"threshold_uncertainty_score":0.9998838},"labels":[],"label_agreement":null},{"id":"W3089338039","doi":"10.1093/mnras/stab424","title":"Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language ‘captioning’ model","year":2021,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University; Royal Society; Government of Ontario","keywords":"Galaxy; Deep learning; sort; Surface brightness; Sky; Image (mathematics); Artificial neural network; Leverage (statistics)","score_opus":0.005327329558957749,"score_gpt":0.22736021647365892,"score_spread":0.22203288691470116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089338039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71521354,0.000050190607,0.28394547,0.00034633104,0.00014246712,0.00010379897,0.000025697127,0.00004031741,0.00013221113],"genre_scores_gemma":[0.81227344,6.564442e-8,0.18753707,0.000038386355,0.00005708702,0.000011233777,0.00004762624,0.0000058793707,0.000029212164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885225,0.00007902713,0.000394815,0.00022881273,0.00025923637,0.00018585905],"domain_scores_gemma":[0.99877876,0.000115569404,0.00041808758,0.00050110515,0.00013467945,0.000051778876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016172853,0.00013256239,0.0001927532,0.000016611324,0.00013269353,0.000090497844,0.0006309947,0.00008400271,0.000022678312],"category_scores_gemma":[0.000058615762,0.00011336541,0.00031393906,0.00013576752,0.00009317398,0.0006268674,0.00042525493,0.00035155125,0.000012972585],"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":[0.0000096340045,0.000054700806,0.0026499182,0.00001420004,0.000038885748,5.1032853e-8,0.0015917134,0.98256356,0.0045645316,0.00012225378,0.00004846335,0.008342081],"study_design_scores_gemma":[0.00024426178,0.000008085319,0.10091542,0.000013284395,0.000025863454,3.9732264e-8,0.00015985365,0.893525,0.0049402816,0.00006254823,0.000015086048,0.00009026225],"about_ca_topic_score_codex":0.0019872105,"about_ca_topic_score_gemma":0.000034010187,"teacher_disagreement_score":0.0982655,"about_ca_system_score_codex":0.00010078654,"about_ca_system_score_gemma":0.00007836153,"threshold_uncertainty_score":0.4622907},"labels":[],"label_agreement":null},{"id":"W3090136599","doi":"10.1145/3377816.3381723","title":"Eye of the mind","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Coding (social sciences); World Wide Web; Software; Multimedia; Information retrieval; Human–computer interaction; Data science; Programming language","score_opus":0.01688305020625226,"score_gpt":0.2609230488219535,"score_spread":0.24403999861570125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090136599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1940719,0.000008205234,0.68238825,0.09513729,0.000038644037,0.0001072806,5.3742974e-7,0.000060532184,0.028187333],"genre_scores_gemma":[0.94835466,1.0242246e-7,0.050693773,0.0007983736,0.000011084266,0.0000018796624,5.5879198e-8,0.000001111048,0.00013898278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997305,0.00001524469,0.000055096712,0.00008652309,0.00007326267,0.000039373488],"domain_scores_gemma":[0.9996693,0.000022217002,0.000025787864,0.00024506229,0.000014121534,0.000023477047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002882597,0.00002237489,0.000029468347,0.0000044774342,0.000024537227,0.0000099621775,0.00061630824,0.000008267795,0.000042093106],"category_scores_gemma":[0.00003835743,0.000013535215,0.000021387872,0.00019231605,0.000014023204,0.000031492375,0.00017397387,0.00004789376,0.00008810546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020614154,0.00007783041,0.1344976,0.000019211586,0.000017432954,4.9295596e-7,0.004920601,0.0041111405,0.045383763,0.64645284,0.0042580087,0.16025902],"study_design_scores_gemma":[0.0001010624,0.000018160254,0.29982448,0.000002207024,0.0000018483765,4.1594743e-7,0.000010791438,0.66468334,0.017364182,0.00087022386,0.017063579,0.00005971159],"about_ca_topic_score_codex":0.000046997222,"about_ca_topic_score_gemma":0.0000010317214,"teacher_disagreement_score":0.7542827,"about_ca_system_score_codex":0.0000017980011,"about_ca_system_score_gemma":0.0000127058975,"threshold_uncertainty_score":0.114526436},"labels":[],"label_agreement":null},{"id":"W3092352310","doi":"10.1109/case48305.2020.9216770","title":"Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Bridging (networking); Robot; Semantics (computer science); Human–computer interaction; Tuple; Perception; Artificial intelligence; Ontology; Natural language processing; Programming language","score_opus":0.0795439621350606,"score_gpt":0.31188448238756744,"score_spread":0.23234052025250684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092352310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028255073,0.0000017952275,0.9603262,0.010292491,0.000027096718,0.00035199503,8.9312306e-7,0.00035213798,0.00039232094],"genre_scores_gemma":[0.8478287,3.6564361e-7,0.15134342,0.00066598883,0.00008639159,0.000020119553,0.000014585784,0.000011891399,0.000028570134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991656,0.000026001844,0.00014417125,0.0003251858,0.0001691648,0.00016987199],"domain_scores_gemma":[0.9995648,0.00007827306,0.00007286825,0.00014764867,0.000051836705,0.00008457017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010825383,0.00010321583,0.00010398022,0.000043544143,0.00021427049,0.00016827,0.00022106229,0.000034718953,0.000014089561],"category_scores_gemma":[0.000033430722,0.00009179227,0.000032695356,0.00021320608,0.000021497284,0.00029639198,0.00006490912,0.00010156457,0.000028458766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071437666,0.00009321243,0.015183717,0.000095462005,0.00005297002,0.0000030606402,0.0053983247,0.10376632,0.021465357,0.7998576,0.0006061136,0.053406417],"study_design_scores_gemma":[0.00041410237,0.00014986703,0.017520573,0.000009228547,0.000008419272,0.000004511554,0.00027123655,0.9807327,0.00010015753,0.00059688074,0.00005661097,0.00013573666],"about_ca_topic_score_codex":0.000077611774,"about_ca_topic_score_gemma":0.00001707747,"teacher_disagreement_score":0.87696636,"about_ca_system_score_codex":0.000081761886,"about_ca_system_score_gemma":0.000024984287,"threshold_uncertainty_score":0.37431803},"labels":[],"label_agreement":null},{"id":"W3095478416","doi":"10.1109/cvprw53098.2021.00181","title":"An Improved Attention for Visual Question Answering","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Question answering; Computer science; Benchmark (surveying); Artificial intelligence; Encoder; Context (archaeology); Task (project management); Natural language; Modality (human–computer interaction); Relation (database); Information retrieval; Natural language processing; Data mining","score_opus":0.014382356879745518,"score_gpt":0.349374374597222,"score_spread":0.33499201771747644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095478416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17670655,0.000018278475,0.82092285,0.00069688924,0.00039779843,0.0005305925,0.000002665738,0.0005851565,0.00013924958],"genre_scores_gemma":[0.607508,0.0000024925112,0.3917386,0.00006581052,0.00011618192,0.00030899586,0.00016795206,0.000013524857,0.00007847878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984669,0.00009255822,0.00025622602,0.00083957275,0.00014162945,0.00020309263],"domain_scores_gemma":[0.9985592,0.000055223656,0.00016138467,0.0009033911,0.0002295436,0.000091306785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038656706,0.00018617883,0.00018319082,0.000097440585,0.00013480018,0.00062518375,0.0007669559,0.00019272655,0.000010510236],"category_scores_gemma":[0.000060988343,0.0001994537,0.00012123719,0.00012078368,0.000013077008,0.00031175508,0.0005959415,0.00034873182,0.000007817545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001756719,0.00087712187,0.006257091,0.000608336,0.00011954265,0.0000032432652,0.0010870344,0.04384046,0.27881935,0.07509305,0.00008452355,0.5931927],"study_design_scores_gemma":[0.0001340368,0.000057064277,0.03290651,0.000036767156,0.0000100207435,0.0000021071316,0.000017141907,0.96421933,0.0010223027,0.0012958165,0.00007279598,0.00022608554],"about_ca_topic_score_codex":0.0012074324,"about_ca_topic_score_gemma":0.00008165046,"teacher_disagreement_score":0.92037886,"about_ca_system_score_codex":0.000077810895,"about_ca_system_score_gemma":0.000114788934,"threshold_uncertainty_score":0.81334853},"labels":[],"label_agreement":null},{"id":"W3098282109","doi":"","title":"Curiosity Based Exploration for Learning Terrain Models","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"McGill University","funders":"","keywords":"Terrain; Perplexity; Computer science; Artificial intelligence; Discriminative model; Path (computing); Motion planning; Machine learning; Robot; Computer vision; Language model; Cartography; Geography","score_opus":0.09872959158289273,"score_gpt":0.3370356043554977,"score_spread":0.23830601277260494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098282109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018847912,0.000024434623,0.98588896,0.0064249984,0.00021996819,0.00096383464,0.000007820399,0.0009950903,0.0035901114],"genre_scores_gemma":[0.5486608,0.0000013379672,0.44985637,0.00025278033,0.000088290406,0.0006587284,0.00013662713,0.000019713734,0.0003253024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815327,0.00016682576,0.0003018586,0.0008126786,0.0003081752,0.0002571631],"domain_scores_gemma":[0.99802846,0.0001877863,0.00025645783,0.0010274252,0.00036014328,0.00013972017],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009159871,0.00025266127,0.0002580676,0.00016103053,0.00019575979,0.00034450312,0.001266745,0.0002258905,0.000008020653],"category_scores_gemma":[0.0002205527,0.000253096,0.00013208143,0.00014793505,0.000022311837,0.00045868696,0.00094389525,0.0006937653,0.00004067043],"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":[0.000004113379,0.000047695932,0.000084946856,0.000045526423,0.000008685808,2.1546788e-7,0.00075019256,0.9530683,0.000046584086,0.032367613,0.0011266841,0.012449428],"study_design_scores_gemma":[0.00023281279,0.00003432789,0.00007810536,0.000023869114,0.000007529438,3.267466e-7,0.000011943264,0.85499305,0.00009296801,0.14260854,0.0016690623,0.00024748943],"about_ca_topic_score_codex":0.0006167665,"about_ca_topic_score_gemma":0.00002927372,"teacher_disagreement_score":0.54677606,"about_ca_system_score_codex":0.0001367745,"about_ca_system_score_gemma":0.00035834595,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W3101703188","doi":"10.18653/v1/2020.findings-emnlp.44","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":142,"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; Thales (Canada)","funders":"","keywords":"Question answering; Computer science; Embedding; Commonsense knowledge; Artificial intelligence; Exploit; Natural language processing; Natural language; Knowledge representation and reasoning; Focus (optics); Representation (politics); Information retrieval","score_opus":0.030750271106208177,"score_gpt":0.3548092531981962,"score_spread":0.324058982091988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101703188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012148753,0.000012046376,0.97425,0.011950616,0.00007455575,0.00036660596,0.0000023489295,0.0005355134,0.00065956084],"genre_scores_gemma":[0.90310454,8.9714996e-7,0.095315024,0.0012372767,0.00012611925,0.00009134454,0.000023125865,0.000008528144,0.00009316869],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913496,0.00004676664,0.00016744519,0.00037872803,0.0001288124,0.00014331851],"domain_scores_gemma":[0.9993877,0.00015098705,0.00006978777,0.00019905917,0.0000903627,0.00010213349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007824943,0.000086256434,0.0000992411,0.000023773478,0.000120257675,0.00009780205,0.00033721124,0.000038704482,0.0000332153],"category_scores_gemma":[0.00014856289,0.00008617806,0.0000456831,0.00024137019,0.000027033748,0.00032686628,0.00009374151,0.00008600225,0.00006150166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003871203,0.00011633324,0.013650607,0.000059962793,0.000045838013,0.000003440662,0.009004581,0.03789169,0.027348684,0.5804636,0.006242948,0.32513362],"study_design_scores_gemma":[0.00034288215,0.00009086822,0.0061328392,0.0000044899252,0.0000034005807,0.0000014437904,0.000066590386,0.9833768,0.0068809455,0.0005651856,0.0024130573,0.0001214727],"about_ca_topic_score_codex":0.00018998876,"about_ca_topic_score_gemma":0.000003736307,"teacher_disagreement_score":0.9454851,"about_ca_system_score_codex":0.000019978475,"about_ca_system_score_gemma":0.000027206359,"threshold_uncertainty_score":0.35142392},"labels":[],"label_agreement":null},{"id":"W3105009590","doi":"","title":"Multimodal Graph Networks for Compositional Generalization in Visual Question Answering","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"","keywords":"Computer science; Question answering; Generalization; Graph; Artificial intelligence; Graph theory; Natural language processing; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.015426769876601897,"score_gpt":0.2875687495257047,"score_spread":0.2721419796491028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105009590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054058544,0.000060338916,0.9432809,0.0014032326,0.00019562872,0.0005851852,0.0000042672505,0.0003488459,0.00006308937],"genre_scores_gemma":[0.9822419,0.0000017088524,0.016357496,0.0007849505,0.0001658184,0.0002305188,0.0002061108,0.000009052368,0.0000024020358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871904,0.000071195514,0.00055274664,0.00020760475,0.00023781505,0.0002116232],"domain_scores_gemma":[0.99923134,0.00004981189,0.00030127118,0.0001076509,0.00022016098,0.000089780864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002436444,0.00014168373,0.0001544991,0.00015643722,0.00022893542,0.0005634334,0.00030312221,0.00008312639,8.639394e-7],"category_scores_gemma":[0.000059579896,0.00014678111,0.000039149058,0.0006092894,0.000018191613,0.0029141358,0.000051623374,0.00016238673,0.0000088308125],"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":[0.000014343778,0.00001568653,0.0025598002,0.00015851749,0.0000024817934,2.080637e-7,0.00093621365,0.968623,0.0004968447,0.007415575,0.00006324927,0.019714091],"study_design_scores_gemma":[0.00047866788,0.000051754687,0.008364079,0.000054960594,0.0000024843964,0.000007569316,0.00003443695,0.9903178,0.00006903364,0.000042671127,0.00042075597,0.00015574957],"about_ca_topic_score_codex":0.0001365879,"about_ca_topic_score_gemma":0.0000024475012,"teacher_disagreement_score":0.9281834,"about_ca_system_score_codex":0.000060685918,"about_ca_system_score_gemma":0.00004190025,"threshold_uncertainty_score":0.598556},"labels":[],"label_agreement":null},{"id":"W3106697459","doi":"10.18653/v1/2020.aacl-main.48","title":"Multimodal Pretraining for Dense Video Captioning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"","keywords":"Closed captioning; Timeline; Computer science; Leverage (statistics); Variety (cybernetics); Multimedia; Construct (python library); Artificial intelligence; Human–computer interaction; Natural language processing; Image (mathematics)","score_opus":0.044387721720699685,"score_gpt":0.32001766122166764,"score_spread":0.2756299395009679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106697459","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":[0.0070716706,0.000042576983,0.97832805,0.008885398,0.00042850283,0.00111602,0.000020784013,0.0013153742,0.00279161],"genre_scores_gemma":[0.49919224,0.0000016579083,0.49956405,0.00040542128,0.00019159095,0.00046186495,0.000039509872,0.000024867237,0.00011879841],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759394,0.00008035083,0.0004265733,0.0012289466,0.00029010235,0.0003801044],"domain_scores_gemma":[0.9977616,0.00045507628,0.00027416213,0.0011185075,0.00018259489,0.00020803441],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003809892,0.0003334065,0.0003563816,0.00012894598,0.00026033056,0.0004862454,0.0018194756,0.0002698615,0.000030271269],"category_scores_gemma":[0.00055355043,0.00035020773,0.00023616407,0.00019905281,0.00003880547,0.00016360189,0.0018727393,0.0009027802,0.00011666623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004122889,0.00020019032,0.0032751493,0.00078350597,0.0003339214,0.000015975564,0.013310466,0.24084578,0.005038639,0.47064662,0.0054460084,0.26006252],"study_design_scores_gemma":[0.00030884877,0.00003433163,0.003317076,0.000052831252,0.000017999446,0.0000049399428,0.000023524204,0.97633815,0.00022932776,0.017906241,0.0013762439,0.0003904703],"about_ca_topic_score_codex":0.00060905924,"about_ca_topic_score_gemma":0.00001720371,"teacher_disagreement_score":0.73549235,"about_ca_system_score_codex":0.00009645816,"about_ca_system_score_gemma":0.00024003128,"threshold_uncertainty_score":0.999895},"labels":[],"label_agreement":null},{"id":"W3108413361","doi":"10.1007/978-3-030-58583-9_22","title":"Structure-Aware Generation Network for Recipe Generation from Images","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"BC Research (Canada)","funders":"","keywords":"Recipe; Computer science; Closed captioning; Task (project management); Benchmark (surveying); Tree (set theory); Artificial intelligence; Tree structure; Natural language processing; Sentence; Machine learning; Image (mathematics); Information retrieval; Data structure","score_opus":0.027145977666984025,"score_gpt":0.26912500691998603,"score_spread":0.24197902925300202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108413361","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":[0.00019204927,0.00030935486,0.992006,0.0041094795,0.0020091343,0.0008692757,0.00009590521,0.00025432606,0.0001544808],"genre_scores_gemma":[0.2082339,0.000013749794,0.78393215,0.0021352605,0.005199254,0.000043767002,0.0003300102,0.000046313304,0.000065583605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961689,0.000057531488,0.00056272885,0.0020177239,0.00068768737,0.0005054309],"domain_scores_gemma":[0.9973319,0.00043059955,0.00040851315,0.0013277417,0.00031825615,0.0001829766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038920718,0.0005329378,0.0004861421,0.00024156025,0.000536102,0.0008437317,0.002472594,0.0003536239,0.000025999716],"category_scores_gemma":[0.00013447044,0.00052207423,0.00013461446,0.0004859235,0.00022198951,0.0005031342,0.00070739764,0.0007610358,0.000027365366],"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":[0.0000043113937,0.000009782118,0.00007527173,0.000011752624,0.000016489636,0.0000060220277,0.0002797064,0.5433257,0.005427144,0.029067658,0.0007920994,0.42098403],"study_design_scores_gemma":[0.00019857001,0.00008702354,0.0002862572,0.00004951953,0.0000121870635,0.000005475313,2.7886369e-8,0.8907131,0.003130005,0.10306461,0.0019574782,0.00049577246],"about_ca_topic_score_codex":0.00013379483,"about_ca_topic_score_gemma":0.00023549698,"teacher_disagreement_score":0.42048827,"about_ca_system_score_codex":0.00024650746,"about_ca_system_score_gemma":0.0003853143,"threshold_uncertainty_score":0.9997231},"labels":[],"label_agreement":null},{"id":"W3111344731","doi":"10.1109/smc42975.2020.9283183","title":"Quantifying the Impact of Complementary Visual and Textual Cues Under Image Captioning","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Closed captioning; Artificial intelligence; Feature (linguistics); Convolutional neural network; Encoder; Sentence; Natural language processing; Representation (politics); Sensory cue; Recurrent neural network; Pattern recognition (psychology); Image (mathematics); Speech recognition; Artificial neural network","score_opus":0.06289478724702684,"score_gpt":0.3833081381672803,"score_spread":0.32041335092025347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111344731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53327364,0.000019114483,0.46159273,0.0044294996,0.000005446627,0.00008983389,0.0000023239486,0.000069973896,0.00051745574],"genre_scores_gemma":[0.9621356,0.0000021232618,0.037463106,0.0003576641,0.000025343177,0.0000040156237,0.0000042636957,0.000004553473,0.0000032926725],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993799,0.00005778599,0.00014470033,0.00018643298,0.00011529228,0.00011592781],"domain_scores_gemma":[0.9995295,0.00015997715,0.00006328104,0.00016020663,0.000028399469,0.000058666916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001291622,0.00007553952,0.00008965458,0.0000235723,0.00015294661,0.00009120854,0.00032323532,0.000012095307,0.00006819315],"category_scores_gemma":[0.000022479537,0.000048220958,0.000041572606,0.00018583178,0.00006419606,0.00017992315,0.00027264928,0.00011102842,0.00001566718],"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":[0.000026474296,0.00020891256,0.38274822,0.000057280937,0.000245741,0.000003410295,0.013190068,0.023272792,0.1964238,0.3345663,0.0028268772,0.046430115],"study_design_scores_gemma":[0.00014432285,0.00007364972,0.32621157,0.0000032002774,0.0000035058724,0.0000034506413,0.000412143,0.6723684,0.0004339188,0.00026662726,0.000016938075,0.00006227395],"about_ca_topic_score_codex":0.004449304,"about_ca_topic_score_gemma":0.00003669156,"teacher_disagreement_score":0.6490956,"about_ca_system_score_codex":0.00001269954,"about_ca_system_score_gemma":0.000025289854,"threshold_uncertainty_score":0.6726047},"labels":[],"label_agreement":null},{"id":"W3111882491","doi":"","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Oracle; Mobile robot navigation; Computer vision; Observability; Turn-by-turn navigation; Feature (linguistics); Set (abstract data type); Navigation system; Human–computer interaction; Mobile robot; Robot","score_opus":0.1059553040641273,"score_gpt":0.23744483563010366,"score_spread":0.13148953156597637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111882491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28896964,0.000032010226,0.70912975,0.00026360163,0.0005217132,0.00043213094,0.000007976294,0.0004813626,0.00016185518],"genre_scores_gemma":[0.9141681,0.0000117432455,0.08528218,0.000101971855,0.00020923243,0.0000027696997,0.00006893482,0.000032313612,0.00012275013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972653,0.00027674987,0.0003077442,0.0016143708,0.00016019396,0.0003756584],"domain_scores_gemma":[0.99761695,0.00013736961,0.00047529332,0.001360664,0.00018784359,0.00022186158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028062647,0.0004070369,0.0003758182,0.0002554755,0.0004076368,0.00021285425,0.0018259336,0.0003101691,0.00002526906],"category_scores_gemma":[0.000049810373,0.0005234115,0.00024919465,0.0007595571,0.00009589125,0.00041300655,0.0023613628,0.0011264926,0.00020630506],"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":[0.000010471415,0.000108752356,0.0064974315,0.00024701768,0.00009353643,0.00019505649,0.00081463606,0.9761765,0.0011131539,0.012839117,0.000032325537,0.0018720161],"study_design_scores_gemma":[0.00045278083,0.000020178408,0.008418474,0.00020381605,0.00007849128,0.0000085747215,0.000043408556,0.9865894,0.00017130746,0.0034312257,0.00007383983,0.00050850754],"about_ca_topic_score_codex":0.0018322105,"about_ca_topic_score_gemma":0.000029376908,"teacher_disagreement_score":0.6251985,"about_ca_system_score_codex":0.00037352106,"about_ca_system_score_gemma":0.0002312146,"threshold_uncertainty_score":0.99972177},"labels":[],"label_agreement":null},{"id":"W3118480672","doi":"10.48550/arxiv.2101.01447","title":"End-to-End Video Question-Answer Generation with Generator-Pretester Network","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Ministry of Science and Technology, Taiwan; Nvidia","keywords":"Computer science; Task (project management); Generator (circuit theory); Question answering; Annotation; Artificial intelligence; Ground truth; Information retrieval; Multimedia; Power (physics)","score_opus":0.04454339780986381,"score_gpt":0.20328930949263468,"score_spread":0.15874591168277086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118480672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33187166,0.00004506709,0.66579175,0.00044441305,0.00039067864,0.00034496796,0.000006529459,0.00027021253,0.0008347461],"genre_scores_gemma":[0.9262731,0.000024682473,0.0716856,0.00060240657,0.00054133736,0.0000144302285,0.000115847375,0.000037069112,0.0007055076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969883,0.0003753409,0.00025251458,0.001744603,0.00019073415,0.00044853822],"domain_scores_gemma":[0.9968777,0.00011411727,0.0002518667,0.002060568,0.0003943696,0.00030138003],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034828708,0.00041655038,0.0003540692,0.00019880074,0.00034400015,0.00050079403,0.0015017125,0.0002843088,0.00010426996],"category_scores_gemma":[0.000042502743,0.0004570997,0.00013912446,0.0010388807,0.00007300176,0.00042943298,0.0015363877,0.000788411,0.00013518248],"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":[0.00000794317,0.000043664088,0.014280221,0.000016607912,0.00007593969,0.00010343382,0.00019546346,0.9196961,0.0002991445,0.06402448,0.00041646388,0.0008405447],"study_design_scores_gemma":[0.00030337265,0.00006408365,0.015650034,0.00010702278,0.00008464983,0.00001551545,0.0000126486,0.9801172,0.00031642083,0.0015699121,0.0010749591,0.00068418484],"about_ca_topic_score_codex":0.0008323955,"about_ca_topic_score_gemma":0.00041991193,"teacher_disagreement_score":0.5944015,"about_ca_system_score_codex":0.00026075236,"about_ca_system_score_gemma":0.00038153835,"threshold_uncertainty_score":0.99978805},"labels":[],"label_agreement":null},{"id":"W3121592593","doi":"","title":"Long Range Arena : A Benchmark for Efficient Transformers","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":57,"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":"Suite; Benchmarking; Computer science; Transformer; Benchmark (surveying); Artificial intelligence; Machine learning; Data mining; Engineering","score_opus":0.01244723705163878,"score_gpt":0.2729188266178351,"score_spread":0.2604715895661963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121592593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035698157,0.000067667475,0.9485661,0.0050392617,0.000101344565,0.00026583098,0.0000033146607,0.00017042847,0.010087922],"genre_scores_gemma":[0.86824864,0.0000024016797,0.13063923,0.0003848316,0.000028231816,0.00012258028,0.000010129488,0.0000067585884,0.00055717136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912226,0.000024810412,0.00014059148,0.0003424987,0.00014671481,0.00022314051],"domain_scores_gemma":[0.99928945,0.00016204697,0.000026850365,0.00034507416,0.00009485837,0.00008170234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001595608,0.00008695674,0.00009895159,0.00004411011,0.00013909012,0.000084960404,0.00033752347,0.000032527223,0.00009814283],"category_scores_gemma":[0.00004821744,0.00007886214,0.00009379714,0.0003371341,0.000016613021,0.0000680282,0.00005305467,0.00008213604,0.000045891404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018993785,0.0006396228,0.009915725,0.00014795005,0.00008095326,0.000021831784,0.0030830668,0.02052997,0.0042881784,0.35793278,0.00257798,0.60076296],"study_design_scores_gemma":[0.00073554274,0.000036259727,0.044707924,0.000012665675,0.000009816151,0.000017208255,0.000036468013,0.94149345,0.003013979,0.0008547575,0.008859206,0.00022273955],"about_ca_topic_score_codex":0.000064298,"about_ca_topic_score_gemma":0.000038798506,"teacher_disagreement_score":0.92096347,"about_ca_system_score_codex":0.000026898471,"about_ca_system_score_gemma":0.00007512095,"threshold_uncertainty_score":0.32159048},"labels":[],"label_agreement":null},{"id":"W3122240496","doi":"10.1109/iccv48922.2021.01003","title":"Self-Supervised Representation Learning from Flow Equivariance","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Representation (politics); Segmentation; Feature learning; Computer vision; Frame (networking); Object (grammar); Transformation (genetics); Transformation geometry; Pattern recognition (psychology)","score_opus":0.045308909399612,"score_gpt":0.3297275159253669,"score_spread":0.2844186065257549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122240496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024635365,0.00003251941,0.9485203,0.0136845475,0.002678174,0.00024521598,0.000020389502,0.0004841571,0.009699302],"genre_scores_gemma":[0.6216665,0.000084548934,0.37512773,0.0010514007,0.00080989505,0.000053763986,0.00027412054,0.000028762137,0.00090328837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959667,0.00048197003,0.0006208299,0.0014633795,0.0010822655,0.0003849107],"domain_scores_gemma":[0.99686474,0.00051112473,0.00030012685,0.0011234753,0.0009853501,0.00021519262],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031233914,0.00036673815,0.0003568252,0.00022273134,0.00032150606,0.0011511492,0.0018220119,0.00016306413,0.0015466885],"category_scores_gemma":[0.00014095,0.0003910657,0.00019654272,0.000615834,0.00003836422,0.0007859069,0.0007526921,0.00077403383,0.0014815003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010171298,0.0012826219,0.0034144793,0.00003367701,0.0004415474,0.00040078632,0.0029635078,0.10103859,0.032729007,0.19770506,0.007870507,0.6520185],"study_design_scores_gemma":[0.00081426813,0.00012242568,0.0062552425,0.000132773,0.000011194342,0.000023329741,0.000032076226,0.9794156,0.0025203552,0.004081417,0.0061974446,0.00039387628],"about_ca_topic_score_codex":0.00026096776,"about_ca_topic_score_gemma":0.000021153044,"teacher_disagreement_score":0.878377,"about_ca_system_score_codex":0.00021511131,"about_ca_system_score_gemma":0.0002611759,"threshold_uncertainty_score":0.99988574},"labels":[],"label_agreement":null},{"id":"W3122520957","doi":"10.1109/iros51168.2021.9636080","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Multimodal Machine Learning Applications","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":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Robot; Imitation; Task (project management); Salient; Representation (politics); Unsupervised learning; Deep learning; Machine learning; Human–computer interaction","score_opus":0.0406571803570758,"score_gpt":0.3241998143792468,"score_spread":0.28354263402217095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122520957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5555636,0.00007708317,0.43916214,0.0010096075,0.0007418142,0.00024829005,0.00003259104,0.000071962124,0.0030928545],"genre_scores_gemma":[0.9961653,0.00006345639,0.0015464339,0.000055411394,0.00022997877,0.000054090462,0.00030080663,0.000018111412,0.0015664337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976203,0.00025384428,0.00058971194,0.0006745888,0.00066088676,0.00020068549],"domain_scores_gemma":[0.99828327,0.00027912014,0.00042355584,0.00039119343,0.00050874456,0.0001141097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025424015,0.00023721292,0.00033222986,0.00012901345,0.0001992342,0.0004141887,0.0005421926,0.000098830635,0.00012944826],"category_scores_gemma":[0.00012564124,0.00023118967,0.00010407254,0.00018684875,0.000054596716,0.00030323747,0.00015154232,0.0003804751,0.000081534876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017198778,0.0007299303,0.0120813595,0.000058948135,0.00022801445,0.000015066488,0.005020058,0.077757075,0.26760006,0.6056808,0.00054540415,0.030266035],"study_design_scores_gemma":[0.00035215853,0.00013990556,0.009897914,0.00032112692,0.00002108778,0.000009535812,0.00050292275,0.9613643,0.020512654,0.0055920123,0.000938575,0.00034777826],"about_ca_topic_score_codex":0.0013989282,"about_ca_topic_score_gemma":0.000026322748,"teacher_disagreement_score":0.88360727,"about_ca_system_score_codex":0.00009474781,"about_ca_system_score_gemma":0.00005956552,"threshold_uncertainty_score":0.9427641},"labels":[],"label_agreement":null},{"id":"W3133365413","doi":"10.1007/s10791-021-09398-0","title":"Neural ranking models for document retrieval","year":2021,"lang":"en","type":"preprint","venue":"Information Retrieval","topic":"Multimodal Machine Learning Applications","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":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; National Institute of Standards and Technology; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence; Machine learning; Set (abstract data type); Variety (cybernetics); Information retrieval; Artificial neural network; Deep learning; Learning to rank; Data mining","score_opus":0.02256006568427007,"score_gpt":0.29165840351195466,"score_spread":0.2690983378276846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133365413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04124403,0.000113104295,0.951335,0.0025351665,0.0013943673,0.0014635592,0.000044837623,0.0005711074,0.0012987934],"genre_scores_gemma":[0.86149025,0.000020281153,0.13652611,0.00088946446,0.00019944494,0.000098002354,0.0006880732,0.000021633166,0.00006673157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970396,0.00010415518,0.0010039641,0.0005231541,0.00088223896,0.00044686947],"domain_scores_gemma":[0.99659675,0.00027397845,0.0007667113,0.0013829722,0.00081933104,0.00016026023],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000976382,0.00037575487,0.0004195159,0.00032877488,0.00030860055,0.0018741086,0.0016955911,0.00039580135,0.00002584736],"category_scores_gemma":[0.00047302234,0.00040250932,0.00032725662,0.00055272394,0.000039755752,0.0029805733,0.0016800114,0.0009526065,0.000047810176],"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":[0.00018912969,0.00005924394,0.00007008817,0.00061685196,0.00013181324,0.000003048625,0.0065932767,0.86375654,0.00013147744,0.07432712,0.00065763557,0.053463805],"study_design_scores_gemma":[0.0007125494,0.000052188916,0.0005041033,0.00007367885,0.000025390507,0.000012825454,0.000048694892,0.9826886,0.0006501641,0.012329965,0.0024774263,0.00042441476],"about_ca_topic_score_codex":0.00010356543,"about_ca_topic_score_gemma":0.0000013685257,"teacher_disagreement_score":0.8202462,"about_ca_system_score_codex":0.000288609,"about_ca_system_score_gemma":0.0004656279,"threshold_uncertainty_score":0.9998427},"labels":[],"label_agreement":null},{"id":"W3133424709","doi":"10.1109/iros45743.2020.9340905","title":"Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Alberta","funders":"","keywords":"Computer science; Ontology; Robot; Scheme (mathematics); Artificial intelligence; Human–computer interaction; Process (computing); Object (grammar); Mobile robot; Computer vision","score_opus":0.08615830094156307,"score_gpt":0.3290150866216928,"score_spread":0.24285678568012975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133424709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27108485,0.0000687061,0.7247258,0.0017595519,0.000011212608,0.00019791067,8.388003e-7,0.00015810464,0.001993086],"genre_scores_gemma":[0.9678757,0.000002482449,0.03169222,0.00037827183,0.000013813424,0.000012932933,0.000004510605,0.0000085510455,0.000011468868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899656,0.00007063019,0.00023093764,0.00043046588,0.00011408214,0.00015730964],"domain_scores_gemma":[0.9995011,0.0001011031,0.00007784319,0.00022609477,0.000014914073,0.00007893006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117881114,0.00011922559,0.00018057114,0.000058790272,0.00014386284,0.00011259851,0.00018694035,0.000067686145,0.000002821145],"category_scores_gemma":[0.000024657496,0.00011245614,0.0000143552925,0.0001649459,0.000040769835,0.00036304037,0.00020504811,0.00015730273,0.000004202498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006081794,0.000022810867,0.010787224,0.000062431114,0.00000848484,0.000012275168,0.00809801,0.045409072,0.0035395843,0.9282712,0.000031825857,0.0037510071],"study_design_scores_gemma":[0.00048132616,0.000050731196,0.024176147,0.000029985806,0.000003699748,0.000011479243,0.0005768954,0.97042996,0.000041979518,0.0040756073,0.0000044093867,0.000117794385],"about_ca_topic_score_codex":0.002345641,"about_ca_topic_score_gemma":0.0010400815,"teacher_disagreement_score":0.9250209,"about_ca_system_score_codex":0.000090832364,"about_ca_system_score_gemma":0.000014665388,"threshold_uncertainty_score":0.45858282},"labels":[],"label_agreement":null},{"id":"W3139837796","doi":"10.1016/j.media.2022.102374","title":"Weakly supervised segmentation with cross-modality equivariant constraints","year":2022,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Multimodal Machine Learning Applications","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":"École de Technologie Supérieure","funders":"Compute Canada","keywords":"Computer science; Segmentation; Modality (human–computer interaction); Modalities; Artificial intelligence; Equivariant map; Machine learning; Constraint (computer-aided design); Exploit; Pattern recognition (psychology); Divergence (linguistics); Pixel; Mathematics","score_opus":0.016168797614745857,"score_gpt":0.34553033631595975,"score_spread":0.3293615387012139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139837796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076671116,0.00003655124,0.9119485,0.007991182,0.00011906153,0.000393149,0.00008336013,0.0003726998,0.0023843865],"genre_scores_gemma":[0.82523835,0.000015849855,0.17251067,0.00075773365,0.00008956269,0.0003903887,0.0008007248,0.000024407338,0.00017230067],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99447024,0.00063571474,0.00073503266,0.0014805222,0.002213736,0.0004647615],"domain_scores_gemma":[0.99635834,0.00034013262,0.00043514525,0.0021191062,0.00027240868,0.0004748503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018582494,0.00039447247,0.00074104214,0.0005004907,0.00040252297,0.0007352938,0.0029249238,0.000243294,0.009329114],"category_scores_gemma":[0.00048516167,0.00034458324,0.00045333005,0.0020056257,0.0005592493,0.00027169293,0.0030204598,0.0017385983,0.0000847293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015581877,0.0036143526,0.43499428,0.0009088427,0.021112138,0.0025874244,0.008306571,0.15109463,0.0033232318,0.031522688,0.0012227019,0.34115732],"study_design_scores_gemma":[0.00055371237,0.0000433734,0.11549924,0.00002438666,0.0008773951,0.000015050833,0.00006255078,0.8806363,0.00011185055,0.0015511092,0.00012409616,0.0005009636],"about_ca_topic_score_codex":0.0037830765,"about_ca_topic_score_gemma":0.000108450935,"teacher_disagreement_score":0.7485672,"about_ca_system_score_codex":0.00023607186,"about_ca_system_score_gemma":0.00072835805,"threshold_uncertainty_score":0.99990064},"labels":[],"label_agreement":null},{"id":"W3157108758","doi":"10.1109/iccv48922.2021.01558","title":"Segmentation-grounded Scene Graph Generation","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Multimodal Machine Learning Applications","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Air Force; Compute Canada; Defense Advanced Research Projects Agency; Air Force Research Laboratory; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Scene graph; Segmentation; Graph; Pixel; Bounding overwatch; Pattern recognition (psychology); Granularity; Computer vision; Image segmentation; Object (grammar); Theoretical computer science","score_opus":0.06238528048595809,"score_gpt":0.3508478787254485,"score_spread":0.2884625982394904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157108758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058733806,0.00005258126,0.9182375,0.009479547,0.008952981,0.0007207353,0.000059617363,0.00035769536,0.0034055326],"genre_scores_gemma":[0.749262,0.0002070536,0.24505815,0.0014212054,0.0017233056,0.000266311,0.0014293496,0.000052252853,0.00058038393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99387455,0.00050562096,0.0010878313,0.0023249695,0.0017204913,0.00048652047],"domain_scores_gemma":[0.99515516,0.00021305749,0.00079905696,0.0019350537,0.0016099564,0.00028773706],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056545413,0.000772175,0.0006313597,0.0007291581,0.0003794547,0.0033972624,0.0034306627,0.0004554813,0.0010188792],"category_scores_gemma":[0.00005651338,0.00082282274,0.00042619382,0.00053506426,0.00008517941,0.0007256211,0.0021287936,0.0015053222,0.00049319764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007407671,0.0020120249,0.0007447541,0.00015477726,0.0008929053,0.00022411178,0.0022216565,0.15457372,0.04505915,0.22740941,0.017611844,0.54902154],"study_design_scores_gemma":[0.000670346,0.00015967063,0.0035462987,0.0003891233,0.000024578703,0.000030047197,0.000027379292,0.9856494,0.0035447308,0.0044717262,0.0006857833,0.0008009083],"about_ca_topic_score_codex":0.0007335012,"about_ca_topic_score_gemma":0.00011381564,"teacher_disagreement_score":0.83107567,"about_ca_system_score_codex":0.000546116,"about_ca_system_score_gemma":0.0005999462,"threshold_uncertainty_score":0.9998943},"labels":[],"label_agreement":null},{"id":"W3167565399","doi":"10.1109/tpami.2022.3194311","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","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 Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; CHIST-ERA; Nvidia","keywords":"Notation; Benchmark (surveying); Task (project management); Set (abstract data type); Question answering; Computer science; Artificial neural network; Artificial intelligence; Variable (mathematics); Architecture; Speech recognition; Mathematics; Arithmetic; Programming language; Engineering","score_opus":0.015824980517555244,"score_gpt":0.28340041613584366,"score_spread":0.2675754356182884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167565399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008827525,0.00005447072,0.98879075,0.0016034658,0.00016710864,0.00028513596,0.00008230975,0.00017330996,0.000015900212],"genre_scores_gemma":[0.99145097,0.000016367769,0.0075100195,0.0005114983,0.00002074307,0.00037129948,0.000013617929,0.000015199301,0.00009029994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984804,0.00013865897,0.00028936416,0.0005873704,0.00026220965,0.00024201216],"domain_scores_gemma":[0.99899054,0.00025563355,0.00010822026,0.0004947236,0.00004883846,0.000102052836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030671392,0.00019522877,0.0002356479,0.00051681075,0.000723228,0.00011250792,0.00054344296,0.000031941527,0.000087786015],"category_scores_gemma":[0.00000835053,0.00019010091,0.00023292477,0.0010790229,0.000029783783,0.00010631992,0.00001538076,0.00047009528,0.00000489369],"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":[0.000008641827,0.000074475705,0.00021675715,0.000009073953,0.000103237326,0.0000015017753,0.00026563543,0.5889529,0.0005614514,0.00014771208,0.0000022907748,0.40965632],"study_design_scores_gemma":[0.00009077267,0.00018241428,0.0014472947,0.000004204345,0.00023204762,0.000022364895,0.000033148357,0.9934439,0.003723141,0.0004268397,0.000182827,0.00021103938],"about_ca_topic_score_codex":0.0017651769,"about_ca_topic_score_gemma":0.0007724437,"teacher_disagreement_score":0.98262346,"about_ca_system_score_codex":0.00005674768,"about_ca_system_score_gemma":0.00001725149,"threshold_uncertainty_score":0.775209},"labels":[],"label_agreement":null},{"id":"W3171547673","doi":"10.48550/arxiv.2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":73,"is_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":"Ground; Transformer; Task (project management); Computer science; Engineering; Electrical engineering; Systems engineering; Voltage","score_opus":0.11713264509518619,"score_gpt":0.23845911190050736,"score_spread":0.12132646680532118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171547673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31167468,0.000020105967,0.6842224,0.00011097319,0.00016740397,0.0004800976,0.000005491342,0.00040559957,0.0029132587],"genre_scores_gemma":[0.88590556,0.000027253998,0.11327163,0.00015123244,0.00006957598,0.000013783022,0.000047948244,0.000039453917,0.00047357767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966491,0.00022215885,0.0003147085,0.002042614,0.00018939096,0.00058202056],"domain_scores_gemma":[0.9976081,0.00010245498,0.00020026871,0.0015265679,0.00017496344,0.00038760193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033385208,0.00044801016,0.00049181154,0.0004624802,0.00036727256,0.00039276233,0.0024390637,0.0003349241,0.000018026647],"category_scores_gemma":[0.000055380577,0.00058166054,0.0002943728,0.0012395261,0.000057971705,0.00042243183,0.0012601196,0.0012405491,0.00011389205],"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":[0.00003840444,0.0014598938,0.0067698653,0.00042395815,0.00037463143,0.00013373914,0.0047362847,0.79893184,0.0024423632,0.17329444,0.00003935804,0.011355202],"study_design_scores_gemma":[0.0005456803,0.000038141454,0.009403799,0.00012467493,0.00007357481,0.000008114811,0.0002863908,0.9878785,0.00018745355,0.00044370673,0.00029162198,0.0007183229],"about_ca_topic_score_codex":0.0018858452,"about_ca_topic_score_gemma":0.00011064119,"teacher_disagreement_score":0.57423085,"about_ca_system_score_codex":0.0004579193,"about_ca_system_score_gemma":0.00022458103,"threshold_uncertainty_score":0.9996635},"labels":[],"label_agreement":null},{"id":"W3172726328","doi":"10.18653/v1/2021.naacl-main.153","title":"Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Question answering; Computer science; Natural language processing; Fusion; Artificial intelligence; Information retrieval; Linguistics; Philosophy","score_opus":0.018629945614470084,"score_gpt":0.37460044306566087,"score_spread":0.3559704974511908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172726328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36108637,0.00006380151,0.6359329,0.00061061786,0.00023177972,0.0002243253,0.0000034039897,0.00043243292,0.0014143547],"genre_scores_gemma":[0.8412337,0.0000019858555,0.15655537,0.00020710526,0.00013679948,0.00008373113,0.000035847814,0.000019847323,0.0017256098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984497,0.00008427536,0.00029185857,0.0006448914,0.0001964505,0.00033284852],"domain_scores_gemma":[0.99853927,0.0003365928,0.000090646856,0.00054496655,0.00034927326,0.0001392493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039308012,0.00018444438,0.00017153594,0.00009551896,0.00035539665,0.00035834016,0.00047321818,0.00008686068,0.00008364843],"category_scores_gemma":[0.00026644993,0.00018573571,0.0001097618,0.0005163371,0.00004161198,0.00028181172,0.00023359637,0.00019919296,0.00014644621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010055224,0.0018539388,0.047802586,0.00028951606,0.00005243276,0.0000349974,0.0014791675,0.04133692,0.12001228,0.08980128,0.0009709768,0.69626534],"study_design_scores_gemma":[0.00077545387,0.00007212407,0.06167239,0.000038830727,0.000006973163,0.0000058888154,0.000013518448,0.88369924,0.04450734,0.00048386425,0.008437309,0.00028703926],"about_ca_topic_score_codex":0.00010415031,"about_ca_topic_score_gemma":0.00007891375,"teacher_disagreement_score":0.84236234,"about_ca_system_score_codex":0.000082846374,"about_ca_system_score_gemma":0.00025818564,"threshold_uncertainty_score":0.75740826},"labels":[],"label_agreement":null},{"id":"W3173904629","doi":"10.21428/594757db.898c7976","title":"Descriptive Image Captioning with Salient Retrieval Priors","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Salient; Closed captioning; Benchmark (surveying); Prior probability; Exploit; Artificial intelligence; Image (mathematics); Range (aeronautics); Modal; Information retrieval; Natural language processing; Pattern recognition (psychology); Machine learning; Bayesian probability","score_opus":0.009867451841899348,"score_gpt":0.2439625610612905,"score_spread":0.23409510921939114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173904629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21715488,0.000015047418,0.77042776,0.0023595172,0.000043547432,0.000084236526,5.800088e-7,0.0002505395,0.009663884],"genre_scores_gemma":[0.6119559,0.0000011214646,0.3870574,0.00021054965,0.000016053977,0.000006144089,0.0000025712754,0.0000058853907,0.0007443649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904,0.000057509667,0.00011547456,0.00037594256,0.00022884701,0.00018221715],"domain_scores_gemma":[0.99911416,0.000054990032,0.000049659066,0.00050010247,0.00019875076,0.000082316146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012865821,0.000089759335,0.0000866517,0.000041203864,0.00015686553,0.00020541211,0.00031500548,0.000025858255,0.00007703134],"category_scores_gemma":[0.00007371056,0.000074549374,0.000027864611,0.00052768906,0.00003838923,0.0002765744,0.0001829983,0.00016314187,0.00016485008],"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":[0.000039620663,0.0004224381,0.028185578,0.00003216901,0.00010887629,0.00022699422,0.010256217,0.0053106477,0.15057547,0.78403354,0.001454868,0.019353606],"study_design_scores_gemma":[0.0017190927,0.0002876192,0.34980863,0.00009088749,0.000037926147,0.0002958513,0.0013919214,0.51340127,0.121047236,0.0060547288,0.004770138,0.0010946963],"about_ca_topic_score_codex":0.00021161865,"about_ca_topic_score_gemma":0.000026175356,"teacher_disagreement_score":0.7779788,"about_ca_system_score_codex":0.00006351147,"about_ca_system_score_gemma":0.00013246325,"threshold_uncertainty_score":0.30400354},"labels":[],"label_agreement":null},{"id":"W3173937618","doi":"10.18653/v1/2021.acl-short.36","title":"Enhancing Descriptive Image Captioning with Natural Language Inference","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Closed captioning; Computer science; Inference; Natural language; Computational linguistics; Natural language processing; Natural (archaeology); Joint (building); Artificial intelligence; Linguistics; Image (mathematics); History; Engineering; Philosophy","score_opus":0.007255126184124819,"score_gpt":0.2684051231919964,"score_spread":0.26114999700787156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173937618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21651083,0.00007712322,0.7762111,0.0006532438,0.00004405145,0.00005401775,4.2279683e-7,0.00025487458,0.006194358],"genre_scores_gemma":[0.63004744,7.4489736e-7,0.36912045,0.00015622411,0.000017153765,0.000011914814,0.0000034638394,0.0000044467088,0.0006381838],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991717,0.00005037574,0.000104575134,0.00032555172,0.00016198393,0.00018584458],"domain_scores_gemma":[0.99921083,0.00011340956,0.00004562462,0.0004150979,0.00015944726,0.000055569915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090842266,0.000093793984,0.00008828912,0.000041150364,0.00014288943,0.00022688005,0.00031809733,0.000021298089,0.00006670271],"category_scores_gemma":[0.0001315288,0.000076736374,0.000022847698,0.00038934912,0.000028630822,0.00043107735,0.0001832303,0.0002285777,0.00012618306],"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":[0.000005881576,0.00010460962,0.007064388,0.000029186032,0.000047735473,0.00018604248,0.017193004,0.0009653778,0.7656012,0.16703027,0.000094362076,0.041677944],"study_design_scores_gemma":[0.00081148196,0.00008001864,0.12783042,0.00012871427,0.000017703049,0.00022454961,0.0032695436,0.49910086,0.36639816,0.0010115353,0.00033994325,0.0007870768],"about_ca_topic_score_codex":0.0007373218,"about_ca_topic_score_gemma":0.00045194535,"teacher_disagreement_score":0.49813548,"about_ca_system_score_codex":0.00004296396,"about_ca_system_score_gemma":0.00011094241,"threshold_uncertainty_score":0.31292185},"labels":[],"label_agreement":null},{"id":"W3174481471","doi":"10.18653/v1/2021.acl-long.564","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":50,"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":"Open Philanthropy Project; Canadian Institute for Advanced Research","keywords":"Question answering; Outlier; Computational linguistics; Natural language processing; Computer science; Artificial intelligence; Corpus linguistics; Volume (thermodynamics); Linguistics; Information retrieval; Philosophy","score_opus":0.029758105145624873,"score_gpt":0.36747120422434215,"score_spread":0.33771309907871727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174481471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68092805,0.0000058982746,0.31647524,0.0010228313,0.000053342923,0.00027466146,0.0000026285325,0.000073204974,0.0011641373],"genre_scores_gemma":[0.9361259,9.819245e-7,0.063457616,0.00008924067,0.000051990017,0.0000531887,0.000008291338,0.000015214928,0.00019758583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986174,0.00023867439,0.0002471133,0.00041039483,0.00023164006,0.0002547748],"domain_scores_gemma":[0.998129,0.0009485353,0.0002527672,0.0003291086,0.0002483874,0.000092218535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042104474,0.00016441663,0.00018380757,0.000082438,0.00034513423,0.00011744726,0.0003765931,0.00006024725,0.000015713433],"category_scores_gemma":[0.0017341335,0.00012098104,0.00014881017,0.00047274114,0.00008234368,0.0002511607,0.00014912887,0.00038421692,0.00001259373],"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":[0.000058143556,0.0002557319,0.03744756,0.000040040915,0.00029656343,0.0000030521228,0.03326857,0.5119997,0.07309273,0.030694827,0.00009391431,0.31274915],"study_design_scores_gemma":[0.00041675637,0.00033594368,0.115360886,0.0000513625,0.000014677889,0.0000045896345,0.0015539154,0.84257656,0.037922606,0.0015338841,0.00004767815,0.00018116907],"about_ca_topic_score_codex":0.00064529845,"about_ca_topic_score_gemma":0.000022741398,"teacher_disagreement_score":0.3305768,"about_ca_system_score_codex":0.0001353361,"about_ca_system_score_gemma":0.00020559898,"threshold_uncertainty_score":0.49334636},"labels":[],"label_agreement":null},{"id":"W3176425931","doi":"10.1609/aaai.v35i3.16353","title":"Semantic Grouping Network for Video Captioning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":148,"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":"Computer science; Interpretability; Closed captioning; Margin (machine learning); Word (group theory); Redundancy (engineering); Phrase; Artificial intelligence; Natural language processing; Speech recognition; Image (mathematics); Machine learning","score_opus":0.06834906582068068,"score_gpt":0.31396189647539346,"score_spread":0.2456128306547128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176425931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11387255,0.000057446567,0.86625713,0.011830116,0.0006104794,0.0006800652,0.0000041546004,0.0002191642,0.0064689005],"genre_scores_gemma":[0.93858767,0.000008178519,0.060620118,0.0004062097,0.00014454032,0.00008765005,0.0000010034705,0.000013370155,0.00013128936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983254,0.000019656272,0.00045491394,0.00053245586,0.00030562317,0.0003619149],"domain_scores_gemma":[0.9981371,0.00024165456,0.00034563165,0.00036065298,0.00084406557,0.00007086856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005272002,0.00017141282,0.00022081556,0.00005674926,0.00042681306,0.00032030005,0.0013835336,0.000060039845,0.000028826347],"category_scores_gemma":[0.000799697,0.00014717624,0.00013837757,0.0007704102,0.000109865345,0.00026799922,0.00037462235,0.00027486248,0.000050537543],"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":[0.0000095158985,0.000053936747,0.00060846796,0.000038916805,0.000012076385,2.2537624e-7,0.00042664786,0.0016709277,0.022265848,0.9482062,0.00011727778,0.026589952],"study_design_scores_gemma":[0.000029043766,0.000060251863,0.0011989865,0.0002655203,0.00001541216,0.000009451949,0.00017505401,0.52085954,0.12729722,0.3495454,0.00033278042,0.00021138364],"about_ca_topic_score_codex":0.00007888712,"about_ca_topic_score_gemma":0.000019156994,"teacher_disagreement_score":0.8247151,"about_ca_system_score_codex":0.00003957254,"about_ca_system_score_gemma":0.00011676428,"threshold_uncertainty_score":0.6001673},"labels":[],"label_agreement":null},{"id":"W3177283914","doi":"10.1145/3452918.3458795","title":"Context-Aware Question-Answer for Interactive Media Experiences","year":2021,"lang":"en","type":"article","venue":"ACM International Conference on Interactive Media Experiences","topic":"Multimodal Machine Learning Applications","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":"Computer science; Context (archaeology); Entertainment; Quality (philosophy); Multimedia; World Wide Web; Information retrieval; Context model; Artificial intelligence","score_opus":0.05343325353059438,"score_gpt":0.3770970106831698,"score_spread":0.32366375715257545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177283914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71468824,0.00013835584,0.23500071,0.023106348,0.01432094,0.00085389335,0.00012520111,0.0005214271,0.011244862],"genre_scores_gemma":[0.980064,0.000038631748,0.014124371,0.0012925162,0.0005556969,0.0034684918,0.0001553272,0.00002621713,0.00027479976],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.996256,0.0002930235,0.0006597089,0.001350591,0.00095751794,0.00048317388],"domain_scores_gemma":[0.99239624,0.0038782975,0.0004879402,0.0010183429,0.001956395,0.000262782],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031788036,0.0004581193,0.00044463642,0.0003126957,0.0003337368,0.0006809661,0.0034498847,0.00014256491,0.0021718945],"category_scores_gemma":[0.006896667,0.00041687922,0.00022249558,0.00041140403,0.00038210276,0.0018055376,0.000714031,0.00057232205,0.00020705519],"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":[0.0003066188,0.0007090679,0.0016694135,0.000013105413,0.00023510802,0.00006312806,0.5224385,0.000048122412,0.0034897828,0.3997709,0.0019402634,0.06931596],"study_design_scores_gemma":[0.0021245833,0.0005760326,0.0062487414,0.00065788656,0.000032693522,0.00013759015,0.70391124,0.10957295,0.12146498,0.03818953,0.015373822,0.0017099205],"about_ca_topic_score_codex":0.00027906735,"about_ca_topic_score_gemma":0.00022325481,"teacher_disagreement_score":0.36158136,"about_ca_system_score_codex":0.00024883906,"about_ca_system_score_gemma":0.000428476,"threshold_uncertainty_score":0.9998283},"labels":[],"label_agreement":null},{"id":"W3192616105","doi":"10.48550/arxiv.2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Automatic summarization; Computer science; Bridging (networking); Phrase; Artificial intelligence; Modal; Semantics (computer science); Natural language processing; Mobile device; Set (abstract data type); Information retrieval; Human–computer interaction; World Wide Web; Programming language","score_opus":0.028257931777442832,"score_gpt":0.19122617935735842,"score_spread":0.16296824757991557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192616105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44404095,0.000023824221,0.5541018,0.000054749282,0.00007423855,0.00036291988,0.0000031740856,0.00062729884,0.00071099965],"genre_scores_gemma":[0.95721537,0.00003223753,0.041524317,0.00004666418,0.00005040815,0.000016050504,0.00014831379,0.000040796534,0.00092586136],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733305,0.00035280114,0.00025311267,0.0014716309,0.00018534229,0.00040408576],"domain_scores_gemma":[0.9973641,0.00020071796,0.00041350265,0.001514166,0.00030764184,0.00019987389],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025872793,0.00040524534,0.00039953427,0.0002977542,0.0003775938,0.00038210498,0.0016570158,0.00028940008,0.00008788604],"category_scores_gemma":[0.00007828058,0.00045062258,0.00015676598,0.001127812,0.000109031374,0.00043774437,0.0018757711,0.0012814946,0.00011718662],"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":[0.0000068455333,0.00012047857,0.0218749,0.000084233325,0.00008478664,0.00011098432,0.0006955216,0.96423864,0.00005421828,0.00806846,0.000011666626,0.00464928],"study_design_scores_gemma":[0.00045323223,0.00007399375,0.012716857,0.00016941715,0.00006785114,0.000008787422,0.00032024685,0.98488325,0.000041498402,0.0006140777,0.00014008034,0.00051068544],"about_ca_topic_score_codex":0.0017101526,"about_ca_topic_score_gemma":0.00010647522,"teacher_disagreement_score":0.51317436,"about_ca_system_score_codex":0.0002349823,"about_ca_system_score_gemma":0.00035474636,"threshold_uncertainty_score":0.99979454},"labels":[],"label_agreement":null},{"id":"W3195852121","doi":"10.1109/ecbios51820.2021.9510291","title":"Policy and Value Deep RL for Temporal Language-Agnostic Street Image Captioning","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Artificial intelligence; Natural language; Image (mathematics); Word (group theory); Natural language processing; Encoder; Linguistics","score_opus":0.009107360291103987,"score_gpt":0.30280202643381243,"score_spread":0.29369466614270845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195852121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084042534,0.000080182705,0.9076267,0.004462326,0.000034147626,0.00015813492,0.0000050549615,0.0001961068,0.0033948545],"genre_scores_gemma":[0.64826745,0.0000022173501,0.35087466,0.00036346968,0.00007519802,0.000032765463,0.000014565525,0.0000067914043,0.00036286958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923074,0.00004201502,0.00012439262,0.00031597845,0.00009813399,0.00018874527],"domain_scores_gemma":[0.9991065,0.00032631648,0.00004200126,0.00036209903,0.00007777604,0.00008530465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012489039,0.00008760935,0.00009427511,0.000065412234,0.00015938375,0.00017526036,0.00023453306,0.0000325575,0.000016781703],"category_scores_gemma":[0.00040899374,0.00008561931,0.00003385463,0.00025674625,0.000027498389,0.0001830736,0.00019390525,0.00008556396,0.000021780459],"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":[0.0000022227894,0.000087931825,0.013304191,0.00005126325,0.000024345109,0.000019018436,0.0018362406,0.0019463232,0.011076207,0.9172949,0.0002997101,0.054057598],"study_design_scores_gemma":[0.00072150363,0.000054077223,0.06668845,0.000020670423,0.000013952753,0.000047739228,0.00029607047,0.91548264,0.00501488,0.010489721,0.0008517663,0.00031855324],"about_ca_topic_score_codex":0.0025359762,"about_ca_topic_score_gemma":0.00028735903,"teacher_disagreement_score":0.9135363,"about_ca_system_score_codex":0.000025137784,"about_ca_system_score_gemma":0.000098594515,"threshold_uncertainty_score":0.38336542},"labels":[],"label_agreement":null},{"id":"W3197581510","doi":"10.1609/aaai.v36i10.21306","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Commonsense reasoning; Closed captioning; Computer science; Fluency; Transformer; Commonsense knowledge; Generative grammar; Artificial intelligence; Natural language processing; Image (mathematics); Linguistics; Engineering; Knowledge extraction","score_opus":0.14225812018072292,"score_gpt":0.355538293976938,"score_spread":0.21328017379621506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197581510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45031416,0.00004384155,0.54151756,0.004106794,0.0008557382,0.0018398421,0.000026704405,0.00015209979,0.0011432705],"genre_scores_gemma":[0.97974336,0.000043615426,0.018938195,0.00016876931,0.00020385506,0.0007198716,0.000020124724,0.000038121143,0.00012406355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964491,0.000088679946,0.0011584952,0.0011594446,0.0006785804,0.00046568114],"domain_scores_gemma":[0.99721014,0.0002487608,0.0010261785,0.0005945244,0.0008280515,0.00009235722],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016695197,0.0004193254,0.0005003658,0.00040894473,0.0005331907,0.00057680113,0.0026703544,0.0002466482,0.000059064074],"category_scores_gemma":[0.00065794523,0.0003982006,0.00020502294,0.000909564,0.00014067894,0.00036551338,0.0018145221,0.0012894529,0.000014623029],"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":[0.000059505957,0.0002329849,0.00014526126,0.00012831097,0.000020612713,3.653725e-7,0.0030228256,0.068417385,0.07438916,0.8321348,0.00010138886,0.021347387],"study_design_scores_gemma":[0.000034567656,0.00009353005,0.00012167867,0.0001527661,0.000013331649,0.0000021722158,0.0002717386,0.77356905,0.073463045,0.15193301,0.000028582726,0.00031650977],"about_ca_topic_score_codex":0.0009507194,"about_ca_topic_score_gemma":0.00029238287,"teacher_disagreement_score":0.7051517,"about_ca_system_score_codex":0.00037887236,"about_ca_system_score_gemma":0.00036672415,"threshold_uncertainty_score":0.999847},"labels":[],"label_agreement":null},{"id":"W3200042178","doi":"10.33552/gjes.2020.04.000596","title":"SRIN: A New Dataset for Social Robot Indoor Navigation","year":2020,"lang":"en","type":"article","venue":"Global Journal of Engineering Sciences","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada","keywords":"The Internet; Computer science; Robot; Internet of Things; Computer security; Transport engineering; World Wide Web; Artificial intelligence; Engineering","score_opus":0.035873728696510024,"score_gpt":0.31969755222435503,"score_spread":0.283823823527845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200042178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022830434,0.00007016762,0.96293783,0.013738822,0.00020683785,0.000084942396,0.00006514021,0.00003898269,0.000026821826],"genre_scores_gemma":[0.7288591,9.955719e-7,0.27045837,0.000312888,0.00035441015,0.000001821021,0.000009212604,0.000002412788,7.517746e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999098,0.000012908779,0.00024091598,0.0001640336,0.00030861996,0.00017550333],"domain_scores_gemma":[0.9994608,0.00005780559,0.00018035345,0.00007699962,0.00006703854,0.0001570119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030491364,0.00008259657,0.00012515749,0.000037264464,0.00012760164,0.00018670692,0.0011030148,0.000027386935,0.0000022199365],"category_scores_gemma":[0.00020626123,0.00007277137,0.000059555125,0.0006255956,0.00003067714,0.0005081503,0.00008893648,0.00011452743,0.000006548113],"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":[0.000030850377,0.00007484025,0.0040600267,0.00008379996,0.00007312682,0.00001793504,0.0013161546,0.7517599,0.012839499,0.12621959,0.03690308,0.06662121],"study_design_scores_gemma":[0.0007252172,0.00038981653,0.013818011,0.00004254666,0.000018346533,0.00012399211,0.000030425083,0.9546597,0.0006330919,0.0019631472,0.02734504,0.00025068663],"about_ca_topic_score_codex":0.000026012856,"about_ca_topic_score_gemma":4.149151e-7,"teacher_disagreement_score":0.7060287,"about_ca_system_score_codex":0.000037398455,"about_ca_system_score_gemma":0.00016179172,"threshold_uncertainty_score":0.29675302},"labels":[],"label_agreement":null},{"id":"W3200172683","doi":"10.18653/v1/2021.emnlp-main.516","title":"Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","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":"Contextualization; Computer science; Generalization; Context (archaeology); Set (abstract data type); Exploit; Parameterized complexity; Artificial intelligence; Test set; Embedding; Cube (algebra); Machine learning; Algorithm; Mathematics; Programming language","score_opus":0.06160955148695172,"score_gpt":0.46076189392771477,"score_spread":0.39915234244076303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200172683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7771295,0.0023884634,0.21577853,0.0034026213,0.0001741653,0.0007532968,0.0000034566315,0.00002680726,0.0003431587],"genre_scores_gemma":[0.94096375,0.000007461574,0.05866545,0.00015411808,0.000058563495,0.00008852058,0.0000021254234,0.0000149499365,0.00004506943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802566,0.000286964,0.000576772,0.00046347428,0.00029910463,0.00034800547],"domain_scores_gemma":[0.99729437,0.0013682339,0.00053393893,0.0002793272,0.00047931157,0.00004482003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015876108,0.00021828129,0.00037177064,0.0001176688,0.00025774882,0.00022227729,0.0012608126,0.00011509023,0.000008913917],"category_scores_gemma":[0.0035043857,0.00011241762,0.00017693908,0.0014430127,0.00015899647,0.00035705577,0.00047821773,0.00082958216,1.915006e-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":[0.00008803403,0.00018873761,0.01570872,0.00010718204,0.000027047416,0.0000011122762,0.013974718,0.0047122845,0.081775874,0.006997934,0.000018553397,0.8763998],"study_design_scores_gemma":[0.00036658603,0.000045202207,0.031917617,0.0004655492,0.000011480159,0.000008360422,0.0025869687,0.95139205,0.011768366,0.0012924487,0.0000067968585,0.00013855698],"about_ca_topic_score_codex":0.00017905192,"about_ca_topic_score_gemma":0.000031433072,"teacher_disagreement_score":0.9466798,"about_ca_system_score_codex":0.00011061916,"about_ca_system_score_gemma":0.00015226178,"threshold_uncertainty_score":0.45842573},"labels":[],"label_agreement":null},{"id":"W3202332982","doi":"10.1609/aaai.v36i10.21306","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Commonsense reasoning; Computer science; Fluency; Transformer; Generative grammar; Commonsense knowledge; Artificial intelligence; Natural language processing; Image (mathematics); Linguistics; Knowledge extraction; Engineering","score_opus":0.04270963079109104,"score_gpt":0.30356759393094573,"score_spread":0.2608579631398547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202332982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3198872,0.000022007865,0.67806184,0.0011979041,0.00012740398,0.00032527145,0.000002643833,0.0001269111,0.0002487862],"genre_scores_gemma":[0.9081731,0.0000017846162,0.09046747,0.00043609878,0.00009331213,0.0004405472,0.000044779452,0.000014913194,0.00032804042],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985455,0.00018085282,0.00032674047,0.00044370155,0.0002471728,0.0002560253],"domain_scores_gemma":[0.9992664,0.00016157553,0.00009854927,0.0003471805,0.000071156144,0.000055164208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085325114,0.00011635966,0.00013127328,0.00020914986,0.0006229937,0.00014593737,0.00041006148,0.000034526525,0.000053785207],"category_scores_gemma":[0.00005410363,0.00013039458,0.000043638553,0.000686238,0.0000121168405,0.00034824104,0.00027332635,0.00022674428,0.000011692981],"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":[0.000012326247,0.00014821053,0.000542105,0.000008528631,0.000007991524,0.0000024651345,0.001590126,0.6449586,0.081972174,0.2581816,0.0011408764,0.011434977],"study_design_scores_gemma":[0.00033458153,0.00006162122,0.00062858494,0.0000017705321,0.0000021680723,0.000011468944,0.00007884265,0.99268675,0.0023710527,0.0031622325,0.0004995907,0.00016133874],"about_ca_topic_score_codex":0.0012172917,"about_ca_topic_score_gemma":0.000658186,"teacher_disagreement_score":0.58828586,"about_ca_system_score_codex":0.0002597319,"about_ca_system_score_gemma":0.00008780927,"threshold_uncertainty_score":0.53173363},"labels":[],"label_agreement":null},{"id":"W3203338521","doi":"10.18653/v1/2021.emnlp-main.328","title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":39,"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":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Waypoint; Computer science; Task (project management); Human–computer interaction; Embodied cognition; Path (computing); Natural language; Work (physics); Measure (data warehouse); Metric (unit); Shortest path problem; Artificial intelligence; Multimedia; Programming language; Real-time computing; Engineering; Theoretical computer science; Database","score_opus":0.026221236821911142,"score_gpt":0.3976567197951307,"score_spread":0.37143548297321954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203338521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95542055,0.0035468012,0.033580136,0.0054782904,0.00014735707,0.0007318463,0.0000064785386,0.00006364192,0.0010249206],"genre_scores_gemma":[0.68806607,0.000011220822,0.31140107,0.00031142888,0.000028916706,0.0000620965,0.000005809175,0.000014803764,0.00009858154],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781007,0.00016589418,0.0005381184,0.00074742857,0.0003774822,0.00036099317],"domain_scores_gemma":[0.9986753,0.00050186424,0.00029430623,0.00029112352,0.00015977194,0.00007767023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012299895,0.00026055935,0.00043381331,0.00013839352,0.0001489283,0.00023176106,0.0007892852,0.0001559829,0.000011625351],"category_scores_gemma":[0.0015611261,0.0001927003,0.000100444246,0.0007765341,0.00012331865,0.00043543262,0.00055074284,0.000525122,0.0000017723673],"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":[0.00003682004,0.00016050955,0.0016719733,0.00022782115,0.000007340699,0.000006621366,0.01576307,0.000017833077,0.49917465,0.0060883234,0.0000062364543,0.4768388],"study_design_scores_gemma":[0.0018901702,0.00017035185,0.02438025,0.0018473371,0.0000330355,0.000047828788,0.009068174,0.48672062,0.46417862,0.0108879255,0.0001040176,0.0006716737],"about_ca_topic_score_codex":0.000150018,"about_ca_topic_score_gemma":0.0000143421075,"teacher_disagreement_score":0.4867028,"about_ca_system_score_codex":0.00010405682,"about_ca_system_score_gemma":0.00007817574,"threshold_uncertainty_score":0.78580904},"labels":[],"label_agreement":null},{"id":"W3204859046","doi":"10.18280/ts.380403","title":"Label Importance Ranking with Entropy Variation Complex Networks for Structured Video Captioning","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Multimodal Machine Learning Applications","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":"Beijing Municipal Science and Technology Commission","keywords":"Variation (astronomy); Closed captioning; Ranking (information retrieval); Computer science; Entropy (arrow of time); Artificial intelligence; Data mining; Image (mathematics); Astrophysics","score_opus":0.019463123209371765,"score_gpt":0.2584458161975389,"score_spread":0.23898269298816716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204859046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070407346,0.00004380189,0.92753726,0.001302661,0.000067973124,0.00039857408,0.0000072383473,0.00016114218,0.00007398033],"genre_scores_gemma":[0.7136,0.000001473205,0.28562185,0.00039854168,0.00014906641,0.00011339474,0.00009248756,0.000010371395,0.000012852449],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860746,0.00007429497,0.00028725146,0.0004623592,0.00027739495,0.00029122588],"domain_scores_gemma":[0.9990511,0.0001576842,0.0002009054,0.00031998556,0.00019762974,0.00007268904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026020122,0.00015622271,0.00016662826,0.00004633875,0.00034126794,0.00023225076,0.00034397308,0.000044571974,0.00013487122],"category_scores_gemma":[0.000022149414,0.00014779532,0.00004618292,0.00032509805,0.000022859609,0.00024128122,0.0000621906,0.00014481816,0.0000033673925],"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":[0.0000966068,0.00023824649,0.035008658,0.0000565437,0.00019813876,0.000017514514,0.0018047079,0.4943839,0.059513107,0.36226895,0.0005356019,0.045878023],"study_design_scores_gemma":[0.0014392887,0.000054497195,0.12756446,0.000018504417,0.000022471011,0.000014007869,0.0000127779795,0.86777914,0.00025339657,0.0018880112,0.0007802051,0.00017326485],"about_ca_topic_score_codex":0.000047293193,"about_ca_topic_score_gemma":0.000048162077,"teacher_disagreement_score":0.6431926,"about_ca_system_score_codex":0.00007676472,"about_ca_system_score_gemma":0.00007715976,"threshold_uncertainty_score":0.60269177},"labels":[],"label_agreement":null},{"id":"W3205031498","doi":"10.1145/3474085.3481545","title":"Personalized Multi-modal Video Retrieval on Mobile Devices","year":2021,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Centre for Social Innovation","funders":"","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Context (archaeology); Mobile device; Matching (statistics); Process (computing); Modal; Face (sociological concept); World Wide Web","score_opus":0.02194809163755661,"score_gpt":0.31169704922897834,"score_spread":0.2897489575914217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205031498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32049724,0.00021815803,0.6608034,0.00499931,0.0002441564,0.00034131933,0.0000049918103,0.000819873,0.012071557],"genre_scores_gemma":[0.81864727,0.0000051050756,0.17495674,0.0014178696,0.000050820498,0.0000329922,0.000007395566,0.000010848302,0.0048709926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986323,0.0001086734,0.00017315772,0.00054689386,0.0003075732,0.00023140431],"domain_scores_gemma":[0.9987496,0.00023256839,0.000058741003,0.000709957,0.00013430165,0.00011482352],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019026817,0.00013318325,0.00014417413,0.000056613582,0.0001743636,0.00017680791,0.00061608676,0.00005977961,0.00036568276],"category_scores_gemma":[0.00013849165,0.00011951965,0.00008567055,0.0004976618,0.000036277386,0.00017778967,0.0002293935,0.00022060731,0.00080726115],"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":[0.00007201699,0.0020640295,0.024007054,0.00007856212,0.00014466252,0.0001388014,0.003839498,0.008576953,0.05626157,0.81926966,0.0029833661,0.08256382],"study_design_scores_gemma":[0.0017818374,0.00017488828,0.08705168,0.000032177337,0.000013205304,0.00005090431,0.00015261072,0.81087005,0.020469412,0.0007561947,0.07807907,0.0005679427],"about_ca_topic_score_codex":0.00013195242,"about_ca_topic_score_gemma":0.000024205237,"teacher_disagreement_score":0.81851345,"about_ca_system_score_codex":0.000044815366,"about_ca_system_score_gemma":0.000103776045,"threshold_uncertainty_score":0.99997073},"labels":[],"label_agreement":null},{"id":"W3211759539","doi":"","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Multimodal Machine Learning Applications","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; Transformer; Artificial intelligence; Segmentation; Encoder; Ground; Leverage (statistics); Margin (machine learning); Language model; Machine learning; Natural language processing; Engineering","score_opus":0.040190123109037815,"score_gpt":0.30488632255680165,"score_spread":0.26469619944776385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211759539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048040655,0.000099716126,0.945763,0.0005466587,0.0002751439,0.0004973779,0.000003541508,0.00060780114,0.0041661407],"genre_scores_gemma":[0.9345828,0.0000017855053,0.06432245,0.00056702126,0.00008420798,0.00024186577,0.00005121257,0.000015598229,0.00013305183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978309,0.000102529586,0.0007379532,0.00036787926,0.00055129634,0.00040942614],"domain_scores_gemma":[0.9987611,0.000040626353,0.00023561681,0.00040024312,0.00036599283,0.00019640781],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043590105,0.00022379342,0.00026716664,0.0002610426,0.0005347241,0.0016607993,0.0006126375,0.00010321689,0.000002397775],"category_scores_gemma":[0.00010668798,0.00022515343,0.00006738031,0.0011362083,0.000019445863,0.0038098185,0.00008281011,0.0003364967,0.00014097065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027868586,0.0005352687,0.0019045828,0.0031132598,0.00006795787,0.000005301476,0.035520907,0.18230477,0.016749687,0.036334664,0.0002651694,0.7231706],"study_design_scores_gemma":[0.00040103673,0.000028228209,0.0025904889,0.00012350887,0.0000077159375,0.00009470901,0.00067777117,0.9913728,0.0005695572,0.000007659619,0.0038441045,0.0002823851],"about_ca_topic_score_codex":0.00029027605,"about_ca_topic_score_gemma":0.000005803499,"teacher_disagreement_score":0.88654214,"about_ca_system_score_codex":0.00015101419,"about_ca_system_score_gemma":0.00014066098,"threshold_uncertainty_score":0.9993756},"labels":[],"label_agreement":null},{"id":"W3212471218","doi":"10.3390/app112110449","title":"Towards Contactless Learning Activities during Pandemics Using Autonomous Service Robots","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Multimodal Machine Learning Applications","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":"Concordia University","funders":"","keywords":"Robot; Cheating; Personalization; Robotics; Artificial intelligence; Computer science; Service (business); Process (computing); Pandemic; Service-learning; Service robot; Human–computer interaction; Coronavirus disease 2019 (COVID-19); Psychology; Business; World Wide Web; Pedagogy; Marketing; Medicine","score_opus":0.03339591726116201,"score_gpt":0.2934661571553078,"score_spread":0.2600702398941458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212471218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.843577,0.000056977173,0.14680588,0.00081571453,0.000129602,0.00011423619,8.523099e-7,0.0003524554,0.008147269],"genre_scores_gemma":[0.9140924,0.0000066017037,0.08540093,0.00031586696,0.0000665061,0.000026573516,0.0000019477627,0.000010883805,0.000078278725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998073,0.00008391003,0.00023521525,0.0007143194,0.00043870858,0.00045487992],"domain_scores_gemma":[0.999061,0.00016761942,0.00016690744,0.00040975522,0.00008350348,0.00011122972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046319052,0.00018398091,0.00021944402,0.000112067835,0.0011578333,0.0005283814,0.0010693935,0.00007488254,0.000014861296],"category_scores_gemma":[0.000049444225,0.00018368122,0.000046520465,0.0013011472,0.00012951756,0.00048353898,0.0006232495,0.00037167215,0.00002652448],"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":[0.0000053909534,0.00009410933,0.011831297,0.00006246719,0.00003060043,0.000019441002,0.004612108,0.40595976,0.4004234,0.14880167,0.0000048429292,0.028154928],"study_design_scores_gemma":[0.0004933627,0.000025664438,0.03986155,0.000043855358,0.000016815595,0.00012780285,0.00167853,0.87088156,0.08255472,0.0031293589,0.0005270875,0.0006596663],"about_ca_topic_score_codex":0.0004880514,"about_ca_topic_score_gemma":0.000076284385,"teacher_disagreement_score":0.46492183,"about_ca_system_score_codex":0.00009683961,"about_ca_system_score_gemma":0.0004526631,"threshold_uncertainty_score":0.89052343},"labels":[],"label_agreement":null},{"id":"W3213111926","doi":"10.48550/arxiv.2012.02339","title":"Understanding Guided Image Captioning Performance across Domains","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Readability; Transformer; Artificial intelligence; Natural language processing; Image (mathematics); Domain (mathematical analysis); Key (lock); Information retrieval; Programming language","score_opus":0.2005041772895836,"score_gpt":0.23192816123849722,"score_spread":0.0314239839489136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213111926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42848825,0.0000018565377,0.56830114,0.0006437115,0.000028865194,0.000067924884,0.0000015096774,0.0002452769,0.0022214756],"genre_scores_gemma":[0.99027264,0.000010306446,0.009199295,0.0003300843,0.00004197346,5.717566e-7,0.0000028329935,0.000010759767,0.0001315512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891675,0.000051957883,0.000119324315,0.0005328147,0.000072458766,0.00030667093],"domain_scores_gemma":[0.9991808,0.000064974694,0.00009623962,0.0004261578,0.000052753712,0.00017907507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014906486,0.00012923458,0.000117110554,0.00004705587,0.000509341,0.00012613172,0.0008852807,0.00004926784,0.00002439138],"category_scores_gemma":[0.00004280735,0.00015331767,0.0000620949,0.00088075787,0.00008808537,0.000740041,0.00037969204,0.00022577992,0.00030556775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018073733,0.00004445846,0.048864372,0.000037040914,0.00003837187,0.00008595796,0.003147081,0.32473436,0.0031708602,0.61891353,0.00046868474,0.00047724062],"study_design_scores_gemma":[0.00044849786,0.000034640343,0.011578768,0.000009249927,0.0000070851156,0.0000052248333,0.0002143431,0.9848822,0.00021324347,0.0021067609,0.00030467863,0.00019534973],"about_ca_topic_score_codex":0.000086928565,"about_ca_topic_score_gemma":0.000007067195,"teacher_disagreement_score":0.6601478,"about_ca_system_score_codex":0.00018687053,"about_ca_system_score_gemma":0.000038906514,"threshold_uncertainty_score":0.62521136},"labels":[],"label_agreement":null},{"id":"W4200066496","doi":"10.1109/iros51168.2021.9636422","title":"Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Multimodal Machine Learning Applications","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":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Trajectory; Generalization; Terrain; Constraint (computer-aided design); Feature (linguistics); Task (project management); Computer vision; Collision avoidance; Visual space; Machine learning; Collision; Mathematics; Engineering; Psychology","score_opus":0.042992689432445066,"score_gpt":0.328001037531914,"score_spread":0.28500834809946896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200066496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16891725,0.00013288074,0.82864887,0.0005417153,0.00087331096,0.000508265,0.000027504122,0.000033874723,0.00031635232],"genre_scores_gemma":[0.99628574,0.00004419766,0.0029453891,0.000054350803,0.000100341334,0.00019953496,0.00006283887,0.00001544385,0.00029215208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997754,0.00018885458,0.0007242157,0.0006893431,0.00035240315,0.0002912346],"domain_scores_gemma":[0.9986024,0.00023630491,0.00030683537,0.00032089255,0.0004157637,0.00011780224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004688568,0.00023930415,0.00035514153,0.00022451131,0.000091000074,0.00024622935,0.00053806655,0.00012249102,0.000051478128],"category_scores_gemma":[0.000111829155,0.00023263598,0.00012151649,0.00019178996,0.0000978116,0.00017014382,0.00012506115,0.00024201341,0.00000946281],"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":[0.0001939592,0.0011488504,0.013987827,0.00036423156,0.00037958365,0.0000945752,0.0038461383,0.49052718,0.18228547,0.15046015,0.000068441164,0.1566436],"study_design_scores_gemma":[0.00048402185,0.00017395405,0.00463093,0.0003418033,0.000008252447,0.000048831018,0.0003441373,0.9893458,0.003903109,0.00041193512,0.000084145526,0.00022311966],"about_ca_topic_score_codex":0.0005145292,"about_ca_topic_score_gemma":0.00013837636,"teacher_disagreement_score":0.8273685,"about_ca_system_score_codex":0.00011455946,"about_ca_system_score_gemma":0.00012921898,"threshold_uncertainty_score":0.948662},"labels":[],"label_agreement":null},{"id":"W4200635486","doi":"10.1609/aaai.v36i3.20243","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"National Key Research and Development Program of China","keywords":"Closed captioning; Computer science; Artificial intelligence; Natural language processing; Inference; MAGIC (telescope); Sentence; Image (mathematics)","score_opus":0.05780263208315548,"score_gpt":0.305284387201188,"score_spread":0.24748175511803253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200635486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2076304,0.00001098996,0.7765041,0.0105388025,0.0005263461,0.001641389,0.00008592793,0.0002585402,0.0028034996],"genre_scores_gemma":[0.92677397,0.0000021035714,0.07271465,0.00017436943,0.00004351519,0.00020361852,0.0000053164717,0.00001293205,0.00006953301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980696,0.000041973555,0.00044624877,0.00060514815,0.0005367034,0.00030032205],"domain_scores_gemma":[0.9982684,0.00040680158,0.00043822767,0.00027446295,0.0005210633,0.000091025395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064632157,0.00021282776,0.00020874431,0.00020284239,0.000917053,0.00018980786,0.0013614385,0.000056701756,0.00012058646],"category_scores_gemma":[0.0007161337,0.00019434698,0.000124243,0.00062490255,0.000313915,0.00038486053,0.00063390966,0.00043660423,0.000015950529],"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":[0.00012957094,0.0001626841,0.0017571328,0.000026844353,0.0000137431725,2.3182527e-7,0.00093281694,0.0057342467,0.02263709,0.9482769,0.000047247737,0.020281537],"study_design_scores_gemma":[0.00016714896,0.00022545911,0.0029984855,0.000035775556,0.00001984335,0.000003019663,0.0004624599,0.86105376,0.014722032,0.11986993,0.00017296751,0.00026912472],"about_ca_topic_score_codex":0.0002682291,"about_ca_topic_score_gemma":0.0000087313365,"teacher_disagreement_score":0.8553195,"about_ca_system_score_codex":0.00008071475,"about_ca_system_score_gemma":0.00017227286,"threshold_uncertainty_score":0.792524},"labels":[],"label_agreement":null},{"id":"W4206247875","doi":"10.1007/978-3-030-92659-5_11","title":"ScaleNet: An Unsupervised Representation Learning Method for Limited Information","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"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":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Task (project management); Convolutional neural network; Representation (politics); Pattern recognition (psychology); Rotation (mathematics); Enhanced Data Rates for GSM Evolution; Scale (ratio); Machine learning; Artificial neural network; Deep learning; Feature learning","score_opus":0.025142420801092375,"score_gpt":0.31748589307844777,"score_spread":0.2923434722773554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206247875","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":[0.00017527022,0.00008006678,0.9959822,0.0012734458,0.00049387757,0.0007435487,0.000006214567,0.000322575,0.0009227804],"genre_scores_gemma":[0.03197448,0.000014866863,0.9662402,0.0010703021,0.00026520187,0.00007346195,0.0001865827,0.000030151943,0.00014470532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967544,0.00012980161,0.0006191434,0.0012546116,0.0007591056,0.00048291677],"domain_scores_gemma":[0.99631774,0.0010085145,0.00041392123,0.0014110071,0.00067044864,0.0001783768],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012565863,0.0004029464,0.00042845498,0.00084669807,0.00047265665,0.00096916035,0.0021503828,0.00031337023,0.000017527245],"category_scores_gemma":[0.00049863366,0.00041782888,0.00017162203,0.0008840032,0.0001649055,0.0018122318,0.0006960434,0.0008685595,0.000025239291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043007426,0.000014367227,0.00007946042,0.000027495225,0.000007602035,0.0000020113976,0.0009174494,0.29263994,0.0002651239,0.015536849,0.0000035174878,0.69050187],"study_design_scores_gemma":[0.00033750053,0.00014200155,0.0008691851,0.00010999961,0.000011393384,0.000024066429,8.282012e-7,0.96714413,0.0007889176,0.02766297,0.0024639072,0.00044507894],"about_ca_topic_score_codex":0.0001641099,"about_ca_topic_score_gemma":0.00005004626,"teacher_disagreement_score":0.6900568,"about_ca_system_score_codex":0.00022058803,"about_ca_system_score_gemma":0.00038729972,"threshold_uncertainty_score":0.9998273},"labels":[],"label_agreement":null},{"id":"W4213017138","doi":"10.1145/3488560.3498507","title":"A GNN-based Multi-task Learning Framework for Personalized Video Search","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Multimodal Machine Learning Applications","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":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Task (project management); Human–computer interaction; Multimedia; Systems engineering; Engineering","score_opus":0.12830707427337426,"score_gpt":0.3845772540133766,"score_spread":0.2562701797400023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213017138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7793296,0.00009053453,0.17471012,0.04107394,0.00041103878,0.001661834,0.0009624957,0.00025896062,0.001501456],"genre_scores_gemma":[0.809578,0.0000112791295,0.18956938,0.00027530783,0.00005165685,0.0001813725,0.00008497149,0.000015594165,0.0002324462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975807,0.00006476993,0.00028530654,0.00075986795,0.00096381904,0.00034553785],"domain_scores_gemma":[0.99793583,0.000711427,0.00019001601,0.00058506493,0.00045867029,0.00011898358],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0015282499,0.00017383254,0.00018873093,0.00023281958,0.0007355177,0.0003613566,0.0059990417,0.0000471009,0.000117708136],"category_scores_gemma":[0.0026292887,0.00015064082,0.000070130416,0.00036663606,0.00015244818,0.00037404118,0.004582709,0.00079477613,0.000004550345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058194867,0.0005249693,0.08413579,0.0002080808,0.00019108577,0.000001574795,0.005449163,0.0025047325,0.02044212,0.83732694,0.0012267032,0.047406897],"study_design_scores_gemma":[0.00089953316,0.00020191116,0.0046717497,0.000099235964,0.000009134086,0.000005653245,0.0011261894,0.9872219,0.0005350826,0.0014125528,0.0036447127,0.00017235283],"about_ca_topic_score_codex":0.00010792217,"about_ca_topic_score_gemma":0.0000024054486,"teacher_disagreement_score":0.98471713,"about_ca_system_score_codex":0.00007616987,"about_ca_system_score_gemma":0.00027132907,"threshold_uncertainty_score":0.999379},"labels":[],"label_agreement":null},{"id":"W4221149779","doi":"10.1109/icra46639.2022.9812195","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Multimodal Machine Learning Applications","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; Robot; Artificial intelligence; Task (project management); Generalization; Representation (politics); Visual servoing; Computer vision; Task analysis; Categorical variable; Machine learning; Mathematics; Engineering","score_opus":0.05002559006014977,"score_gpt":0.30352058687195377,"score_spread":0.253494996811804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221149779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06805657,0.000032046155,0.91868484,0.004012386,0.00031349267,0.00030249282,0.000023489703,0.00032737563,0.008247315],"genre_scores_gemma":[0.94890636,0.000021370157,0.04910109,0.0002473925,0.000080017075,0.00017804847,0.00078565045,0.000014359074,0.00066569744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978167,0.00025548277,0.00039161206,0.0006058421,0.00075022376,0.0001801791],"domain_scores_gemma":[0.9989483,0.00011340153,0.00035488556,0.00033153326,0.00017546295,0.000076439064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037725244,0.00016834706,0.00016144129,0.0004729494,0.0008334273,0.0004972732,0.00068416685,0.000049422844,0.00035585224],"category_scores_gemma":[0.00010143128,0.0001922757,0.000055677236,0.00066090986,0.000034682962,0.00040516362,0.00040313767,0.00044686365,0.000026828808],"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":[0.000004687902,0.00013822567,0.0053993324,0.0000041637372,0.000035979774,0.000002025428,0.0003608499,0.6014196,0.0056494577,0.37880683,0.0003254729,0.007853351],"study_design_scores_gemma":[0.0003635932,0.000083007166,0.031508908,0.000006986894,0.000009622063,0.000008543073,0.00017173903,0.9586618,0.00012833966,0.008459392,0.0004049151,0.00019314534],"about_ca_topic_score_codex":0.0005644976,"about_ca_topic_score_gemma":0.0000063934854,"teacher_disagreement_score":0.8808498,"about_ca_system_score_codex":0.00014904987,"about_ca_system_score_gemma":0.0000676745,"threshold_uncertainty_score":0.78407747},"labels":[],"label_agreement":null},{"id":"W4221155360","doi":"10.1109/cvpr52688.2022.00503","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Embedding; Knowledge extraction; Construct (python library); Domain knowledge; Question answering; Pipeline (software); Relation (database); Commonsense knowledge; Knowledge base; Artificial intelligence; Domain (mathematical analysis); Bridge (graph theory); Natural language processing; Data mining","score_opus":0.06767699411909972,"score_gpt":0.37926226941430574,"score_spread":0.311585275295206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221155360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32850057,0.000038879985,0.6688764,0.0007310643,0.0007533727,0.00066328974,0.00004130839,0.00025576504,0.00013934361],"genre_scores_gemma":[0.97984177,0.000020879956,0.018544096,0.0004319355,0.00026112294,0.00050715875,0.00029032823,0.00003430702,0.00006838775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734354,0.0005316333,0.0004614732,0.0010120594,0.0003157188,0.000335585],"domain_scores_gemma":[0.99819994,0.000692323,0.00027948388,0.00034525731,0.00029076164,0.00019222042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075057335,0.0003494691,0.00031946448,0.00045105786,0.0009597972,0.0004408958,0.00034075594,0.00012250888,0.00013658196],"category_scores_gemma":[0.0000359179,0.00037679923,0.000097918084,0.0003551563,0.00005932809,0.0005189896,0.00026857023,0.000544189,0.00006086493],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008627146,0.0005197531,0.0008585485,0.00009068382,0.000017357901,0.0000034798625,0.00074078864,0.0018611331,0.0038728565,0.0005009706,0.00029892163,0.99114925],"study_design_scores_gemma":[0.0016673603,0.0009836555,0.018625446,0.00011844054,0.000019006826,0.000031829113,0.00004761305,0.9752714,0.00075626565,0.00074863865,0.0012864396,0.0004439069],"about_ca_topic_score_codex":0.000108899825,"about_ca_topic_score_gemma":0.00004015421,"teacher_disagreement_score":0.9907053,"about_ca_system_score_codex":0.00012127412,"about_ca_system_score_gemma":0.000101751626,"threshold_uncertainty_score":0.9998684},"labels":[],"label_agreement":null},{"id":"W4225683910","doi":"10.24963/ijcai.2022/762","title":"A Survey of Vision-Language Pre-Trained Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":136,"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; Transformer; Pace; Artificial intelligence; Pointer (user interface); Deep learning; Mainstream; Focus (optics); Natural language processing; Human–computer interaction; Engineering","score_opus":0.06806887872685286,"score_gpt":0.3226548770219884,"score_spread":0.25458599829513556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225683910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7610486,0.00005234881,0.19496465,0.018774766,0.001392664,0.0013833297,0.0002346389,0.00028959685,0.021859374],"genre_scores_gemma":[0.9951455,0.000009845175,0.004325453,0.00017071307,0.00003273653,0.0001095392,0.0000074943237,0.000016291491,0.00018242623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709976,0.00006994529,0.0008302303,0.00055769697,0.001189873,0.00025247596],"domain_scores_gemma":[0.9973458,0.00026252287,0.00083647395,0.00044174658,0.0010371188,0.00007636206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014386115,0.00021982183,0.0002928567,0.00027971936,0.0003333049,0.00014088712,0.0037928177,0.000051848063,0.00023731089],"category_scores_gemma":[0.00074326026,0.00018491739,0.00015719773,0.00083052035,0.00020651137,0.00038778796,0.0015281603,0.00053437124,0.000020086469],"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":[0.00011384955,0.00049376424,0.0008779544,0.000026681793,0.000043592823,5.121116e-7,0.004407074,0.018243227,0.018551586,0.94071263,0.0001370585,0.016392067],"study_design_scores_gemma":[0.00005685314,0.00021221889,0.018015115,0.00009044784,0.0000069236994,0.0000075748026,0.0004266881,0.8683635,0.027150746,0.085420564,0.000042811138,0.0002065563],"about_ca_topic_score_codex":0.0019883513,"about_ca_topic_score_gemma":0.0000805459,"teacher_disagreement_score":0.8552921,"about_ca_system_score_codex":0.00012523124,"about_ca_system_score_gemma":0.00013665881,"threshold_uncertainty_score":0.7540712},"labels":[],"label_agreement":null},{"id":"W4235356794","doi":"10.1109/cvpr.2019.00004","title":"Table of Contents","year":2019,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"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":"Microsoft Research Asia; Xidian University; Institute of Automation, Chinese Academy of Sciences; Council for Research in the Social Sciences, Columbia University; Beijing Institute of Technology; Chinese University of Hong Kong; College of Engineering, Michigan State University; Tongji University; Chinese Academy of Sciences; Connaught Fund; Pohang University of Science and Technology; Harbin Institute of Technology; Agency for Science, Technology and Research; Commonwealth Scientific and Industrial Research Organisation; De La Salle University; Eidgenössische Technische Hochschule Zürich; Tencent; National Laboratory of Pattern Recognition; Johns Hopkins University; Northwestern University; Microsoft Research","keywords":"Table (database); Computer science; Table of contents; Database; World Wide Web","score_opus":0.011581806221787398,"score_gpt":0.25684472083258575,"score_spread":0.24526291461079835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235356794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42396462,0.0000110665105,0.4569023,0.0009262641,0.00008422202,0.0001466359,5.1892204e-7,0.000120795914,0.1178436],"genre_scores_gemma":[0.9489112,3.0792575e-7,0.048104785,0.00010768797,0.0000028474774,0.0000032315265,3.6628447e-7,0.0000015624289,0.0028680337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996886,0.000008352598,0.000066805434,0.00010098119,0.000074371645,0.000060881302],"domain_scores_gemma":[0.99954915,0.00003059445,0.000030444928,0.00033674852,0.00003463444,0.000018424693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000049427133,0.000025781299,0.000050160976,0.000020815893,0.000009978053,0.000010652115,0.0003585152,0.000011052046,0.00013413376],"category_scores_gemma":[0.000010464859,0.000021397344,0.000012702811,0.00012832232,0.000005635515,0.00008755502,0.0000864403,0.000032739394,0.0005677765],"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":[9.725643e-7,0.0000550497,0.17564648,0.000009675742,0.000006783199,1.284318e-7,0.000107297295,0.00065966556,0.031639196,0.78152525,0.0006487912,0.009700708],"study_design_scores_gemma":[0.00045027913,0.000058438876,0.37208897,0.000008449329,0.0000013980568,0.0000022348322,0.0000120933655,0.5977815,0.0151787,0.0028547286,0.011443401,0.00011981566],"about_ca_topic_score_codex":0.00043707647,"about_ca_topic_score_gemma":0.0000015387533,"teacher_disagreement_score":0.77867055,"about_ca_system_score_codex":0.0000027080139,"about_ca_system_score_gemma":0.000007931376,"threshold_uncertainty_score":0.72978073},"labels":[],"label_agreement":null},{"id":"W4249356701","doi":"10.1115/detc2018-85670","title":"Visual Similarity to Aid Alternative-Use Concept Generation for Retired Wind-Turbine Blades","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reuse; Similarity (geometry); Turbine; Computer science; Scale (ratio); Turbine blade; Work (physics); Wind power; Artificial intelligence; Industrial engineering; Human–computer interaction; Engineering; Mechanical engineering; Image (mathematics)","score_opus":0.05234988231998867,"score_gpt":0.35103724004132,"score_spread":0.2986873577213313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249356701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27109528,0.0000029431094,0.723305,0.00441235,0.0001788506,0.00046187782,0.000007279771,0.00021505567,0.00032139607],"genre_scores_gemma":[0.7246997,3.9042376e-7,0.27238962,0.001664507,0.0005224055,0.00005257595,0.000018603778,0.000009939131,0.000642272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987396,0.000067357156,0.00021193406,0.00053529727,0.00020365228,0.00024214566],"domain_scores_gemma":[0.9988297,0.00015416642,0.0000762876,0.0004969865,0.00030932177,0.00013348846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021456207,0.0001388777,0.00013215329,0.00008206219,0.00027057825,0.00025866684,0.0005769169,0.00005735858,0.0000375839],"category_scores_gemma":[0.00029624198,0.00012644708,0.00004884127,0.0002846565,0.000067912275,0.00041840732,0.00020289554,0.00009294174,0.00008636525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099278324,0.0006255,0.006907742,0.000020806996,0.00012496945,0.000003060873,0.008702037,0.0128470175,0.31988695,0.48769394,0.048073962,0.115014724],"study_design_scores_gemma":[0.0004212246,0.00033556027,0.0071867765,0.000004437643,0.000005000163,0.0000015292968,0.0000066288217,0.91682136,0.0608402,0.00075305544,0.013430435,0.00019379116],"about_ca_topic_score_codex":0.00055945007,"about_ca_topic_score_gemma":0.00011620773,"teacher_disagreement_score":0.90397435,"about_ca_system_score_codex":0.000049621623,"about_ca_system_score_gemma":0.000039417788,"threshold_uncertainty_score":0.5156362},"labels":[],"label_agreement":null},{"id":"W4280596375","doi":"10.1111/cgf.14573","title":"Chart Question Answering: State of the Art and Future Directions","year":2022,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Multimodal Machine Learning Applications","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":"York University","funders":"","keywords":"Question answering; Computer science; Bar chart; Chart; Pie chart; Information retrieval; Task (project management); Domain (mathematical analysis); Data science; Artificial intelligence","score_opus":0.00627797374679749,"score_gpt":0.2314319068587537,"score_spread":0.22515393311195622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280596375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17641027,0.00042945013,0.7827832,0.036972374,0.00211848,0.00053655397,0.000026366606,0.0003901015,0.00033318598],"genre_scores_gemma":[0.98498017,0.00006940384,0.013876675,0.00078804273,0.00009694909,0.00007901546,0.000006402495,0.000012428394,0.0000909044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906296,0.0001267976,0.00015960817,0.0002661348,0.00022160789,0.00016289896],"domain_scores_gemma":[0.9991931,0.00004821681,0.00011332766,0.0005494424,0.00005009369,0.00004587175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023637187,0.00009422237,0.000097707365,0.00012296201,0.00058657944,0.00005047565,0.00062025146,0.000018296048,0.00000391842],"category_scores_gemma":[0.0000038035207,0.00008079866,0.00006559437,0.0007269415,0.00006271425,0.00011723089,0.00085468695,0.0003231881,0.0000021562585],"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":[0.0000044095787,0.00014520079,0.032739837,0.000020385314,0.00003692805,0.0000013184716,0.0014739188,0.0029302977,0.00021595156,0.7854877,0.003298659,0.17364538],"study_design_scores_gemma":[0.00015597531,0.00008248611,0.2224642,0.00000663292,0.000005266947,0.000035981175,0.000012979383,0.44785717,0.00006512822,0.013722002,0.3154586,0.0001335634],"about_ca_topic_score_codex":0.00005532945,"about_ca_topic_score_gemma":0.000017907378,"teacher_disagreement_score":0.8085699,"about_ca_system_score_codex":0.000017567027,"about_ca_system_score_gemma":0.000026177648,"threshold_uncertainty_score":0.4511554},"labels":[],"label_agreement":null},{"id":"W4281760878","doi":"10.3390/electronics11111785","title":"Deep Learning-Based Context-Aware Video Content Analysis on IoT Devices","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Multimodal Machine Learning Applications","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":"Thunder Bay Regional Research Institute; Lakehead University","funders":"","keywords":"Computer science; Closed captioning; Artificial intelligence; Deep learning; Inference; Transformer; Sentence; Language model; Hyperparameter; Machine learning; Context (archaeology); Natural language processing; Image (mathematics)","score_opus":0.017826067059981115,"score_gpt":0.2683236016153511,"score_spread":0.25049753455537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281760878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26550362,0.0012696919,0.7279394,0.0039742375,0.000078970435,0.0003197116,0.000003968361,0.00065831677,0.00025204828],"genre_scores_gemma":[0.99547976,0.0000052923738,0.0019569336,0.0020614704,0.000025711337,0.0002118278,0.00006077463,0.00001947582,0.00017876897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773633,0.00044246067,0.00024408138,0.0006265091,0.0004965388,0.00045406306],"domain_scores_gemma":[0.99852365,0.00026441034,0.00020110546,0.0008002834,0.00009157663,0.00011897278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005160265,0.00018103178,0.00024347594,0.00030348857,0.0007835387,0.00012644417,0.0012643818,0.000039182047,0.00018395274],"category_scores_gemma":[0.000062945954,0.00018946361,0.00016712552,0.0014684887,0.000024761577,0.00008648099,0.00018678946,0.0008831271,0.00006353918],"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":[0.000020755526,0.00021983191,0.0100672,0.000003221001,0.00015238357,0.0000040631608,0.00030013907,0.9165818,0.00017395502,0.019776814,0.000034991084,0.052664835],"study_design_scores_gemma":[0.0003319059,0.0006370657,0.017142748,0.0000013733189,0.00006837525,0.0000022824327,0.00006588674,0.943246,0.00023226252,0.00017523995,0.037882008,0.00021481817],"about_ca_topic_score_codex":0.00027346108,"about_ca_topic_score_gemma":0.0007352905,"teacher_disagreement_score":0.7299761,"about_ca_system_score_codex":0.00034929728,"about_ca_system_score_gemma":0.00016583681,"threshold_uncertainty_score":0.7726102},"labels":[],"label_agreement":null},{"id":"W4283805152","doi":"10.1609/aaai.v36i2.20123","title":"Improving Zero-Shot Phrase Grounding via Reasoning on External Knowledge and Spatial Relations","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Phrase; Computer science; Noun phrase; Artificial intelligence; Ground; Visual reasoning; Natural language processing; Modal; Noun; Engineering","score_opus":0.04921381018470201,"score_gpt":0.30577594182359497,"score_spread":0.25656213163889297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283805152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48768568,0.000038772603,0.50117195,0.002037569,0.00045049906,0.00055846537,0.0000070155625,0.00017938382,0.007870695],"genre_scores_gemma":[0.9925399,0.0000039242373,0.0069136806,0.00010615301,0.000071024246,0.000113473594,7.721232e-7,0.000017585597,0.00023348775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980992,0.000053302585,0.0004471016,0.00061611563,0.00046940686,0.00031486846],"domain_scores_gemma":[0.9987004,0.0001833568,0.00045307277,0.0003326148,0.00022583258,0.00010474742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074691145,0.00021414971,0.00019936716,0.0002005888,0.001103275,0.0002610757,0.0015006041,0.00004920814,0.00009162783],"category_scores_gemma":[0.0004352316,0.00019196377,0.000080584636,0.0006160505,0.00015220148,0.0002952781,0.0009919889,0.0007432819,0.00005007889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003891971,0.00016021861,0.0015677762,0.000017666725,0.0000072360504,4.4518853e-7,0.0019777587,0.0005403792,0.053954784,0.7174312,0.000019234096,0.22428443],"study_design_scores_gemma":[0.000054887805,0.0002920445,0.004257427,0.00012224946,0.000014046584,0.000019332294,0.00025037155,0.8827375,0.0340874,0.07776742,0.00011540074,0.00028188698],"about_ca_topic_score_codex":0.00081309216,"about_ca_topic_score_gemma":0.000018712448,"teacher_disagreement_score":0.88219714,"about_ca_system_score_codex":0.00013180941,"about_ca_system_score_gemma":0.00008996032,"threshold_uncertainty_score":0.8485611},"labels":[],"label_agreement":null},{"id":"W4287891193","doi":"10.18653/v1/2022.wordplay-1.4","title":"A Sequence Modelling Approach to Question Answering in Text-Based Games","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Institut National de la Recherche Scientifique","funders":"","keywords":"Question answering; Computer science; Transformer; Reinforcement learning; Artificial intelligence; Machine learning; Benchmark (surveying); Language model; Task (project management); Natural language processing","score_opus":0.03687691377713465,"score_gpt":0.2905471630438144,"score_spread":0.25367024926667975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287891193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07208377,0.000008842902,0.92225975,0.0014748956,0.000026549122,0.00022942391,9.4983557e-7,0.00026457204,0.0036512301],"genre_scores_gemma":[0.6163695,1.497065e-7,0.38296792,0.00035309247,0.0000057415727,0.00024547853,0.0000026262155,0.0000050563413,0.00005046288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988994,0.000109178785,0.00015262509,0.0004127008,0.00023261378,0.00019350978],"domain_scores_gemma":[0.9994068,0.00005654996,0.000034127843,0.00042040116,0.00002037775,0.00006175202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045984163,0.00008333355,0.00008409071,0.00020418591,0.00015463654,0.00006795308,0.0006945529,0.000015361822,0.000013140803],"category_scores_gemma":[0.00001950981,0.00009067946,0.000022658927,0.00084056973,0.000008925999,0.00013691022,0.00025537476,0.00023597239,0.00001824919],"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":[0.0000022041881,0.00005748651,0.00096138363,0.000003892199,5.8877015e-7,7.914561e-7,0.00038243493,0.9353591,0.0006274399,0.056297578,0.000009858541,0.006297248],"study_design_scores_gemma":[0.00009792855,0.000029797813,0.0014660473,0.0000042133174,5.227496e-7,0.000003490025,0.000030342335,0.99681306,0.00011088407,0.00081509264,0.0005133383,0.00011528277],"about_ca_topic_score_codex":0.00243915,"about_ca_topic_score_gemma":0.000010749454,"teacher_disagreement_score":0.5442857,"about_ca_system_score_codex":0.00014565958,"about_ca_system_score_gemma":0.00005953374,"threshold_uncertainty_score":0.36978012},"labels":[],"label_agreement":null},{"id":"W4292409471","doi":"10.3390/sym14081715","title":"Utilizing Language Models to Expand Vision-Based Commonsense Knowledge Graphs","year":2022,"lang":"en","type":"article","venue":"Symmetry","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Commonsense knowledge; Computer science; Commonsense reasoning; Language model; Artificial intelligence; Transformer; Embedding; Natural language processing; Question answering; Knowledge base; Natural language understanding; Knowledge graph; Natural language","score_opus":0.02364263878367856,"score_gpt":0.31271794585807844,"score_spread":0.2890753070743999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292409471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64299583,0.000582698,0.3401005,0.0028250942,0.00031984248,0.0004621965,0.000027253762,0.0007143441,0.011972266],"genre_scores_gemma":[0.9609546,4.801765e-7,0.037483912,0.0012012628,0.000021225142,0.00014067086,0.0000100949155,0.000019913854,0.00016781653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998515,0.00023911423,0.00019286932,0.0004643365,0.00030034588,0.00028833255],"domain_scores_gemma":[0.998403,0.00034770876,0.000061280174,0.0009827723,0.00004159921,0.00016361088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045517934,0.00014113534,0.00015221225,0.0003594504,0.0005260396,0.00008988412,0.0010418107,0.000028883807,0.000045409837],"category_scores_gemma":[0.000043806653,0.00015075134,0.00008445783,0.001347321,0.000023417177,0.00011390244,0.00074283,0.000348493,0.0001172739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043590662,0.0010625747,0.0047177975,0.000059843525,0.000043302316,0.00006499097,0.015632026,0.13240556,0.011571436,0.6473216,0.009813334,0.17726395],"study_design_scores_gemma":[0.0003426003,0.00009953524,0.0038791317,0.000011067192,0.0000048375937,0.0000093423105,0.0004600201,0.98737097,0.0005464905,0.004613384,0.002410915,0.00025169243],"about_ca_topic_score_codex":0.0006071377,"about_ca_topic_score_gemma":0.000026754513,"teacher_disagreement_score":0.8549654,"about_ca_system_score_codex":0.00007927427,"about_ca_system_score_gemma":0.00007957214,"threshold_uncertainty_score":0.6147461},"labels":[],"label_agreement":null},{"id":"W4292937774","doi":"10.17760/d20429166","title":"Improving instruction generation for vision-language navigation by reward designing","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Multimodal Machine Learning Applications","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":"Science North","funders":"","keywords":"Computer science; Generator (circuit theory); Function (biology); Artificial intelligence; Language model; Human–computer interaction","score_opus":0.009269301080167717,"score_gpt":0.30295176087001363,"score_spread":0.2936824597898459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292937774","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":[0.13151471,0.00025622948,0.8654847,0.00016715075,0.00087283214,0.0007012199,0.000011797905,0.000360761,0.0006305795],"genre_scores_gemma":[0.32942864,0.000012013731,0.6470047,0.00011466242,0.00047887553,0.00069829985,0.015560251,0.00007209939,0.006630449],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796474,0.00009568581,0.00045468638,0.00089433184,0.00033712253,0.00025342495],"domain_scores_gemma":[0.9983781,0.000113639544,0.00044767035,0.00063037704,0.00034904137,0.00008118857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034973674,0.0002806085,0.00024406282,0.00015901888,0.00043319553,0.0005512889,0.0004947815,0.00031765527,0.00001924639],"category_scores_gemma":[0.00018565524,0.00030403928,0.00012432107,0.00039431403,0.000009660532,0.0005779881,0.00005153027,0.00033854268,0.000017942544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000743564,0.00004233649,0.000015290212,0.00015659099,0.000022939483,9.947513e-7,0.0017915787,0.00063633645,0.6016032,0.0029244032,0.002333577,0.3904653],"study_design_scores_gemma":[0.0004826096,0.00007988446,0.00020481329,0.000102359016,0.00003516869,0.000008464828,0.00049604545,0.86901253,0.12819566,0.0002591333,0.00064290315,0.0004804333],"about_ca_topic_score_codex":0.00090092974,"about_ca_topic_score_gemma":0.000083268365,"teacher_disagreement_score":0.8683762,"about_ca_system_score_codex":0.0001432153,"about_ca_system_score_gemma":0.0002122336,"threshold_uncertainty_score":0.9999412},"labels":[],"label_agreement":null},{"id":"W4293868279","doi":"10.1109/crv55824.2022.00038","title":"3DVQA: Visual Question Answering for 3D Environments","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Question answering; Computer science; Task (project management); Artificial intelligence; Domain (mathematical analysis); Modality (human–computer interaction); Relation (database); Point (geometry); Baseline (sea); Natural language processing; Information retrieval; Computer vision; Data mining","score_opus":0.009262272345025406,"score_gpt":0.28865129407987955,"score_spread":0.27938902173485414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293868279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026522227,0.000009323361,0.9710537,0.0011217134,0.00009773209,0.00022090902,0.0000017909045,0.00015664857,0.0008159348],"genre_scores_gemma":[0.75043166,5.143253e-7,0.24812149,0.00023333215,0.000023866578,0.00032997856,0.0000082108945,0.0000061862343,0.00084479526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993334,0.00004225468,0.00009448679,0.00024480865,0.00015390421,0.00013117706],"domain_scores_gemma":[0.99963576,0.00005678752,0.000038537273,0.00022922958,0.000004481048,0.00003518818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021638128,0.00005677047,0.00005035934,0.00004373768,0.00033034247,0.000034544722,0.0003664819,0.000011141746,0.000074845855],"category_scores_gemma":[0.000015388954,0.00006128337,0.000025696925,0.000109236535,0.000008441841,0.00011609367,0.0003171229,0.00009329182,0.000036994865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017059856,0.00057887525,0.0116726635,0.000017429817,0.000031917825,0.0000026870491,0.0010232122,0.10375852,0.035248093,0.31579277,0.0012804563,0.53057635],"study_design_scores_gemma":[0.00017938073,0.00008645045,0.017019784,6.714658e-7,0.0000019240938,0.0000037035506,0.000011882,0.92728645,0.0005099086,0.0007976117,0.054008335,0.000093919916],"about_ca_topic_score_codex":0.00011290927,"about_ca_topic_score_gemma":0.0000015357864,"teacher_disagreement_score":0.82352793,"about_ca_system_score_codex":0.000070588525,"about_ca_system_score_gemma":0.0000114791665,"threshold_uncertainty_score":0.25407606},"labels":[],"label_agreement":null},{"id":"W4293868331","doi":"10.1109/crv55824.2022.00015","title":"Semi-supervised Grounding Alignment for Multi-modal Feature Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Phrase; Margin (machine learning); Leverage (statistics); Machine learning; Ground; Sentence; Feature (linguistics); Transformer; Modal; Classifier (UML); Feature learning; Natural language processing; Question answering; Supervised learning; Feature extraction; Pattern recognition (psychology); Artificial neural network; Engineering","score_opus":0.031631322508959094,"score_gpt":0.30216253552996014,"score_spread":0.270531213021001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293868331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030668,0.000043894364,0.9622232,0.004592615,0.00022158869,0.00056031824,0.0000044787694,0.0005764044,0.0011095268],"genre_scores_gemma":[0.6748187,0.0000012434458,0.31997284,0.00048952893,0.000048885995,0.0006109164,0.000022849488,0.000017437676,0.0040175896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850935,0.00013349409,0.00016136513,0.0005243244,0.00032713785,0.000344306],"domain_scores_gemma":[0.9991618,0.00017422398,0.0000830682,0.00044399188,0.00004145767,0.000095461764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038486344,0.00014854161,0.00014127253,0.00010426935,0.0011417957,0.00014851347,0.00097054505,0.000036171547,0.000108071305],"category_scores_gemma":[0.000062935906,0.00015041936,0.00010161585,0.00036328676,0.000014268245,0.00018296462,0.00069604325,0.0004374604,0.000027184042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004634715,0.0008358521,0.027812049,0.00008928313,0.00014370464,0.00001383193,0.00883314,0.23306477,0.038538318,0.5145453,0.009610729,0.16646664],"study_design_scores_gemma":[0.00068856595,0.000098711396,0.006185419,0.0000025318054,0.000005471731,0.0000134759675,0.00025109047,0.94639045,0.00021696613,0.00034351624,0.04559798,0.00020579352],"about_ca_topic_score_codex":0.00018260804,"about_ca_topic_score_gemma":0.000004036093,"teacher_disagreement_score":0.7133257,"about_ca_system_score_codex":0.00018105833,"about_ca_system_score_gemma":0.0000452288,"threshold_uncertainty_score":0.87818843},"labels":[],"label_agreement":null},{"id":"W4297688052","doi":"10.1093/jcde/qwac084","title":"TransNav: spatial sequential transformer network for visual navigation","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Design and Engineering","topic":"Multimodal Machine Learning Applications","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":"National Key Research and Development Program of China; Ministry of Natural Resources","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Inference; Transformer; Machine learning; Engineering","score_opus":0.012894214952839501,"score_gpt":0.2588550867853863,"score_spread":0.24596087183254683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297688052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03393207,0.00008362642,0.96494496,0.00059586245,0.00025113704,0.00015803454,0.0000022772883,0.000028209473,0.0000038491257],"genre_scores_gemma":[0.6491894,0.0000011892714,0.35061947,0.000036019035,0.00012291221,0.000016745777,0.000005762926,0.000006515208,0.0000019657016],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991956,0.000048027196,0.00027781443,0.00009901646,0.0002545924,0.00012496985],"domain_scores_gemma":[0.99942625,0.00028172732,0.000109729626,0.000037577916,0.00008338376,0.00006135061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054579164,0.00007811671,0.000118608405,0.00009137658,0.00018939299,0.00005592181,0.00018033835,0.000017918279,0.0000059195645],"category_scores_gemma":[0.000009917725,0.000082302235,0.000068568435,0.00016035612,0.0000075249645,0.00018697786,0.00001484756,0.00019150726,3.134658e-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":[0.00002497507,0.000021088888,0.000024056844,0.000011751666,0.000024754083,0.0000022981799,0.00020900292,0.9763049,0.0015650028,0.008526666,0.00005710988,0.0132284],"study_design_scores_gemma":[0.00054656307,0.0002386568,0.0028107732,0.000009453625,0.000012022448,0.00015139401,0.000003943779,0.98947406,0.000107703345,0.005700796,0.0008582113,0.00008641226],"about_ca_topic_score_codex":0.00000692838,"about_ca_topic_score_gemma":6.524047e-8,"teacher_disagreement_score":0.6152574,"about_ca_system_score_codex":0.00004258366,"about_ca_system_score_gemma":0.000070507565,"threshold_uncertainty_score":0.33561876},"labels":[],"label_agreement":null},{"id":"W4306882122","doi":"10.48550/arxiv.2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Task (project management); Salient; Imitation; Robot; Representation (politics); Unsupervised learning; Machine learning; Deep learning; Human–computer interaction","score_opus":0.0409648179073554,"score_gpt":0.21768011579033145,"score_spread":0.17671529788297605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306882122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.576324,0.000008831929,0.42298767,0.00006382254,0.00005985665,0.00012550638,0.000006252752,0.00013437521,0.00028969953],"genre_scores_gemma":[0.9935667,0.000009610465,0.0056266794,0.000020073297,0.00006361244,0.0000021108945,0.00040885294,0.000021278654,0.00028107007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810904,0.00029894893,0.00024265751,0.0010040601,0.00014678542,0.00019850883],"domain_scores_gemma":[0.9980652,0.0002627445,0.00049865915,0.0008921139,0.00018782762,0.00009348269],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014806923,0.000247195,0.0003336097,0.00013850805,0.00020742872,0.00011933076,0.0010503193,0.00019036983,0.000020545449],"category_scores_gemma":[0.00007514604,0.00031438726,0.00019673865,0.00040108542,0.000057471283,0.00035311154,0.0011049394,0.0008321207,0.000026917021],"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":[0.00000490889,0.00034263392,0.024446668,0.000046788584,0.000103462575,0.000016695298,0.0028743192,0.908547,0.013865808,0.04759615,0.00004909402,0.002106499],"study_design_scores_gemma":[0.00030979328,0.00003783984,0.050116695,0.00008644362,0.00006336636,4.2163626e-7,0.00012056086,0.92363167,0.0017592835,0.023503125,0.000042524043,0.00032826798],"about_ca_topic_score_codex":0.0030043954,"about_ca_topic_score_gemma":0.00003527508,"teacher_disagreement_score":0.417361,"about_ca_system_score_codex":0.00014256274,"about_ca_system_score_gemma":0.00006872289,"threshold_uncertainty_score":0.9999308},"labels":[],"label_agreement":null},{"id":"W4307475428","doi":"10.1145/3526113.3545621","title":"Opal: Multimodal Image Generation for News Illustration","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"USable; Computer science; Pipeline (software); Image (mathematics); Tone (literature); Multimedia; Artificial intelligence; Human–computer interaction; Linguistics; Programming language","score_opus":0.03235914812416576,"score_gpt":0.29676236432622527,"score_spread":0.26440321620205953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307475428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028052198,0.00000543365,0.9637879,0.004855834,0.00019117676,0.00053388556,0.000007937034,0.00030317754,0.002262459],"genre_scores_gemma":[0.6091956,3.5882618e-7,0.38896695,0.00046900538,0.000106027386,0.0005703252,0.00006771179,0.0000075275734,0.000616512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999063,0.00006963436,0.00017034677,0.00035016658,0.00018892721,0.00015789023],"domain_scores_gemma":[0.99934155,0.00006145578,0.00007198153,0.00041447592,0.00006327958,0.000047232803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024550597,0.00008252144,0.000070411515,0.00007097811,0.00054654997,0.00013387656,0.0004981143,0.000018937693,0.00016617162],"category_scores_gemma":[0.00004315937,0.0000859488,0.000050728293,0.0002257438,0.000012097762,0.00029708017,0.00019316819,0.00012066135,0.000032762986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001035612,0.00024369621,0.0005415227,0.000009545901,0.000014991104,0.0000012865128,0.0009935611,0.080211826,0.24368398,0.41462383,0.016165465,0.24349995],"study_design_scores_gemma":[0.00031321507,0.00006950128,0.0016601764,1.668971e-7,0.0000022993854,0.0000050801377,0.000028001827,0.97970206,0.0012258649,0.000999782,0.015882159,0.00011169377],"about_ca_topic_score_codex":0.0006318132,"about_ca_topic_score_gemma":0.00004742044,"teacher_disagreement_score":0.89949024,"about_ca_system_score_codex":0.0000663836,"about_ca_system_score_gemma":0.000045871304,"threshold_uncertainty_score":0.4203676},"labels":[],"label_agreement":null},{"id":"W4308222681","doi":"10.1145/3536221.3556597","title":"A Framework for Video-Text Retrieval with Noisy Supervision","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Closed captioning; Artificial intelligence; Modal; Relevance (law); Context (archaeology); Task (project management); Natural language processing; Domain (mathematical analysis); Machine learning; Information retrieval; Image (mathematics)","score_opus":0.01734851815095571,"score_gpt":0.2900835527978527,"score_spread":0.27273503464689697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308222681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052465294,0.000020144289,0.9385199,0.0072987536,0.00008333672,0.0003895341,0.000004361926,0.0003080958,0.00091060816],"genre_scores_gemma":[0.554049,2.6732633e-7,0.44461256,0.0009776868,0.00002750496,0.00011611357,0.0000037556456,0.000009285147,0.00020379382],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888784,0.00005476085,0.00012719097,0.00040453093,0.0003170483,0.00020864047],"domain_scores_gemma":[0.9987421,0.00040034874,0.00005421576,0.0006759172,0.000057476456,0.00006992476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030155448,0.00009403291,0.000100356774,0.00006879255,0.0005009005,0.00009218143,0.0009011822,0.000022638977,0.00024717473],"category_scores_gemma":[0.000098161196,0.00007803131,0.00004458937,0.0006109869,0.000017729597,0.00013174501,0.00043033424,0.00028203672,0.000044433455],"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":[0.00007298307,0.00012887204,0.0022799924,0.000010433105,0.000013406996,0.0000028009865,0.0006993723,0.005745654,0.0005936053,0.9733261,0.0013076551,0.015819147],"study_design_scores_gemma":[0.0007701203,0.0008070837,0.010400649,0.0000112372745,0.00000946195,0.00004233186,0.00011818976,0.85901725,0.0006860195,0.057158932,0.070603654,0.00037506968],"about_ca_topic_score_codex":0.00013571222,"about_ca_topic_score_gemma":0.0000038142553,"teacher_disagreement_score":0.91616714,"about_ca_system_score_codex":0.00005184929,"about_ca_system_score_gemma":0.00006374994,"threshold_uncertainty_score":0.3852572},"labels":[],"label_agreement":null},{"id":"W4310921857","doi":"10.48550/arxiv.2212.03338","title":"Framework-agnostic Semantically-aware Global Reasoning for Segmentation","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Pixel; Representation (politics); Semantics (computer science); Object (grammar); Transformer; Natural language processing; Pattern recognition (psychology); Machine learning","score_opus":0.055302229931168075,"score_gpt":0.25294454173164577,"score_spread":0.1976423118004777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310921857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095302835,0.000022908693,0.9018183,0.0005034813,0.00043102168,0.00074777013,0.00007953599,0.00046267852,0.00063146965],"genre_scores_gemma":[0.90190023,0.000021828566,0.097490534,0.00017305235,0.0000719757,0.00002616501,0.00011716498,0.000019494264,0.00017956231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978462,0.00016852528,0.00021306745,0.001263905,0.00014015255,0.00036813435],"domain_scores_gemma":[0.99762684,0.0005256723,0.0002915595,0.0012490108,0.00014794123,0.00015896768],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026968002,0.00028530104,0.0002697202,0.00011959845,0.00045146438,0.00016915805,0.0019701682,0.00023014477,0.00009011586],"category_scores_gemma":[0.00027606543,0.00037274053,0.00021067198,0.000664396,0.00005740285,0.00020201832,0.002418846,0.00075389136,0.000051771676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013815556,0.0000745733,0.014512903,0.000065401684,0.000052471325,0.000028774733,0.00012539473,0.4756604,0.0000054416837,0.508255,0.000117891264,0.0010879292],"study_design_scores_gemma":[0.00027998805,0.000050556635,0.010524674,0.00007071052,0.000077588455,0.000003515482,0.000057141926,0.8581185,0.0000093768,0.13018547,0.00026316877,0.00035933882],"about_ca_topic_score_codex":0.0003976158,"about_ca_topic_score_gemma":0.000018335146,"teacher_disagreement_score":0.8065974,"about_ca_system_score_codex":0.00055130804,"about_ca_system_score_gemma":0.00021761411,"threshold_uncertainty_score":0.99987245},"labels":[],"label_agreement":null},{"id":"W4312261477","doi":"10.1109/cvpr52688.2022.00517","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":185,"is_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":"Principle of compositionality; Computer science; Set (abstract data type); Task (project management); Artificial intelligence; Natural language processing; Language model; Field (mathematics); State (computer science); Programming language","score_opus":0.042859049951476526,"score_gpt":0.31686812750494875,"score_spread":0.2740090775534722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312261477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2280766,0.000047468828,0.7679021,0.0019478196,0.00047274784,0.0007839287,0.00018536781,0.00023741674,0.00034659382],"genre_scores_gemma":[0.97343403,0.000026011137,0.023178808,0.002361622,0.00020283752,0.00032946203,0.00038954974,0.00002894611,0.000048719157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972237,0.00040389993,0.00046223254,0.001033601,0.0005248436,0.00035174686],"domain_scores_gemma":[0.9983299,0.00051133183,0.00025632256,0.0004847668,0.0002175214,0.00020019432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006912344,0.00033774227,0.00036783185,0.00026477707,0.0010281884,0.00058615935,0.00052606716,0.00007798632,0.00015310958],"category_scores_gemma":[0.000018295636,0.00033292006,0.00010215689,0.00025452673,0.00007934779,0.00038788762,0.0005616833,0.0005084338,0.00003028885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012125031,0.00059314485,0.00030295868,0.00018738522,0.00004934161,0.000025558391,0.0040286053,0.0029440266,0.0032096335,0.007885403,0.0010201518,0.97963256],"study_design_scores_gemma":[0.0011950467,0.00090892805,0.0027894154,0.00014064324,0.000018373974,0.00006951799,0.00007815531,0.9791534,0.00012146692,0.014439977,0.0006448157,0.00044028388],"about_ca_topic_score_codex":0.00015809447,"about_ca_topic_score_gemma":0.00001398406,"teacher_disagreement_score":0.97919226,"about_ca_system_score_codex":0.00007116452,"about_ca_system_score_gemma":0.000052477004,"threshold_uncertainty_score":0.99991226},"labels":[],"label_agreement":null},{"id":"W4312330522","doi":"10.1007/978-3-031-20044-1_16","title":"Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Pipeline (software); Cluster analysis; Image segmentation; Encoder; Embedding; Semantics (computer science); Object (grammar); Segmentation-based object categorization; Natural language processing; Pattern recognition (psychology); Scale-space segmentation; Computer vision","score_opus":0.013622829848246207,"score_gpt":0.30939730922828884,"score_spread":0.29577447938004264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312330522","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":[0.00065765594,0.00022095302,0.99436134,0.00094811904,0.00058939116,0.0007652923,0.0000037927484,0.00017916254,0.0022742858],"genre_scores_gemma":[0.49729967,0.000008883276,0.5014739,0.000813862,0.00013666801,0.000036842288,0.000009791543,0.00003439711,0.0001859805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996669,0.00007220263,0.0004947395,0.001561406,0.0007107958,0.0004918533],"domain_scores_gemma":[0.9976104,0.00080164085,0.0003861313,0.0009729954,0.00007941149,0.00014946033],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011883508,0.00040881918,0.00042709458,0.0008104994,0.0007824057,0.0013944623,0.0033441836,0.000092587856,0.000081270155],"category_scores_gemma":[0.000087905915,0.0004218706,0.000053669744,0.00069347775,0.00025471553,0.0009874256,0.0060868203,0.0009498888,0.000014195252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040229866,0.00002053155,0.00017295823,0.00004814543,0.000009481935,0.00004746192,0.0019896268,0.14577377,0.0016613292,0.0045049866,0.0000037523364,0.8457639],"study_design_scores_gemma":[0.00030975402,0.00008074886,0.00060421036,0.00021978677,0.000008052276,0.000091182636,8.822569e-7,0.9885008,0.00020615188,0.0093055405,0.00021721056,0.0004556964],"about_ca_topic_score_codex":0.0004186618,"about_ca_topic_score_gemma":0.00027942285,"teacher_disagreement_score":0.84530824,"about_ca_system_score_codex":0.00031705806,"about_ca_system_score_gemma":0.00016691972,"threshold_uncertainty_score":0.99982333},"labels":[],"label_agreement":null},{"id":"W4312372711","doi":"10.1109/cvpr52688.2022.00495","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":204,"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; University of Toronto","funders":"","keywords":"Computer science; Focus (optics); Information retrieval; Representation (politics); ENCODE; Pooling; Recall; Natural language processing; Artificial intelligence; Similarity (geometry); Text retrieval; Code (set theory); Function (biology); Image (mathematics); Linguistics","score_opus":0.03439024797878233,"score_gpt":0.32644121003245424,"score_spread":0.2920509620536719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312372711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4102937,0.00002858537,0.5840504,0.0030542435,0.0010195368,0.0007496413,0.00020724667,0.00033651982,0.00026012005],"genre_scores_gemma":[0.9874263,0.000024653997,0.007792443,0.0031564517,0.0003643972,0.00032369126,0.0004684079,0.000043900327,0.00039977024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99654275,0.00045581584,0.0005904011,0.0012202935,0.00070194283,0.0004888052],"domain_scores_gemma":[0.99787146,0.00048906833,0.0003623997,0.000753598,0.00028797478,0.00023552604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009117155,0.00038962113,0.0003962401,0.00035970824,0.001055059,0.00083268137,0.0009489253,0.00012274641,0.00077392167],"category_scores_gemma":[0.0000510013,0.0004004747,0.00020450952,0.00048173717,0.00009146509,0.00051541516,0.00061130244,0.0007279167,0.00025861236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021023967,0.000495816,0.0022335022,0.0000938766,0.000053344153,0.000025027739,0.0011319579,0.00083150185,0.0054607126,0.0011726569,0.005133914,0.98315746],"study_design_scores_gemma":[0.0026523795,0.0015709979,0.037148517,0.000113955684,0.000027789536,0.00010190958,0.000102081714,0.9497818,0.0008196452,0.0030965684,0.003813624,0.0007707585],"about_ca_topic_score_codex":0.00014470644,"about_ca_topic_score_gemma":0.000015572956,"teacher_disagreement_score":0.9823867,"about_ca_system_score_codex":0.00010085636,"about_ca_system_score_gemma":0.000080539736,"threshold_uncertainty_score":0.99984473},"labels":[],"label_agreement":null},{"id":"W4312458841","doi":"10.1109/cvpr52688.2022.00359","title":"Modular Action Concept Grounding in Semantic Video Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","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":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Action (physics); Task (project management); Generalization; Object (grammar); Modular design; Machine learning; Minimum bounding box; Exploit; Bounding overwatch; Natural language processing; Image (mathematics)","score_opus":0.05111951061090442,"score_gpt":0.3018798975331176,"score_spread":0.2507603869222132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312458841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4457001,0.00001646418,0.55085444,0.0014895365,0.001061418,0.0004132434,0.000041615567,0.00023827935,0.00018490637],"genre_scores_gemma":[0.9947589,0.00004581147,0.0030863148,0.0013774859,0.00021669427,0.00024138256,0.00018638327,0.000024261739,0.000062780215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969688,0.0006281324,0.0004915929,0.0009640662,0.00059385074,0.00035354044],"domain_scores_gemma":[0.9987961,0.00020591762,0.00024930545,0.000496368,0.00010399026,0.00014831773],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058939477,0.0002922155,0.0003096399,0.0005034421,0.0005888255,0.0003817811,0.00053912157,0.000090408896,0.0004758391],"category_scores_gemma":[0.000015318406,0.00031584903,0.00008311683,0.0005867538,0.000053085227,0.00059519673,0.00038023447,0.0008140736,0.00011886718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034441637,0.0003406825,0.0030728711,0.000036791644,0.00002366758,0.000030577175,0.0013823676,0.0041390127,0.0039029708,0.0007703364,0.000811522,0.98545474],"study_design_scores_gemma":[0.0011092837,0.0006151628,0.05792396,0.000110704335,0.00001044194,0.00007306029,0.000116968804,0.93601334,0.00028096745,0.0025313024,0.0008512975,0.00036351412],"about_ca_topic_score_codex":0.00033304148,"about_ca_topic_score_gemma":0.000031713666,"teacher_disagreement_score":0.98509127,"about_ca_system_score_codex":0.00016018131,"about_ca_system_score_gemma":0.00004882285,"threshold_uncertainty_score":0.99992937},"labels":[],"label_agreement":null},{"id":"W4312523916","doi":"10.1109/cvpr52688.2022.01509","title":"Multi-Modal Dynamic Graph Transformer for Visual Grounding","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","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":"Computer science; Initialization; Transformer; Ground; Modal; Graph; Ground truth; Artificial intelligence; Data mining; Pattern recognition (psychology); Theoretical computer science; Voltage","score_opus":0.04175260766584023,"score_gpt":0.32924491239606796,"score_spread":0.28749230473022774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312523916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21552795,0.000016135615,0.78061014,0.0017803652,0.0008463611,0.00074828265,0.00012291654,0.00025482776,0.000093004564],"genre_scores_gemma":[0.9668524,0.00003987338,0.029860854,0.002097001,0.000106101914,0.0006090317,0.0002985841,0.000038262937,0.000097891396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971735,0.00032397654,0.00048071126,0.0010469904,0.00050712656,0.00046773485],"domain_scores_gemma":[0.9987014,0.000310492,0.00021798928,0.00040436283,0.00015520351,0.00021053058],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056501594,0.00036883628,0.00036532368,0.00043762394,0.0010395746,0.00044415373,0.000710237,0.00009134837,0.0004922473],"category_scores_gemma":[0.000010078155,0.00037496988,0.00018795134,0.00042339202,0.00006743616,0.00038934962,0.00020215657,0.00061742694,0.00010714824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005950466,0.0004801673,0.00041736927,0.00005672762,0.000038759914,0.000009050889,0.0008136295,0.0003573734,0.0040874924,0.00055419677,0.00040180277,0.99272394],"study_design_scores_gemma":[0.0019495039,0.0011820605,0.008995846,0.00006698782,0.000019186537,0.00005783324,0.00007838245,0.983728,0.00020697287,0.0021597114,0.0010088645,0.00054666004],"about_ca_topic_score_codex":0.00010057065,"about_ca_topic_score_gemma":0.000035368615,"teacher_disagreement_score":0.99217725,"about_ca_system_score_codex":0.000087338834,"about_ca_system_score_gemma":0.000060911552,"threshold_uncertainty_score":0.99987024},"labels":[],"label_agreement":null},{"id":"W4312661653","doi":"10.1007/978-3-031-13064-9_24","title":"Caption and Observation Based on the Algorithm for Triangulation (COBALT): Preliminary Results from a Beta Trial","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in information systems and organisation","topic":"Multimodal Machine Learning Applications","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":"HEC Montréal","funders":"","keywords":"Suite; Workflow; Triangulation; Cobalt; Computer science; BETA (programming language); Software; Ecosystem; Simulation; Data science; Database; Geography; Ecology; Operating system; Archaeology; Cartography; Chemistry; Biology; Programming language","score_opus":0.02611223881160609,"score_gpt":0.24220170956167514,"score_spread":0.21608947075006904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312661653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012357872,0.000078419725,0.9898981,0.0031339189,0.0005156297,0.0036503132,0.0003485817,0.00012150238,0.0010177693],"genre_scores_gemma":[0.9497762,0.000044812346,0.04010287,0.0012103359,0.0006893145,0.000996941,0.006842259,0.000056899396,0.0002803799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812454,0.000121332676,0.00081901293,0.000366711,0.00043528815,0.00013312268],"domain_scores_gemma":[0.99669397,0.0017491112,0.00090252864,0.00048751745,0.00012669453,0.000040165014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009771318,0.0002643446,0.00026649737,0.0002847695,0.00039315055,0.00038758919,0.00023223707,0.00030282149,0.000017354781],"category_scores_gemma":[0.00034252586,0.00021999676,0.00005127143,0.00010931347,0.000028653323,0.0006898122,0.00007296752,0.00037538182,0.000008107275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004037908,0.000050108014,0.00006165131,0.00017432084,0.000061469545,6.862663e-7,0.0094411615,0.10193419,0.000036499798,0.23675479,0.00021532946,0.6472319],"study_design_scores_gemma":[0.007342204,0.00044319098,0.001588668,0.00009086043,0.00002568509,0.0000021312912,0.000019206165,0.9703081,0.000021125443,0.007405462,0.0125056915,0.0002476488],"about_ca_topic_score_codex":0.00077437825,"about_ca_topic_score_gemma":0.000016074488,"teacher_disagreement_score":0.9497952,"about_ca_system_score_codex":0.0002293953,"about_ca_system_score_gemma":0.000101162776,"threshold_uncertainty_score":0.8971207},"labels":[],"label_agreement":null},{"id":"W4313343280","doi":"10.1007/978-3-031-23028-8_29","title":"Refining AttnGAN Using Attention on Attention Network","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Architecture; Relation (database); Function (biology); Artificial intelligence; Network architecture; Attention network; State (computer science); Mode (computer interface); Image (mathematics); Natural language processing; Data mining; Human–computer interaction; Programming language","score_opus":0.027820712809457675,"score_gpt":0.28309235193141985,"score_spread":0.25527163912196216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343280","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":[0.002256808,0.00010193484,0.9906448,0.0009995007,0.0018753719,0.00031871305,0.0000036947984,0.00031874265,0.0034804193],"genre_scores_gemma":[0.37698254,0.000011964307,0.619987,0.0014688876,0.000984155,0.000034673816,0.000034288365,0.00008011529,0.000416378],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541056,0.00011195464,0.00058078597,0.0018982415,0.0012659817,0.000732457],"domain_scores_gemma":[0.9969971,0.0004481596,0.00054100296,0.0017229624,0.00014273902,0.00014804091],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014072912,0.00051467645,0.00044521174,0.0007662011,0.001061967,0.00049838645,0.0028941853,0.00022878921,0.000053711585],"category_scores_gemma":[0.00007786648,0.00054206373,0.00018360656,0.0010661826,0.00028374614,0.0005070435,0.0018113309,0.0016371448,0.0000778851],"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":[0.0000049958126,0.000030683466,0.0009924627,0.00001696335,0.000010676674,0.000026045564,0.00011146797,0.62160826,0.00046870278,0.06618712,0.000011581785,0.31053105],"study_design_scores_gemma":[0.00021502584,0.00017274504,0.005626535,0.00030851658,0.0000123284435,0.000057235007,8.472163e-8,0.9618,0.000018287768,0.028782371,0.0023722707,0.0006346494],"about_ca_topic_score_codex":0.00019203985,"about_ca_topic_score_gemma":0.000043149128,"teacher_disagreement_score":0.37472573,"about_ca_system_score_codex":0.000750008,"about_ca_system_score_gemma":0.00029717817,"threshold_uncertainty_score":0.9997031},"labels":[],"label_agreement":null},{"id":"W4313563617","doi":"10.1145/3551349.3560433","title":"Consistent Scene Graph Generation by Constraint Optimization","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scene graph; Local consistency; Consistency (knowledge bases); Constraint (computer-aided design); Graph; Probabilistic logic; Context (archaeology); Artificial intelligence; Theoretical computer science; Constraint satisfaction; Mathematics","score_opus":0.016020957269543702,"score_gpt":0.24106832676481343,"score_spread":0.22504736949526974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313563617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048425277,0.000036865953,0.98615855,0.0042681484,0.00013002381,0.00020046867,0.000008076135,0.00026441782,0.004090949],"genre_scores_gemma":[0.74328667,0.000002762741,0.25538304,0.00089004525,0.000015782685,0.00012254636,0.000071951756,0.000005131089,0.0002220643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990708,0.000111758396,0.0001619849,0.00029536578,0.00023285636,0.00012718288],"domain_scores_gemma":[0.9994425,0.00003306891,0.00007144215,0.00034874026,0.000048120844,0.000056086505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021633114,0.00007462762,0.00006743497,0.00007048623,0.00043910329,0.00009122958,0.0003752171,0.000015825603,0.00045862634],"category_scores_gemma":[0.000017675067,0.000078552504,0.000034333312,0.00033713403,0.000030500432,0.00011189344,0.00020937242,0.00012830592,0.000017437917],"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":[8.4761166e-7,0.00010095376,0.00043052828,0.000001389226,0.000009321311,8.830981e-7,0.00011819804,0.8251953,0.006846244,0.14322183,0.009821482,0.014252997],"study_design_scores_gemma":[0.00017250149,0.00003400013,0.00016123382,3.7016898e-7,0.0000024326753,0.000014797634,0.000019811747,0.99522436,0.0005938627,0.0002304318,0.003445738,0.00010043894],"about_ca_topic_score_codex":0.00022138977,"about_ca_topic_score_gemma":0.0000025672437,"teacher_disagreement_score":0.73844415,"about_ca_system_score_codex":0.00006025313,"about_ca_system_score_gemma":0.000045417673,"threshold_uncertainty_score":0.5021637},"labels":[],"label_agreement":null},{"id":"W4313639341","doi":"10.1002/9781119898566.ch2","title":"Metaverse: The New North Star","year":2023,"lang":"en","type":"other","venue":"","topic":"Multimodal Machine Learning Applications","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":"Institut National de la Recherche Scientifique","funders":"","keywords":"Metaverse; Computer science; Key (lock); Human–computer interaction; Virtual reality; Computer security","score_opus":0.015090409323806033,"score_gpt":0.2642368463415059,"score_spread":0.24914643701769987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313639341","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":[0.0000034363234,0.000076118136,0.30046505,0.007073561,0.00033591423,0.00033393668,0.000006251943,0.0042340374,0.6874717],"genre_scores_gemma":[0.00013251764,0.000030758005,0.0515126,0.00042456124,0.00023787389,0.000024590385,0.0000042413158,0.00029219486,0.94734067],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911875,0.000037206137,0.00009870539,0.0003449991,0.0002301279,0.00017021188],"domain_scores_gemma":[0.99849695,0.00010412177,0.00009207234,0.0012229575,0.000010761822,0.00007313888],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008435864,0.00014792243,0.00012756116,0.000101087055,0.00006287465,0.00009207392,0.0016028791,0.00006848441,0.0012649266],"category_scores_gemma":[0.00003337805,0.00009113251,0.000065322376,0.0004750276,0.00002313825,0.000035629586,0.00032279018,0.00024177029,0.009637134],"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":[8.2909295e-8,0.00000438131,0.00009603805,0.0000023660423,0.00003024313,0.000001229947,0.000054224558,0.00007643202,3.00677e-7,0.03667059,0.9466296,0.016434498],"study_design_scores_gemma":[0.000051814597,0.000004691599,0.00299705,0.000005786412,0.000008470683,8.710361e-7,0.0000021647268,0.009985534,9.098498e-7,0.00024200908,0.9865821,0.00011862376],"about_ca_topic_score_codex":0.015049712,"about_ca_topic_score_gemma":0.008372201,"teacher_disagreement_score":0.25986898,"about_ca_system_score_codex":0.000016957147,"about_ca_system_score_gemma":0.00008659843,"threshold_uncertainty_score":0.99964803},"labels":[],"label_agreement":null},{"id":"W4317659260","doi":"10.1145/3580519","title":"Validation of an Improved Vision-Based Web Page Parsing Pipeline","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Multimodal Machine Learning Applications","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; McGill University; Mount Allison University","funders":"","keywords":"Computer science; Parsing; Pipeline (software); Segmentation; Ground truth; Web page; Set (abstract data type); Artificial intelligence; Pruning; Zoom; Machine learning; Visualization; Interface (matter); Information retrieval; World Wide Web; Programming language","score_opus":0.021552036406250807,"score_gpt":0.294845347279104,"score_spread":0.2732933108728532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317659260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34768477,0.0000031562347,0.637315,0.013953492,0.00013288554,0.00027711084,0.00002388866,0.00050026726,0.000109461864],"genre_scores_gemma":[0.974986,0.0000054454467,0.024545236,0.00023284496,0.000023129229,0.00007173096,0.000016830558,0.000016909555,0.00010182916],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987997,0.00018922501,0.00025322766,0.00031799014,0.00024725826,0.00019261496],"domain_scores_gemma":[0.9974989,0.0007232075,0.000108190354,0.0015205261,0.00008405169,0.00006511265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061590096,0.0001228637,0.00011884162,0.00021363456,0.00034401068,0.00007532621,0.0010990017,0.0000572645,0.000060079903],"category_scores_gemma":[0.00010543043,0.00009643479,0.000087455934,0.0011292978,0.000053543677,0.00021676644,0.000016105969,0.0002516064,0.00014902516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037985483,0.0005521195,0.00009756384,0.000031610467,0.000031667034,0.0000019189486,0.0007092657,0.1764535,0.5837359,0.0012859775,0.000285106,0.23677742],"study_design_scores_gemma":[0.00028970506,0.00009000406,0.0007848453,0.000018799596,0.000012355973,0.0000011250959,0.000029633971,0.95254296,0.044472028,0.0013753283,0.00028166638,0.00010157122],"about_ca_topic_score_codex":0.00012066421,"about_ca_topic_score_gemma":0.00002033388,"teacher_disagreement_score":0.77608943,"about_ca_system_score_codex":0.000029162122,"about_ca_system_score_gemma":0.0001025904,"threshold_uncertainty_score":0.3932497},"labels":[],"label_agreement":null},{"id":"W4318824050","doi":"10.1109/icdm54844.2022.00125","title":"Set2Box: Similarity Preserving Representation Learning for Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Data Mining (ICDM)","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Similarity (geometry); Computer science; ENCODE; Set (abstract data type); Representation (politics); Source code; Code (set theory); Theoretical computer science; Data mining; Artificial intelligence; Algorithm; Programming language","score_opus":0.23452707947196416,"score_gpt":0.419734007872125,"score_spread":0.18520692840016084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318824050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25978014,0.000051246097,0.6618473,0.037737943,0.0049491865,0.0020355112,0.001985378,0.0012262476,0.030387087],"genre_scores_gemma":[0.9542998,0.000011490588,0.04047726,0.00054226484,0.00017318212,0.00054308,0.0025907815,0.000028408178,0.0013337075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687606,0.0003094678,0.00042063327,0.0011448059,0.00092705066,0.00032200856],"domain_scores_gemma":[0.9970747,0.0006660201,0.00037349024,0.0015631902,0.0002241551,0.00009839324],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011625573,0.00020841579,0.00019967764,0.00026269164,0.0008299335,0.00044357395,0.005304681,0.00005041321,0.00076445733],"category_scores_gemma":[0.0009017986,0.00024727604,0.000069880254,0.0003858184,0.0000377272,0.000875972,0.002708214,0.0007075078,0.00003996925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076422264,0.0013194487,0.046388052,0.00011070179,0.00067504955,0.00008062921,0.009402017,0.25502685,0.021422394,0.2844718,0.14697202,0.23336682],"study_design_scores_gemma":[0.0006503809,0.00013043,0.0033573783,0.000019393497,0.000011196211,0.00001718937,0.00048509738,0.97583234,0.0002109704,0.0020529144,0.016971957,0.0002607311],"about_ca_topic_score_codex":0.0003410012,"about_ca_topic_score_gemma":0.000036053993,"teacher_disagreement_score":0.7208055,"about_ca_system_score_codex":0.00017245674,"about_ca_system_score_gemma":0.00017461501,"threshold_uncertainty_score":0.999998},"labels":[],"label_agreement":null},{"id":"W4319323278","doi":"10.48550/arxiv.2302.01403","title":"Self-Supervised Relation Alignment for Scene Graph Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Alliance de recherche numérique du Canada; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Scene graph; Graph; Message passing; Artificial intelligence; Regularization (linguistics); Machine learning; Pattern recognition (psychology); Theoretical computer science; Parallel computing","score_opus":0.11173321987582735,"score_gpt":0.22186852859608186,"score_spread":0.11013530872025451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319323278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09230739,0.000014143649,0.9043463,0.00059228827,0.0005436808,0.0009355586,0.000022457,0.0009809607,0.00025724786],"genre_scores_gemma":[0.91279155,0.00007122028,0.086071275,0.00006771155,0.00016609975,0.000026616917,0.00023137496,0.00003055632,0.00054362055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980949,0.00012823853,0.0002267624,0.0011627492,0.00011121898,0.00027609934],"domain_scores_gemma":[0.9981075,0.00013495567,0.00024178112,0.0012146451,0.00018028366,0.000120819925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003605912,0.0002536741,0.00021485939,0.0003104587,0.00031083243,0.00013822776,0.001155787,0.0002594691,0.00000543955],"category_scores_gemma":[0.000041911255,0.00031602872,0.0002013649,0.00059453544,0.000027450787,0.0002442739,0.0008258593,0.00033873878,0.00013701634],"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":[0.000006846644,0.00009224997,0.0023084725,0.000076620614,0.00009059552,0.00000803045,0.00029382514,0.7377714,0.00039353335,0.2574534,0.00043658516,0.0010684587],"study_design_scores_gemma":[0.00042155807,0.00003259332,0.004092544,0.000019020139,0.000060159593,6.1199694e-7,0.000008995607,0.95840937,0.00019668078,0.036042873,0.00041133282,0.00030424996],"about_ca_topic_score_codex":0.00031421485,"about_ca_topic_score_gemma":0.000029698613,"teacher_disagreement_score":0.82048416,"about_ca_system_score_codex":0.0002675906,"about_ca_system_score_gemma":0.00012738032,"threshold_uncertainty_score":0.9999292},"labels":[],"label_agreement":null},{"id":"W4319971251","doi":"10.3390/a16020097","title":"Nemesis: Neural Mean Teacher Learning-Based Emotion-Centric Speaker","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Multimodal Machine Learning Applications","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":"Laurentian University","funders":"","keywords":"Closed captioning; Computer science; Natural language processing; Artificial intelligence; Task (project management); Natural language; Principle of maximum entropy; Image (mathematics); Perceptron; Artificial neural network; Speech recognition","score_opus":0.017980481412018783,"score_gpt":0.2741770904438704,"score_spread":0.2561966090318516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319971251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23856291,0.000077697565,0.7410672,0.012186175,0.0007469144,0.0005253482,0.0000035366265,0.004344125,0.0024861384],"genre_scores_gemma":[0.97635084,0.000004426039,0.021211488,0.0003303604,0.00023458786,0.000061029546,0.000035689238,0.000032817876,0.0017387373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980984,0.00018935351,0.00023752394,0.00055914966,0.00045109706,0.00046449617],"domain_scores_gemma":[0.9988167,0.00016604167,0.0001078404,0.0006623991,0.00009296894,0.00015400503],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046043802,0.00018879492,0.00016646108,0.00027221098,0.0003109202,0.00017472413,0.0008439913,0.000074296135,0.00010882987],"category_scores_gemma":[0.0001468855,0.00018320882,0.00010539499,0.0017503812,0.000042120886,0.00021466373,0.00021001896,0.00049640366,0.0025438573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006228163,0.00034203834,0.036199156,0.0000337613,0.00006683283,0.00011167523,0.0026956783,0.25943345,0.0002982124,0.002475566,0.009092323,0.6892451],"study_design_scores_gemma":[0.0003089934,0.000037806098,0.13715541,0.0000059380027,0.0000068704035,0.00000662231,0.00003858926,0.8574295,0.000050622933,0.00016873894,0.0046066227,0.00018429199],"about_ca_topic_score_codex":0.0003898521,"about_ca_topic_score_gemma":0.0000052194882,"teacher_disagreement_score":0.73778796,"about_ca_system_score_codex":0.000053083055,"about_ca_system_score_gemma":0.000058774593,"threshold_uncertainty_score":0.9982328},"labels":[],"label_agreement":null},{"id":"W4320481739","doi":"10.1007/978-3-031-25069-9_15","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"McGill University","funders":"","keywords":"Closed captioning; Optimal distinctiveness theory; Computer science; Image (mathematics); Artificial intelligence; Metric (unit); Natural language processing; Embedding; Ground truth; Focus (optics); Baseline (sea); Consistency (knowledge bases); Pattern recognition (psychology); Machine learning; Information retrieval","score_opus":0.017930149582978804,"score_gpt":0.27462452038326973,"score_spread":0.25669437080029095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320481739","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":[0.000031614112,0.000033329725,0.9927144,0.0011400806,0.0011132566,0.0005616924,0.000007014993,0.0007625709,0.0036360528],"genre_scores_gemma":[0.06173897,0.000014560439,0.9367412,0.0004972134,0.00045262516,0.000050439958,0.000045922538,0.00007439424,0.0003846966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957835,0.00006582428,0.000629845,0.0019062024,0.0009659451,0.0006486561],"domain_scores_gemma":[0.99670947,0.00068573054,0.00045530824,0.0015896977,0.00037223674,0.00018753562],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010391171,0.0005387054,0.00046061593,0.00089793355,0.0005670371,0.0007346213,0.003116718,0.000296629,0.000031845655],"category_scores_gemma":[0.00028785263,0.00054374535,0.00013651112,0.0011895575,0.0005968287,0.00073741266,0.0016956595,0.0010339655,0.00026066127],"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":[0.0000021610947,0.000020908015,0.000080307924,0.000021510223,0.000009644907,0.000027794275,0.00042965333,0.7851023,0.00018484068,0.023291383,0.000016702108,0.19081278],"study_design_scores_gemma":[0.00018431059,0.000060411992,0.0009307068,0.00015135515,0.000008242938,0.000036417354,1.0001115e-7,0.92423165,0.00007242405,0.07368872,0.00010665588,0.0005290293],"about_ca_topic_score_codex":0.0002665897,"about_ca_topic_score_gemma":0.00006982936,"teacher_disagreement_score":0.19028375,"about_ca_system_score_codex":0.00044312546,"about_ca_system_score_gemma":0.00024174046,"threshold_uncertainty_score":0.9997014},"labels":[],"label_agreement":null},{"id":"W4321608662","doi":"10.36227/techrxiv.22133894.v1","title":"Image Captioning for the Visually Impaired and Blind: A Recipe for Low-Resource Languages","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Visually impaired; Computer science; Assistive technology; Hearing impaired; Human–computer interaction; Resource (disambiguation); Artificial intelligence; Computer vision; Speech recognition; Natural language processing; Image (mathematics); Audiology","score_opus":0.03894768839832212,"score_gpt":0.3599525522228245,"score_spread":0.3210048638245024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321608662","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":[0.008997686,0.00012542786,0.97614044,0.01131838,0.00013758216,0.0022176201,0.000050215785,0.000781261,0.00023138188],"genre_scores_gemma":[0.24048622,0.000023293314,0.75040555,0.00061868667,0.0004728082,0.0046325456,0.00014050034,0.00008626191,0.0031341591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984515,0.000057165107,0.0002801378,0.0007368877,0.00017295597,0.00030136068],"domain_scores_gemma":[0.99665385,0.001978046,0.00020057276,0.0009502156,0.00014111308,0.000076223085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008977535,0.00022859882,0.00023002291,0.00012107713,0.00041573646,0.0006227339,0.0012112437,0.0001514955,0.0000055878677],"category_scores_gemma":[0.00050853594,0.00017000992,0.00015344791,0.00014988438,0.000060695136,0.00008128434,0.0013395534,0.0003526745,0.000019032332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038560957,0.0005411756,0.0018423817,0.0035460093,0.0012743362,0.000013632496,0.028991546,0.07907676,0.013970283,0.22001493,0.06599492,0.58434844],"study_design_scores_gemma":[0.00051023875,0.000043181455,0.004482293,0.000064136584,0.000032705837,0.000003457613,0.00015795421,0.98656845,0.00013298598,0.005308099,0.0024464272,0.00025008866],"about_ca_topic_score_codex":0.0008527261,"about_ca_topic_score_gemma":0.00011909707,"teacher_disagreement_score":0.9074917,"about_ca_system_score_codex":0.000037636524,"about_ca_system_score_gemma":0.0000938583,"threshold_uncertainty_score":0.69328034},"labels":[],"label_agreement":null},{"id":"W4327523052","doi":"10.1109/access.2023.3257280","title":"Video Relationship Detection Using Mixture of Experts","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Multimodal Machine Learning Applications","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":"Microsoft Research Asia; Microsoft Research; Microsoft","keywords":"Computer science; Artificial intelligence; Inference; Machine learning; Classifier (UML); Artificial neural network; Predicate (mathematical logic); Object detection; Pattern recognition (psychology)","score_opus":0.07794275924308183,"score_gpt":0.37545058696163475,"score_spread":0.2975078277185529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327523052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59397584,0.000008963502,0.4051058,0.00024666876,0.0002011841,0.00007917988,6.4658985e-7,0.00021417899,0.00016751357],"genre_scores_gemma":[0.9939139,0.0000014433208,0.005887517,0.000050784678,0.00006730707,0.000025514044,0.0000014886618,0.0000087988155,0.000043248092],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992489,0.000059787515,0.00016383328,0.00022558866,0.00017125721,0.00013063468],"domain_scores_gemma":[0.9991317,0.00020746389,0.00010389307,0.00045138254,0.00006751782,0.000038051767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017819027,0.000068710506,0.00008164948,0.00019197025,0.00014943613,0.00008977206,0.00068857183,0.000057316574,0.000004883622],"category_scores_gemma":[0.00012437963,0.00006831365,0.000036859383,0.0012500386,0.000020653779,0.00052105146,0.0001271227,0.00010815109,0.000037751946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001589713,0.00013523639,0.35009447,0.00013155656,0.000046160796,0.000012998796,0.004364379,0.23341294,0.29085293,0.012494285,0.001540611,0.10689854],"study_design_scores_gemma":[0.000118319214,0.0000098365845,0.30528316,0.000017894568,0.000004456543,0.00000563513,0.000010115622,0.65565634,0.034050588,0.0044914936,0.00024109565,0.000111058085],"about_ca_topic_score_codex":0.0004956007,"about_ca_topic_score_gemma":0.000022527614,"teacher_disagreement_score":0.42224342,"about_ca_system_score_codex":0.000027199947,"about_ca_system_score_gemma":0.000025418509,"threshold_uncertainty_score":0.278575},"labels":[],"label_agreement":null},{"id":"W4328029477","doi":"10.1111/cgf.14668","title":"A Drone Video Clip Dataset and its Applications in Automated Cinematography","year":2022,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Multimodal Machine Learning Applications","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":"Korea Creative Content Agency","keywords":"Drone; Computer science; Computer vision; Artificial intelligence; Cinematography; CLIPS; Video capture; Computer graphics (images); Video processing","score_opus":0.010880231189374133,"score_gpt":0.2707722317890653,"score_spread":0.25989200059969114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328029477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101970166,0.00085108506,0.88473064,0.0075357677,0.00027328145,0.0017834398,0.00063104794,0.0021121118,0.00011246032],"genre_scores_gemma":[0.97791076,0.000024110377,0.01928328,0.0013009543,0.000025749965,0.0007494414,0.000681556,0.00002011891,0.000004016097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981223,0.000152185,0.00034900187,0.00068949483,0.00029788408,0.00038917782],"domain_scores_gemma":[0.9985537,0.0002209947,0.0001405504,0.00091047614,0.00004213438,0.00013216784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039054692,0.00019757189,0.00021856504,0.000685768,0.00059146626,0.00013052244,0.0013087097,0.000048023063,0.00000937511],"category_scores_gemma":[0.000009656349,0.00021799954,0.000059875263,0.0023319689,0.00004372008,0.00025697262,0.0017263254,0.00047841857,0.000012761699],"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":[0.000004267538,0.0003391365,0.043577924,0.000039226892,0.0000320568,0.000009699817,0.00035412953,0.002573307,0.00008947349,0.93711674,0.012101565,0.0037624508],"study_design_scores_gemma":[0.00041629077,0.00006751926,0.041270483,0.0000068016634,0.0000054670804,0.000035721274,0.000016854103,0.916761,0.000008602514,0.0068136854,0.034364704,0.00023289617],"about_ca_topic_score_codex":0.0002000026,"about_ca_topic_score_gemma":0.00004326744,"teacher_disagreement_score":0.9303031,"about_ca_system_score_codex":0.000024092966,"about_ca_system_score_gemma":0.00003737288,"threshold_uncertainty_score":0.8889763},"labels":[],"label_agreement":null},{"id":"W4361193744","doi":"10.48550/arxiv.2303.14979","title":"Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Computer science; Relevance (law); Artificial intelligence; Lexicon; Generator (circuit theory); Training set; Labeled data; Natural language processing; Information retrieval; Machine learning","score_opus":0.14579180794735194,"score_gpt":0.2567737515440782,"score_spread":0.11098194359672628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361193744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.434102,0.000009095304,0.5628383,0.00022830897,0.00044929935,0.0006697125,0.000028755372,0.001432484,0.00024204093],"genre_scores_gemma":[0.93187076,0.000023548873,0.066719055,0.00008931252,0.00017839034,0.000010059775,0.000056842204,0.000060904433,0.0009911224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969485,0.00015691249,0.00033171833,0.0018111883,0.00015516588,0.00059654674],"domain_scores_gemma":[0.99674404,0.000710082,0.00032558286,0.0016623066,0.0003107896,0.00024721242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005997346,0.00042789034,0.0004673472,0.00035916598,0.00037697516,0.00020956378,0.0027254021,0.00041914082,0.000011210141],"category_scores_gemma":[0.00035570672,0.00054033595,0.00036264342,0.0008325124,0.000082323335,0.00023844022,0.0017547463,0.0008905613,0.00018251619],"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":[0.00023385146,0.00032234544,0.0011945113,0.000407483,0.00049884483,0.00017441496,0.011816006,0.84864926,0.0028614793,0.12471902,0.00022602528,0.008896745],"study_design_scores_gemma":[0.0010379223,0.000060774226,0.001353397,0.000067744484,0.00007666912,0.000002280034,0.00018188001,0.97200376,0.0008204256,0.02366012,0.00017062311,0.0005644324],"about_ca_topic_score_codex":0.00022605424,"about_ca_topic_score_gemma":0.00004310496,"teacher_disagreement_score":0.4977688,"about_ca_system_score_codex":0.00025672326,"about_ca_system_score_gemma":0.0006279382,"threshold_uncertainty_score":0.99970484},"labels":[],"label_agreement":null},{"id":"W4364322545","doi":"10.1109/tai.2023.3266183","title":"Visual Relationship Detection for Workplace Safety Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Computer science; Bayesian network; Context (archaeology); Object detection; Visualization; Artificial neural network; Artificial intelligence; Object (grammar); Graphical user interface; Machine learning; Data mining; Pattern recognition (psychology); Programming language","score_opus":0.05401277960001292,"score_gpt":0.34603996480937,"score_spread":0.29202718520935705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364322545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020640746,0.0000059142435,0.992886,0.0017521462,0.0004968441,0.0011398032,0.000023241337,0.0013647045,0.00026727034],"genre_scores_gemma":[0.9762117,0.000012159484,0.021105282,0.000111573456,0.0001092969,0.0018618505,0.000010144008,0.000029441506,0.0005485544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981189,0.00009377291,0.000494517,0.00063818996,0.0002760807,0.00037857314],"domain_scores_gemma":[0.9975764,0.0013711009,0.000119288576,0.00063700794,0.00016061444,0.00013556948],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053604686,0.00019771041,0.00015407037,0.0004451168,0.0011306498,0.00016476624,0.0006087538,0.00013679003,0.000028611232],"category_scores_gemma":[0.000058790927,0.00022173172,0.00015844834,0.0024675983,0.000080785074,0.00030160256,0.000005549959,0.00039974568,0.002153392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048156482,0.00017570228,0.000012826593,0.000014708523,0.00001555166,4.515549e-7,0.00033453247,0.21080808,0.0028621003,0.055180274,0.000025732765,0.73052186],"study_design_scores_gemma":[0.000049865164,0.00011891771,0.0005328475,0.000014362057,0.000017157658,0.0000042044976,0.00009615291,0.8986674,0.058317248,0.03942723,0.0024704768,0.00028416788],"about_ca_topic_score_codex":0.000081570455,"about_ca_topic_score_gemma":0.00013195,"teacher_disagreement_score":0.9741476,"about_ca_system_score_codex":0.00012819473,"about_ca_system_score_gemma":0.00006701315,"threshold_uncertainty_score":0.99862355},"labels":[],"label_agreement":null},{"id":"W4367672600","doi":"10.36227/techrxiv.22133894.v2","title":"Image Captioning for the Visually Impaired and Blind: A Recipe for Low-Resource Languages","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Visually impaired; Assistive technology; Hearing impaired; Human–computer interaction; Artificial intelligence; Speech recognition; Computer vision; Image (mathematics); Natural language processing; Audiology","score_opus":0.03894768839832212,"score_gpt":0.3599525522228245,"score_spread":0.3210048638245024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367672600","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":[0.008997686,0.00012542786,0.97614044,0.01131838,0.00013758216,0.0022176201,0.000050215785,0.000781261,0.00023138188],"genre_scores_gemma":[0.24048622,0.000023293314,0.75040555,0.00061868667,0.0004728082,0.0046325456,0.00014050034,0.00008626191,0.0031341591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984515,0.000057165107,0.0002801378,0.0007368877,0.00017295597,0.00030136068],"domain_scores_gemma":[0.99665385,0.001978046,0.00020057276,0.0009502156,0.00014111308,0.000076223085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008977535,0.00022859882,0.00023002291,0.00012107713,0.00041573646,0.0006227339,0.0012112437,0.0001514955,0.0000055878677],"category_scores_gemma":[0.00050853594,0.00017000992,0.00015344791,0.00014988438,0.000060695136,0.00008128434,0.0013395534,0.0003526745,0.000019032332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038560957,0.0005411756,0.0018423817,0.0035460093,0.0012743362,0.000013632496,0.028991546,0.07907676,0.013970283,0.22001493,0.06599492,0.58434844],"study_design_scores_gemma":[0.00051023875,0.000043181455,0.004482293,0.000064136584,0.000032705837,0.000003457613,0.00015795421,0.98656845,0.00013298598,0.005308099,0.0024464272,0.00025008866],"about_ca_topic_score_codex":0.0008527261,"about_ca_topic_score_gemma":0.00011909707,"teacher_disagreement_score":0.9074917,"about_ca_system_score_codex":0.000037636524,"about_ca_system_score_gemma":0.0000938583,"threshold_uncertainty_score":0.69328034},"labels":[],"label_agreement":null},{"id":"W4375854264","doi":"10.1109/cbs55922.2023.10115355","title":"Cross-modal Task Understanding and Execution of Voice-fingertip Reading Instruction by Using Small Family Service Robotic","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Task (project management); Robot; Service robot; Service (business); Artificial intelligence; Modal; Object (grammar); Human–computer interaction; Speech recognition; Natural language processing; Computer vision","score_opus":0.06714828239946975,"score_gpt":0.3062395290434044,"score_spread":0.23909124664393466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375854264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5275551,0.000010657353,0.47150785,0.00027466158,0.00008239571,0.0000889511,0.0000012941892,0.00021568764,0.00026337727],"genre_scores_gemma":[0.96868014,0.000007658124,0.031101173,0.00009955153,0.000024079895,0.000006669611,0.000010028552,0.000013832412,0.00005688513],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988407,0.000052775024,0.00027123603,0.00040015375,0.00019020973,0.0002449536],"domain_scores_gemma":[0.9992478,0.00012712956,0.00015141853,0.0003213717,0.000078553894,0.0000737218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032080276,0.00012817763,0.00015007082,0.00020315283,0.00029906575,0.00017808465,0.00030445596,0.000078116806,0.0000022216507],"category_scores_gemma":[0.000044895398,0.00013427147,0.000028318973,0.0011463033,0.000051415405,0.00042196215,0.0002393138,0.00015151096,0.000016714383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018636774,0.000055191424,0.050482478,0.00022489633,0.0000475029,0.0000028102743,0.00237964,0.15270041,0.71422726,0.06605698,0.00009914936,0.013705071],"study_design_scores_gemma":[0.0002868739,0.000019881578,0.047171187,0.00003741746,0.000008810074,0.00001203601,0.00019568768,0.94851303,0.0011820174,0.0024048649,0.000024454108,0.00014375112],"about_ca_topic_score_codex":0.0031461113,"about_ca_topic_score_gemma":0.000035639576,"teacher_disagreement_score":0.7958126,"about_ca_system_score_codex":0.00014540991,"about_ca_system_score_gemma":0.000036531557,"threshold_uncertainty_score":0.54754317},"labels":[],"label_agreement":null},{"id":"W4376958607","doi":"10.32473/flairs.36.133328","title":"Towards a multi-modal Deep Learning Architecture for User Modeling","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Multimodal Machine Learning Applications","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":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Modal; Convolutional neural network; User modeling; Representation (politics); Feature (linguistics); Feature learning; Machine learning; Architecture; Human–computer interaction; User interface","score_opus":0.16179346554749333,"score_gpt":0.40432547208867836,"score_spread":0.24253200654118504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376958607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12088357,0.00001851446,0.862153,0.014503742,0.00046345702,0.00080406957,0.0000122265565,0.00030212497,0.00085932773],"genre_scores_gemma":[0.9251984,0.00007259184,0.07347722,0.00006500505,0.00029300488,0.0003863071,0.0000076981305,0.000027359329,0.0004724064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964392,0.00004212186,0.0005637996,0.0007536059,0.00149364,0.0007076304],"domain_scores_gemma":[0.9956569,0.000510332,0.0002039103,0.00030471766,0.0031838198,0.00014029973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028736927,0.00022816926,0.00023444438,0.00024425826,0.00079887063,0.0006153047,0.0044365535,0.0001477999,0.000024322773],"category_scores_gemma":[0.002624923,0.00018881848,0.00036859125,0.0016253799,0.0002990125,0.0004725218,0.0017140984,0.0011775737,0.00006694995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051351497,0.000118319,0.0009440446,0.0001176528,0.00012032072,3.521524e-7,0.009741803,0.10441184,0.07089645,0.7246037,0.00042542192,0.08856871],"study_design_scores_gemma":[0.000058373716,0.000049857226,0.00025500768,0.000075256656,0.0000050366166,0.0000023416312,0.0017948681,0.88073087,0.023089286,0.09296522,0.0008043615,0.0001695287],"about_ca_topic_score_codex":0.00042554797,"about_ca_topic_score_gemma":0.000028603656,"teacher_disagreement_score":0.80431485,"about_ca_system_score_codex":0.00018468389,"about_ca_system_score_gemma":0.0002510227,"threshold_uncertainty_score":0.8244294},"labels":[],"label_agreement":null},{"id":"W4378419434","doi":"10.1007/978-3-031-33380-4_19","title":"TCR: Short Video Title Generation and Cover Selection with Attention Refinement","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 Alberta","funders":"","keywords":"Computer science; Closed captioning; Selection (genetic algorithm); Cover (algebra); Task (project management); Popularity; Information retrieval; Focus (optics); Quality (philosophy); Multimedia; Artificial intelligence; Image (mathematics)","score_opus":0.024619940049163257,"score_gpt":0.2689565636779841,"score_spread":0.24433662362882083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378419434","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":[0.000361759,0.00002926545,0.99409926,0.00055291643,0.00030393153,0.00019360546,0.00000128721,0.00015055164,0.0043074503],"genre_scores_gemma":[0.45114702,0.000054390126,0.5412181,0.0006256514,0.0008281345,0.000046366928,0.000035958266,0.000059779857,0.0059846053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866706,0.000012349317,0.0001502815,0.0006368165,0.00036525444,0.000168238],"domain_scores_gemma":[0.99937916,0.00005791972,0.0000669235,0.00035697708,0.00009168192,0.00004734176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025912342,0.00016131441,0.00012697237,0.0002684928,0.00014726107,0.00020811602,0.0003799468,0.00009260982,0.000022916589],"category_scores_gemma":[0.000015532127,0.00013950745,0.000021363023,0.0003052173,0.00010284088,0.00015531726,0.00021725579,0.00027359172,0.00016460528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024412686,0.000017106957,0.0007368108,0.000025100146,0.000013436047,0.00000762753,0.00012778069,0.047222737,0.0012924025,0.032904062,0.0003722821,0.91727823],"study_design_scores_gemma":[0.00007834032,0.00010050893,0.00257352,0.000065475804,0.0000061900996,0.000021771226,2.2447333e-8,0.98850816,0.00020948499,0.005267842,0.0029404513,0.00022822907],"about_ca_topic_score_codex":0.00003524358,"about_ca_topic_score_gemma":0.00006692608,"teacher_disagreement_score":0.94128543,"about_ca_system_score_codex":0.000106768486,"about_ca_system_score_gemma":0.000100830744,"threshold_uncertainty_score":0.56889486},"labels":[],"label_agreement":null},{"id":"W4378465251","doi":"10.48550/arxiv.2305.14998","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Nvidia","keywords":"Closed captioning; Robustness (evolution); Computer science; Artificial intelligence; Computer vision; Image (mathematics); Natural language processing","score_opus":0.1578930036878109,"score_gpt":0.25725857490790355,"score_spread":0.09936557122009265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378465251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50396293,0.000005475089,0.49493468,0.000054810123,0.00015137905,0.00028844233,0.000014254267,0.00008293379,0.0005051259],"genre_scores_gemma":[0.9890393,0.0000149153775,0.010742467,0.0000031291556,0.000023969875,0.000004346515,0.0000369062,0.000013450489,0.000121488294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998081,0.0005811433,0.00026174547,0.00063936936,0.00029433094,0.0001423735],"domain_scores_gemma":[0.99587023,0.000222562,0.00069946505,0.0022723149,0.00088569155,0.00004971112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013904225,0.0001578461,0.00021131107,0.00044895988,0.00013480762,0.00004741155,0.0029720499,0.00018180312,0.000012302827],"category_scores_gemma":[0.0004990558,0.00015788547,0.00010056537,0.001825798,0.00011267264,0.00032648494,0.0016139196,0.00043565143,0.000007076157],"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":[0.0000023648527,0.00006327035,0.0024850788,0.00005693933,0.000021986581,6.9240826e-7,0.00024734272,0.94409704,0.00039853534,0.04979198,0.000012526863,0.0028222448],"study_design_scores_gemma":[0.0001928425,0.0000178027,0.21737137,0.000048494807,0.00006377821,3.1913575e-7,0.000060142556,0.7726909,0.0002800934,0.009161095,0.0000019881054,0.00011118081],"about_ca_topic_score_codex":0.0009187682,"about_ca_topic_score_gemma":0.000095445874,"teacher_disagreement_score":0.48507643,"about_ca_system_score_codex":0.00019236503,"about_ca_system_score_gemma":0.0002284152,"threshold_uncertainty_score":0.6438383},"labels":[],"label_agreement":null},{"id":"W4379522641","doi":"10.21428/594757db.e0f8ffcd","title":"Guided Learning of Human Sensor Models with Low-Level Grounding","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Interpretability; Representation (politics); Computer science; Artificial intelligence; Machine learning; Raw data; Pattern recognition (psychology)","score_opus":0.07235375822604777,"score_gpt":0.3253710443923826,"score_spread":0.25301728616633484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379522641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4181359,0.0000011561837,0.5732946,0.0003674072,0.000015182297,0.000092376235,4.307254e-7,0.0005279031,0.007565086],"genre_scores_gemma":[0.8930677,9.1622167e-7,0.10446227,0.00003835394,0.000018990193,0.00002034615,0.000005291154,0.000014534749,0.0023715675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988911,0.00005971644,0.00021292655,0.0003247224,0.00027620097,0.0002352977],"domain_scores_gemma":[0.999148,0.00012011196,0.000110772424,0.00046348307,0.000094982905,0.00006265053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033163922,0.00010803908,0.00014672469,0.0001849639,0.00022121957,0.00006668641,0.00054159225,0.000035157347,0.000017080658],"category_scores_gemma":[0.000035046985,0.00009003399,0.00003697088,0.0008280866,0.00003647068,0.00027022694,0.00022398887,0.00018252706,0.00010886375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023889925,0.000043991007,0.008547578,0.000041970874,0.000027922326,0.000006948193,0.0016656476,0.31785083,0.03312493,0.63095415,0.00027826676,0.0074553574],"study_design_scores_gemma":[0.00023803169,0.000052320844,0.024583708,0.000026181955,0.0000034351467,0.0000064768833,0.0000805427,0.9685934,0.0017637841,0.004467902,0.00004304833,0.00014116382],"about_ca_topic_score_codex":0.0007679304,"about_ca_topic_score_gemma":0.000009685609,"teacher_disagreement_score":0.6507426,"about_ca_system_score_codex":0.000023667944,"about_ca_system_score_gemma":0.00002776588,"threshold_uncertainty_score":0.36714795},"labels":[],"label_agreement":null},{"id":"W4383560362","doi":"10.54254/2755-2721/5/20230511","title":"To describe the content of image: The view from image captioning","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Natural language; Field (mathematics); Artificial intelligence; Natural language processing; Task (project management); Image (mathematics); Domain (mathematical analysis); Perspective (graphical); Engineering","score_opus":0.018034436956163823,"score_gpt":0.234893111473301,"score_spread":0.21685867451713717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383560362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1504046,0.000040884344,0.8455959,0.0034178423,0.00004237112,0.00018769238,0.0000048595775,0.00016820476,0.00013765857],"genre_scores_gemma":[0.90131944,0.0000031739937,0.098319225,0.00020786599,0.000037214173,0.000085967426,0.000011069467,0.000007757054,0.00000829526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936444,0.000012137718,0.00015462602,0.00017755857,0.00017113864,0.00012008356],"domain_scores_gemma":[0.99920064,0.0004709657,0.00003978189,0.00019750866,0.000051256102,0.000039820792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019343285,0.00008314702,0.00008806521,0.000047506437,0.00014468828,0.00009573499,0.00036290247,0.000014470512,0.0000031203194],"category_scores_gemma":[0.000031279542,0.000056646673,0.000023402017,0.00040148804,0.000028023893,0.00006302103,0.00019732502,0.00011262525,0.000054196218],"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":[0.0000015709315,0.000007522605,0.000059758768,0.000010944298,0.000022791157,6.116461e-7,0.0012791178,0.7314239,0.024229866,0.2249698,0.00012837032,0.01786574],"study_design_scores_gemma":[0.00010374022,0.0000051464713,0.13244352,0.000012518334,0.0000046274977,0.000001941734,0.00006567689,0.8623604,0.0002553093,0.0043335143,0.0003393533,0.00007424738],"about_ca_topic_score_codex":0.00014988436,"about_ca_topic_score_gemma":9.54688e-7,"teacher_disagreement_score":0.7509148,"about_ca_system_score_codex":0.000010749358,"about_ca_system_score_gemma":0.000014959612,"threshold_uncertainty_score":0.23099843},"labels":[],"label_agreement":null},{"id":"W4385565354","doi":"10.18653/v1/2023.acl-long.526","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Paragraph; Natural language; Artificial intelligence; Transformer; Augmented reality; Sentence; Natural language processing; Code (set theory); Human–computer interaction; Programming language; World Wide Web","score_opus":0.01060861406612697,"score_gpt":0.3164279157877798,"score_spread":0.30581930172165284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385565354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6322293,0.00001749533,0.3579767,0.005963779,0.00019595576,0.0002005163,4.7048837e-7,0.0018869621,0.0015287839],"genre_scores_gemma":[0.9448292,0.0000012225095,0.049120996,0.0006774462,0.0001129944,0.00005061585,0.000039555023,0.000011044899,0.0051568747],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906814,0.000056930323,0.0001254744,0.00032569887,0.00020386474,0.00021990895],"domain_scores_gemma":[0.99946296,0.00005260409,0.000030872776,0.00031966742,0.00005338766,0.00008053536],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021626722,0.00009169162,0.0000732189,0.00017922466,0.00015942955,0.00016393643,0.0004358505,0.000021262354,0.000040100433],"category_scores_gemma":[0.00012515787,0.00008450847,0.000029965338,0.0009951461,0.000007461802,0.00019210659,0.00026698364,0.00018100264,0.002208155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028490751,0.00004501673,0.0033919443,0.000009111224,0.000019620724,0.00001675617,0.005715028,0.036245953,0.5138891,0.01655805,0.013692117,0.41041452],"study_design_scores_gemma":[0.00011109575,0.000025429312,0.022491526,0.0000024389087,0.0000012298791,0.0000027665285,0.00007210416,0.97197974,0.0029717619,0.00001823252,0.0022088224,0.000114858405],"about_ca_topic_score_codex":0.0003115227,"about_ca_topic_score_gemma":0.000022646895,"teacher_disagreement_score":0.9357338,"about_ca_system_score_codex":0.000030998923,"about_ca_system_score_gemma":0.000018053863,"threshold_uncertainty_score":0.9985687},"labels":[],"label_agreement":null},{"id":"W4385566910","doi":"10.18653/v1/2023.semeval-1.281","title":"UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"SemEval; Computer science; Natural language processing; Task (project management); Encoder; Artificial intelligence; Context (archaeology); Word (group theory); Machine translation; Code (set theory); Word-sense disambiguation; Set (abstract data type); Text segmentation; Test set; Segmentation; Linguistics; Programming language; WordNet","score_opus":0.03527268440563371,"score_gpt":0.34970334595647884,"score_spread":0.31443066155084515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385566910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6475829,0.000018753422,0.3479793,0.0031103604,0.00011817392,0.0006526415,0.00000965448,0.00036081337,0.00016740669],"genre_scores_gemma":[0.9788561,0.000008471879,0.01871948,0.00019282511,0.000059401806,0.00018600844,0.00021809275,0.000017185432,0.0017424556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877197,0.00007442115,0.00023954023,0.00046930287,0.00021915868,0.00022560141],"domain_scores_gemma":[0.9987775,0.0007359558,0.00009554604,0.00023007629,0.00007967642,0.00008125202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038070674,0.00013861904,0.00012402974,0.00014572468,0.00030971374,0.00011513776,0.00012971042,0.00006619225,0.000018857769],"category_scores_gemma":[0.00012899723,0.00013732181,0.000049719187,0.00044374078,0.000033697164,0.0003096775,0.000081790684,0.00007248077,0.0001664976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006765933,0.000070496375,0.002662882,0.000050587336,0.000033014585,0.0000013996761,0.006221891,0.0028668696,0.044074927,0.006816362,0.0009692003,0.93616474],"study_design_scores_gemma":[0.0010734772,0.000059758106,0.03366746,0.000009653908,0.0000126767045,0.0000034126156,0.00014941514,0.9599767,0.0027025957,0.0006699473,0.0015028353,0.00017208308],"about_ca_topic_score_codex":0.000493446,"about_ca_topic_score_gemma":0.00064947276,"teacher_disagreement_score":0.9571098,"about_ca_system_score_codex":0.00005764322,"about_ca_system_score_gemma":0.000026490687,"threshold_uncertainty_score":0.5599821},"labels":[],"label_agreement":null},{"id":"W4385571036","doi":"10.18653/v1/2023.findings-acl.120","title":"Pragmatic Inference with a CLIP Listener for Contrastive Captioning","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Samsung","keywords":"Closed captioning; Discriminative model; Computer science; Leverage (statistics); Artificial intelligence; Inference; Fluency; Speech recognition; Natural language processing; Prosody; Hyperparameter; Image (mathematics); Linguistics","score_opus":0.018521158491553363,"score_gpt":0.31106428574775147,"score_spread":0.29254312725619813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02662808,0.0000023451407,0.9659983,0.0023054965,0.000031693588,0.00038203073,0.0000025098036,0.0006459183,0.0040036486],"genre_scores_gemma":[0.8195517,5.826654e-7,0.17909394,0.0001645539,0.000021641443,0.00036019823,0.000009019018,0.000007027413,0.00079135236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999272,0.000026614458,0.00011867689,0.00025908515,0.00012483388,0.00019877266],"domain_scores_gemma":[0.99886507,0.0006134703,0.000061390136,0.00028891323,0.00011543882,0.000055699347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000211385,0.00008128473,0.00009489774,0.0000760147,0.00015994417,0.00012102249,0.00033704608,0.000024435252,0.000010137846],"category_scores_gemma":[0.0002049557,0.000060737948,0.00002342695,0.0004822593,0.000028005908,0.00018590795,0.00007904183,0.00008213267,0.00016380283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010662832,0.000048498838,0.009930144,0.000044777546,0.000037156606,0.0000033225635,0.0017671604,0.02814701,0.0010484782,0.92597985,0.00065756537,0.03232539],"study_design_scores_gemma":[0.00035702725,0.00007262147,0.048133217,0.000021166432,0.0000050527387,0.0000048520383,0.000045670047,0.9463313,0.00007667247,0.004200518,0.0006338891,0.000117985706],"about_ca_topic_score_codex":0.00021282234,"about_ca_topic_score_gemma":0.000041864656,"teacher_disagreement_score":0.92177933,"about_ca_system_score_codex":0.000018160183,"about_ca_system_score_gemma":0.000058457932,"threshold_uncertainty_score":0.24768215},"labels":[],"label_agreement":null},{"id":"W4385572364","doi":"10.18653/v1/2023.findings-acl.590","title":"Zero-shot Visual Question Answering with Language Model Feedback","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 de Montréal","funders":"National Natural Science Foundation of China","keywords":"Closed captioning; Computer science; Leverage (statistics); Language model; Task (project management); Artificial intelligence; Context (archaeology); Question answering; Natural language processing; Code (set theory); Scheme (mathematics); Machine learning; Speech recognition; Image (mathematics); Programming language; Engineering","score_opus":0.01670687766372517,"score_gpt":0.3167307179897402,"score_spread":0.300023840326015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385572364","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33252382,0.0000031218883,0.6610377,0.00080970034,0.00001809696,0.00008438669,5.241133e-7,0.001042907,0.0044797547],"genre_scores_gemma":[0.89533305,0.0000013507466,0.10266477,0.00014629,0.000019936337,0.000032688105,0.000008529749,0.000011917366,0.0017814749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917996,0.000025023366,0.000097605414,0.00030030773,0.00019175583,0.00020536737],"domain_scores_gemma":[0.99945915,0.000042818363,0.00003320712,0.0003625247,0.000033890028,0.00006843651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017093502,0.000094587616,0.00007726386,0.000101433296,0.000104242536,0.00010121099,0.00037147113,0.000031669297,0.000010429388],"category_scores_gemma":[0.000018243158,0.00007743699,0.00001997986,0.0005894365,0.000018372775,0.00023936218,0.00014921262,0.00012357012,0.00048935215],"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":[0.000010561837,0.00009192865,0.0064656143,0.000028441078,0.000020827878,0.000019258263,0.003460993,0.7314746,0.033534087,0.16716762,0.0011461382,0.056579947],"study_design_scores_gemma":[0.00013168826,0.000029459838,0.014721541,0.00000914626,0.0000018295796,0.0000045763513,0.000030452338,0.9834166,0.00091602345,0.00056917605,0.00005455634,0.0001149177],"about_ca_topic_score_codex":0.000510218,"about_ca_topic_score_gemma":0.000034249166,"teacher_disagreement_score":0.5628092,"about_ca_system_score_codex":0.000023486395,"about_ca_system_score_gemma":0.000031479474,"threshold_uncertainty_score":0.62897956},"labels":[],"label_agreement":null},{"id":"W4385572788","doi":"10.18653/v1/2022.conll-1.19","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Parsing; Computer science; Natural language processing; Meaning (existential); Representation (politics); Artificial intelligence; Bottom-up parsing; S-attributed grammar; Top-down parsing; Linguistics; Psychology; Philosophy","score_opus":0.02291593934030156,"score_gpt":0.3295676427037844,"score_spread":0.30665170336348285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385572788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4486877,0.000008232925,0.5365151,0.006116392,0.00014872297,0.00019615584,0.0000033875622,0.00040807843,0.007916238],"genre_scores_gemma":[0.9160696,2.783877e-7,0.08301357,0.0005441784,0.00004665842,0.00006699358,0.000014199808,0.000008617217,0.00023584944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988427,0.000073943236,0.0001706271,0.000423992,0.00032436266,0.00016434981],"domain_scores_gemma":[0.9991957,0.0001969822,0.000065357504,0.0004342873,0.000029502746,0.00007815854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020588089,0.00008000816,0.0000876954,0.000097270386,0.0003617857,0.00015515652,0.00059339433,0.000011933056,0.0003793619],"category_scores_gemma":[0.00006748112,0.000086009815,0.000034602173,0.00043466975,0.000008347976,0.0002054652,0.0005393754,0.00018116941,0.00022525691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003127454,0.00060855644,0.06557521,0.000011335459,0.00007570873,0.000054750864,0.010934288,0.20755832,0.2262465,0.061169695,0.013912581,0.41382176],"study_design_scores_gemma":[0.00030852083,0.00007833488,0.45330346,0.000005234633,0.000007342866,0.000009898616,0.00035241843,0.5295284,0.0074095167,0.006304284,0.0024126403,0.00027997504],"about_ca_topic_score_codex":0.004829047,"about_ca_topic_score_gemma":0.0000164689,"teacher_disagreement_score":0.46738195,"about_ca_system_score_codex":0.000055255638,"about_ca_system_score_gemma":0.000025114468,"threshold_uncertainty_score":0.7300106},"labels":[],"label_agreement":null},{"id":"W4385573082","doi":"10.18653/v1/2022.emnlp-main.92","title":"Generative Multi-hop Retrieval","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Samsung; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Encoder; Vector space model; Embedding; Information retrieval; Bottleneck; Generative grammar; Artificial intelligence; Data mining; Theoretical computer science","score_opus":0.02634004319737722,"score_gpt":0.2973385893803788,"score_spread":0.2709985461830016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028592711,0.000023449105,0.9599193,0.0060109575,0.00014575517,0.0001527049,0.0000027957353,0.00038021913,0.0047721597],"genre_scores_gemma":[0.7016108,4.5038254e-7,0.29487127,0.00090953696,0.000022703474,0.000040644434,0.0000034147797,0.0000049770993,0.0025361858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913573,0.0001116936,0.000103256396,0.0002887094,0.0002206683,0.00013992055],"domain_scores_gemma":[0.9993671,0.000057963738,0.000040696457,0.00044917502,0.000033205917,0.000051864292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021418348,0.00006489859,0.0000625751,0.000057092017,0.00043321736,0.000055208424,0.0007725716,0.000011447164,0.00040554086],"category_scores_gemma":[0.00003863504,0.00006293809,0.00003263249,0.0004454062,0.000014667685,0.00010241266,0.00066946144,0.00022199005,0.00015408732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012649916,0.0004973889,0.005786384,0.000004080814,0.00003485734,0.000017612669,0.0038638937,0.049398746,0.03211284,0.86724365,0.008258816,0.032769088],"study_design_scores_gemma":[0.00025224074,0.000045769153,0.00982752,2.38688e-7,0.0000012018176,0.000011318451,0.000039379134,0.97115374,0.0013526347,0.00086703117,0.016328808,0.00012012355],"about_ca_topic_score_codex":0.00016571686,"about_ca_topic_score_gemma":0.0000036836002,"teacher_disagreement_score":0.921755,"about_ca_system_score_codex":0.000058394187,"about_ca_system_score_gemma":0.000043976048,"threshold_uncertainty_score":0.4440388},"labels":[],"label_agreement":null},{"id":"W4385573711","doi":"10.18653/v1/2022.findings-emnlp.385","title":"Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Continuation; Computer science; Benchmark (surveying); Generalization; Distillation; Artificial intelligence; Limiting; Noise (video); Machine learning; Image (mathematics); Mathematics; Engineering; Programming language","score_opus":0.016878236703238153,"score_gpt":0.27409466346508604,"score_spread":0.25721642676184786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010885096,0.00004810163,0.9741973,0.0035623389,0.00017906904,0.0005740392,0.0000059973563,0.00018062074,0.010367431],"genre_scores_gemma":[0.93993264,0.0000036983727,0.05921784,0.00011283804,0.000036665882,0.00017471558,0.000057633024,0.000009675537,0.00045429138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876475,0.00025922188,0.00034160726,0.00028522866,0.00021425441,0.00013491171],"domain_scores_gemma":[0.99862677,0.00026401205,0.0003346592,0.0005369791,0.00022042565,0.000017156755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005064516,0.00010128108,0.00011941058,0.00006282913,0.0004576352,0.00006076936,0.00056313357,0.000028381392,0.00012591066],"category_scores_gemma":[0.00014292744,0.00008251058,0.00005561865,0.0006468294,0.000042640717,0.00042684612,0.0002878228,0.00016280806,0.000011274997],"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":[0.000011309176,0.0001536582,0.0010636118,0.00000883208,0.00001976645,4.9084985e-8,0.004837546,0.60954833,0.003970692,0.35228556,0.00050114136,0.0275995],"study_design_scores_gemma":[0.0003168105,0.00005723212,0.010696725,0.00000218206,0.000009707117,0.0000016670491,0.00012779055,0.9823396,0.00034817602,0.001410002,0.004592523,0.00009755996],"about_ca_topic_score_codex":0.00047242298,"about_ca_topic_score_gemma":0.000028722847,"teacher_disagreement_score":0.9290475,"about_ca_system_score_codex":0.000077173056,"about_ca_system_score_gemma":0.000062431616,"threshold_uncertainty_score":0.35198063},"labels":[],"label_agreement":null},{"id":"W4385573873","doi":"10.18653/v1/2022.emnlp-main.586","title":"Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; Leverhulme Trust","keywords":"Phrase; Computer science; Margin (machine learning); Artificial intelligence; Annotation; Object (grammar); Natural language processing; Perspective (graphical); Expectation–maximization algorithm; Maximization; Pattern recognition (psychology); Speech recognition; Machine learning; Maximum likelihood; Mathematics","score_opus":0.008977920109588727,"score_gpt":0.2370852657185742,"score_spread":0.22810734560898546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09660258,0.000008548746,0.90007645,0.0012006174,0.00005563721,0.0004881945,0.0000025796032,0.00037286457,0.0011925038],"genre_scores_gemma":[0.8449617,4.0915222e-7,0.15367623,0.00015442476,0.00002745344,0.0007451896,0.000043621956,0.000015099622,0.00037584445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890417,0.00011673064,0.00015223032,0.00037454968,0.00024814386,0.00020417124],"domain_scores_gemma":[0.9991745,0.0003380985,0.00010387988,0.0002193169,0.0001053121,0.000058927937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024316952,0.00010757017,0.00010950535,0.00012119577,0.00095216697,0.00012415765,0.00040485384,0.00001533759,0.00011523755],"category_scores_gemma":[0.00010980288,0.000102401136,0.000035115303,0.00049348106,0.000018533923,0.00032133076,0.00012460472,0.0001915164,0.000008987635],"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":[0.000118167714,0.00024878874,0.025184335,0.000022980674,0.00006835693,0.000005030418,0.0100078555,0.5806776,0.0060120644,0.33498418,0.0002757218,0.042394873],"study_design_scores_gemma":[0.0007982721,0.00024161853,0.010988118,0.0000034231737,0.000008040012,0.00000992474,0.0012571465,0.9847247,0.00018607418,0.00060276955,0.0010015672,0.00017832608],"about_ca_topic_score_codex":0.00017586174,"about_ca_topic_score_gemma":0.000010041604,"teacher_disagreement_score":0.74835914,"about_ca_system_score_codex":0.00010349057,"about_ca_system_score_gemma":0.00006953641,"threshold_uncertainty_score":0.73233944},"labels":[],"label_agreement":null},{"id":"W4385574225","doi":"10.18653/v1/2022.findings-emnlp.31","title":"Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Relevance (law); Lexicon; Generator (circuit theory); Training set; Labeled data; Natural language processing; Machine learning; Information retrieval","score_opus":0.03598622992703411,"score_gpt":0.30980805225086244,"score_spread":0.27382182232382835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385574225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3796904,0.000014980906,0.61548865,0.0015345849,0.00020474516,0.0005233831,0.0000074183104,0.00089441525,0.0016414012],"genre_scores_gemma":[0.66276467,3.5723815e-7,0.33616263,0.00050880166,0.000053036525,0.00016016346,0.000008473001,0.000013987802,0.00032789103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842334,0.00009957678,0.0002515269,0.00054175727,0.00033594313,0.0003478537],"domain_scores_gemma":[0.9987339,0.0004109571,0.00008490237,0.00058377726,0.00008318863,0.00010327537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006181504,0.00013916686,0.00016233587,0.00010235809,0.0006798501,0.00010647164,0.0011298751,0.000034102126,0.000133127],"category_scores_gemma":[0.00017767806,0.00014787681,0.00010251489,0.00045568857,0.000018480992,0.00015350999,0.00043210774,0.00027745584,0.000027196233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028667477,0.0010026912,0.00072100305,0.000080181795,0.00018735904,0.00001701876,0.0824364,0.047446582,0.17973866,0.22998822,0.001348542,0.45674667],"study_design_scores_gemma":[0.0010708681,0.00016169633,0.0006111771,0.0000016869906,0.0000073634014,0.000013269849,0.00046639892,0.9843068,0.007334538,0.0018498674,0.0039367937,0.00023953117],"about_ca_topic_score_codex":0.000061100116,"about_ca_topic_score_gemma":0.0000048402417,"teacher_disagreement_score":0.9368602,"about_ca_system_score_codex":0.000091493945,"about_ca_system_score_gemma":0.00023525541,"threshold_uncertainty_score":0.6030241},"labels":[],"label_agreement":null},{"id":"W4385574233","doi":"10.18653/v1/2022.findings-emnlp.519","title":"Lexi: Self-Supervised Learning of the UI Language","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Leverage (statistics); Natural language processing; Metadata; Artificial intelligence; Context (archaeology); Human–computer interaction; Task (project management); Information retrieval; World Wide Web","score_opus":0.006479628782001468,"score_gpt":0.2396702365762321,"score_spread":0.23319060779423062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385574233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8390237,0.000058692287,0.11898568,0.005485292,0.00014812112,0.00029162085,0.000001727435,0.0006636489,0.03534152],"genre_scores_gemma":[0.96614695,3.409239e-7,0.032408204,0.0002858396,0.000012311362,0.000039438015,8.52581e-7,0.000005872258,0.001100197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991603,0.00018417946,0.00011327852,0.00017556362,0.00025196504,0.00011472222],"domain_scores_gemma":[0.9992697,0.00008809672,0.00006587375,0.0005316511,0.000020560732,0.000024109313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024587425,0.00005520214,0.000066420165,0.000036943387,0.00033581958,0.000023105027,0.0011649387,0.0000109156035,0.00025178035],"category_scores_gemma":[0.000038742543,0.00004103621,0.00005420026,0.0004696889,0.000014690467,0.000059109698,0.0009174267,0.00029653378,0.000025043733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045648485,0.00037062788,0.08533011,0.000030963623,0.00004900255,0.0000038590747,0.02796168,0.07979141,0.032454483,0.70386106,0.0012767237,0.06886549],"study_design_scores_gemma":[0.00020358153,0.000039909737,0.042208094,0.0000015984866,0.000003980104,0.000009092057,0.00044105214,0.949474,0.0013588632,0.00042524634,0.005736899,0.00009773236],"about_ca_topic_score_codex":0.0006004856,"about_ca_topic_score_gemma":0.0000037577074,"teacher_disagreement_score":0.86968255,"about_ca_system_score_codex":0.0000281854,"about_ca_system_score_gemma":0.00004109564,"threshold_uncertainty_score":0.27568182},"labels":[],"label_agreement":null},{"id":"W4385612782","doi":"10.1145/3539618.3591903","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Test (biology); Multimedia; Content (measure theory); Information retrieval; Image retrieval; Content-based image retrieval; Image (mathematics); Artificial intelligence","score_opus":0.037569380739278235,"score_gpt":0.3233776406108255,"score_spread":0.2858082598715473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385612782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5381185,0.0000012520462,0.44454652,0.007941007,0.000297593,0.0008423575,0.000009726587,0.0022040063,0.006039053],"genre_scores_gemma":[0.8733532,0.0000025878549,0.11937,0.00044030056,0.0000875281,0.00007795948,0.000062395826,0.000018554078,0.0065874862],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985625,0.00006191894,0.00025933477,0.00052233244,0.00030662373,0.00028727157],"domain_scores_gemma":[0.99855447,0.0002947147,0.00007163797,0.00062257744,0.00021873107,0.00023788525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046275542,0.00013385636,0.00013331271,0.00028542042,0.00024213013,0.00022091779,0.00055705133,0.00006275869,0.0001552895],"category_scores_gemma":[0.0006129761,0.00012911907,0.000044350963,0.0017109853,0.000028622891,0.00045154354,0.00019448384,0.00014099761,0.0042899963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011549091,0.0009515777,0.10788206,0.000035539062,0.000052033338,0.0000349314,0.009466965,0.0021045671,0.5978154,0.017706845,0.067143746,0.19669089],"study_design_scores_gemma":[0.00035415,0.00026099372,0.32220507,0.000003653846,0.000004093616,0.000008507342,0.00006439194,0.6666416,0.008177719,0.00022464465,0.0018848409,0.00017035105],"about_ca_topic_score_codex":0.0010266588,"about_ca_topic_score_gemma":0.00009436182,"teacher_disagreement_score":0.664537,"about_ca_system_score_codex":0.0001157328,"about_ca_system_score_gemma":0.00009167993,"threshold_uncertainty_score":0.9964853},"labels":[],"label_agreement":null},{"id":"W4385784741","doi":"10.1007/978-3-319-08234-9_501-1","title":"Automated Image Captioning for the Visually Impaired","year":2023,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Multimodal Machine Learning Applications","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":"CNIB Foundation; Ontario Tech University","funders":"","keywords":"Closed captioning; Visually impaired; Computer science; Computer vision; Image (mathematics); Artificial intelligence; Human–computer interaction","score_opus":0.01395764660038844,"score_gpt":0.2692701808536056,"score_spread":0.25531253425321715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385784741","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":[0.00043329113,0.00084755634,0.96623737,0.0028280371,0.0010289181,0.0014096613,0.00008426911,0.0018301413,0.025300762],"genre_scores_gemma":[0.07323427,0.021972628,0.75357366,0.0021826348,0.0038381887,0.0010845269,0.00049462484,0.00080111425,0.14281838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984253,0.0000263531,0.00046133343,0.00054342585,0.00029668154,0.00024691026],"domain_scores_gemma":[0.9974531,0.0011286656,0.00039097652,0.00070302485,0.00023800456,0.00008624883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004082728,0.00032543694,0.00038856748,0.0002774724,0.00026721988,0.00017562044,0.00091902993,0.00019411507,0.0000040888876],"category_scores_gemma":[0.000033490673,0.000256776,0.00022531264,0.0001367897,0.00020218085,0.00012665,0.0004582074,0.00035280004,0.000012802409],"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":[0.000004106312,0.000014840907,0.00009641888,0.00009655842,0.0001394626,0.000003010761,0.0004888374,0.00021860434,0.0000044500516,0.9547811,0.0040583573,0.04009422],"study_design_scores_gemma":[0.00031195921,0.00017895737,0.015003395,0.00014564855,0.00006982198,0.000009624128,0.0000031812963,0.84828204,0.0000018224549,0.06730237,0.06830741,0.00038379326],"about_ca_topic_score_codex":0.000096711046,"about_ca_topic_score_gemma":0.000014533917,"teacher_disagreement_score":0.88747877,"about_ca_system_score_codex":0.000010358756,"about_ca_system_score_gemma":0.000083515624,"threshold_uncertainty_score":0.99998844},"labels":[],"label_agreement":null},{"id":"W4385832667","doi":"10.1007/978-3-031-39821-6_7","title":"Efficient Video Captioning with Frame Similarity-Based Filtering","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Frame (networking); Similarity (geometry); Task (project management); Feature (linguistics); Convolutional neural network; Convolution (computer science); Computer vision; Pattern recognition (psychology); Speech recognition; Artificial neural network; Natural language processing; Image (mathematics)","score_opus":0.017219776979267562,"score_gpt":0.2568358270065685,"score_spread":0.2396160500273009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385832667","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":[0.00065546355,0.000036295973,0.9942691,0.0020665054,0.000586834,0.00048802854,0.000006819962,0.0007806741,0.001110326],"genre_scores_gemma":[0.36944106,0.0000018319915,0.62910026,0.0010065596,0.00020240946,0.000039844093,0.000008915236,0.00006387538,0.00013525729],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955934,0.00004340553,0.00046785144,0.001903497,0.001234331,0.0007574796],"domain_scores_gemma":[0.99642336,0.00090648734,0.00032099767,0.0018800624,0.0002555931,0.00021350564],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009189797,0.000568093,0.00047665514,0.0010374049,0.00053656014,0.0007448134,0.003145352,0.0002814564,0.000017411365],"category_scores_gemma":[0.00014534855,0.00051281694,0.00011235635,0.0011914239,0.0005717149,0.00016474938,0.0011216732,0.0014367314,0.00016155654],"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":[0.0000035096432,0.000019152341,0.00012674383,0.0000336287,0.0000066767657,0.000046169454,0.0002985006,0.9260166,0.00015218229,0.009276878,0.0000030769118,0.06401683],"study_design_scores_gemma":[0.00024935327,0.000113983115,0.0010702827,0.0005177561,0.000007660852,0.000025060062,9.878221e-8,0.98400795,0.00030903207,0.012844149,0.00024575417,0.00060894265],"about_ca_topic_score_codex":0.00016906182,"about_ca_topic_score_gemma":0.000096185315,"teacher_disagreement_score":0.3687856,"about_ca_system_score_codex":0.0003413929,"about_ca_system_score_gemma":0.000604713,"threshold_uncertainty_score":0.9997323},"labels":[],"label_agreement":null},{"id":"W4386065347","doi":"10.1109/cvpr52729.2023.00646","title":"Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Computer science; Benchmark (surveying); Object (grammar); Generalization; Representation (politics); Natural language; Artificial intelligence; Action (physics); Domain (mathematical analysis); Path (computing); Semantics (computer science); State (computer science); Human–computer interaction; Programming language","score_opus":0.07991573117494452,"score_gpt":0.34829690584924206,"score_spread":0.26838117467429756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386065347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61952364,0.000084768755,0.3765788,0.0022667556,0.00012677569,0.0001878262,0.0000013167269,0.000957039,0.0002730552],"genre_scores_gemma":[0.9172843,0.000011071714,0.08224046,0.00017142369,0.00010117175,0.000055807166,0.000015718131,0.000022724653,0.00009732305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998204,0.0001874218,0.000276468,0.0005890664,0.0003861479,0.00035693226],"domain_scores_gemma":[0.99880683,0.00030578158,0.00009009719,0.00061427685,0.000029249039,0.00015375145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079412025,0.00019645371,0.00025813267,0.00028312457,0.0003852388,0.0002822753,0.00050915946,0.00006337713,0.000039743663],"category_scores_gemma":[0.00006912294,0.0001606702,0.000109323046,0.0012694924,0.000066305554,0.00067732943,0.00049959146,0.0003141163,0.00022847141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038629954,0.00045682915,0.011183497,0.00025946222,0.0016058559,0.00031553974,0.05001678,0.01763453,0.21917681,0.5006403,0.0008964942,0.19777533],"study_design_scores_gemma":[0.00023727473,0.00005016535,0.013487008,0.000021867656,0.0000865924,0.00003274475,0.00028353283,0.9734098,0.0028360812,0.009105304,0.00015281908,0.000296813],"about_ca_topic_score_codex":0.00033375784,"about_ca_topic_score_gemma":0.000008018678,"teacher_disagreement_score":0.95577526,"about_ca_system_score_codex":0.000063638996,"about_ca_system_score_gemma":0.00004843475,"threshold_uncertainty_score":0.6551941},"labels":[],"label_agreement":null},{"id":"W4386071509","doi":"10.1109/cvpr52729.2023.00690","title":"PACO: Parts and Attributes of Common Objects","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":62,"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; Object (grammar); Benchmark (surveying); Artificial intelligence; Code (set theory); Segmentation; Object detection; Information retrieval; Natural language processing; Computer vision; Pattern recognition (psychology); Set (abstract data type); Programming language; Geography","score_opus":0.021330160297669664,"score_gpt":0.2892003363021184,"score_spread":0.26787017600444873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386071509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93330836,0.000038646718,0.054114167,0.005578033,0.000057841375,0.00015708747,0.000003168275,0.0006598709,0.0060828137],"genre_scores_gemma":[0.9903898,0.0000070744504,0.009271326,0.0000783957,0.000008272894,0.00001132332,0.0000031999548,0.0000030025567,0.00022755211],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99953246,0.000026373631,0.00009453137,0.00014776539,0.00009164859,0.00010719989],"domain_scores_gemma":[0.99940836,0.00019930319,0.00003479341,0.000292625,0.000023244347,0.000041648596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015063302,0.00004588727,0.00008031131,0.000056006393,0.000052921652,0.00002729599,0.00023221238,0.000019749456,0.000007550742],"category_scores_gemma":[0.00003948042,0.000039462044,0.000014529267,0.00039189303,0.00002632219,0.000076704026,0.00021585087,0.000051543884,0.00007893367],"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":[0.0000024776373,0.000121943114,0.40282568,0.000070487156,0.000028948742,0.0000074728396,0.002155651,0.0021144047,0.0081872335,0.4752185,0.00906972,0.10019745],"study_design_scores_gemma":[0.00013240823,0.000033995675,0.71977526,0.000007808515,0.0000020307784,0.0000031804204,0.00002163342,0.2682069,0.0037456274,0.0068264194,0.0011611114,0.00008361696],"about_ca_topic_score_codex":0.00029618613,"about_ca_topic_score_gemma":0.000021974947,"teacher_disagreement_score":0.4683921,"about_ca_system_score_codex":0.0000034030409,"about_ca_system_score_gemma":0.0000097819775,"threshold_uncertainty_score":0.16092154},"labels":[],"label_agreement":null},{"id":"W4386076676","doi":"10.1109/cvpr52729.2023.00246","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Computer science; Consistency (knowledge bases); Generative grammar; Context (archaeology); Artificial intelligence; Task (project management); Sentence; Natural language processing; Visualization; Quality (philosophy); Generative model","score_opus":0.03342713523481007,"score_gpt":0.3042961115903501,"score_spread":0.27086897635554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386076676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37547925,0.000041360538,0.59175676,0.01942907,0.0008525903,0.00050351775,0.0000066393936,0.002889881,0.009040914],"genre_scores_gemma":[0.97631675,0.0000033945405,0.01675176,0.0010352916,0.00016688873,0.00013768139,0.0000833983,0.000013979748,0.0054908567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877673,0.00018926199,0.00014528853,0.00039878156,0.00027707574,0.00021286949],"domain_scores_gemma":[0.9991144,0.00015588658,0.00007325445,0.0004682325,0.00008911948,0.00009910208],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004886209,0.000115114926,0.00011200744,0.00018386704,0.00042214256,0.0001006964,0.00036307384,0.000056129553,0.00010114945],"category_scores_gemma":[0.00008750512,0.00011523827,0.000055986504,0.0004607781,0.000052695235,0.00017173152,0.00015813932,0.00020922483,0.002347181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069120724,0.00027908033,0.0018017117,0.00003916893,0.00010159965,0.000039891245,0.0018333974,0.0152808735,0.12530054,0.48048866,0.2118641,0.16296405],"study_design_scores_gemma":[0.0003318715,0.00004562481,0.030444324,0.0000035156065,0.00000630387,0.000008542167,0.00009379849,0.95067054,0.0016123019,0.00030024667,0.01626722,0.00021571659],"about_ca_topic_score_codex":0.00009518949,"about_ca_topic_score_gemma":0.000035022746,"teacher_disagreement_score":0.93538964,"about_ca_system_score_codex":0.000111659145,"about_ca_system_score_gemma":0.00008582836,"threshold_uncertainty_score":0.9984296},"labels":[],"label_agreement":null},{"id":"W4386159122","doi":"10.1109/icme55011.2023.00259","title":"CHAN: Cross-Modal Hybrid Attention Network for Temporal Language Grounding in Videos","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"China Postdoctoral Science Foundation","keywords":"Computer science; Modality (human–computer interaction); Modalities; Modal; Semantics (computer science); Sentence; Frame (networking); Key (lock); Artificial intelligence; Natural language processing; Word (group theory); Task (project management); Focus (optics); Speech recognition; Linguistics; Engineering","score_opus":0.02041856827068133,"score_gpt":0.34065249028803046,"score_spread":0.3202339220173491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386159122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53911144,0.000010453707,0.4582437,0.0011631026,0.00020087545,0.00032785983,0.0000027934905,0.0005193587,0.000420383],"genre_scores_gemma":[0.95013434,0.000001098969,0.047882594,0.00015428902,0.00027423695,0.00023211702,0.000060729042,0.000014504503,0.0012461075],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881214,0.000040528783,0.00022059894,0.0003896258,0.00015415132,0.00038297946],"domain_scores_gemma":[0.9992873,0.00017410555,0.00006927192,0.0003816065,0.000031346855,0.00005638353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006786029,0.00010500047,0.00011998376,0.00014385808,0.0001813021,0.0002128692,0.0005100369,0.000035791403,0.000013417701],"category_scores_gemma":[0.00006753462,0.00010379748,0.00006495661,0.0007319894,0.000019460436,0.00032170338,0.00020220826,0.00012824828,0.0002109927],"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":[0.000026678901,0.00013283495,0.6175849,0.00009093495,0.00003297441,0.00004282747,0.0013893157,0.038114347,0.003853695,0.23816873,0.0072615147,0.09330128],"study_design_scores_gemma":[0.0003414419,0.000022175731,0.32047862,0.00001146162,0.0000012489221,0.0000033275126,0.000021861082,0.6745865,0.00007191549,0.003610168,0.00072994956,0.000121335645],"about_ca_topic_score_codex":0.0010610921,"about_ca_topic_score_gemma":0.00014230427,"teacher_disagreement_score":0.63647217,"about_ca_system_score_codex":0.000051110954,"about_ca_system_score_gemma":0.000021451062,"threshold_uncertainty_score":0.42327383},"labels":[],"label_agreement":null},{"id":"W4386162736","doi":"10.1145/3617592","title":"Deep Learning Approaches on Image Captioning: A Review","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Multimodal Machine Learning Applications","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":"McMaster University","funders":"","keywords":"Closed captioning; Computer science; Deep learning; Artificial intelligence; Modalities; Context (archaeology); Field (mathematics); Natural language processing; Image (mathematics); Machine learning","score_opus":0.17702160835122344,"score_gpt":0.3854094199385489,"score_spread":0.20838781158732544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386162736","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":[8.06847e-7,0.73121136,0.2647992,0.00027175533,0.00025205957,0.0009254103,0.0000025606064,0.0016306087,0.0009062338],"genre_scores_gemma":[0.00003768383,0.95009017,0.048593346,0.000096996344,0.00027746064,0.00016974735,0.0002464404,0.00016126463,0.00032686268],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902976,0.0054466166,0.0011961072,0.0016641825,0.0006402469,0.0007552553],"domain_scores_gemma":[0.9904139,0.0050650397,0.0011674849,0.0030193918,0.00013552251,0.00019867765],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008427287,0.00079573446,0.0020979606,0.0004325797,0.00064607983,0.00043629913,0.004868736,0.00028611036,0.000013844952],"category_scores_gemma":[0.00529073,0.00072416785,0.00068465545,0.0024589384,0.000078456505,0.0001568771,0.0024849158,0.002233828,0.0039974004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.431405e-8,0.00003721167,0.000015644759,0.016510759,0.000083846084,0.000012773422,0.00006745695,0.00091540767,2.7381683e-8,0.0014848046,0.00029497565,0.980577],"study_design_scores_gemma":[0.00020926197,0.0001228636,0.0008468081,0.10544641,0.00037075032,0.000120995355,0.000007399732,0.20273896,1.3860878e-7,0.00045083844,0.68771863,0.0019669596],"about_ca_topic_score_codex":0.00022048388,"about_ca_topic_score_gemma":0.0000074894997,"teacher_disagreement_score":0.97861004,"about_ca_system_score_codex":0.00019895376,"about_ca_system_score_gemma":0.00020342154,"threshold_uncertainty_score":0.99952096},"labels":[],"label_agreement":null},{"id":"W4386243186","doi":"10.1109/crv60082.2023.00048","title":"Few-Shot Personality-Specific Image Captioning via Meta-Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; University of Manitoba","funders":"","keywords":"Closed captioning; Computer science; Focus (optics); Benchmark (surveying); Shot (pellet); Set (abstract data type); Artificial intelligence; Big Five personality traits; Machine learning; Image (mathematics); Personality; Information retrieval","score_opus":0.06926265009916809,"score_gpt":0.3147886427505567,"score_spread":0.24552599265138858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386243186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030671598,0.00007631589,0.9350541,0.0069679534,0.00012495981,0.00019243953,0.0000014018675,0.0026138024,0.024297394],"genre_scores_gemma":[0.86992216,0.000013131038,0.12575363,0.00020938262,0.00009099373,0.000109371955,0.000019312696,0.00002289688,0.0038591118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981899,0.00018613374,0.0002471246,0.0006026224,0.00038225975,0.00039191387],"domain_scores_gemma":[0.99877095,0.00028773615,0.00009431458,0.00061928475,0.00010039703,0.0001272886],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00081258354,0.00018157122,0.0002293536,0.00019800503,0.0005255695,0.0003437652,0.0008162135,0.000054603115,0.00084591337],"category_scores_gemma":[0.00008131597,0.00016169262,0.00018877852,0.0012252108,0.0000522281,0.00042041947,0.00036058656,0.00043249212,0.0048521743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012007276,0.0002606816,0.012894967,0.00008852224,0.001118973,0.00010347586,0.010959677,0.049651086,0.13684492,0.6630389,0.018212419,0.10681434],"study_design_scores_gemma":[0.00025724093,0.000037664722,0.06952807,0.000005248514,0.000059404065,0.000028817358,0.00014185555,0.8772398,0.00083651807,0.0034074748,0.048005376,0.00045250094],"about_ca_topic_score_codex":0.00062811363,"about_ca_topic_score_gemma":0.000010982475,"teacher_disagreement_score":0.83925056,"about_ca_system_score_codex":0.000046545603,"about_ca_system_score_gemma":0.00002520376,"threshold_uncertainty_score":0.9959227},"labels":[],"label_agreement":null},{"id":"W4386249615","doi":"10.1109/crv60082.2023.00034","title":"Naive Scene Graphs: How Visual is Modern Visual Relationship Detection?","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Artificial intelligence; Scene graph; Categorical variable; Naive Bayes classifier; Pixel; Bounding overwatch; Pattern recognition (psychology); Classifier (UML); Object detection; Graph; Computer vision; Machine learning; Theoretical computer science; Support vector machine","score_opus":0.02509051419035251,"score_gpt":0.3185390179645395,"score_spread":0.29344850377418696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386249615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32807085,0.000009825178,0.66316533,0.005800258,0.0001335505,0.00019803202,0.0000013851533,0.0015722582,0.0010485164],"genre_scores_gemma":[0.9851903,0.000003677399,0.012326565,0.00034716667,0.00005816864,0.00009897,0.000008298272,0.000020450645,0.0019464482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847186,0.00009890304,0.00017821293,0.00055895955,0.00036575375,0.00032629614],"domain_scores_gemma":[0.99887073,0.00030266718,0.00008451438,0.00049075915,0.00011887055,0.00013246838],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000292324,0.00016065536,0.00012605774,0.00037799415,0.0004757291,0.00026381668,0.0005489148,0.00009768217,0.000028314127],"category_scores_gemma":[0.00015645244,0.00015710152,0.00009279902,0.0019531837,0.000046407367,0.00044925063,0.00026631018,0.00030099342,0.0012164819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028500135,0.00048760267,0.23454121,0.00006368999,0.00015317161,0.00002178089,0.005420691,0.0075566582,0.022051917,0.1883177,0.007248908,0.53410816],"study_design_scores_gemma":[0.00015495997,0.00005446407,0.22215618,0.0000039819433,0.000004251603,0.0000048784427,0.00003149811,0.7597622,0.0014653417,0.01594209,0.00026120426,0.00015890664],"about_ca_topic_score_codex":0.00023649348,"about_ca_topic_score_gemma":0.000030758816,"teacher_disagreement_score":0.75220555,"about_ca_system_score_codex":0.000045084376,"about_ca_system_score_gemma":0.000044366316,"threshold_uncertainty_score":0.9995612},"labels":[],"label_agreement":null},{"id":"W4386566765","doi":"10.18653/v1/2023.eacl-main.185","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Samsung; Canadian Institute for Advanced Research","keywords":"Computer science; Adaptation (eye); Artificial intelligence; Computational linguistics; Association (psychology); Shot (pellet); Natural language processing; Speech recognition; Psychology; Neuroscience; Chemistry","score_opus":0.043569357639590814,"score_gpt":0.3403577905972081,"score_spread":0.2967884329576173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386566765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35773626,0.0000067528363,0.64017516,0.0005825993,0.000045562138,0.0006157326,0.000008140525,0.00042886546,0.00040094464],"genre_scores_gemma":[0.7489352,5.3256235e-7,0.25048837,0.000035611778,0.000020676238,0.00019990516,0.000028815251,0.000014456833,0.00027638816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984959,0.000065157146,0.00036173282,0.0004646202,0.00030784972,0.00030477776],"domain_scores_gemma":[0.99843186,0.0005986953,0.00017222065,0.0005834356,0.00013602944,0.00007775396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059975876,0.00014141008,0.00017853199,0.0002120596,0.00014820053,0.000078454636,0.0006411629,0.00005952225,0.000008221476],"category_scores_gemma":[0.00020030478,0.00012711335,0.00009126877,0.00076256413,0.00003461654,0.00019105022,0.00020503403,0.000104919905,0.000024765668],"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":[0.000010914604,0.00009970641,0.000041093343,0.000047450558,0.000011406494,6.9663e-7,0.0048646023,0.89801925,0.007824316,0.041717283,0.00007350539,0.04728977],"study_design_scores_gemma":[0.00039447905,0.00012178728,0.0031179849,0.000023416982,0.0000058342007,0.0000014952888,0.00028446366,0.99140894,0.0013037713,0.003157304,0.00003799047,0.00014250579],"about_ca_topic_score_codex":0.0005109547,"about_ca_topic_score_gemma":0.000014064752,"teacher_disagreement_score":0.391199,"about_ca_system_score_codex":0.000030819487,"about_ca_system_score_gemma":0.00007258593,"threshold_uncertainty_score":0.5183532},"labels":[],"label_agreement":null},{"id":"W4386978004","doi":"10.48550/arxiv.2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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. Stephen's University","funders":"National Natural Science Foundation of China","keywords":"Distillation; Computer science; Inheritance (genetic algorithm); Modal; Artificial intelligence; Feature (linguistics); AKA; Machine learning; Transferability; Code (set theory); Scratch; Image (mathematics); Pattern recognition (psychology); Programming language; Chemistry; Chromatography","score_opus":0.08317322424467298,"score_gpt":0.21212730965512777,"score_spread":0.12895408541045478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386978004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40672925,0.000025737663,0.591271,0.00036693687,0.00028425612,0.00021373566,0.000008966738,0.00054208847,0.00055804825],"genre_scores_gemma":[0.99082255,0.000106017564,0.008361423,0.00004890626,0.000098188924,0.000002932722,0.000025614094,0.000026892398,0.00050746254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805516,0.00015042153,0.00020781637,0.0012043394,0.00009510739,0.00028713455],"domain_scores_gemma":[0.998062,0.00025467438,0.00030184054,0.0011303975,0.00010615997,0.00014492265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027736297,0.00027315927,0.00026287048,0.00020343639,0.00027852086,0.0001460306,0.0011200384,0.00023955764,0.000008910362],"category_scores_gemma":[0.00008487624,0.00033562415,0.00009592927,0.0006153628,0.00010407563,0.00025781314,0.0020699278,0.0007028929,0.00016247366],"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":[0.000035337758,0.00016899916,0.31875834,0.00031635302,0.00016713455,0.000179482,0.0013002823,0.38342422,0.00036268536,0.27880713,0.0003914956,0.016088508],"study_design_scores_gemma":[0.00018039194,0.00001180118,0.16349074,0.00005663206,0.000024258543,0.0000027244157,0.000009196989,0.78812385,0.000017835975,0.047433574,0.00033611024,0.00031287887],"about_ca_topic_score_codex":0.00074432197,"about_ca_topic_score_gemma":0.00013238956,"teacher_disagreement_score":0.5840933,"about_ca_system_score_codex":0.00013938356,"about_ca_system_score_gemma":0.00006827656,"threshold_uncertainty_score":0.9999096},"labels":[],"label_agreement":null},{"id":"W4387076386","doi":"10.48550/arxiv.2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":20,"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":"Institute for Catastrophic Loss Reduction","keywords":"Perception; Computer science; Benchmark (surveying); Construct (python library); Correctness; Artificial intelligence; Softmax function; Pipeline (software); Quality (philosophy); Foundation (evidence); Visual perception; Natural language processing; Machine learning; Psychology; Deep learning; Programming language","score_opus":0.1809078712691692,"score_gpt":0.25629417249861564,"score_spread":0.07538630122944642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387076386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17060119,0.000004961969,0.8256488,0.00060660054,0.0005279896,0.0009837555,0.00005317152,0.00054643495,0.0010270887],"genre_scores_gemma":[0.9614499,0.000048414306,0.034912623,0.00018641462,0.00014640231,0.00003267336,0.00028346942,0.00004793604,0.002892123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728227,0.00013815633,0.00028519146,0.0017044717,0.00017150387,0.00041842152],"domain_scores_gemma":[0.99702096,0.00035935958,0.0003442711,0.0018247213,0.00026778155,0.00018292866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004070057,0.00038870523,0.0003330888,0.00048558606,0.00037759825,0.00024531127,0.0020497618,0.00032919727,0.00001766852],"category_scores_gemma":[0.00008019755,0.0004585063,0.00028284825,0.0006977989,0.00006404803,0.00045998453,0.0015818505,0.00060487294,0.00034754994],"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":[0.000020349105,0.000089274195,0.00007777896,0.000051073588,0.00002935087,0.000009664541,0.00013043357,0.6483781,0.000072467876,0.3471719,0.00043698883,0.0035326248],"study_design_scores_gemma":[0.00037624236,0.0000716177,0.0024314858,0.00007536744,0.000026790964,6.241773e-7,0.0000064419532,0.73874366,0.00004748438,0.25757614,0.000299802,0.00034432387],"about_ca_topic_score_codex":0.00067851035,"about_ca_topic_score_gemma":0.000047963287,"teacher_disagreement_score":0.79084873,"about_ca_system_score_codex":0.0003355673,"about_ca_system_score_gemma":0.00021621372,"threshold_uncertainty_score":0.9997867},"labels":[],"label_agreement":null},{"id":"W4387389875","doi":"10.48550/arxiv.2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Leverage (statistics); Computer science; Metric (unit); Machine learning; Proxy (statistics); Question answering; Task (project management); Artificial intelligence; Set (abstract data type); Context (archaeology); Data mining; Information retrieval","score_opus":0.13621283737109485,"score_gpt":0.26115521070933334,"score_spread":0.12494237333823849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387389875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40839982,0.000023009512,0.5899733,0.00004968529,0.00019870869,0.00039814354,0.000012043769,0.00069990166,0.0002454061],"genre_scores_gemma":[0.9724457,0.0000060241746,0.027082292,0.000039156443,0.00006483164,0.000006115744,0.00004449295,0.000036463196,0.00027489293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977291,0.00029238136,0.00023212396,0.0011330453,0.00021742714,0.0003959234],"domain_scores_gemma":[0.9975131,0.00013839189,0.0003732724,0.0016497603,0.00020051506,0.00012493605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009868939,0.00027769344,0.00026562973,0.00038433576,0.00027505867,0.00018366828,0.0016532647,0.00023444004,0.00002726082],"category_scores_gemma":[0.00012516761,0.0003429442,0.00015898337,0.00076922245,0.0000339446,0.00047054896,0.002483519,0.0006379568,0.00018533091],"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":[0.0000012787616,0.000044277167,0.00041014765,0.00007773249,0.000036946763,0.000031123105,0.00068893505,0.95486724,0.00021195196,0.040073093,0.000016867867,0.0035404097],"study_design_scores_gemma":[0.0003248446,0.000008319071,0.0014650112,0.00007222067,0.00009604236,0.0000021015924,0.0000952235,0.9642697,0.000027614386,0.033311732,0.0000037289626,0.00032343893],"about_ca_topic_score_codex":0.002631533,"about_ca_topic_score_gemma":0.00008576987,"teacher_disagreement_score":0.5640459,"about_ca_system_score_codex":0.00046852868,"about_ca_system_score_gemma":0.00035122287,"threshold_uncertainty_score":0.99990225},"labels":[],"label_agreement":null},{"id":"W4387969760","doi":"10.1145/3581783.3612863","title":"Deep Video Understanding with Video-Language Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Process (computing); Artificial intelligence; Selection (genetic algorithm); Matching (statistics); Modal; Graph; Dual (grammatical number); Multimedia; Machine learning; Human–computer interaction; Natural language processing; Theoretical computer science; Programming language","score_opus":0.035195777888689314,"score_gpt":0.2896068538903968,"score_spread":0.2544110760017075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387969760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013418221,0.000007657529,0.96368957,0.0032245796,0.00002391288,0.00013250479,4.846032e-7,0.0013609079,0.018142158],"genre_scores_gemma":[0.86274606,0.0000016702588,0.1358302,0.00034609577,0.00001678187,0.00003363221,0.0000036202607,0.000013388156,0.0010085457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989976,0.000024424695,0.00011245239,0.00035859164,0.00024067464,0.00026620083],"domain_scores_gemma":[0.9991187,0.0001243315,0.00004022647,0.0006033135,0.000021904812,0.00009151128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001920451,0.00010674269,0.00009241733,0.00015007297,0.00018479044,0.00014058784,0.00059620664,0.000032463824,0.000025910505],"category_scores_gemma":[0.000028543684,0.000084452746,0.000028243145,0.0008648836,0.000029714995,0.00025174528,0.00020618818,0.00013933716,0.00043293517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033306635,0.00002028715,0.0010183175,0.00000953229,0.000014556248,0.000013181587,0.0027156924,0.37425143,0.0011776623,0.61532193,0.0008590276,0.004595075],"study_design_scores_gemma":[0.00017699822,0.000018014569,0.0013072989,0.0000064185188,0.0000027374983,0.000005384144,0.00024724644,0.98811877,0.00012388012,0.009816114,0.00004668882,0.00013044241],"about_ca_topic_score_codex":0.0002184631,"about_ca_topic_score_gemma":0.000095822215,"teacher_disagreement_score":0.84932786,"about_ca_system_score_codex":0.00007802131,"about_ca_system_score_gemma":0.000038805887,"threshold_uncertainty_score":0.55646497},"labels":[],"label_agreement":null},{"id":"W4388937551","doi":"10.1109/icccnt56998.2023.10307136","title":"Assistive Application for the Visually Impaired using Machine Learning and Image Processing","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Horizon College and Seminary","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Benchmark (surveying); Metric (unit); Task (project management); Process (computing); Visually impaired; DECIPHER; Visualization; Image (mathematics); Image processing; Computer vision; Natural language processing; Machine learning; Pattern recognition (psychology); Human–computer interaction","score_opus":0.02367214711049958,"score_gpt":0.34182813294411823,"score_spread":0.31815598583361865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388937551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032174926,0.00006630707,0.9639375,0.0024286967,0.000019305247,0.00054431526,0.0000018557607,0.0006515335,0.0001755492],"genre_scores_gemma":[0.8531531,0.0000066307525,0.1462906,0.00008660831,0.00004312377,0.00021290511,0.000010037219,0.000016024993,0.00018093929],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991011,0.0000440036,0.0001520908,0.000354859,0.00013802406,0.00020991072],"domain_scores_gemma":[0.99909884,0.0004191536,0.00011079962,0.0002198895,0.00010313809,0.00004815601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005296297,0.00010772105,0.000094946314,0.00008135202,0.00077781786,0.00024232188,0.0003475681,0.000033313052,0.0000024690833],"category_scores_gemma":[0.00014753557,0.00007756436,0.000032938173,0.00060470175,0.000051233696,0.00023670001,0.00022753896,0.00014781769,0.000018693907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001829093,0.000063005114,0.030939693,0.000111375244,0.000042841035,0.0000012103333,0.0015937013,0.0075556333,0.11008758,0.023671785,0.00010222924,0.82581264],"study_design_scores_gemma":[0.00016382676,0.000020310825,0.040668767,0.0000062353115,0.000009592121,0.000004878691,0.00005045374,0.9567686,0.00041844492,0.0005956218,0.0011939442,0.00009936338],"about_ca_topic_score_codex":0.0003777405,"about_ca_topic_score_gemma":0.000017761173,"teacher_disagreement_score":0.9492129,"about_ca_system_score_codex":0.000027607168,"about_ca_system_score_gemma":0.00004776324,"threshold_uncertainty_score":0.59824246},"labels":[],"label_agreement":null},{"id":"W4389285856","doi":"10.1007/978-3-031-48796-5_10","title":"StableYolo: Optimizing Image Generation for Large Language Models","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 Waterloo","funders":"","keywords":"Computer science; Image (mathematics); Inference; Process (computing); Artificial intelligence; Computation; Bounded function; Approx; Baseline (sea); Image quality; Computer vision; Algorithm; Programming language; Operating system; Mathematics","score_opus":0.02895945149165552,"score_gpt":0.2932319525451203,"score_spread":0.2642725010534648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389285856","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":[0.00008965445,0.00013258557,0.9951405,0.0010922515,0.000839685,0.0008138583,0.000040073206,0.00053280813,0.0013186076],"genre_scores_gemma":[0.05616044,0.000019621271,0.94148153,0.0007438355,0.0006090126,0.000099362864,0.00006262852,0.00007186899,0.00075169664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964741,0.00003251271,0.00045731093,0.00162566,0.0006644436,0.000745967],"domain_scores_gemma":[0.99729025,0.0005190783,0.00026828167,0.0015039548,0.00027705426,0.00014139853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001266573,0.0004381765,0.00041491102,0.0007068659,0.00046930966,0.0007271974,0.0026156357,0.0002632142,0.000009425294],"category_scores_gemma":[0.00014389279,0.00043490122,0.0001386921,0.0005873291,0.00015534056,0.00080218667,0.0011536696,0.0006617069,0.00007055571],"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":[0.000003336412,0.0000329451,0.0000052002833,0.000057210502,0.00001405043,0.00002296615,0.0024741478,0.61354303,0.0037286114,0.19192052,0.00009837249,0.18809958],"study_design_scores_gemma":[0.00025172948,0.00005427451,0.000010341807,0.00007897933,0.0000063690695,0.000008752293,3.8175557e-7,0.922767,0.0009109441,0.07527845,0.00020442618,0.0004283814],"about_ca_topic_score_codex":0.000081847626,"about_ca_topic_score_gemma":0.00009217717,"teacher_disagreement_score":0.30922392,"about_ca_system_score_codex":0.0002379413,"about_ca_system_score_gemma":0.00033639438,"threshold_uncertainty_score":0.9998103},"labels":[],"label_agreement":null},{"id":"W4389518385","doi":"10.18653/v1/2023.arabicnlp-1.1","title":"Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Closed captioning; Computer science; Fluency; Natural language processing; Artificial intelligence; Arabic; Language model; Encoder; Image (mathematics); Generative model; Speech recognition; Generative grammar; Linguistics","score_opus":0.012239302839231678,"score_gpt":0.3186121580308731,"score_spread":0.3063728551916414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10087356,0.0000073979386,0.89408046,0.002261915,0.00002187818,0.0003153806,0.0000044850303,0.00080134487,0.0016336081],"genre_scores_gemma":[0.5824144,0.0000010076253,0.41534418,0.00023010293,0.000021124131,0.0002013403,0.000012110875,0.000015476015,0.0017602984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892074,0.000017799644,0.00015182112,0.00043889385,0.00017984539,0.0002908781],"domain_scores_gemma":[0.99903864,0.00014959018,0.000059553407,0.00058674475,0.000081940445,0.00008351441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025526845,0.00012406959,0.00011463755,0.00013488515,0.00021989684,0.00016452969,0.0005411517,0.000039151633,0.00001786771],"category_scores_gemma":[0.000054124193,0.00009802474,0.00004660842,0.000489696,0.000030856158,0.00030246144,0.00016030889,0.00011325424,0.0003173376],"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":[0.000038048685,0.00021162478,0.0025058326,0.000097248776,0.00006916108,0.000020546498,0.012112452,0.7216381,0.04029589,0.11009529,0.0087894425,0.1041264],"study_design_scores_gemma":[0.00031474157,0.00003594713,0.0048734024,0.000014612492,0.0000043078267,0.000003524679,0.000060103557,0.9926086,0.00024070728,0.0015922076,0.00009882624,0.00015303111],"about_ca_topic_score_codex":0.00012496363,"about_ca_topic_score_gemma":0.00003151642,"teacher_disagreement_score":0.4815408,"about_ca_system_score_codex":0.000025760612,"about_ca_system_score_gemma":0.00005253158,"threshold_uncertainty_score":0.40788388},"labels":[],"label_agreement":null},{"id":"W4389518749","doi":"10.18653/v1/2023.emnlp-main.297","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); Image retrieval; Search engine; Image (mathematics); Ranking (information retrieval); Artificial intelligence","score_opus":0.03877009136996899,"score_gpt":0.3183061662962966,"score_spread":0.2795360749263276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6498493,0.000009783316,0.32528776,0.009099186,0.00034272482,0.0005121695,0.000014969057,0.002384763,0.012499338],"genre_scores_gemma":[0.93091816,0.000008477702,0.06547994,0.00029008044,0.00009712813,0.00006994049,0.000015357062,0.000016230937,0.003104696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835527,0.00008848147,0.00020462283,0.0005021266,0.00043240405,0.0004170923],"domain_scores_gemma":[0.99873805,0.00016806427,0.00004058814,0.00077873905,0.000115268995,0.00015930684],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003341877,0.00013760266,0.00013956983,0.00020361152,0.00020716747,0.00024525775,0.0010897121,0.000054948818,0.00026307066],"category_scores_gemma":[0.00008207939,0.00012319844,0.0000899921,0.0007983185,0.00006580144,0.00038957945,0.0007747915,0.00027749964,0.005401521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020355701,0.00066955044,0.20125853,0.00011642169,0.00015968195,0.000111734254,0.0033657558,0.0055601993,0.30242577,0.37090796,0.05359483,0.06180922],"study_design_scores_gemma":[0.00035846359,0.000019631258,0.2524323,0.000005766991,0.0000022141785,0.0000023989107,0.000029943809,0.7439229,0.0006173651,0.00021577836,0.002260788,0.00013248133],"about_ca_topic_score_codex":0.0016197189,"about_ca_topic_score_gemma":0.00006058956,"teacher_disagreement_score":0.73836267,"about_ca_system_score_codex":0.000049931703,"about_ca_system_score_gemma":0.000076675555,"threshold_uncertainty_score":0.9953729},"labels":[],"label_agreement":null},{"id":"W4389519026","doi":"10.18653/v1/2023.emnlp-main.496","title":"GD-COMET: A Geo-Diverse Commonsense Inference Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Comet; Commonsense knowledge; Inference; Task (project management); Computer science; Commonsense reasoning; Range (aeronautics); Natural language processing; Artificial intelligence; Data science; Knowledge-based systems; Astronomy; Physics; Engineering; Systems engineering","score_opus":0.05572125529200657,"score_gpt":0.3378330340009139,"score_spread":0.28211177870890736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21819177,0.0000032897,0.7633341,0.004812294,0.00005689657,0.00015111809,0.0000047601034,0.0016837504,0.011762014],"genre_scores_gemma":[0.9059949,0.0000046448254,0.0914844,0.0005248067,0.000013532048,0.000036918904,0.00000573939,0.000008108053,0.0019269335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989556,0.000046973066,0.00015224452,0.00034568566,0.00022526535,0.00027422726],"domain_scores_gemma":[0.9986537,0.00026727887,0.000047295485,0.00085535034,0.00006297279,0.0001133924],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023938582,0.00011298279,0.00011358471,0.00019104344,0.00018799033,0.00011099815,0.00094198354,0.00004610623,0.00004125693],"category_scores_gemma":[0.000120752215,0.00010416859,0.000048755042,0.0010045475,0.000038783845,0.00020904325,0.00061735604,0.00019077756,0.0033286244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040313103,0.00010665589,0.012260469,0.000014508116,0.000020478836,0.000020193484,0.001956016,0.2825129,0.0023983277,0.6438255,0.011791528,0.045089412],"study_design_scores_gemma":[0.00013396247,0.000011305691,0.024621379,0.000003160257,0.0000020900718,0.0000026225869,0.000019796098,0.9650005,0.00008732372,0.009336124,0.0006509504,0.000130777],"about_ca_topic_score_codex":0.00084928365,"about_ca_topic_score_gemma":0.00004739739,"teacher_disagreement_score":0.68780315,"about_ca_system_score_codex":0.000022562177,"about_ca_system_score_gemma":0.000058607046,"threshold_uncertainty_score":0.9974474},"labels":[],"label_agreement":null},{"id":"W4389520066","doi":"10.18653/v1/2023.findings-emnlp.46","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Similarity (geometry); Sparse approximation; Artificial intelligence; Frame (networking); Representation (politics); Space (punctuation); Pattern recognition (psychology); Information retrieval; Image (mathematics)","score_opus":0.025579838549131522,"score_gpt":0.2862182801294178,"score_spread":0.26063844158028626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389520066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28788283,0.000039310427,0.69447184,0.008978336,0.00019127803,0.0003964721,0.0000042825136,0.0044415975,0.0035940902],"genre_scores_gemma":[0.9297216,0.000013039215,0.058174778,0.0004020397,0.000046359342,0.000031541134,0.000046180332,0.000029134946,0.0115353605],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981127,0.00015957636,0.00027333945,0.00062834006,0.00035750985,0.00046853078],"domain_scores_gemma":[0.99861264,0.0003342621,0.00007219345,0.00070993404,0.000085610896,0.00018538025],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059423066,0.0001888266,0.00018290519,0.00018248433,0.0003378547,0.0002080809,0.0010671295,0.00008980622,0.00016853496],"category_scores_gemma":[0.0004860012,0.00017957205,0.00008688925,0.0016747742,0.000045393524,0.00028596047,0.00045346114,0.00041247328,0.0041527734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087970686,0.0008998448,0.13865511,0.00012300056,0.00020313481,0.00009475227,0.009927029,0.032683708,0.3746163,0.09090308,0.13918935,0.21261673],"study_design_scores_gemma":[0.00064445817,0.000046109937,0.028824583,0.000006552232,0.0000036911804,0.000003816486,0.000052688287,0.9505155,0.0014948382,0.00020788437,0.017947655,0.00025219563],"about_ca_topic_score_codex":0.00045035232,"about_ca_topic_score_gemma":0.00000890897,"teacher_disagreement_score":0.91783184,"about_ca_system_score_codex":0.00004097077,"about_ca_system_score_gemma":0.00004698812,"threshold_uncertainty_score":0.9966226},"labels":[],"label_agreement":null},{"id":"W4389520202","doi":"10.18653/v1/2023.findings-emnlp.60","title":"InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Pooling; Modal; Graph; Representation (politics); Convolution (computer science); Theoretical computer science; Algorithm; Artificial intelligence; Artificial neural network","score_opus":0.022764599988271933,"score_gpt":0.2924877190307626,"score_spread":0.2697231190424907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389520202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50403494,0.000015209708,0.48492357,0.0037682669,0.00028821485,0.00024474575,0.000010557742,0.0021019252,0.0046125674],"genre_scores_gemma":[0.9751423,0.000010104214,0.02046536,0.0005424511,0.000056054047,0.000023609779,0.000052876403,0.000015494164,0.003691748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985879,0.000064245076,0.00021610806,0.0004799896,0.0003164054,0.0003353648],"domain_scores_gemma":[0.9989327,0.000118502794,0.000074056756,0.0006403568,0.00009597089,0.00013837402],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041266842,0.00013156452,0.00011344433,0.00017046586,0.00027181904,0.00021347894,0.00080405147,0.000093007824,0.00007276518],"category_scores_gemma":[0.00014256289,0.00012849552,0.00006536306,0.0016693472,0.000103552884,0.00042045783,0.00032932224,0.00023758913,0.0019113441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047867972,0.00030533603,0.16192207,0.00006134,0.000082563885,0.000023506354,0.0014823042,0.079066135,0.048511792,0.35897216,0.33781546,0.011709461],"study_design_scores_gemma":[0.00042849718,0.000037513924,0.096256495,0.0000040723985,0.0000030570386,0.000004922989,0.000015577032,0.89226544,0.0013028262,0.004052045,0.005405332,0.00022420297],"about_ca_topic_score_codex":0.0007230179,"about_ca_topic_score_gemma":0.000020516658,"teacher_disagreement_score":0.81319934,"about_ca_system_score_codex":0.00005147575,"about_ca_system_score_gemma":0.000052454317,"threshold_uncertainty_score":0.9988658},"labels":[],"label_agreement":null},{"id":"W4389520321","doi":"10.18653/v1/2023.emnlp-main.735","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Situated; Natural park; Reading (process); Natural language; Natural language processing; Linguistics; Artificial intelligence; Philosophy; Ecology","score_opus":0.02192735941460207,"score_gpt":0.2936765613624693,"score_spread":0.2717492019478672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389520321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31404805,0.00004300604,0.6821197,0.00043043846,0.000016209116,0.00018171877,0.000007603127,0.0007882437,0.0023649677],"genre_scores_gemma":[0.9798061,0.000004108706,0.019108271,0.000215846,0.00001751963,0.000025168185,0.00003116366,0.000021274562,0.00077051774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987625,0.000044684995,0.00013593347,0.00044695177,0.00023525702,0.0003746624],"domain_scores_gemma":[0.9993025,0.00020998128,0.000061196944,0.00028574496,0.000036573485,0.00010401676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026541553,0.00016353946,0.0001674615,0.000175666,0.00023604029,0.00017308636,0.00031406665,0.000050768263,0.000005826639],"category_scores_gemma":[0.000037126698,0.0001299089,0.000024968433,0.0005823907,0.000036931164,0.0004705037,0.0002453278,0.00024280297,0.000030461326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005352487,0.00008025633,0.001540319,0.00004145389,0.00013239527,0.00010147699,0.04919908,0.08574125,0.0151609965,0.842696,0.00034876855,0.0049044653],"study_design_scores_gemma":[0.00066357595,0.000024106039,0.0015347416,0.0000305944,0.000009363061,0.000009130003,0.002918931,0.9919784,0.00016646774,0.0024713997,9.505965e-7,0.0001923205],"about_ca_topic_score_codex":0.00035221627,"about_ca_topic_score_gemma":0.0001438005,"teacher_disagreement_score":0.9062372,"about_ca_system_score_codex":0.00007144401,"about_ca_system_score_gemma":0.000031624288,"threshold_uncertainty_score":0.52975315},"labels":[],"label_agreement":null},{"id":"W4389520394","doi":"10.18653/v1/2023.emnlp-main.652","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Softmax function; Inference; Boosting (machine learning); Information retrieval; Normalization (sociology); Similarity (geometry); Dual (grammatical number); Data mining; Artificial intelligence; Image (mathematics); Deep learning","score_opus":0.011786407206670723,"score_gpt":0.2904348914203238,"score_spread":0.27864848421365307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389520394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733485,0.000013964881,0.02120798,0.0018805878,0.00004319255,0.0001605108,0.0000012415121,0.0004728999,0.0028711448],"genre_scores_gemma":[0.9745099,0.000004605803,0.02471931,0.00017624746,0.000033774315,0.000015764806,0.0000040222817,0.000012628505,0.00052377756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998748,0.000046566267,0.00018897951,0.00047348125,0.00023579418,0.00030719515],"domain_scores_gemma":[0.9990733,0.00030879027,0.00006291473,0.0004220372,0.00004971922,0.00008320734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040819214,0.00012529179,0.00014199277,0.00012602654,0.00014323827,0.00024099133,0.0004459643,0.000060986455,0.000012253195],"category_scores_gemma":[0.0001266531,0.000107000655,0.000017732418,0.0010354866,0.00008408966,0.0003774687,0.00027090972,0.00028276548,0.000063621],"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":[0.000018218952,0.00003364015,0.9686395,0.000038930597,0.000008955018,0.000033288936,0.0010237596,0.0045313817,0.0029319942,0.013343878,0.00009796361,0.009298484],"study_design_scores_gemma":[0.00027926313,0.000016769054,0.68834746,0.000023302146,7.3805154e-7,0.00001020019,0.000018396342,0.31024775,0.00034500335,0.00053961674,0.000054214826,0.00011725601],"about_ca_topic_score_codex":0.00041656065,"about_ca_topic_score_gemma":0.00007451014,"teacher_disagreement_score":0.30571637,"about_ca_system_score_codex":0.00002381292,"about_ca_system_score_gemma":0.00006440512,"threshold_uncertainty_score":0.436336},"labels":[],"label_agreement":null},{"id":"W4389521029","doi":"10.18653/v1/2023.conll-1.7","title":"ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Automatic summarization; Natural language; Architecture; Artificial intelligence; Closed captioning; Artificial neural network; Modal; Set (abstract data type); Modalities; Natural language processing; Modality (human–computer interaction); Question answering; Natural language understanding; Inference; Programming language; Image (mathematics)","score_opus":0.023390957982274044,"score_gpt":0.30562016566167766,"score_spread":0.2822292076794036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389521029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91408265,0.000066879,0.07892129,0.004329296,0.00006235561,0.0001097874,0.0000018122855,0.00044464623,0.0019812766],"genre_scores_gemma":[0.9886282,0.0000021902247,0.01103873,0.00009599371,0.00002101389,0.0000056834547,0.000002481271,0.000005885548,0.00019983227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933976,0.000037239137,0.00010423973,0.00020974902,0.00014474698,0.00016424876],"domain_scores_gemma":[0.9993972,0.00026246803,0.000037464328,0.00024503717,0.000012298427,0.000045535686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117590535,0.00007522107,0.00009047288,0.00017128461,0.000084539824,0.00004671234,0.0003209694,0.000020729274,0.0000059923477],"category_scores_gemma":[0.000058150417,0.000059477206,0.000027872848,0.0004170181,0.00006569778,0.000053893476,0.0002488711,0.00014388925,0.000010578568],"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":[0.000013517784,0.00004151043,0.055075374,0.00009746418,0.00005077969,0.000020601588,0.0063842926,0.009773092,0.030950928,0.79528,0.0005548198,0.101757616],"study_design_scores_gemma":[0.00016504733,0.000027177048,0.26470467,0.0000075745907,0.0000023900038,0.000015840427,0.00017555273,0.72222257,0.0008218089,0.011709875,0.000041510084,0.00010598716],"about_ca_topic_score_codex":0.0004087625,"about_ca_topic_score_gemma":0.000046957313,"teacher_disagreement_score":0.7835701,"about_ca_system_score_codex":0.0000124683775,"about_ca_system_score_gemma":0.000010852203,"threshold_uncertainty_score":0.24254102},"labels":[],"label_agreement":null},{"id":"W4389523744","doi":"10.18653/v1/2023.emnlp-main.629","title":"APoLLo : Unified Adapter and Prompt Learning for Vision Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Army Research Office","keywords":"Computer science; Adapter (computing); Generalization; Artificial intelligence; Overfitting; Encoder; Modalities; Machine learning; Artificial neural network","score_opus":0.022641774636371664,"score_gpt":0.30940200390185413,"score_spread":0.28676022926548245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389523744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15054722,0.000018151053,0.84173596,0.0029291862,0.000030240682,0.00032488327,7.9722577e-7,0.00086257624,0.0035509826],"genre_scores_gemma":[0.9285682,0.0000031632012,0.067032605,0.000099740784,0.000021899528,0.0000785839,0.000008985151,0.000010539056,0.0041763033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992858,0.000028883574,0.000101188474,0.00029950996,0.00010470103,0.00017988842],"domain_scores_gemma":[0.9994622,0.00015951433,0.000033556138,0.0002566347,0.000030171565,0.000057934005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024656035,0.00007769869,0.00008144606,0.00009697455,0.00016664917,0.00010787769,0.0002626178,0.000029099801,0.0000061943374],"category_scores_gemma":[0.000041789346,0.000066499066,0.000025931553,0.000271903,0.000015032497,0.00022828877,0.00020820882,0.00010736775,0.00006292025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015488416,0.000059044603,0.0010111579,0.00007110854,0.000025452018,0.000006182254,0.00796209,0.1054641,0.01674828,0.4901232,0.002292771,0.3762211],"study_design_scores_gemma":[0.00020645195,0.000047071942,0.003900938,0.0000062039453,0.0000018621345,0.0000019958438,0.000076355325,0.9885209,0.00022333818,0.0053361515,0.0015879415,0.000090745976],"about_ca_topic_score_codex":0.00019214927,"about_ca_topic_score_gemma":0.0000075102607,"teacher_disagreement_score":0.8830568,"about_ca_system_score_codex":0.000008152261,"about_ca_system_score_gemma":0.000015638845,"threshold_uncertainty_score":0.27117532},"labels":[],"label_agreement":null},{"id":"W4389523846","doi":"10.18653/v1/2023.emnlp-main.906","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chart; Computer science; Automatic summarization; Artificial intelligence; Natural language processing; Generalizability theory; Question answering; Machine learning","score_opus":0.01654483011686048,"score_gpt":0.3042212782774124,"score_spread":0.28767644816055193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389523846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14543998,0.000019791782,0.8500236,0.0025266432,0.00003119814,0.0003147428,0.000005743628,0.00076716935,0.0008710958],"genre_scores_gemma":[0.8085307,0.0000066475905,0.1898355,0.00016590756,0.000017080241,0.000029449577,0.000017497869,0.000011096598,0.001386149],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991666,0.00002566115,0.000108718625,0.00036259685,0.00012687578,0.00020956593],"domain_scores_gemma":[0.999242,0.0001969238,0.000040505158,0.00038437275,0.00004497867,0.00009119065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021559802,0.000097002434,0.0001039974,0.00012434206,0.00020264563,0.000078162666,0.00032755922,0.000044365952,0.0000062099643],"category_scores_gemma":[0.000054983644,0.00009005526,0.000032330976,0.00033084516,0.000026946776,0.00021557277,0.0002809225,0.00009226301,0.000039821713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041036237,0.0001066212,0.0007948924,0.0001080603,0.000041940002,0.00001143915,0.017980175,0.06010184,0.039260358,0.7354628,0.008573112,0.13751774],"study_design_scores_gemma":[0.00039447512,0.00003741092,0.0030317362,0.000014601266,0.00000319354,0.0000031142306,0.000091180504,0.9945099,0.00008359998,0.0010594687,0.0006617668,0.00010958288],"about_ca_topic_score_codex":0.00007695809,"about_ca_topic_score_gemma":0.000008799842,"teacher_disagreement_score":0.934408,"about_ca_system_score_codex":0.000016380834,"about_ca_system_score_gemma":0.000029059534,"threshold_uncertainty_score":0.3672347},"labels":[],"label_agreement":null},{"id":"W4390481874","doi":"10.1109/ssci52147.2023.10371820","title":"Image Caption Generation Based on Image-Text Matching Schema in Deep Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Closed captioning; Reinforcement learning; Computer science; Artificial intelligence; Matching (statistics); Schema (genetic algorithms); Image (mathematics); Deep learning; Machine learning; Computer vision","score_opus":0.018295307871210587,"score_gpt":0.28744745214003,"score_spread":0.2691521442688194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390481874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122163974,0.0000017336364,0.86826366,0.0028798473,0.00006131279,0.00022594944,1.0561461e-7,0.00059300725,0.0058104172],"genre_scores_gemma":[0.8520607,0.0000022901197,0.1470612,0.00028630774,0.000052488056,0.00009758919,0.000046838613,0.000014198404,0.00037842602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860185,0.0001135198,0.0002652013,0.00042316638,0.00031920176,0.000277053],"domain_scores_gemma":[0.999238,0.00011995348,0.00009004268,0.00043534802,0.000055153894,0.00006146356],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00060155266,0.00013745122,0.00010936056,0.0003504286,0.0002157977,0.00023138509,0.0003529197,0.000050745537,0.00010110936],"category_scores_gemma":[0.000116871604,0.00013772896,0.00004322611,0.0007882276,0.000017422532,0.00043392394,0.00013587669,0.0003138281,0.0014369695],"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":[0.0000028539,0.000026468088,0.0006740712,0.000011357606,0.000002120515,0.000005408094,0.00046462571,0.899397,0.0783317,0.009330526,0.00017150142,0.011582375],"study_design_scores_gemma":[0.00031554454,0.000037863705,0.01236524,0.000014279778,0.0000013300944,9.1104624e-7,0.000034606437,0.9838833,0.0028007745,0.00026264213,0.00013421442,0.00014930192],"about_ca_topic_score_codex":0.0007731055,"about_ca_topic_score_gemma":0.00005630588,"teacher_disagreement_score":0.72989666,"about_ca_system_score_codex":0.00011713877,"about_ca_system_score_gemma":0.00003413944,"threshold_uncertainty_score":0.99934053},"labels":[],"label_agreement":null},{"id":"W4390708079","doi":"10.1007/978-3-031-23161-2_501","title":"Automated Image Captioning for the Visually Impaired","year":2024,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Multimodal Machine Learning Applications","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":"CNIB Foundation; Ontario Tech University","funders":"","keywords":"Closed captioning; Visually impaired; Computer vision; Computer science; Image (mathematics); Artificial intelligence; Computer graphics (images); Human–computer interaction","score_opus":0.009772799513870566,"score_gpt":0.2649087258365698,"score_spread":0.25513592632269927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390708079","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":[0.00038686703,0.005027946,0.91674006,0.003865588,0.0013065863,0.0014501354,0.000094959854,0.0015206574,0.069607176],"genre_scores_gemma":[0.12165448,0.019017091,0.6966376,0.0020377692,0.004129528,0.000835825,0.0003211354,0.00063375017,0.15473282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846816,0.000017053455,0.00044727713,0.0005766331,0.00026933194,0.00022152811],"domain_scores_gemma":[0.9980786,0.000714481,0.00027610542,0.00065081083,0.00019730812,0.000082706145],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032704943,0.0003395386,0.00036837335,0.00026914338,0.0002001115,0.00026016557,0.0008241905,0.00018922362,0.000006377086],"category_scores_gemma":[0.000015630756,0.00025614174,0.00024683547,0.00011218242,0.00020302432,0.00012571247,0.00045294256,0.00041927467,0.0000127247295],"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":[0.0000028606976,0.000011882981,0.000030208366,0.00013784523,0.00013934994,0.0000031441687,0.00044492877,0.00010666747,0.0000040912805,0.9696948,0.0030075822,0.026416633],"study_design_scores_gemma":[0.00017027905,0.0001432041,0.0024814312,0.0001776915,0.000089618916,0.000014911238,0.0000021900787,0.72395164,0.0000017919164,0.10636422,0.16630107,0.0003019183],"about_ca_topic_score_codex":0.00007282963,"about_ca_topic_score_gemma":0.000009259552,"teacher_disagreement_score":0.8633306,"about_ca_system_score_codex":0.000012763464,"about_ca_system_score_gemma":0.0000812587,"threshold_uncertainty_score":0.9999891},"labels":[],"label_agreement":null},{"id":"W4390873290","doi":"10.1109/iccv51070.2023.01282","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Toronto Metropolitan University","funders":"HORIZON EUROPE Health; Tsinghua Shenzhen International Graduate School; National Natural Science Foundation of China","keywords":"Computer science; Adapter (computing); Leverage (statistics); Transformer; Artificial intelligence; Natural language processing; Event (particle physics); Semantics (computer science); Feature learning; Task (project management); Speech recognition; Programming language","score_opus":0.025625017955884403,"score_gpt":0.319102130015953,"score_spread":0.2934771120600686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018695971,0.0000097362845,0.968509,0.004136206,0.00016654406,0.0003902173,0.0000027153217,0.0017017028,0.0063878833],"genre_scores_gemma":[0.58699995,0.0000010118373,0.41161725,0.0002379232,0.00009520441,0.00016098261,0.000008564337,0.000015599873,0.0008634885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872017,0.000057028767,0.00022846647,0.00046125305,0.00019815472,0.0003349388],"domain_scores_gemma":[0.99877936,0.00043728916,0.000087776534,0.000501411,0.00011161627,0.00008253466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008012564,0.00012535388,0.00011900546,0.00015094437,0.00026345247,0.00021294618,0.00059383764,0.000046156656,0.00002822672],"category_scores_gemma":[0.00036245462,0.000120245844,0.00006633212,0.00057532894,0.000026510043,0.0004606992,0.00019089131,0.00014922228,0.00041163687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000109367975,0.000059767128,0.0031860026,0.00006641473,0.000032522887,0.0000059763893,0.0025185551,0.0068864617,0.022608792,0.4637499,0.009284813,0.49158987],"study_design_scores_gemma":[0.0002086591,0.000045712204,0.009347602,0.000021264814,0.0000036084898,0.00000479526,0.00006575998,0.97830003,0.00063089805,0.0036471286,0.0075598503,0.00016469929],"about_ca_topic_score_codex":0.000277136,"about_ca_topic_score_gemma":0.000016752723,"teacher_disagreement_score":0.97141355,"about_ca_system_score_codex":0.000032450178,"about_ca_system_score_gemma":0.000039903403,"threshold_uncertainty_score":0.5290896},"labels":[],"label_agreement":null},{"id":"W4390874807","doi":"10.1109/acii59096.2023.10388198","title":"Contextual Emotion Estimation from Image Captions","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Estimation; Image (mathematics); Artificial intelligence; Natural language processing; Computer vision; Engineering","score_opus":0.017812830750340628,"score_gpt":0.2950309506352097,"score_spread":0.27721811988486905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390874807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1362297,0.0000020922087,0.852312,0.004708279,0.00008960957,0.00011061328,0.000006228947,0.0015915732,0.004949905],"genre_scores_gemma":[0.7993649,0.000001212587,0.19965217,0.00011616091,0.000032428234,0.00003270063,0.00007561333,0.000005385512,0.0007193991],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992962,0.000039771276,0.00013093234,0.000252705,0.00014737468,0.00013305403],"domain_scores_gemma":[0.9992943,0.00014999043,0.00004178749,0.0004104711,0.000050110168,0.00005333636],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012727642,0.00006796427,0.0000633252,0.00010095415,0.00011726743,0.000129529,0.00035031853,0.000032638312,0.00009081891],"category_scores_gemma":[0.00009956551,0.000065778964,0.000030907977,0.0005138529,0.000022007935,0.0003761514,0.0001215757,0.00009292271,0.0060492875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025619563,0.00011733808,0.0029440597,0.000007754474,0.000029271876,0.0000071770282,0.002954645,0.030065438,0.031898566,0.527832,0.026380444,0.37776077],"study_design_scores_gemma":[0.00010887997,0.0000073491337,0.13129635,0.000002836287,0.0000019283825,9.213595e-7,0.000027909975,0.8569775,0.00022320873,0.010929237,0.000356224,0.000067628265],"about_ca_topic_score_codex":0.0019309608,"about_ca_topic_score_gemma":0.000028551529,"teacher_disagreement_score":0.8269121,"about_ca_system_score_codex":0.000024309218,"about_ca_system_score_gemma":0.000019267907,"threshold_uncertainty_score":0.99472463},"labels":[],"label_agreement":null},{"id":"W4391173394","doi":"10.1117/1.jei.33.1.013028","title":"TEG: image theme recognition using text-embedding-guided few-shot adaptation","year":2024,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"Multimodal Machine Learning Applications","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":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Theme (computing); Image processing; Embedding; Adaptation (eye); Pattern recognition (psychology); Image (mathematics); Optics; Physics","score_opus":0.036764065489061935,"score_gpt":0.3436573871034038,"score_spread":0.3068933216143419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391173394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09085244,0.0013372906,0.9027542,0.0036618533,0.00029028553,0.000116961724,8.8494687e-7,0.00014594833,0.0008401683],"genre_scores_gemma":[0.8844052,0.000040301577,0.11505302,0.0001475074,0.00028974464,0.000003989222,0.0000024096096,0.00002565462,0.000032208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983097,0.00011630428,0.00050955254,0.00027240862,0.0003657383,0.00042633753],"domain_scores_gemma":[0.99890274,0.0001801483,0.0003233216,0.00023946192,0.0002755763,0.00007872892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010383921,0.00016126828,0.00018123275,0.00041717582,0.00017093997,0.00054607895,0.0005207742,0.000033102933,0.000038281163],"category_scores_gemma":[0.00012936593,0.00014732433,0.00015124376,0.00061281654,0.000031783635,0.0015114085,0.000073256895,0.0007477925,0.00005340539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032373584,0.00018513798,0.00043503768,0.00013261878,0.00024255562,0.00018335514,0.00422339,0.034375075,0.3456748,0.022210792,0.0021074475,0.5901974],"study_design_scores_gemma":[0.00023620659,0.000046401143,0.0001875911,0.00016137003,0.000042345993,0.0011914144,0.00006542436,0.9785334,0.0025193465,0.015276406,0.0015736523,0.00016647794],"about_ca_topic_score_codex":0.000111465095,"about_ca_topic_score_gemma":0.0000035881485,"teacher_disagreement_score":0.9441583,"about_ca_system_score_codex":0.0004892609,"about_ca_system_score_gemma":0.0005477462,"threshold_uncertainty_score":0.6007712},"labels":[],"label_agreement":null},{"id":"W4391335180","doi":"10.1145/3610977.3634999","title":"Generative Expressive Robot Behaviors using Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"","keywords":"Computer science; Robot; Human–computer interaction; Leverage (statistics); Motion (physics); Generative model; Generative grammar; Natural language; Context (archaeology); Artificial intelligence; Social robot; Mobile robot; Robot control","score_opus":0.03655862504537216,"score_gpt":0.3494611117712703,"score_spread":0.31290248672589815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391335180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0899788,0.0005246359,0.90313786,0.0007056296,0.00045496423,0.00050841767,0.000062629275,0.0008547187,0.0037723149],"genre_scores_gemma":[0.6209808,0.0000039842253,0.37780887,0.0001533045,0.00013777957,0.00015607045,0.00003610191,0.000033759574,0.0006893273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765867,0.00012965045,0.00032649355,0.0011460407,0.00035653316,0.00038258484],"domain_scores_gemma":[0.99804074,0.000056178436,0.00016875198,0.0014917819,0.00011049669,0.00013207625],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002225986,0.00036892397,0.0003178945,0.00022525678,0.00016501707,0.0005592474,0.0015299422,0.00026671705,0.00006854277],"category_scores_gemma":[0.000018314833,0.00033645114,0.00018096945,0.00025499216,0.000031456977,0.00017485979,0.00631549,0.0013051531,0.00015919637],"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":[0.0000012047062,0.00013468295,0.0000625421,0.00008606923,0.00007029644,0.00006614638,0.011135716,0.7965993,0.013490935,0.17429914,0.00048706098,0.0035668535],"study_design_scores_gemma":[0.00008390247,0.0000072131743,0.000082757026,0.00008439511,0.00003647068,0.000008302399,0.00008682143,0.97104603,0.0027211762,0.025441727,0.00003107357,0.00037013786],"about_ca_topic_score_codex":0.0023301446,"about_ca_topic_score_gemma":0.000044794946,"teacher_disagreement_score":0.53100204,"about_ca_system_score_codex":0.00015254012,"about_ca_system_score_gemma":0.00023199829,"threshold_uncertainty_score":0.99990875},"labels":[],"label_agreement":null},{"id":"W4391457730","doi":"10.5206/fpq/2022.3/4.14292","title":"Bias Dilemma","year":2022,"lang":"en","type":"article","venue":"Feminist Philosophy Quarterly","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Dilemma; Computer science; Epistemology; Philosophy","score_opus":0.0307340521760262,"score_gpt":0.2603152871605439,"score_spread":0.2295812349845177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391457730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38403812,0.00023280898,0.16771363,0.08945974,0.0033521666,0.002059938,0.00032888324,0.0052142628,0.34760046],"genre_scores_gemma":[0.9872604,1.4855205e-7,0.010605142,0.0013237618,0.00022118687,0.00035862543,0.00002750104,0.000021588141,0.0001816617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816483,0.00018573274,0.00029290473,0.00056654366,0.00048298188,0.00030702076],"domain_scores_gemma":[0.9983649,0.0001469874,0.00016208536,0.0011560299,0.000035399975,0.00013459161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003147335,0.00017746298,0.00016749746,0.00015150194,0.0007665001,0.00016701475,0.0017943429,0.000029971008,0.00018768373],"category_scores_gemma":[0.000017631985,0.00019566482,0.00011265897,0.00062200165,0.000054485652,0.00017998333,0.00026577548,0.000433789,0.00048422965],"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":[0.0000065638574,0.00025084318,0.002302311,0.000011614589,0.000017913184,0.000030771043,0.0036537054,0.0002505172,0.00013681564,0.9634577,0.0017434031,0.028137842],"study_design_scores_gemma":[0.0014884087,0.0032713935,0.02191431,0.000018267536,0.000023124576,0.0003169144,0.00032398675,0.080105364,0.00008306333,0.48653743,0.40455115,0.0013665856],"about_ca_topic_score_codex":0.000116820935,"about_ca_topic_score_gemma":0.0000010415446,"teacher_disagreement_score":0.60322225,"about_ca_system_score_codex":0.00007694458,"about_ca_system_score_gemma":0.00006703183,"threshold_uncertainty_score":0.797898},"labels":[],"label_agreement":null},{"id":"W4391516313","doi":"10.1007/978-981-99-8850-1_25","title":"PointerNet with Local and Global Contexts for Natural Language Moment Localization","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Moment (physics); Natural (archaeology); Natural language; Natural language processing; Artificial intelligence; Physics; Geography; Archaeology","score_opus":0.005756129519541871,"score_gpt":0.26191497201004543,"score_spread":0.2561588424905036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391516313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013995521,0.0012532094,0.9952332,0.0014352028,0.00047942818,0.00061165146,0.00001556373,0.00019372665,0.00063809345],"genre_scores_gemma":[0.80822545,0.000005754195,0.19030207,0.00090946804,0.0001356803,0.00003093687,0.000016186865,0.000023668694,0.00035075494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769413,0.000012564504,0.0002626615,0.0011968594,0.0004699172,0.00036386383],"domain_scores_gemma":[0.99882644,0.00018202045,0.00012383529,0.0006154273,0.00013729034,0.000115003575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002843527,0.00035525762,0.00029283317,0.00023293709,0.00013148204,0.0005113639,0.0011240973,0.00013576701,0.0000035734358],"category_scores_gemma":[0.000019817438,0.00028073738,0.00005337477,0.00034156273,0.00050392386,0.00023027892,0.0006563625,0.0004104656,0.00001670504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000150032565,0.000016496508,0.00012294574,0.000098145836,0.000020127365,0.000034725515,0.0009005725,0.049399257,0.00001724056,0.17412917,0.000023968349,0.77522236],"study_design_scores_gemma":[0.0002805279,0.00017041652,0.0002117397,0.0002989624,0.000010743474,0.0000945538,3.863678e-7,0.9474008,0.0000873925,0.049994975,0.0011147022,0.00033480686],"about_ca_topic_score_codex":0.00013618756,"about_ca_topic_score_gemma":0.00027923303,"teacher_disagreement_score":0.89800155,"about_ca_system_score_codex":0.00031474355,"about_ca_system_score_gemma":0.00017475618,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"W4391654261","doi":"10.2196/32690","title":"Vision-Language Model for Generating Textual Descriptions From Clinical Images: Model Development and Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":37,"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":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Natural language processing; Artificial intelligence; Standardization; Deep learning; Metric (unit); Closed captioning; Quality (philosophy); Information retrieval; Machine learning; Image (mathematics)","score_opus":0.15177448273116914,"score_gpt":0.505880174163475,"score_spread":0.35410569143230586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391654261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42439038,0.0000529406,0.574213,0.0002970564,0.00002862509,0.00073304493,0.000025755797,0.00011879573,0.00014034864],"genre_scores_gemma":[0.7458573,0.0000039859583,0.25285143,0.00003214442,0.00005281886,0.00095618167,0.00004451102,0.000013973389,0.00018763842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976703,0.00032032916,0.00050281256,0.0005741948,0.00058119686,0.00035120003],"domain_scores_gemma":[0.998152,0.0009531198,0.000054511893,0.00042919238,0.00026878025,0.0001423507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027502372,0.00014240114,0.00016747686,0.00028259712,0.0007230772,0.00083630125,0.00054885197,0.00006988031,0.0000037076607],"category_scores_gemma":[0.0001748805,0.00012183797,0.00005087475,0.00042318428,0.00008604677,0.0010089333,0.00060827105,0.00059314526,0.000070936105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034778415,0.0014257963,0.00081192725,0.00013632944,0.0001588658,0.0000067442793,0.23587431,0.08863649,0.0053261556,0.022443254,0.0062652626,0.6388801],"study_design_scores_gemma":[0.0003421786,0.00014458782,0.0026776954,0.000040168663,0.000004040339,8.308344e-7,0.001541893,0.99275607,0.00026470807,0.0020186899,0.00007329626,0.00013586169],"about_ca_topic_score_codex":0.00006782267,"about_ca_topic_score_gemma":0.000016643651,"teacher_disagreement_score":0.90411955,"about_ca_system_score_codex":0.0001220946,"about_ca_system_score_gemma":0.00031837882,"threshold_uncertainty_score":0.8064472},"labels":[],"label_agreement":null},{"id":"W4391871827","doi":"10.48550/arxiv.2402.08532","title":"Captions Are Worth a Thousand Words: Enhancing Product Retrieval with Pretrained Image-to-Text Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Mitacs","keywords":"Product (mathematics); Computer science; Image (mathematics); Natural language processing; Information retrieval; Artificial intelligence; Mathematics","score_opus":0.03925230774777872,"score_gpt":0.2080312265532537,"score_spread":0.168778918805475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391871827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3297325,0.00006818911,0.66503197,0.00091691944,0.000196667,0.0008837129,0.000035990586,0.00083703396,0.0022970254],"genre_scores_gemma":[0.9610539,0.000024913013,0.036020614,0.00008625404,0.00015797398,0.000012596204,0.000020452211,0.000064906395,0.002558388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963756,0.00016822135,0.0002954504,0.0023724057,0.00023288514,0.0005554011],"domain_scores_gemma":[0.9965626,0.00012666475,0.00029837605,0.0023205108,0.0003449808,0.0003468476],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040216517,0.0005212362,0.00046102484,0.0006107881,0.00032160126,0.00045474822,0.002032361,0.00020091933,0.000025466306],"category_scores_gemma":[0.0000940859,0.0005348248,0.00018604477,0.0022824495,0.00013175656,0.00040288048,0.0028174063,0.0016276612,0.0002946622],"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":[0.00008036475,0.00013021547,0.0007319079,0.00023888476,0.00017735874,0.000261826,0.0021197922,0.9387016,0.00048529304,0.05628735,0.00024005669,0.000545353],"study_design_scores_gemma":[0.0003226938,0.00007015716,0.002423385,0.0005459877,0.00015455546,0.000018445706,0.00012666447,0.95485824,0.0002662586,0.040302992,0.00012053715,0.0007900542],"about_ca_topic_score_codex":0.00044984298,"about_ca_topic_score_gemma":0.00031468552,"teacher_disagreement_score":0.6313214,"about_ca_system_score_codex":0.00036695655,"about_ca_system_score_gemma":0.00052335253,"threshold_uncertainty_score":0.9997103},"labels":[],"label_agreement":null},{"id":"W4392384263","doi":"10.1145/3616855.3635757","title":"Text-Video Retrieval via Multi-Modal Hypergraph Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Hypergraph; Matching (statistics); Artificial intelligence; Representation (politics); Visual Word; Pipeline (software); Information retrieval; Pattern recognition (psychology); Natural language processing; Image retrieval; Image (mathematics)","score_opus":0.011400809876122384,"score_gpt":0.2742944262598563,"score_spread":0.2628936163837339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392384263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058102575,0.00047214155,0.9839397,0.0039118486,0.0005065053,0.0001921841,0.0000010669545,0.0016799237,0.003486343],"genre_scores_gemma":[0.86503446,0.000012960011,0.13294795,0.00043307492,0.00015836763,0.00001930426,0.0000045477095,0.000020608008,0.0013686988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848753,0.00006618771,0.00023561002,0.0006255952,0.00024186014,0.00034324286],"domain_scores_gemma":[0.99876654,0.00024037813,0.000030887644,0.0007634735,0.000051864572,0.0001468778],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003281045,0.00017558393,0.00013850738,0.00016231457,0.00016550528,0.0003983207,0.0009586597,0.00010305571,0.00009744392],"category_scores_gemma":[0.000045400757,0.00014950089,0.00011673229,0.00114688,0.00005194311,0.00034999306,0.00031669863,0.000454599,0.00078066037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016551305,0.0003409247,0.0064531034,0.000062499166,0.00014337066,0.00007704266,0.0007449581,0.045824412,0.007464713,0.4865968,0.009643397,0.44263223],"study_design_scores_gemma":[0.00012920497,0.00002919429,0.013697425,0.000013742853,0.0000064147243,0.000028895107,0.0000025634624,0.97467977,0.00015885055,0.0013147625,0.009746465,0.00019270265],"about_ca_topic_score_codex":0.00037658357,"about_ca_topic_score_gemma":0.000017370081,"teacher_disagreement_score":0.92885536,"about_ca_system_score_codex":0.00004110371,"about_ca_system_score_gemma":0.000046639743,"threshold_uncertainty_score":0.9999973},"labels":[],"label_agreement":null},{"id":"W4392680666","doi":"10.1145/3613904.3642752","title":"AQuA: Automated Question-Answering in Software Tutorial Videos with Visual Anchors","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Autodesk (Canada)","funders":"","keywords":"Computer science; Documentation; Pipeline (software); Feature (linguistics); Software; Human–computer interaction; Multimedia; Question answering; Information retrieval; World Wide Web; Programming language","score_opus":0.007411309493075668,"score_gpt":0.3091428584012771,"score_spread":0.3017315489082014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392680666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23668025,0.00012853667,0.7457805,0.0018214994,0.0022466457,0.0010077371,0.000010360198,0.011182462,0.0011419681],"genre_scores_gemma":[0.7694921,0.0000039725096,0.22948976,0.00006415184,0.0003559025,0.0003370011,0.000032132444,0.000046239005,0.00017874359],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728656,0.00014114,0.00046642387,0.0012502469,0.00046638315,0.0003892552],"domain_scores_gemma":[0.99844706,0.00018809122,0.00015168134,0.0009690248,0.00011276224,0.00013135801],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044197752,0.000408477,0.00038701392,0.00043460407,0.00008888119,0.000582141,0.0012000635,0.0003161802,0.00002522008],"category_scores_gemma":[0.00015327468,0.00035463242,0.000084882005,0.0007463197,0.000046812023,0.00016042491,0.0022945777,0.0015939109,0.00028674913],"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":[0.00006622234,0.0005911261,0.052479766,0.0013938161,0.00030092892,0.00032616334,0.0044089793,0.75322026,0.00059730746,0.106092215,0.0028068537,0.07771636],"study_design_scores_gemma":[0.0002574615,0.0000554362,0.025280615,0.00050234614,0.000016380567,0.000012925777,0.000007559857,0.96748215,0.00010857335,0.0054239472,0.0003574007,0.00049522513],"about_ca_topic_score_codex":0.007358635,"about_ca_topic_score_gemma":0.00046601996,"teacher_disagreement_score":0.5328118,"about_ca_system_score_codex":0.0002875742,"about_ca_system_score_gemma":0.00046903786,"threshold_uncertainty_score":0.99989057},"labels":[],"label_agreement":null},{"id":"W4392864334","doi":"10.1145/3649896","title":"Realizing Efficient On-Device Language-based Image Retrieval","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Multimodal Machine Learning Applications","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; Centre for Social Innovation","funders":"","keywords":"Computer science; Information retrieval; Image retrieval; Latency (audio); Ranking (information retrieval); Modal; Language model; Deep learning; Context (archaeology); Artificial intelligence; Image (mathematics)","score_opus":0.02008231110073879,"score_gpt":0.32669562855509837,"score_spread":0.3066133174543596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392864334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041858964,0.0005338694,0.97736305,0.014065817,0.000095174786,0.0008969984,0.000057059893,0.0015457001,0.0012564267],"genre_scores_gemma":[0.61917156,0.00007215189,0.3799933,0.00035813585,0.00005638073,0.00022638505,0.000047905316,0.000033868473,0.000040334115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977533,0.00021735366,0.0004865892,0.0008286006,0.0003449214,0.00036919216],"domain_scores_gemma":[0.9916998,0.0033715297,0.00011835036,0.0044447132,0.00014674688,0.0002188556],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00056306145,0.00031613314,0.00023497791,0.000490926,0.0014072753,0.00052299706,0.0025888719,0.00012219214,0.000018720546],"category_scores_gemma":[0.00008834914,0.00031971786,0.00014534635,0.0015963985,0.00026977478,0.00014894683,0.00016225927,0.0009525082,0.00037762124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001667639,0.0012115245,0.000039864808,0.00013380438,0.00011405124,0.0000046306595,0.002602668,0.0235949,0.013247133,0.061059624,0.00009563346,0.8978795],"study_design_scores_gemma":[0.00033523884,0.00006746731,0.00061483943,0.00015938425,0.000042297128,0.000012560817,0.00015263747,0.98462814,0.002149586,0.00049226056,0.010999811,0.00034578642],"about_ca_topic_score_codex":0.00020021781,"about_ca_topic_score_gemma":0.0000126558,"teacher_disagreement_score":0.9610332,"about_ca_system_score_codex":0.00013099184,"about_ca_system_score_gemma":0.00014423954,"threshold_uncertainty_score":0.9999255},"labels":[],"label_agreement":null},{"id":"W4392904379","doi":"10.1109/icassp48485.2024.10447954","title":"Multimodal Transformer with a Low-Computational-Cost Guarantee","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Computer science; Transformer; Action recognition; Inference; FLOPS; Modalities; Artificial intelligence; Machine learning; Computational complexity theory; Algorithm; Engineering; Parallel computing","score_opus":0.006684249304437783,"score_gpt":0.2641704279134448,"score_spread":0.257486178609007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392904379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030664563,0.000053871227,0.9539686,0.0053283786,0.00007971114,0.00033840447,0.0000043512046,0.0009224089,0.00863973],"genre_scores_gemma":[0.8189991,0.000002209608,0.18005182,0.00030960835,0.00003486145,0.00010301098,0.000009070131,0.00001530728,0.00047499093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988135,0.000024428284,0.00016759097,0.00047098252,0.0002860012,0.00023746693],"domain_scores_gemma":[0.99937344,0.00015806152,0.000017612996,0.0003286365,0.00005932411,0.00006292195],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012766424,0.00014993198,0.00010655074,0.00014278053,0.00011487539,0.00030445066,0.00048450456,0.00003987797,0.000107842396],"category_scores_gemma":[0.0000065674585,0.00010852789,0.000059353057,0.0005974325,0.00004310599,0.00044141797,0.000019167861,0.00022039386,0.00088547694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012377925,0.00014391166,0.0006248493,0.0000701211,0.0000759997,0.000043151664,0.0019312568,0.14046082,0.0010429857,0.5899469,0.00080499466,0.2648426],"study_design_scores_gemma":[0.0002516664,0.000036178426,0.007455108,0.000037029415,0.0000059977797,0.00005256818,0.0000090923295,0.9830256,0.00036709517,0.0041634855,0.00441129,0.00018487108],"about_ca_topic_score_codex":0.0002633875,"about_ca_topic_score_gemma":0.000024049514,"teacher_disagreement_score":0.8425648,"about_ca_system_score_codex":0.000035466714,"about_ca_system_score_gemma":0.000112350695,"threshold_uncertainty_score":0.9998925},"labels":[],"label_agreement":null},{"id":"W4393147243","doi":"10.1609/aaai.v38i13.29407","title":"XKD: Cross-Modal Knowledge Distillation with Domain Alignment for Video Representation Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":20,"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; Vector Institute","funders":"Mitacs","keywords":"Modal; Representation (politics); Computer science; Domain (mathematical analysis); Artificial intelligence; Computer vision; Mathematics; Chemistry","score_opus":0.05995314657169955,"score_gpt":0.36507794310485103,"score_spread":0.3051247965331515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393147243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30148697,0.000039559807,0.68540126,0.0033662408,0.0003108179,0.0009887468,0.0000059537506,0.00031461156,0.008085832],"genre_scores_gemma":[0.9835305,0.0000051531506,0.015764402,0.000031384214,0.00010020585,0.00020784436,0.0000024713895,0.000020040206,0.0003379527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982537,0.000024694034,0.00043019128,0.0006511091,0.00036997715,0.0002702969],"domain_scores_gemma":[0.99860877,0.0002929282,0.00024458172,0.00026083636,0.00052371534,0.00006919991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005806557,0.00019887707,0.00018546934,0.0001350346,0.00034170476,0.00069173175,0.00095912593,0.00006036211,0.00002016503],"category_scores_gemma":[0.00030062164,0.00014382214,0.00010132497,0.0007375325,0.00019424543,0.00045783096,0.00020284748,0.00029937734,0.00007079534],"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":[0.00005580997,0.00006515378,0.0012656536,0.00008332867,0.000019249786,1.779701e-7,0.0026090483,0.0022375034,0.019129882,0.91378355,0.00004326772,0.060707394],"study_design_scores_gemma":[0.00004633685,0.00026427247,0.0019293629,0.00030936993,0.000016878517,0.0000060454954,0.00033337943,0.720797,0.110062964,0.16492374,0.0010761997,0.00023442716],"about_ca_topic_score_codex":0.00008154387,"about_ca_topic_score_gemma":0.000010439144,"teacher_disagreement_score":0.74885976,"about_ca_system_score_codex":0.00008943336,"about_ca_system_score_gemma":0.00010549346,"threshold_uncertainty_score":0.6670385},"labels":[],"label_agreement":null},{"id":"W4393147811","doi":"10.1609/aaai.v38i10.29037","title":"Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Computer science; Bayesian probability; Artificial intelligence; Machine learning; Bayesian statistics; Natural language processing; Bayesian inference; Psychology; Cognitive psychology","score_opus":0.07165001741030415,"score_gpt":0.3458690247856473,"score_spread":0.27421900737534316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393147811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05095797,0.000090698595,0.93823177,0.0053533684,0.00022945632,0.0016467987,0.000022709199,0.0004986961,0.0029685085],"genre_scores_gemma":[0.94976294,0.000009684145,0.049205378,0.00005264312,0.00009633319,0.00019316138,0.0000066727303,0.0000373476,0.0006358573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726224,0.000024504978,0.0005396551,0.0011027737,0.00062550575,0.0004453324],"domain_scores_gemma":[0.9982677,0.00019205199,0.00024387389,0.00070398755,0.00048310906,0.00010925478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009833882,0.0002964724,0.00028117985,0.00017805645,0.00040613164,0.00089553965,0.0032555594,0.00009055988,0.000026499623],"category_scores_gemma":[0.00042863537,0.00020655183,0.00007377079,0.00073934405,0.00012502089,0.0006621016,0.00080860296,0.0006359485,0.00004488758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010198745,0.00019247003,0.00006556595,0.000322932,0.000054770622,0.0000018739714,0.0035180096,0.01553611,0.029342614,0.5541974,0.000072367904,0.39659396],"study_design_scores_gemma":[0.000035264173,0.0002651373,0.000021489852,0.0005929664,0.00002784395,0.000011643189,0.00047641245,0.96100605,0.022713894,0.014361618,0.00023016453,0.00025751788],"about_ca_topic_score_codex":0.00017219558,"about_ca_topic_score_gemma":0.000038078317,"teacher_disagreement_score":0.9454699,"about_ca_system_score_codex":0.00005786073,"about_ca_system_score_gemma":0.00028821302,"threshold_uncertainty_score":0.8635709},"labels":[],"label_agreement":null},{"id":"W4393152659","doi":"10.1609/aaai.v38i17.29906","title":"YTCommentQA: Video Question Answerability in Instructional Videos","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science","score_opus":0.047121977550224924,"score_gpt":0.32778641041260964,"score_spread":0.28066443286238474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393152659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79605967,0.00006868511,0.12695722,0.06249717,0.0012494228,0.0010422013,0.000010673016,0.00054370594,0.01157127],"genre_scores_gemma":[0.9910025,0.0000132093965,0.0086012,0.00017652851,0.00006372593,0.000077755874,7.1801804e-7,0.000009489703,0.000054849777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981985,0.000035953624,0.0005265895,0.0005833948,0.00041289174,0.00024265125],"domain_scores_gemma":[0.99904484,0.00017638388,0.0001421719,0.00030083425,0.00027483283,0.00006092963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079887157,0.00017681699,0.00017654954,0.00020967617,0.00012628853,0.00031620418,0.0013430024,0.00008207957,0.000060743954],"category_scores_gemma":[0.00043369253,0.00013995319,0.00009129631,0.0010824954,0.00018940329,0.0005497886,0.00028584112,0.0005313481,0.00012016359],"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":[0.000011588282,0.00008469527,0.0016883876,0.000040259663,0.0000051071816,2.4963686e-7,0.00054121664,0.00022065324,0.009428273,0.86774117,0.000052321022,0.12018606],"study_design_scores_gemma":[0.000021559896,0.00008035611,0.012262025,0.00029071048,0.0000056929653,0.0000078923995,0.000083632985,0.42406148,0.05649419,0.5059009,0.00059227063,0.00019926553],"about_ca_topic_score_codex":0.00043303805,"about_ca_topic_score_gemma":0.000033405642,"teacher_disagreement_score":0.42384082,"about_ca_system_score_codex":0.0001292622,"about_ca_system_score_gemma":0.00011281549,"threshold_uncertainty_score":0.57071257},"labels":[],"label_agreement":null},{"id":"W4393169473","doi":"10.1007/978-3-031-54845-1_5","title":"Empowering Canadian Geography Students and Faculty: New Approaches to Curriculum and Course Material Development Using Generative AI as a Writing Assistant","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Multimodal Machine Learning Applications","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":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Course (navigation); Curriculum; Generative grammar; Mathematics education; Curriculum development; Pedagogy; Engineering ethics; Sociology; Engineering; Psychology; Computer science; Artificial intelligence","score_opus":0.06565042245054759,"score_gpt":0.3345357804165687,"score_spread":0.2688853579660211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393169473","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":[0.5671524,0.0015099698,0.24465917,0.01618706,0.0016699943,0.006033837,0.0003287252,0.0014789484,0.16097991],"genre_scores_gemma":[0.37558496,0.000019854751,0.5844351,0.0014191415,0.00048232134,0.00012819796,0.0001450476,0.00016260371,0.037622757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978649,0.000015170232,0.0003668574,0.00097012793,0.00039925496,0.0003836878],"domain_scores_gemma":[0.99886626,0.000016246724,0.000099155324,0.00030602893,0.000047670128,0.0006646185],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021680087,0.00043251607,0.0003364413,0.00040444502,0.00038401777,0.0015408148,0.00049772655,0.0001669802,0.000029230681],"category_scores_gemma":[0.0000056249983,0.00040933755,0.000046664518,0.000109441724,0.000044673296,0.00015773882,0.0008073081,0.00035038745,0.00003475361],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000100258185,0.00007630567,0.029349303,0.00027113763,0.001055182,0.00023649435,0.010562034,0.00073605584,0.0002249494,0.89982134,0.0009236198,0.056733575],"study_design_scores_gemma":[0.0030901027,0.00071151176,0.17327376,0.0063129896,0.0011237577,0.0012247487,0.0016400194,0.2858822,0.00090975914,0.04684849,0.4648832,0.014099443],"about_ca_topic_score_codex":0.054604333,"about_ca_topic_score_gemma":0.0141306715,"teacher_disagreement_score":0.8529728,"about_ca_system_score_codex":0.00019496547,"about_ca_system_score_gemma":0.00058268104,"threshold_uncertainty_score":0.99983585},"labels":[],"label_agreement":null},{"id":"W4395689368","doi":"10.1038/s41598-024-60256-7","title":"A self-supervised framework for cross-modal search in histopathology archives using scale harmonization","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Multimodal Machine Learning Applications","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":"Brock University; University of Waterloo","funders":"Mayo Clinic","keywords":"Harmonization; Computer science; Modal; Modalities; Digital pathology; Scale (ratio); Data science; Representation (politics); Artificial intelligence; Big data; Space (punctuation); Scarcity; Scheme (mathematics); Machine learning; Information retrieval; Pattern recognition (psychology); Data mining","score_opus":0.0269233348395202,"score_gpt":0.3435729190752458,"score_spread":0.3166495842357256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395689368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38656953,0.00013506463,0.60997754,0.00036308696,0.0020674313,0.00038679768,0.0000014029766,0.00028127184,0.00021787541],"genre_scores_gemma":[0.5638313,8.4830214e-7,0.43576807,0.000015884598,0.00005189298,0.000061749604,0.000012085061,0.000012855626,0.00024526636],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975936,0.00009621592,0.00042943115,0.0011850666,0.00030996065,0.00038572273],"domain_scores_gemma":[0.99853885,0.00022712398,0.00008001903,0.0009680185,0.00009122551,0.00009473529],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014112607,0.00012965837,0.00015136802,0.00045354056,0.00039729365,0.0011631917,0.00045526237,0.000087512955,0.000013277791],"category_scores_gemma":[0.00018688547,0.00013023819,0.00008536403,0.001146522,0.0001917468,0.00031805114,0.00023128916,0.00028008505,0.000019131094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003113078,0.0008892263,0.3013776,0.001232406,0.00004002535,0.0013748696,0.049025577,0.079197526,0.18737352,0.23816995,0.0005724188,0.14071578],"study_design_scores_gemma":[0.000059658232,0.000013140259,0.01131251,0.00005627841,0.000004281493,0.00017024827,0.000011359747,0.8927628,0.0016335297,0.09184236,0.0019989228,0.00013492134],"about_ca_topic_score_codex":0.00007110266,"about_ca_topic_score_gemma":0.000008152045,"teacher_disagreement_score":0.81356525,"about_ca_system_score_codex":0.000109836794,"about_ca_system_score_gemma":0.0003365243,"threshold_uncertainty_score":0.9998737},"labels":[],"label_agreement":null},{"id":"W4395955659","doi":"10.55041/ijsrem31987","title":"IMAGE CAPTION GENERATOR USING DEEP LEARNING","year":2024,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Multimodal Machine Learning Applications","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; Convolutional neural network; Closed captioning; Artificial intelligence; Encoder; Generator (circuit theory); Deep learning; Image (mathematics); Convolution (computer science); Task (project management); Pattern recognition (psychology); Computer vision; Artificial neural network","score_opus":0.039044449502799415,"score_gpt":0.35767770657940445,"score_spread":0.31863325707660506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395955659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2898254,0.00080816186,0.70773566,0.00071211014,0.0006569761,0.0000937234,4.0616573e-7,0.000034535264,0.00013299742],"genre_scores_gemma":[0.9031614,0.00009436899,0.09656138,0.0000030977756,0.00007785578,0.0000060681914,8.6963905e-7,0.000007149726,0.00008778898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858636,0.00008380746,0.000275491,0.00024239418,0.00058862765,0.00022335279],"domain_scores_gemma":[0.9994729,0.000115868876,0.000034110344,0.00012446061,0.00017436604,0.000078289515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031415862,0.00007115661,0.00008572009,0.0014850943,0.00013273643,0.0010354392,0.00037804118,0.00002063405,0.000006480808],"category_scores_gemma":[0.000045926216,0.00006457552,0.00004509708,0.00092823396,0.000060910425,0.0005261237,0.00021234057,0.0005010841,0.000013257412],"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":[0.000014845306,0.00012944393,0.00048736637,0.000956128,0.00013732864,0.0007034926,0.0013711222,0.51508397,0.12046123,0.16898277,0.0003385143,0.19133379],"study_design_scores_gemma":[0.00011347997,0.000024457075,0.002261914,0.00041476448,0.0000029054002,0.00009476499,0.000038189162,0.99078506,0.00014286848,0.0007156424,0.0053446027,0.00006136929],"about_ca_topic_score_codex":0.000017684992,"about_ca_topic_score_gemma":9.097003e-7,"teacher_disagreement_score":0.613336,"about_ca_system_score_codex":0.00012416721,"about_ca_system_score_gemma":0.00002657864,"threshold_uncertainty_score":0.9984764},"labels":[],"label_agreement":null},{"id":"W4396647722","doi":"10.2196/56627","title":"Advancing Accuracy in Multimodal Medical Tasks Through Bootstrapped Language-Image Pretraining (BioMedBLIP): Performance Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Multimodal Machine Learning Applications","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; Computer science; Artificial intelligence; Natural language processing; Computer vision; World Wide Web","score_opus":0.020379232693986376,"score_gpt":0.38706889653301435,"score_spread":0.36668966383902796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396647722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83362335,0.00010639205,0.15912898,0.0016944367,0.00039820196,0.0014175571,0.000003854818,0.0006389476,0.0029882933],"genre_scores_gemma":[0.96165097,0.000023829443,0.03692906,0.0005974742,0.00017620652,0.00054211076,0.000042502736,0.000023273737,0.000014583689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99416935,0.00023358015,0.0012328128,0.00038841204,0.0033444758,0.00063134404],"domain_scores_gemma":[0.9976522,0.0008976618,0.00019277113,0.0007601622,0.00011775127,0.00037946555],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004175759,0.00029589285,0.0003417718,0.00036506384,0.0001635769,0.00034483927,0.0015893707,0.000274554,0.00049112167],"category_scores_gemma":[0.0017954271,0.0002530158,0.00007826392,0.0014644844,0.0001438887,0.0024645946,0.0005460601,0.0015583974,0.0003033568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010696049,0.0005136951,0.0031630194,0.00039974024,0.000049370283,0.00009124005,0.15932655,0.0005187844,0.000064108404,0.0013952176,0.00046346543,0.8340041],"study_design_scores_gemma":[0.0012211556,0.00015068759,0.017112259,0.00045769833,0.000012399682,0.000053752756,0.004689606,0.9752806,0.000040762156,0.000080436905,0.0006263702,0.00027426626],"about_ca_topic_score_codex":0.00019286583,"about_ca_topic_score_gemma":0.000068571084,"teacher_disagreement_score":0.97476184,"about_ca_system_score_codex":0.00022030981,"about_ca_system_score_gemma":0.0010589355,"threshold_uncertainty_score":0.9999922},"labels":[],"label_agreement":null},{"id":"W4396674347","doi":"10.32920/25761540","title":"An Attempt at Defining And Quantifying Image Describability Through Semantic Connection Between Visual and Language","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Natural language processing; Image (mathematics); Artificial intelligence; Task (project management); Ground truth; Judgement; Semantics (computer science); Domain (mathematical analysis); Mathematics; Programming language","score_opus":0.04252563624348574,"score_gpt":0.37419961974821603,"score_spread":0.3316739835047303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396674347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75846076,0.00040080844,0.23872742,0.00077325717,0.00015024377,0.00030425173,0.000014271079,0.0006834127,0.00048558554],"genre_scores_gemma":[0.8878292,0.000016396265,0.11184461,0.00006127304,0.00008590309,0.000047240523,0.000060580514,0.000029652258,0.000025189453],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975028,0.00022690163,0.00036333918,0.0013970307,0.00022519988,0.0002847493],"domain_scores_gemma":[0.9982941,0.00052108953,0.00014140648,0.00085703837,0.000057719986,0.00012864893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006897528,0.0003217916,0.00037656244,0.00011890153,0.00030611074,0.0007972798,0.00043680402,0.0002211414,0.00001577311],"category_scores_gemma":[0.00013393271,0.00030581935,0.00006233147,0.00019009343,0.00012635656,0.00030358232,0.003333206,0.00084459886,0.000067181485],"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":[0.000022722405,0.0002620714,0.6640357,0.0046104444,0.00036173125,0.00006287237,0.036517374,0.00083675614,0.025690762,0.1430198,0.0001805352,0.12439924],"study_design_scores_gemma":[0.00025521134,0.00009880074,0.3193316,0.0002404926,0.000107172345,0.000048857506,0.00038485578,0.6547446,0.00195881,0.022064181,0.000039591814,0.00072580186],"about_ca_topic_score_codex":0.005331233,"about_ca_topic_score_gemma":0.0002528118,"teacher_disagreement_score":0.6539079,"about_ca_system_score_codex":0.000101228994,"about_ca_system_score_gemma":0.000052277588,"threshold_uncertainty_score":0.9999394},"labels":[],"label_agreement":null},{"id":"W4396674455","doi":"10.32920/25761540.v1","title":"An Attempt at Defining And Quantifying Image Describability Through Semantic Connection Between Visual and Language","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Computer science; Image (mathematics); Natural language processing; Task (project management); Artificial intelligence; Judgement; Ground truth; Semantics (computer science); Domain (mathematical analysis); Mathematics; Programming language","score_opus":0.04252563624348574,"score_gpt":0.37419961974821603,"score_spread":0.3316739835047303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396674455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75846076,0.00040080844,0.23872742,0.00077325717,0.00015024377,0.00030425173,0.000014271079,0.0006834127,0.00048558554],"genre_scores_gemma":[0.8878292,0.000016396265,0.11184461,0.00006127304,0.00008590309,0.000047240523,0.000060580514,0.000029652258,0.000025189453],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975028,0.00022690163,0.00036333918,0.0013970307,0.00022519988,0.0002847493],"domain_scores_gemma":[0.9982941,0.00052108953,0.00014140648,0.00085703837,0.000057719986,0.00012864893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006897528,0.0003217916,0.00037656244,0.00011890153,0.00030611074,0.0007972798,0.00043680402,0.0002211414,0.00001577311],"category_scores_gemma":[0.00013393271,0.00030581935,0.00006233147,0.00019009343,0.00012635656,0.00030358232,0.003333206,0.00084459886,0.000067181485],"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":[0.000022722405,0.0002620714,0.6640357,0.0046104444,0.00036173125,0.00006287237,0.036517374,0.00083675614,0.025690762,0.1430198,0.0001805352,0.12439924],"study_design_scores_gemma":[0.00025521134,0.00009880074,0.3193316,0.0002404926,0.000107172345,0.000048857506,0.00038485578,0.6547446,0.00195881,0.022064181,0.000039591814,0.00072580186],"about_ca_topic_score_codex":0.005331233,"about_ca_topic_score_gemma":0.0002528118,"teacher_disagreement_score":0.6539079,"about_ca_system_score_codex":0.000101228994,"about_ca_system_score_gemma":0.000052277588,"threshold_uncertainty_score":0.9999394},"labels":[],"label_agreement":null},{"id":"W4396723194","doi":"10.1145/3589334.3645603","title":"Multimodal Relation Extraction via a Mixture of Hierarchical Visual Context Learners","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Ottawa","funders":"Universitas Brawijaya","keywords":"Computer science; Relation (database); Relationship extraction; Context (archaeology); Extraction (chemistry); Artificial intelligence; Context model; Natural language processing; Data mining; Chromatography; Chemistry","score_opus":0.009990317320447086,"score_gpt":0.3100381747683123,"score_spread":0.3000478574478652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396723194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10029749,0.00008816315,0.89327466,0.002550151,0.00020809621,0.00017059504,9.78503e-7,0.0004744253,0.0029354442],"genre_scores_gemma":[0.9420259,0.0000034955385,0.05734766,0.000087991066,0.00006753659,0.000022531387,0.000008843053,0.000012093881,0.0004239258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883443,0.00009476686,0.0002580868,0.00039207903,0.00026226282,0.00015840195],"domain_scores_gemma":[0.99921596,0.0003095912,0.000058010148,0.00028819713,0.000053053813,0.000075182616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024800558,0.000112551825,0.00012162813,0.0001799054,0.00007636056,0.00009139564,0.00028994502,0.00011016359,0.00008621279],"category_scores_gemma":[0.0000691654,0.000100626945,0.00008625048,0.0004827755,0.00005393909,0.0004234102,0.00008575993,0.0004523641,0.00022886702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015103959,0.00014358606,0.0021043876,0.000056628753,0.00003936336,0.000007462132,0.0015520765,0.0028897938,0.05210512,0.28455183,0.00038810098,0.6561465],"study_design_scores_gemma":[0.00013914892,0.000064290376,0.021597788,0.000022456083,0.0000068519466,0.00002300498,0.000020571217,0.97070754,0.0017099103,0.0032772194,0.0023166528,0.00011457825],"about_ca_topic_score_codex":0.0005794591,"about_ca_topic_score_gemma":0.000018661689,"teacher_disagreement_score":0.9678177,"about_ca_system_score_codex":0.00004605431,"about_ca_system_score_gemma":0.000060341834,"threshold_uncertainty_score":0.41034478},"labels":[],"label_agreement":null},{"id":"W4396832936","doi":"10.1145/3613905.3636316","title":"Computational Methodologies for Understanding, Automating, and Evaluating User Interfaces","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Domain (mathematical analysis); Human–computer interaction; Field (mathematics); User interface; Data science; Interface (matter); Modeling language; Software engineering; Programming language; Software","score_opus":0.22434966393392727,"score_gpt":0.4633460451970769,"score_spread":0.23899638126314962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396832936","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":[0.016873382,0.00014154626,0.9770624,0.0037624228,0.00011980525,0.00021720263,0.0000019453717,0.00086832023,0.0009529455],"genre_scores_gemma":[0.45942935,6.094389e-7,0.5403182,0.000065394015,0.0000128851525,0.000034419398,0.0000015933629,0.000004506588,0.00013303311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991976,0.00008313889,0.00014990733,0.0003163255,0.00012739496,0.00012561481],"domain_scores_gemma":[0.9973661,0.0024010486,0.000034751385,0.00013250078,0.00003591393,0.000029724562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008860518,0.00008269968,0.00008602645,0.00009131238,0.00015904813,0.00044640945,0.00023923247,0.000029633664,0.000017557148],"category_scores_gemma":[0.00031562694,0.00006778349,0.000026095988,0.00015901074,0.000040384533,0.00025036078,0.00016952504,0.00008809767,0.00001285819],"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":[9.067655e-7,0.0000037933949,0.00023100931,0.000049227147,0.000019963682,2.1704298e-7,0.00085427804,0.014519255,0.0003194454,0.93456817,0.0006591778,0.048774548],"study_design_scores_gemma":[0.000064995584,0.000041207382,0.0011855297,0.000020796135,0.0000045161487,0.000005637565,0.00009293233,0.74246687,0.000085618856,0.2557688,0.00019820333,0.000064917396],"about_ca_topic_score_codex":0.00004172024,"about_ca_topic_score_gemma":0.0000035321038,"teacher_disagreement_score":0.7279476,"about_ca_system_score_codex":0.000048859616,"about_ca_system_score_gemma":0.000041748375,"threshold_uncertainty_score":0.4304737},"labels":[],"label_agreement":null},{"id":"W4396893649","doi":"10.1111/cogs.13448","title":"Learning the Meanings of Function Words From Grounded Language Using a Visual Question Answering Model","year":2024,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Multimodal Machine Learning Applications","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Social Sciences and Humanities Research Council","keywords":"Function (biology); Question answering; Computer science; Meaning (existential); Artificial intelligence; Semantics (computer science); Visual reasoning; Natural language processing; Context (archaeology); Logical reasoning; Cognitive science; Linguistics; Psychology","score_opus":0.018542381159367582,"score_gpt":0.33580491063980183,"score_spread":0.31726252948043426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396893649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4761598,0.00008820446,0.52292234,0.0000650588,0.00009256879,0.00007934872,0.0000013271213,0.00013881759,0.00045252554],"genre_scores_gemma":[0.9849798,0.0000025460872,0.014831645,0.00006122165,0.000055902674,0.000014724077,0.0000029952403,0.000009354701,0.000041793235],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985619,0.00009275601,0.00016597321,0.0005062173,0.0004533602,0.00021978145],"domain_scores_gemma":[0.9991655,0.0003207913,0.00008756895,0.0001894636,0.00018245526,0.00005422993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097580027,0.000109435176,0.0000936927,0.00018403803,0.00044029343,0.0003789374,0.0005321649,0.000030718697,0.0000072085522],"category_scores_gemma":[0.00043241616,0.00008693219,0.00004221939,0.0014654804,0.00034558418,0.0009314016,0.0002891432,0.00032484703,0.000022210328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016211738,0.00004798423,0.0014255284,0.00002688274,0.000024984443,0.0000053314766,0.029593455,0.053744722,0.56616443,0.037933573,0.0000020790633,0.3110148],"study_design_scores_gemma":[0.00006849873,0.000043568103,0.009054216,0.00015559958,0.00001790014,0.0000039428464,0.0008306863,0.98120505,0.00566291,0.0028506322,0.0000045714814,0.00010244576],"about_ca_topic_score_codex":0.0009821884,"about_ca_topic_score_gemma":0.000011497213,"teacher_disagreement_score":0.9274603,"about_ca_system_score_codex":0.000078304285,"about_ca_system_score_gemma":0.00019790645,"threshold_uncertainty_score":0.3654102},"labels":[],"label_agreement":null},{"id":"W4400338820","doi":"10.1016/j.cviu.2024.104064","title":"Implicit and explicit commonsense for multi-sentence video captioning","year":2024,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"Alliance de recherche numérique du Canada; Vector Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Closed captioning; Computer science; Commonsense knowledge; Sentence; Paragraph; Natural language processing; Artificial intelligence; Task (project management); Object (grammar); Isolation (microbiology); Commonsense reasoning; Knowledge base; Transformer; Image (mathematics); World Wide Web","score_opus":0.07097240444014455,"score_gpt":0.34862258458640083,"score_spread":0.2776501801462563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400338820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017047152,0.0005504735,0.97902733,0.0023496987,0.00021855219,0.00032504305,0.000005186093,0.00040575975,0.00007077803],"genre_scores_gemma":[0.62760526,0.00006223261,0.3719692,0.00024593883,0.000057541016,0.000018629262,0.0000035405426,0.000015204077,0.000022455293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987079,0.00004920284,0.00022459467,0.0006267597,0.00012629064,0.0002652858],"domain_scores_gemma":[0.9989784,0.00048908574,0.000048208847,0.00030030374,0.00004216752,0.00014187266],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003236919,0.00018600287,0.00017611132,0.00020682038,0.00048836664,0.0012680062,0.00024564826,0.000052194955,0.0000028901006],"category_scores_gemma":[0.000027037268,0.0001681552,0.0000566351,0.00024126799,0.00007767029,0.0005925259,0.00037610182,0.00018821016,0.00000991445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025000914,0.000090912945,0.0008173416,0.00039930307,0.00006980126,0.000047316502,0.004858207,0.00017748396,0.053179532,0.7821314,0.005540929,0.15266283],"study_design_scores_gemma":[0.00041220902,0.00009757619,0.0014480121,0.00018504681,0.000009162768,0.00011327231,0.00013258366,0.98924357,0.0001554888,0.006860015,0.0011351707,0.00020787661],"about_ca_topic_score_codex":0.000053924236,"about_ca_topic_score_gemma":0.0000057770394,"teacher_disagreement_score":0.9890661,"about_ca_system_score_codex":0.00008752615,"about_ca_system_score_gemma":0.000020838956,"threshold_uncertainty_score":0.9997688},"labels":[],"label_agreement":null},{"id":"W4400367343","doi":"10.7717/peerj-cs.2097","title":"Knowledge enhanced bottom-up affordance grounding for robotic interaction","year":2024,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research","keywords":"Affordance; Computer science; Artificial intelligence; Ground; Natural language; Robot; Human–computer interaction; Top-down and bottom-up design; Natural language processing; Robotics; Machine learning; Programming language; Engineering","score_opus":0.029840325518459308,"score_gpt":0.35218747684773544,"score_spread":0.3223471513292761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400367343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017646773,0.00017275536,0.97207415,0.0018250946,0.0063186144,0.00041130028,9.1376995e-7,0.0009301219,0.000620284],"genre_scores_gemma":[0.6912135,0.0000032458986,0.30791155,0.00010267141,0.00031992616,0.0001092634,0.000002041724,0.000012723835,0.0003251124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749696,0.000045722823,0.00030432647,0.00117794,0.00040802924,0.00056702015],"domain_scores_gemma":[0.9981895,0.0004976819,0.000083951854,0.0007906862,0.00026401135,0.00017413692],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011099124,0.00021538802,0.00019508443,0.00044857824,0.000579641,0.0016219111,0.0021876697,0.00004580387,0.0000059183717],"category_scores_gemma":[0.00010512324,0.00020414744,0.00011062378,0.0020541537,0.00019238905,0.0020426481,0.0006069292,0.00032096,0.0002759598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037694483,0.00007113071,0.00004485568,0.00012063764,0.000013483732,0.0000024317353,0.0030482833,0.016448386,0.01964718,0.27538982,0.00096649624,0.6842435],"study_design_scores_gemma":[0.00013177477,0.00008156268,0.0020738149,0.00011177845,0.0000059544213,0.00003076114,0.0000074358336,0.9849921,0.0047563957,0.0042775525,0.003281401,0.00024948103],"about_ca_topic_score_codex":0.000044272605,"about_ca_topic_score_gemma":0.0000072016473,"teacher_disagreement_score":0.9685437,"about_ca_system_score_codex":0.00027447127,"about_ca_system_score_gemma":0.00030407612,"threshold_uncertainty_score":0.9994145},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4400617959","doi":"10.1016/j.eswa.2024.124762","title":"Open-vocabulary object detection via debiased curriculum self-training","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Multimodal Machine Learning Applications","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 Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Vocabulary; Curriculum; Natural language processing; Machine learning; Object (grammar); Computer vision; Pattern recognition (psychology); Psychology; Linguistics; Pedagogy","score_opus":0.014389172244817729,"score_gpt":0.28630577759657566,"score_spread":0.27191660535175793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400617959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015797268,0.0014306133,0.9872579,0.0009486729,0.0002797556,0.0023672562,0.0000047277176,0.0024118915,0.0037194558],"genre_scores_gemma":[0.9103977,0.000013941443,0.07762258,0.0001412336,0.00033028162,0.011253217,0.000022831777,0.000052518273,0.00016569126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976942,0.00013792198,0.00040558976,0.0010083612,0.00036297712,0.0003909682],"domain_scores_gemma":[0.9979807,0.00019309243,0.00013379093,0.0013449411,0.00014042438,0.00020701323],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004319779,0.00028176967,0.00026541273,0.0002330015,0.00062282686,0.0012789556,0.0017751012,0.00010885905,0.000010516407],"category_scores_gemma":[0.000014767973,0.00023772872,0.00006748837,0.0015816119,0.000041549443,0.0007448306,0.00031838682,0.00033944857,0.00041966196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020730993,0.0013453513,0.002115989,0.00063742854,0.0007931887,0.00007753001,0.024500445,0.008371565,0.044941433,0.45243132,0.0046884133,0.4600766],"study_design_scores_gemma":[0.0002972296,0.000089412875,0.00067527045,0.00013730505,0.000020675403,0.00033863593,0.00032098367,0.81595993,0.00062151515,0.00045345747,0.18059796,0.00048759527],"about_ca_topic_score_codex":0.002946172,"about_ca_topic_score_gemma":0.00006296553,"teacher_disagreement_score":0.9096353,"about_ca_system_score_codex":0.00020025947,"about_ca_system_score_gemma":0.00022960498,"threshold_uncertainty_score":0.9997578},"labels":[],"label_agreement":null},{"id":"W4400676369","doi":"10.1007/978-3-031-65112-0_3","title":"Concept-Based Analysis of Neural Networks via Vision-Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Natural language processing; Computer vision","score_opus":0.01025510262428448,"score_gpt":0.278116982880562,"score_spread":0.26786188025627755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400676369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024367025,0.0009823473,0.9959181,0.0007209982,0.0006168456,0.00033159222,0.000015120518,0.0002533946,0.00091793167],"genre_scores_gemma":[0.8156432,0.0000039055976,0.18341579,0.0006440803,0.00013901838,0.000011332816,0.00002636046,0.000031001484,0.00008529527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960957,0.00004673882,0.00067582104,0.0016877163,0.0009674652,0.00052656134],"domain_scores_gemma":[0.9963897,0.00079676183,0.00037362226,0.0020390707,0.00022755376,0.00017332648],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062598777,0.0005074555,0.0007847229,0.001970162,0.00015507771,0.0003826804,0.003554343,0.00030192372,0.000033499313],"category_scores_gemma":[0.000033225733,0.0004557157,0.0003778619,0.0029740075,0.00070760463,0.00035297382,0.0011192608,0.0010951975,0.000013157792],"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":[0.0000017873024,0.000017072833,0.000020636919,0.000013676961,0.000051246043,0.000019126617,0.0004938092,0.7825116,0.00004031678,0.012281091,0.0000027278065,0.20454691],"study_design_scores_gemma":[0.00011308615,0.000085482665,0.00018126336,0.000113111346,0.00011941448,0.0000056631916,1.1617996e-7,0.97199595,0.00009278708,0.02685661,0.00002116844,0.00041532316],"about_ca_topic_score_codex":0.00029373108,"about_ca_topic_score_gemma":0.00008443709,"teacher_disagreement_score":0.8153995,"about_ca_system_score_codex":0.0001747036,"about_ca_system_score_gemma":0.00020401774,"threshold_uncertainty_score":0.9997895},"labels":[],"label_agreement":null},{"id":"W4400819487","doi":"10.1145/3658172","title":"S3: Speech, Script and Scene driven Head and Eye Animation","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Multimodal Machine Learning Applications","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; University of Toronto","funders":"","keywords":"Computer science; Animation; Computer graphics (images); Head (geology); Computer facial animation; Artificial intelligence; Computer vision; Computer animation; Speech recognition","score_opus":0.019613478951137613,"score_gpt":0.2959048077076894,"score_spread":0.27629132875655177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400819487","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12614949,0.00032870515,0.8570954,0.015368587,0.00018356062,0.00020708996,0.00001189618,0.00049484044,0.0001603948],"genre_scores_gemma":[0.91064715,0.00028388907,0.088473134,0.00044473246,0.000021608595,0.00003391491,0.0000033840229,0.000014240054,0.00007794096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990431,0.00004707143,0.00015071427,0.0004231295,0.00017850062,0.0001574692],"domain_scores_gemma":[0.9991505,0.00015416024,0.000024313042,0.00053466763,0.00004023657,0.000096105476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015515421,0.00013219463,0.0001015351,0.00030818066,0.0002946234,0.00028222226,0.00030686546,0.00006742535,0.000009149686],"category_scores_gemma":[0.00002067137,0.0001305889,0.000043653377,0.00068866875,0.000086645254,0.00038030304,0.000018117817,0.00036065537,0.000026331823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001207337,0.00022095058,0.0041131545,0.00018908271,0.00011344585,0.000018237119,0.0018790326,0.00092764024,0.0054524094,0.13120602,0.00028421762,0.8555837],"study_design_scores_gemma":[0.0003942099,0.00022042198,0.082605414,0.00015108229,0.000055667286,0.00007382813,0.000029194338,0.8688389,0.0011206296,0.03496913,0.011149622,0.00039189245],"about_ca_topic_score_codex":0.00020819713,"about_ca_topic_score_gemma":0.00008443255,"teacher_disagreement_score":0.8679113,"about_ca_system_score_codex":0.000018810048,"about_ca_system_score_gemma":0.000026800655,"threshold_uncertainty_score":0.5325261},"labels":[],"label_agreement":null},{"id":"W4401042805","doi":"10.18653/v1/2024.findings-naacl.267","title":"Semantically-Prompted Language Models Improve Visual Descriptions","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"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":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Computer science; Natural language processing; Artificial intelligence; Visual language; Programming language; Linguistics","score_opus":0.012386323627262873,"score_gpt":0.29864222577329397,"score_spread":0.2862559021460311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401042805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03779262,0.00012744455,0.9431986,0.0032363322,0.00019941654,0.00018339859,0.0000028748107,0.0017529026,0.013506389],"genre_scores_gemma":[0.8765419,0.0000026130601,0.12118341,0.00023841189,0.00006649193,0.00005576126,0.0000058244,0.0000137096495,0.0018918618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893045,0.000035152,0.00016614833,0.00044325515,0.00018977222,0.00023520604],"domain_scores_gemma":[0.9992826,0.00009374874,0.000015794003,0.00046446008,0.000041694086,0.000101699625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016117068,0.00011596623,0.00009332584,0.00012376714,0.00010348991,0.00040805052,0.00052693585,0.000051648945,0.00009522383],"category_scores_gemma":[0.000027196113,0.000097372584,0.00006507676,0.00046327533,0.000029770516,0.0004959074,0.00024289054,0.0002327339,0.0009174235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.11932e-7,0.00006587781,0.0000299839,0.000023668452,0.000020875808,0.000015586666,0.000975657,0.0010293364,0.031268455,0.9056326,0.00062435603,0.060312897],"study_design_scores_gemma":[0.0000590534,0.000024983403,0.00045176566,0.00001237086,0.000006345401,0.000010928392,0.000026814658,0.98597926,0.0009998468,0.011736713,0.000562744,0.00012915049],"about_ca_topic_score_codex":0.00046566283,"about_ca_topic_score_gemma":0.000014779132,"teacher_disagreement_score":0.98494995,"about_ca_system_score_codex":0.00003486961,"about_ca_system_score_gemma":0.000058856986,"threshold_uncertainty_score":0.99986047},"labels":[],"label_agreement":null},{"id":"W4401413869","doi":"10.1109/icra57147.2024.10610980","title":"Aligning Knowledge Graph with Visual Perception for Object-goal Navigation","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Perception; Graph; Artificial intelligence; Goal orientation; Object (grammar); Human–computer interaction; Computer vision; Psychology; Theoretical computer science; Neuroscience; Social psychology","score_opus":0.01089643671907688,"score_gpt":0.32150315258729995,"score_spread":0.3106067158682231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401413869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12716237,0.000037362362,0.8686215,0.0007634356,0.00011515715,0.00028992523,0.0000011163927,0.0007485867,0.0022605122],"genre_scores_gemma":[0.825271,0.0000011326647,0.17409576,0.000046417565,0.00010081582,0.00016912926,0.000022013264,0.00001318176,0.00028050286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991697,0.000025184203,0.00012274877,0.00039241495,0.00012328719,0.00016667847],"domain_scores_gemma":[0.9995307,0.00011294816,0.000023659219,0.00020105537,0.00007870372,0.00005298168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020591485,0.00010611345,0.00007596737,0.0001238311,0.00016595812,0.00027516394,0.00024101582,0.000042543794,0.000008431571],"category_scores_gemma":[0.000009848654,0.00008381277,0.000050487517,0.00048532573,0.000024885401,0.00035922023,0.000054159158,0.00011679408,0.00017412426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015844413,0.00019693485,0.0012324069,0.00020094024,0.00006966258,0.0000042575016,0.008593338,0.004234737,0.044110753,0.53007007,0.00155802,0.40971306],"study_design_scores_gemma":[0.00028259144,0.00022542817,0.009141874,0.00008641423,0.00001477165,0.000025449983,0.0001024392,0.9809168,0.0013721188,0.0050154435,0.0025961355,0.0002205175],"about_ca_topic_score_codex":0.00013494074,"about_ca_topic_score_gemma":0.000021183292,"teacher_disagreement_score":0.97668207,"about_ca_system_score_codex":0.00004710278,"about_ca_system_score_gemma":0.000058188984,"threshold_uncertainty_score":0.34177855},"labels":[],"label_agreement":null},{"id":"W4401416408","doi":"10.1109/icra57147.2024.10611485","title":"Talk2BEV: Language-enhanced Bird’s-eye View Maps for Autonomous Driving","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Human–computer interaction; Computer vision","score_opus":0.008734051775047096,"score_gpt":0.30360339631739724,"score_spread":0.29486934454235014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401416408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011152332,0.00046200783,0.97319716,0.004564949,0.00031798828,0.0004084625,0.0000034745922,0.0029369544,0.0069566946],"genre_scores_gemma":[0.8086462,0.000006504685,0.18703073,0.00030917348,0.0001118168,0.00023291715,0.0000055963496,0.0000315308,0.0036255536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884707,0.00002837467,0.00020313241,0.0005091,0.00013493806,0.00027738095],"domain_scores_gemma":[0.99904495,0.00022636223,0.000034299752,0.0005711729,0.000038632315,0.000084593434],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002551655,0.00014015315,0.00013944414,0.000113121314,0.00012830048,0.00035967052,0.0006981524,0.000050526505,0.00006965572],"category_scores_gemma":[0.000062071675,0.000121353136,0.000099062185,0.00041010295,0.000020263302,0.00027721422,0.00019319462,0.00016114934,0.0008469348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010095773,0.000048616617,0.00019046904,0.00014848569,0.00003635076,0.0000071696554,0.0019672443,0.0006540229,0.021354906,0.30365208,0.0027662462,0.6691734],"study_design_scores_gemma":[0.00020440586,0.000061727966,0.0032655774,0.000096430085,0.000014007543,0.00001010876,0.000049672013,0.91645056,0.006464487,0.0054406384,0.06755761,0.00038478858],"about_ca_topic_score_codex":0.00022970815,"about_ca_topic_score_gemma":0.000043147797,"teacher_disagreement_score":0.9157965,"about_ca_system_score_codex":0.000056097288,"about_ca_system_score_gemma":0.00007585027,"threshold_uncertainty_score":0.99993104},"labels":[],"label_agreement":null},{"id":"W4401690668","doi":"10.1016/j.heliyon.2024.e36272","title":"Enhancing image caption generation through context-aware attention mechanism","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Multimodal Machine Learning Applications","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":"Athabasca University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Context (archaeology); Mechanism (biology); Image (mathematics); Psychology; Computer science; Computer vision; History; Epistemology; Philosophy","score_opus":0.021577888728825483,"score_gpt":0.29426680512841585,"score_spread":0.27268891639959036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401690668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07115507,0.0006030859,0.92378986,0.0024170822,0.00063325284,0.00021443822,0.0000033408678,0.0007272855,0.00045656582],"genre_scores_gemma":[0.9491285,0.00009999365,0.049682554,0.00028729255,0.0003083796,0.00008537807,0.000039064358,0.000018543771,0.00035031504],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988067,0.00007989195,0.00021726593,0.0004722674,0.00023339922,0.00019046804],"domain_scores_gemma":[0.9994009,0.0000460965,0.00005172454,0.0003788037,0.00007995896,0.000042496977],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024753535,0.00012855016,0.000096724965,0.00008707286,0.00019839221,0.0003886145,0.0002575388,0.00007559515,0.00004887811],"category_scores_gemma":[0.00002616798,0.00012753757,0.00006749846,0.0003045878,0.000015179609,0.0008728537,0.00009340628,0.00020504447,0.0011237856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.1209737e-7,0.000022052982,0.000022430915,0.00012636777,0.000010933291,0.000007453294,0.00087504275,0.00009758176,0.66259515,0.31559944,0.00015973086,0.020482983],"study_design_scores_gemma":[0.00021219118,0.00006836333,0.0017499569,0.00033627462,0.000020651378,0.000042193235,0.0000749051,0.85795045,0.12564524,0.009463986,0.004089203,0.00034660185],"about_ca_topic_score_codex":0.0001950571,"about_ca_topic_score_gemma":0.00008321204,"teacher_disagreement_score":0.8779734,"about_ca_system_score_codex":0.00010027099,"about_ca_system_score_gemma":0.00004262493,"threshold_uncertainty_score":0.99965394},"labels":[],"label_agreement":null},{"id":"W4402593760","doi":"10.1109/iciea61579.2024.10665031","title":"TALON: Improving Large Language Model Cognition with Tactility-Vision Fusion","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Cognition; Artificial intelligence; Psychology; Neuroscience","score_opus":0.006413338553997826,"score_gpt":0.28071533987002073,"score_spread":0.2743020013160229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402593760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10247458,0.000072419505,0.8876034,0.0011301811,0.00004923485,0.00018587307,0.000005899367,0.0009806373,0.007497787],"genre_scores_gemma":[0.8936704,0.000001699947,0.10540086,0.00018919959,0.000034612673,0.00003137914,0.000021489555,0.000013096664,0.0006372677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894595,0.00003185369,0.00012203207,0.00045790442,0.00023782744,0.00020441801],"domain_scores_gemma":[0.99934024,0.000069720605,0.000028958797,0.0004448083,0.0000466618,0.00006962281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024425218,0.00011483367,0.00008047108,0.0001019355,0.00015653405,0.00029634434,0.00029772427,0.00004819135,0.000052465013],"category_scores_gemma":[0.000019572795,0.0000850743,0.000034863646,0.00036998634,0.000015607313,0.00058610877,0.00020426753,0.00023618892,0.0002158403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033545093,0.00043858605,0.0006229572,0.00033168905,0.00004202342,0.00008697882,0.0054404493,0.008771609,0.13510063,0.23389566,0.0014873185,0.61374855],"study_design_scores_gemma":[0.00014937735,0.000048925867,0.0012584688,0.000036328936,0.000007770834,0.000014600778,0.000037480575,0.9958216,0.0014585548,0.0007076098,0.00033531696,0.00012397027],"about_ca_topic_score_codex":0.0002458621,"about_ca_topic_score_gemma":0.0000590507,"teacher_disagreement_score":0.98705,"about_ca_system_score_codex":0.00003335474,"about_ca_system_score_gemma":0.00005675366,"threshold_uncertainty_score":0.34692293},"labels":[],"label_agreement":null},{"id":"W4402703105","doi":"10.1109/cvpr52733.2024.01295","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Advanced Micro Devices (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Artificial intelligence; Human–computer interaction; Multimedia; History; Archaeology","score_opus":0.008162838442675452,"score_gpt":0.2595758568692203,"score_spread":0.25141301842654484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402703105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42745736,0.0001950739,0.5568953,0.002721435,0.00016046737,0.00035848632,5.771464e-7,0.0013775434,0.010833705],"genre_scores_gemma":[0.9541733,0.0000024858555,0.044160273,0.00022986063,0.00007715524,0.00010543018,0.000003911033,0.00003075846,0.001216785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981604,0.00008358784,0.00031666257,0.0007022942,0.00031776365,0.00041929752],"domain_scores_gemma":[0.9990116,0.00025562523,0.00006146919,0.00048733805,0.0000611205,0.00012285956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043173428,0.00022952742,0.00019621743,0.0002556982,0.00022205511,0.0005262686,0.0006775793,0.000080430604,0.00010609871],"category_scores_gemma":[0.00008190128,0.00018193755,0.000058397585,0.00091892114,0.000047794136,0.0007753054,0.00020672851,0.00079466903,0.000444906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017874612,0.000141979,0.22289896,0.00012672998,0.000069699665,0.00019974531,0.024380213,0.03446629,0.0025910987,0.08443977,0.0003133744,0.6303543],"study_design_scores_gemma":[0.0003153892,0.000106211715,0.036695626,0.00012799876,0.0000030643353,0.000056978788,0.00047903508,0.9589215,0.0003862333,0.00030081734,0.0022920643,0.00031511235],"about_ca_topic_score_codex":0.0014337503,"about_ca_topic_score_gemma":0.0010472499,"teacher_disagreement_score":0.92445517,"about_ca_system_score_codex":0.00011314241,"about_ca_system_score_gemma":0.00014049925,"threshold_uncertainty_score":0.7419198},"labels":[],"label_agreement":null},{"id":"W4402716477","doi":"10.1109/cvpr52733.2024.00913","title":"MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":245,"is_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; University of Waterloo","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Cognitive science; Psychology; Geology","score_opus":0.043292078810416655,"score_gpt":0.3393487419959848,"score_spread":0.29605666318556817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402716477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005412483,0.0004617868,0.98510087,0.0066525675,0.00022811981,0.00047778478,0.000009739605,0.00061459455,0.0010420366],"genre_scores_gemma":[0.5672937,0.0000113719125,0.43194756,0.00011170081,0.00006791369,0.00013080773,0.000007979491,0.000016158565,0.00041281],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985488,0.000037639482,0.00022096177,0.00069266866,0.00016702032,0.00033288938],"domain_scores_gemma":[0.99882674,0.0005391802,0.000047118483,0.00040306736,0.000044446842,0.00013941698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031381234,0.0001933609,0.00016592523,0.00016631444,0.00036126727,0.0005087583,0.00041415935,0.00007712817,0.000025777665],"category_scores_gemma":[0.00013567608,0.00016572222,0.00007664437,0.00033291834,0.00006452441,0.00040726826,0.00032282723,0.00020723107,0.000019827445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013377596,0.000101391226,0.0010254806,0.000120458615,0.00009322617,0.000016330348,0.0075113806,0.0019189725,0.008016533,0.93686914,0.0024361964,0.041877486],"study_design_scores_gemma":[0.00041305393,0.000042082953,0.001721348,0.00008872141,0.000007339887,0.0000128389065,0.00029528412,0.99039984,0.00024460125,0.005010615,0.0015349216,0.00022936496],"about_ca_topic_score_codex":0.00034255226,"about_ca_topic_score_gemma":0.000049014543,"teacher_disagreement_score":0.98848087,"about_ca_system_score_codex":0.00014528271,"about_ca_system_score_gemma":0.000059146565,"threshold_uncertainty_score":0.67579556},"labels":[],"label_agreement":null},{"id":"W4402727410","doi":"10.1109/cvpr52733.2024.01307","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Modal; Ranking (information retrieval); Computer science; Linguistics; Natural language processing; Artificial intelligence; Materials science; Philosophy","score_opus":0.024641684716629628,"score_gpt":0.3549871254119355,"score_spread":0.33034544069530586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402727410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16693974,0.00013979634,0.82636577,0.002221588,0.00026070618,0.00021820991,0.0000070447477,0.00049533386,0.003351822],"genre_scores_gemma":[0.85689574,0.0000033706206,0.14245066,0.0003352837,0.00019768368,0.000029705428,0.000004563753,0.000016253345,0.00006673009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998295,0.00006479244,0.00029132972,0.0007030421,0.0003064095,0.0003393926],"domain_scores_gemma":[0.9984173,0.0010365384,0.00004707832,0.0002532396,0.0000787255,0.0001670987],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00040596744,0.00019382036,0.00018305636,0.00017401585,0.00048808637,0.0013462903,0.00041146914,0.000051238385,0.000041825017],"category_scores_gemma":[0.00026828944,0.0001860621,0.000047641202,0.00044128543,0.00011231277,0.0003528895,0.00026834948,0.00031777503,0.00007327583],"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":[0.000018058174,0.000030699324,0.0031603565,0.00007293487,0.00004605922,0.000022517008,0.002759141,0.0034928974,0.02724063,0.95117354,0.00012243427,0.011860725],"study_design_scores_gemma":[0.00019342055,0.00007908838,0.021565743,0.00022441034,0.000009952527,0.0000408886,0.000044548437,0.9319856,0.0026484723,0.04257637,0.00030231685,0.0003291509],"about_ca_topic_score_codex":0.00012658376,"about_ca_topic_score_gemma":0.000010315226,"teacher_disagreement_score":0.9284927,"about_ca_system_score_codex":0.00015989998,"about_ca_system_score_gemma":0.00007320373,"threshold_uncertainty_score":0.9996904},"labels":[],"label_agreement":null},{"id":"W4402728032","doi":"10.1109/cvpr52733.2024.00386","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-Shelf Vision-Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; University of British Columbia","funders":"","keywords":"Computer science; Vocabulary; Segmentation; Natural language processing; Artificial intelligence; Image segmentation; Linguistics","score_opus":0.01812614014927617,"score_gpt":0.3248814039916032,"score_spread":0.30675526384232704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402728032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055574857,0.0010098908,0.9276848,0.010536159,0.00034008786,0.00050506444,0.0000056923077,0.00047721015,0.0038662455],"genre_scores_gemma":[0.91599166,0.000038153772,0.081741996,0.00078196387,0.00007731047,0.00012116696,0.000044257264,0.000018321894,0.0011851817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998608,0.00010165074,0.00024841068,0.0005493813,0.0003015717,0.00019099114],"domain_scores_gemma":[0.9988083,0.00018891749,0.00004247463,0.0008594596,0.000023727296,0.000077086406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003066964,0.00014159249,0.00011279727,0.000074325966,0.00020995585,0.0008462602,0.0016052016,0.00004013772,0.00023920741],"category_scores_gemma":[0.000013677851,0.000100139696,0.00006006783,0.0004468101,0.000023774679,0.0008430154,0.00078546494,0.00019810483,0.00076552347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074430186,0.00023530227,0.00025897523,0.000031828233,0.00015546114,0.00004778921,0.011813768,0.035592735,0.03216125,0.20310251,0.0171597,0.69943327],"study_design_scores_gemma":[0.000118407035,0.000022182718,0.0012711532,0.000023581897,0.0000130464205,0.000004396067,0.00010113929,0.9821598,0.0013788554,0.013267171,0.0015005058,0.00013976195],"about_ca_topic_score_codex":0.0041478337,"about_ca_topic_score_gemma":0.00008436532,"teacher_disagreement_score":0.94656706,"about_ca_system_score_codex":0.00004421937,"about_ca_system_score_gemma":0.00005765092,"threshold_uncertainty_score":0.98395103},"labels":[],"label_agreement":null},{"id":"W4402728164","doi":"10.1109/cvpr52733.2024.01335","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"Computer science; Human–computer interaction; Artificial intelligence; Natural language processing; Computer graphics (images); Programming language; Computer vision","score_opus":0.026130957254922278,"score_gpt":0.32129488570047404,"score_spread":0.2951639284455518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402728164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09770814,0.00015283453,0.8971252,0.001702044,0.000059959388,0.0002601017,0.000008781683,0.00021017992,0.0027727836],"genre_scores_gemma":[0.5711043,0.0000015851856,0.42714313,0.00019758701,0.00001858365,0.000018290502,0.000004218901,0.000013993998,0.0014983407],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986258,0.000053317774,0.00036630654,0.00043999872,0.00029247208,0.00022210892],"domain_scores_gemma":[0.9988754,0.00010552269,0.00007153252,0.000760525,0.000074367854,0.000112681104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032188126,0.00015165556,0.00021388827,0.00022963333,0.00003152218,0.00007711741,0.0007845397,0.000054683678,0.00007307062],"category_scores_gemma":[0.000030779473,0.0001292683,0.00008013156,0.0004723323,0.000032944474,0.0002072227,0.00040617454,0.00015585078,0.00014335032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010776075,0.00014854435,0.0001952002,0.00015248841,0.000054312866,0.000015224346,0.004806331,0.21120694,0.56866235,0.12885134,0.005285904,0.08061059],"study_design_scores_gemma":[0.00012412581,0.000067974914,0.00035359903,0.000056783425,0.000010848362,0.000005355753,0.00001646325,0.97663665,0.020975828,0.0011929135,0.000422924,0.00013651747],"about_ca_topic_score_codex":0.0004265622,"about_ca_topic_score_gemma":0.000013655145,"teacher_disagreement_score":0.76542974,"about_ca_system_score_codex":0.000024802079,"about_ca_system_score_gemma":0.000058865913,"threshold_uncertainty_score":0.52714086},"labels":[],"label_agreement":null},{"id":"W4402753993","doi":"10.1109/cvpr52733.2024.02677","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center","keywords":"Computer science; Diffusion; Artificial intelligence; Computer vision; Physics","score_opus":0.014081222439961093,"score_gpt":0.2562263197521697,"score_spread":0.2421450973122086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402753993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15042537,0.000069510774,0.84111613,0.004277347,0.00011722289,0.0001376785,6.593232e-7,0.00070083304,0.0031552573],"genre_scores_gemma":[0.9238832,0.0000071527165,0.074376784,0.00019620566,0.00011078343,0.00002317034,0.000013090526,0.000009062787,0.0013805651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991844,0.000032006516,0.00010541691,0.00034984527,0.00019499827,0.00013329706],"domain_scores_gemma":[0.99947864,0.000047442398,0.00001802541,0.00037212102,0.000028121472,0.000055635803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012935122,0.00009139844,0.000073336196,0.00009606126,0.00011107879,0.00031482507,0.0002698891,0.000031340907,0.00005391298],"category_scores_gemma":[0.000008806485,0.000063556734,0.000020457388,0.0004208275,0.00001438168,0.00022339262,0.000081923055,0.00012761894,0.0003298104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006266191,0.00018838035,0.005833949,0.00010830258,0.000056606583,0.00008637326,0.0011175005,0.005365737,0.1055593,0.38764474,0.0050783153,0.48895454],"study_design_scores_gemma":[0.00010259905,0.000042847187,0.006464179,0.000018667924,0.0000054775546,0.00004268023,0.0000021875492,0.988541,0.0015785318,0.00032120608,0.0027762598,0.00010435205],"about_ca_topic_score_codex":0.00033823415,"about_ca_topic_score_gemma":0.000050105842,"teacher_disagreement_score":0.9831753,"about_ca_system_score_codex":0.000024866493,"about_ca_system_score_gemma":0.000040165516,"threshold_uncertainty_score":0.42391554},"labels":[],"label_agreement":null},{"id":"W4402754270","doi":"10.1109/cvpr52733.2024.02674","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Graph; Language model; Theoretical computer science","score_opus":0.02582463357507845,"score_gpt":0.30266158494447193,"score_spread":0.27683695136939346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402754270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016259363,0.00036096567,0.97667956,0.0026306931,0.00020525906,0.00035883675,0.000017415185,0.00085195684,0.0026359723],"genre_scores_gemma":[0.7414111,0.0000059650706,0.25694713,0.0003997954,0.00015075524,0.0001612562,0.000047289774,0.000014555058,0.00086215977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990013,0.000031706633,0.0001565176,0.00042680287,0.00015284098,0.00023081669],"domain_scores_gemma":[0.99931675,0.00008178197,0.000016764378,0.0004637807,0.00005368808,0.000067217414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028286714,0.00011037116,0.00009211145,0.00013036253,0.00014460545,0.00031719066,0.0004413209,0.00004994637,0.000058224872],"category_scores_gemma":[0.000019185463,0.00009624018,0.000086254135,0.0003803263,0.0000094063535,0.00043839213,0.000099592726,0.000105380466,0.00010892483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011238172,0.000046123805,0.000025602569,0.000035474677,0.000016441965,0.000002047487,0.0011535793,0.005744387,0.02731567,0.9194241,0.003857806,0.04237763],"study_design_scores_gemma":[0.00014631347,0.000020966278,0.000092910246,0.000007797878,0.0000057781444,0.0000027537071,0.000018322271,0.98784226,0.0024277573,0.006879673,0.0024301729,0.00012530792],"about_ca_topic_score_codex":0.00022969666,"about_ca_topic_score_gemma":0.000051688417,"teacher_disagreement_score":0.98209786,"about_ca_system_score_codex":0.000024811703,"about_ca_system_score_gemma":0.000046174486,"threshold_uncertainty_score":0.39245608},"labels":[],"label_agreement":null},{"id":"W4402772286","doi":"10.1109/cvpr52733.2024.01355","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Perspective (graphical); Computer science; Human–computer interaction; Artificial intelligence; Natural language processing","score_opus":0.02926812550214529,"score_gpt":0.357759155973917,"score_spread":0.3284910304717717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402772286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15370025,0.00064368604,0.8161112,0.005554781,0.00014756172,0.0003544838,0.000003846005,0.00083193736,0.022652268],"genre_scores_gemma":[0.8036267,0.0000018419144,0.1960558,0.00007843756,0.00003757555,0.000027028582,0.0000013354553,0.000012172102,0.0001591176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982645,0.00011689986,0.00023892788,0.00064675306,0.0005179548,0.00021499286],"domain_scores_gemma":[0.99832255,0.0005926225,0.00006769788,0.0007664601,0.00018431219,0.00006633125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090305874,0.0001488321,0.00017331148,0.00014249746,0.00019923455,0.00020843909,0.0008214459,0.000064211694,0.000098876946],"category_scores_gemma":[0.00025549854,0.0001248014,0.00009451635,0.0005885012,0.00006154116,0.00062037905,0.00023660138,0.000321303,0.000058830134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030161775,0.000080148704,0.00012998433,0.00009082896,0.000035416873,0.000004144227,0.090296805,0.054531146,0.0037230882,0.8265341,0.00014151065,0.024429813],"study_design_scores_gemma":[0.00008465844,0.000077078956,0.0018367554,0.000068107205,0.000009285589,0.00000572551,0.0015184841,0.9384106,0.0003582834,0.05749167,0.000011761031,0.00012760078],"about_ca_topic_score_codex":0.006346277,"about_ca_topic_score_gemma":0.000084482956,"teacher_disagreement_score":0.8838794,"about_ca_system_score_codex":0.0001923584,"about_ca_system_score_gemma":0.00011320601,"threshold_uncertainty_score":0.9593715},"labels":[],"label_agreement":null},{"id":"W4402904107","doi":"10.1109/cvprw63382.2024.00708","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Closed captioning; Computer science; Speech recognition; Artificial intelligence; Image (mathematics)","score_opus":0.012493589958756626,"score_gpt":0.31336517459600666,"score_spread":0.30087158463725006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402904107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09366612,0.0002709993,0.900588,0.0023326743,0.000100946316,0.0003733252,0.000005170576,0.0014187923,0.0012439692],"genre_scores_gemma":[0.86366576,0.0000015830765,0.13263279,0.00023960882,0.000077995035,0.000231515,0.000008581335,0.000018497989,0.003123667],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989166,0.000023379513,0.00018888824,0.00044806392,0.00015113088,0.00027188726],"domain_scores_gemma":[0.99929994,0.00026067,0.000025669511,0.00028595212,0.000044897944,0.000082854946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002912615,0.00012701724,0.00013611246,0.0001234197,0.00015223051,0.0004177384,0.00039986408,0.00005414291,0.000026390702],"category_scores_gemma":[0.00004884139,0.00011231556,0.00010018234,0.00031300337,0.000018455414,0.0003032845,0.00005603235,0.00014185005,0.00015884535],"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":[0.0000057267566,0.000054611843,0.000004538693,0.000041411913,0.000026772119,0.0000030845035,0.0029245028,0.763625,0.0045473794,0.12112105,0.0017726155,0.105873294],"study_design_scores_gemma":[0.00031106896,0.000034547244,0.000026658725,0.000014939778,0.00001011316,0.000006567515,0.00004389389,0.9978584,0.00014020194,0.00047031237,0.0009393001,0.0001440034],"about_ca_topic_score_codex":0.00007678003,"about_ca_topic_score_gemma":0.000037927806,"teacher_disagreement_score":0.7699996,"about_ca_system_score_codex":0.00004728443,"about_ca_system_score_gemma":0.000107794476,"threshold_uncertainty_score":0.45800957},"labels":[],"label_agreement":null},{"id":"W4402961730","doi":"10.1007/978-3-031-72784-9_27","title":"SafaRi: Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Segmentation; Transformer; Artificial intelligence; Sequence (biology); Computer vision; Pattern recognition (psychology); Electrical engineering; Voltage; Biology","score_opus":0.039102226118176285,"score_gpt":0.3031783288866046,"score_spread":0.26407610276842836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402961730","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":[0.00020984153,0.00026701464,0.9930919,0.00140758,0.000925181,0.0012137824,0.000027688558,0.00036748545,0.0024895447],"genre_scores_gemma":[0.2407322,0.0000233284,0.757759,0.00051173504,0.00029275817,0.00015679149,0.000026275098,0.000058366306,0.00043959386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960909,0.00002864191,0.00055781,0.0018913572,0.0008177826,0.0006134902],"domain_scores_gemma":[0.9977536,0.00056174694,0.00019473002,0.0010809435,0.00024068389,0.00016824828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070445164,0.0005493785,0.00042992595,0.0007377212,0.0003905884,0.00055653515,0.0024540867,0.00030605143,0.000018504701],"category_scores_gemma":[0.000047792215,0.00049916335,0.00017972263,0.00057207205,0.00036234688,0.0007730264,0.00042788155,0.00093038206,0.00007079749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019652396,0.00002916993,0.00001824439,0.00014522634,0.000018331826,0.000016695209,0.0024888595,0.07092346,0.03218238,0.077271484,0.000016058859,0.81687045],"study_design_scores_gemma":[0.00023505367,0.00016341191,0.00005167149,0.00058124564,0.0000143896805,0.000022319351,6.0237466e-7,0.8337447,0.013083926,0.15091358,0.000638739,0.0005503677],"about_ca_topic_score_codex":0.000090487105,"about_ca_topic_score_gemma":0.00005476833,"teacher_disagreement_score":0.81632006,"about_ca_system_score_codex":0.00049460336,"about_ca_system_score_gemma":0.00041572252,"threshold_uncertainty_score":0.999746},"labels":[],"label_agreement":null},{"id":"W4402963229","doi":"10.1145/3664647.3680815","title":"Text-Region Matching for Multi-Label Image Recognition with Missing Labels","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"RIKEN; Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Computer science; Bridging (networking); Pascal (unit); Artificial intelligence; Matching (statistics); Semantics (computer science); Benchmark (surveying); Class (philosophy); Margin (machine learning); Pattern recognition (psychology); Image (mathematics); Visualization; Semantic gap; Natural language processing; Machine learning; Image retrieval; Mathematics","score_opus":0.07659082094066458,"score_gpt":0.34661633013744864,"score_spread":0.27002550919678403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402963229","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":[0.012512558,0.00010639682,0.97462666,0.008361388,0.00029047963,0.0012591213,0.000025232821,0.0013857625,0.001432395],"genre_scores_gemma":[0.07049713,0.000007742447,0.9273075,0.00032953193,0.0001478372,0.0006023333,0.00009910433,0.00007270531,0.0009361075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977344,0.00007661403,0.00036337285,0.0012111234,0.00025092604,0.0003635628],"domain_scores_gemma":[0.9982417,0.00021777597,0.00024070799,0.00093236385,0.00024208525,0.00012533493],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00035886676,0.00038673874,0.0003130741,0.00024635295,0.0002526327,0.0010791983,0.000960915,0.00022579929,0.000011462178],"category_scores_gemma":[0.000066030814,0.00032501723,0.00011048176,0.0002761757,0.000049935697,0.00022834513,0.0013270713,0.0009943336,0.0002689141],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002245759,0.00031977633,0.000056932815,0.0013909077,0.0001499207,0.000025901038,0.0018008162,0.00091250124,0.006345236,0.017924068,0.0015231209,0.9695284],"study_design_scores_gemma":[0.0005668666,0.00004749545,0.00031575584,0.0006886498,0.000060034534,0.00003836936,0.000021804355,0.91464376,0.0013252944,0.08157394,0.00018522124,0.0005327895],"about_ca_topic_score_codex":0.00090986124,"about_ca_topic_score_gemma":0.00004446523,"teacher_disagreement_score":0.9689956,"about_ca_system_score_codex":0.00012330823,"about_ca_system_score_gemma":0.00019208292,"threshold_uncertainty_score":0.9999578},"labels":[],"label_agreement":null},{"id":"W4403289479","doi":"10.1016/j.knosys.2024.112610","title":"Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Multimodal Machine Learning Applications","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":"Carleton University","funders":"Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Modal; Computer science; Feature (linguistics); Fusion; Artificial intelligence; Computer vision; Human–computer interaction; Linguistics; Materials science","score_opus":0.009174197934916771,"score_gpt":0.28593626638038167,"score_spread":0.2767620684454649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403289479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5178989,0.01092705,0.4587696,0.0026920494,0.0029702645,0.0022546866,0.000054626267,0.0013107467,0.00312206],"genre_scores_gemma":[0.9970167,0.0000027189135,0.0014934952,0.00007851954,0.00016627928,0.0002878414,0.00007638319,0.000036412162,0.0008416287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977785,0.00031867638,0.00034546823,0.0008567174,0.00040478155,0.0002958627],"domain_scores_gemma":[0.99848396,0.0004196478,0.00009945693,0.0008082157,0.00004211093,0.00014662593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006002862,0.00028767847,0.0002572046,0.00039923255,0.00014215847,0.0002990221,0.00050011807,0.00020512255,0.00003109183],"category_scores_gemma":[0.000040121347,0.00025212075,0.00008936949,0.00038964674,0.00007366311,0.00020348853,0.00010984181,0.0005577733,0.0004587414],"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":[0.00036370655,0.004087049,0.09063546,0.008473615,0.0001167296,0.00083528383,0.032354806,0.39977983,0.07182606,0.035354,0.019734662,0.3364388],"study_design_scores_gemma":[0.0006301574,0.00012640741,0.018847294,0.00074097887,0.000005785155,0.0000056839353,0.000022447006,0.9583797,0.00026724077,0.000017517337,0.020696718,0.0002600987],"about_ca_topic_score_codex":0.0003782444,"about_ca_topic_score_gemma":0.000015871456,"teacher_disagreement_score":0.5585998,"about_ca_system_score_codex":0.0010321245,"about_ca_system_score_gemma":0.00022153546,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W4403585977","doi":"10.48550/arxiv.2409.03868","title":"Few-shot Adaptation of Medical Vision-Language Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Adaptation (eye); Shot (pellet); Computer science; Computer vision; Artificial intelligence; Optometry; Psychology; Medicine; Neuroscience; Chemistry","score_opus":0.08143299940705799,"score_gpt":0.252326790397519,"score_spread":0.17089379099046098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403585977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24624085,0.00014837107,0.7492529,0.00067879114,0.00024928988,0.00020368803,0.000014358073,0.00029997423,0.0029117647],"genre_scores_gemma":[0.9933511,0.00007362936,0.0059957793,0.000052760846,0.000056871242,0.0000023388727,0.000025553512,0.000020101745,0.00042187888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980977,0.00014141384,0.000257922,0.00096463197,0.00032433285,0.00021399633],"domain_scores_gemma":[0.99806243,0.00017554959,0.0002121854,0.0012384264,0.00012417867,0.00018725487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000450711,0.00023001555,0.00027917416,0.0003299124,0.00007497269,0.00008649064,0.0023966425,0.0003578634,0.000070988965],"category_scores_gemma":[0.0000643685,0.00025257524,0.00018551806,0.00066352944,0.00010210814,0.00018208694,0.0035025824,0.0010141146,0.00015321175],"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":[0.0000042497404,0.000061389626,0.00005434818,0.000092345545,0.00003721014,0.0000804073,0.0010004484,0.5903126,0.000024384033,0.40414295,0.00008260562,0.004107065],"study_design_scores_gemma":[0.00016697877,0.000024311848,0.00026617126,0.00016531946,0.00003694273,0.0000036510996,0.000107817774,0.9050758,0.000028724668,0.09386835,0.000054010256,0.00020193632],"about_ca_topic_score_codex":0.002843371,"about_ca_topic_score_gemma":0.00010365579,"teacher_disagreement_score":0.74711025,"about_ca_system_score_codex":0.00010916328,"about_ca_system_score_gemma":0.00037368812,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W4403780086","doi":"10.48550/arxiv.2409.13675","title":"OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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; Canada Research Chairs","keywords":"Computer science; Mobile robot; Mobile robot navigation; Human–computer interaction; Computer vision; Artificial intelligence; Robot; Robot control","score_opus":0.07101110598157714,"score_gpt":0.2646310933133353,"score_spread":0.19361998733175814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403780086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4354949,0.000045310124,0.5626351,0.00011965699,0.00017308605,0.0006715173,0.000079542675,0.00052324776,0.00025759946],"genre_scores_gemma":[0.95058626,0.000008134949,0.047375057,0.000060002214,0.00041012355,0.000026400738,0.0009591989,0.000042871234,0.00053195615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774754,0.00015311604,0.0002274136,0.0014211625,0.00012509253,0.00032567745],"domain_scores_gemma":[0.99837554,0.00009421891,0.00022595943,0.0010024816,0.00015276739,0.0001490451],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003176939,0.00032135815,0.00030463072,0.00024726987,0.0003192544,0.00025946106,0.0016372242,0.00034876168,0.0000060561274],"category_scores_gemma":[0.000020175796,0.0003706426,0.00024201222,0.00058040034,0.00007674311,0.0002844479,0.0017895442,0.00091485126,0.000045916557],"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":[0.000030581887,0.00071679713,0.00044161172,0.00050037814,0.00010786544,0.000041922143,0.0040005706,0.8791185,0.0006665315,0.08782548,0.0002587364,0.026291056],"study_design_scores_gemma":[0.00028381686,0.00008238713,0.0021775805,0.000054854045,0.00007153371,0.0000029299893,0.00022798934,0.9868251,0.00005094833,0.009707836,0.00012922478,0.00038580058],"about_ca_topic_score_codex":0.0006201873,"about_ca_topic_score_gemma":0.000031061387,"teacher_disagreement_score":0.5152601,"about_ca_system_score_codex":0.00022770747,"about_ca_system_score_gemma":0.00015707526,"threshold_uncertainty_score":0.99987453},"labels":[],"label_agreement":null},{"id":"W4403842289","doi":"10.1007/978-3-031-73347-5_17","title":"Reason2Drive: Towards Interpretable and Chain-Based Reasoning for Autonomous Driving","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Chain (unit)","score_opus":0.00964357850915667,"score_gpt":0.26815169255353205,"score_spread":0.2585081140443754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403842289","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":[0.00020965782,0.0006825259,0.99172544,0.0027786512,0.0008872741,0.00074017554,0.0000097461925,0.00048191444,0.0024846098],"genre_scores_gemma":[0.3497646,0.0000106436055,0.648533,0.00078406336,0.00026147842,0.00007809116,0.000007116198,0.000056692068,0.0005043424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964254,0.000024053768,0.00044941631,0.001973613,0.00046610556,0.00066141074],"domain_scores_gemma":[0.99728686,0.000757225,0.00023232216,0.0012635852,0.00024904864,0.00021094529],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010292722,0.0005443784,0.0005201021,0.00078865647,0.0003579109,0.0010753826,0.0023114071,0.00028375234,0.0000089405785],"category_scores_gemma":[0.00030462586,0.0005186336,0.00014461487,0.00049298204,0.00046478794,0.00031618786,0.0013028946,0.0009367312,0.000019290092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004578808,0.000015760195,0.00014019996,0.00014598877,0.000019451818,0.000018282857,0.0011429035,0.053916648,0.00016064243,0.09480866,0.000012397202,0.8496145],"study_design_scores_gemma":[0.0001764321,0.00011498558,0.0002455688,0.0008126942,0.000015357815,0.000037215992,1.5216746e-7,0.93560266,0.0002322852,0.059489943,0.002755046,0.00051762536],"about_ca_topic_score_codex":0.00012919096,"about_ca_topic_score_gemma":0.000069063615,"teacher_disagreement_score":0.88168603,"about_ca_system_score_codex":0.0003719504,"about_ca_system_score_gemma":0.000703525,"threshold_uncertainty_score":0.9999616},"labels":[],"label_agreement":null},{"id":"W4403990800","doi":"10.1007/978-3-031-72986-7_25","title":"TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Vector Institute; University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Image (mathematics); Artificial intelligence; Generative model; Natural language processing; Information retrieval","score_opus":0.0669570626640727,"score_gpt":0.353602100343215,"score_spread":0.2866450376791423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403990800","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":[0.0033717158,0.00065289694,0.9903692,0.0018480769,0.00047081878,0.0006293731,0.000006731352,0.00019029122,0.002460907],"genre_scores_gemma":[0.34317,0.00001876827,0.655461,0.00080280023,0.00020069368,0.000044500594,0.0000037002837,0.000039664683,0.0002588737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959447,0.000057317455,0.0005334938,0.0020047647,0.00085099146,0.00060874916],"domain_scores_gemma":[0.9976466,0.0008082977,0.00016460424,0.0010101468,0.00017539601,0.00019497031],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014321741,0.0004782771,0.0004509625,0.0014423591,0.0002504042,0.0012551396,0.0019898047,0.00018644992,0.000010529454],"category_scores_gemma":[0.0002415096,0.0004566625,0.00006838868,0.0010852808,0.00033423054,0.0007216838,0.0022804085,0.0010662316,0.00009354665],"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":[0.0000021036894,0.00001577642,0.000048676226,0.000053032047,0.0000075455296,0.000049383445,0.0043340554,0.5341828,0.0017594568,0.033028074,0.000006963407,0.42651215],"study_design_scores_gemma":[0.000098394485,0.00006276883,0.00025709794,0.00061052287,0.00000520674,0.000025390773,4.4120753e-7,0.7826997,0.00037222783,0.2154562,0.00003466683,0.00037737723],"about_ca_topic_score_codex":0.00024315434,"about_ca_topic_score_gemma":0.00021384658,"teacher_disagreement_score":0.4261348,"about_ca_system_score_codex":0.00032471062,"about_ca_system_score_gemma":0.00033528687,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W4404545360","doi":"10.1007/978-3-031-73021-4_23","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 Waterloo","funders":"","keywords":"Benchmarking; Computer science; Training (meteorology); Artificial intelligence; Human–computer interaction; Geography","score_opus":0.011900803562801286,"score_gpt":0.2410022629830654,"score_spread":0.2291014594202641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404545360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004902272,0.00013902022,0.9904026,0.0013569145,0.0009933759,0.0003378051,0.000008208249,0.00033071009,0.005941177],"genre_scores_gemma":[0.5437327,0.00003063612,0.45514634,0.0006130256,0.00027887954,0.0000066255284,0.000016816095,0.00002586265,0.00014911329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973132,0.0000220487,0.00043615274,0.0010187014,0.0007155314,0.000494367],"domain_scores_gemma":[0.99817634,0.00045219564,0.00023028761,0.0008062607,0.0001520331,0.0001828853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007469812,0.00042517507,0.00035411687,0.0011196195,0.0003240305,0.00091836666,0.0017132722,0.0002926553,0.000012699113],"category_scores_gemma":[0.00009252292,0.00042360363,0.00008165185,0.0007879056,0.0005269156,0.0014112879,0.0012939734,0.001244877,0.00005751297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026082657,0.0000050373274,0.00006941816,0.0000427331,0.000011485337,0.000021312275,0.0044666026,0.03882652,0.00003346474,0.094291754,0.000007739723,0.8622213],"study_design_scores_gemma":[0.0001919382,0.00008219004,0.0004607524,0.00027070873,0.000009705698,0.0000565213,0.0000013715402,0.9428531,0.000043119482,0.050992433,0.004580496,0.00045769385],"about_ca_topic_score_codex":0.00016296451,"about_ca_topic_score_gemma":0.00002895542,"teacher_disagreement_score":0.90402657,"about_ca_system_score_codex":0.00034425542,"about_ca_system_score_gemma":0.00044797154,"threshold_uncertainty_score":0.9998216},"labels":[],"label_agreement":null},{"id":"W4404554547","doi":"10.2139/ssrn.5028149","title":"Visualrwkv-Hm: Enhancing Linear Visual-Language Models Via Hybrid Mixing","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Multimodal Machine Learning Applications","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":"Mixing (physics); Computer science; Mathematics; Natural language processing; Artificial intelligence; Physics","score_opus":0.008782071585116355,"score_gpt":0.303193492823928,"score_spread":0.29441142123881164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404554547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14314502,0.007624673,0.8451958,0.0015778089,0.00087589055,0.00037247155,0.0000049035666,0.0006433317,0.0005601396],"genre_scores_gemma":[0.9768717,0.0009854175,0.019445993,0.00018016095,0.001455865,0.00007281503,0.000025139347,0.00013788135,0.00082497665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99319524,0.0003155745,0.00094917725,0.0013197764,0.0008589858,0.0033612489],"domain_scores_gemma":[0.9976073,0.00017083912,0.00059297803,0.0011402222,0.0002057007,0.0002829623],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0033873706,0.000677395,0.00063074194,0.0006483992,0.0004704834,0.0008096105,0.0027568922,0.0002960548,0.000019239287],"category_scores_gemma":[0.0001013946,0.0006677515,0.00050780305,0.00047877978,0.0000544437,0.00036486736,0.0031778573,0.014902821,0.00044067568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035339035,0.00044781424,0.000065557644,0.00043934415,0.0013355874,0.00022641044,0.0056638457,0.18523772,0.016125979,0.37177667,0.00017669774,0.418469],"study_design_scores_gemma":[0.00015425976,0.00008748607,0.000013292371,0.00017613405,0.00005642499,0.00072506885,0.00010345197,0.61281914,0.0010881516,0.3842652,0.00006343593,0.00044798598],"about_ca_topic_score_codex":0.0010663499,"about_ca_topic_score_gemma":0.000312917,"teacher_disagreement_score":0.8337267,"about_ca_system_score_codex":0.0021957033,"about_ca_system_score_gemma":0.004848486,"threshold_uncertainty_score":0.99957734},"labels":[],"label_agreement":null},{"id":"W4404782669","doi":"10.18653/v1/2024.emnlp-main.944","title":"On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Korea Advanced Institute of Science and Technology","keywords":"Situated; Computer science; Reading (process); Natural language; Natural (archaeology); Natural language processing; Artificial intelligence; Human–computer interaction; Linguistics","score_opus":0.012004506382721153,"score_gpt":0.3344200225874453,"score_spread":0.32241551620472414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404782669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7165072,0.0007109378,0.27956,0.0024245793,0.00012620282,0.00025965733,0.000001569417,0.00023397848,0.00017588717],"genre_scores_gemma":[0.9902537,0.00000970871,0.009232372,0.0003418415,0.000012655499,0.000017641412,0.0000074985805,0.000014259356,0.000110344365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990209,0.00004088154,0.00013594943,0.00045371175,0.00014273038,0.00020585959],"domain_scores_gemma":[0.9991886,0.00054543896,0.000029083474,0.00016759719,0.000009307826,0.000059993894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035502532,0.00012232806,0.00011338703,0.00023412706,0.00010900632,0.000826622,0.00013952641,0.000041959058,0.000004529855],"category_scores_gemma":[0.0000655603,0.00010193849,0.000021293994,0.00030959526,0.000027762457,0.00030381777,0.00011438539,0.00017446396,0.000005745862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012306919,0.00017344664,0.0013198059,0.00049443304,0.000069021,0.00015644457,0.05507266,0.0019712884,0.051120948,0.63986516,0.0007331326,0.24890062],"study_design_scores_gemma":[0.0003668944,0.00005899407,0.0044671814,0.0006229634,0.0000051813586,0.000012829378,0.003235783,0.9903799,0.00035936196,0.0003255908,0.000013610914,0.00015165149],"about_ca_topic_score_codex":0.00013087821,"about_ca_topic_score_gemma":0.000036814363,"teacher_disagreement_score":0.9884087,"about_ca_system_score_codex":0.000103187784,"about_ca_system_score_gemma":0.000011716181,"threshold_uncertainty_score":0.7971135},"labels":[],"label_agreement":null},{"id":"W4404783412","doi":"10.18653/v1/2022.aacl-main.61","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Economic and Social Research Council; Engineering and Physical Sciences Research Council","keywords":"Debiasing; Adversarial system; Computer science; Artificial intelligence; Computer vision; Natural language processing; Psychology; Cognitive science","score_opus":0.017603201543926292,"score_gpt":0.26099538542813217,"score_spread":0.24339218388420586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404783412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12557474,0.000035025634,0.85907805,0.0046451436,0.000092448034,0.0004377851,0.000001284388,0.00055222143,0.009583317],"genre_scores_gemma":[0.91660964,6.644203e-7,0.08185062,0.000487402,0.000064821645,0.0001763217,0.0000064393967,0.00002177077,0.0007823098],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979742,0.00038237622,0.0001987295,0.0005214236,0.00059627154,0.00032697097],"domain_scores_gemma":[0.99863714,0.00032205667,0.00014702743,0.00076547253,0.000048731443,0.00007959989],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007344374,0.00016489002,0.00014325239,0.00010157528,0.0014586443,0.00026100196,0.0012551708,0.000025491181,0.00013742935],"category_scores_gemma":[0.00006698756,0.00010926103,0.00006145456,0.00073253247,0.000054287866,0.00036337605,0.00059994636,0.00075454434,0.00003870628],"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":[0.000029450253,0.0001162268,0.0009468941,0.0000054622064,0.000031777177,0.000012830079,0.014452689,0.9044392,0.0020403266,0.042547,0.00020427137,0.035173874],"study_design_scores_gemma":[0.00042018702,0.00017419277,0.0012215847,0.0000071575405,0.0000086702,0.000060029688,0.0010780126,0.9927996,0.00017104452,0.0010216341,0.0028361399,0.0002017887],"about_ca_topic_score_codex":0.0014928359,"about_ca_topic_score_gemma":0.000037208265,"teacher_disagreement_score":0.79103494,"about_ca_system_score_codex":0.00008454046,"about_ca_system_score_gemma":0.00012935216,"threshold_uncertainty_score":0.99984133},"labels":[],"label_agreement":null},{"id":"W4404783635","doi":"10.18653/v1/2024.findings-emnlp.83","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Visual language; Human–computer interaction; Natural language processing; Knowledge management; World Wide Web; Linguistics","score_opus":0.007573520661421284,"score_gpt":0.3036279570150422,"score_spread":0.2960544363536209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404783635","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02662303,0.0005416931,0.93758005,0.00077602523,0.00009908757,0.00015732895,5.8625363e-7,0.0014161437,0.032806043],"genre_scores_gemma":[0.79590225,0.0000041873527,0.20221357,0.00011336473,0.000081053935,0.000047093705,0.0000018972602,0.00001802008,0.0016185933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894136,0.000033736756,0.00013040664,0.0004810278,0.00015601002,0.0002574676],"domain_scores_gemma":[0.9992567,0.0001304488,0.00002031751,0.00044913008,0.000039167277,0.00010424931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016529951,0.00013927261,0.000105434694,0.00014017035,0.000103598475,0.00026546084,0.0004852651,0.00003626169,0.0000468956],"category_scores_gemma":[0.000007283115,0.000100906174,0.000037457303,0.0006390956,0.000022856942,0.0006252,0.00017630646,0.0002207807,0.0005166443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025127088,0.00009664215,0.00015509865,0.00006634113,0.000029538243,0.00003125648,0.0059137307,0.01949325,0.002892741,0.67259043,0.00084021565,0.29788822],"study_design_scores_gemma":[0.00007938632,0.000059562055,0.00027112805,0.000049154438,0.000005144066,0.000019099345,0.00003238876,0.99351436,0.0009905667,0.0022348443,0.002579946,0.00016441653],"about_ca_topic_score_codex":0.00021944202,"about_ca_topic_score_gemma":0.00008732895,"teacher_disagreement_score":0.97402114,"about_ca_system_score_codex":0.000054757606,"about_ca_system_score_gemma":0.00008889793,"threshold_uncertainty_score":0.6640589},"labels":[],"label_agreement":null},{"id":"W4404792981","doi":"10.18653/v1/2024.emnlp-main.633","title":"TroL: Traversal of Layers for Large Language and Vision Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Ministry of Science and ICT, South Korea; Korea Institute of Science and Technology Information","keywords":"Tree traversal; Computer science; Artificial intelligence; Programming language","score_opus":0.010395003013021922,"score_gpt":0.32150961418095675,"score_spread":0.3111146111679348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404792981","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059907477,0.00013564005,0.9368111,0.0011072184,0.000034721274,0.00013765502,0.000008954247,0.0001600125,0.0016972101],"genre_scores_gemma":[0.90607405,0.0000029825728,0.09355082,0.000058846577,0.00001350643,0.00001563102,0.0000023797777,0.000005189934,0.00027656648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995515,0.000011211195,0.00008202597,0.00018683856,0.00007360134,0.00009487698],"domain_scores_gemma":[0.99964625,0.000119557146,0.0000132579025,0.00017407647,0.000014917185,0.00003194071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015653204,0.000047697256,0.00006363588,0.000056698635,0.000030887553,0.000052385396,0.00016688612,0.000025061132,0.000007881702],"category_scores_gemma":[0.000009602549,0.0000387016,0.000031355652,0.00010900999,0.000008738916,0.00017807828,0.00006190904,0.000051201598,0.000005971366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033936565,0.000027551832,0.00004823911,0.000058842612,0.000010739264,8.599268e-7,0.00264285,0.0010458297,0.0061442493,0.9434745,0.0005216712,0.046021324],"study_design_scores_gemma":[0.00016190697,0.000042170563,0.00045878382,0.000009088611,0.0000034794632,0.0000015092611,0.00005158828,0.9928613,0.0006603799,0.0048599094,0.00084494933,0.000044962584],"about_ca_topic_score_codex":0.00011670376,"about_ca_topic_score_gemma":0.000008700012,"teacher_disagreement_score":0.99181545,"about_ca_system_score_codex":0.0000059508834,"about_ca_system_score_gemma":0.000014503648,"threshold_uncertainty_score":0.15782054},"labels":[],"label_agreement":null},{"id":"W4404820294","doi":"10.1007/978-3-031-72848-8_26","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 for Social Innovation","funders":"","keywords":"Closed captioning; Computer science; Image (mathematics); Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.008056717923322488,"score_gpt":0.2529892578538221,"score_spread":0.2449325399304996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404820294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074401393,0.00031062937,0.99116427,0.0021522862,0.0007963286,0.0006948758,0.000008334775,0.0004480042,0.0036812846],"genre_scores_gemma":[0.5556617,0.000009230408,0.44266844,0.0005218237,0.00030194793,0.00003691817,0.000016906195,0.00005480046,0.00072826876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606466,0.00003520569,0.0004905232,0.0017758638,0.0010199534,0.0006137845],"domain_scores_gemma":[0.9975608,0.00034687144,0.00030535192,0.0013228293,0.0002962685,0.00016790806],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00057530846,0.00057098677,0.00050449744,0.00081373774,0.00040871635,0.0013981946,0.002063905,0.00022330425,0.000040163493],"category_scores_gemma":[0.00005129005,0.00047829413,0.000100006495,0.0008716362,0.00053981284,0.0006834109,0.0006925442,0.0011134038,0.00019678395],"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":[0.000027440086,0.000043948494,0.00028201155,0.00023987044,0.00009438586,0.00023175601,0.0025102473,0.51590115,0.004830314,0.17634197,0.00004592622,0.29945096],"study_design_scores_gemma":[0.0004380094,0.00013132843,0.0004722235,0.0003890122,0.000029478164,0.000109680645,4.0257618e-7,0.87291723,0.000674035,0.123897865,0.0003619216,0.0005787801],"about_ca_topic_score_codex":0.00022831834,"about_ca_topic_score_gemma":0.00023997463,"teacher_disagreement_score":0.5549177,"about_ca_system_score_codex":0.00039589306,"about_ca_system_score_gemma":0.00047353577,"threshold_uncertainty_score":0.9997669},"labels":[],"label_agreement":null},{"id":"W4404893151","doi":"10.1007/978-3-031-72897-6_19","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence","score_opus":0.03741656571281926,"score_gpt":0.3051162996673086,"score_spread":0.2676997339544893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404893151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029634606,0.00080443965,0.9952172,0.0010689026,0.0006583696,0.00086547644,0.00071612175,0.00015304785,0.00048682195],"genre_scores_gemma":[0.6013475,0.000013139362,0.39747924,0.00046020997,0.0002063663,0.00005474471,0.00029057154,0.000048569687,0.00009967951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674565,0.00002468927,0.0005826677,0.0014673339,0.00067237316,0.00050726393],"domain_scores_gemma":[0.995375,0.0025786192,0.0003152975,0.0014723504,0.00011541127,0.00014335144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071982393,0.00044660122,0.0005242923,0.0007393411,0.0001904278,0.00039032698,0.0029107358,0.00021664088,0.000010237322],"category_scores_gemma":[0.00024620816,0.0004147055,0.00013803986,0.0005545322,0.0006927061,0.00051003153,0.0012082345,0.00066238415,0.00001906277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008423173,0.000047598125,0.000019941388,0.00028110878,0.00004066575,0.00007818734,0.0050298567,0.38418737,0.00022367577,0.52853054,0.00031351633,0.08123912],"study_design_scores_gemma":[0.00015686656,0.000089874105,0.000004120073,0.0003322515,0.000012820744,0.000017824968,0.0000011423114,0.62004656,0.00021126284,0.3785673,0.00027179136,0.0002882],"about_ca_topic_score_codex":0.00021268359,"about_ca_topic_score_gemma":0.00007110508,"teacher_disagreement_score":0.6013179,"about_ca_system_score_codex":0.00036750868,"about_ca_system_score_gemma":0.00037827052,"threshold_uncertainty_score":0.9998305},"labels":[],"label_agreement":null},{"id":"W4404999448","doi":"10.3390/info15120766","title":"Enabling Perspective-Aware Ai with Contextual Scene Graph Generation","year":2024,"lang":"en","type":"article","venue":"Information","topic":"Multimodal Machine Learning Applications","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Contextual design; Artificial intelligence; Graph; Human–computer interaction; Perspective (graphical); Data science; Natural language processing; Object (grammar); Theoretical computer science","score_opus":0.012782248264085423,"score_gpt":0.2756536029919525,"score_spread":0.2628713547278671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404999448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012876829,0.0000672093,0.9798029,0.0042613936,0.00018866273,0.00019688148,0.0000037681207,0.00054665504,0.0020556839],"genre_scores_gemma":[0.98578966,0.000005060074,0.013430795,0.0005356194,0.00009403975,0.00005033637,0.000041909596,0.0000051478855,0.00004744401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993179,0.000022046295,0.00016897195,0.0001474638,0.00021850159,0.000125131],"domain_scores_gemma":[0.9994179,0.00003129325,0.00004906819,0.00024009742,0.00021951455,0.000042125277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016102963,0.00009009288,0.00006135379,0.0002264055,0.0001586378,0.00066424895,0.00021704371,0.000038598053,0.000014099434],"category_scores_gemma":[0.000026522686,0.000074687756,0.000026888716,0.00051636435,0.000020525853,0.0032177682,0.000041958217,0.00017649772,0.00029039427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006979326,0.000022527416,0.0003393804,0.000050009185,0.00003672523,0.0000026842783,0.010946321,0.024811737,0.00089525484,0.7323886,0.003220978,0.22727877],"study_design_scores_gemma":[0.00014705908,0.00004584376,0.0013066214,0.0000267505,0.0000046475434,0.000020186213,0.00019577252,0.98670495,0.00053263275,0.001040679,0.009854983,0.000119894044],"about_ca_topic_score_codex":0.00040472683,"about_ca_topic_score_gemma":0.00001990089,"teacher_disagreement_score":0.97291285,"about_ca_system_score_codex":0.00009592123,"about_ca_system_score_gemma":0.00008834465,"threshold_uncertainty_score":0.6405368},"labels":[],"label_agreement":null},{"id":"W4405023785","doi":"10.1109/cvpr52734.2025.01822","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Computer science; Resource (disambiguation); Artificial intelligence; Data science; Natural language processing; Geography","score_opus":0.022328242076495475,"score_gpt":0.3794272945488076,"score_spread":0.3570990524723121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405023785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48192182,0.00012977728,0.09037516,0.034156874,0.00021148838,0.000567986,0.000006096519,0.0013138015,0.39131698],"genre_scores_gemma":[0.91513187,0.0000025964257,0.06569078,0.006526785,0.00004190255,0.000041827207,0.000010375534,0.0000068642735,0.012546988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998931,0.00009073329,0.00015414697,0.00038520157,0.00022586893,0.00021307325],"domain_scores_gemma":[0.999044,0.00018332039,0.000057715366,0.0006081515,0.000057115718,0.0000496767],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022599618,0.00013312289,0.00011406265,0.00010677849,0.00014560061,0.00017013431,0.00082469126,0.000044649067,0.0002970384],"category_scores_gemma":[0.00009842736,0.00010336765,0.000054032014,0.00027946764,0.000022253578,0.00015175756,0.00032733713,0.000180007,0.0015117537],"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":[0.000020405958,0.00038221234,0.06549941,0.00009894813,0.00018184743,0.00003301172,0.006038045,0.007720529,0.027607832,0.40980998,0.07573645,0.40687135],"study_design_scores_gemma":[0.0013489678,0.00017834218,0.7105346,0.00015477918,0.000053189382,0.000012831462,0.0016712346,0.26191533,0.006182518,0.002299559,0.014850084,0.0007986035],"about_ca_topic_score_codex":0.0014882742,"about_ca_topic_score_gemma":0.00003767823,"teacher_disagreement_score":0.64503515,"about_ca_system_score_codex":0.000045255405,"about_ca_system_score_gemma":0.00002664893,"threshold_uncertainty_score":0.9992657},"labels":[],"label_agreement":null},{"id":"W4405140008","doi":"10.1007/978-981-96-0917-8_17","title":"Vision Language Models are blind","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Computer vision; Speech recognition","score_opus":0.017041941641969042,"score_gpt":0.2930850625544102,"score_spread":0.27604312091244115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405140008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021870037,0.000853511,0.98313165,0.0030255965,0.0009687793,0.00041140153,0.000008788063,0.00050023344,0.010881323],"genre_scores_gemma":[0.5044688,0.00003356642,0.4915295,0.0013067204,0.00060512533,0.00002691232,0.000010206211,0.000075123346,0.0019440829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607843,0.000024574045,0.0004335933,0.0018843838,0.00097429764,0.00060474064],"domain_scores_gemma":[0.9971272,0.00035374166,0.00023549751,0.0019259726,0.00015475391,0.00020283397],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072954927,0.00050406804,0.00043404804,0.000995828,0.00022532852,0.00091016304,0.003754475,0.0003193092,0.000025775353],"category_scores_gemma":[0.00005324244,0.00044926867,0.00014622218,0.000815464,0.0003806997,0.00059958146,0.0020867155,0.0013879581,0.0004050672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000423005,0.000039661343,0.000021483791,0.000078767414,0.000013213155,0.00015973141,0.0017432116,0.33163753,0.00023310352,0.13543308,0.000074335374,0.5305617],"study_design_scores_gemma":[0.00011333025,0.000047746013,0.000066437424,0.00032901912,0.000005638938,0.000033641645,1.4509459e-7,0.7331767,0.00012145335,0.26517606,0.00055989745,0.00036989938],"about_ca_topic_score_codex":0.00011496887,"about_ca_topic_score_gemma":0.00009711508,"teacher_disagreement_score":0.5301918,"about_ca_system_score_codex":0.00027743718,"about_ca_system_score_gemma":0.0002874842,"threshold_uncertainty_score":0.9997959},"labels":[],"label_agreement":null},{"id":"W4405414691","doi":"10.1007/s00371-024-03729-0","title":"Dynamic text prompt joint multimodal features for accurate plant disease image captioning","year":2024,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Multimodal Machine Learning Applications","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":"Carleton University","funders":"Natural Science Foundation of Hebei Province; National Natural Science Foundation of China","keywords":"Closed captioning; Computer science; Feature (linguistics); Artificial intelligence; Plant disease; Image (mathematics); Machine learning; Natural language processing","score_opus":0.01490606545697368,"score_gpt":0.31847195957354424,"score_spread":0.30356589411657053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405414691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05832147,0.00020944867,0.9308178,0.008406746,0.0005519024,0.0008158161,0.000044606495,0.0007840012,0.000048215054],"genre_scores_gemma":[0.8867386,0.0000032478988,0.11202733,0.00039362977,0.00027955818,0.00023956606,0.000059531583,0.000032493674,0.00022601224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984177,0.000108142165,0.00025120034,0.00060931925,0.00024338906,0.00037029118],"domain_scores_gemma":[0.998844,0.00031538552,0.00007120727,0.00055653637,0.000070920105,0.00014193018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003680032,0.00023561144,0.00016884686,0.00012924439,0.0004154758,0.0009320166,0.00084754726,0.000046038862,0.000011443833],"category_scores_gemma":[0.000033713844,0.00016010345,0.00015521786,0.00029096022,0.00007629937,0.00034925048,0.00045289865,0.00035192413,0.00023174807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022911502,0.0008761086,0.00029760477,0.001132368,0.00053140026,0.0001858635,0.012196517,0.10859238,0.024041831,0.28350544,0.029984917,0.53842646],"study_design_scores_gemma":[0.00019635475,0.00007149208,0.027118977,0.000080814905,0.000020123563,0.000024035797,0.0000064209485,0.96817195,0.00008731084,0.0023977992,0.0016037857,0.0002209401],"about_ca_topic_score_codex":0.00008537691,"about_ca_topic_score_gemma":0.0000071542754,"teacher_disagreement_score":0.85957956,"about_ca_system_score_codex":0.000070033864,"about_ca_system_score_gemma":0.00009580062,"threshold_uncertainty_score":0.8987458},"labels":[],"label_agreement":null},{"id":"W4405436672","doi":"10.1016/j.neucom.2024.129177","title":"A simple yet effective knowledge guided method for entity-aware video captioning on a basketball benchmark","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Multimodal Machine Learning Applications","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":"Beijing Postdoctoral Science Foundation; Natural Science Foundation of Beijing Municipality; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Closed captioning; Basketball; Computer science; Benchmark (surveying); Simple (philosophy); Artificial intelligence; Machine learning; Information retrieval; Natural language processing; Image (mathematics)","score_opus":0.019089827883115702,"score_gpt":0.36385435458996085,"score_spread":0.34476452670684515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405436672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024409305,0.000072874325,0.96995443,0.0006540804,0.0006165453,0.0011178595,0.000007655744,0.0010581155,0.0021091078],"genre_scores_gemma":[0.80209714,6.2778815e-7,0.19679491,0.00038984063,0.00029698675,0.00029167795,0.000012738301,0.000040239498,0.00007586353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975788,0.00035535204,0.0003479204,0.0010459676,0.00021761059,0.0004543531],"domain_scores_gemma":[0.995524,0.0035552334,0.000104347346,0.00055865373,0.0001369155,0.00012084688],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009876094,0.00026367753,0.00025265306,0.0002759105,0.0005017546,0.00050424156,0.00077111303,0.00008010173,0.000009828356],"category_scores_gemma":[0.000375107,0.00026717116,0.00016653992,0.00080227497,0.000019962954,0.00022363068,0.00043126446,0.0004784643,0.00014474838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000146279735,0.00018865663,0.0005582093,0.0004180098,0.00008663783,0.00003096976,0.0022552756,0.086678945,0.0069684926,0.11813935,0.007892541,0.77676827],"study_design_scores_gemma":[0.00027269797,0.00018124009,0.004611653,0.00014645031,0.000017412394,0.000028520126,0.0000056684066,0.9738282,0.0006937786,0.0047748913,0.01519876,0.00024075194],"about_ca_topic_score_codex":0.00018226674,"about_ca_topic_score_gemma":0.00001143076,"teacher_disagreement_score":0.8871492,"about_ca_system_score_codex":0.00012443856,"about_ca_system_score_gemma":0.0000884256,"threshold_uncertainty_score":0.99997807},"labels":[],"label_agreement":null},{"id":"W4405766356","doi":"10.48550/arxiv.2412.16694","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Context (archaeology); Open domain; Question answering; Domain (mathematical analysis); Computer science; Information retrieval; History; Mathematics; Archaeology","score_opus":0.054690372831736674,"score_gpt":0.2341087230419267,"score_spread":0.17941835021019004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405766356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20276985,0.00008973023,0.78535104,0.0013291786,0.0009867975,0.00086772983,0.00004239221,0.0009724893,0.0075908294],"genre_scores_gemma":[0.99097395,0.000044176722,0.0046937116,0.00018622697,0.00011163354,0.000012693272,0.000041273954,0.000048115468,0.0038882128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705917,0.00018693594,0.0003061135,0.0018385104,0.00014341474,0.0004658801],"domain_scores_gemma":[0.9970488,0.00015014397,0.00026890982,0.0020776566,0.00018048924,0.00027401594],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005002515,0.0004706376,0.00044360175,0.00036225215,0.00033868343,0.0007495511,0.004904113,0.00035572756,0.00009450823],"category_scores_gemma":[0.00004065593,0.00055352953,0.00024657656,0.0008578605,0.00014178132,0.00049570104,0.011191837,0.0015901666,0.001178534],"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":[0.000017803912,0.000112466056,0.0049722935,0.00022720124,0.00016697505,0.00054386025,0.0008138181,0.08619419,0.000024634426,0.90232086,0.00065676856,0.0039491113],"study_design_scores_gemma":[0.0005202135,0.000042036732,0.0054717674,0.00035809897,0.00007490974,0.000019698584,0.00014025446,0.77993846,0.000053994245,0.20932113,0.0032543757,0.0008050906],"about_ca_topic_score_codex":0.0038136893,"about_ca_topic_score_gemma":0.0004834409,"teacher_disagreement_score":0.78820413,"about_ca_system_score_codex":0.00054181693,"about_ca_system_score_gemma":0.00042897582,"threshold_uncertainty_score":0.9996916},"labels":[],"label_agreement":null},{"id":"W4405812114","doi":"10.1109/tpami.2024.3522295","title":"A Review of Deep Learning for Video Captioning","year":2024,"lang":"en","type":"review","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Closed captioning; Computer science; Artificial intelligence; Deep learning; Computer vision; Natural language processing; Multimedia; Image (mathematics)","score_opus":0.038680409321068095,"score_gpt":0.3533350145359122,"score_spread":0.3146546052148441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405812114","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":[4.990513e-8,0.4930765,0.50630754,0.000060863655,0.000074095165,0.0003588404,0.000029932493,0.00007456989,0.00001758682],"genre_scores_gemma":[0.003206652,0.9910859,0.004742466,0.00020593272,0.000028189632,0.00054374355,0.00004155385,0.00004345603,0.00010211446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971661,0.00023444694,0.0011058969,0.0009595639,0.00026680325,0.00026717453],"domain_scores_gemma":[0.9977887,0.0006141767,0.00054293725,0.00078500086,0.00014506537,0.00012407808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066533755,0.0004872657,0.0016922186,0.0010399012,0.00021729147,0.00013450622,0.0008147939,0.00013036025,0.00007597768],"category_scores_gemma":[0.000036378606,0.00039108886,0.0015152907,0.0023432092,0.000060677543,0.000115796756,0.000016121634,0.0008875323,0.00006479816],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.2477403e-7,0.000045532433,0.0000013006113,0.034363884,0.001018437,0.0000013639475,0.000058785594,0.0022411474,3.382181e-7,0.00013500376,0.0000062839235,0.96212727],"study_design_scores_gemma":[0.000079035526,0.00025813875,0.0000038915473,0.07554998,0.029131975,0.00007194918,0.000012321467,0.5772578,0.000109321205,0.00024861543,0.31607974,0.0011972123],"about_ca_topic_score_codex":0.0007138774,"about_ca_topic_score_gemma":0.00016110782,"teacher_disagreement_score":0.9609301,"about_ca_system_score_codex":0.00006769127,"about_ca_system_score_gemma":0.00006072378,"threshold_uncertainty_score":0.9998541},"labels":[],"label_agreement":null},{"id":"W4405882647","doi":"10.1007/978-981-96-2061-6_31","title":"MM-CARP: Multimodal Model with Cross-Modal Retrieval-Augmented and Visual Region Perception","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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 New Brunswick","funders":"","keywords":"Computer science; Modal; Perception; Artificial intelligence; Computer vision; Pattern recognition (psychology)","score_opus":0.014400977277997834,"score_gpt":0.2924754395763145,"score_spread":0.27807446229831667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405882647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011409789,0.00017565627,0.98424226,0.0014569685,0.00039525895,0.00065441156,0.000006831325,0.00046978885,0.0011890269],"genre_scores_gemma":[0.7441878,0.00002848405,0.2540898,0.00045149986,0.00025633865,0.00001725401,0.000012481358,0.000062436855,0.00089394866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952162,0.000033432767,0.00051474286,0.0024447695,0.0011302109,0.000660665],"domain_scores_gemma":[0.99781,0.00025562834,0.00025994587,0.0011065126,0.00031139562,0.00025650815],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006054967,0.00068821805,0.0005041692,0.0008832005,0.0004402003,0.0012824223,0.0016920246,0.0004186936,0.000007965759],"category_scores_gemma":[0.000055845863,0.00058368105,0.00010705078,0.0007702522,0.00110991,0.0007648299,0.0013828293,0.0014884042,0.000060507562],"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":[0.00009048649,0.0000915605,0.0009835252,0.0001795987,0.000041200397,0.00014163373,0.0023232102,0.5696635,0.0014624213,0.02598442,0.000013344381,0.39902508],"study_design_scores_gemma":[0.00039401813,0.0002449701,0.0020885307,0.0003497554,0.000017454238,0.00017847319,2.7436045e-7,0.95906746,0.00012341978,0.036802124,0.00008137335,0.00065213174],"about_ca_topic_score_codex":0.000115694136,"about_ca_topic_score_gemma":0.00003883502,"teacher_disagreement_score":0.73277795,"about_ca_system_score_codex":0.00044574408,"about_ca_system_score_gemma":0.00043587852,"threshold_uncertainty_score":0.99975437},"labels":[],"label_agreement":null},{"id":"W4406343535","doi":"10.1007/s43621-025-00815-8","title":"A comprehensive review of large language models: issues and solutions in learning environments","year":2025,"lang":"en","type":"review","venue":"Discover Sustainability","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":77,"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":"University of Johannesburg","keywords":"Computer science; Management science; Engineering","score_opus":0.021348942387629334,"score_gpt":0.3679048077687132,"score_spread":0.34655586538108385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406343535","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":[0.000020392143,0.97192717,0.025674934,0.00037003047,0.000022181335,0.0016440027,0.000038743092,0.000044513003,0.00025801468],"genre_scores_gemma":[0.0006421635,0.9974589,0.0010211295,0.000057920854,0.000008939631,0.0003678037,0.00007997834,0.000013902874,0.00034928392],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969787,0.0009225166,0.000699694,0.0007632137,0.0002465637,0.0003893323],"domain_scores_gemma":[0.99793386,0.00049243233,0.00033375685,0.001101333,0.00007685003,0.000061743915],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007336382,0.00033302893,0.0013274364,0.00021354096,0.000116334224,0.000042487027,0.0007485139,0.00013959852,0.000007829877],"category_scores_gemma":[0.00064462883,0.0003007152,0.00024920417,0.0007152905,0.00011176529,0.00031283102,0.001383108,0.00064983073,0.0000034983502],"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":[0.0000011262958,0.00025222628,0.00019185459,0.3341057,0.000042512835,0.000006969096,0.0008605773,0.00026262557,1.09310136e-7,0.031222444,0.000053526946,0.6330003],"study_design_scores_gemma":[0.00024105492,0.000035103472,0.00064464443,0.04427492,0.00017688143,0.0000043782816,0.0003471844,0.00913708,1.7376247e-7,0.0041174227,0.9405468,0.0004743488],"about_ca_topic_score_codex":0.0008425879,"about_ca_topic_score_gemma":0.000010580282,"teacher_disagreement_score":0.9404933,"about_ca_system_score_codex":0.00036757652,"about_ca_system_score_gemma":0.00048086763,"threshold_uncertainty_score":0.9999445},"labels":[],"label_agreement":null},{"id":"W4406365662","doi":"10.2139/ssrn.5097096","title":"Lifelong Scene Graph Generation","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Multimodal Machine Learning Applications","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":"Graph; Computer science; Theoretical computer science","score_opus":0.013710368100805935,"score_gpt":0.28395544944492856,"score_spread":0.2702450813441226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406365662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018030925,0.0028355774,0.96995467,0.006476979,0.00095928303,0.0002764622,0.0000037667012,0.0002324347,0.0012299087],"genre_scores_gemma":[0.94851595,0.0038753913,0.043960113,0.00043714087,0.0012942938,0.000077803,0.00003673676,0.000023931136,0.0017786198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996477,0.00024524404,0.0004666959,0.0006496925,0.00041528136,0.0017460881],"domain_scores_gemma":[0.99822766,0.000057530742,0.0004133099,0.00096122135,0.00022955492,0.00011075692],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018578854,0.00030632917,0.000289331,0.00043023014,0.00045515771,0.00047636632,0.0022468644,0.00025700423,0.0000069266544],"category_scores_gemma":[0.0001041415,0.00030554202,0.0002421207,0.00042599312,0.00002989857,0.00019896148,0.000893577,0.0068308334,0.000040099167],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035557237,0.000080737445,0.0011340298,0.000020050697,0.00021069784,0.0000023121238,0.00017649092,0.021015987,0.0002731142,0.7979024,0.0004556227,0.178725],"study_design_scores_gemma":[0.00036166701,0.00007295751,0.0018816761,0.00007609299,0.000050239873,0.00016133359,0.000020680727,0.32396713,0.00016072739,0.6712623,0.0015222427,0.00046290178],"about_ca_topic_score_codex":0.000588274,"about_ca_topic_score_gemma":0.00043951636,"teacher_disagreement_score":0.93048507,"about_ca_system_score_codex":0.0010680191,"about_ca_system_score_gemma":0.0059737205,"threshold_uncertainty_score":0.9999397},"labels":[],"label_agreement":null},{"id":"W4406612097","doi":"10.1109/smc54092.2024.10831147","title":"TransUAAE-CapGen: Caption Generation from Histopathological Patches through Transformer and UNet-Based Adversarial Autoencoder","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Autoencoder; Adversarial system; Computer science; Transformer; Artificial intelligence; Computer vision; Deep learning; Engineering; Electrical engineering","score_opus":0.03054306869164053,"score_gpt":0.27079084329428615,"score_spread":0.24024777460264563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406612097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10530245,0.00030040657,0.88489556,0.007419185,0.00030316258,0.0002021525,0.000012592804,0.00057226093,0.0009922498],"genre_scores_gemma":[0.7631743,0.000013989614,0.23607156,0.00038744012,0.00015216587,0.000051632076,0.000050992865,0.000009300463,0.00008862604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987277,0.000089594876,0.00021813641,0.00058788696,0.00020189994,0.00017479669],"domain_scores_gemma":[0.9995172,0.000106194486,0.000022736354,0.00026776537,0.000024947998,0.00006118319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016745846,0.00015764081,0.00013312868,0.000049654307,0.00014343976,0.00019559947,0.0002261257,0.00012232614,0.0001332948],"category_scores_gemma":[0.000010754688,0.00012814047,0.00006854185,0.00019821405,0.000062170446,0.0004266405,0.000014719771,0.00020968683,0.0000704743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040398387,0.00030826573,0.0018269154,0.00006158943,0.00006636736,0.00005502818,0.012597229,0.029643396,0.21114972,0.49228978,0.002411601,0.24954972],"study_design_scores_gemma":[0.00032153606,0.000057584177,0.006706257,0.000008935163,0.000020886724,0.000005055588,0.000012813351,0.9780297,0.002150517,0.0045963344,0.007905999,0.00018437007],"about_ca_topic_score_codex":0.0016486212,"about_ca_topic_score_gemma":0.000115034585,"teacher_disagreement_score":0.9483863,"about_ca_system_score_codex":0.0000562129,"about_ca_system_score_gemma":0.00007007046,"threshold_uncertainty_score":0.52254164},"labels":[],"label_agreement":null},{"id":"W4406800169","doi":"10.1007/978-3-031-78554-2_17","title":"Medical Report Generation from Medical Images Using Vision Transformer and Bart Deep Learning Architectures","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Computer science; Artificial intelligence; Transformer; Computer vision; Deep learning; Medical imaging; Electrical engineering; Engineering","score_opus":0.011354863637457269,"score_gpt":0.2946669953497657,"score_spread":0.28331213171230846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406800169","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":[0.0029113588,0.00072787935,0.9899252,0.004268204,0.0006640343,0.00031134402,0.0000026942944,0.00020030169,0.0009889841],"genre_scores_gemma":[0.36092603,0.00010089209,0.6363535,0.0015214314,0.00087167753,0.000014256194,0.00003816259,0.0000358879,0.00013813916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994642,0.000121986945,0.0007281595,0.0018357543,0.0021805805,0.0004915078],"domain_scores_gemma":[0.9973611,0.00092324463,0.0002616451,0.0009180657,0.00016848746,0.00036743336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016399146,0.0004832541,0.0005285696,0.00063374906,0.00053519267,0.00048443465,0.0019994292,0.0005909136,0.0000839606],"category_scores_gemma":[0.0008945064,0.00042733923,0.00010852215,0.00044406034,0.00076688215,0.00026108086,0.0008607259,0.0020458598,0.000007369118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003253032,0.000020766425,0.0005407026,0.000019274119,0.000014832459,0.00023093945,0.0004247569,0.035259783,0.0005580121,0.0030347754,0.000010012837,0.9598829],"study_design_scores_gemma":[0.00023296403,0.0000563189,0.0015713435,0.00040340403,0.000013454071,0.00034925793,9.897829e-8,0.97670335,0.00048385235,0.018906767,0.0008643987,0.00041479745],"about_ca_topic_score_codex":0.0005451828,"about_ca_topic_score_gemma":0.00023941693,"teacher_disagreement_score":0.95946807,"about_ca_system_score_codex":0.00015255799,"about_ca_system_score_gemma":0.0009190362,"threshold_uncertainty_score":0.99981785},"labels":[],"label_agreement":null},{"id":"W4407046109","doi":"10.1111/area.12996","title":"Visualising an undergraduate geography field class using generative AI: Intent, expectations and surprises about the racial depiction of students","year":2025,"lang":"en","type":"article","venue":"Area","topic":"Multimodal Machine Learning Applications","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":"Okanagan College; Simon Fraser University","funders":"","keywords":"Surprise; Depiction; Generative grammar; Narrative; Field (mathematics); Class (philosophy); Sociology; Epistemology; Intentionality; Computer science; Visual arts; Artificial intelligence; Philosophy; Communication; Art","score_opus":0.024255905152098346,"score_gpt":0.371160724422869,"score_spread":0.34690481927077066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407046109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55733514,0.000050053677,0.44113398,0.0011657213,0.00006872004,0.00010228541,0.0000010707614,0.00003264899,0.000110415596],"genre_scores_gemma":[0.99170214,0.000010807778,0.0077924533,0.00043555346,0.00001969366,0.00002054244,0.0000035831945,0.000003716054,0.000011503338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99923223,0.00013128082,0.00017108765,0.0002203364,0.00014244323,0.000102631515],"domain_scores_gemma":[0.99927664,0.000206112,0.000091607544,0.00028315326,0.00011410414,0.0000283756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000121375706,0.00008040149,0.00009202998,0.00013272908,0.00035905023,0.00016371586,0.00033960535,0.00003138906,0.0000011510648],"category_scores_gemma":[0.000074659634,0.00006531898,0.00003541409,0.0003970084,0.000058692873,0.00024929532,0.00015978282,0.00012135545,5.7028404e-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":[0.000016173744,0.00023836244,0.85703796,0.00001723476,0.00013907749,0.0000012349605,0.010216759,0.004579484,0.0068165925,0.08793215,0.00011943387,0.03288554],"study_design_scores_gemma":[0.000270191,0.000060369624,0.5528705,0.00004370574,0.000034510926,0.0000022999534,0.00065124047,0.43562293,0.0035408705,0.0067345593,0.000052607636,0.0001161797],"about_ca_topic_score_codex":0.0015858046,"about_ca_topic_score_gemma":0.0002950218,"teacher_disagreement_score":0.43436703,"about_ca_system_score_codex":0.000017213135,"about_ca_system_score_gemma":0.000030027688,"threshold_uncertainty_score":0.27615604},"labels":[],"label_agreement":null},{"id":"W4407910063","doi":"10.2139/ssrn.5153814","title":"Tdri: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Multimodal Machine Learning Applications","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":"Adaptation (eye); Phase (matter); Image (mathematics); Computer science; Human–computer interaction; Artificial intelligence; Psychology; Chemistry","score_opus":0.02233089557443285,"score_gpt":0.35833504786809367,"score_spread":0.3360041522936608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407910063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022066796,0.0004921266,0.9717187,0.0041195857,0.0004017335,0.00074455846,0.000038362945,0.000080432204,0.00033769492],"genre_scores_gemma":[0.88919127,0.000798219,0.10770025,0.00025154656,0.0007191075,0.00041807903,0.000318491,0.000023149456,0.00057988026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976077,0.0001954843,0.00044517216,0.00059120473,0.00022867706,0.0009317823],"domain_scores_gemma":[0.9985148,0.00016923399,0.0005095898,0.00043227113,0.00029551654,0.00007861927],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014460137,0.0002660943,0.0002678215,0.00027692295,0.000382732,0.00043723657,0.00066041487,0.000117996875,0.0000037674479],"category_scores_gemma":[0.00015861852,0.00026477102,0.00012512265,0.0001250838,0.000032573866,0.00028957415,0.00032110713,0.0024580394,0.000005861684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101938356,0.0003456068,0.00008318403,0.00006805329,0.00041671476,0.000002011367,0.0021190895,0.013684591,0.004821494,0.50787836,0.00064294634,0.469836],"study_design_scores_gemma":[0.001963031,0.00029949893,0.00012484212,0.00005221447,0.00006643937,0.00005099995,0.00011924501,0.8200524,0.00043787732,0.1750637,0.0014797766,0.00028998958],"about_ca_topic_score_codex":0.0004909318,"about_ca_topic_score_gemma":0.0008353994,"teacher_disagreement_score":0.8671245,"about_ca_system_score_codex":0.0011002427,"about_ca_system_score_gemma":0.0023315887,"threshold_uncertainty_score":0.99998045},"labels":[],"label_agreement":null},{"id":"W4408014605","doi":"10.1016/j.eswa.2025.126965","title":"Referring Expression Comprehension in semi-structured human–robot interaction","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"Young Scientists Fund; National Natural Science Foundation of China","keywords":"Computer science; Expression (computer science); Human–robot interaction; Human–computer interaction; Artificial intelligence; Robot; Comprehension; Natural language processing; Programming language","score_opus":0.01705013750644576,"score_gpt":0.3216777303456205,"score_spread":0.3046275928391748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408014605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026575107,0.00034010585,0.96599275,0.0007899862,0.00016201852,0.001389743,0.0000017617476,0.0004972421,0.0042513087],"genre_scores_gemma":[0.9692498,0.0000064686637,0.02727165,0.00011026059,0.00007100459,0.0029844954,0.00002712932,0.000016410639,0.0002628182],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832577,0.00012159186,0.0004318127,0.00065268995,0.0002237809,0.0002443572],"domain_scores_gemma":[0.99831414,0.00012846828,0.00018679915,0.0011874392,0.00010787626,0.00007526482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014616395,0.00020329788,0.00023914182,0.00035155105,0.00039605817,0.00017048907,0.00075008685,0.000104154926,0.0000053543044],"category_scores_gemma":[0.000011652999,0.00017561321,0.000035561898,0.00092750235,0.000036981604,0.0003095846,0.00020727745,0.0003269672,0.000035316443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003476164,0.0004295099,0.019928679,0.00018580667,0.000046952504,0.000004621338,0.0027945945,0.07834681,0.6281351,0.25328124,0.0021362524,0.01467568],"study_design_scores_gemma":[0.0032535407,0.00012513853,0.17298375,0.0022004286,0.000021713773,0.00010001458,0.0013417379,0.59272295,0.030949706,0.0030229946,0.19178787,0.0014901706],"about_ca_topic_score_codex":0.0013902369,"about_ca_topic_score_gemma":0.00008363291,"teacher_disagreement_score":0.94267464,"about_ca_system_score_codex":0.00020011929,"about_ca_system_score_gemma":0.00005028578,"threshold_uncertainty_score":0.7161299},"labels":[],"label_agreement":null},{"id":"W4408100255","doi":"10.1109/lra.2025.3547631","title":"GPT-Driven Gestures: Leveraging Large Language Models to Generate Expressive Robot Motion for Enhanced Human-Robot Interaction","year":2025,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Multimodal Machine Learning Applications","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; University of Victoria","funders":"","keywords":"Gesture; Robot; Computer science; Motion (physics); Human–computer interaction; Human–robot interaction; Artificial intelligence; Communication; Psychology","score_opus":0.02232718226525392,"score_gpt":0.3102131524758498,"score_spread":0.28788597021059587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408100255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17805159,0.0000133866215,0.8136369,0.00720894,0.0003084607,0.00047454092,0.0000046345226,0.00024354835,0.000057983776],"genre_scores_gemma":[0.81236285,0.0000022030601,0.18485892,0.0024245298,0.000083422914,0.00015201031,0.000029165361,0.0000127905805,0.00007410864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987704,0.000070696995,0.00028640495,0.00046469248,0.0001492362,0.0002585828],"domain_scores_gemma":[0.9992108,0.00010715279,0.0001567343,0.0003628426,0.000095078736,0.00006739103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016514082,0.00017644756,0.00017598164,0.00025334297,0.0003941834,0.00029933572,0.00031160808,0.00006224907,0.0000017367532],"category_scores_gemma":[0.000025818992,0.00018578417,0.0000576012,0.00025701718,0.000014765781,0.0004754294,0.00009628625,0.0001565562,0.000008185952],"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":[0.0000019829567,0.000024476189,0.000018291219,0.000026614245,0.000014511158,4.6537124e-7,0.0019719014,0.67867833,0.3105779,0.005145337,0.000324207,0.003215971],"study_design_scores_gemma":[0.00044139658,0.000018743925,0.0021576255,0.000081334416,0.000015577345,0.000001266132,0.00006907151,0.9714866,0.024846353,0.00062782195,0.0000693143,0.00018486813],"about_ca_topic_score_codex":0.00007592809,"about_ca_topic_score_gemma":0.0000097939865,"teacher_disagreement_score":0.63431126,"about_ca_system_score_codex":0.00009215227,"about_ca_system_score_gemma":0.000017538094,"threshold_uncertainty_score":0.75760585},"labels":[],"label_agreement":null},{"id":"W4408355766","doi":"10.1109/icassp49660.2025.10888770","title":"SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Image stitching; Computer science; Scoliosis; Computer vision; Artificial intelligence; Surgery; Medicine","score_opus":0.013241337446606015,"score_gpt":0.33688605324469206,"score_spread":0.32364471579808607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408355766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033994228,0.000022094233,0.9555225,0.0070398776,0.00024205688,0.00082067936,0.000008640872,0.0005154398,0.0018345262],"genre_scores_gemma":[0.50762266,3.25687e-7,0.49081036,0.0012569596,0.00003503115,0.00020190421,0.0000048959687,0.000008360144,0.00005950448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826676,0.00013283538,0.00029783457,0.0007167659,0.00021575768,0.00037006396],"domain_scores_gemma":[0.99800766,0.00059859664,0.00008296581,0.0009753657,0.0002019273,0.00013350527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005012609,0.00021648649,0.00021893764,0.00023910726,0.0005049672,0.00048806725,0.0011663332,0.000104200226,0.000044773242],"category_scores_gemma":[0.0005041035,0.00019392598,0.0000871898,0.00085808727,0.000064641696,0.00025632954,0.00020610925,0.0003458596,0.000057370333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015428552,0.0003343711,0.00093919964,0.000037876576,0.0000259774,0.0000012167583,0.00087966,0.15870155,0.0038676981,0.8199463,0.00034374665,0.014907005],"study_design_scores_gemma":[0.00036840563,0.00006935101,0.007421769,0.0000854117,0.000012513445,2.8408772e-7,0.000050202776,0.98226655,0.0031109645,0.005508779,0.00088481174,0.00022095423],"about_ca_topic_score_codex":0.00035726462,"about_ca_topic_score_gemma":0.000027340802,"teacher_disagreement_score":0.823565,"about_ca_system_score_codex":0.00009020469,"about_ca_system_score_gemma":0.00020336822,"threshold_uncertainty_score":0.79080725},"labels":[],"label_agreement":null},{"id":"W4409263021","doi":"10.1109/wacv61041.2025.00265","title":"AiDe: Improving 3D Open-Vocabulary Semantic Segmentation by Aligned Vision-Language Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Computer science; Natural language processing; Segmentation; Artificial intelligence; Vocabulary; Vocabulary learning; Image segmentation; Linguistics","score_opus":0.006589663231590595,"score_gpt":0.30603053788351264,"score_spread":0.29944087465192204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409263021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054908875,0.00014174536,0.9312276,0.0027108467,0.000113922644,0.0004909675,8.5362706e-7,0.00048460407,0.009920579],"genre_scores_gemma":[0.8267138,0.000004735589,0.16578215,0.0010930217,0.000015838406,0.00008382595,0.00003184088,0.000012721103,0.0062620435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845415,0.00016902399,0.00029565467,0.00059244124,0.00021961107,0.0002691095],"domain_scores_gemma":[0.9989285,0.00021744147,0.00012245392,0.00061699905,0.00004226698,0.00007234996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049593317,0.00016395633,0.00016853449,0.0001481247,0.00042961075,0.0006884261,0.0013963917,0.00006429199,0.00006856915],"category_scores_gemma":[0.00013397352,0.0001575343,0.000039364215,0.0006526917,0.000026322477,0.00070884597,0.0010131329,0.00019918696,0.00015175539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008894939,0.00019155811,0.0060650483,0.00006322202,0.000045096458,0.000008165735,0.0014657145,0.0029243892,0.31644765,0.0126819825,0.0053550657,0.6547432],"study_design_scores_gemma":[0.00071034324,0.000074926465,0.0056917346,0.00004515971,0.000014578707,0.0000043617665,0.00026217385,0.97604895,0.014884439,0.00035688406,0.0016398911,0.00026654996],"about_ca_topic_score_codex":0.0032375667,"about_ca_topic_score_gemma":0.000029059825,"teacher_disagreement_score":0.97312456,"about_ca_system_score_codex":0.00007201015,"about_ca_system_score_gemma":0.00008007608,"threshold_uncertainty_score":0.66385084},"labels":[],"label_agreement":null},{"id":"W4409362862","doi":"10.1609/aaai.v39i25.34900","title":"Learn2Aggregate: Supervised Generation of Chvatal-Gomory Cuts Using Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Huawei Technologies (Canada); University of Toronto","funders":"","keywords":"Graph; Mathematics; Artificial neural network; Artificial intelligence; Computer science; Combinatorics; Pattern recognition (psychology)","score_opus":0.09341661046799989,"score_gpt":0.3222071388322298,"score_spread":0.22879052836422992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409362862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6680882,0.000061546816,0.32575092,0.002584704,0.00043682838,0.00053511345,0.000002848356,0.0001055788,0.0024342495],"genre_scores_gemma":[0.9925431,0.000018896968,0.0070876866,0.00017250807,0.00005799003,0.00002435748,0.0000012844855,0.000010289381,0.000083914994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998251,0.000036266665,0.00061327126,0.00049210165,0.0003235741,0.0002837569],"domain_scores_gemma":[0.9983096,0.000086490196,0.0004315278,0.0004343779,0.0006816101,0.000056356428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004350749,0.00020995458,0.00027038783,0.00023098683,0.0002626746,0.00016770628,0.0018424719,0.00010497318,0.000019835612],"category_scores_gemma":[0.0002971167,0.0001735795,0.0001307833,0.0013724328,0.00027163237,0.00034283934,0.00043231103,0.00038349774,0.0000060408083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027882765,0.00013464228,0.0018540173,0.00004804135,0.000021070317,1.5822015e-7,0.00044139463,0.026225273,0.18168123,0.71184987,0.000052612464,0.07766382],"study_design_scores_gemma":[0.00002545827,0.000045848243,0.0006784121,0.00010820249,0.000013369724,0.0000014385894,0.00006372348,0.7871101,0.19504419,0.016782876,0.000008948868,0.00011747835],"about_ca_topic_score_codex":0.00034493775,"about_ca_topic_score_gemma":0.000012851361,"teacher_disagreement_score":0.76088476,"about_ca_system_score_codex":0.00003955113,"about_ca_system_score_gemma":0.000099915465,"threshold_uncertainty_score":0.7078366},"labels":[],"label_agreement":null},{"id":"W4409364374","doi":"10.1609/aaai.v39i16.33918","title":"Enhance Vision-Language Alignment with Noise","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","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":"Computer science; Noise (video); Computer vision; Artificial intelligence; Image (mathematics)","score_opus":0.019751031522510835,"score_gpt":0.3212355657977287,"score_spread":0.3014845342752179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409364374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47588918,0.00005662848,0.41970947,0.029168399,0.00036265244,0.0012026178,0.000005291884,0.00033979147,0.07326597],"genre_scores_gemma":[0.9868169,0.000009590896,0.011941034,0.00041734008,0.000021594724,0.0000784682,3.1772822e-7,0.00000827113,0.00070649973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834955,0.000017081993,0.00038230314,0.0005475313,0.0004268632,0.00027668494],"domain_scores_gemma":[0.99864626,0.00011119345,0.00027243604,0.0005132727,0.0003922405,0.00006460001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033503282,0.00020163199,0.00020506894,0.0001358557,0.00022755764,0.00022867924,0.0022490139,0.000058926435,0.000038006037],"category_scores_gemma":[0.00020087868,0.0001375988,0.00006766708,0.0009588222,0.00022286641,0.00024623683,0.00043823916,0.0002984,0.00009327448],"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":[0.00003386652,0.00015439911,0.00034476715,0.00002847185,0.000013506564,2.608549e-7,0.0009821545,0.00016464035,0.068745226,0.83930635,0.00011540629,0.090110965],"study_design_scores_gemma":[0.00003899115,0.0001974507,0.002219888,0.00044143063,0.000015320158,0.0000021544183,0.00042041228,0.11069067,0.82372636,0.06176519,0.0002397384,0.00024241133],"about_ca_topic_score_codex":0.00016377862,"about_ca_topic_score_gemma":0.00001294856,"teacher_disagreement_score":0.77754116,"about_ca_system_score_codex":0.00005499429,"about_ca_system_score_gemma":0.000110402885,"threshold_uncertainty_score":0.5611116},"labels":[],"label_agreement":null},{"id":"W4409439325","doi":"10.3390/ijgi14040170","title":"Text Geolocation Prediction via Self-Supervised Learning","year":2025,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Multimodal Machine Learning Applications","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":"Geolocation; Computer science; Artificial intelligence; Machine learning; Data science; Information retrieval; World Wide Web","score_opus":0.0027755090878996986,"score_gpt":0.24370838338605022,"score_spread":0.24093287429815052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409439325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027880972,0.00003036228,0.95841193,0.007370256,0.0015899832,0.0001621864,0.0000036702093,0.00017803727,0.0043725856],"genre_scores_gemma":[0.951684,0.000048648708,0.04717465,0.00077552703,0.00015800488,0.000015079692,0.000047615613,0.0000042111114,0.000092267546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980908,0.000092251976,0.00085111114,0.00011137078,0.0006974421,0.0001570024],"domain_scores_gemma":[0.99724483,0.00012805675,0.00073355844,0.000226012,0.0015997656,0.00006778337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071735587,0.00013492993,0.00014778509,0.0008443035,0.00019096423,0.00039405285,0.0011563796,0.00009655946,0.000035564688],"category_scores_gemma":[0.00036322948,0.00013187913,0.00011310509,0.00044731083,0.000022511433,0.005148039,0.00016723722,0.0004590907,0.00017015314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009184831,0.00017404756,0.022571212,0.000044531687,0.0003404701,0.0000032156229,0.003581007,0.0735028,0.0009997832,0.048458207,0.0036328284,0.84660006],"study_design_scores_gemma":[0.0010289793,0.00008814468,0.071418785,0.000075384145,0.000023818731,0.00008238719,0.00010581118,0.866937,0.0005784984,0.0025292437,0.057007663,0.00012429093],"about_ca_topic_score_codex":0.000109018045,"about_ca_topic_score_gemma":0.0000016664644,"teacher_disagreement_score":0.92380303,"about_ca_system_score_codex":0.00030486565,"about_ca_system_score_gemma":0.00020231189,"threshold_uncertainty_score":0.5377875},"labels":[],"label_agreement":null},{"id":"W4409539127","doi":"10.1145/3729242","title":"Cascade Transformer for Hierarchical Semantic Reasoning in Text-Based Visual Question Answering","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Multimodal Machine Learning Applications","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. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Question answering; Transformer; Cascade; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.010491793156558554,"score_gpt":0.308018523082175,"score_spread":0.2975267299256164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409539127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0668355,0.00018631839,0.9255808,0.0061466815,0.00019506463,0.00066176924,0.0000034018362,0.0003329319,0.00005753616],"genre_scores_gemma":[0.9790961,0.000034898338,0.020017214,0.000058313064,0.000008409958,0.00066824356,0.0000026028051,0.000011194113,0.00010301469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987634,0.000055909717,0.0003560939,0.00045935868,0.00009479637,0.00027045698],"domain_scores_gemma":[0.99909264,0.00030452534,0.000051516283,0.000454366,0.000055072076,0.00004187923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029119436,0.00015833408,0.00022750974,0.0009879516,0.00022594602,0.00006548627,0.00044030737,0.00023037479,0.0000022511297],"category_scores_gemma":[0.0000787974,0.00015617975,0.000052172374,0.0009215378,0.0000788598,0.00008929672,0.000008333551,0.00042771516,0.000005539091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053276883,0.00040947,0.0034196642,0.00032759472,0.000070316055,0.000005270366,0.00027425474,0.031737864,0.005593534,0.34178042,0.000009899821,0.6163184],"study_design_scores_gemma":[0.000613989,0.00026488194,0.0014097468,0.00050748314,0.000023638673,0.000026307365,0.00015297129,0.9702283,0.01804575,0.005884711,0.0025907895,0.000251397],"about_ca_topic_score_codex":0.0006682552,"about_ca_topic_score_gemma":0.00014772115,"teacher_disagreement_score":0.93849045,"about_ca_system_score_codex":0.000089971174,"about_ca_system_score_gemma":0.000060152404,"threshold_uncertainty_score":0.63688254},"labels":[],"label_agreement":null},{"id":"W4410196438","doi":"10.1007/s44196-025-00853-0","title":"Dual Adapter Tuning of Vision–Language Models Using Large Language Models","year":2025,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Multimodal Machine Learning Applications","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; Alliance de recherche numérique du Canada","keywords":"Computer science; Adapter (computing); Language model; Dual (grammatical number); Artificial intelligence; Natural language processing; Linguistics; Computer hardware","score_opus":0.029692916415672392,"score_gpt":0.364484520778666,"score_spread":0.3347916043629936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410196438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072042935,0.0008536196,0.9243035,0.00047484593,0.0011161331,0.00015968394,0.0000258739,0.00003907768,0.0009843643],"genre_scores_gemma":[0.92015946,0.00001036141,0.07939022,0.00013522663,0.00018102308,0.0000050721524,0.000010404078,0.000012767121,0.00009544808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968865,0.00018753024,0.0012549874,0.00028449422,0.001167173,0.00021929835],"domain_scores_gemma":[0.9963543,0.0005439515,0.0009557193,0.00029238238,0.0017600289,0.000093628776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009797689,0.00019761341,0.00035914476,0.0008071434,0.00009679285,0.00023800902,0.0015790334,0.000085510794,0.000016535416],"category_scores_gemma":[0.000116086994,0.00018552573,0.00020228105,0.00046237666,0.000066242465,0.0011351261,0.00033247756,0.00035091303,0.0000074830464],"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":[0.000019656807,0.00010723321,0.00009840056,0.000018535382,0.00013857822,0.000028602733,0.0022466523,0.7529647,0.0007851245,0.2389219,0.00004466196,0.0046260045],"study_design_scores_gemma":[0.00025236045,0.0000450995,0.00023923792,0.00042185298,0.000015840133,0.00020303449,0.0008541123,0.963013,0.00041866885,0.03434312,0.0000557893,0.0001378788],"about_ca_topic_score_codex":0.00042240566,"about_ca_topic_score_gemma":0.000004895651,"teacher_disagreement_score":0.8481165,"about_ca_system_score_codex":0.00018692543,"about_ca_system_score_gemma":0.00034803883,"threshold_uncertainty_score":0.756552},"labels":[],"label_agreement":null},{"id":"W4410773142","doi":"10.1016/j.neucom.2025.130504","title":"Synergy-driven multi-modal prompting for weakly supervised semantic segmentation","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Multimodal Machine Learning Applications","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":"Key Technology Research and Development Program of Shandong; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Modal; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Computer vision","score_opus":0.01945021987538133,"score_gpt":0.3093893573511156,"score_spread":0.2899391374757343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410773142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22985607,0.00001014027,0.7671751,0.0012462004,0.00023937503,0.00072326564,0.0000012028754,0.0004916536,0.00025700816],"genre_scores_gemma":[0.6280618,4.0025432e-7,0.37129948,0.00038031972,0.000056031826,0.00009686552,0.000009554295,0.000013560365,0.000081997394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983209,0.00010080676,0.00036981454,0.00066012435,0.00017018932,0.00037818615],"domain_scores_gemma":[0.9987821,0.00044114454,0.00014522993,0.00045437404,0.00011409843,0.00006305847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025869036,0.00018923647,0.00019678855,0.00019102154,0.0005140365,0.00026842547,0.00081644964,0.000058676633,0.0000011738053],"category_scores_gemma":[0.00016263631,0.0002041948,0.00009626413,0.0005364,0.000025293275,0.00019700268,0.00037720212,0.00022920912,0.000014015765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015657886,0.00038337876,0.024812803,0.0004445277,0.00007647498,0.000014225597,0.0020795665,0.19303524,0.20237143,0.056087516,0.00027357292,0.5204056],"study_design_scores_gemma":[0.0006715744,0.000032069976,0.03286013,0.00006163677,0.000011246235,0.0000038685685,0.000028465092,0.96325064,0.0021901946,0.00042155475,0.0003049351,0.000163677],"about_ca_topic_score_codex":0.00009658992,"about_ca_topic_score_gemma":0.000009089761,"teacher_disagreement_score":0.7702154,"about_ca_system_score_codex":0.00005486975,"about_ca_system_score_gemma":0.00007118936,"threshold_uncertainty_score":0.83268225},"labels":[],"label_agreement":null},{"id":"W4410970740","doi":"10.1007/s13735-025-00370-y","title":"Chameleon: A Multimodal Learning Framework Robust to Missing Modalities","year":2025,"lang":"en","type":"article","venue":"International Journal of Multimedia Information Retrieval","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"Austrian Science Fund","keywords":"Computer science; Modalities; Artificial intelligence; Machine learning","score_opus":0.009476488817652846,"score_gpt":0.2941190413649713,"score_spread":0.28464255254731846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410970740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03969735,0.000046370205,0.93985826,0.01637367,0.0022112548,0.00020488162,0.0000061745577,0.000120067256,0.0014819911],"genre_scores_gemma":[0.64948004,0.000015641313,0.34878838,0.0013573258,0.00025151143,0.0000057998577,0.000009673072,0.0000065681957,0.000085044056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729955,0.00011004925,0.0010736263,0.0001680411,0.0010879529,0.00026075167],"domain_scores_gemma":[0.9962489,0.0007379367,0.0007362274,0.00028272462,0.0017957407,0.00019844153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094328856,0.00019857852,0.000270606,0.001160478,0.00017314886,0.0006301628,0.0018364755,0.00014813505,0.00005385448],"category_scores_gemma":[0.004738107,0.00019172954,0.00016841447,0.00074333657,0.000051942206,0.0022451666,0.00034326955,0.00084623095,0.00013592206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005352847,0.00019796808,0.010366848,0.000051441424,0.00042351708,0.000025781927,0.016247474,0.31123066,0.0011713522,0.04846058,0.0014305424,0.6098586],"study_design_scores_gemma":[0.0014914813,0.00013180332,0.031687688,0.0003862497,0.000018722338,0.000079377205,0.00047005512,0.92938966,0.0021599173,0.003095845,0.030781655,0.0003075551],"about_ca_topic_score_codex":0.00006926805,"about_ca_topic_score_gemma":8.992079e-7,"teacher_disagreement_score":0.618159,"about_ca_system_score_codex":0.00029424473,"about_ca_system_score_gemma":0.00033753898,"threshold_uncertainty_score":0.7818504},"labels":[],"label_agreement":null},{"id":"W4411119193","doi":"10.18653/v1/2025.naacl-srw.37","title":"ELIOT: Zero-Shot Video-Text Retrieval through Relevance-Boosted Captioning and Structural Information Extraction","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Shot (pellet); Relevance (law); Computer science; Zero (linguistics); Information retrieval; Feature extraction; Artificial intelligence; Extraction (chemistry); Natural language processing; Speech recognition; Image (mathematics); Linguistics","score_opus":0.012664193052196262,"score_gpt":0.30361140910088824,"score_spread":0.290947216048692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411119193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18298501,0.00006874561,0.8018888,0.0029434355,0.0002563718,0.00025629235,0.000001499681,0.00037826702,0.011221526],"genre_scores_gemma":[0.916199,0.000024706735,0.08268702,0.0006083397,0.000024229408,0.000012923685,0.000015998645,0.0000041311573,0.00042361286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998941,0.000052834857,0.00032612658,0.0002754295,0.00021138588,0.00019320622],"domain_scores_gemma":[0.999043,0.00021397599,0.00014397604,0.00040896845,0.00014537715,0.000044684963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018768718,0.00013506056,0.00012287972,0.00014537679,0.00037914375,0.00036108834,0.00030305382,0.00008967378,0.000028855413],"category_scores_gemma":[0.00026134818,0.00012754716,0.00003161175,0.000666247,0.000044330674,0.0026413766,0.0001665934,0.00028135147,0.00006608206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006941021,0.000025827969,0.00618535,0.000095102776,0.000049731316,0.0000013036699,0.0029367695,0.00925018,0.014508115,0.7222518,0.0018647464,0.24276169],"study_design_scores_gemma":[0.0008266741,0.000052091367,0.21058461,0.000060487346,0.000017211838,0.000037914713,0.00010803388,0.7414425,0.0048795384,0.02744995,0.014214291,0.00032671908],"about_ca_topic_score_codex":0.0006542549,"about_ca_topic_score_gemma":0.000015193252,"teacher_disagreement_score":0.733214,"about_ca_system_score_codex":0.000090823894,"about_ca_system_score_gemma":0.00006142888,"threshold_uncertainty_score":0.52012223},"labels":[],"label_agreement":null},{"id":"W4411176006","doi":"10.1016/j.nlp.2025.100159","title":"Next-generation image captioning: A survey of methodologies and emerging challenges from transformers to Multimodal Large Language Models","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Closed captioning; Computer science; Transformer; Natural language processing; Artificial intelligence; Image (mathematics); Engineering; Electrical engineering","score_opus":0.0630583087593844,"score_gpt":0.36922933374050865,"score_spread":0.30617102498112425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411176006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36207098,0.023232965,0.61281675,0.0014575182,0.00011368827,0.00011005009,0.000011650969,0.00007837762,0.00010801007],"genre_scores_gemma":[0.69978535,0.00009196009,0.29990226,0.00011684517,0.00005051312,0.000007910132,0.000013866404,0.000008405426,0.00002289935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983776,0.00034414936,0.0003580232,0.00036824544,0.00026543523,0.00028650652],"domain_scores_gemma":[0.99897027,0.00028164568,0.00019345009,0.00019852059,0.000267955,0.00008817682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013332793,0.00018027157,0.00027342833,0.00029493222,0.00033960518,0.00034907303,0.00048527183,0.00008957508,0.0000059583817],"category_scores_gemma":[0.0006287405,0.00015364404,0.000054122134,0.00043771975,0.000038773505,0.0009760634,0.00013246156,0.00055302185,0.0000011943442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026655867,0.000036442227,0.00033529187,0.000055835502,0.000038446044,0.000007667559,0.028725203,0.0012872299,0.1492496,0.0004874309,0.000020122337,0.81973004],"study_design_scores_gemma":[0.0005892712,0.000030000403,0.030684708,0.00015000871,0.000023227572,0.00002108556,0.0030431107,0.95764405,0.007010986,0.0005701382,0.000011199518,0.00022222802],"about_ca_topic_score_codex":0.0015696003,"about_ca_topic_score_gemma":0.00048466926,"teacher_disagreement_score":0.9563568,"about_ca_system_score_codex":0.00005261588,"about_ca_system_score_gemma":0.000113623704,"threshold_uncertainty_score":0.6265422},"labels":[],"label_agreement":null},{"id":"W4411357823","doi":"10.1007/978-3-031-82606-1_2","title":"Navigational Assistance for the Blind in Complex Indoor Spaces Using a Vision-Enabled Large Language Model","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Multimodal Machine Learning Applications","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":"Thompson Rivers University; Algoma University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Human–computer interaction","score_opus":0.11730223578359025,"score_gpt":0.43918222356397013,"score_spread":0.32187998778037985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411357823","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":[0.00023837353,0.0027262692,0.9883809,0.0022807547,0.00021447294,0.0011372316,0.00014614244,0.00006625544,0.0048095942],"genre_scores_gemma":[0.4698757,0.00021534396,0.5149494,0.0009809023,0.00016458538,0.00043580477,0.00017665143,0.000048269787,0.01315338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751705,0.000044733784,0.000754995,0.0007976846,0.0005370659,0.0003484468],"domain_scores_gemma":[0.9949293,0.0036570483,0.00037640976,0.0004901116,0.000508228,0.00003889283],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077955914,0.00037427465,0.00048116743,0.0003732911,0.00041197488,0.00013572429,0.0012655949,0.00014476774,0.000015580548],"category_scores_gemma":[0.00030502488,0.0003251687,0.00013726667,0.00037578095,0.00028318216,0.00018720055,0.00072971196,0.00062920176,0.000013524259],"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":[0.00001470713,0.000031303116,0.000044341166,0.000055511253,0.000051241917,0.0000033163035,0.0012870054,0.52536064,0.0000019955485,0.46948004,0.0002045954,0.0034652948],"study_design_scores_gemma":[0.00022204594,0.000015520029,0.00035449897,0.00035362275,0.000012829048,0.0000028483432,0.00018582132,0.75851995,0.0000020872924,0.23922078,0.00088070094,0.00022932084],"about_ca_topic_score_codex":0.0000705233,"about_ca_topic_score_gemma":0.00028043875,"teacher_disagreement_score":0.47343153,"about_ca_system_score_codex":0.00039771415,"about_ca_system_score_gemma":0.00034490673,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W4411449683","doi":"10.1145/3729343","title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Multimodal Machine Learning Applications","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":"Computer science; Robustness (evolution); Artificial intelligence; Software deployment; Machine learning; Generative grammar; Human–computer interaction; Software engineering","score_opus":0.04418603467234083,"score_gpt":0.3291355321729803,"score_spread":0.28494949750063947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411449683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3871718,0.000057672307,0.6110937,0.0007001637,0.00013141213,0.00045827407,7.020895e-7,0.00034149666,0.00004478878],"genre_scores_gemma":[0.58904624,5.4545256e-7,0.41080588,0.000033645487,0.000017583965,0.000057237598,4.0385464e-7,0.000009129562,0.000029332574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917954,0.0000036163876,0.00020524728,0.00028743927,0.00017330084,0.00015087484],"domain_scores_gemma":[0.99860644,0.0006514203,0.00014125025,0.00035308246,0.0002192228,0.000028564698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033410275,0.0001247346,0.00012991665,0.00013148425,0.00014733266,0.000091021095,0.0008393736,0.000051267325,3.247624e-7],"category_scores_gemma":[0.00822916,0.00010608372,0.000040526338,0.00048039033,0.0000132901505,0.0002913797,0.00045700296,0.00015365338,6.639933e-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":[0.000008842745,0.000034660447,0.008937951,0.00039473694,0.000021530504,3.942682e-8,0.00038035586,0.8999712,0.02028123,0.019939335,0.00010736671,0.049922757],"study_design_scores_gemma":[0.00017373954,0.00005467214,0.050868023,0.0002057838,0.0000143988955,0.0000023533569,0.00000928476,0.93895227,0.002071254,0.0075522256,0.0000064642936,0.00008953584],"about_ca_topic_score_codex":0.000033813452,"about_ca_topic_score_gemma":2.4831306e-7,"teacher_disagreement_score":0.20187442,"about_ca_system_score_codex":0.000050075174,"about_ca_system_score_gemma":0.000018611143,"threshold_uncertainty_score":0.9851667},"labels":[],"label_agreement":null},{"id":"W4412106036","doi":"10.1016/j.cviu.2025.104442","title":"FedVLP: Visual-aware latent prompt generation for Multimodal Federated Learning","year":2025,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Multimodal Machine Learning Applications","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 Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.032529756933271155,"score_gpt":0.3306209197960363,"score_spread":0.29809116286276516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412106036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015467078,0.000060648148,0.98081714,0.0021537372,0.00030897584,0.000585866,0.0000013589613,0.00038559746,0.00021957696],"genre_scores_gemma":[0.84273505,0.000017628012,0.1565951,0.0003344515,0.00009210228,0.000040390387,0.000033304976,0.00001458582,0.00013741669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847543,0.0001132825,0.00029458362,0.00065912213,0.00016418386,0.00029338023],"domain_scores_gemma":[0.9992314,0.00021616134,0.00010984982,0.00021208916,0.00013497128,0.000095501615],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003476711,0.00021570259,0.00021582702,0.00025988434,0.0011295952,0.0011725783,0.0002608515,0.00008568257,0.0000047433086],"category_scores_gemma":[0.000046217432,0.00020159867,0.000071622926,0.0003676571,0.000051125397,0.0004886826,0.00032962102,0.00024075616,0.000008139435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001292159,0.00068962283,0.0037258107,0.00050152355,0.00025171522,0.000023735487,0.002942399,0.015167029,0.15991956,0.24998815,0.020885471,0.5457758],"study_design_scores_gemma":[0.00095309777,0.00017657234,0.001172321,0.00007850927,0.00000934166,0.000005574674,0.000044956203,0.9942533,0.0009722817,0.0013839332,0.0007375023,0.00021264357],"about_ca_topic_score_codex":0.000023579332,"about_ca_topic_score_gemma":0.000004237028,"teacher_disagreement_score":0.9790862,"about_ca_system_score_codex":0.00018818017,"about_ca_system_score_gemma":0.000052364776,"threshold_uncertainty_score":0.9998643},"labels":[],"label_agreement":null},{"id":"W4413038007","doi":"10.1038/s42256-025-01072-0","title":"High-level visual representations in the human brain are aligned with large language models","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Multimodal Machine Learning Applications","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","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Artificial intelligence; Brain activity and meditation; Natural language processing; Cognitive psychology; Psychology; Neuroscience; Electroencephalography","score_opus":0.01296838644040375,"score_gpt":0.3531533419880927,"score_spread":0.3401849555476889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413038007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061625924,0.0003331723,0.9154471,0.01879992,0.000086523214,0.00051357737,0.000027592087,0.00019774867,0.0029684498],"genre_scores_gemma":[0.97558147,0.000003092829,0.01985988,0.003905787,0.000046249428,0.00013504957,0.000038536793,0.0000129627,0.00041698918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803793,0.00027458253,0.00031605794,0.00062401546,0.00041168593,0.00033574476],"domain_scores_gemma":[0.99802905,0.0005978076,0.00014200048,0.0010740418,0.00010966042,0.00004744312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000672017,0.00022414082,0.00020590553,0.00029482544,0.00033372283,0.00019666567,0.0019805818,0.00016557687,0.000018158005],"category_scores_gemma":[0.00024799866,0.00015515625,0.000058539674,0.0017108566,0.00006455926,0.00028062428,0.0003028882,0.0010004303,0.000020735391],"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":[0.000008891647,0.0002611256,0.00843823,0.000018825143,0.000021511969,0.00003232559,0.0028578478,0.012771342,0.00048935413,0.9685365,0.0007021826,0.0058618635],"study_design_scores_gemma":[0.0006001126,0.00009879271,0.21212922,0.00016002175,0.000023126178,0.00002981832,0.0011747243,0.6984182,0.0027325144,0.083466165,0.0006348056,0.00053250813],"about_ca_topic_score_codex":0.0025968044,"about_ca_topic_score_gemma":0.0025282842,"teacher_disagreement_score":0.9139555,"about_ca_system_score_codex":0.0000543869,"about_ca_system_score_gemma":0.000061770996,"threshold_uncertainty_score":0.6327088},"labels":[],"label_agreement":null},{"id":"W4413144748","doi":"10.1109/cvpr52734.2025.01367","title":"Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Vector Institute","funders":"","keywords":"Computer science; Natural language processing; Ground; Artificial intelligence; Engineering","score_opus":0.0074882238277879185,"score_gpt":0.2949452169845906,"score_spread":0.2874569931568027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413144748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08114185,0.00010093462,0.8916423,0.0040528276,0.00021387698,0.00022399439,0.000005475587,0.00054006855,0.02207869],"genre_scores_gemma":[0.97626495,0.0000040946775,0.017139433,0.0011551217,0.00001589196,0.000039589533,0.000012895931,0.00001141634,0.0053566196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863416,0.00008249143,0.00021474292,0.0004954975,0.00021632806,0.0003567828],"domain_scores_gemma":[0.9988048,0.00020139858,0.00006799857,0.00080007024,0.000040605926,0.000085104795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034004045,0.00016106405,0.0001672853,0.00015831689,0.00029984376,0.00020417102,0.0010284586,0.00006087924,0.000043947955],"category_scores_gemma":[0.000056378136,0.00014109687,0.00006376022,0.00070015754,0.000025304582,0.0002904254,0.00039123127,0.00024106527,0.000066848996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047611475,0.00035974395,0.004443881,0.00005176106,0.00006217841,0.000008335513,0.0053054667,0.004982634,0.008209815,0.9083492,0.025334194,0.042887986],"study_design_scores_gemma":[0.00025433462,0.00001665944,0.0018303542,0.00002949512,0.000006899262,0.0000033924432,0.00019935964,0.9892314,0.0005420286,0.006881724,0.0008300184,0.00017435443],"about_ca_topic_score_codex":0.002503071,"about_ca_topic_score_gemma":0.00017164357,"teacher_disagreement_score":0.98424876,"about_ca_system_score_codex":0.00007058264,"about_ca_system_score_gemma":0.000058553647,"threshold_uncertainty_score":0.57537633},"labels":[],"label_agreement":null},{"id":"W4413145524","doi":"10.1109/cvpr52734.2025.01376","title":"BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":13,"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":"Computer science; Artificial intelligence; Natural language processing","score_opus":0.00969014896680131,"score_gpt":0.3362562618677056,"score_spread":0.32656611290090426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413145524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010813104,0.000027698106,0.966169,0.015815167,0.00013013043,0.0006149017,0.0000021761562,0.0005951621,0.0058326484],"genre_scores_gemma":[0.6310441,6.335484e-7,0.36424106,0.0008653128,0.000031990665,0.00024791973,0.000009814252,0.000007893451,0.003551291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872077,0.00004283796,0.00022292972,0.0005132809,0.0002000613,0.0003001366],"domain_scores_gemma":[0.9989399,0.00026502847,0.000038588343,0.0005201307,0.00008414839,0.00015224465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036591265,0.00012286239,0.00014653454,0.00035274518,0.00022415607,0.0001487946,0.0009267444,0.00006766018,0.000022692879],"category_scores_gemma":[0.00021704582,0.000105476654,0.000060102273,0.0010646302,0.0000323959,0.00018381674,0.00042943127,0.00016481841,0.00011512671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012583396,0.00024072344,0.00014498713,0.00005720529,0.00003215284,0.0000020415096,0.002229748,0.012375177,0.01648339,0.44320926,0.010734974,0.5144778],"study_design_scores_gemma":[0.00028528884,0.00010236559,0.00055615674,0.000024432999,0.000003653238,0.0000012665769,0.000053932843,0.96605325,0.0005855385,0.006402269,0.02579999,0.00013187472],"about_ca_topic_score_codex":0.00020372128,"about_ca_topic_score_gemma":0.000005363171,"teacher_disagreement_score":0.9536781,"about_ca_system_score_codex":0.000041789608,"about_ca_system_score_gemma":0.00008683619,"threshold_uncertainty_score":0.4301213},"labels":[],"label_agreement":null},{"id":"W4413145832","doi":"10.1109/cvpr52734.2025.02749","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Object (grammar); Natural language processing; Programming language","score_opus":0.005370343066093995,"score_gpt":0.31150685231513425,"score_spread":0.30613650924904023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413145832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13636309,0.00015201034,0.7896875,0.002736358,0.00015612673,0.00029027488,2.2322718e-7,0.000808533,0.069805846],"genre_scores_gemma":[0.9680888,0.000005283884,0.017210122,0.00045538406,0.000039333343,0.00005514222,0.0000063803914,0.000006441361,0.014133126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883837,0.00013546906,0.00019881126,0.00040669928,0.00018024948,0.00024039067],"domain_scores_gemma":[0.9991285,0.0002719427,0.000072551,0.00040278645,0.00007253633,0.000051667495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023503831,0.00010477861,0.00013394904,0.00022011602,0.00022555739,0.0002071152,0.00048189264,0.00004758479,0.00008853023],"category_scores_gemma":[0.00032975906,0.0000987681,0.0000542415,0.0011823004,0.000016479476,0.00024068274,0.00020865856,0.0002304836,0.00031952938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037432113,0.00040258537,0.14546654,0.000051382773,0.00013283498,0.000018872397,0.002607249,0.036979146,0.048632257,0.2642687,0.005892179,0.49551082],"study_design_scores_gemma":[0.00081210537,0.000033534303,0.043377243,0.000010602855,0.0000105260815,0.0000028185411,0.00016795067,0.94485384,0.0062431283,0.0008091453,0.0035211344,0.00015798245],"about_ca_topic_score_codex":0.0013085104,"about_ca_topic_score_gemma":0.000019034316,"teacher_disagreement_score":0.9078747,"about_ca_system_score_codex":0.000052645308,"about_ca_system_score_gemma":0.0000726507,"threshold_uncertainty_score":0.410701},"labels":[],"label_agreement":null},{"id":"W4413145840","doi":"10.1109/cvpr52734.2025.00877","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Security token; Pruning; Diversity (politics); Artificial intelligence; Computer network; Biology","score_opus":0.01616403560729983,"score_gpt":0.3084121409683172,"score_spread":0.29224810536101736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413145840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019313028,0.000014211214,0.9717262,0.003435084,0.00012436992,0.00052089134,0.000008560347,0.0005527451,0.004304955],"genre_scores_gemma":[0.75147974,3.739498e-7,0.2462035,0.001443927,0.000017981783,0.00008150303,0.000012877215,0.000006469971,0.00075362273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987365,0.000047170306,0.00018210657,0.00048083992,0.00019324728,0.0003601134],"domain_scores_gemma":[0.998937,0.00031076928,0.000059948983,0.00048067144,0.00013022372,0.00008138021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003152252,0.00014908878,0.00015822957,0.00018586988,0.00078989746,0.0001276792,0.0010412629,0.000075091484,0.00001502013],"category_scores_gemma":[0.000063512314,0.00014687495,0.00010455385,0.00043424944,0.000019617986,0.0003526785,0.0011275241,0.00016022823,0.000025875144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026275531,0.0003839016,0.014331027,0.000058271613,0.000044479835,0.000001339319,0.00049664895,0.07624512,0.00054515136,0.8905915,0.0019528621,0.0153234005],"study_design_scores_gemma":[0.0011070911,0.000031121952,0.0047227587,0.0000126798595,0.000010286175,1.7913396e-7,0.000016849312,0.98596424,0.0005176318,0.0054465774,0.0020108877,0.00015967635],"about_ca_topic_score_codex":0.00048066437,"about_ca_topic_score_gemma":0.000028824317,"teacher_disagreement_score":0.90971917,"about_ca_system_score_codex":0.000061968,"about_ca_system_score_gemma":0.00010349383,"threshold_uncertainty_score":0.6075333},"labels":[],"label_agreement":null},{"id":"W4413146224","doi":"10.1109/cvpr52734.2025.02140","title":"VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Training (meteorology); Segmentation; Artificial intelligence; Diffusion; Image segmentation; Computer vision","score_opus":0.020627162872346897,"score_gpt":0.28407019326650984,"score_spread":0.26344303039416295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413146224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01896515,0.0000054407387,0.93792653,0.011395838,0.000116430056,0.0002958588,0.0000014325893,0.00047789997,0.030815402],"genre_scores_gemma":[0.8540496,0.0000010937299,0.14225218,0.0028137667,0.000015548943,0.00007896208,0.000007450194,0.0000071439804,0.00077423116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987789,0.00008020186,0.00020974626,0.00045134098,0.00027715522,0.00020267861],"domain_scores_gemma":[0.99852467,0.00026415178,0.00006039935,0.0010387655,0.000051305717,0.000060739796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002338527,0.00013792547,0.00012606679,0.00023459981,0.00020187574,0.0001313632,0.00093329325,0.000054194796,0.000034057055],"category_scores_gemma":[0.000084136474,0.00012356375,0.00005788239,0.0005521601,0.000022465847,0.00022927977,0.0001972576,0.0001591088,0.00006071055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016770193,0.00029951739,0.001192649,0.000038205308,0.000015879159,0.0000024714625,0.0010452395,0.28880054,0.00721694,0.5415107,0.002734296,0.1571268],"study_design_scores_gemma":[0.0006336638,0.00004085077,0.007009414,0.00003470288,0.000005830691,4.5363157e-7,0.000023716104,0.9623792,0.00085578766,0.02872634,0.00017249127,0.000117514],"about_ca_topic_score_codex":0.00027974264,"about_ca_topic_score_gemma":0.000023109418,"teacher_disagreement_score":0.8350845,"about_ca_system_score_codex":0.00006393105,"about_ca_system_score_gemma":0.000081377744,"threshold_uncertainty_score":0.5038783},"labels":[],"label_agreement":null},{"id":"W4413155320","doi":"10.1109/cvpr52734.2025.01341","title":"BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"CLARITY; Computer science; Artificial intelligence; Image (mathematics); Natural language processing; Information retrieval; Computer vision; Chemistry","score_opus":0.0067285771908953814,"score_gpt":0.268057067877984,"score_spread":0.26132849068708863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413155320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050436635,0.00004133901,0.9377904,0.0012099805,0.00008742977,0.00017443266,0.0000040841605,0.00013407407,0.010121649],"genre_scores_gemma":[0.7524374,7.743074e-7,0.2471763,0.0000872224,0.0000053743133,0.000015022606,0.0000020137597,0.0000028922136,0.0002729802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990982,0.000057414683,0.00029422194,0.00027982713,0.00012647305,0.0001438728],"domain_scores_gemma":[0.9988104,0.00015485664,0.0001232918,0.00071625743,0.0001535362,0.000041618765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020161604,0.00009007711,0.00016027108,0.00016024707,0.0000918374,0.000028795841,0.0007408096,0.00005730755,0.000059084585],"category_scores_gemma":[0.00007264741,0.0000861668,0.00008933877,0.00067832076,0.000116997675,0.00020592782,0.00029193575,0.0001835273,0.000010225784],"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":[0.0000021907513,0.00017761167,0.00697802,0.0000663807,0.00003151536,5.7171445e-7,0.00055222784,0.0006330394,0.08694236,0.77162796,0.00025670213,0.1327314],"study_design_scores_gemma":[0.00056260085,0.000066433466,0.17090918,0.000034410554,0.000029330738,0.0000032565513,0.00006802903,0.7162447,0.06267668,0.04875213,0.00039806578,0.00025518303],"about_ca_topic_score_codex":0.0039072265,"about_ca_topic_score_gemma":0.000050139133,"teacher_disagreement_score":0.72287583,"about_ca_system_score_codex":0.000017239874,"about_ca_system_score_gemma":0.00008166688,"threshold_uncertainty_score":0.59065837},"labels":[],"label_agreement":null},{"id":"W4413769926","doi":"10.1097/wno.0000000000002393","title":"Artificial Intelligence Diagnosis of Ocular Motility Disorders From Clinical Videos","year":2025,"lang":"en","type":"article","venue":"Journal of Neuro-Ophthalmology","topic":"Multimodal Machine Learning Applications","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":"Toronto Western Hospital","funders":"","keywords":"Computer science; Medicine; Artificial intelligence","score_opus":0.05013311516629099,"score_gpt":0.3844152274446197,"score_spread":0.3342821122783287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413769926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80274296,0.00013741931,0.189384,0.006469473,0.0008671978,0.00011949633,0.0000043816644,0.000017040036,0.00025803634],"genre_scores_gemma":[0.98103267,0.000050596787,0.01856894,0.00022757208,0.00009550137,0.000008956181,8.086806e-7,0.0000075405005,0.000007425062],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99706113,0.000708821,0.0013757044,0.00038446416,0.00025598786,0.00021388054],"domain_scores_gemma":[0.9949085,0.0032978675,0.00077298854,0.0006989511,0.00021294439,0.000108757326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087022054,0.0001524504,0.00050124165,0.00023447881,0.000076428354,0.00003282664,0.0015228342,0.00014314482,0.000078114834],"category_scores_gemma":[0.0025274225,0.0001405712,0.00031165854,0.0005216262,0.00022289393,0.0001744766,0.00035412642,0.00072831113,0.000018587121],"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":[0.00006369345,0.0009461495,0.89185655,0.00001754679,0.00010104288,0.00017308799,0.00011834216,0.00285024,0.00076942804,0.008066279,0.00017946007,0.09485819],"study_design_scores_gemma":[0.0001383515,0.00047507166,0.85378194,0.000032168853,0.00004345496,0.00020456043,0.000014101286,0.031235958,0.0016408418,0.11186752,0.0004583291,0.00010769159],"about_ca_topic_score_codex":0.00026436814,"about_ca_topic_score_gemma":0.0000039469014,"teacher_disagreement_score":0.1782897,"about_ca_system_score_codex":0.000024609622,"about_ca_system_score_gemma":0.00014827262,"threshold_uncertainty_score":0.5732327},"labels":[],"label_agreement":null},{"id":"W4413944815","doi":"10.1109/icra55743.2025.11128004","title":"OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Computer science; Mobile robot; Mobile robot navigation; Human–computer interaction; Robot; Computer vision; Social robot; Artificial intelligence; Multimedia; Robot control","score_opus":0.018775548245875733,"score_gpt":0.35996635047231645,"score_spread":0.3411908022264407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413944815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1448641,0.00002486258,0.8518273,0.0009506597,0.000061069346,0.00055960496,0.00000850498,0.00040003192,0.0013038644],"genre_scores_gemma":[0.6468693,4.76906e-7,0.35175574,0.00031317974,0.00011274067,0.00020082762,0.00022170974,0.000007502297,0.000518522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989559,0.000066332614,0.00019929663,0.00043246287,0.0001485303,0.00019744496],"domain_scores_gemma":[0.9992708,0.000091158625,0.000068678804,0.00042784458,0.00008874411,0.00005274871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025864763,0.00011676756,0.00013287467,0.00009519308,0.00031289292,0.00015057628,0.00064626214,0.00008231002,0.00000591562],"category_scores_gemma":[0.000028835604,0.0001084001,0.00006356173,0.00041191228,0.000027001863,0.0003144683,0.00016466955,0.00015452037,0.000009510675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016640173,0.0012669554,0.001476974,0.00011602335,0.000031215342,7.608629e-7,0.004299686,0.018381456,0.01267862,0.11655129,0.0014733893,0.843707],"study_design_scores_gemma":[0.00033926804,0.000067680056,0.021796774,0.000008565234,0.000007022616,0.0000010283208,0.00020210113,0.9755974,0.00058755267,0.0006661635,0.0005956326,0.00013083688],"about_ca_topic_score_codex":0.00038799676,"about_ca_topic_score_gemma":0.000021048048,"teacher_disagreement_score":0.9572159,"about_ca_system_score_codex":0.00004662977,"about_ca_system_score_gemma":0.000052762836,"threshold_uncertainty_score":0.44204277},"labels":[],"label_agreement":null},{"id":"W4413986970","doi":"10.14778/3748191.3748195","title":"Déjà Vu: Efficient Video-Language Query Engine with Learning-Based Inter-Frame Computation Reuse","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Reuse; Déjà vu; Frame (networking); Computation; Artificial intelligence; Natural language processing; Programming language; Computer network; Engineering; Psychology","score_opus":0.0037931050791894048,"score_gpt":0.24165399323101416,"score_spread":0.23786088815182477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413986970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5481965,0.00007601039,0.43889576,0.009459417,0.00016477353,0.0008095074,0.00000187378,0.00038961563,0.002006523],"genre_scores_gemma":[0.95854926,0.0000014245213,0.040700175,0.00032213458,0.000019750978,0.00012030779,0.0000021901008,0.000014019594,0.00027071548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985976,0.000025252104,0.00031048074,0.0004346843,0.0003766759,0.00025531],"domain_scores_gemma":[0.9988494,0.00015111965,0.00030402956,0.00038896166,0.00024777482,0.00005871621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004027556,0.00019776456,0.00020685502,0.00021760644,0.00018824107,0.00013236476,0.0014451675,0.000049597016,0.00000598591],"category_scores_gemma":[0.00032772758,0.00013925364,0.00008572943,0.00082918647,0.00008308865,0.000103159175,0.0006119481,0.00036797917,0.000012665251],"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":[0.00012998679,0.0010601173,0.019983426,0.0005842034,0.00019163701,0.000002187144,0.007576079,0.83196187,0.0627114,0.03501408,0.0021860686,0.03859892],"study_design_scores_gemma":[0.00097353914,0.00017216578,0.009407695,0.00035755493,0.00003531475,0.0000045842808,0.00019027607,0.9290221,0.05805768,0.00051644904,0.0010582367,0.00020440343],"about_ca_topic_score_codex":0.000276922,"about_ca_topic_score_gemma":0.0000032278306,"teacher_disagreement_score":0.41035277,"about_ca_system_score_codex":0.0001517321,"about_ca_system_score_gemma":0.00007515073,"threshold_uncertainty_score":0.5678598},"labels":[],"label_agreement":null},{"id":"W4414317082","doi":"10.20944/preprints202509.1607.v1","title":"Capturing Narrative Semantics from Captions for Relational Scene Abstraction","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"","keywords":"Interpretability; Scene graph; Closed captioning; Semantics (computer science); Graph; Scalability; Natural language; Exploit; Abstraction","score_opus":0.14039488549821855,"score_gpt":0.38429230633133954,"score_spread":0.243897420833121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414317082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41660348,0.00004379392,0.57228607,0.005455686,0.00096868654,0.0011017441,0.0001641939,0.0005130421,0.0028633282],"genre_scores_gemma":[0.8822582,0.000016522921,0.11503604,0.00010123114,0.00026643212,0.0007566917,0.00033934988,0.000020164383,0.0012053942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9972671,0.00012559883,0.00058856833,0.0013687197,0.0003504667,0.00029951564],"domain_scores_gemma":[0.9967235,0.00055883476,0.0005080597,0.0017097557,0.00038525005,0.00011462294],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004730793,0.0003443055,0.00034867108,0.00023718408,0.00046033718,0.00008762547,0.0012735227,0.00039065394,0.00012456706],"category_scores_gemma":[0.00046550942,0.00040597317,0.00023914558,0.00020801589,0.00005908599,0.00024817447,0.0019115993,0.0012631429,0.0003645631],"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":[0.000052672825,0.0006270368,0.37605357,0.00037693867,0.00076307164,0.00000522678,0.02039149,0.46456346,0.008266472,0.123514056,0.00030855543,0.0050774612],"study_design_scores_gemma":[0.00032311003,0.000005710806,0.6653286,0.00019678067,0.000062307234,0.000001843883,0.00008705681,0.2828863,0.0031654085,0.045416974,0.0021134482,0.00041247354],"about_ca_topic_score_codex":0.0027692523,"about_ca_topic_score_gemma":0.000095108706,"teacher_disagreement_score":0.4656547,"about_ca_system_score_codex":0.00030425144,"about_ca_system_score_gemma":0.00039427116,"threshold_uncertainty_score":0.9998392},"labels":[],"label_agreement":null},{"id":"W4414857280","doi":"10.48550/arxiv.2505.24434","title":"Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Pointwise; Flow (mathematics); Vector field; Matching (statistics); Graph; Flow velocity; Scalability; Artificial neural network; Pattern recognition (psychology)","score_opus":0.022610567812840356,"score_gpt":0.27731955546846776,"score_spread":0.2547089876556274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414857280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21650517,0.000060683113,0.77801406,0.0026113915,0.000561867,0.00044485822,0.000020426922,0.00052906666,0.001252479],"genre_scores_gemma":[0.75764257,0.000026651445,0.24055506,0.00059435185,0.00034317613,0.00024101278,0.00014801932,0.00002653713,0.0004226106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973177,0.00016203294,0.00046068008,0.0012642827,0.00038083005,0.0004144869],"domain_scores_gemma":[0.9971725,0.00015183077,0.00028485805,0.002005653,0.00025023372,0.00013495033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003255577,0.0004600778,0.0004065582,0.000255961,0.000389369,0.00038207613,0.0016372186,0.00034709045,0.00004130526],"category_scores_gemma":[0.00006513619,0.0004295374,0.00016466275,0.0004924749,0.000050911658,0.00031703577,0.0013452751,0.0014361945,0.00012102618],"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":[0.00003823687,0.000496796,0.10392317,0.0009291709,0.00052001246,0.00011617699,0.008867919,0.764177,0.0130833,0.009657959,0.0030373402,0.095152885],"study_design_scores_gemma":[0.00032834485,0.000050575243,0.037959658,0.00026233037,0.000052872212,0.00001177407,0.000021389691,0.9525603,0.004683044,0.0031159662,0.00027089275,0.0006828647],"about_ca_topic_score_codex":0.001239934,"about_ca_topic_score_gemma":0.00037954585,"teacher_disagreement_score":0.5411374,"about_ca_system_score_codex":0.00010708785,"about_ca_system_score_gemma":0.00034155665,"threshold_uncertainty_score":0.99981564},"labels":[],"label_agreement":null},{"id":"W4415184565","doi":"10.36227/techrxiv.176049757.72015578/v1","title":"Lightweight Adaptation of Large Language and Vision Models in Robotics","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Robotics; Adaptation (eye); Machine vision; Robot; Foundation (evidence); Field (mathematics)","score_opus":0.015941705709779763,"score_gpt":0.3216170326830381,"score_spread":0.30567532697325833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415184565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025853153,0.00027250923,0.96810955,0.001192527,0.000065910914,0.00027584448,0.000010637175,0.00009497933,0.004124909],"genre_scores_gemma":[0.691157,0.000031944594,0.30846024,0.000045374527,0.000007652068,0.000018918447,0.000016111559,0.0000035153248,0.00025923213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989646,0.00007413757,0.00027735368,0.00040393852,0.00015748687,0.00012248916],"domain_scores_gemma":[0.9990421,0.0001129308,0.00012991503,0.0006211721,0.00006119214,0.00003269374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002603801,0.00012617139,0.00020754345,0.00025001712,0.000028376113,0.00004961171,0.00052550645,0.00014698254,0.000003816347],"category_scores_gemma":[0.000027183703,0.00011841805,0.000034573102,0.00022327395,0.000013595578,0.00012404127,0.0012790372,0.00034000803,0.0000026106334],"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":[0.000001645376,0.000087549786,0.00059018855,0.00012669417,0.0000064233063,0.0000011268103,0.0032908486,0.5994225,0.00005779635,0.38010162,0.000024639327,0.016288966],"study_design_scores_gemma":[0.0001668571,0.000010489842,0.0045744334,0.000118144875,0.000004436645,3.3854724e-7,0.000047829315,0.9795432,0.00009984295,0.015304944,0.000028560611,0.000100934994],"about_ca_topic_score_codex":0.0018182509,"about_ca_topic_score_gemma":0.00029911628,"teacher_disagreement_score":0.6653038,"about_ca_system_score_codex":0.000028768338,"about_ca_system_score_gemma":0.00007989336,"threshold_uncertainty_score":0.4828948},"labels":[],"label_agreement":null},{"id":"W4415214274","doi":"10.1016/j.neucom.2025.131217","title":"Sycophancy in vision-language models: A systematic analysis and an inference-time mitigation framework","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"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 Key Research and Development Program of China; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China; Canadian Anesthesiologists' Society","keywords":"Sensitivity (control systems); Inference; Filter (signal processing); Trustworthiness; Decoding methods; Polarity (international relations); Path (computing); Mechanism (biology)","score_opus":0.0071095148556247585,"score_gpt":0.32275936569275615,"score_spread":0.3156498508371314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415214274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4119566,0.00007157703,0.58707684,0.00020789354,0.000027741224,0.00025466565,3.3466864e-7,0.00015418149,0.00025017586],"genre_scores_gemma":[0.90420353,0.0000018223308,0.0954662,0.00025027708,0.000017469712,0.000037196263,0.0000030500455,0.0000064160467,0.000014031061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983226,0.00031435004,0.00040937957,0.00055836403,0.00018234544,0.0002129535],"domain_scores_gemma":[0.99813133,0.0009575966,0.00015279258,0.0006398484,0.000051970845,0.00006648578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042894087,0.00014679655,0.00033107583,0.00063353014,0.00015932256,0.00029155894,0.0005624528,0.000073354735,0.0000022734885],"category_scores_gemma":[0.00031945933,0.0001463165,0.000051592437,0.0024776163,0.000021365942,0.00037099025,0.00028961452,0.00029438236,0.000010593132],"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":[0.0000072743483,0.00038560294,0.047135115,0.0035470054,0.00019949158,0.00003204727,0.015259179,0.6878718,0.0038891707,0.16408539,0.000008513112,0.077579394],"study_design_scores_gemma":[0.00010623386,0.000018843179,0.044488765,0.0008392567,0.000038459057,0.0000013345026,0.000031788604,0.94541705,0.000036682857,0.008915423,2.8342353e-7,0.00010588515],"about_ca_topic_score_codex":0.00022973359,"about_ca_topic_score_gemma":0.000015866837,"teacher_disagreement_score":0.49224693,"about_ca_system_score_codex":0.000031520125,"about_ca_system_score_gemma":0.000033711425,"threshold_uncertainty_score":0.5966613},"labels":[],"label_agreement":null},{"id":"W4415306945","doi":"10.1109/iccv51701.2025.00863","title":"Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Perspective (graphical); Visual reasoning; Focus (optics); Construct (python library); Bridge (graph theory); Mental image; Spatial intelligence; Orientation (vector space); Object (grammar)","score_opus":0.013292323184660523,"score_gpt":0.34967133245220955,"score_spread":0.33637900926754905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415306945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013704153,0.00016872377,0.9675068,0.0015292112,0.00022349303,0.0006848962,0.000016913236,0.00053588545,0.015629873],"genre_scores_gemma":[0.87834316,0.0000072223065,0.120692916,0.00016809558,0.000047508536,0.000106666674,0.00004062683,0.000014370073,0.00057942024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997672,0.00017401036,0.0003866357,0.0011191916,0.00035809065,0.00029005366],"domain_scores_gemma":[0.9980833,0.00026289475,0.0001808971,0.0012369273,0.000158845,0.000077142424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037199177,0.00030807726,0.00031522085,0.00046830496,0.00013672422,0.0002722793,0.0012255637,0.00022139115,0.000041504143],"category_scores_gemma":[0.00008700489,0.00032165673,0.0001303366,0.00047433187,0.000031891086,0.00043279622,0.0024790356,0.0009437059,0.00003701013],"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":[0.000004761203,0.00009864567,0.00033830272,0.00003159217,0.000014793647,0.0000060522952,0.0051057176,0.9555285,0.0000888288,0.018793648,0.00005816996,0.019930962],"study_design_scores_gemma":[0.00020745973,0.000009288062,0.0049537183,0.00016762184,0.000005599506,0.0000015836125,0.00020535204,0.9773979,0.00004689099,0.016700316,0.000013951983,0.00029031732],"about_ca_topic_score_codex":0.009461692,"about_ca_topic_score_gemma":0.00012656035,"teacher_disagreement_score":0.86463904,"about_ca_system_score_codex":0.0006350387,"about_ca_system_score_gemma":0.0001875582,"threshold_uncertainty_score":0.9999235},"labels":[],"label_agreement":null},{"id":"W4415535740","doi":"10.1016/j.array.2025.100538","title":"Mamba-caption: Long-range sequence modelling for efficient and accurate image captioning","year":2025,"lang":"en","type":"article","venue":"Array","topic":"Multimodal Machine Learning Applications","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 de Moncton","funders":"University of Johannesburg","keywords":"Closed captioning; Security token; Convolutional neural network; Trigram; Embedding; Clipping (morphology); Decoding methods; Image (mathematics); Pattern recognition (psychology)","score_opus":0.029847909417003684,"score_gpt":0.31212076700627617,"score_spread":0.2822728575892725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415535740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09550691,0.00011017972,0.9004003,0.002583886,0.00010424351,0.00030511743,0.000004426,0.00016590343,0.00081906107],"genre_scores_gemma":[0.76889426,0.000006916083,0.23058653,0.00018431393,0.000027024285,0.000107616586,0.0000046941796,0.0000057221137,0.00018290318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990983,0.000032758984,0.00016565788,0.00039819622,0.000100364356,0.00020472413],"domain_scores_gemma":[0.9992341,0.00016804707,0.00006454988,0.0003821233,0.00009734483,0.00005388082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027648284,0.00010748734,0.000103855804,0.00008956556,0.00032373,0.0001962194,0.00034214463,0.000039263752,0.0000041831895],"category_scores_gemma":[0.000045644545,0.00010783033,0.000037866557,0.00027043684,0.00004862037,0.00018666676,0.0000789094,0.00012187073,0.000025427058],"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":[0.000015757478,0.00008971311,0.00327863,0.00014932496,0.000034931098,0.0000042436195,0.0017423183,0.73041403,0.028888829,0.21563837,0.00019154996,0.019552274],"study_design_scores_gemma":[0.00023058674,0.000011987337,0.0030366445,0.000038657385,0.000007892429,0.000004347229,0.000012962202,0.9922223,0.0007573893,0.0031295563,0.00043296197,0.00011469587],"about_ca_topic_score_codex":0.00013934652,"about_ca_topic_score_gemma":0.000006024338,"teacher_disagreement_score":0.67338735,"about_ca_system_score_codex":0.00004117974,"about_ca_system_score_gemma":0.000042819287,"threshold_uncertainty_score":0.43971932},"labels":[],"label_agreement":null},{"id":"W4415540597","doi":"10.1145/3746027.3755141","title":"Twin Co-Adaptive Dialogue for Progressive Image Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Workflow; Process (computing); Image (mathematics); Quality (philosophy); Iterative and incremental development; Base (topology); Series (stratigraphy); Conjunction (astronomy)","score_opus":0.0294783400563756,"score_gpt":0.3478488747859853,"score_spread":0.3183705347296097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415540597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004202215,0.00027089316,0.97200173,0.007680427,0.00062092196,0.0028865095,0.000056850135,0.0002454212,0.0120350085],"genre_scores_gemma":[0.6044338,0.000007676044,0.3899484,0.001011401,0.0003521514,0.0012326887,0.00007886325,0.000017627986,0.002917444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733156,0.00022014306,0.000555125,0.0011097246,0.00025921973,0.0005242428],"domain_scores_gemma":[0.9976035,0.00042506115,0.00027338896,0.00096618844,0.0005996631,0.00013224377],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051456346,0.0003408455,0.00033009844,0.00027473108,0.0007691086,0.0006716746,0.0010397427,0.00018369508,0.000118227596],"category_scores_gemma":[0.0003336307,0.00033789105,0.00018393979,0.0008364238,0.00021235835,0.0005151305,0.000308407,0.0003248483,0.00023887413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049543305,0.00047567845,0.00059213396,0.00007765221,0.00014416853,0.0000037428106,0.0013042706,0.0016817285,0.013516241,0.60945344,0.022877319,0.34982404],"study_design_scores_gemma":[0.0008688535,0.00020896079,0.0040031387,0.000042429692,0.000047569174,0.0000022174072,0.00003487367,0.97401804,0.011657271,0.0038707443,0.0049184524,0.00032742816],"about_ca_topic_score_codex":0.00038594598,"about_ca_topic_score_gemma":0.000040800154,"teacher_disagreement_score":0.97233635,"about_ca_system_score_codex":0.00016811378,"about_ca_system_score_gemma":0.0005080105,"threshold_uncertainty_score":0.9999073},"labels":[],"label_agreement":null},{"id":"W4415623941","doi":"10.21203/rs.3.rs-7752202/v1","title":"Towards Multimodal Retrieval-Augmented Generation for Medical Visual Question Answering","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Multimodal Machine Learning Applications","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":"Task (project management); Question answering; Trustworthiness; Reliability (semiconductor); Natural language generation; Natural language; Health care; Medical information","score_opus":0.06851537538957315,"score_gpt":0.4775223534019001,"score_spread":0.40900697801232694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415623941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0676542,0.00064012717,0.9057912,0.015331489,0.0017410007,0.007164208,0.0002568036,0.0005298353,0.00089112576],"genre_scores_gemma":[0.9230679,0.00077246345,0.06781765,0.00017061527,0.0026317039,0.0025581566,0.0012957609,0.00009156143,0.001594172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98308957,0.003542117,0.0017472979,0.0035561165,0.0060461615,0.0020187239],"domain_scores_gemma":[0.98869276,0.0023322671,0.00045878204,0.0025425395,0.004864005,0.0011096543],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.016562304,0.0008663758,0.00097450236,0.0017066863,0.0022119398,0.0015719004,0.0039691427,0.001757717,0.0003911677],"category_scores_gemma":[0.014977623,0.00094572594,0.00057607767,0.0027650932,0.0005207887,0.0005159429,0.0057985606,0.0054186354,0.00018529441],"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":[0.00089664874,0.0027875393,0.0029827694,0.0064720847,0.0005205089,0.00005366716,0.004037764,0.048166428,0.014446378,0.06627603,0.002718326,0.85064185],"study_design_scores_gemma":[0.0016795002,0.000673885,0.009991556,0.002188092,0.000037813883,0.000008929605,0.000080210695,0.97403216,0.004344334,0.0015147757,0.004716473,0.0007322509],"about_ca_topic_score_codex":0.005378817,"about_ca_topic_score_gemma":0.00023653396,"teacher_disagreement_score":0.92586577,"about_ca_system_score_codex":0.0019032768,"about_ca_system_score_gemma":0.006495356,"threshold_uncertainty_score":0.9995382},"labels":[],"label_agreement":null},{"id":"W4415822394","doi":"10.1109/ro-man63969.2025.11217693","title":"Transparent Social Navigation for Autonomous Mobile Robots Via Vision-Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"York University","keywords":"Robot; Transparency (behavior); Confusion; Mobile robot; Preference; Service (business); Natural language; Social robot","score_opus":0.016128799605941622,"score_gpt":0.3404957217373021,"score_spread":0.3243669221313605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415822394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014686756,0.000043126478,0.979089,0.0021108428,0.00010996954,0.0006653792,0.000005322062,0.0004077238,0.0028818448],"genre_scores_gemma":[0.87135226,5.9617867e-7,0.12721309,0.000246311,0.000033304623,0.0005483735,0.000028688137,0.000007034662,0.00057034293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907553,0.000032640128,0.0002133373,0.0003635913,0.0001247881,0.00019008898],"domain_scores_gemma":[0.9994165,0.000101469814,0.00005276043,0.00032284603,0.000066880275,0.000039566803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001589291,0.00010918854,0.00012830136,0.0000763111,0.00027586837,0.00009968296,0.0005393856,0.000064749474,0.000012353311],"category_scores_gemma":[0.000005471444,0.00010478929,0.000083725405,0.0002773144,0.000021849075,0.00025314518,0.00007312164,0.00010398192,0.000020044112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073503984,0.00018656444,0.000038033115,0.000045790664,0.000021825606,5.7485516e-7,0.0030863332,0.27792737,0.0047403914,0.23797882,0.0007015898,0.47526535],"study_design_scores_gemma":[0.0003053505,0.000034304896,0.0011298726,0.000009283917,0.0000072642406,6.772835e-7,0.000027003554,0.97975844,0.0010162921,0.017152956,0.00044942013,0.00010912627],"about_ca_topic_score_codex":0.00032448338,"about_ca_topic_score_gemma":0.000014199933,"teacher_disagreement_score":0.8566655,"about_ca_system_score_codex":0.00006933304,"about_ca_system_score_gemma":0.000060142458,"threshold_uncertainty_score":0.4273183},"labels":[],"label_agreement":null},{"id":"W4415848069","doi":"10.1051/wujns/2025305405","title":"Navigating with Spatial Intelligence: A Survey of Scene Graph-Based Object Goal Navigation","year":2025,"lang":"","type":"article","venue":"Wuhan University Journal of Natural Sciences","topic":"Multimodal Machine Learning Applications","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":"Science and Technology Program of Hubei Province","keywords":"Focus (optics); Graph; Object (grammar); Field (mathematics); Robot; Intelligent agent; Scene graph; Generalization","score_opus":0.01439905649340406,"score_gpt":0.2964890693527256,"score_spread":0.28209001285932156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415848069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6777772,0.00038646845,0.31967604,0.0014188242,0.00044201102,0.00018162183,0.000007887901,0.00001568595,0.00009429251],"genre_scores_gemma":[0.9573062,0.00003412697,0.042549513,0.000049775863,0.0000345567,1.3840035e-7,0.0000036636006,0.000004499974,0.000017509154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99647766,0.0007262597,0.00067698164,0.0005173804,0.0011866068,0.00041513596],"domain_scores_gemma":[0.99520946,0.0008148956,0.0017448256,0.00032108312,0.001737538,0.00017223142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029180956,0.0002770143,0.0004944386,0.0005165824,0.0010005884,0.00022689906,0.002737733,0.0001253437,0.000008875096],"category_scores_gemma":[0.00040767097,0.00023363963,0.00020151438,0.006452426,0.001559884,0.0010122791,0.00029129916,0.0013286978,0.0000021849771],"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":[0.0010257015,0.0006607417,0.4047006,0.00019589804,0.00027157037,0.000117435724,0.003052917,0.21662925,0.0045529343,0.0066102115,0.00002437743,0.36215836],"study_design_scores_gemma":[0.0013019984,0.0015355075,0.60249877,0.002958337,0.00012125264,0.000058119465,0.0009961545,0.3806081,0.008828994,0.000660674,0.000020479454,0.0004115748],"about_ca_topic_score_codex":0.016429652,"about_ca_topic_score_gemma":0.0014516783,"teacher_disagreement_score":0.3617468,"about_ca_system_score_codex":0.0002380327,"about_ca_system_score_gemma":0.0017951478,"threshold_uncertainty_score":0.99012005},"labels":[],"label_agreement":null},{"id":"W4415871599","doi":"10.36227/techrxiv.174612962.26131807/v4","title":"LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Face (sociological concept); Reliability (semiconductor); Field (mathematics); Identification (biology); Action (physics)","score_opus":0.028474859388193614,"score_gpt":0.3582016073138506,"score_spread":0.329726747925657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415871599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17104657,0.00035199794,0.81601375,0.005008223,0.001291246,0.0011432507,0.000020671236,0.00023643265,0.004887882],"genre_scores_gemma":[0.993551,0.000012794437,0.0031898406,0.00038899915,0.000046240883,0.00015399109,0.00005542317,0.000011999561,0.0025897068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702585,0.0009568717,0.00063111336,0.00083126716,0.00028094393,0.0002739738],"domain_scores_gemma":[0.9975394,0.00059329526,0.00028818133,0.0008511199,0.0006085405,0.000119466575],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001288852,0.00026639292,0.00029450117,0.00039559812,0.0006609979,0.0014876317,0.00048509068,0.00014806476,0.00006213576],"category_scores_gemma":[0.00029626067,0.00027873364,0.000041792417,0.0016901712,0.00008545138,0.00044282593,0.0002445408,0.00032743328,0.0000892807],"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":[0.00016297944,0.0022873473,0.2533732,0.0012031494,0.00033893986,0.0000072158537,0.0024149765,0.15059605,0.007003262,0.49701202,0.014305739,0.07129511],"study_design_scores_gemma":[0.0004988623,0.00010586769,0.22239012,0.00013595074,0.000021642069,0.0000011216698,0.000099083445,0.7737767,0.00019341106,0.00011421094,0.0024712288,0.00019177873],"about_ca_topic_score_codex":0.015562584,"about_ca_topic_score_gemma":0.0020628439,"teacher_disagreement_score":0.82250446,"about_ca_system_score_codex":0.0002741585,"about_ca_system_score_gemma":0.00037917556,"threshold_uncertainty_score":0.9999665},"labels":[],"label_agreement":null},{"id":"W4415955467","doi":"10.1109/iccv51701.2025.00074","title":"MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea","keywords":"Conversation; Benchmark (surveying); Set (abstract data type); Perception; Context (archaeology); Key (lock)","score_opus":0.02903482643643528,"score_gpt":0.38900244767120323,"score_spread":0.35996762123476794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415955467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08133004,0.0005452146,0.9117511,0.0027036364,0.00028711895,0.0020766521,0.000051753297,0.0001700581,0.0010844083],"genre_scores_gemma":[0.7153011,0.000021832693,0.28269854,0.000453004,0.00002700003,0.0001519615,0.00003128481,0.000013467668,0.0013017883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972634,0.0002632153,0.000524512,0.0011013363,0.000328178,0.0005193568],"domain_scores_gemma":[0.997579,0.00088801247,0.00026630552,0.00072440464,0.00040139884,0.0001408826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015949525,0.000340925,0.00033825223,0.0002937173,0.00072609034,0.00039018062,0.00055843045,0.0002042774,0.00007988051],"category_scores_gemma":[0.00057020056,0.00033481146,0.00012912629,0.0005891669,0.00009194624,0.0008254114,0.000663058,0.0003340603,0.000024367939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016086234,0.0010351765,0.0047417386,0.0006686631,0.00022661596,0.000002847052,0.051980384,0.039649434,0.020052915,0.17569552,0.0006718193,0.705114],"study_design_scores_gemma":[0.0041153044,0.0001481208,0.015907854,0.00015109571,0.00007566044,0.0000012562178,0.0013195514,0.9759289,0.00039095973,0.0014492143,0.00020321469,0.00030886577],"about_ca_topic_score_codex":0.0009506146,"about_ca_topic_score_gemma":0.00010813003,"teacher_disagreement_score":0.9362795,"about_ca_system_score_codex":0.00014315231,"about_ca_system_score_gemma":0.00019714762,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"id":"W4416034471","doi":"10.18653/v1/2025.findings-emnlp.1340","title":"QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Chung-Ang University","keywords":"Automatic summarization; Question answering; Metric (unit); Narrative; Key (lock)","score_opus":0.024177218021763723,"score_gpt":0.3427726956916791,"score_spread":0.3185954776699154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416034471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031316128,0.0002651104,0.94917935,0.006105961,0.0004542761,0.0047437237,0.000022532684,0.00038211484,0.0075308103],"genre_scores_gemma":[0.80485207,0.000023232182,0.19188797,0.00021588444,0.00008902933,0.0016445188,0.00014470745,0.000030533447,0.0011120192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995055,0.0007121003,0.0009045315,0.0016470365,0.0010468144,0.0006345014],"domain_scores_gemma":[0.9936374,0.0009983841,0.0005812068,0.0017979252,0.0028133644,0.00017175773],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027427182,0.00055646006,0.00051292864,0.0012096699,0.0011582257,0.0007060734,0.0015060299,0.00032727513,0.000120224046],"category_scores_gemma":[0.0031588466,0.0005159281,0.000122773,0.004618055,0.00015301617,0.0012057205,0.000470159,0.0005450112,0.00002901031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037571095,0.00058748975,0.0098879775,0.00029071036,0.000313445,8.1768974e-7,0.0062494804,0.18430257,0.0018239185,0.2513966,0.000759388,0.5440119],"study_design_scores_gemma":[0.0034327912,0.00047483903,0.060286954,0.0002964964,0.00025735004,0.0000025140523,0.00032142104,0.92111474,0.0010055896,0.01159371,0.0006993117,0.00051425543],"about_ca_topic_score_codex":0.0030652438,"about_ca_topic_score_gemma":0.0008290447,"teacher_disagreement_score":0.77353597,"about_ca_system_score_codex":0.00079093233,"about_ca_system_score_gemma":0.0012329064,"threshold_uncertainty_score":0.9997292},"labels":[],"label_agreement":null},{"id":"W4416035046","doi":"10.18653/v1/2025.findings-emnlp.387","title":"AdaptMerge: Inference Time Adaptive Visual and Language-Guided Token Merging for Efficient Large Multimodal Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind","keywords":"Inference; Security token; Feature (linguistics); Visualization; Pattern recognition (psychology)","score_opus":0.0188835584601864,"score_gpt":0.3386773881967409,"score_spread":0.3197938297365545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10459071,0.00071423926,0.8854785,0.0018467412,0.00025040246,0.0018838982,0.000076676646,0.00036068307,0.004798179],"genre_scores_gemma":[0.87414193,0.000021460804,0.12180279,0.0005335218,0.00007591889,0.00033392356,0.000023012104,0.00003474801,0.0030326683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575925,0.00025436765,0.0008451789,0.0015996984,0.00046926382,0.0010722571],"domain_scores_gemma":[0.9968268,0.0011507111,0.0002874663,0.00094044884,0.0004815436,0.0003129991],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010041812,0.00060874654,0.00064678275,0.00045351725,0.0009161753,0.00041751855,0.0011234292,0.0002562132,0.00016170974],"category_scores_gemma":[0.00041174254,0.00061279844,0.00020532412,0.0010581343,0.00016842793,0.0004534516,0.0015328742,0.00053301145,0.000106772844],"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":[0.00026695037,0.001074488,0.0004523587,0.00018159846,0.00029664682,0.000006255964,0.009188128,0.53167456,0.0036372382,0.36267632,0.0008757595,0.08966965],"study_design_scores_gemma":[0.002087764,0.0002689518,0.0018211482,0.0001468406,0.000091541464,0.0000026698947,0.00034377453,0.9923074,0.0007237989,0.0013320064,0.000270487,0.0006036098],"about_ca_topic_score_codex":0.0019947109,"about_ca_topic_score_gemma":0.000053019623,"teacher_disagreement_score":0.7695513,"about_ca_system_score_codex":0.00016701868,"about_ca_system_score_gemma":0.00045298398,"threshold_uncertainty_score":0.99963236},"labels":[],"label_agreement":null},{"id":"W4416035530","doi":"10.18653/v1/2025.emnlp-main.1379","title":"CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Anomaly detection; Cave; Perception; Visual reasoning; Commonsense reasoning; Visualization; Cognition; Resource (disambiguation)","score_opus":0.007723986487770126,"score_gpt":0.27797688700207784,"score_spread":0.2702529005143077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7473465,0.000025003512,0.24900158,0.00060665194,0.00002042995,0.00007439255,1.0770875e-7,0.000059734637,0.002865602],"genre_scores_gemma":[0.9598317,0.0000025038769,0.03974796,0.00017753609,0.0000040514774,0.000020464653,3.6170837e-7,0.0000028960274,0.00021253523],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99936795,0.000062251354,0.00013090111,0.0002379555,0.00006331202,0.00013765476],"domain_scores_gemma":[0.99947995,0.00025983102,0.000028750146,0.00020043436,0.0000032133755,0.000027825206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018810226,0.00007073728,0.00008059638,0.00012447112,0.00011870793,0.00006548921,0.00017986525,0.000028273333,0.0000036314646],"category_scores_gemma":[0.000058790494,0.000071189155,0.000010495012,0.00020329769,0.000027441223,0.000105449035,0.00030066332,0.0001294155,0.0000096792],"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":[0.0000048353368,0.00006693651,0.7326713,0.000011198393,0.000010671915,0.000008738917,0.0024771648,0.0009791688,0.006703273,0.027895445,0.000019658555,0.2291516],"study_design_scores_gemma":[0.0002153966,0.000014698474,0.5432405,0.000014190058,0.0000012331253,0.0000039479432,0.0001960019,0.4540408,0.0014074593,0.00054789556,0.00023793719,0.00007996975],"about_ca_topic_score_codex":0.00062233023,"about_ca_topic_score_gemma":0.00010294652,"teacher_disagreement_score":0.45306164,"about_ca_system_score_codex":0.000028689952,"about_ca_system_score_gemma":0.000009707907,"threshold_uncertainty_score":0.29030094},"labels":[],"label_agreement":null},{"id":"W4416036439","doi":"10.18653/v1/2025.emnlp-main.567","title":"Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Azrieli Foundation; European Commission; University of Manchester; Open Philanthropy Project","keywords":"Natural language; Language model; Feature (linguistics); Semantics (computer science); Language understanding; Automated reasoning","score_opus":0.03062317003061937,"score_gpt":0.3144617111784772,"score_spread":0.28383854114785784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416036439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07011579,0.00086828775,0.9079902,0.0022092059,0.00018791803,0.00047291387,0.0000036813567,0.00010345312,0.018048503],"genre_scores_gemma":[0.8807611,0.00006538699,0.114078835,0.00035192727,0.0000267016,0.000025398223,0.000004500551,0.000016661055,0.0046694926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729913,0.00022671327,0.000590669,0.0010035447,0.00022725348,0.00065269094],"domain_scores_gemma":[0.9986691,0.0002653025,0.00015122443,0.00072320993,0.00005697341,0.00013422639],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001042602,0.00030342548,0.0003537677,0.00045039976,0.00046540683,0.0005026939,0.0005616946,0.00017263096,0.00016936936],"category_scores_gemma":[0.00011407497,0.00033454306,0.00007880003,0.0013422879,0.00007377075,0.0007660343,0.00087997544,0.000606307,0.00009276115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014261256,0.00034406123,0.041085433,0.00029105655,0.00006031797,0.000016068176,0.011359313,0.011837779,0.003821689,0.9219338,0.00007114206,0.009165039],"study_design_scores_gemma":[0.0014149951,0.000016380422,0.016936528,0.00063304283,0.000015335583,0.000005228141,0.0031252343,0.9754012,0.00012373521,0.0019979405,0.000029955045,0.0003003834],"about_ca_topic_score_codex":0.0017502408,"about_ca_topic_score_gemma":0.00199365,"teacher_disagreement_score":0.96356344,"about_ca_system_score_codex":0.00039438502,"about_ca_system_score_gemma":0.00013132782,"threshold_uncertainty_score":0.99991065},"labels":[],"label_agreement":null},{"id":"W4416036623","doi":"10.18653/v1/2025.emnlp-main.607","title":"ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Chart; Natural language; Natural (archaeology); Empirical research; Natural language generation","score_opus":0.0389669361203135,"score_gpt":0.3372278773477799,"score_spread":0.29826094122746644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416036623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.152199,0.000113351714,0.8121129,0.014984473,0.0004066049,0.000936031,0.00000121984,0.00025595588,0.018990412],"genre_scores_gemma":[0.96990544,0.000042546744,0.025408588,0.0007517051,0.000072711875,0.00014337222,0.000010697264,0.000029909697,0.003635011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957,0.0002259775,0.0011255199,0.0014180029,0.0006351496,0.00089536724],"domain_scores_gemma":[0.99788004,0.00017285332,0.0003825848,0.0012290328,0.0001860068,0.00014949031],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015164869,0.00048293214,0.00049292867,0.0008582877,0.00066453376,0.0006920958,0.00099759,0.00017275712,0.0002392862],"category_scores_gemma":[0.00011663689,0.0004678091,0.00011409985,0.00271876,0.000115730974,0.0006948515,0.0005543033,0.0007467521,0.00013923885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006383448,0.00071798655,0.21322,0.000505049,0.00019628863,0.000034077086,0.00403223,0.014324145,0.042989112,0.6891615,0.00065767654,0.03409809],"study_design_scores_gemma":[0.002248333,0.00016556447,0.28386366,0.002204104,0.000062287065,0.000008238099,0.0012544519,0.7025041,0.0032575086,0.0028667815,0.00077960634,0.0007853661],"about_ca_topic_score_codex":0.0019723882,"about_ca_topic_score_gemma":0.0017280714,"teacher_disagreement_score":0.81770647,"about_ca_system_score_codex":0.001334668,"about_ca_system_score_gemma":0.0003508817,"threshold_uncertainty_score":0.9997774},"labels":[],"label_agreement":null},{"id":"W4416037147","doi":"10.18653/v1/2025.emnlp-industry.187","title":"GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Scalability; Natural language; Natural (archaeology); Empirical research; Scale (ratio); Component (thermodynamics)","score_opus":0.02182292723303706,"score_gpt":0.34061300225866864,"score_spread":0.31879007502563156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416037147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010994643,0.0024039086,0.9727901,0.005337604,0.0011502093,0.0035146805,0.000024409224,0.00021129886,0.0035731217],"genre_scores_gemma":[0.81620115,0.000011085413,0.18056527,0.0005187176,0.0000657796,0.0012846098,0.0000115275625,0.000020758622,0.0013211145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964135,0.0004768753,0.00073453406,0.0012231938,0.00056851486,0.0005833613],"domain_scores_gemma":[0.9956122,0.001721019,0.00029626966,0.0013855625,0.00079806306,0.00018685986],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028707094,0.00036107452,0.000496064,0.000326483,0.0007048476,0.001387364,0.00084554334,0.0003168777,0.00009492743],"category_scores_gemma":[0.0013570022,0.00035478815,0.00013572235,0.0011005166,0.00013207817,0.00032460902,0.00032047267,0.0004671659,0.000038796108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008345191,0.00038854874,0.008589187,0.0010649923,0.00020095622,7.297051e-7,0.0006873576,0.10915733,0.00074621494,0.7717724,0.0016436568,0.10566517],"study_design_scores_gemma":[0.0010322754,0.0001296912,0.004475712,0.00081684295,0.00018840615,0.0000016157677,0.000109885405,0.9774149,0.00023828667,0.010387505,0.004880624,0.0003242278],"about_ca_topic_score_codex":0.0021594227,"about_ca_topic_score_gemma":0.000036460646,"teacher_disagreement_score":0.8682576,"about_ca_system_score_codex":0.00036936087,"about_ca_system_score_gemma":0.0009805313,"threshold_uncertainty_score":0.9998904},"labels":[],"label_agreement":null},{"id":"W4416037383","doi":"10.18653/v1/2025.emnlp-demos.68","title":"From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Institute for Advanced Research","keywords":"Natural (archaeology); Empirical research; Natural language; Action (physics)","score_opus":0.01081601759030118,"score_gpt":0.3170005470036598,"score_spread":0.3061845294133586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416037383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4811887,0.00005820226,0.50513166,0.0020350125,0.0003048677,0.0004080034,0.00001534168,0.00020254224,0.010655651],"genre_scores_gemma":[0.80036235,0.000008722329,0.19629604,0.0014557384,0.00008907589,0.00008621164,0.000010522902,0.000027760741,0.001663558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613374,0.000168237,0.0007791689,0.0015312234,0.0006358751,0.000751752],"domain_scores_gemma":[0.99717,0.00027209622,0.00023634332,0.0017339501,0.00029095315,0.00029665921],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000391113,0.0005447813,0.0005098749,0.00041468252,0.0005140592,0.00091139314,0.0028873524,0.00015202437,0.00036092734],"category_scores_gemma":[0.00003806476,0.000478161,0.000125867,0.0012592528,0.00018474014,0.0012043081,0.0021493027,0.0010241922,0.0003751219],"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":[0.00038905095,0.001153029,0.0529927,0.000105492334,0.00018198961,0.000049994425,0.052592758,0.17454392,0.0077496087,0.020449843,0.0010501893,0.68874145],"study_design_scores_gemma":[0.00058277376,0.000542687,0.021564355,0.0015424287,0.00005003731,0.000009386652,0.00078794005,0.97250026,0.0014204173,0.00026797267,0.00019456512,0.0005371887],"about_ca_topic_score_codex":0.013954021,"about_ca_topic_score_gemma":0.0002949886,"teacher_disagreement_score":0.79795635,"about_ca_system_score_codex":0.00023396935,"about_ca_system_score_gemma":0.00028169423,"threshold_uncertainty_score":0.999767},"labels":[],"label_agreement":null},{"id":"W4416047703","doi":"10.48550/arxiv.2505.21979","title":"Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pearl; Benchmark (surveying); Arabic; Workflow; Benchmarking; Mainstream; Semantics (computer science)","score_opus":0.03124253345628599,"score_gpt":0.31305448999951957,"score_spread":0.2818119565432336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416047703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8398669,0.00013392713,0.1481492,0.0053407424,0.00174291,0.0011041381,0.0013758417,0.0012485007,0.0010378797],"genre_scores_gemma":[0.9603963,0.00003941221,0.033917747,0.00055683014,0.00030416253,0.00032747292,0.0037945658,0.000024537962,0.0006389773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99691314,0.00020295935,0.0005356118,0.0015057382,0.00039580176,0.0004467834],"domain_scores_gemma":[0.996411,0.00011594437,0.0003801141,0.0027079256,0.0002137525,0.0001712334],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026653166,0.000489799,0.00043454318,0.00025228996,0.0003481515,0.00029108123,0.0029252886,0.00039485586,0.000045388926],"category_scores_gemma":[0.00017146934,0.00047148758,0.00018082387,0.0004997589,0.000095438045,0.00041768074,0.0037332901,0.0016902429,0.0005864525],"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":[0.000053939897,0.0007938454,0.78983146,0.0011641565,0.0005699423,0.00006874176,0.0040907627,0.04745862,0.0016316326,0.011040217,0.025782708,0.117513955],"study_design_scores_gemma":[0.00076389004,0.00003481818,0.7233551,0.00024319839,0.000062372805,0.000025248839,0.000046750672,0.25462285,0.0002469411,0.0010910097,0.018626222,0.0008816005],"about_ca_topic_score_codex":0.0046490384,"about_ca_topic_score_gemma":0.000102206635,"teacher_disagreement_score":0.20716424,"about_ca_system_score_codex":0.00019450352,"about_ca_system_score_gemma":0.00028528567,"threshold_uncertainty_score":0.9997737},"labels":[],"label_agreement":null},{"id":"W4416052645","doi":"10.1109/iccv51701.2025.00693","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Impact","funders":"Gauss Centre for Supercomputing; European Space Agency","keywords":"Multimodality; Inference; Geospatial analysis; Generative grammar; Security token; Semantics (computer science); Modalities; Multimodal learning; Earth observation","score_opus":0.038109397919419856,"score_gpt":0.33133000540431273,"score_spread":0.29322060748489287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416052645","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":[0.016218215,0.000019380583,0.97118694,0.0069942344,0.00053047837,0.0017406053,0.00027687752,0.0005969105,0.0024363652],"genre_scores_gemma":[0.12286648,0.0000045527026,0.8675647,0.0016042104,0.00016034803,0.0013679365,0.0003609496,0.000013665087,0.0060571996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975302,0.00015539333,0.00046494353,0.0012067419,0.00027244244,0.00037022747],"domain_scores_gemma":[0.9972929,0.0002974367,0.0002709445,0.0016829631,0.00035902284,0.0000967829],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061723986,0.0003342458,0.0003763194,0.00014549897,0.00030341587,0.0003055393,0.0015875815,0.00033504056,0.00002366191],"category_scores_gemma":[0.00015879003,0.00032651075,0.0002215501,0.00023118264,0.000030047739,0.00018984781,0.0018044295,0.0006069547,0.000029506844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051285155,0.0012350082,0.016604075,0.0009043545,0.00033982922,0.0000015807921,0.0086443275,0.14474037,0.0026166064,0.6232163,0.0060809436,0.19556534],"study_design_scores_gemma":[0.00036514434,0.000019893387,0.051755752,0.00003318656,0.00001587975,2.88249e-7,0.000013955045,0.92689806,0.0024325373,0.009294133,0.008856577,0.00031458813],"about_ca_topic_score_codex":0.0009454895,"about_ca_topic_score_gemma":0.00033059742,"teacher_disagreement_score":0.78215766,"about_ca_system_score_codex":0.00008375333,"about_ca_system_score_gemma":0.00030104,"threshold_uncertainty_score":0.9999187},"labels":[],"label_agreement":null},{"id":"W4416098793","doi":"10.1109/iccv51701.2025.00626","title":"Placeit3d: Language-Guided Object Placement in Real 3D Scenes","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Task (project management); Suite; Benchmark (surveying); Object (grammar); Asset (computer security); Point (geometry); 3d model","score_opus":0.024564468975065434,"score_gpt":0.34878465117733887,"score_spread":0.32422018220227344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416098793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11342319,0.00027558795,0.52737325,0.005936141,0.001101712,0.002275466,0.00004143245,0.0021285876,0.34744465],"genre_scores_gemma":[0.5649371,0.00009930803,0.4184119,0.0007444332,0.00015480544,0.0007518657,0.000106507425,0.000025957394,0.014768069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975358,0.00020234656,0.0004946182,0.0010320137,0.00036424721,0.00037096455],"domain_scores_gemma":[0.99765575,0.00024864322,0.00017454615,0.001763167,0.000071701936,0.00008617822],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058170327,0.000330441,0.0003760308,0.00043808194,0.00008046699,0.00022076086,0.002071067,0.00024618488,0.000105949206],"category_scores_gemma":[0.000113201204,0.0003213639,0.00009836992,0.000457068,0.00002919379,0.00008205639,0.003289943,0.0008592439,0.00011876882],"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":[0.00005155414,0.000991606,0.062812686,0.0011101934,0.0002426156,0.000106625324,0.016222782,0.6154639,0.0009941814,0.15459536,0.022597497,0.12481099],"study_design_scores_gemma":[0.00076660747,0.000027628961,0.0438691,0.00028549376,0.000016043101,0.0000051062757,0.00010595826,0.95053434,0.0006596986,0.0014099819,0.0016571109,0.00066291867],"about_ca_topic_score_codex":0.025362844,"about_ca_topic_score_gemma":0.001227434,"teacher_disagreement_score":0.45151395,"about_ca_system_score_codex":0.00026881616,"about_ca_system_score_gemma":0.00045761632,"threshold_uncertainty_score":0.9999238},"labels":[],"label_agreement":null},{"id":"W4416118802","doi":"10.48550/arxiv.2504.05227","title":"A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Popularity; Feature (linguistics); Reality check; Check-in; Noise (video); Visualization","score_opus":0.06354629236181726,"score_gpt":0.38898361299617124,"score_spread":0.325437320634354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416118802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92422193,0.0005731335,0.07111218,0.0019299814,0.00024685016,0.00089975365,0.000023384395,0.00024168611,0.0007511043],"genre_scores_gemma":[0.94566697,0.0000306503,0.053833358,0.00008017285,0.000086496955,0.00015024385,0.000030205467,0.000017816683,0.00010407076],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99704397,0.00042043228,0.0007463363,0.0011053389,0.00026245037,0.00042146],"domain_scores_gemma":[0.9969966,0.0003410789,0.00059957267,0.0018546466,0.00011691951,0.00009122185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010064715,0.0003397445,0.0006584989,0.0003595008,0.00009949959,0.000067691486,0.0018519675,0.0003941982,0.000011158768],"category_scores_gemma":[0.00043027903,0.0003447267,0.00015562837,0.0005169035,0.00016179835,0.00013857307,0.0021907159,0.0012286323,0.0000075043204],"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":[0.000040299845,0.00040747327,0.824469,0.00092114846,0.0001427939,0.0000441626,0.035659492,0.04244831,0.009578376,0.0024781914,0.000062593455,0.0837482],"study_design_scores_gemma":[0.00034421374,0.000034124107,0.57664466,0.0007881128,0.000021260794,0.000007958172,0.00016695497,0.41977334,0.0006571823,0.0011373566,0.000118770105,0.00030608306],"about_ca_topic_score_codex":0.003576689,"about_ca_topic_score_gemma":0.00014399008,"teacher_disagreement_score":0.37732503,"about_ca_system_score_codex":0.00016503134,"about_ca_system_score_gemma":0.0006170973,"threshold_uncertainty_score":0.99990046},"labels":[],"label_agreement":null},{"id":"W4416183485","doi":"10.1109/mipr67560.2025.00054","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Retraining; Normalization (sociology); Inference; Reliability (semiconductor); Adaptation (eye); Test data; Reduction (mathematics)","score_opus":0.009100288445900715,"score_gpt":0.32291833367351613,"score_spread":0.3138180452276154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416183485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06309055,0.00036929632,0.8157803,0.011134628,0.0002110875,0.00055827765,0.000005228252,0.00025766328,0.108592995],"genre_scores_gemma":[0.76135784,0.0000149606185,0.23473655,0.0005232276,0.00003355961,0.00010861654,0.000009138944,0.000016102302,0.003199998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967522,0.00030033212,0.00087906106,0.0010750272,0.00038570742,0.0006076769],"domain_scores_gemma":[0.99765474,0.00056750147,0.00020781237,0.0011903828,0.000243593,0.00013600306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094452675,0.00032898827,0.00033526626,0.00082469924,0.0006539383,0.00083216955,0.0012953907,0.00016924532,0.000250803],"category_scores_gemma":[0.00041148442,0.00037377354,0.00012788275,0.0026693752,0.00014537395,0.001457678,0.00084721844,0.00084448257,0.00020600275],"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":[0.0000034260268,0.00038476454,0.0016306142,0.00009655406,0.000028432149,0.000016222399,0.009503652,0.22341877,0.0077400687,0.6073005,0.00030706893,0.1495699],"study_design_scores_gemma":[0.0005846454,0.000021543854,0.023461612,0.00036493948,0.000012992057,0.0000038497333,0.00063929457,0.954853,0.00042454692,0.019286959,0.00004237776,0.000304228],"about_ca_topic_score_codex":0.0077402354,"about_ca_topic_score_gemma":0.0006029321,"teacher_disagreement_score":0.7314342,"about_ca_system_score_codex":0.00028646638,"about_ca_system_score_gemma":0.0003523288,"threshold_uncertainty_score":0.99987143},"labels":[],"label_agreement":null},{"id":"W4416237890","doi":"10.1007/978-3-032-08452-1_4","title":"Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"Flexibility (engineering); Benchmark (surveying); Key (lock); Activity recognition; Health care; Generative grammar; Deep learning; Code (set theory)","score_opus":0.016681572316009224,"score_gpt":0.32324759820422455,"score_spread":0.30656602588821535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416237890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018568833,0.00012993476,0.9895157,0.0062644677,0.00032964686,0.001084419,0.000030187184,0.00021259525,0.0005761218],"genre_scores_gemma":[0.66479117,0.000008806919,0.33375573,0.0010723057,0.00007536757,0.00007790722,0.000041116222,0.000024171792,0.00015343852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968416,0.00006376775,0.0004309504,0.0016180043,0.0004999466,0.00054572755],"domain_scores_gemma":[0.99762803,0.000634649,0.00029711047,0.001129787,0.00020672337,0.0001037204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00099127,0.00040101403,0.0004484539,0.0010696434,0.00033843357,0.00030532703,0.0019823033,0.0003359274,0.0000028929753],"category_scores_gemma":[0.00010111496,0.0004182148,0.000114079776,0.0006629944,0.00019482244,0.0005737225,0.00082643144,0.0010451677,0.000008672235],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005875861,0.000038853606,0.000023582052,0.00014017116,0.0000031069796,0.0000068264258,0.00065266725,0.029239869,0.0005515348,0.0076361727,0.000007869381,0.96169347],"study_design_scores_gemma":[0.00023617306,0.00009731738,0.0004521973,0.00051432295,0.0000030592,0.0000050061476,1.3624141e-7,0.7797246,0.00022863876,0.21838179,0.00003789116,0.0003188924],"about_ca_topic_score_codex":0.0008173267,"about_ca_topic_score_gemma":0.0011068272,"teacher_disagreement_score":0.9613746,"about_ca_system_score_codex":0.0005906916,"about_ca_system_score_gemma":0.0003681689,"threshold_uncertainty_score":0.99982697},"labels":[],"label_agreement":null},{"id":"W4416252247","doi":"10.1109/ijcnn64981.2025.11228324","title":"GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Pattern recognition (psychology); Cluster analysis; Closed captioning; Feature extraction; Contextual image classification; Graph; Feature vector; Pixel; Artificial neural network","score_opus":0.00910167173983274,"score_gpt":0.28663465930706206,"score_spread":0.27753298756722933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416252247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13037466,0.00023343817,0.8533223,0.0067631807,0.00016259127,0.0018389691,0.000011748764,0.0003650894,0.006927998],"genre_scores_gemma":[0.80922997,0.0000759899,0.18717507,0.00027934343,0.000044292006,0.0004630051,0.000044357734,0.000042974516,0.0026450225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961097,0.00020844274,0.0008175846,0.0016647414,0.00042751225,0.00077197974],"domain_scores_gemma":[0.9973314,0.0008218514,0.00042746664,0.0006321511,0.0005555413,0.00023161963],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00084506645,0.0005391047,0.000513653,0.0004200148,0.0017978088,0.0009226211,0.0006285237,0.0002492603,0.000024791252],"category_scores_gemma":[0.00036707098,0.000520997,0.00013271731,0.0014247996,0.00035216523,0.0015297922,0.00015638302,0.00087413506,0.000042992135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041259656,0.00033382227,0.0069761476,0.0005585971,0.00013332508,0.0000014690646,0.0037446672,0.0131458165,0.27868056,0.0321586,0.00019043288,0.663664],"study_design_scores_gemma":[0.0029426324,0.00039638914,0.055996932,0.00046597412,0.000074694915,0.0000045425577,0.0010738367,0.9243299,0.008165,0.00042988968,0.0055389795,0.00058126106],"about_ca_topic_score_codex":0.00043126312,"about_ca_topic_score_gemma":0.0003299008,"teacher_disagreement_score":0.9111841,"about_ca_system_score_codex":0.00024021558,"about_ca_system_score_gemma":0.00031906142,"threshold_uncertainty_score":0.99972415},"labels":[],"label_agreement":null},{"id":"W4416365506","doi":"10.21203/rs.3.rs-7900022/v1","title":"GRAVITI: Grounded Retrieval Generation Framework for VideoLLM Hallucination Mitigation","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Security token; Process (computing); Decoding methods; Task (project management); Task analysis; Ground; Detector","score_opus":0.11216086555727185,"score_gpt":0.46550703184026554,"score_spread":0.3533461662829937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416365506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010554198,0.0006091493,0.9585718,0.017193723,0.0016821384,0.009119516,0.00034619562,0.00038334003,0.0015399416],"genre_scores_gemma":[0.6863066,0.00031336397,0.30557725,0.00014137171,0.0018898149,0.0025282742,0.001611683,0.00006660152,0.001565008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867244,0.0030898552,0.0015552077,0.003418479,0.0035357107,0.0016763816],"domain_scores_gemma":[0.9828301,0.005547086,0.0007488656,0.0035746815,0.0067962147,0.00050305156],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009260503,0.00080912147,0.0008396881,0.0019122724,0.0037536868,0.002886669,0.0033703146,0.0017494858,0.00013497577],"category_scores_gemma":[0.011525923,0.0009574533,0.0005625752,0.0039221826,0.00042835812,0.00083497533,0.0027340623,0.0050792675,0.00023208522],"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":[0.00020401512,0.0006018873,0.0006338534,0.0021995865,0.00016765918,0.000004813832,0.002981594,0.020547088,0.0020714272,0.803544,0.001054552,0.16598955],"study_design_scores_gemma":[0.00074040535,0.00040269064,0.014462875,0.0016118811,0.000049401177,0.000003367793,0.00010035202,0.77178025,0.003306081,0.20344962,0.0034307176,0.00066234387],"about_ca_topic_score_codex":0.0017301701,"about_ca_topic_score_gemma":0.00019999433,"teacher_disagreement_score":0.75123316,"about_ca_system_score_codex":0.00217177,"about_ca_system_score_gemma":0.002294439,"threshold_uncertainty_score":0.99954647},"labels":[],"label_agreement":null},{"id":"W4416366377","doi":"10.1109/tvcg.2025.3634791","title":"Probing the Visualization Literacy of Vision Language Models: The Good, the Bad, and the Ugly","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Multimodal Machine Learning Applications","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":"Visualization; Chart; Correctness; Comprehension; Data visualization; Program comprehension; Code (set theory); Visual reasoning; Key (lock)","score_opus":0.009481657295951497,"score_gpt":0.30011784424893456,"score_spread":0.29063618695298304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416366377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0133448625,0.00029144294,0.98208576,0.0031288115,0.00020742326,0.0007218189,0.0000037505254,0.00010788762,0.0001082373],"genre_scores_gemma":[0.99670637,0.000304359,0.00048186068,0.002290703,0.000028134442,0.00010328133,0.0000035723144,0.000011548121,0.00007017766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983448,0.00057502254,0.00034454223,0.00031367582,0.00027794752,0.00014404708],"domain_scores_gemma":[0.99808055,0.0009025614,0.00016644888,0.0006514559,0.00017003366,0.000028965585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079816394,0.00017048664,0.00015168042,0.00015929692,0.0011910535,0.00043431,0.0006530877,0.00006622338,0.0000019177862],"category_scores_gemma":[0.000009186262,0.000080632046,0.00008457068,0.0012786674,0.00035871073,0.00030940856,0.000029360996,0.00028498922,0.0000010369047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000175026,0.00007038458,0.00003593562,0.00002251654,0.000039282433,1.045834e-7,0.009935677,0.011356682,0.000018583049,0.95502436,0.000051178657,0.023427792],"study_design_scores_gemma":[0.0005638955,0.000045161298,0.0011627931,0.0000649812,0.000043580407,0.000005876049,0.00016508141,0.99067175,0.00018021585,0.006450289,0.00055792835,0.000088463516],"about_ca_topic_score_codex":0.00019437408,"about_ca_topic_score_gemma":0.000034956818,"teacher_disagreement_score":0.9833615,"about_ca_system_score_codex":0.000011334539,"about_ca_system_score_gemma":0.000037159116,"threshold_uncertainty_score":0.9160741},"labels":[],"label_agreement":null},{"id":"W4416401253","doi":"10.1109/ismar-adjunct68609.2025.00263","title":"Project LOCOMO AR: Augmented Reality with Carbon Metrics for Sustainable AI Use","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Algoma University","funders":"National Research Foundation","keywords":"Augmented reality; Carbon footprint; Visualization; Data visualization; Carbon fibers; Field (mathematics)","score_opus":0.028191111005435008,"score_gpt":0.33895225613586555,"score_spread":0.3107611451304305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416401253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011935885,0.0000950949,0.95429665,0.014779313,0.00012379784,0.0057143173,0.000013979309,0.0004638436,0.012577137],"genre_scores_gemma":[0.8797993,0.000018325694,0.08112592,0.0021956267,0.000051645453,0.0011946548,0.00002794739,0.000038130263,0.03554846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583185,0.00032084747,0.0006972795,0.0014840829,0.0005368169,0.0011291114],"domain_scores_gemma":[0.99450743,0.001044606,0.00031890708,0.0021529822,0.0018036958,0.00017235597],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013245246,0.00049336633,0.0005389366,0.0009904744,0.00072029076,0.0013348793,0.001462629,0.00021154119,0.000012111546],"category_scores_gemma":[0.0011331243,0.000427251,0.00015303645,0.007166311,0.00017847872,0.0007676502,0.00084337767,0.0006142849,0.000004463664],"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":[0.00042783597,0.0016779258,0.042583834,0.0015000205,0.00050081423,0.000027936398,0.000919581,0.014123874,0.00006833998,0.8785776,0.02438703,0.035205226],"study_design_scores_gemma":[0.0016757395,0.0004249068,0.010169075,0.00008056279,0.00014657315,0.00000391474,0.00021156484,0.9240821,0.00054336974,0.0025170455,0.059668243,0.0004769262],"about_ca_topic_score_codex":0.08078625,"about_ca_topic_score_gemma":0.0006136832,"teacher_disagreement_score":0.9099582,"about_ca_system_score_codex":0.0006437928,"about_ca_system_score_gemma":0.00171373,"threshold_uncertainty_score":0.9998179},"labels":[],"label_agreement":null},{"id":"W4416402720","doi":"10.1109/ismar-adjunct68609.2025.00223","title":"Region-Guided Interactive Docent for Paintings in Mixed Reality","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Interface","keywords":"Painting; Mixed reality; Cursor (databases); Visitor pattern; Augmented reality; Virtual reality","score_opus":0.03880225086164991,"score_gpt":0.3627388482090029,"score_spread":0.323936597347353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416402720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025418943,0.00004582616,0.8923066,0.06419538,0.0006847427,0.0017900857,0.0000045194543,0.00019227364,0.01536162],"genre_scores_gemma":[0.94777846,0.000018019131,0.04650708,0.0018678555,0.00006251101,0.0004668717,0.000009151196,0.00001497436,0.0032750554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964607,0.00042374444,0.00099299,0.0012762451,0.00022098921,0.00062538404],"domain_scores_gemma":[0.99605054,0.0016919201,0.0003663197,0.001316067,0.00044798295,0.0001271549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001486788,0.0003362254,0.00045102707,0.00043141854,0.00029308605,0.00033572328,0.0014113104,0.00017482515,0.00003091991],"category_scores_gemma":[0.0018158559,0.00034641844,0.0002149001,0.0015214662,0.00012046816,0.00039084518,0.00078451535,0.00057607144,0.000041083513],"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":[0.000112287766,0.0008465378,0.021975731,0.00026591946,0.00009452792,0.0000058283467,0.0030844514,0.002573255,0.00031133145,0.5848015,0.024738891,0.36118972],"study_design_scores_gemma":[0.0012115138,0.000057082514,0.14825203,0.0002652096,0.000019404488,0.000003887485,0.00017693751,0.8082467,0.00078107376,0.025050897,0.015622084,0.0003132167],"about_ca_topic_score_codex":0.009313788,"about_ca_topic_score_gemma":0.00046193114,"teacher_disagreement_score":0.9223595,"about_ca_system_score_codex":0.0004788681,"about_ca_system_score_gemma":0.0003642993,"threshold_uncertainty_score":0.9998988},"labels":[],"label_agreement":null},{"id":"W4416417137","doi":"10.1007/s11432-025-4676-4","title":"Large multimodal models evaluation: a survey","year":2025,"lang":"en","type":"article","venue":"Science China Information Sciences","topic":"Multimodal Machine Learning Applications","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":"","keywords":"Competence (human resources); Data collection; Evaluation methods; Term (time); Multimodal interaction","score_opus":0.03383829650789999,"score_gpt":0.36397139492180575,"score_spread":0.33013309841390576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416417137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117004864,0.000029590517,0.8119052,0.002361432,0.000556769,0.00052347465,0.0000109550265,0.000254271,0.067353435],"genre_scores_gemma":[0.96852285,0.0000036080273,0.03051215,0.00080099667,0.000011190814,0.00009056756,0.000009792696,0.0000016003477,0.00004722603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629015,0.00017480626,0.0005063062,0.00053215877,0.0019144937,0.00058211386],"domain_scores_gemma":[0.99777216,0.00018370619,0.0002486819,0.0007980067,0.00086170656,0.00013575288],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.014650929,0.00017010981,0.00015417363,0.0010704603,0.0023042762,0.0016687899,0.0039214264,0.00005200508,0.000034874567],"category_scores_gemma":[0.0016233438,0.00014280569,0.000040455925,0.008383013,0.0008222583,0.013349769,0.00074997434,0.00020178242,0.000186222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033446427,0.00006947488,0.012539795,0.000011431719,0.0000044846024,9.254999e-8,0.0042409943,0.11054345,0.00013148725,0.79297066,0.00054144266,0.078943335],"study_design_scores_gemma":[0.00021749847,0.000020209887,0.26739678,0.000010221831,0.0000017821795,0.0000015313094,0.0000930798,0.7118121,0.00013529205,0.019802334,0.00039008466,0.00011912413],"about_ca_topic_score_codex":0.0010473029,"about_ca_topic_score_gemma":0.00006669278,"teacher_disagreement_score":0.851518,"about_ca_system_score_codex":0.00017915266,"about_ca_system_score_gemma":0.0019271958,"threshold_uncertainty_score":0.9993676},"labels":[],"label_agreement":null},{"id":"W4416548821","doi":"10.1109/iccv51701.2025.01902","title":"Representation Shift: Unifying Token Compression with Flashattention","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Security token; Data compression; Compression (physics); Computation; Transformer; Representation (politics); Overhead (engineering); Lossless compression; Decoding methods","score_opus":0.013642536399723782,"score_gpt":0.3111054682249951,"score_spread":0.2974629318252713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416548821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069290705,0.00001249785,0.8963562,0.0062720836,0.00006161806,0.00018336668,2.0270383e-7,0.00035515276,0.027468156],"genre_scores_gemma":[0.90363544,0.0000015110086,0.09487093,0.00026171235,0.000011153915,0.000036511337,0.000007607279,0.0000035581068,0.001171554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99922335,0.00006301076,0.00013164929,0.00030878565,0.00015419791,0.00011898794],"domain_scores_gemma":[0.99926823,0.000089646004,0.000056272875,0.00050547376,0.000047519952,0.000032859156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011267554,0.00007541875,0.00007887892,0.00012247184,0.00017953488,0.00013986252,0.00041223882,0.00003005315,0.000022259434],"category_scores_gemma":[0.000018739154,0.00005939434,0.000023469813,0.0006546723,0.000019193905,0.00034309085,0.00017018261,0.00011304364,0.00005915344],"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":[0.000018226214,0.00012358159,0.122613646,0.00003532205,0.00003458661,0.0000031297584,0.00051804085,0.012624248,0.005501462,0.7176453,0.0015006488,0.13938184],"study_design_scores_gemma":[0.00039023135,0.000020768312,0.5815554,0.000055625438,0.0000069756957,0.0000019397162,0.000024127487,0.40711117,0.0027206352,0.006737133,0.0012659213,0.00011007706],"about_ca_topic_score_codex":0.00049645314,"about_ca_topic_score_gemma":0.000029381257,"teacher_disagreement_score":0.83434474,"about_ca_system_score_codex":0.00002754922,"about_ca_system_score_gemma":0.000028082886,"threshold_uncertainty_score":0.24220309},"labels":[],"label_agreement":null},{"id":"W4416551090","doi":"10.48550/arxiv.2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Mitacs","keywords":"Spurious relationship; Regularization (linguistics); Preference; Set (abstract data type); Simple (philosophy); Optimization problem","score_opus":0.026327536959017347,"score_gpt":0.2761713555977348,"score_spread":0.24984381863871746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416551090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14117321,0.000098688106,0.8541145,0.0009730953,0.00009451741,0.0007549766,0.000039364888,0.00051460374,0.0022370908],"genre_scores_gemma":[0.6019744,0.000029870627,0.3971023,0.00012646429,0.000022500566,0.00021440489,0.00008421659,0.000015193876,0.00043064717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763596,0.00019686719,0.00048007714,0.0009465506,0.00042536884,0.00031516614],"domain_scores_gemma":[0.99686456,0.00011408077,0.00051547156,0.0021622425,0.000253165,0.000090490525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040724207,0.00033392405,0.00044978768,0.0001958209,0.00012450662,0.000072838426,0.0016299187,0.0002416326,0.000017844344],"category_scores_gemma":[0.0000610915,0.0003015032,0.00009665088,0.00045205874,0.0000339125,0.00020449857,0.0017148422,0.00055802445,0.000013082546],"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":[0.000039508166,0.00043628862,0.013946615,0.00049703126,0.0001985242,0.000005407869,0.0034012005,0.94439673,0.00058736186,0.03562594,0.00008454901,0.0007808273],"study_design_scores_gemma":[0.0007200027,0.000047904236,0.010593245,0.0002718149,0.00006338276,0.0000015291196,0.0000231412,0.98550355,0.0014616074,0.0008843021,0.00011185199,0.00031767657],"about_ca_topic_score_codex":0.0004662362,"about_ca_topic_score_gemma":0.000023241544,"teacher_disagreement_score":0.46080118,"about_ca_system_score_codex":0.00013022895,"about_ca_system_score_gemma":0.0003332731,"threshold_uncertainty_score":0.99994373},"labels":[],"label_agreement":null},{"id":"W4416726017","doi":"10.1109/igarss55030.2025.11243055","title":"CSA Mamba: A Channel-Spatial Attention Mamba Network for Image Captioning","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Innovation Fund; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China; State Key Laboratory of Integrated Services Networks; Natural Science Foundation of Jiangsu Province; Ministry of Natural Resources","keywords":"Closed captioning; Feature (linguistics); Image (mathematics); Task (project management); Natural language; Natural (archaeology); Perception","score_opus":0.011025088727546225,"score_gpt":0.2918848238776111,"score_spread":0.2808597351500649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416726017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006118631,0.0002442403,0.9696696,0.013984416,0.0019818556,0.001988115,0.00003119407,0.00045113222,0.005530826],"genre_scores_gemma":[0.78632647,0.000022941378,0.20289917,0.0010526964,0.0008897134,0.00076878443,0.00009396838,0.000034628134,0.007911607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615854,0.00023643742,0.0008542541,0.0013772107,0.00035678147,0.001016754],"domain_scores_gemma":[0.9972701,0.00044846183,0.00037399176,0.0012216526,0.00048125483,0.00020451813],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010589333,0.0004653209,0.00045423937,0.0002823215,0.0015255355,0.00089399266,0.0011866158,0.00025192308,0.00018927047],"category_scores_gemma":[0.00022355794,0.0005149846,0.00036947144,0.0013348967,0.00014682897,0.000539237,0.000703957,0.00052150176,0.0003256998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019570097,0.00092156796,0.00624662,0.00069533015,0.00045767034,0.000014912066,0.0008908653,0.100210205,0.004122337,0.42687097,0.047026142,0.41234767],"study_design_scores_gemma":[0.0011856601,0.00012697825,0.041412618,0.00022257889,0.00010364858,0.000007486791,0.00003576917,0.9422381,0.00013899739,0.009855395,0.0042224154,0.00045037267],"about_ca_topic_score_codex":0.004296084,"about_ca_topic_score_gemma":0.00038377952,"teacher_disagreement_score":0.84202784,"about_ca_system_score_codex":0.00021255517,"about_ca_system_score_gemma":0.00028649476,"threshold_uncertainty_score":0.99977434},"labels":[],"label_agreement":null},{"id":"W4416748856","doi":"10.1109/iros60139.2025.11246761","title":"Refined Policy Distillation: From VLA Generalists to RL Experts","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Ministry of Education","keywords":"Reinforcement learning; Complement (music); Policy learning; Generalization; Perspective (graphical); Key (lock); Task (project management)","score_opus":0.012370089613082181,"score_gpt":0.33520705237334264,"score_spread":0.32283696276026047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416748856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05754455,0.00020941962,0.73985195,0.15027757,0.0007767258,0.000589313,0.00003497936,0.00042258902,0.05029292],"genre_scores_gemma":[0.8391844,0.000013608855,0.12812151,0.012207902,0.0008336607,0.0001335004,0.00003451519,0.000022156484,0.019448753],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653417,0.0002275068,0.0007360344,0.0014471414,0.00044916803,0.0006059797],"domain_scores_gemma":[0.9964463,0.00033673045,0.00015870211,0.0023749655,0.00026431712,0.00041896233],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021398129,0.00043352178,0.00041203026,0.0005202834,0.00056780985,0.00073026837,0.0018354254,0.00019599198,0.0005976524],"category_scores_gemma":[0.0005326049,0.0004382784,0.00015567528,0.0027978637,0.00008357569,0.00027545588,0.0013413292,0.00025335,0.0009059611],"study_design_candidate":"theoretical_or_conceptual","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":[0.000030591505,0.00022803675,0.011805017,0.000021789167,0.00009194661,0.0000058420806,0.002630864,0.0121231545,0.004768512,0.59597397,0.032990765,0.3393295],"study_design_scores_gemma":[0.00054211856,0.00004814442,0.308431,0.000087465785,0.000020995776,0.0000018094682,0.000022935605,0.5453138,0.000845143,0.006003175,0.1381327,0.0005507245],"about_ca_topic_score_codex":0.04120293,"about_ca_topic_score_gemma":0.00065233407,"teacher_disagreement_score":0.7816398,"about_ca_system_score_codex":0.00036308565,"about_ca_system_score_gemma":0.000575573,"threshold_uncertainty_score":0.99987197},"labels":[],"label_agreement":null},{"id":"W4416749111","doi":"10.1109/iros60139.2025.11247593","title":"OpenNav: Open-World Navigation with Multimodal Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Rehabilitation Institute; University of Toronto","funders":"","keywords":"Robustness (evolution); Leverage (statistics); Robot; Natural language; Semantic mapping; Mobile robot navigation; Bridging (networking); Perception","score_opus":0.014743656412547906,"score_gpt":0.3263966893968688,"score_spread":0.3116530329843209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416749111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017577715,0.00015106803,0.8081486,0.0099925315,0.00024224786,0.002091476,0.000043558986,0.00032450128,0.1614283],"genre_scores_gemma":[0.79939896,0.000005972126,0.1604035,0.0029631632,0.000054351334,0.00029561247,0.000076167475,0.00003424585,0.03676805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960127,0.00032289722,0.00068246084,0.0015926501,0.0005323736,0.0008569431],"domain_scores_gemma":[0.99645436,0.00022499477,0.00029493085,0.0023476474,0.00033589674,0.0003421729],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009848876,0.00052851887,0.00053162413,0.0004046794,0.00092603953,0.0021206264,0.004669073,0.00015411065,0.00052331865],"category_scores_gemma":[0.000061013685,0.0004662905,0.0001029859,0.0030612245,0.00013081635,0.0022871685,0.0033616072,0.0008724482,0.00043199467],"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":[0.00008713316,0.0009513498,0.0036557182,0.00012235656,0.00014120096,0.000025693791,0.0031638148,0.033512395,0.0006735159,0.89455736,0.0024830117,0.060626466],"study_design_scores_gemma":[0.002711821,0.00008362014,0.0063429647,0.00045220822,0.000054308766,0.000007732105,0.0001921938,0.97930765,0.0010327033,0.0042002145,0.005051686,0.0005629135],"about_ca_topic_score_codex":0.012855718,"about_ca_topic_score_gemma":0.0012850261,"teacher_disagreement_score":0.94579524,"about_ca_system_score_codex":0.00019835113,"about_ca_system_score_gemma":0.00078384666,"threshold_uncertainty_score":0.99977887},"labels":[],"label_agreement":null},{"id":"W4416749249","doi":"10.1109/iros60139.2025.11247596","title":"MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"Toyota Motor Europe","keywords":"Object (grammar); Scheme (mathematics); Code (set theory); Set (abstract data type); Mobile device; Mobile robot; Foundation (evidence)","score_opus":0.01470210709137515,"score_gpt":0.334111618908203,"score_spread":0.31940951181682786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416749249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064844325,0.00081983244,0.83771366,0.0041664536,0.00051638094,0.0011575627,0.0000029413966,0.0004909186,0.09028794],"genre_scores_gemma":[0.83381516,0.00005246634,0.15514168,0.001190028,0.00010663799,0.00030617006,0.000025756086,0.000020768719,0.009341325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971517,0.00019953246,0.00059562305,0.0010489516,0.00047391953,0.0005303214],"domain_scores_gemma":[0.9977126,0.00017051495,0.00022306209,0.0016533964,0.00014945379,0.00009097081],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050061056,0.00034785032,0.00031059238,0.00018187992,0.0005870818,0.0005603258,0.0011319567,0.00016569976,0.0004978266],"category_scores_gemma":[0.000104145234,0.0003599969,0.00014379644,0.001465917,0.000100096026,0.0006564247,0.0007280621,0.00045595874,0.00039237403],"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":[0.000021147478,0.00037772759,0.0035958677,0.00013608823,0.00016668919,0.0000108153845,0.014796565,0.014709259,0.003003178,0.6653559,0.0020491034,0.29577765],"study_design_scores_gemma":[0.0008677081,0.00008938491,0.05794964,0.00021071867,0.00008761091,0.0000062922554,0.0014865439,0.92054373,0.0011940824,0.0031673226,0.013910237,0.00048673313],"about_ca_topic_score_codex":0.010450199,"about_ca_topic_score_gemma":0.00010204733,"teacher_disagreement_score":0.90583444,"about_ca_system_score_codex":0.00029151872,"about_ca_system_score_gemma":0.0001383456,"threshold_uncertainty_score":0.9998852},"labels":[],"label_agreement":null},{"id":"W4416749785","doi":"10.1109/iros60139.2025.11246581","title":"TagGuideBot: Enhancing Robot Intelligence with Object Tags and VLMs","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Robot; Object (grammar); Naturalness; Point (geometry); Motion (physics); Semantics (computer science); Semantic mapping; Visualization; SMT placement equipment","score_opus":0.009074963396594306,"score_gpt":0.2836824222708823,"score_spread":0.274607458874288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416749785","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015195597,0.0007053369,0.9486501,0.006196456,0.00024891406,0.0006401731,0.0000011286224,0.00028571684,0.028076567],"genre_scores_gemma":[0.80406696,0.00009690015,0.18848349,0.001095199,0.00004322894,0.00006829428,0.0000012169917,0.00001747204,0.0061272597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968212,0.00015671234,0.00065827044,0.0013626477,0.00036892126,0.00063222094],"domain_scores_gemma":[0.99742365,0.0005839664,0.00020751341,0.0013345593,0.0002244894,0.00022584558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006659425,0.00044229513,0.0004208629,0.00032025267,0.00066129444,0.00075940235,0.0012530846,0.00014681704,0.00017446408],"category_scores_gemma":[0.00022258033,0.00037728212,0.000067557914,0.0017580953,0.00031188942,0.0004471174,0.0009719709,0.00064618496,0.00016577812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033151184,0.00019561633,0.0121911215,0.00020061954,0.00013258168,0.000014084007,0.0025375832,0.01597306,0.005314452,0.26924703,0.00023822763,0.69392246],"study_design_scores_gemma":[0.00030958484,0.0002608637,0.027619028,0.00048389082,0.00006372821,0.000036517104,0.0002545656,0.94279474,0.022052867,0.0036812378,0.0018053134,0.00063769025],"about_ca_topic_score_codex":0.0036773442,"about_ca_topic_score_gemma":0.0005952177,"teacher_disagreement_score":0.92682165,"about_ca_system_score_codex":0.000100196805,"about_ca_system_score_gemma":0.00045640048,"threshold_uncertainty_score":0.9998679},"labels":[],"label_agreement":null},{"id":"W4416750376","doi":"10.1109/iros60139.2025.11247280","title":"Interpreting Behaviors and Geometric Constraints as Knowledge Graphs for Robot Manipulation Control","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Robot; Visual servoing; Scripting language; Flexibility (engineering); Control (management); Robot control; Semantics (computer science); Personal robot","score_opus":0.014274494479371737,"score_gpt":0.32774743408913143,"score_spread":0.3134729396097597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416750376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06474545,0.00075860246,0.9222321,0.0019690436,0.0005730039,0.0018860004,0.000012338542,0.00020225806,0.007621199],"genre_scores_gemma":[0.96474415,0.000023509418,0.033477765,0.00041820857,0.00002962777,0.00028966006,0.00000900467,0.000019436402,0.0009886617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734956,0.00018951704,0.00073633326,0.0010247447,0.0001803399,0.0005195346],"domain_scores_gemma":[0.99696857,0.0015629543,0.0002710122,0.0006186798,0.0003923439,0.00018643022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093463884,0.0003572071,0.00042125885,0.0012154566,0.0006209407,0.00053889514,0.0007154443,0.00021539722,0.000116596086],"category_scores_gemma":[0.00082138355,0.0003820726,0.00017429801,0.0020654246,0.00031983873,0.00031643323,0.00035713846,0.00038009143,0.000058107773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025215511,0.00022465098,0.03982314,0.00010876995,0.00007590119,7.7751844e-7,0.0005153398,0.0009733621,0.0007863825,0.38053852,0.00012393795,0.576804],"study_design_scores_gemma":[0.0017879053,0.00017247461,0.15936711,0.00016262452,0.00014621957,0.000011058617,0.000079250625,0.8300532,0.0002599382,0.007321864,0.00029755762,0.00034079808],"about_ca_topic_score_codex":0.0004946734,"about_ca_topic_score_gemma":0.000033439625,"teacher_disagreement_score":0.89999866,"about_ca_system_score_codex":0.00010857324,"about_ca_system_score_gemma":0.00020975016,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W4416817077","doi":"10.1016/j.compbiomed.2025.111347","title":"Med-VCD: Mitigating hallucination for medical large vision language models through visual contrastive decoding","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Multimodal Machine Learning Applications","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":"Decoding methods; Context (archaeology); Redundancy (engineering); Hallucinating; Modalities; Language model","score_opus":0.011914720684248828,"score_gpt":0.40482713905938916,"score_spread":0.39291241837514035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416817077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044822395,0.0007007646,0.9416897,0.011371174,0.0003731504,0.0002982604,0.0000019416448,0.00008530341,0.00065729546],"genre_scores_gemma":[0.892086,0.00005153714,0.105074644,0.0025945592,0.00009692553,0.000046587902,0.00003332476,0.000004057294,0.000012324725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998832,0.00012693241,0.00029408204,0.0004073479,0.00009702837,0.00024265164],"domain_scores_gemma":[0.99831045,0.0013369233,0.00008073413,0.00015486704,0.000056500183,0.000060534243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008740314,0.000121026824,0.00025851952,0.00014864044,0.00016839216,0.000012480244,0.00032737665,0.00015021092,0.000004578971],"category_scores_gemma":[0.0005045275,0.0000984892,0.000021279426,0.0002452959,0.00016959179,0.00013722779,0.00021455667,0.00023252863,7.803382e-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":[0.000019517836,0.000080183054,0.0031075508,0.000050767132,0.000026360976,0.000005257469,0.003796558,0.00020303656,0.000954794,0.6961957,0.0003307452,0.2952295],"study_design_scores_gemma":[0.0019400626,0.00015164426,0.0050298017,0.00029767802,0.000006886228,0.0000060711845,0.00012107768,0.9528896,0.00007391527,0.039008953,0.00038727332,0.00008700273],"about_ca_topic_score_codex":0.00012905386,"about_ca_topic_score_gemma":0.000040597195,"teacher_disagreement_score":0.9526866,"about_ca_system_score_codex":0.000038284106,"about_ca_system_score_gemma":0.000047800564,"threshold_uncertainty_score":0.4016273},"labels":[],"label_agreement":null},{"id":"W4417002434","doi":"10.1109/tits.2025.3635279","title":"Peer Learning Approach to Unbiased Scene Graph Generation for Traffic Scene Understanding","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Multimodal Machine Learning Applications","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":"Shenzhen Research Foundation; Chuzhou Science and Technology Program","keywords":"Graph; Boosting (machine learning); Scene graph; Peer-to-peer; Voting; Graph theory","score_opus":0.08458328145002182,"score_gpt":0.31384607157836014,"score_spread":0.22926279012833833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417002434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014560984,0.00020744177,0.9717531,0.001706169,0.0049025794,0.005468862,0.00024310539,0.0006415607,0.0005162007],"genre_scores_gemma":[0.9738775,0.00009224263,0.018486265,0.00024887707,0.00021647087,0.0025367697,0.0002885673,0.00011007975,0.0041432157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930121,0.00050079724,0.002103203,0.0020885684,0.0013464749,0.00094888],"domain_scores_gemma":[0.99620485,0.0005302421,0.00050745916,0.0010723752,0.0012165342,0.0004685227],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0017684489,0.00087219727,0.00087460625,0.0019789839,0.0020905326,0.000980616,0.0010098864,0.0005114448,0.000032991487],"category_scores_gemma":[0.00004464968,0.0010111725,0.00067852344,0.003585709,0.00013317044,0.00052943826,0.0000017144104,0.0010748772,0.0000978945],"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":[0.0002192304,0.00089760846,0.000042253978,0.00050707324,0.0003453073,0.0000012435017,0.0059721298,0.94765717,0.0023467976,0.015377049,0.0003861995,0.026247915],"study_design_scores_gemma":[0.0012417805,0.00041693676,0.00020111672,0.0005210838,0.0003702549,0.0000040163304,0.0021791246,0.9839167,0.0073750177,0.00009139631,0.002818867,0.0008637124],"about_ca_topic_score_codex":0.00086160126,"about_ca_topic_score_gemma":0.00028315003,"teacher_disagreement_score":0.95931655,"about_ca_system_score_codex":0.0010509971,"about_ca_system_score_gemma":0.00042949608,"threshold_uncertainty_score":0.99923384},"labels":[],"label_agreement":null},{"id":"W4417036181","doi":"10.48550/arxiv.2512.04072","title":"SkillFactory: Self-Distillation For Learning Cognitive Behaviors","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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; Alfred P. Sloan Foundation; Institute for Information and Communications Technology Promotion; Open Philanthropy Project; National Science Foundation","keywords":"Leverage (statistics); Reinforcement learning; Cognition; Initialization; Task (project management); Cognitive model; Priming (agriculture)","score_opus":0.059094410595447955,"score_gpt":0.23556282801553996,"score_spread":0.176468417420092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417036181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30541748,0.000032153046,0.6884898,0.00012841354,0.0006058596,0.0018414641,0.00013193641,0.0007428567,0.0026100408],"genre_scores_gemma":[0.9855503,0.00013614046,0.007765801,0.00006786196,0.00014465892,0.00003177981,0.00025697183,0.000046836045,0.0059996787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948598,0.00058443623,0.00056642044,0.0029718678,0.0001949962,0.0008224534],"domain_scores_gemma":[0.99460906,0.0016047625,0.0010097353,0.0012782824,0.0011320638,0.00036609845],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006449759,0.00082260434,0.0007394335,0.00070786214,0.0014110871,0.00033099245,0.0020515453,0.0007394874,0.00009362825],"category_scores_gemma":[0.0004957231,0.0011250033,0.0006284846,0.001540513,0.000226693,0.00052905414,0.0020869297,0.0018982686,0.00019881202],"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":[0.0001480321,0.00064127176,0.10381602,0.00040101857,0.00046785592,0.000033343902,0.0028167942,0.7526694,0.000043165648,0.12619932,0.00006141563,0.012702364],"study_design_scores_gemma":[0.001432162,0.0001859334,0.052306645,0.00036554493,0.0007977815,0.0000026660116,0.00026171797,0.9366078,0.00006959313,0.004900114,0.002057186,0.0010128858],"about_ca_topic_score_codex":0.00090806297,"about_ca_topic_score_gemma":0.000050855015,"teacher_disagreement_score":0.68072397,"about_ca_system_score_codex":0.00076157995,"about_ca_system_score_gemma":0.00081941526,"threshold_uncertainty_score":0.99988896},"labels":[],"label_agreement":null},{"id":"W4417068938","doi":"10.1109/iccv51701.2025.02126","title":"Aurelia: Test-Time Reasoning Distillation in Audio-Visual LLMs","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology; University of Toronto","funders":"","keywords":"Benchmark (surveying); Process (computing); Case-based reasoning; Visual reasoning; Reasoning system; Deductive reasoning; Code (set theory)","score_opus":0.006768323365754613,"score_gpt":0.2952767481250392,"score_spread":0.28850842475928457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417068938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03629496,0.00010393942,0.9108362,0.0061440715,0.00041301546,0.0009472929,0.00002267518,0.001374865,0.043862935],"genre_scores_gemma":[0.8099886,0.000011918934,0.18451704,0.00023657165,0.000093881274,0.00016313027,0.00006278891,0.000014351873,0.004911697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977325,0.000120936034,0.00047418592,0.0010271997,0.00033105531,0.00031411566],"domain_scores_gemma":[0.997843,0.0006117555,0.00023107351,0.0011200183,0.00010964148,0.00008445778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050761795,0.0003005209,0.00035549412,0.00034973028,0.000113060654,0.00027168306,0.0013382924,0.0003103691,0.000056766097],"category_scores_gemma":[0.0008026726,0.0003066634,0.00010291041,0.0005980091,0.000032437012,0.00014069285,0.0023599854,0.0010286302,0.0002912509],"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":[0.000020428524,0.0008046276,0.22290508,0.00043595675,0.00010118932,0.000028768849,0.0021801388,0.3723829,0.0011263167,0.19445385,0.008385998,0.19717471],"study_design_scores_gemma":[0.00013503696,0.000013710598,0.1824304,0.00016181328,0.0000067314495,0.00000160168,0.0000023442979,0.81373036,0.000072457464,0.0026559234,0.00053286034,0.000256746],"about_ca_topic_score_codex":0.0026253965,"about_ca_topic_score_gemma":0.000053545173,"teacher_disagreement_score":0.7736937,"about_ca_system_score_codex":0.0002187003,"about_ca_system_score_gemma":0.00032476577,"threshold_uncertainty_score":0.99993855},"labels":[],"label_agreement":null},{"id":"W4417249200","doi":"10.1109/ivcnz67716.2025.11281867","title":"Visual Question Answering Using Multimodal Data Augmentation for Hausa","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 du Québec à Montréal","funders":"","keywords":"Hausa; Question answering; Multimodality; Baseline (sea); Multimodal therapy; Multimodal interaction","score_opus":0.06130410411759673,"score_gpt":0.44171603674840976,"score_spread":0.380411932630813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417249200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058394693,0.00012758333,0.9348113,0.0032609669,0.001111628,0.0015108212,0.000051240982,0.00029194402,0.00043984177],"genre_scores_gemma":[0.5951667,0.000008897376,0.4037439,0.00027013902,0.00013959227,0.000061224026,0.00016863378,0.000017301014,0.00042363346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996721,0.00019912627,0.0007310332,0.001492682,0.00032451286,0.00053164246],"domain_scores_gemma":[0.99709815,0.00043417572,0.0002839421,0.001767452,0.0002891756,0.00012713575],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001161906,0.00034771123,0.00030901434,0.0003601211,0.0008650378,0.00074010814,0.0019166952,0.00018129898,0.000041967203],"category_scores_gemma":[0.000408757,0.0003985777,0.000085667205,0.00094884343,0.00009534355,0.0015580239,0.0014896938,0.0003069424,0.000038310372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009798584,0.00065089564,0.010892197,0.00038540357,0.00018043218,0.0000015066082,0.0006729448,0.07928314,0.034474045,0.096711196,0.0005452215,0.77610505],"study_design_scores_gemma":[0.0011254296,0.000074087795,0.017759144,0.00017643621,0.00010355592,0.0000030830422,0.00006849961,0.97606826,0.0019025996,0.0009124369,0.0014543736,0.0003520877],"about_ca_topic_score_codex":0.0062683066,"about_ca_topic_score_gemma":0.00014977483,"teacher_disagreement_score":0.89678514,"about_ca_system_score_codex":0.000288093,"about_ca_system_score_gemma":0.00043560023,"threshold_uncertainty_score":0.99984664},"labels":[],"label_agreement":null},{"id":"W4417276938","doi":"10.48550/arxiv.2511.17366","title":"METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Bottleneck; Robustness (evolution); Teleoperation; Robot; Generalization; Robotics; Action (physics); Leverage (statistics)","score_opus":0.11413634178860264,"score_gpt":0.38653272736077604,"score_spread":0.2723963855721734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417276938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32107228,0.0005452062,0.67305934,0.0011311389,0.0010243908,0.0021834946,0.000108857,0.00073606893,0.00013917882],"genre_scores_gemma":[0.7229206,0.00013428906,0.27079254,0.0005547369,0.00022076623,0.0011229082,0.00022977109,0.00009424803,0.003930163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924574,0.0005610698,0.0016890708,0.0032902611,0.0006508704,0.0013513517],"domain_scores_gemma":[0.9934638,0.0010151254,0.0012616384,0.002960882,0.0008237512,0.00047478138],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013698771,0.0012594331,0.0012633258,0.00097389857,0.0012114191,0.0006485641,0.0035262334,0.0009418061,0.000063982836],"category_scores_gemma":[0.0014316705,0.0013491566,0.0007400846,0.001844027,0.00020501402,0.0005695876,0.0021787926,0.0027656353,0.00022402561],"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":[0.00009919639,0.0006303151,0.011127175,0.00040889013,0.00027395482,0.000006925087,0.01586725,0.49039805,0.0030098734,0.00038117214,0.00015116476,0.47764602],"study_design_scores_gemma":[0.0016352378,0.00012927185,0.032090895,0.00065005117,0.0002458392,0.000019023139,0.00078439486,0.9605453,0.0006921056,0.00022600837,0.0018962153,0.0010856626],"about_ca_topic_score_codex":0.0038061794,"about_ca_topic_score_gemma":0.00020270384,"teacher_disagreement_score":0.47656035,"about_ca_system_score_codex":0.00081886793,"about_ca_system_score_gemma":0.0011371025,"threshold_uncertainty_score":0.999535},"labels":[],"label_agreement":null},{"id":"W4417283646","doi":"10.1145/3748636.3762801","title":"VisLN: An Interactive Visualization System for Vision Language Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; University of Waterloo","funders":"","keywords":"Interpretability; Visualization; Debugging; Limiting; Field (mathematics); Interface (matter); User interface; Semantics (computer science)","score_opus":0.008161125548401855,"score_gpt":0.37837080423029906,"score_spread":0.3702096786818972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417283646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07506144,0.000070801514,0.91606766,0.00094087346,0.00089879567,0.0016289906,0.00001718416,0.0005963909,0.004717872],"genre_scores_gemma":[0.9654799,0.0000020539258,0.032047853,0.00024845803,0.00014163637,0.0002843012,0.00020972641,0.000024903287,0.001561151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746704,0.0003472508,0.0006112714,0.0009713797,0.0002720244,0.00033100514],"domain_scores_gemma":[0.9976631,0.00039454078,0.00033684517,0.00096760644,0.000516811,0.00012112123],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006745467,0.0002874536,0.0002882189,0.00033783342,0.0005695698,0.0007360711,0.00085065473,0.00018200756,0.000024198087],"category_scores_gemma":[0.00014192994,0.00029341292,0.00011971714,0.0011286747,0.000048665985,0.0012872595,0.00028022495,0.00022816045,0.00009730612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010142896,0.000517625,0.00045976375,0.00072098256,0.00007305108,0.000001866733,0.009439427,0.0047458536,0.018909695,0.6223549,0.00041441913,0.34226096],"study_design_scores_gemma":[0.00074677396,0.0002783111,0.0044205,0.0005835388,0.000047114005,0.000004205593,0.0014402618,0.980246,0.010656167,0.0004949244,0.0008171519,0.00026502294],"about_ca_topic_score_codex":0.0011231997,"about_ca_topic_score_gemma":0.000025021602,"teacher_disagreement_score":0.97550017,"about_ca_system_score_codex":0.00038550224,"about_ca_system_score_gemma":0.00019848227,"threshold_uncertainty_score":0.9999518},"labels":[],"label_agreement":null},{"id":"W4417283698","doi":"10.1145/3748636.3760462","title":"Cognitive Foundation Agents for Generalizable Vision-and-Language Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Embodied cognition; Task (project management); Cognition; Process (computing); Adaptation (eye); Asynchronous communication; Key (lock); Suite","score_opus":0.018163979812692393,"score_gpt":0.3740435197282998,"score_spread":0.3558795399156074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417283698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08960913,0.0002166528,0.8981264,0.0054597147,0.00042284717,0.001469442,0.000015568612,0.00014294288,0.0045372895],"genre_scores_gemma":[0.91163754,0.000036049514,0.07529927,0.0015201533,0.00008591867,0.0003374742,0.00019367076,0.000015654909,0.010874268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979366,0.00019079496,0.00044130898,0.00084171194,0.00025176533,0.00033779422],"domain_scores_gemma":[0.99803036,0.0008174891,0.0001936907,0.00043675702,0.00041659357,0.00010513017],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007068318,0.00025171236,0.00022902124,0.00020866179,0.0009078366,0.00066528254,0.00040969686,0.00015883309,0.00014913516],"category_scores_gemma":[0.00046048142,0.00025308545,0.00008990778,0.00070491235,0.000102105936,0.00057337433,0.0003452452,0.0002652188,0.00012694365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046819754,0.00028192598,0.0026896321,0.00031458144,0.00012504579,0.000001191314,0.005681695,0.0014856526,0.0021333732,0.27179778,0.0013104535,0.71413183],"study_design_scores_gemma":[0.0011956807,0.000110478126,0.019889046,0.0002883866,0.000079191785,0.0000023756045,0.00021473327,0.96748835,0.0014780302,0.0050348598,0.003967239,0.00025164895],"about_ca_topic_score_codex":0.0013664062,"about_ca_topic_score_gemma":0.000028295786,"teacher_disagreement_score":0.9660027,"about_ca_system_score_codex":0.00009149624,"about_ca_system_score_gemma":0.0002049918,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W4417283734","doi":"10.1145/3748636.3762753","title":"SpatialGPT: Zero-Shot Vision-and-Language Navigation via Spatial CoT over Structured Spatial Memory","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Leverage (statistics); Landmark; Spatial intelligence; Inference; Spatial contextual awareness; Task (project management); Generalization; Natural language; Context (archaeology)","score_opus":0.0059991082141304065,"score_gpt":0.2956740214560306,"score_spread":0.2896749132419002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417283734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24836534,0.00026947953,0.74173164,0.002645393,0.0017191903,0.0012733918,0.00003782588,0.00035561415,0.003602111],"genre_scores_gemma":[0.97564876,0.000020726211,0.020859923,0.0011901787,0.00044125612,0.00009037856,0.00013880774,0.000055267643,0.0015546783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99424624,0.0005603433,0.0012715174,0.0020123569,0.0010353494,0.00087419065],"domain_scores_gemma":[0.9960719,0.0005531373,0.0005756814,0.0020679056,0.00032069525,0.0004107287],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007112044,0.0008648592,0.00079534843,0.0005024767,0.0009900751,0.0009230011,0.0016021089,0.0005385775,0.0014644673],"category_scores_gemma":[0.00025752472,0.0008366862,0.00025878943,0.0011826174,0.00043407586,0.0006617192,0.0015725447,0.0012059531,0.00020374321],"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":[0.0001243559,0.00028120074,0.0050715883,0.00020541075,0.00016058444,0.000023889623,0.0039324053,0.0029157388,0.039755967,0.010539113,0.0006989448,0.9362908],"study_design_scores_gemma":[0.0017495627,0.00019495263,0.22491845,0.00017903805,0.00011294141,0.00001984019,0.000043525764,0.76071095,0.0072305356,0.0036804187,0.00047820888,0.00068156194],"about_ca_topic_score_codex":0.069349065,"about_ca_topic_score_gemma":0.002008047,"teacher_disagreement_score":0.9356092,"about_ca_system_score_codex":0.0002467901,"about_ca_system_score_gemma":0.00044642607,"threshold_uncertainty_score":0.99944836},"labels":[],"label_agreement":null},{"id":"W4417285899","doi":"10.1109/iccv51701.2025.01969","title":"VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 of Waterloo","funders":"","keywords":"ENCODE; Security token; Encoding (memory); Benchmark (surveying); Reduction (mathematics); Quadratic equation; Video tracking; Minification","score_opus":0.013961524523885186,"score_gpt":0.25840242052327045,"score_spread":0.24444089599938526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417285899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013610094,0.0000173067,0.9165506,0.0071152225,0.00006857628,0.00024417572,0.0000010735248,0.00045979675,0.061933156],"genre_scores_gemma":[0.95284307,0.0000034485308,0.045027167,0.0007737202,0.0000129343325,0.000036849062,0.0000028949037,0.000008993245,0.0012909493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890816,0.000034218123,0.00016212261,0.00040360255,0.0002059342,0.00028596108],"domain_scores_gemma":[0.99925596,0.00013835885,0.00004141686,0.00044650506,0.000036681613,0.00008110475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017556406,0.00014314563,0.00013090164,0.00018139547,0.00026817713,0.00018081554,0.00057726185,0.00002833322,0.000038824055],"category_scores_gemma":[0.000015323249,0.00011536715,0.000045407083,0.0006284519,0.000055279586,0.00031033924,0.00009207311,0.0002067891,0.000051850893],"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":[0.000018027791,0.00009572883,0.03010815,0.000053673026,0.00009992698,0.000024537247,0.00028694206,0.002661584,0.00051656994,0.91916496,0.0022703225,0.044699583],"study_design_scores_gemma":[0.0029676491,0.00027971188,0.12952057,0.00027976418,0.00009106703,0.00010405568,0.0004823112,0.804541,0.010025051,0.04233921,0.008107667,0.0012619793],"about_ca_topic_score_codex":0.00043159188,"about_ca_topic_score_gemma":0.000101662525,"teacher_disagreement_score":0.93923295,"about_ca_system_score_codex":0.00015720216,"about_ca_system_score_gemma":0.000108835666,"threshold_uncertainty_score":0.4704536},"labels":[],"label_agreement":null},{"id":"W4417298816","doi":"10.48550/arxiv.2505.14685","title":"Language Models use Lookbacks to Track Beliefs","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Council for Higher Education; Azrieli Foundation; European Commission; Open Philanthropy Project; National Science Foundation","keywords":"Character (mathematics); Construct (python library); Visibility; Recall; Encoding (memory); State (computer science); Language model; Resolution (logic); Relation (database)","score_opus":0.050421206238252234,"score_gpt":0.32180394722060623,"score_spread":0.271382740982354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417298816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58150584,0.00011303865,0.40972394,0.0035116784,0.00037366306,0.00064007915,0.0000474634,0.0007311745,0.0033531429],"genre_scores_gemma":[0.9064794,0.000017229608,0.08496651,0.0020955421,0.00017272908,0.00028271438,0.000047456204,0.000028845034,0.0059095584],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745286,0.00012283014,0.00041182135,0.0012560663,0.0003222578,0.00043418666],"domain_scores_gemma":[0.99638647,0.00023100371,0.00016823917,0.0028362959,0.00015056442,0.00022742196],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002693281,0.0003820706,0.00038457412,0.0002642628,0.00015581037,0.00030112008,0.0027291146,0.0002902803,0.000026875598],"category_scores_gemma":[0.00018011278,0.00040149828,0.00017878,0.0004668436,0.00003473428,0.0003066711,0.0033807196,0.0011228311,0.00079525757],"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":[0.000021814716,0.0006789401,0.20321414,0.0004349882,0.00028112918,0.00008339909,0.023935873,0.65883464,0.002083914,0.031656615,0.013578214,0.06519635],"study_design_scores_gemma":[0.0004403033,0.000053609027,0.4829059,0.00041380245,0.00005295794,0.0000067135447,0.000041429026,0.50189143,0.001217904,0.0030282629,0.008710929,0.0012367672],"about_ca_topic_score_codex":0.0034186502,"about_ca_topic_score_gemma":0.000101370344,"teacher_disagreement_score":0.3249736,"about_ca_system_score_codex":0.00012056871,"about_ca_system_score_gemma":0.00021481255,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W4417322872","doi":"10.48550/arxiv.2510.21059","title":"Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Scalability; Task (project management); Software; Labrador Retriever; Source code; Collaborative editing","score_opus":0.026394916922155075,"score_gpt":0.33343174393782127,"score_spread":0.3070368270156662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417322872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06442338,0.00045327787,0.9196916,0.007781101,0.0021525184,0.002735679,0.00007106497,0.0003170456,0.0023743045],"genre_scores_gemma":[0.91416645,0.000125476,0.07997604,0.0005356649,0.0008507497,0.0009839794,0.00019632187,0.000073004965,0.0030922887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940984,0.00039247624,0.0015893223,0.0024710193,0.0003466942,0.0011020531],"domain_scores_gemma":[0.9944015,0.0011104788,0.0010171182,0.002345692,0.00086461345,0.00026058557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012881057,0.00085601246,0.00093796634,0.0012596451,0.0007181323,0.00032182757,0.0030293982,0.00084316387,0.0000685301],"category_scores_gemma":[0.0022108417,0.0010449117,0.00043221918,0.0027380576,0.00018555572,0.0006481676,0.0031068565,0.0019446989,0.00021704774],"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":[0.000058138252,0.0006365799,0.11499,0.00093886803,0.00014785699,0.0000036855113,0.006151462,0.70003146,0.00024933525,0.009340867,0.00015753698,0.16729423],"study_design_scores_gemma":[0.0010386768,0.000062315165,0.09670562,0.0006490991,0.000050468367,0.000004189449,0.000057568606,0.896889,0.000114693925,0.0012368405,0.0024873442,0.00070421264],"about_ca_topic_score_codex":0.0028225745,"about_ca_topic_score_gemma":0.0004929106,"teacher_disagreement_score":0.84974307,"about_ca_system_score_codex":0.0013494397,"about_ca_system_score_gemma":0.0016761918,"threshold_uncertainty_score":0.9992001},"labels":[],"label_agreement":null},{"id":"W4417423761","doi":"10.1109/iccv51701.2025.00061","title":"NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Simon Fraser University","funders":"","keywords":"Subcategory; Set (abstract data type); Lexicon; Matching (statistics); Face (sociological concept); Word (group theory); Noun; Function (biology)","score_opus":0.02047313720632901,"score_gpt":0.3049961903917769,"score_spread":0.2845230531854479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417423761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024071317,0.000017331411,0.9286385,0.0043376666,0.0001693516,0.000111889116,8.5044394e-7,0.0006905659,0.041962486],"genre_scores_gemma":[0.8326239,5.8461524e-7,0.16450185,0.0012284601,0.000015842532,0.0000747942,0.0000020808352,0.00000670118,0.0015457835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888116,0.00008646631,0.00020673497,0.0004436917,0.00015882049,0.00022315305],"domain_scores_gemma":[0.9987665,0.00034387363,0.00007843674,0.00064187293,0.00011149191,0.00005785973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021734349,0.00013785715,0.00012912368,0.00020176548,0.0002721917,0.0001381456,0.00061627076,0.00006923442,0.000026920907],"category_scores_gemma":[0.00023643259,0.00012807219,0.00004387052,0.0010806913,0.00003525233,0.00018213212,0.00016305625,0.00026982767,0.00015212905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002403714,0.00024413031,0.0057879505,0.00004170215,0.000051037743,0.000003229717,0.00031253594,0.008365888,0.041276887,0.30756733,0.0009501929,0.6353751],"study_design_scores_gemma":[0.00090217346,0.000082451385,0.03650285,0.00003911751,0.00001102221,0.0000016825261,0.000010770415,0.91301644,0.03857751,0.0060126744,0.004607942,0.00023539663],"about_ca_topic_score_codex":0.0009536653,"about_ca_topic_score_gemma":0.00012343987,"teacher_disagreement_score":0.9046505,"about_ca_system_score_codex":0.00007553449,"about_ca_system_score_gemma":0.00010566819,"threshold_uncertainty_score":0.5222632},"labels":[],"label_agreement":null},{"id":"W4417455182","doi":"10.1038/s41597-025-06365-y","title":"An Egocentric Life-Saving Interventional Procedure Dataset of Actions, Medical Questions, Maneuvers and Tools","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Multimodal Machine Learning Applications","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":"U.S. Army Research Institute of Environmental Medicine; U.S. Army Medical Research and Development Command; Purdue University; School of Medicine, Indiana University; U.S. Department of Defense; National Science Foundation","keywords":"CLIPS; Action (physics); Resource (disambiguation); Object (grammar); Field (mathematics); Metadata","score_opus":0.04955760178494154,"score_gpt":0.3772135807482431,"score_spread":0.32765597896330156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417455182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16725059,0.0011322503,0.7900633,0.015672147,0.0026330273,0.0010359032,0.021144012,0.0005258997,0.0005428425],"genre_scores_gemma":[0.94452786,0.000015574997,0.038796443,0.0002059468,0.00003591373,0.000023548217,0.016180307,0.0000057114503,0.00020871096],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803823,0.00011717976,0.00034923502,0.0008361574,0.0004830352,0.00017614014],"domain_scores_gemma":[0.99708706,0.00015574136,0.00013036416,0.0023576315,0.00009306795,0.00017612113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016230427,0.00009611359,0.00011993031,0.00030261747,0.00038005816,0.0006456452,0.0032262176,0.00005754856,0.000097942764],"category_scores_gemma":[0.0016420743,0.00009315918,0.000019630796,0.0009911532,0.00024239747,0.0017359395,0.0017181517,0.00021349791,0.000027127673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014913522,0.0013280631,0.029798426,0.00041113357,0.00009710309,0.000008707041,0.0002557801,0.00019914517,0.0014064136,0.17437224,0.45244867,0.3396594],"study_design_scores_gemma":[0.00054308015,0.000040498944,0.21843494,0.00028990392,0.000042110376,0.00003129369,0.00014289319,0.65146565,0.00011878681,0.0026996823,0.12592047,0.00027068824],"about_ca_topic_score_codex":0.00019234988,"about_ca_topic_score_gemma":0.00011543911,"teacher_disagreement_score":0.77727723,"about_ca_system_score_codex":0.000026781125,"about_ca_system_score_gemma":0.00045784176,"threshold_uncertainty_score":0.62259716},"labels":[],"label_agreement":null},{"id":"W4417515405","doi":"10.1109/tvt.2025.3608811","title":"DriveSOTIF: Advancing SOTIF Through Multimodal Large Language Models","year":2025,"lang":"en","type":"preprint","venue":"IEEE Transactions on Vehicular Technology","topic":"Multimodal Machine Learning Applications","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":"University of New Brunswick; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmarking; Inference; Baseline (sea); Domain (mathematical analysis); Work (physics); Language model; Task analysis; Language understanding","score_opus":0.009577541560101646,"score_gpt":0.28380894074969765,"score_spread":0.274231399189596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417515405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01904006,0.00036566769,0.9686222,0.005414793,0.0009953381,0.0010573397,0.00018228505,0.0035278695,0.00079445983],"genre_scores_gemma":[0.75254214,0.00009581728,0.24573897,0.00039045853,0.000035525878,0.000732801,0.00002208498,0.000043616106,0.00039857888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960835,0.0001779414,0.00063343847,0.0017808093,0.00044231137,0.00088198954],"domain_scores_gemma":[0.9958099,0.00017627155,0.0002940322,0.0034006203,0.0002076303,0.00011154766],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00029719094,0.00067479076,0.00072019285,0.001102444,0.00056147156,0.00013367343,0.0030132758,0.0013803098,0.000032346],"category_scores_gemma":[0.000030076062,0.0007382352,0.00041813578,0.0012508327,0.00016734423,0.00033432126,0.00016539528,0.003796613,0.00015071647],"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":[0.000008117629,0.00056330394,0.000024690522,0.00012552497,0.00019270579,0.000046018627,0.0011571535,0.9175804,0.0016977228,0.035260417,0.000064040396,0.04327989],"study_design_scores_gemma":[0.0006662267,0.000063217136,0.00003683597,0.00024125264,0.00008311522,0.000025328178,0.00013354434,0.9512185,0.019640971,0.026243312,0.000994044,0.0006536516],"about_ca_topic_score_codex":0.00061024574,"about_ca_topic_score_gemma":0.0001720347,"teacher_disagreement_score":0.7335021,"about_ca_system_score_codex":0.00032678893,"about_ca_system_score_gemma":0.00032044286,"threshold_uncertainty_score":0.99991614},"labels":[],"label_agreement":null},{"id":"W4417517804","doi":"10.48550/arxiv.2505.08455","title":"VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Mitacs","keywords":"Causal reasoning; Causal model; Visual reasoning; Key (lock); Benchmark (surveying); Language model; Simple (philosophy); Modular design; Model-based reasoning","score_opus":0.05864879819581904,"score_gpt":0.3154730716831285,"score_spread":0.25682427348730946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417517804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7564404,0.00041287974,0.23851964,0.00039057372,0.00042667156,0.0003836098,0.000053680207,0.00042745317,0.0029451111],"genre_scores_gemma":[0.9755223,0.00005955135,0.022995466,0.00010605417,0.00014754124,0.0004384382,0.000052765678,0.000028698745,0.0006492149],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723905,0.00014243147,0.0006328069,0.0010202393,0.00042414543,0.0005413136],"domain_scores_gemma":[0.99662155,0.00034347622,0.0003850564,0.0023109636,0.00021103036,0.00012790506],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067000027,0.00040337787,0.00055805576,0.00030014114,0.00019818674,0.00010242439,0.0020374213,0.00024008524,0.00003206776],"category_scores_gemma":[0.0003304857,0.000423647,0.0002247838,0.00040382944,0.0000827164,0.00052884663,0.003291407,0.0011199891,0.00003964398],"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":[0.00001808033,0.00040742493,0.6704209,0.0020539716,0.00029378137,0.000037842194,0.052054085,0.10919976,0.00062430784,0.15550001,0.00016619293,0.00922368],"study_design_scores_gemma":[0.00058380706,0.000057008783,0.34107298,0.0015471329,0.0000838606,0.000007760036,0.00090562046,0.640992,0.004796841,0.008686777,0.00023503367,0.0010311808],"about_ca_topic_score_codex":0.0053502535,"about_ca_topic_score_gemma":0.00025125005,"teacher_disagreement_score":0.5317922,"about_ca_system_score_codex":0.00017215408,"about_ca_system_score_gemma":0.00032335392,"threshold_uncertainty_score":0.99982154},"labels":[],"label_agreement":null},{"id":"W6888591465","doi":"10.2021/ju.v2i1.2493","title":"Songs of Prescience: Canadian Musical Activism in Climate Breakdown","year":2022,"lang":"en","type":"article","venue":"The Journal of Macrodynamic Analysis (Memorial University of Newfoundland)","topic":"Multimodal Machine Learning Applications","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":"Musical; Climate change; Agency (philosophy); Government (linguistics)","score_opus":0.00571727521634234,"score_gpt":0.2124514039836661,"score_spread":0.20673412876732378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888591465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9662637,0.000015136245,0.03099308,0.0018609061,0.00019156137,0.00009699776,0.00002250392,0.0000075206017,0.00054855715],"genre_scores_gemma":[0.9980812,0.000027349473,0.0017559339,0.00002335575,0.000042320644,1.2666571e-7,0.000003480936,0.0000038770945,0.000062327555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981544,0.0004493205,0.00035841126,0.00018076287,0.00059624005,0.00026086427],"domain_scores_gemma":[0.9982249,0.00027892087,0.00073618453,0.0004665904,0.00015945529,0.0001339443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018947483,0.000104105595,0.00040871708,0.00092288456,0.00039255212,0.000022160672,0.0022654047,0.00003750176,0.00013758769],"category_scores_gemma":[0.000053088665,0.000093204224,0.00025851175,0.0023186936,0.00017364572,0.00025646485,0.00045992754,0.00047346888,0.0000020926911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005827379,0.00043317777,0.10775418,0.000023092283,0.0009635919,0.00010778345,0.013801214,0.854409,0.004022317,0.008884966,0.00021221256,0.008805749],"study_design_scores_gemma":[0.0011900272,0.00019926042,0.41439548,0.00000988383,0.00052655075,0.000058776288,0.0014744789,0.5804214,0.000005269306,0.00077201705,0.0007913104,0.00015553462],"about_ca_topic_score_codex":0.30392286,"about_ca_topic_score_gemma":0.19850878,"teacher_disagreement_score":0.3066413,"about_ca_system_score_codex":0.00045078757,"about_ca_system_score_gemma":0.0004825359,"threshold_uncertainty_score":0.81611633},"labels":[],"label_agreement":null},{"id":"W6889145698","doi":"10.25384/sage.22097725","title":"Supplemental Material - Sex-specific frailty and chronological age normative carotid artery intima-media thickness values using the Canadian longitudinal study of aging","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Multimodal Machine Learning Applications","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":"Dalhousie University","funders":"","keywords":"Normative; Longitudinal study; Carotid arteries; Ageing; Common carotid artery; Longitudinal data; Ultrasound; Vascular disease","score_opus":0.14693944079663723,"score_gpt":0.3703898591655418,"score_spread":0.22345041836890456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889145698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983009,0.00013114208,0.014038481,0.0011540637,0.00028887135,0.0004146811,0.00087567134,0.00006592932,0.000022172002],"genre_scores_gemma":[0.9933783,0.00008209497,0.0061271912,0.0000426424,0.00019850107,0.0000119093065,0.0001447965,0.000011048644,0.0000035327746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99798346,0.00038880587,0.00040897142,0.00044006805,0.0004090703,0.00036961262],"domain_scores_gemma":[0.99821746,0.00025028663,0.00021204585,0.0011180126,0.000052025258,0.00015013671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015434335,0.00016642685,0.0002437927,0.00022709412,0.0007862894,0.000597493,0.0019292462,0.000052046635,0.00025965078],"category_scores_gemma":[0.00007017522,0.0001224707,0.000024723076,0.0005157012,0.00015823812,0.0006666091,0.0017014509,0.00046140066,0.000013431552],"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":[0.000021592099,0.0005440604,0.7962956,0.00007368048,0.0005134728,0.0007009954,0.084199674,0.002838685,0.014681063,0.0003271207,0.0036021916,0.09620188],"study_design_scores_gemma":[0.00046236248,0.000060339404,0.9578785,0.00008904916,0.000023110275,0.00014527886,0.0030358532,0.037346408,0.00015270097,0.000466065,0.00015545255,0.00018488911],"about_ca_topic_score_codex":0.047494717,"about_ca_topic_score_gemma":0.037978083,"teacher_disagreement_score":0.1615829,"about_ca_system_score_codex":0.00009409969,"about_ca_system_score_gemma":0.000116271025,"threshold_uncertainty_score":0.9795763},"labels":[],"label_agreement":null},{"id":"W6892225984","doi":"10.5075/epfl-thesis-10642","title":"Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning","year":2024,"lang":"en","type":"dissertation","venue":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","topic":"Multimodal Machine Learning Applications","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; Institute for Catastrophic Loss Reduction","keywords":"Generalization; Artificial neural network; Prior probability; Representation (politics); Commonsense knowledge; Plan (archaeology); Knowledge representation and reasoning; Commonsense reasoning; Qualitative reasoning","score_opus":0.014842905866114312,"score_gpt":0.31280392241144955,"score_spread":0.29796101654533524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892225984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2972273,0.0013284656,0.68966264,0.000431478,0.0015173752,0.0037224728,0.000121600184,0.0017950503,0.0041936445],"genre_scores_gemma":[0.82490015,0.000019604504,0.17218776,0.00015440838,0.00014631983,0.0017297174,0.00018668026,0.000094705254,0.00058067235],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955003,0.00015831503,0.0009575995,0.0015262751,0.00062543596,0.0012320279],"domain_scores_gemma":[0.99708575,0.00046417044,0.0004805502,0.0012405933,0.00037427843,0.0003546745],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014810741,0.0006691858,0.0006627045,0.0014393992,0.00038764012,0.00078478275,0.002839173,0.00063215464,0.000007296222],"category_scores_gemma":[0.0008736572,0.0007313379,0.0002481901,0.0028075913,0.00012868352,0.00064205733,0.00043777027,0.0013291732,0.000019735762],"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":[0.00009588248,0.00039506474,0.0011897061,0.0011297908,0.00004179753,0.000034256234,0.0385625,0.44816154,0.0088319825,0.33137038,0.0010553509,0.16913176],"study_design_scores_gemma":[0.00025798174,0.00009502385,0.003733971,0.0006826918,0.000024033714,0.000021450423,0.00025461227,0.97508955,0.002127946,0.016236657,0.0007328313,0.0007432794],"about_ca_topic_score_codex":0.0021916544,"about_ca_topic_score_gemma":0.001330727,"teacher_disagreement_score":0.5276728,"about_ca_system_score_codex":0.0008115705,"about_ca_system_score_gemma":0.0016127464,"threshold_uncertainty_score":0.99951375},"labels":[],"label_agreement":null},{"id":"W6893799380","doi":"10.5281/zenodo.4804705","title":"[Download~^Mp3] Georgia Anne Muldrow - Overload Album Download","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Multimodal Machine Learning Applications","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; Information overload; Reading (process)","score_opus":0.02121420118311327,"score_gpt":0.25456332880264326,"score_spread":0.23334912761953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893799380","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":[0.00008822583,0.0010594438,0.038647417,0.0024763504,0.0003609591,0.0007017906,0.000871917,0.004674876,0.951119],"genre_scores_gemma":[0.022976082,0.0011702862,0.033986747,0.0023589344,0.0020340073,0.0000023310508,0.041675,0.021406073,0.87439054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961576,0.00060829805,0.00040635085,0.0013576683,0.00076050573,0.00070960587],"domain_scores_gemma":[0.9965762,0.00004997933,0.00036254726,0.0022130746,0.0004288787,0.00036931233],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005562177,0.00044155386,0.00040966301,0.0006119284,0.0015381563,0.0017568117,0.0041708583,0.0003016454,0.056564692],"category_scores_gemma":[0.0005533659,0.00049094454,0.0001529703,0.0012780894,0.00019329686,0.00021420808,0.0036571007,0.00090451527,0.040081803],"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":[0.000005879995,0.00016731126,0.0000026235277,0.000107808286,0.000085696716,0.000034738317,0.00037613045,0.000052077932,0.0013587296,0.0055837333,0.8990342,0.093191065],"study_design_scores_gemma":[0.00047305482,0.00009135951,0.00027009554,0.000118110256,0.000018426786,0.00013512302,0.000024128149,0.0016333618,0.00008933917,0.000075343574,0.99656385,0.0005078089],"about_ca_topic_score_codex":0.00044819133,"about_ca_topic_score_gemma":0.00000319289,"teacher_disagreement_score":0.09752964,"about_ca_system_score_codex":0.00025066073,"about_ca_system_score_gemma":0.000026503754,"threshold_uncertainty_score":0.9997617},"labels":[],"label_agreement":null},{"id":"W6901676980","doi":"10.60692/4sy44-gqy76","title":"Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Multimodal Machine Learning Applications","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":"Contextualization; Generalization; Set (abstract data type); Exploit; Parameterized complexity; Cube (algebra); Test set; Implementation","score_opus":0.0418449064862477,"score_gpt":0.2992807166771646,"score_spread":0.2574358101909169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901676980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44505847,0.0000069043044,0.5542569,0.000096156255,0.00009363217,0.00035045488,0.000008989508,0.00003137738,0.000097075244],"genre_scores_gemma":[0.99906915,8.578472e-8,0.00060255657,0.00006346209,0.00004431652,0.00017567826,0.00001895697,0.000006290299,0.000019502108],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872243,0.00018848867,0.0005599247,0.00014667613,0.00018042779,0.00020202943],"domain_scores_gemma":[0.99874437,0.00012000349,0.00037982163,0.00048647722,0.00023120658,0.000038094688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056111766,0.00012301165,0.00017008034,0.00010091622,0.00027306017,0.00026754662,0.00044121867,0.00006109095,0.0000035620164],"category_scores_gemma":[0.00009697802,0.00007066749,0.00010627313,0.00045116243,0.00002762117,0.0006677489,0.0001464397,0.00013729132,0.000009490381],"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":[0.000054904434,0.000015322288,0.2383931,0.00012699734,0.00007808561,0.0000011742083,0.17675897,0.5462621,0.0000630133,0.013351392,0.000077544435,0.024817403],"study_design_scores_gemma":[0.00041754244,0.00001882636,0.15444398,0.000075657066,0.0000046848563,0.000013557819,0.0045566536,0.8402656,0.00011100656,0.0000026859082,0.000021454238,0.000068399306],"about_ca_topic_score_codex":0.00012857567,"about_ca_topic_score_gemma":0.000003334948,"teacher_disagreement_score":0.5540107,"about_ca_system_score_codex":0.00010279617,"about_ca_system_score_gemma":0.000050829898,"threshold_uncertainty_score":0.28817368},"labels":[],"label_agreement":null},{"id":"W6902603111","doi":"10.6084/m9.figshare.c.7906156","title":"Health and social service provider perspectives on challenges, approaches, and recommendations for treating long COVID: a qualitative study of Canadian provider experiences","year":2025,"lang":"en","type":"other","venue":"Figshare","topic":"Multimodal Machine Learning Applications","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 Toronto; University Health Network; Centre for Addiction and Mental Health","funders":"","keywords":"Mental health; Thematic analysis; Psychosocial; Qualitative research; Service provider; Psychoeducation; Health care; Intervention (counseling)","score_opus":0.16322238570063383,"score_gpt":0.3940439448848523,"score_spread":0.23082155918421846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902603111","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":[0.00088467536,0.03501633,0.0022395432,0.38733265,0.00027878335,0.04547396,0.33673352,0.0019261105,0.19011444],"genre_scores_gemma":[0.55573267,0.0005212866,0.12277314,0.009074323,0.0016372778,0.10386946,0.12536031,0.0015345634,0.07949696],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99844074,0.00028931675,0.00021391163,0.00069815,0.00013642063,0.00022145643],"domain_scores_gemma":[0.99871755,0.00041977016,0.00034810102,0.0002755989,0.0000990612,0.00013994832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014179926,0.00022124163,0.0003285339,0.00051882194,0.00035355784,0.00009434008,0.00034371673,0.000110710265,0.00061458035],"category_scores_gemma":[0.00034522315,0.00021623896,0.000025973659,0.00034113452,0.000015176694,0.00008859506,0.0001309118,0.00018727516,0.00000430836],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003964417,0.00014143632,0.000005708369,0.0011361705,0.00006533753,3.1858445e-7,0.8810667,0.0000020649297,2.1354941e-8,0.0031712453,0.08587111,0.028535953],"study_design_scores_gemma":[0.00070682314,0.0004221449,0.0003036953,0.001388608,0.000012184105,0.0000012833294,0.88461083,0.002506831,3.8199045e-7,0.00008482709,0.10960222,0.00036015114],"about_ca_topic_score_codex":0.103258304,"about_ca_topic_score_gemma":0.21282764,"teacher_disagreement_score":0.554848,"about_ca_system_score_codex":0.00011347903,"about_ca_system_score_gemma":0.00076532573,"threshold_uncertainty_score":0.9027132},"labels":[],"label_agreement":null},{"id":"W6903066260","doi":"10.1016/j.neucom.2025.130979","title":"MKE-PLLM: A benchmark for multilingual knowledge editing on pretrained large language model","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Multimodal Machine Learning Applications","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":"Major Science and Technology Projects in Yunnan Province; Applied Basic Research Foundation of Yunnan Province; Yunnan Provincial Science and Technology Department; National Natural Science Foundation of China","keywords":"Benchmark (surveying); Usability; Robustness (evolution); Focus (optics); Language model; Baseline (sea)","score_opus":0.013848097286401212,"score_gpt":0.3358910638878189,"score_spread":0.32204296660141774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6903066260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18100263,0.00003246684,0.8079965,0.0007005068,0.00036857807,0.0006317678,0.000012716093,0.00063354045,0.0086212475],"genre_scores_gemma":[0.882193,2.9170613e-7,0.116142,0.0008823007,0.00029887853,0.00008537846,0.00001236789,0.000022297685,0.00036343583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805045,0.00011084603,0.00035452872,0.00076924247,0.00017031051,0.00054465065],"domain_scores_gemma":[0.99790287,0.0011142339,0.00014123104,0.0006315768,0.00012345667,0.00008660804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068297307,0.0002333646,0.00022463061,0.00023169507,0.0005413794,0.00016013483,0.0009757519,0.000087917586,0.000001945133],"category_scores_gemma":[0.0008430019,0.00024525006,0.00012765129,0.0005299944,0.000020987996,0.000116805015,0.00046446212,0.00043380898,0.000019243596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028688832,0.0007339072,0.001478142,0.00032179925,0.000049382437,0.000010346051,0.011623859,0.20847143,0.0126434425,0.19411336,0.0024482762,0.5680774],"study_design_scores_gemma":[0.0007271238,0.000044640135,0.0014613237,0.00008472874,0.000007716395,0.0000019382871,0.00004829634,0.9935567,0.0015327368,0.0007557743,0.0016034242,0.00017560007],"about_ca_topic_score_codex":0.000017723294,"about_ca_topic_score_gemma":0.000007714104,"teacher_disagreement_score":0.78508526,"about_ca_system_score_codex":0.000054570824,"about_ca_system_score_gemma":0.000117014395,"threshold_uncertainty_score":1},"labels":[],"label_agreement":null},{"id":"W6906665089","doi":"10.17632/3kt8gyckfb.3","title":"Risk of violence in elderly people in Brazil: representativeness of the age group // Risco de violência em pessoas idosas no Brasil: representatividade da faixa etária","year":2025,"lang":"en","type":"dataset","venue":"Mendeley Data","topic":"Multimodal Machine Learning Applications","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":"Representativeness heuristic; Depression (economics); Public health; Elderly people; Scale (ratio); Odds; Geriatric Depression Scale; Age groups","score_opus":0.022087678782424795,"score_gpt":0.34694101141329153,"score_spread":0.32485333263086674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6906665089","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":[0.033017207,0.00024929672,0.018322347,0.00028063412,0.00035290534,0.0013957943,0.9462354,0.0000599372,0.00008647703],"genre_scores_gemma":[0.12917575,0.001116396,0.014001329,0.00015567378,0.00009217429,0.00035594768,0.8550188,0.00003662247,0.000047328536],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99302244,0.002310516,0.0013313115,0.0018776159,0.0008678886,0.00059020723],"domain_scores_gemma":[0.9871895,0.0017414715,0.0013330563,0.009527482,0.000120487035,0.0000880084],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0026239224,0.0004976867,0.0009810097,0.0005226511,0.00013581051,0.0001549118,0.012523738,0.00033104574,0.000037906088],"category_scores_gemma":[0.002754507,0.00044165098,0.00014018653,0.0023704015,0.00020487368,0.00060877285,0.0075924858,0.0016960307,0.000010543524],"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":[0.00017069232,0.0016839277,0.21888702,0.0013941454,0.0002822774,0.00008855485,0.0028169872,0.004282262,0.0011145427,0.0011033827,0.7400413,0.028134886],"study_design_scores_gemma":[0.002606826,0.00018755262,0.9012088,0.0029952787,0.00021394616,0.00001782514,0.00040382106,0.05240357,0.00071519945,0.00441436,0.03368248,0.0011503389],"about_ca_topic_score_codex":0.15190083,"about_ca_topic_score_gemma":0.044094894,"teacher_disagreement_score":0.70635885,"about_ca_system_score_codex":0.0001642877,"about_ca_system_score_gemma":0.0005028167,"threshold_uncertainty_score":0.99980354},"labels":[],"label_agreement":null},{"id":"W6920901177","doi":"10.60692/rz8hd-c0104","title":"Pragmatic Inference with a CLIP Listener for Contrastive Captioning","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Discriminative model; Inference; Leverage (statistics); Fluency; Prosody; Hyperparameter","score_opus":0.031017765884502436,"score_gpt":0.2535954053786056,"score_spread":0.22257763949410314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920901177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11469594,3.6199182e-7,0.8816448,0.00023346244,0.00010502906,0.00073465187,0.000035782505,0.00097194983,0.0015780537],"genre_scores_gemma":[0.9780795,2.247105e-8,0.020793447,0.00010113881,0.00003717845,0.00084239256,0.00003621474,0.000008724997,0.00010140715],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882054,0.0000512818,0.00040315132,0.0001958374,0.00025908838,0.00027008625],"domain_scores_gemma":[0.9987748,0.00008165298,0.00031497132,0.0004406522,0.00030589273,0.00008200496],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044156652,0.00014897613,0.00017839846,0.00026673457,0.00027013422,0.00040556787,0.00039108237,0.000057879137,0.0000022617492],"category_scores_gemma":[0.000091011774,0.00011459022,0.000043702414,0.0006369408,0.000024619167,0.0009957686,0.000085059655,0.00009688609,0.00082796183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001251536,0.000010853708,0.29672742,0.001976926,0.00023493737,0.000007906634,0.38299444,0.11276446,0.000022757933,0.19212763,0.00039409596,0.012613429],"study_design_scores_gemma":[0.000956552,0.00006666255,0.114838414,0.00016455447,0.000013334082,0.000026978083,0.0023745196,0.8810558,0.000040806965,0.00002109782,0.0002308221,0.00021050358],"about_ca_topic_score_codex":0.000026634585,"about_ca_topic_score_gemma":4.1036287e-7,"teacher_disagreement_score":0.86338353,"about_ca_system_score_codex":0.000073663745,"about_ca_system_score_gemma":0.000065893466,"threshold_uncertainty_score":0.99995},"labels":[],"label_agreement":null},{"id":"W6923552786","doi":"10.14288/1.0428359","title":"Millsite, Cultus Lake","year":2023,"lang":"en","type":"other","venue":"cIRcle (University of British Columbia)","topic":"Multimodal Machine Learning Applications","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":"FLAGS register; Period (music); Field (mathematics); Lake district","score_opus":0.007062395759626506,"score_gpt":0.18946458951139203,"score_spread":0.18240219375176553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923552786","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":[0.017326707,0.0006382425,0.07507072,0.0008493874,0.0012012678,0.0014501287,0.0017301913,0.009825261,0.8919081],"genre_scores_gemma":[0.09062011,0.00049489643,0.026455656,0.00008010013,0.00015473462,0.0000033989747,0.00009319857,0.0005274191,0.8815705],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986949,0.000048539987,0.0000991131,0.0006186142,0.0002899672,0.00024885905],"domain_scores_gemma":[0.9987548,0.000048277197,0.00022411098,0.0007771882,0.00007426796,0.00012133501],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010205929,0.00006523762,0.0002976443,0.00011110573,0.00014415599,0.00013340266,0.0014074865,0.00023374223,0.0004370927],"category_scores_gemma":[0.000029499608,0.00026515496,0.00013970675,0.0005945273,0.00014418834,0.00013369131,0.00046453354,0.00024204043,0.0008527227],"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":[4.1789932e-7,0.000056988214,0.0024213358,0.000060656344,0.000053230237,0.00010734317,0.00007644576,0.0000089924,0.000005025515,0.000021631353,0.41489026,0.5822977],"study_design_scores_gemma":[0.00033879973,0.000025463825,0.7985567,0.0002383076,0.00001951002,0.000020710318,0.00003415986,0.0012572211,1.8349374e-8,0.0001343917,0.19909962,0.00027512197],"about_ca_topic_score_codex":0.40869316,"about_ca_topic_score_gemma":0.85752755,"teacher_disagreement_score":0.79613537,"about_ca_system_score_codex":0.00003925318,"about_ca_system_score_gemma":0.000064312524,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W6950241977","doi":"10.5683/sp3/j5ebgi","title":"Enquête sur la population active, mars 2003 [Canada] [Remanié Recensement 2011]","year":2023,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Multimodal Machine Learning Applications","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":"Statistics Canada","funders":"","keywords":"Population; Research methodology; Sugar industry; Irrigation district","score_opus":0.020696347780857084,"score_gpt":0.27558383669010195,"score_spread":0.25488748890924484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950241977","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":[0.00015928132,0.00016056305,0.0019237903,0.0077439933,0.0012564835,0.0011200286,0.9862443,0.00026168945,0.0011298711],"genre_scores_gemma":[0.00018834861,0.00055334903,0.0038561416,0.0006485377,0.00040752447,0.00032743136,0.9905982,0.00009176052,0.0033286896],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952382,0.00068988604,0.00078900997,0.0013254185,0.0011569499,0.0008005719],"domain_scores_gemma":[0.99540174,0.00067285454,0.0007234115,0.0022886826,0.00054432306,0.0003689896],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007078324,0.0006449084,0.0005920366,0.00026236364,0.00044796444,0.0003513853,0.0018637262,0.00044177522,0.00017572104],"category_scores_gemma":[0.0008039257,0.0007284568,0.00012198464,0.0009559162,0.0000953172,0.00036528285,0.0007379426,0.0010061673,0.0012242924],"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":[0.000014117544,0.000111561705,0.0004895586,0.00011823559,0.00009856613,0.00008337598,0.000060263275,0.0010392526,0.0000050514927,0.0035606113,0.9623061,0.032113306],"study_design_scores_gemma":[0.00026618998,0.000037737296,0.17342837,0.0001355923,0.00007487916,0.00002218173,0.000008009426,0.019370146,0.0000076260153,0.0001935803,0.8058943,0.0005613803],"about_ca_topic_score_codex":0.99702203,"about_ca_topic_score_gemma":0.97863793,"teacher_disagreement_score":0.17293881,"about_ca_system_score_codex":0.0008097141,"about_ca_system_score_gemma":0.0012290988,"threshold_uncertainty_score":0.9995534},"labels":[],"label_agreement":null},{"id":"W6959225239","doi":"10.7488/ds/4481","title":"Tower Blocks UK: Glasgow City Red Road, glw6-16.jpg","year":2023,"lang":"en","type":"other","venue":"University of Edinburgh","topic":"Multimodal Machine Learning Applications","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":"Tower; Block (permutation group theory); Corporation; Project commissioning; Quarter (Canadian coin); Architecture; Frame (networking)","score_opus":0.012415950960147632,"score_gpt":0.22580329123917134,"score_spread":0.2133873402790237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6959225239","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":[0.00040563315,0.000059817165,0.060654216,0.0015918228,0.0006689972,0.0003235859,0.000037531165,0.0014117081,0.9348467],"genre_scores_gemma":[0.021977872,0.00007091809,0.009414841,0.000042971733,0.0002154893,8.172936e-7,0.000018816545,0.00008061338,0.9681777],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850744,0.000018499259,0.00014654326,0.0006424323,0.00038785764,0.000297204],"domain_scores_gemma":[0.99822366,0.00009840312,0.00032350337,0.0011131507,0.00009142563,0.00014982754],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018793362,0.00024830282,0.00036023415,0.00042206293,0.00014262577,0.000029702962,0.0018538245,0.00032721926,0.034501478],"category_scores_gemma":[0.000074524076,0.0003011532,0.0001770039,0.00059526134,0.0001397859,0.000088032866,0.00073929405,0.00039920522,0.00001998929],"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":[0.0000046127516,0.00004179665,0.0014237382,0.0000019315066,0.00006360349,0.000015798174,0.00020034707,0.000047915666,0.000018019813,0.0001962801,0.9913434,0.0066425954],"study_design_scores_gemma":[0.00048372571,0.00004260068,0.00078920624,0.000111909736,0.0000435191,0.000003230505,0.00005490412,0.004452206,0.000013082796,0.00062344136,0.993,0.00038222593],"about_ca_topic_score_codex":0.01567319,"about_ca_topic_score_gemma":0.00094964245,"teacher_disagreement_score":0.051239375,"about_ca_system_score_codex":0.00013271628,"about_ca_system_score_gemma":0.0001077935,"threshold_uncertainty_score":0.99994403},"labels":[],"label_agreement":null},{"id":"W7008927071","doi":"","title":"A deep learning approach for automatically generating descriptions of images containing people","year":2018,"lang":"en","type":"dissertation","venue":"Library Open Repository (Universidad Complutense Madrid)","topic":"Multimodal Machine Learning Applications","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 Institute for Advanced Research","keywords":"Deep learning; Task (project management); Field (mathematics); Generator (circuit theory); Image (mathematics); Artificial neural network; Image processing","score_opus":0.0137681633948925,"score_gpt":0.25263805203592743,"score_spread":0.23886988864103492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008927071","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":[0.0779057,0.00023765293,0.84407616,0.0002257642,0.0006041411,0.0023771685,0.00002449978,0.0009180025,0.073630944],"genre_scores_gemma":[0.3204405,0.0000057999378,0.6661584,0.0000547627,0.00016497476,0.0002351609,0.0010743755,0.00009547632,0.011770573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674803,0.00038996554,0.0007477271,0.0012081771,0.00040259378,0.0005035098],"domain_scores_gemma":[0.99676543,0.00035809082,0.0011071792,0.001185717,0.00036004686,0.0002235027],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028281912,0.000509471,0.00086795544,0.00044799873,0.001532204,0.0013102033,0.0037954848,0.0003151553,0.000047873757],"category_scores_gemma":[0.00006903806,0.00058655965,0.00037874296,0.0008023263,0.00010050861,0.0024820338,0.0010025285,0.0006419954,0.000015313559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025495745,0.0034016378,0.023398647,0.0066070915,0.0047439006,0.0002798769,0.106595576,0.11372251,0.11287802,0.5165264,0.026465265,0.082831524],"study_design_scores_gemma":[0.00085818797,0.0004208159,0.016734209,0.00022658608,0.00016650467,0.00006473358,0.0029516711,0.97510374,0.0012963724,0.0005657014,0.0008779179,0.00073355954],"about_ca_topic_score_codex":0.0003605845,"about_ca_topic_score_gemma":0.000015244289,"teacher_disagreement_score":0.86138123,"about_ca_system_score_codex":0.00007092724,"about_ca_system_score_gemma":0.00041277846,"threshold_uncertainty_score":0.99976766},"labels":[],"label_agreement":null},{"id":"W7020581563","doi":"","title":"[Letter from P. H. Raiford] with his accounts for the 4th quarter 1850","year":2013,"lang":"en","type":"article","venue":"ThinkTech (Texas Tech University)","topic":"Multimodal Machine Learning Applications","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); Period (music); Work (physics)","score_opus":0.008198097357393535,"score_gpt":0.19695276931930603,"score_spread":0.18875467196191248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020581563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044210654,0.000022948938,0.9244226,0.024338761,0.00010101876,0.0011896356,0.000018442079,0.00075647316,0.0049394597],"genre_scores_gemma":[0.8700308,0.000006811794,0.12335156,0.0027005468,0.00013018952,0.0000331949,0.000015134057,0.000028089951,0.0037036326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986702,0.000050803214,0.0001276244,0.0005187678,0.00027591517,0.00035667565],"domain_scores_gemma":[0.99796784,0.00041571146,0.00013061127,0.0012238405,0.00017043203,0.00009158844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001472584,0.00021201215,0.00017072404,0.0001911707,0.00045701666,0.0002360573,0.0022971518,0.00011458405,0.00014288693],"category_scores_gemma":[0.000020983645,0.00015267114,0.00008404266,0.0006508801,0.00011584941,0.0007662033,0.00032259445,0.00036645614,0.0005439866],"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":[0.00026531937,0.0009572403,0.041488785,0.00009330983,0.0012375837,0.000085473446,0.0070006414,0.0019468018,0.011607737,0.33326545,0.39195654,0.21009512],"study_design_scores_gemma":[0.0023793038,0.00029718527,0.06996029,0.000050659037,0.00012654961,0.000011435563,0.00020062528,0.11076533,0.002038515,0.013352872,0.7998987,0.0009185639],"about_ca_topic_score_codex":0.0036889557,"about_ca_topic_score_gemma":0.00010424122,"teacher_disagreement_score":0.8258202,"about_ca_system_score_codex":0.00011269401,"about_ca_system_score_gemma":0.000062603365,"threshold_uncertainty_score":0.69920284},"labels":[],"label_agreement":null},{"id":"W7023356908","doi":"","title":"Ontario Cuts Solar, Wind Power Subsidies in Review - Bloomberg","year":2012,"lang":"en","type":"other","venue":"","topic":"Multimodal Machine Learning Applications","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":"Subsidy; Wind power; Power (physics); Government (linguistics); Boom; Renewable energy","score_opus":0.012317281740169082,"score_gpt":0.264892721266981,"score_spread":0.2525754395268119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023356908","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":[0.000013609292,0.015126524,0.0065446114,0.0017162822,0.0002443045,0.00057199504,0.0000021437838,0.00035856097,0.97542197],"genre_scores_gemma":[0.00069179514,0.0011642851,0.030546436,0.0013181183,0.00007427592,0.000054905922,0.000014346809,0.00014119114,0.96599466],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847883,0.00008182811,0.0002871415,0.00052039995,0.0002596875,0.00037209925],"domain_scores_gemma":[0.9983819,0.000047025915,0.00019582898,0.0012409494,0.000023535233,0.00011076172],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028410906,0.00030055345,0.00043584235,0.00021042884,0.000033259952,0.00005267174,0.0011410346,0.00019377498,0.012637417],"category_scores_gemma":[0.00002873542,0.00025982066,0.00009097656,0.0003046149,0.00003279457,0.0001242236,0.00033741567,0.0005489372,0.0035027172],"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":[5.527501e-7,0.0001749908,0.019580625,0.0003344028,0.000046222973,0.0000075646844,0.00045887672,0.000002496401,0.000004246333,0.016475603,0.9537729,0.009141492],"study_design_scores_gemma":[0.000105356674,0.000009031225,0.014275213,0.0009086827,0.000013584863,0.000008312504,7.701741e-7,0.000039915907,0.00000212281,0.00009914809,0.98422885,0.00030903646],"about_ca_topic_score_codex":0.093103066,"about_ca_topic_score_gemma":0.09453824,"teacher_disagreement_score":0.0304559,"about_ca_system_score_codex":0.000107731445,"about_ca_system_score_gemma":0.0001452506,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W7023947339","doi":"","title":"Representing the Reprehensible: Fairy Tales, News Stories & the Monstrous Karla Homolka","year":2006,"lang":"en","type":"article","venue":"Journals @ The Mount (Mount Saint Vincent University)","topic":"Multimodal Machine Learning Applications","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":"Meaning (existential); Personality; Public discourse; Love story","score_opus":0.012024814242046801,"score_gpt":0.22903020554153866,"score_spread":0.21700539129949187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023947339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77022034,0.0013816137,0.1549947,0.067278616,0.0006802665,0.0009891401,0.000014304549,0.0004177101,0.0040232954],"genre_scores_gemma":[0.99496967,0.0002249178,0.0023896266,0.0006878576,0.0005229855,0.000006858795,0.00000437244,0.000025000187,0.0011687276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964243,0.00082441483,0.00051219034,0.00066293793,0.0009037119,0.0006724545],"domain_scores_gemma":[0.9955174,0.0009765227,0.0007530044,0.0023289574,0.00031997787,0.000104157996],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0014228325,0.00034717502,0.00029128062,0.00023729725,0.0030601805,0.00090426917,0.0040534553,0.000104820145,0.000029738429],"category_scores_gemma":[0.00020385902,0.00019886643,0.0002989936,0.0015929667,0.00043987282,0.00067752413,0.0014697973,0.0012178967,0.000081559614],"study_design_candidate":"theoretical_or_conceptual","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":[0.000024008676,0.00013002349,0.015686508,0.000007861354,0.00009951123,0.00010174514,0.0008919477,0.032782145,0.0014243214,0.9392708,0.002437737,0.007143398],"study_design_scores_gemma":[0.00052390405,0.00004380111,0.09463459,0.00007601199,0.0001062323,0.00030166132,0.0018998418,0.049413115,0.0001884048,0.0048122657,0.8475717,0.00042851854],"about_ca_topic_score_codex":0.044174917,"about_ca_topic_score_gemma":0.0011319614,"teacher_disagreement_score":0.93445855,"about_ca_system_score_codex":0.0043107355,"about_ca_system_score_gemma":0.00020837183,"threshold_uncertainty_score":0.99951154},"labels":[],"label_agreement":null},{"id":"W7023957047","doi":"","title":"A repeatable procedure to determine a representative average rail profile","year":2016,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Multimodal Machine Learning Applications","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 Manitoba","funders":"","keywords":"Nucleofection; Hyporeflexia; Articular cartilage damage; Diafiltration; Dysgeusia; Fusible alloy","score_opus":0.013899201395223808,"score_gpt":0.24615642030262666,"score_spread":0.23225721890740286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023957047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81374806,0.00008179136,0.11024326,0.007052568,0.00047295296,0.0026904566,0.00013471443,0.0006937959,0.06488241],"genre_scores_gemma":[0.84056544,0.00003095078,0.10136131,0.00010170586,0.00012632566,0.000027154743,0.00026668547,0.00006517301,0.057455238],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99817455,0.00009556331,0.000145795,0.0008555622,0.00041861951,0.0003099204],"domain_scores_gemma":[0.99795413,0.000113083806,0.00040196237,0.0010474556,0.0003173733,0.0001659807],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001722102,0.0002598463,0.00036522624,0.000339732,0.0003250573,0.000053288113,0.0015393292,0.0001847401,0.000029241315],"category_scores_gemma":[0.00013467591,0.00029125088,0.0001318413,0.00054437714,0.00004064803,0.0004115091,0.0003620554,0.000292414,0.00046956402],"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":[0.0029615923,0.0026795303,0.11333789,0.0062810257,0.0019239757,0.0014089884,0.09486413,0.00212011,0.24121264,0.055702522,0.25472584,0.22278176],"study_design_scores_gemma":[0.0025715518,0.00065077137,0.9278122,0.0015227358,0.00017905813,0.00003881101,0.01016665,0.018671172,0.012914251,0.0018004179,0.021656476,0.0020158803],"about_ca_topic_score_codex":0.0031524452,"about_ca_topic_score_gemma":0.0391344,"teacher_disagreement_score":0.81447434,"about_ca_system_score_codex":0.00014414925,"about_ca_system_score_gemma":0.0002094341,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W7024176244","doi":"","title":"re:mote regina :: tom mulcaire","year":2005,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Multimodal Machine Learning Applications","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":"Exhibition; Presentation (obstetrics); The arts; Cape; Performance art; Work (physics)","score_opus":0.0055000953988734265,"score_gpt":0.2017011791838166,"score_spread":0.1962010837849432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024176244","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":[0.000005694362,0.00022782716,0.00013899802,0.003409423,0.00021386976,0.0004639039,0.000046181307,0.0007962739,0.9946978],"genre_scores_gemma":[0.00063309126,0.000106461506,0.039913718,0.0006037604,0.0002544696,0.00002968013,0.00007348843,0.000116814,0.9582685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981256,0.000089149864,0.00052028394,0.000378512,0.0005248936,0.00036155665],"domain_scores_gemma":[0.9976229,0.00012369685,0.0007619962,0.0011990464,0.000133957,0.00015838961],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024278225,0.00038837828,0.0004080935,0.00013643275,0.000102723265,0.00012242953,0.0013728762,0.0004075428,0.122295395],"category_scores_gemma":[0.00012761314,0.00039835944,0.00017139455,0.000021108972,0.000102541184,4.6341367e-7,0.0002942492,0.00046036177,0.030268818],"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":[0.000006628124,0.00003420644,0.0000023560224,0.000139978,0.000028737442,0.000006643878,0.00012264104,0.00082145695,1.4465301e-7,0.00040943487,0.97365093,0.024776857],"study_design_scores_gemma":[0.00032375782,0.000057191653,0.000035677986,0.00016789218,0.000019177674,0.00003368175,0.000015346499,0.0020245484,0.000003488712,0.000015313039,0.9969137,0.00039025277],"about_ca_topic_score_codex":0.007308164,"about_ca_topic_score_gemma":0.0012195859,"teacher_disagreement_score":0.09202658,"about_ca_system_score_codex":0.000070693626,"about_ca_system_score_gemma":0.000047822898,"threshold_uncertainty_score":0.9998468},"labels":[],"label_agreement":null},{"id":"W7024237576","doi":"","title":"The road between now and then","year":2001,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Multimodal Machine Learning Applications","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":"Government (linguistics); Work (physics); Natural (archaeology); Perspective (graphical)","score_opus":0.003395538986901898,"score_gpt":0.16150011742275414,"score_spread":0.15810457843585224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024237576","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":[0.000506917,0.0009413759,0.002410162,0.012976091,0.00010506093,0.00022468601,0.000100876576,0.00004370934,0.9826911],"genre_scores_gemma":[0.16127324,0.0012273777,0.009474086,0.0010775898,0.0002804787,0.000030176225,0.000010741086,0.00015527495,0.82647103],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983401,0.00006403998,0.00016747435,0.0002925506,0.0009043976,0.00023148925],"domain_scores_gemma":[0.99888134,0.00030282506,0.00019127407,0.00044599242,2.1156868e-7,0.00017832973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000011616142,0.0001858974,0.00020003431,0.000020672811,0.0002141189,0.000064839405,0.0007060918,0.00003586803,0.000024410101],"category_scores_gemma":[0.0000024270212,0.00014093339,0.00001654379,0.00007203788,0.000090344685,0.00009851005,0.00037367712,0.00019313826,8.76538e-9],"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":[0.00002456055,0.000020737523,0.11454892,0.00016875549,0.00028437385,0.000041536972,0.00010722838,0.000023696335,0.00027418428,0.318753,0.102228925,0.4635241],"study_design_scores_gemma":[0.00013595646,0.000019095161,0.11240997,0.0000715878,0.000011951955,0.0000038746152,0.00008196473,0.0030997444,0.00021995197,0.0013581091,0.88236535,0.00022243935],"about_ca_topic_score_codex":0.023642384,"about_ca_topic_score_gemma":0.059413344,"teacher_disagreement_score":0.7801364,"about_ca_system_score_codex":0.0000031658387,"about_ca_system_score_gemma":0.00056235504,"threshold_uncertainty_score":0.98285925},"labels":[],"label_agreement":null},{"id":"W7024299326","doi":"","title":"The role of agricultural policies in rural development/ comparative study between Iran and Japan","year":2018,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Multimodal Machine Learning Applications","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":"Agriculture; Quarter (Canadian coin); Agricultural policy; Agricultural productivity; Rural area; Theme (computing); Rural economy; Rural development","score_opus":0.1967255651573538,"score_gpt":0.5365624480065508,"score_spread":0.33983688284919705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024299326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996314,0.0010667443,0.00027157966,0.00018256524,0.00005863721,0.0005668792,0.0000037799625,0.000024287872,0.0015115334],"genre_scores_gemma":[0.99869955,0.00006756855,0.0010561094,0.000020931475,0.000067788926,0.000044585908,0.0000018952854,0.00000828941,0.00003329782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997988,0.00033438363,0.0006783849,0.00027819912,0.00044307517,0.0002779655],"domain_scores_gemma":[0.998167,0.00047838362,0.000598797,0.0003926326,0.0002435315,0.00011969104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009779021,0.0001992459,0.0004715484,0.00030663254,0.00049742655,0.0009239928,0.0034973794,0.000039353607,0.000056474615],"category_scores_gemma":[0.00008418824,0.00013150864,0.000042862393,0.0010526738,0.00023700745,0.0011627492,0.0015245924,0.0002874948,0.000007942291],"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":[0.000011392187,0.00012148595,0.96050185,0.0000039366087,0.0000699267,2.1473289e-7,0.009343695,0.000030174793,0.010271659,0.0003654295,0.00016719456,0.01911304],"study_design_scores_gemma":[0.00028834958,0.000020994159,0.98780733,0.00005726733,0.000010927388,0.0000021538428,0.002003766,0.0002953853,0.007694974,0.0012921825,0.00035808465,0.00016858928],"about_ca_topic_score_codex":0.0043683,"about_ca_topic_score_gemma":0.0006512315,"teacher_disagreement_score":0.027305475,"about_ca_system_score_codex":0.000049722432,"about_ca_system_score_gemma":0.000066398956,"threshold_uncertainty_score":0.8910084},"labels":[],"label_agreement":null},{"id":"W7024327003","doi":"","title":"Quest : finding form in children's literature","year":2012,"lang":"en","type":"other","venue":"OpenGrey (Institut de l'Information Scientifique et Technique)","topic":"Multimodal Machine Learning Applications","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":"Perspective (graphical); Element (criminal law); Character (mathematics); Fantasy; Context (archaeology); Order (exchange)","score_opus":0.01194257135248826,"score_gpt":0.2796330711531889,"score_spread":0.26769049980070064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024327003","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":[0.00007295751,0.00011994193,0.57240087,0.00071069424,0.00037593217,0.0059798737,0.000082547456,0.0012158375,0.41904134],"genre_scores_gemma":[0.061083008,0.00038713816,0.7973446,0.0025303757,0.00044938416,0.008371362,0.002337902,0.00042419933,0.12707198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972811,0.00018587521,0.00067185005,0.00056907156,0.00058935327,0.00070277986],"domain_scores_gemma":[0.99740225,0.000051847066,0.0006545537,0.0015062643,0.00014663677,0.00023845698],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0027023463,0.0004896863,0.00039871334,0.0019792165,0.00022414057,0.0015095292,0.0023695207,0.00067681173,0.00025491844],"category_scores_gemma":[0.00025071963,0.00048571703,0.00013062962,0.0018938627,0.00010575323,0.0043252497,0.00066864304,0.0012568608,0.0007228148],"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":[0.000007163684,0.0002401184,0.009033102,0.0006941167,0.000054598313,0.0000115219345,0.005630414,0.00029341003,0.00030232154,0.50465554,0.26865196,0.21042573],"study_design_scores_gemma":[0.00039348318,0.000013639109,0.0068718665,0.0018757193,0.000010217555,0.00009669732,0.000006939288,0.0038672055,0.0008743186,0.0010587274,0.9841012,0.0008300392],"about_ca_topic_score_codex":0.00087538484,"about_ca_topic_score_gemma":0.00020972334,"teacher_disagreement_score":0.71544915,"about_ca_system_score_codex":0.00036675364,"about_ca_system_score_gemma":0.0003909147,"threshold_uncertainty_score":0.99975944},"labels":[],"label_agreement":null},{"id":"W7024380295","doi":"","title":"8,789 Shares in Canadian Solar Inc. (NASDAQ:CSIQ) Bought by XTX Topco Ltd","year":2021,"lang":"en","type":"other","venue":"","topic":"Multimodal Machine Learning Applications","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":"Government (linguistics); Consumption (sociology)","score_opus":0.006976955539238327,"score_gpt":0.25498128354957533,"score_spread":0.248004328010337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024380295","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":[0.000060909362,0.0018798577,0.015150153,0.006932776,0.0003334543,0.00049041084,0.00013445907,0.00047305296,0.97454494],"genre_scores_gemma":[0.00962121,0.00010232191,0.039954375,0.002744647,0.00026065425,0.00018439235,0.0005962261,0.00029713183,0.94623905],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977562,0.00012184706,0.00027522337,0.0009044515,0.00028483206,0.0006574373],"domain_scores_gemma":[0.9980421,0.00006807653,0.00011906299,0.0013160509,0.00004488237,0.00040983196],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020435524,0.00033482714,0.00034757692,0.00050642504,0.00009892988,0.00027736498,0.0017956382,0.00037330596,0.009658229],"category_scores_gemma":[0.000083986335,0.00034343326,0.00006588333,0.0006409322,0.000039211598,0.000082676015,0.00035611226,0.0006041314,0.00069812284],"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":[2.5763845e-7,0.00004382639,0.0032179973,0.000031822496,0.000021576532,0.000032296062,0.000110074696,0.00002046014,0.00004249269,0.009491688,0.9734662,0.013521303],"study_design_scores_gemma":[0.00014229512,0.0000098614655,0.0022422676,0.000078870806,0.0000033025651,0.0000056310896,0.0000066496796,0.010183375,0.000035750556,0.0001288715,0.986759,0.00040412365],"about_ca_topic_score_codex":0.9171043,"about_ca_topic_score_gemma":0.87581366,"teacher_disagreement_score":0.04129061,"about_ca_system_score_codex":0.0002537366,"about_ca_system_score_gemma":0.0007211986,"threshold_uncertainty_score":0.9999018},"labels":[],"label_agreement":null},{"id":"W7024396789","doi":"","title":"Role of miRNAs in Translational Control of Human Apolipoprotein B-100 mRNA","year":2013,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Multimodal Machine Learning Applications","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":"Apolipoprotein B; Messenger RNA; Transfection; microRNA; Translational efficiency; Translation (biology); Three prime untranslated region; Translational regulation","score_opus":0.002654248860639226,"score_gpt":0.172964819059867,"score_spread":0.17031057019922777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024396789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86365426,0.0006856536,0.0008727629,0.0017490824,0.00010420942,0.0008458947,0.00029839532,0.00001499143,0.13177474],"genre_scores_gemma":[0.9954669,0.0000127393005,0.0026999463,0.000073103685,0.000018485987,0.000037907455,0.000049711496,0.000014787535,0.0016264358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99772245,0.00007197888,0.0005035065,0.0002591724,0.001262379,0.00018050705],"domain_scores_gemma":[0.99895996,0.0001845965,0.00046020932,0.00028455694,0.0000019908935,0.00010867571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000015369927,0.000180015,0.00036101934,0.000070439695,0.00006332168,0.000012430197,0.0005626246,0.00005082277,0.000029063702],"category_scores_gemma":[0.00000307292,0.00018921304,0.00004069753,0.00011698353,0.00004056905,0.00024043527,0.00003793979,0.00020935481,2.6428888e-9],"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":[0.00014044205,0.000097315635,0.028262084,0.00050391594,0.00009333211,0.0000039799975,0.00066593784,0.00075642404,0.34130415,0.6021909,0.000043631924,0.025937866],"study_design_scores_gemma":[0.0007722707,0.000084701205,0.7760553,0.00029061915,0.000018784009,0.0000010475092,0.000600141,0.038931537,0.17090602,0.011451558,0.00057658757,0.00031146925],"about_ca_topic_score_codex":0.059643008,"about_ca_topic_score_gemma":0.07360684,"teacher_disagreement_score":0.7477932,"about_ca_system_score_codex":0.0000049864966,"about_ca_system_score_gemma":0.0012371861,"threshold_uncertainty_score":0.9466189},"labels":[],"label_agreement":null},{"id":"W7024428693","doi":"","title":"Seattle Mariners vs Toronto Blue Jays Live Broadcast Free Online","year":2022,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Multimodal Machine Learning Applications","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":"Broadcasting (networking); The Internet; Doors; Public access","score_opus":0.010645282151407951,"score_gpt":0.2635796097322182,"score_spread":0.25293432758081025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024428693","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":[0.0005695584,0.000017462013,0.021155896,0.0009617182,0.00065121986,0.0015125445,0.0002276038,0.0014906073,0.9734134],"genre_scores_gemma":[0.0014326919,0.00020192136,0.0469144,0.0004139983,0.0003323795,0.00075659435,0.00026719717,0.00047190665,0.9492089],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99252367,0.0008395018,0.000689766,0.0042365934,0.00095091347,0.00075956766],"domain_scores_gemma":[0.98477024,0.00039199158,0.00069514,0.01361608,0.00010774652,0.0004187836],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0018719229,0.00075245666,0.0007689668,0.00027892555,0.00030991685,0.0002775516,0.0088377,0.00047103444,0.8257103],"category_scores_gemma":[0.0014773199,0.00089080824,0.0003599727,0.00039013292,0.0001737205,0.0002921477,0.014548939,0.0014197988,0.57861644],"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":[0.00003614405,0.0009028691,0.006876765,0.0001638114,0.00038730138,0.000052135176,0.0022545636,0.003513137,0.00013280413,0.006735589,0.9121323,0.06681255],"study_design_scores_gemma":[0.0006716219,0.0000034930238,0.007217684,0.00007481589,0.000063084015,0.00004710233,0.0001611616,0.011339778,0.00003625683,0.0007696742,0.9787332,0.00088213146],"about_ca_topic_score_codex":0.04298885,"about_ca_topic_score_gemma":0.0047942074,"teacher_disagreement_score":0.24709387,"about_ca_system_score_codex":0.0009966461,"about_ca_system_score_gemma":0.00033852743,"threshold_uncertainty_score":0.99935424},"labels":[],"label_agreement":null},{"id":"W7024522294","doi":"","title":"Share original pro max real","year":2022,"lang":"ar","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Multimodal Machine Learning Applications","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":"Brother; Supporter; Spanish Civil War; Hinduism; Clan","score_opus":0.008750522768568851,"score_gpt":0.21705696735389046,"score_spread":0.2083064445853216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024522294","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":[0.00035191225,0.00015652836,0.0000050461554,0.0010106497,0.00047506552,0.0012071189,0.0003151424,0.00043811862,0.9960404],"genre_scores_gemma":[0.0039026262,0.00018556102,0.010564392,0.00039674362,0.00029621297,0.00018417167,0.0005464382,0.00013622153,0.98378766],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587864,0.00022489669,0.0012567065,0.0007266429,0.0012179269,0.0006951686],"domain_scores_gemma":[0.99625427,0.00021336027,0.0014422062,0.0014709593,0.00031872373,0.00030045758],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00060036953,0.0006915729,0.0007319734,0.00019474396,0.00046816547,0.00028152633,0.0023252924,0.0004356492,0.8531856],"category_scores_gemma":[0.00015291477,0.0007489982,0.00032885434,0.000046598565,0.00020636828,7.40302e-7,0.00091785856,0.001206608,0.14936534],"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":[0.000067808964,0.00011826491,0.000103054444,0.00055151613,0.0000866972,0.000035393245,0.0007734571,0.0043282737,3.3235875e-7,0.0015630195,0.9871903,0.0051818485],"study_design_scores_gemma":[0.0006585606,0.00031958998,0.00030448436,0.00015880373,0.000067490095,0.00017728723,0.00012099105,0.0037256796,0.0000022835595,0.000029776582,0.99371374,0.0007213163],"about_ca_topic_score_codex":0.023123182,"about_ca_topic_score_gemma":0.0006338935,"teacher_disagreement_score":0.7038203,"about_ca_system_score_codex":0.00029589544,"about_ca_system_score_gemma":0.00020019911,"threshold_uncertainty_score":0.9994961},"labels":[],"label_agreement":null},{"id":"W7024575673","doi":"","title":"Séquence des cours de français et approche-programme","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Multimodal Machine Learning Applications","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":"Collège de Bois-de-Boulogne","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.020362948217831175,"score_gpt":0.2574546841429343,"score_spread":0.23709173592510313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024575673","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":[0.031765696,0.012960379,0.21221337,0.043686043,0.00023999442,0.0014063099,0.00034135423,0.00082400884,0.6965628],"genre_scores_gemma":[0.4211508,0.0009340462,0.16347878,0.0048054955,0.00071509974,0.0011245424,0.00009300091,0.0005585832,0.40713966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934753,0.0008874424,0.0008968909,0.0015763848,0.0020105252,0.0011534371],"domain_scores_gemma":[0.9882284,0.008342686,0.0009578665,0.0013212317,0.00028004043,0.0008698126],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001483856,0.0010285601,0.00075947325,0.0011231472,0.0005115491,0.0013603468,0.003423868,0.0003066959,0.004664607],"category_scores_gemma":[0.007413724,0.00107754,0.00039549236,0.0019755417,0.0014375345,0.00095921004,0.0013570697,0.0013841139,0.002586116],"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":true,"study_design_scores_codex":[0.0001517718,0.0025536513,0.19614291,0.00086392724,0.0008605283,0.000099057754,0.07439372,0.007086149,0.0017398933,0.37989095,0.30975538,0.026462054],"study_design_scores_gemma":[0.0011649921,0.00021798057,0.19714491,0.0005148992,0.000111339104,0.00019084594,0.00017645289,0.034225177,0.00011885016,0.0055246893,0.7593897,0.0012201745],"about_ca_topic_score_codex":0.49000582,"about_ca_topic_score_gemma":0.90048295,"teacher_disagreement_score":0.44963428,"about_ca_system_score_codex":0.006899947,"about_ca_system_score_gemma":0.08677004,"threshold_uncertainty_score":0.99967635},"labels":[],"label_agreement":null},{"id":"W7024576020","doi":"","title":"Shpenopholis intermedia (Slender Wedge grass)","year":2004,"lang":"en","type":"other","venue":"Connecting Canadians: Canada’s Multicultural Newspapers Beta Website (Athabasca University)","topic":"Multimodal Machine Learning Applications","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":"Wedge (geometry); Focus (optics); Context (archaeology); Deformation (meteorology)","score_opus":0.0071447203416480295,"score_gpt":0.19529153593622825,"score_spread":0.1881468155945802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024576020","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":[0.007948811,0.0019425973,0.0056335833,0.02463093,0.0060106344,0.0038423701,0.0016611184,0.003637285,0.9446927],"genre_scores_gemma":[0.26581377,0.00026950458,0.020691348,0.0028332667,0.0010845597,0.000022103735,0.0008937269,0.0009589105,0.7074328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531806,0.00023000957,0.0004843869,0.0018236522,0.0007686451,0.0013752261],"domain_scores_gemma":[0.99587053,0.00028435007,0.0006901701,0.001556511,0.00024436612,0.0013540563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015073537,0.0010609169,0.00097390363,0.0010953883,0.0007890535,0.00036122533,0.0035927135,0.00059588224,0.0008880331],"category_scores_gemma":[0.00024377758,0.001141221,0.00038807243,0.0014037975,0.0001932585,0.00048958155,0.00059562206,0.0012898968,0.00021112194],"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":[0.000024560415,0.00013983517,0.0016130271,0.00039125176,0.001593546,0.0027301796,0.004592263,0.0019807275,0.00058085704,0.014469439,0.95468795,0.01719636],"study_design_scores_gemma":[0.0014195807,0.00003932855,0.0028890173,0.00046872286,0.00019639608,0.00008419239,0.0017118984,0.0017809544,0.000048075366,0.0000058192845,0.98970294,0.0016530668],"about_ca_topic_score_codex":0.99244726,"about_ca_topic_score_gemma":0.99808294,"teacher_disagreement_score":0.25786498,"about_ca_system_score_codex":0.0045495383,"about_ca_system_score_gemma":0.0047167223,"threshold_uncertainty_score":0.9992718},"labels":[],"label_agreement":null},{"id":"W7024603552","doi":"","title":"Sound transmission loss of orthotropic sandwich panels with soft core and noise control treatment","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Multimodal Machine Learning Applications","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":"Shearing (physics); Sandwich-structured composite; Noise control; Sound transmission class; Orthotropic material; Compressibility; Core (optical fiber); Noise (video)","score_opus":0.017896965668736824,"score_gpt":0.26591228234161557,"score_spread":0.24801531667287874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024603552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5971667,0.000063211715,0.40165642,0.00042000553,0.0000123448835,0.00016972848,0.0000027508654,0.00004107179,0.00046778386],"genre_scores_gemma":[0.96488386,0.000008997181,0.034937415,0.000041352345,0.000028934346,0.000035526773,0.0000019478557,0.000007681517,0.00005426703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993175,0.000036352892,0.00012427107,0.00018510435,0.00014238957,0.00019436446],"domain_scores_gemma":[0.9993498,0.0001079488,0.000070156806,0.0003044494,0.00003561631,0.00013205841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007723643,0.00010956864,0.00016018683,0.000037854294,0.0000828351,0.00002060553,0.000164101,0.000035480934,0.000038765975],"category_scores_gemma":[0.0000065657714,0.00007410914,0.000026482636,0.00011017478,0.000060218517,0.00012787241,0.000019490639,0.00006624211,0.000008592569],"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":[0.000058205183,0.00034942673,0.7585254,0.00003484383,0.000052688454,0.0000031754103,0.0032928227,0.00030024818,0.029093599,0.014840949,0.00001455855,0.19343409],"study_design_scores_gemma":[0.0026410315,0.00044991114,0.9375655,0.000029014629,0.000055428067,0.000047824873,0.000018770386,0.053513475,0.0015788679,0.0026026827,0.0012873492,0.00021011254],"about_ca_topic_score_codex":0.000066517954,"about_ca_topic_score_gemma":0.0000031917052,"teacher_disagreement_score":0.36771718,"about_ca_system_score_codex":0.000020332169,"about_ca_system_score_gemma":0.00002826629,"threshold_uncertainty_score":0.3022083},"labels":[],"label_agreement":null},{"id":"W7024798424","doi":"","title":"Smoke from Canada wildfires increasing health risks in Black and poorer US communities","year":2023,"lang":"en","type":"other","venue":"","topic":"Multimodal Machine Learning Applications","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":"Smoke; Air pollution; Human health; Public health; Poison control","score_opus":0.03799644492927861,"score_gpt":0.3071918132148642,"score_spread":0.2691953682855856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024798424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9645142,0.00025830668,0.00010438783,0.002854408,0.0001080896,0.0002352722,0.00006232501,0.0005820964,0.031280916],"genre_scores_gemma":[0.98836654,0.0002025161,0.009288416,0.0012706891,0.000057478428,0.000019917152,0.000036291014,0.00019762489,0.00056050485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99872947,0.00027858044,0.00021699497,0.000299573,0.00021498399,0.0002604107],"domain_scores_gemma":[0.99850935,0.00047297397,0.00015915558,0.00073993317,0.000010407431,0.00010820038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023504754,0.00020325939,0.0003010542,0.0001937839,0.000099585544,0.000108036045,0.0007106175,0.000100343124,0.00010168973],"category_scores_gemma":[0.00003699923,0.00019735083,0.000017138402,0.0002376506,0.00007621154,0.000042507658,0.000411179,0.0004370139,0.00001975536],"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":[7.016479e-7,0.000009206438,0.9900056,0.00001504909,0.000015042916,0.000003029416,0.0005292811,0.000055759585,1.8318788e-7,0.000781246,0.0019658266,0.0066190544],"study_design_scores_gemma":[0.00013842573,0.000007138672,0.98410964,0.00016924967,0.0000020913453,0.0000012250131,0.00011393095,0.012725377,3.7261978e-7,0.00020679533,0.0023398593,0.00018591978],"about_ca_topic_score_codex":0.99999756,"about_ca_topic_score_gemma":0.99865407,"teacher_disagreement_score":0.03072041,"about_ca_system_score_codex":0.00016939492,"about_ca_system_score_gemma":0.00044755018,"threshold_uncertainty_score":0.80477333},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W7024804035","doi":"","title":"A supported college course for credit: More than just Academics","year":2017,"lang":"en","type":"other","venue":"Arca (British Columbia Electronic Library Network)","topic":"Multimodal Machine Learning Applications","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":"Mental health; Session (web analytics); Presentation (obstetrics); Coaching; Academic advising; Higher education","score_opus":0.011443729804320837,"score_gpt":0.2542931138448453,"score_spread":0.24284938404052447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024804035","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":[0.000064477215,0.012675316,0.0041161557,0.0052830223,0.0019171328,0.005985428,0.0018288495,0.005268852,0.96286076],"genre_scores_gemma":[0.10508523,0.00249957,0.021054422,0.0014682658,0.005047069,0.0018075067,0.0017385711,0.0012592403,0.8600401],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99495643,0.00017104855,0.0005374053,0.0016806739,0.0005210954,0.0021333194],"domain_scores_gemma":[0.9959561,0.0002733712,0.0009549899,0.002337785,0.000059708258,0.0004180469],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034051895,0.00052079855,0.0008986172,0.0001003785,0.000899195,0.0018842798,0.0050043827,0.0010139026,0.015857128],"category_scores_gemma":[0.00006530293,0.000945216,0.00037142087,0.00057565357,0.00027017677,0.00088993757,0.00094287534,0.0017792939,0.00006708599],"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":[0.000007328395,0.00012365158,0.0014858402,0.000075298565,0.00020198373,0.000041233026,0.000017120332,0.000047406316,2.1166503e-7,0.06011161,0.91873854,0.019149765],"study_design_scores_gemma":[0.0010337696,0.00018614031,0.000851318,0.0005357616,0.00010688955,0.00015209292,0.000003593362,0.036827464,9.4397456e-7,0.06732019,0.892051,0.0009308687],"about_ca_topic_score_codex":0.00679352,"about_ca_topic_score_gemma":0.025807142,"teacher_disagreement_score":0.105020754,"about_ca_system_score_codex":0.00011946072,"about_ca_system_score_gemma":0.001927782,"threshold_uncertainty_score":0.99982035},"labels":[],"label_agreement":null},{"id":"W7025005265","doi":"","title":"Ãtude de la conversion de longueur d'onde","year":2000,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Multimodal Machine Learning Applications","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":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.002459851744428148,"score_gpt":0.15972918954532722,"score_spread":0.15726933780089908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025005265","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":[0.028102392,0.0006264325,0.005221308,0.009107056,0.00017752571,0.00024659038,0.00015529412,0.00003556755,0.95632786],"genre_scores_gemma":[0.702578,0.0004442983,0.022067185,0.002793309,0.00015846937,0.00001629987,0.000011044857,0.00009274687,0.27183864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713624,0.0003650671,0.00030030982,0.0004811787,0.0011980548,0.0005191304],"domain_scores_gemma":[0.9980306,0.00073213136,0.00025169947,0.00047124972,3.7886724e-7,0.00051392044],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000025614603,0.0003374888,0.00033343368,0.000042037624,0.0002305008,0.000086316424,0.0008581343,0.000110805966,0.0009718104],"category_scores_gemma":[0.0000067826527,0.0003702356,0.00005087336,0.00012378034,0.00022396355,0.00022243673,0.00031627592,0.00047506473,6.410206e-8],"study_design_candidate":"theoretical_or_conceptual","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":[0.00027134898,0.0002122577,0.15103942,0.00095412164,0.0003208886,0.0005551463,0.0009916838,0.0053607603,0.018839581,0.69908744,0.017796397,0.10457093],"study_design_scores_gemma":[0.0004831357,0.000061763676,0.37967682,0.00036338397,0.00004455508,0.000064162705,0.00017570372,0.10717859,0.008959366,0.0015522854,0.5009049,0.00053532526],"about_ca_topic_score_codex":0.04309317,"about_ca_topic_score_gemma":0.018233584,"teacher_disagreement_score":0.69753516,"about_ca_system_score_codex":0.00002648672,"about_ca_system_score_gemma":0.0044972072,"threshold_uncertainty_score":0.9999414},"labels":[],"label_agreement":null},{"id":"W7025322670","doi":"","title":"Uplatnění amerických plemen koní v České republice","year":2011,"lang":"en","type":"dissertation","venue":"Digital Repository (National Repository of Grey Literature)","topic":"Multimodal Machine Learning Applications","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":"Czech; Quarter (Canadian coin); Work (physics); International comparisons; Western europe","score_opus":0.009545500508091054,"score_gpt":0.2555883167203818,"score_spread":0.24604281621229074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025322670","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":[0.12184059,0.0022685914,0.0028049934,0.00015025151,0.0047406754,0.0012492614,0.00019768714,0.0009569492,0.865791],"genre_scores_gemma":[0.89434636,0.000014285308,0.006717025,0.00008738845,0.00077645876,0.00024352077,0.002217474,0.00011963965,0.09547786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99379337,0.00017253854,0.0016682511,0.0016560146,0.0021563014,0.00055353506],"domain_scores_gemma":[0.99227387,0.0004041865,0.0020206918,0.0016486812,0.0033036415,0.00034893153],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00030424795,0.0008170017,0.0007798029,0.00081211346,0.0005710128,0.0021954323,0.0025608905,0.0006852617,0.000012332238],"category_scores_gemma":[0.00051489985,0.0008452903,0.0005848461,0.0012027967,0.00015640259,0.0030901271,0.00027434735,0.0011579427,0.000050854378],"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":[0.0016534674,0.0069736363,0.062835135,0.00477741,0.004572692,0.0013287648,0.05363882,0.0009671213,0.07915214,0.656367,0.0421498,0.08558404],"study_design_scores_gemma":[0.0041569034,0.0022028773,0.5993064,0.005951427,0.00061820063,0.0038160565,0.00095444836,0.01638395,0.090700924,0.037390765,0.22814955,0.010368516],"about_ca_topic_score_codex":0.0002152333,"about_ca_topic_score_gemma":0.0000057932575,"teacher_disagreement_score":0.77250576,"about_ca_system_score_codex":0.00028041733,"about_ca_system_score_gemma":0.0010432295,"threshold_uncertainty_score":0.9993998},"labels":[],"label_agreement":null},{"id":"W7035770051","doi":"","title":"Ajustement d’enseignantes et d’enseignants immigrants aux conventions professionnelles de l’École québécoise au cœur de l’accompagnement offert par des conseillères pédagogiques","year":2022,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Multimodal Machine Learning Applications","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":"Immigration; Context (archaeology); Citizenship; Naturalization","score_opus":0.020241809669695736,"score_gpt":0.24716665456113623,"score_spread":0.2269248448914405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7035770051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9619652,0.010918534,0.012835843,0.0036214679,0.0010435845,0.0015869448,0.00025517878,0.0004288563,0.0073444047],"genre_scores_gemma":[0.9617395,0.0010227725,0.008571387,0.0006392339,0.00012500648,0.0006822583,0.0006003768,0.000074971715,0.026544496],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99365294,0.0015066083,0.0010209166,0.0013864579,0.0011458303,0.0012872326],"domain_scores_gemma":[0.99597985,0.00056676177,0.0010261643,0.0010146516,0.0006741947,0.000738353],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001028225,0.0008954548,0.00077234616,0.0005856906,0.021468177,0.00027952393,0.0016700147,0.0004761477,0.00024499596],"category_scores_gemma":[0.00023206657,0.001034681,0.00060483074,0.00073462987,0.0007159157,0.00068349735,0.00088464376,0.001219523,0.000067938316],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0008977802,0.0032853337,0.2536169,0.0011892024,0.0011507327,0.0025009203,0.41443792,0.03993716,0.034385096,0.23662236,0.0014714875,0.0105051305],"study_design_scores_gemma":[0.0023932152,0.00046293516,0.73653835,0.0017894252,0.00065024855,0.0011661552,0.14122182,0.08329623,0.0073011843,0.0033139705,0.020308368,0.0015581201],"about_ca_topic_score_codex":0.5180637,"about_ca_topic_score_gemma":0.14564379,"teacher_disagreement_score":0.48292145,"about_ca_system_score_codex":0.0108356,"about_ca_system_score_gemma":0.014358312,"threshold_uncertainty_score":0.99921036},"labels":[],"label_agreement":null},{"id":"W7084159128","doi":"10.5194/egusphere-2025-1572-ac3","title":"Reply on RC3","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Multimodal Machine Learning Applications","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 du Québec à Rimouski; Center for Northern Studies; Nordic Life Science Pipeline (Canada); Université Laval","funders":"","keywords":"Context (archaeology); Snow; Tropical cyclone forecast model; Weather forecasting; Anticipation (artificial intelligence); Hazard; Global Forecast System; Christian ministry","score_opus":0.02589560190014495,"score_gpt":0.34924923993360124,"score_spread":0.3233536380334563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084159128","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":[1.504652e-7,0.002244099,0.108000256,0.45808756,0.00094131735,0.00039812707,0.000015027118,0.00052061887,0.42979285],"genre_scores_gemma":[0.000027348313,0.0007565802,0.042935055,0.11341563,0.0001641504,0.00019806848,0.00013591566,0.000013081232,0.8423542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981305,0.00009108099,0.00031754907,0.0008327802,0.00040891836,0.00021916111],"domain_scores_gemma":[0.9968232,0.00029282426,0.00016376605,0.0024916597,0.00015462315,0.00007394086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035877852,0.00025418657,0.00037780072,0.00016513036,0.00010044315,0.000105267674,0.0023108912,0.00011768366,0.00039043813],"category_scores_gemma":[0.0003869314,0.00021282352,0.00015827102,0.00054635614,0.000017499679,0.000050832787,0.0005453128,0.0007122895,0.0018363444],"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":[1.7462791e-7,0.000022277016,0.0000018517446,0.0003537611,0.000009814699,0.000001290966,0.0000035478895,0.00001742284,2.566585e-7,0.05801754,0.8595628,0.08200927],"study_design_scores_gemma":[0.000047308928,0.00002185555,0.00012529729,0.0013007766,0.0000147087885,0.0000021253666,1.0609889e-7,0.0053628376,0.0000047429244,0.0009290469,0.99198943,0.00020174627],"about_ca_topic_score_codex":0.0012716028,"about_ca_topic_score_gemma":0.000013225205,"teacher_disagreement_score":0.41256133,"about_ca_system_score_codex":0.00006973112,"about_ca_system_score_gemma":0.00024252791,"threshold_uncertainty_score":0.9989408},"labels":[],"label_agreement":null},{"id":"W7085121138","doi":"10.1109/raiic65850.2025.11170191","title":"Application of Vision-Language Models to Pedestrian Behavior Prediction and Scene Understanding in Autonomous Driving","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 Toronto","funders":"","keywords":"Pedestrian; Metric (unit); Perception; Trajectory; Key (lock); Advanced driver assistance systems","score_opus":0.01962526538052656,"score_gpt":0.30733318071728566,"score_spread":0.2877079153367591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7085121138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25134006,0.0000134812435,0.7462702,0.00064789795,0.000021325617,0.00035941222,0.0000011192434,0.00009777031,0.0012487335],"genre_scores_gemma":[0.93862087,0.0000021849394,0.061165042,0.00004588399,0.0000056916892,0.000106911095,0.0000026277746,0.0000040401455,0.000046776233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992209,0.000029319359,0.00022332645,0.00030878064,0.00010226839,0.000115426876],"domain_scores_gemma":[0.99945104,0.00007924294,0.000051251813,0.00034771688,0.000022445436,0.00004831208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022374227,0.00007306748,0.00010318258,0.00030004498,0.00007154846,0.00005384142,0.00025342076,0.00004377293,0.000001784911],"category_scores_gemma":[0.00001981209,0.000075953634,0.00001521374,0.00058005034,0.0000178339,0.0002211714,0.0001767797,0.00009017957,0.000001919407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007923109,0.0002851569,0.16885307,0.000055181492,0.000009813358,0.00000140244,0.0037447135,0.055142313,0.031909827,0.49387282,0.00003885857,0.24607891],"study_design_scores_gemma":[0.00016858996,0.000020657382,0.18919963,0.000024402138,0.000003873872,8.784524e-7,0.00013398753,0.8068459,0.00029677068,0.003248497,0.000006784013,0.000050053597],"about_ca_topic_score_codex":0.0015745383,"about_ca_topic_score_gemma":0.00023159523,"teacher_disagreement_score":0.75170356,"about_ca_system_score_codex":0.00013966911,"about_ca_system_score_gemma":0.000038774935,"threshold_uncertainty_score":0.30972993},"labels":[],"label_agreement":null},{"id":"W7087312099","doi":"10.1007/978-3-032-07845-2_18","title":"Test-Time Adaptation of Medical Vision-Language Models","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","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":"École de Technologie Supérieure","funders":"","keywords":"Adaptation (eye); Benchmark (surveying); Domain adaptation; Downstream (manufacturing); Mutual information; Code (set theory); Class (philosophy); Transfer of learning","score_opus":0.011620095933489439,"score_gpt":0.2857211316042886,"score_spread":0.27410103567079913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7087312099","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":[0.00012085644,0.00022714827,0.99170345,0.0030488677,0.00030873046,0.00035172622,0.000010232671,0.00018327395,0.0040456885],"genre_scores_gemma":[0.34747446,0.000031681015,0.6504289,0.0011450475,0.00017264557,0.00001691521,0.000012518008,0.000025639123,0.00069219153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99568015,0.00004581265,0.00063211145,0.0012382938,0.002014012,0.00038963143],"domain_scores_gemma":[0.9958353,0.0018319946,0.0003461825,0.0015421498,0.00027057034,0.00017382564],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012932983,0.000373688,0.0004946902,0.00088747643,0.00015964531,0.00020350958,0.0047476236,0.0004099784,0.000057606572],"category_scores_gemma":[0.00056778704,0.0003483922,0.0001191271,0.0007885194,0.00052487786,0.00043229174,0.0017399897,0.00092830544,0.00004893115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020574444,0.000044810375,0.000010715652,0.000042863987,0.0000048098386,0.00001633533,0.0010644248,0.18390238,0.00015835522,0.042211127,0.000020835974,0.77252126],"study_design_scores_gemma":[0.00018698309,0.00008723155,0.000087539884,0.00045667557,0.000005917627,0.000015355721,2.1133938e-7,0.94669527,0.0003067977,0.051775858,0.00009870312,0.00028347835],"about_ca_topic_score_codex":0.00032867107,"about_ca_topic_score_gemma":0.000041642346,"teacher_disagreement_score":0.7722378,"about_ca_system_score_codex":0.0001511467,"about_ca_system_score_gemma":0.0010858669,"threshold_uncertainty_score":0.9998968},"labels":[],"label_agreement":null},{"id":"W7093322906","doi":"10.1145/3746276.3760469","title":"TemporalCook: Benchmarking Temporal and Procedural Reasoning in Multimodal Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Benchmark (surveying); Benchmarking; Question answering; Inference; Task (project management); Language model; Code (set theory); Visual reasoning","score_opus":0.009377410152993777,"score_gpt":0.29137206559817114,"score_spread":0.2819946554451774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7093322906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47791162,0.0013237573,0.4958557,0.0052632834,0.00026513648,0.0012577295,0.0000142317185,0.00033850194,0.017770061],"genre_scores_gemma":[0.8802488,0.000032143897,0.11698287,0.0011517389,0.00008207088,0.00011630529,0.000021403639,0.000027753484,0.0013369381],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958363,0.00027466228,0.0009131354,0.0015225523,0.00040516598,0.0010481535],"domain_scores_gemma":[0.9981586,0.00023234,0.0002679126,0.0009845351,0.00012245888,0.0002341547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012979395,0.0005451043,0.0005848022,0.0007210873,0.0005182128,0.00060742244,0.0010492122,0.0002932628,0.00006973107],"category_scores_gemma":[0.00019617745,0.0005635289,0.00011459702,0.0017891332,0.00013977937,0.0011844456,0.0013819808,0.0010150478,0.000021454685],"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":[0.000077407254,0.00088821905,0.47953662,0.0005139163,0.00009317249,0.00008378394,0.018023374,0.01968353,0.00061858847,0.33648625,0.0007911778,0.14320396],"study_design_scores_gemma":[0.0015453096,0.000050911643,0.08253302,0.0004886911,0.00001662022,0.000013235326,0.00057650387,0.9118672,0.00008094788,0.0020602592,0.00027526906,0.0004920128],"about_ca_topic_score_codex":0.012279477,"about_ca_topic_score_gemma":0.0014676139,"teacher_disagreement_score":0.8921837,"about_ca_system_score_codex":0.00019353065,"about_ca_system_score_gemma":0.00045515195,"threshold_uncertainty_score":0.9996816},"labels":[],"label_agreement":null},{"id":"W7103154917","doi":"10.48550/arxiv.2510.25801","title":"Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start","year":2025,"lang":"","type":"preprint","venue":"Open MIND","topic":"Multimodal Machine Learning Applications","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":"Generalization; Reinforcement learning; Task (project management); Task analysis; Verifiable secret sharing; Memorization","score_opus":0.0642883970235779,"score_gpt":0.3301872525248995,"score_spread":0.2658988555013216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103154917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12892272,0.00030795851,0.83323133,0.0015973832,0.0015024645,0.0085076755,0.00021622493,0.0002003213,0.025513945],"genre_scores_gemma":[0.5306039,0.000043510645,0.46419433,0.0000936677,0.00016128561,0.0009129775,0.00019207041,0.000065641856,0.003732633],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98787856,0.0013564088,0.0023959707,0.0052641793,0.0014212611,0.0016836331],"domain_scores_gemma":[0.98956114,0.002166441,0.0019605977,0.004383088,0.0011110962,0.00081764633],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","insufficient_payload"],"category_scores_codex":[0.0035594455,0.0017266519,0.002151138,0.00078858994,0.002055957,0.0046903146,0.011852483,0.0011397197,0.0046399734],"category_scores_gemma":[0.00082039955,0.0019718828,0.00063035113,0.001721838,0.00027364877,0.000780503,0.012148281,0.005326738,0.0030352562],"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":[0.00017891858,0.001399,0.012286608,0.00030741654,0.00056585786,0.000036299563,0.0041346867,0.64107096,0.0010019422,0.0005883687,0.0000838993,0.33834603],"study_design_scores_gemma":[0.0025501556,0.00023442174,0.0058604814,0.001049926,0.0003513414,0.000005960382,0.00008560819,0.9211128,0.0032948095,0.00019936306,0.063476264,0.0017788663],"about_ca_topic_score_codex":0.005243194,"about_ca_topic_score_gemma":0.00049014227,"teacher_disagreement_score":0.40168115,"about_ca_system_score_codex":0.0010395128,"about_ca_system_score_gemma":0.0041970382,"threshold_uncertainty_score":0.99954796},"labels":[],"label_agreement":null},{"id":"W7103204388","doi":"","title":"Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","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":"Generalization; Reinforcement learning; Task (project management); Task analysis; Verifiable secret sharing; Memorization","score_opus":0.036303223380937735,"score_gpt":0.28117547225993805,"score_spread":0.24487224887900033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103204388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5558855,0.0004965705,0.4370067,0.00186728,0.00077497755,0.0011925338,0.000009840047,0.0011724433,0.0015941515],"genre_scores_gemma":[0.9327613,0.00007829245,0.064003,0.00076134375,0.00023897347,0.0004373431,0.000036801237,0.00009488189,0.0015880642],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925026,0.0007596834,0.0015843953,0.0026329157,0.0009142328,0.0016061349],"domain_scores_gemma":[0.99376464,0.0016520359,0.0007934901,0.0024702712,0.0007601547,0.00055940455],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015388789,0.0010609089,0.0011217763,0.00072622456,0.002000302,0.0006803741,0.00299819,0.00054565485,0.00044296496],"category_scores_gemma":[0.00097135874,0.0011867464,0.0004728633,0.0027743967,0.00030441806,0.00064273574,0.0012087988,0.0026130897,0.0016042639],"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":[0.00008196556,0.000921914,0.87687945,0.0002620265,0.00031930444,0.00002304889,0.0010976591,0.09242718,0.0059952983,0.0035862972,0.00015660611,0.018249251],"study_design_scores_gemma":[0.0018058175,0.00018307687,0.3189562,0.0002695766,0.00016367313,0.0000023780115,0.000044532386,0.6664221,0.003318895,0.00012545542,0.007963992,0.0007442911],"about_ca_topic_score_codex":0.0018147837,"about_ca_topic_score_gemma":0.00014052622,"teacher_disagreement_score":0.57399493,"about_ca_system_score_codex":0.00067362963,"about_ca_system_score_gemma":0.0012231575,"threshold_uncertainty_score":0.9996879},"labels":[],"label_agreement":null},{"id":"W7103328463","doi":"","title":"ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering","year":2016,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Question answering; Convolutional neural network; Focus (optics); Feature (linguistics); Natural language; Task (project management); Benchmark (surveying); Image (mathematics); Deep learning","score_opus":0.01630660674486519,"score_gpt":0.31374695009455467,"score_spread":0.2974403433496895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103328463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13743918,0.00000558821,0.8581227,0.0035056225,0.00019582812,0.00023085727,0.0000026083146,0.00038392522,0.00011366611],"genre_scores_gemma":[0.80593073,2.9938133e-7,0.19328,0.00025698997,0.00023146636,0.000098172604,0.000019499159,0.000008479375,0.00017434938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989645,0.00008186083,0.00017533453,0.00036765277,0.0001590249,0.00025166167],"domain_scores_gemma":[0.9992352,0.00019492349,0.000075070944,0.00028741403,0.000113715665,0.00009367231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035770732,0.00010259189,0.000083326966,0.00005090087,0.00023035325,0.000077274395,0.0003233802,0.000049016053,0.000035489877],"category_scores_gemma":[0.000047811,0.000077757366,0.000055465058,0.00015335274,0.000034048015,0.0004998043,0.00005061393,0.00005629349,0.00004854784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004936203,0.00023139466,0.0940362,0.00001962324,0.000016826458,9.009932e-7,0.000033844924,0.051269073,0.037928082,0.57889783,0.0010692353,0.23644762],"study_design_scores_gemma":[0.00036850636,0.00009521267,0.22132637,0.000011737708,0.000002666479,0.0000017341897,8.215525e-7,0.77538407,0.00012203154,0.0019401078,0.00064137584,0.00010536226],"about_ca_topic_score_codex":0.00012351487,"about_ca_topic_score_gemma":0.000027580681,"teacher_disagreement_score":0.724115,"about_ca_system_score_codex":0.000054228487,"about_ca_system_score_gemma":0.000038653965,"threshold_uncertainty_score":0.31708533},"labels":[],"label_agreement":null},{"id":"W7103895521","doi":"10.1109/tase.2025.3628670","title":"Interactive Semantics-Enhanced Vision-Language Model-Driven Hypergraph Reasoning for Robotic Decision-Making in Proactive Human–Robot Collaboration","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Multimodal Machine Learning Applications","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":"National Natural Science Foundation of China","keywords":"Hypergraph; Semantics (computer science); Graph; Process (computing); Construct (python library); Task (project management); Robot; Exploit","score_opus":0.007262317151653083,"score_gpt":0.31891074830319144,"score_spread":0.31164843115153834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103895521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17325127,0.000040182073,0.82410824,0.00045274882,0.0005871453,0.0012349351,0.000008314809,0.00023316554,0.00008401679],"genre_scores_gemma":[0.8391965,0.000015086294,0.16025333,0.000078536956,0.000017477249,0.0003873431,0.0000017656477,0.000022872022,0.000027070077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968301,0.000059320726,0.00073451514,0.0011510437,0.00066087267,0.0005641413],"domain_scores_gemma":[0.9975826,0.00074797065,0.00024501103,0.0006061384,0.0006860148,0.00013227017],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010076667,0.00039229382,0.00040992908,0.0022783144,0.0012206495,0.0009676453,0.0006919292,0.0001651225,0.0000066549496],"category_scores_gemma":[0.00034340608,0.0004421383,0.00009434579,0.00501863,0.00019328207,0.0026245974,0.000023302153,0.0005665796,0.0000069801567],"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":[0.000028607297,0.00014086995,0.0000068019203,0.000068440335,0.000024698173,8.8756883e-7,0.006034742,0.8619649,0.06766782,0.0017625426,0.000002751083,0.06229693],"study_design_scores_gemma":[0.0007115628,0.00010711963,0.003598704,0.0014628367,0.000044493758,0.000004140777,0.0005859375,0.9785926,0.014210027,0.00030443506,0.0000020185248,0.00037614582],"about_ca_topic_score_codex":0.000048132166,"about_ca_topic_score_gemma":0.00004470991,"teacher_disagreement_score":0.66594523,"about_ca_system_score_codex":0.000759393,"about_ca_system_score_gemma":0.0005280686,"threshold_uncertainty_score":0.99980307},"labels":[],"label_agreement":null},{"id":"W7106015545","doi":"10.7939/83017","title":"Development of a Question Answering System Over Building Codes using Retrieval Augmented Generation","year":2025,"lang":"en","type":"dissertation","venue":"University of Alberta Library","topic":"Multimodal Machine Learning Applications","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":"Metric (unit); Rank (graph theory); Code (set theory); Adaptation (eye); Scheme (mathematics); Question answering; Key (lock); Data retrieval","score_opus":0.01316818907790685,"score_gpt":0.24095319270402268,"score_spread":0.22778500362611584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106015545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8775974,0.000049646467,0.1195504,0.00003520933,0.00018674247,0.00022371915,0.0000035421897,0.000092181224,0.0022611832],"genre_scores_gemma":[0.66482824,0.0000067758865,0.33290857,0.0000046559585,0.000021950962,3.0486603e-7,0.00044167158,0.000012277741,0.0017755316],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989082,0.00008296166,0.00029402613,0.00036183442,0.00022958824,0.00012339395],"domain_scores_gemma":[0.99897486,0.000089908055,0.0004796613,0.00033324762,0.00007651577,0.000045835965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099655896,0.00016533915,0.00027468737,0.0003854857,0.00021464007,0.000038953272,0.00061214494,0.00017432324,0.000016593021],"category_scores_gemma":[0.000021731916,0.00021648454,0.00007672327,0.0004822699,0.0000159901,0.00064977224,0.00017654647,0.00016194674,0.0000016542441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006188503,0.0005110229,0.0094565805,0.007383144,0.0010883637,0.000021313845,0.060365114,0.03254996,0.4885484,0.37154943,0.00057790143,0.027329898],"study_design_scores_gemma":[0.00049998914,0.000025759975,0.015295765,0.002023168,0.0000989454,0.0000018754846,0.0008872317,0.91542923,0.063956924,0.00003465749,0.001351958,0.00039448048],"about_ca_topic_score_codex":0.0020311177,"about_ca_topic_score_gemma":0.00021272,"teacher_disagreement_score":0.8828793,"about_ca_system_score_codex":0.00012306523,"about_ca_system_score_gemma":0.00050111435,"threshold_uncertainty_score":0.8827983},"labels":[],"label_agreement":null},{"id":"W7115568583","doi":"10.1109/cvprw63382.2024.11301672","title":"Retraction Notice: T2VBench: Benchmarking Temporal Dynamics for Text-to-Video Generation","year":2024,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Benchmarking; Benchmark (surveying); Dynamics (music); Generative grammar; Temporal database; Temporal scales","score_opus":0.032084276902560584,"score_gpt":0.3291478281031487,"score_spread":0.2970635512005881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115568583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012061897,0.00022753897,0.95270073,0.022437265,0.007264636,0.0018594431,0.000051088802,0.0006701449,0.0027272478],"genre_scores_gemma":[0.7024659,0.00001325982,0.29133624,0.000477295,0.002442728,0.00027971226,0.00021914332,0.000056516525,0.0027092223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99577504,0.00016369586,0.0009214867,0.0017609774,0.00066087674,0.0007179031],"domain_scores_gemma":[0.99731123,0.00064494275,0.00020150561,0.0011177091,0.0003754325,0.00034920155],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015893262,0.0004811402,0.0003434078,0.0005874098,0.00086772384,0.0025952659,0.00092999346,0.00047492905,0.0003455245],"category_scores_gemma":[0.00034424762,0.00050737476,0.00026836156,0.0018628513,0.000059681457,0.001304277,0.00034170246,0.000986736,0.0006331174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001467044,0.00014103367,0.00084455515,0.0002366672,0.00007238144,0.0000057972757,0.0011753411,0.04518799,0.0025056577,0.1751339,0.015608717,0.7590733],"study_design_scores_gemma":[0.0001893763,0.00030898888,0.0035588227,0.00013965882,0.00007285084,0.000024823237,0.000033895958,0.9579786,0.00022409782,0.0010106541,0.03587588,0.00058233243],"about_ca_topic_score_codex":0.0015062033,"about_ca_topic_score_gemma":0.0013000217,"teacher_disagreement_score":0.91279066,"about_ca_system_score_codex":0.00078517245,"about_ca_system_score_gemma":0.0004268738,"threshold_uncertainty_score":0.9997378},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W7116113878","doi":"10.3103/s1060992x25601654","title":"Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding","year":2025,"lang":"en","type":"article","venue":"Optical Memory and Neural Networks","topic":"Multimodal Machine Learning Applications","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":"Key (lock); Spatial analysis; Visualization; Virtual reality; Data collection","score_opus":0.02165555263727299,"score_gpt":0.25402088083715496,"score_spread":0.23236532819988198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116113878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050715353,0.00010487293,0.9432247,0.0024169947,0.00017018584,0.00023377142,4.936777e-7,0.0001793371,0.002954237],"genre_scores_gemma":[0.9810954,0.000009632016,0.018152392,0.00049819215,0.000105569525,0.00002688473,0.0000033988279,0.000011171617,0.00009736876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863297,0.000084790285,0.00024046996,0.0005134319,0.00017402487,0.0003542988],"domain_scores_gemma":[0.9990166,0.00037762482,0.00006484516,0.00036223058,0.0000305756,0.00014815379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021801952,0.00019541147,0.0002278172,0.000074036645,0.0003493735,0.00022650306,0.00035437837,0.00010507668,0.000007450298],"category_scores_gemma":[0.000023345498,0.00015968118,0.00004183837,0.0003214287,0.00012359978,0.00032230857,0.00019641763,0.00046507316,0.0000016253356],"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":[0.00014862504,0.00012707949,0.003952847,0.00006244217,0.000057969548,0.00004971479,0.00039767628,0.5666414,0.00034333015,0.28689012,0.000069771675,0.14125903],"study_design_scores_gemma":[0.00038398613,0.00009796264,0.0015077622,0.000061393286,0.00001784473,0.000018833716,0.00003504645,0.9914102,0.00018090016,0.006088405,0.000013208596,0.00018447453],"about_ca_topic_score_codex":0.00036921815,"about_ca_topic_score_gemma":0.00033978606,"teacher_disagreement_score":0.93038005,"about_ca_system_score_codex":0.000044995715,"about_ca_system_score_gemma":0.00003452125,"threshold_uncertainty_score":0.6511609},"labels":[],"label_agreement":null},{"id":"W7116291721","doi":"10.2139/ssrn.5935496","title":"AI-Generated Visual Content in Education: A Systematic Review of the Past Decade","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Multimodal Machine Learning Applications","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 for Christian Studies; University of Toronto","funders":"","keywords":"Content (measure theory); Photography; Content analysis; Visual methods; Visualization","score_opus":0.014687450165638914,"score_gpt":0.3194863875845943,"score_spread":0.30479893741895536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116291721","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":[0.019731317,0.7197684,0.15662473,0.08720766,0.003804994,0.01171534,0.000020215213,0.000096149946,0.00103117],"genre_scores_gemma":[0.80858356,0.17723565,0.0011667684,0.006423797,0.0004979223,0.0011317445,0.000018218405,0.000052668795,0.004889696],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9898578,0.0028850469,0.0030717533,0.0009140366,0.0010324555,0.002238923],"domain_scores_gemma":[0.9931926,0.00030921705,0.0030821185,0.0018419942,0.0014120198,0.00016205339],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007677822,0.000646387,0.0016502037,0.00047422957,0.00042951794,0.00025683118,0.0048351227,0.0003145033,0.000025522659],"category_scores_gemma":[0.0010693689,0.00047850696,0.0007314951,0.002094606,0.00013556505,0.00016546895,0.0013512286,0.010674383,0.000030351383],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000038655293,0.0022021534,0.0059279823,0.50838935,0.0014119043,0.000002285134,0.0011492476,0.0041990937,0.00021640775,0.4543201,0.0005092979,0.021633493],"study_design_scores_gemma":[0.0011367702,0.00030363924,0.005446798,0.87839955,0.0014394029,0.0011381125,0.0007446149,0.06330761,0.00010700564,0.04646424,0.00039395815,0.0011182994],"about_ca_topic_score_codex":0.0013294095,"about_ca_topic_score_gemma":0.00067812216,"teacher_disagreement_score":0.7888522,"about_ca_system_score_codex":0.003935846,"about_ca_system_score_gemma":0.039074026,"threshold_uncertainty_score":0.9998879},"labels":[],"label_agreement":null},{"id":"W7116666449","doi":"10.1007/978-3-032-13509-4_25","title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"Multimodal Machine Learning Applications","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":"Vector Institute","funders":"","keywords":"Benchmark (surveying); Generalization; Key (lock); Code (set theory); Language model; Computational linguistics","score_opus":0.016982273114531085,"score_gpt":0.30576615892638775,"score_spread":0.28878388581185666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116666449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024208462,0.0011939552,0.8682988,0.001619922,0.0006245733,0.0012381756,0.000015280135,0.00028548195,0.1266996],"genre_scores_gemma":[0.92252016,0.000043915166,0.071358375,0.0015493971,0.0022243618,0.00025545465,0.00038975134,0.00010450022,0.0015541046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99616086,0.00025810557,0.0007096277,0.0013236448,0.0009276713,0.0006200818],"domain_scores_gemma":[0.99680716,0.0011398927,0.00049411925,0.0010306288,0.0004217982,0.00010640453],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0010490805,0.00069768727,0.00071495643,0.00043311124,0.00046550098,0.00030587433,0.0015092292,0.0014824792,0.00016153402],"category_scores_gemma":[0.00027767927,0.0007623902,0.0003779345,0.00045443408,0.00014617677,0.00017039267,0.00040126598,0.002438193,0.000019905761],"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":[0.000016492373,0.000030626896,0.00005052226,0.00002213901,0.000036042355,0.000004465981,0.00035006247,0.6182975,0.0000013965525,0.068195075,0.00024754502,0.31274813],"study_design_scores_gemma":[0.00060941826,0.000024910489,0.00022325873,0.00020878002,0.00006217372,8.252338e-7,5.7541786e-7,0.7949375,0.0000022006086,0.20122162,0.0021871,0.0005216622],"about_ca_topic_score_codex":0.00029004758,"about_ca_topic_score_gemma":0.0002853618,"teacher_disagreement_score":0.9224959,"about_ca_system_score_codex":0.0006046259,"about_ca_system_score_gemma":0.0006279156,"threshold_uncertainty_score":0.9998632},"labels":[],"label_agreement":null},{"id":"W7116933240","doi":"10.1109/etncc66224.2025.11299754","title":"Automatic Image Tagging and Captioning Using Transformer-Based Vision-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Trinity College","funders":"","keywords":"Closed captioning; Transformer; Encoder; Feature extraction; Natural language; Visualization","score_opus":0.012700024091263288,"score_gpt":0.32299977244502204,"score_spread":0.31029974835375873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116933240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24930651,0.0003766642,0.74088025,0.0036244902,0.00012701411,0.0005443924,0.0000045077613,0.00037264221,0.00476351],"genre_scores_gemma":[0.65716475,0.0000071901854,0.3419606,0.00065585715,0.000019191632,0.000024749253,0.0000031403379,0.000018815726,0.00014571776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714,0.0002076737,0.0007024109,0.0009678875,0.00037745584,0.0006045633],"domain_scores_gemma":[0.9982206,0.00039263692,0.0001833666,0.0008772869,0.00013121939,0.00019485275],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007100901,0.0004061431,0.0004127294,0.00056695804,0.0010681056,0.0010697059,0.0007030228,0.00015038288,0.00018840862],"category_scores_gemma":[0.00007419779,0.00042106578,0.00013393037,0.0012301215,0.00022254203,0.0012005096,0.00018242068,0.00050563144,0.0000265242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009970947,0.00028174592,0.00032450687,0.00069407537,0.000080558,0.00001465353,0.006108874,0.33576146,0.054393318,0.05204352,0.00004542939,0.5502419],"study_design_scores_gemma":[0.00083833357,0.00003914992,0.0014260851,0.0005873684,0.00007917205,0.000010327417,0.0002560251,0.9927983,0.0015278276,0.0020226282,0.000021920376,0.00039282505],"about_ca_topic_score_codex":0.0030867977,"about_ca_topic_score_gemma":0.000034008146,"teacher_disagreement_score":0.6570369,"about_ca_system_score_codex":0.00017127226,"about_ca_system_score_gemma":0.0004303595,"threshold_uncertainty_score":0.9999673},"labels":[],"label_agreement":null},{"id":"W7117142650","doi":"10.5281/zenodo.17646067","title":"AMVICC Image Results & Evaluations","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Multimodal Machine Learning Applications","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":"Centennial College","funders":"","keywords":"Image (mathematics); Relation (database); Documentation; Benchmark (surveying); Image processing; Test (biology)","score_opus":0.03376656010708667,"score_gpt":0.3214794476973359,"score_spread":0.2877128875902492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117142650","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":[0.0030008296,0.00022976937,0.476227,0.025180535,0.00046969243,0.0015490674,0.0005523476,0.0022403,0.4905505],"genre_scores_gemma":[0.97363,0.0001706927,0.013964765,0.0007274353,0.00026652488,3.7120532e-7,0.0020481385,0.0014533906,0.007738695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994355,0.0015329943,0.0009132745,0.0015002228,0.00086839485,0.00083010545],"domain_scores_gemma":[0.99421644,0.00018857919,0.00037550429,0.0024795488,0.002393685,0.00034626192],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029369092,0.00037482934,0.0003244025,0.00085135456,0.008295529,0.004542743,0.0050037326,0.00017709302,0.006259318],"category_scores_gemma":[0.004896512,0.00044723638,0.00015931015,0.003579778,0.0004925157,0.0007985985,0.005381733,0.0010058905,0.033307683],"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":[0.00009837066,0.00054172124,0.0000041602652,0.00012128948,0.00012396074,0.000009414088,0.0028412433,0.0012525198,0.0056355954,0.091644414,0.26562375,0.63210356],"study_design_scores_gemma":[0.0013944417,0.00020306173,0.0060524438,0.00013249023,0.000058490827,0.00004016606,0.0001394351,0.14714949,0.00042622967,0.0019338485,0.84209627,0.00037361923],"about_ca_topic_score_codex":0.00017500523,"about_ca_topic_score_gemma":8.8170026e-7,"teacher_disagreement_score":0.97062916,"about_ca_system_score_codex":0.0004791723,"about_ca_system_score_gemma":0.00004525504,"threshold_uncertainty_score":0.99979794},"labels":[],"label_agreement":null},{"id":"W7117145747","doi":"10.5281/zenodo.17646068","title":"AMVICC Image Results & Evaluations","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Multimodal Machine Learning Applications","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":"Centennial College","funders":"","keywords":"Image (mathematics); Relation (database); Documentation; Benchmark (surveying); Image processing; Test (biology)","score_opus":0.03376656010708667,"score_gpt":0.3214794476973359,"score_spread":0.2877128875902492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117145747","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":[0.0030008296,0.00022976937,0.476227,0.025180535,0.00046969243,0.0015490674,0.0005523476,0.0022403,0.4905505],"genre_scores_gemma":[0.97363,0.0001706927,0.013964765,0.0007274353,0.00026652488,3.7120532e-7,0.0020481385,0.0014533906,0.007738695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994355,0.0015329943,0.0009132745,0.0015002228,0.00086839485,0.00083010545],"domain_scores_gemma":[0.99421644,0.00018857919,0.00037550429,0.0024795488,0.002393685,0.00034626192],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029369092,0.00037482934,0.0003244025,0.00085135456,0.008295529,0.004542743,0.0050037326,0.00017709302,0.006259318],"category_scores_gemma":[0.004896512,0.00044723638,0.00015931015,0.003579778,0.0004925157,0.0007985985,0.005381733,0.0010058905,0.033307683],"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":[0.00009837066,0.00054172124,0.0000041602652,0.00012128948,0.00012396074,0.000009414088,0.0028412433,0.0012525198,0.0056355954,0.091644414,0.26562375,0.63210356],"study_design_scores_gemma":[0.0013944417,0.00020306173,0.0060524438,0.00013249023,0.000058490827,0.00004016606,0.0001394351,0.14714949,0.00042622967,0.0019338485,0.84209627,0.00037361923],"about_ca_topic_score_codex":0.00017500523,"about_ca_topic_score_gemma":8.8170026e-7,"teacher_disagreement_score":0.97062916,"about_ca_system_score_codex":0.0004791723,"about_ca_system_score_gemma":0.00004525504,"threshold_uncertainty_score":0.99979794},"labels":[],"label_agreement":null},{"id":"W7117239628","doi":"10.2139/ssrn.5964393","title":"ELSSA: Explainable Large Language Model-Based Decision Support for Public Transit Incident Management","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Multimodal Machine Learning Applications","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":"Supervisor; Context (archaeology); Incident management; Ontology; Graph; Incident report; Pipeline (software); Decision support system","score_opus":0.012841728711211984,"score_gpt":0.3009893901624156,"score_spread":0.28814766145120363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117239628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010054993,0.0015413449,0.97673285,0.0060820384,0.0007352298,0.0028562718,0.0001018992,0.0002294126,0.0016659334],"genre_scores_gemma":[0.8577025,0.002227922,0.12993816,0.0006905855,0.00029569675,0.00095691695,0.00016492468,0.00009314767,0.007930145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98680264,0.0004151742,0.0018074795,0.002107181,0.001518894,0.0073486594],"domain_scores_gemma":[0.994666,0.0004340326,0.0011751694,0.0024201954,0.0007828683,0.0005217503],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01109793,0.0010610234,0.0010416004,0.0014515709,0.0019686029,0.0012828463,0.0057042316,0.0005892432,0.00010541538],"category_scores_gemma":[0.00023375193,0.00111979,0.0011329965,0.0010915437,0.000081564125,0.0006631506,0.0015799743,0.007844212,0.000082545965],"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":true,"study_design_scores_codex":[0.00020953428,0.00094308716,0.00029023516,0.00036054186,0.0006155126,0.000023640341,0.001032474,0.2923728,0.000037645365,0.4414248,0.00027884124,0.26241094],"study_design_scores_gemma":[0.0036243675,0.00036922604,0.0003618941,0.00026831165,0.00028745164,0.00009487045,0.0006915201,0.8163565,0.00005303739,0.17096615,0.006087817,0.0008388875],"about_ca_topic_score_codex":0.00018480635,"about_ca_topic_score_gemma":0.0009414368,"teacher_disagreement_score":0.8476475,"about_ca_system_score_codex":0.0058448347,"about_ca_system_score_gemma":0.015538908,"threshold_uncertainty_score":0.9997539},"labels":[],"label_agreement":null},{"id":"W7117850735","doi":"","title":"CountGD++: Generalized Prompting for Open-World Counting","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","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":"Geomechanica (Canada)","funders":"Engineering and Physical Sciences Research Council; University of Oxford","keywords":"Object (grammar); Generalization; Flexibility (engineering); Visualization; Object detection; Annotation; Visual Objects; Code (set theory)","score_opus":0.08297339521387051,"score_gpt":0.25077044132108456,"score_spread":0.16779704610721405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117850735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1120105,0.00013127025,0.8654003,0.0017517376,0.00069264515,0.002336425,0.000029383651,0.0002806488,0.01736705],"genre_scores_gemma":[0.9397015,0.00003251089,0.02376437,0.00086392084,0.00011841861,0.000021049964,0.00001812262,0.000034745055,0.035445347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624276,0.00026327424,0.0005384941,0.001961254,0.000120346,0.0008738659],"domain_scores_gemma":[0.9963404,0.0006845352,0.00055365823,0.0016170347,0.0005960812,0.00020828456],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012242902,0.0004673333,0.0005679889,0.0005499127,0.0016935179,0.0010892883,0.0046566734,0.00017615038,0.00009344532],"category_scores_gemma":[0.00026607155,0.0005995556,0.00024819304,0.0036508252,0.0002135525,0.0011764449,0.0024462068,0.00053367537,0.00013185732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010477633,0.00023597683,0.016198836,0.00015797929,0.00016121581,0.000016451888,0.00019434761,0.11015031,0.0002811889,0.8648909,0.0017960408,0.005812011],"study_design_scores_gemma":[0.0027726502,0.000055640125,0.005589126,0.00021739509,0.00016793083,0.0000017204219,0.000054213917,0.93984103,0.0001905637,0.021188896,0.029366158,0.0005546645],"about_ca_topic_score_codex":0.002524144,"about_ca_topic_score_gemma":0.00033970023,"teacher_disagreement_score":0.84370196,"about_ca_system_score_codex":0.000462263,"about_ca_system_score_gemma":0.0008241647,"threshold_uncertainty_score":0.99994767},"labels":[],"label_agreement":null},{"id":"W7124161218","doi":"10.1109/icpads67057.2025.11323053","title":"SwiftReTaKe: Quick and Accurate Redundancy Reduction for Cloud-Edge Collaborative Video-Language Understanding","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Simon Fraser University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Cloud computing; Latency (audio); Inference; Redundancy (engineering); Software deployment; Data transmission; Overhead (engineering); Relevance (law); Process (computing)","score_opus":0.0298403845264314,"score_gpt":0.33504563952510236,"score_spread":0.30520525499867096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124161218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028032092,0.0029629192,0.93455034,0.019932104,0.0016582159,0.002372912,0.00005369882,0.00031205616,0.010125635],"genre_scores_gemma":[0.9592801,0.0002561813,0.03169769,0.00030970742,0.00027102925,0.0002844915,0.00002709284,0.000031587562,0.007842161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661833,0.00028183544,0.0007323792,0.0014028382,0.00032946182,0.0006351388],"domain_scores_gemma":[0.99724334,0.0007459477,0.00041413822,0.0008612294,0.00052104803,0.00021428418],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009702289,0.00046006238,0.00047977277,0.0004107241,0.001374074,0.0011101364,0.00068358093,0.00024119682,0.000059732003],"category_scores_gemma":[0.0007240705,0.00048146493,0.00011896821,0.002378052,0.00035024545,0.0007875,0.0004324078,0.00047531453,0.000026291551],"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":[0.00019017623,0.00018915646,0.00038567124,0.00033528137,0.00023071197,0.0000027507624,0.015544269,0.0006545124,0.006135682,0.9108311,0.011743792,0.05375688],"study_design_scores_gemma":[0.00462468,0.00056053937,0.0035920115,0.0008045789,0.00033895794,0.000033914854,0.021765487,0.9048936,0.0064707384,0.04692004,0.0086603295,0.0013351727],"about_ca_topic_score_codex":0.0004601119,"about_ca_topic_score_gemma":0.00011789511,"teacher_disagreement_score":0.93124795,"about_ca_system_score_codex":0.000509068,"about_ca_system_score_gemma":0.0007031494,"threshold_uncertainty_score":0.9999268},"labels":[],"label_agreement":null},{"id":"W7124303850","doi":"10.65109/kagr5160","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","year":2023,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Microsoft (Canada)","funders":"","keywords":"Generalization; Task (project management); Inference; Principle of compositionality; sort; Suite; Task analysis","score_opus":0.047606030914207946,"score_gpt":0.3014580807053827,"score_spread":0.25385204979117476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124303850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59828097,0.0000421404,0.38924602,0.0067600184,0.000082949584,0.0003653872,0.0000054548063,0.001019402,0.0041976483],"genre_scores_gemma":[0.94795036,0.000026809705,0.049769208,0.0002245458,0.00019693657,0.00007374989,0.00012563981,0.000037626563,0.0015951025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968308,0.00035819135,0.00043206938,0.0010522634,0.0007052376,0.00062141335],"domain_scores_gemma":[0.99807477,0.0005144627,0.00018638412,0.00082964945,0.00009581141,0.00029893353],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045188452,0.0003003858,0.00030348732,0.00025330085,0.00056009623,0.00054488814,0.00082506135,0.0001649915,0.0004398169],"category_scores_gemma":[0.00014112148,0.00028516262,0.00009070439,0.0017530761,0.00015276992,0.00036641717,0.00043318621,0.0011710112,0.0025938943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011430834,0.0005574574,0.14704798,0.00005715647,0.00028843322,0.00013660759,0.023689857,0.14544499,0.029495057,0.044839308,0.00023401473,0.6080948],"study_design_scores_gemma":[0.00042305578,0.00018111676,0.30134624,0.000058098743,0.000025926212,0.0000046086834,0.00016357716,0.69641674,0.00048128547,0.00046851143,0.00014586544,0.00028498637],"about_ca_topic_score_codex":0.0044725128,"about_ca_topic_score_gemma":0.00029878574,"teacher_disagreement_score":0.60780984,"about_ca_system_score_codex":0.00006536946,"about_ca_system_score_gemma":0.00019472546,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W7124309595","doi":"10.65109/yyrj6883","title":"OPEx: A Large Language Model-Powered Framework for Embodied Instruction Following","year":2024,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Microsoft (Canada); Université de Montréal","funders":"","keywords":"Embodied cognition; Bridge (graph theory); Natural language; Language model; Language assessment; Higher education","score_opus":0.01866547196441454,"score_gpt":0.34085330740432207,"score_spread":0.32218783543990753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124309595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028716808,0.0012462896,0.9548893,0.003897634,0.002359708,0.001234045,0.00006040763,0.0012038114,0.006392016],"genre_scores_gemma":[0.59683216,0.000011645058,0.40111804,0.0003284115,0.00026132594,0.00022790977,0.000019039391,0.000049871156,0.0011515995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966832,0.00009488984,0.0005957672,0.0013624068,0.00044640712,0.00081735215],"domain_scores_gemma":[0.99784535,0.0004716914,0.00010916214,0.0012504512,0.00008806955,0.00023529302],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008144792,0.00041904103,0.00039089588,0.00030801643,0.0006268403,0.0013972529,0.0011412093,0.00035890765,0.00016264962],"category_scores_gemma":[0.0003556773,0.000417603,0.00052636006,0.0011082486,0.000039753213,0.00083132123,0.00051614706,0.0008399312,0.00037718468],"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":[0.000012098112,0.00009473706,0.00006605477,0.00015321745,0.00012914171,0.000009308929,0.007260625,0.0043883473,0.00056233077,0.8865938,0.00030612963,0.100424215],"study_design_scores_gemma":[0.00052285596,0.00006919447,0.000108072156,0.0002635177,0.00007736144,0.000008752744,0.00022754238,0.90122724,0.00024002635,0.09467531,0.0021407513,0.0004393576],"about_ca_topic_score_codex":0.00024033338,"about_ca_topic_score_gemma":0.000028996055,"teacher_disagreement_score":0.8968389,"about_ca_system_score_codex":0.00017301326,"about_ca_system_score_gemma":0.00029438914,"threshold_uncertainty_score":0.99982756},"labels":[],"label_agreement":null},{"id":"W7124958874","doi":"10.59275/j.melba.2025-5ce1","title":"The Trauma THOMPSON Dataset for Real-World Emergency AI","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Multimodal Machine Learning Applications","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":"U.S. Army Medical Research and Development Command; National Science Foundation","keywords":"Action (physics); Benchmark (surveying); Object (grammar); Psychological intervention; Emergency response; Foundation (evidence); Visualization","score_opus":0.013844783570730974,"score_gpt":0.3552164647173537,"score_spread":0.3413716811466227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124958874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001141494,0.00075311254,0.8617068,0.13480888,0.00080244953,0.0003818783,0.00005023788,0.000059657643,0.00029550004],"genre_scores_gemma":[0.9284665,0.00047539987,0.065084554,0.0022691728,0.0009663533,0.000101425416,0.00026730995,0.00005911272,0.0023101447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977961,0.00035082322,0.0007788466,0.0002300579,0.00040961144,0.00043451338],"domain_scores_gemma":[0.9961441,0.0023299132,0.0005930679,0.0005577145,0.00024479104,0.00013042556],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004744148,0.00019201692,0.00026509297,0.00027039956,0.0013687204,0.00017233753,0.0023875243,0.000036764,0.000015985483],"category_scores_gemma":[0.0013762229,0.00010678023,0.00020266541,0.0007473485,0.00019344356,0.00025172916,0.00030574156,0.0009489017,0.000005018431],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024234643,0.00018437424,0.005605468,0.000104503066,0.00021539196,0.0000034043837,0.00061207294,0.0025866844,0.0015357663,0.038225338,0.11912599,0.83155864],"study_design_scores_gemma":[0.00067614263,0.00008598106,0.0042819683,0.00004588225,0.000067681554,0.00002441959,0.000033884593,0.5303665,0.000074126845,0.0076233638,0.45662034,0.00009973384],"about_ca_topic_score_codex":0.00028887164,"about_ca_topic_score_gemma":0.00003681351,"teacher_disagreement_score":0.927325,"about_ca_system_score_codex":0.00006775029,"about_ca_system_score_gemma":0.00012319606,"threshold_uncertainty_score":0.99993134},"labels":[],"label_agreement":null},{"id":"W7125605555","doi":"10.1109/cascon66301.2025.00103","title":"A Hybrid XAI Pipeline for Multimodal Video Understanding: From Transformers to LLMS","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Robustness (evolution); Scalability; Transformer; Software deployment; Pipeline (software); Exploit; Interoperability","score_opus":0.032083133484990374,"score_gpt":0.31484030074691716,"score_spread":0.2827571672619268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125605555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005786265,0.0001273597,0.9201802,0.05948944,0.0011415808,0.0031565656,0.00027147616,0.00045106083,0.009396058],"genre_scores_gemma":[0.8081467,0.000018029956,0.18316935,0.0044657914,0.00017812772,0.0004379177,0.000060517796,0.000043841996,0.0034797175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952049,0.00013202557,0.001097801,0.0019532419,0.0005130055,0.001098986],"domain_scores_gemma":[0.99626654,0.0014177191,0.00017608653,0.0013211487,0.00025952296,0.00055898796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068508805,0.0006538168,0.00070060935,0.0006014891,0.00088352605,0.00068143604,0.0020048579,0.000198401,0.00037224824],"category_scores_gemma":[0.00039243035,0.0006781225,0.0004521275,0.0012823411,0.00015719258,0.00045954846,0.00039328725,0.000556623,0.00031132932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005687622,0.0010499499,0.001214337,0.00021504033,0.000427386,0.000007187763,0.0039156973,0.022716427,0.004960749,0.3616949,0.03295708,0.57027245],"study_design_scores_gemma":[0.0026587837,0.00016985586,0.0010407848,0.00015970609,0.0001245415,0.0000018471857,0.00029051173,0.9350189,0.0032813859,0.031447627,0.025123037,0.00068299647],"about_ca_topic_score_codex":0.0064385463,"about_ca_topic_score_gemma":0.00042866112,"teacher_disagreement_score":0.9123025,"about_ca_system_score_codex":0.0007222136,"about_ca_system_score_gemma":0.0005680558,"threshold_uncertainty_score":0.999567},"labels":[],"label_agreement":null},{"id":"W7125938337","doi":"10.1109/smc58881.2025.11342935","title":"SkyNet: An Extensible Edge-Cloud Collaborative Framework for Robots in Long-Horizon Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Robot; Executable; Modular design; Set (abstract data type); Commodity","score_opus":0.016238226415821375,"score_gpt":0.3441080191156529,"score_spread":0.3278697926998315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125938337","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019210892,0.0008789185,0.95682734,0.0121716345,0.0019613719,0.0030780712,0.000031544445,0.00030814862,0.005532059],"genre_scores_gemma":[0.5722215,0.000047596783,0.4229932,0.0011079118,0.00030968033,0.0006170221,0.000025338171,0.00003882311,0.0026388995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950417,0.00047864032,0.0010187166,0.0020020283,0.00040993153,0.0010489629],"domain_scores_gemma":[0.9945885,0.0015094978,0.00034575787,0.0022844383,0.00094687304,0.00032496746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010546444,0.00061008875,0.00074654043,0.0006316679,0.0006614613,0.0008398247,0.0021505381,0.00059973734,0.00017731554],"category_scores_gemma":[0.0010472788,0.00065093586,0.00015637385,0.0054770475,0.00023186159,0.00074317266,0.0006550322,0.0011293271,0.0001724666],"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":[0.000104015926,0.0009371754,0.009694845,0.00012431825,0.00007404232,0.000007748623,0.0017242584,0.03521281,0.00024498085,0.75271994,0.0026253276,0.19653052],"study_design_scores_gemma":[0.0012866809,0.00084733055,0.080525614,0.0003978184,0.00004746932,0.0000024084127,0.00024599698,0.7913899,0.0010474967,0.12054109,0.0029201,0.00074812985],"about_ca_topic_score_codex":0.001140782,"about_ca_topic_score_gemma":0.0010180408,"teacher_disagreement_score":0.75617707,"about_ca_system_score_codex":0.00031408397,"about_ca_system_score_gemma":0.0011896534,"threshold_uncertainty_score":0.9995942},"labels":[],"label_agreement":null},{"id":"W7125957124","doi":"10.1109/smc58881.2025.11343454","title":"Grounded Multi-modal Conversation for Zero-shot Visual Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Question answering; Conversation; Comprehension; Modalities; Semantics (computer science); Natural language; Focus (optics); Bridging (networking)","score_opus":0.03046320982700265,"score_gpt":0.3708238761415693,"score_spread":0.3403606663145667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125957124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028332282,0.000103845676,0.9601828,0.0057810727,0.0013816026,0.0018655522,0.0000080911595,0.00052912044,0.0018156266],"genre_scores_gemma":[0.80978435,0.000015001079,0.18678413,0.000614408,0.00009742243,0.00031304246,0.00004090076,0.00002341891,0.002327299],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968954,0.00022311731,0.0007460676,0.001198256,0.00032743614,0.00060975936],"domain_scores_gemma":[0.9978046,0.00051217293,0.00028015408,0.0007720494,0.0004656384,0.00016538729],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093578553,0.00041023677,0.00037252382,0.0004037216,0.0007004674,0.0006642593,0.00088891195,0.00028362364,0.00005217936],"category_scores_gemma":[0.00039330457,0.00046547427,0.00020610963,0.00094972516,0.00013815379,0.0008193726,0.0003756174,0.00040715988,0.00012312407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012380186,0.0011128442,0.0067866016,0.00035159447,0.00016275467,0.000001337648,0.0022027234,0.01148134,0.012281613,0.6549522,0.0002751272,0.310268],"study_design_scores_gemma":[0.0024496608,0.00016392472,0.053042963,0.00010808489,0.000059979637,0.000002423104,0.00008979802,0.9360677,0.0023800193,0.0037683516,0.0014606093,0.0004064819],"about_ca_topic_score_codex":0.00341976,"about_ca_topic_score_gemma":0.0001857937,"teacher_disagreement_score":0.92458636,"about_ca_system_score_codex":0.00038943457,"about_ca_system_score_gemma":0.00036375545,"threshold_uncertainty_score":0.9997797},"labels":[],"label_agreement":null},{"id":"W7126109747","doi":"10.1109/bibm66473.2025.11356692","title":"Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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 extraction; Feature (linguistics); Pattern recognition (psychology); Visualization; Encoding (memory); Computed tomography; Benchmark (surveying); Image (mathematics)","score_opus":0.02757592389559764,"score_gpt":0.38309097058611785,"score_spread":0.3555150466905202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126109747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0815489,0.00043533253,0.8958045,0.017661873,0.0017281328,0.0013311069,0.000010098084,0.00015675715,0.0013232583],"genre_scores_gemma":[0.846764,0.00007876301,0.13246916,0.0003291759,0.00035719608,0.00042949605,0.0001439719,0.000015560336,0.019412624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771917,0.0001250027,0.000549399,0.001063517,0.00023099565,0.00031194024],"domain_scores_gemma":[0.9983503,0.0001885679,0.00031862097,0.0006770417,0.00034669557,0.00011873558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061126373,0.0002656881,0.00023722035,0.0002640842,0.00091221277,0.00068189343,0.0002764203,0.000114623734,0.00003714772],"category_scores_gemma":[0.0002362374,0.0002718819,0.00013717273,0.0006036593,0.00006359592,0.00052263454,0.00021970298,0.0003895349,0.000017764753],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021449634,0.00051093096,0.006426295,0.0001491588,0.000111573776,0.000010221886,0.00019282111,0.0005272415,0.009899761,0.063728705,0.018455187,0.89996666],"study_design_scores_gemma":[0.0004848301,0.00011746079,0.054856937,0.000061681945,0.0000911982,0.00014328913,0.000025876909,0.8946231,0.0007230446,0.0005690939,0.048056636,0.0002468543],"about_ca_topic_score_codex":0.00021989662,"about_ca_topic_score_gemma":0.00014554965,"teacher_disagreement_score":0.8997198,"about_ca_system_score_codex":0.00012437657,"about_ca_system_score_gemma":0.00020650789,"threshold_uncertainty_score":0.99997336},"labels":[],"label_agreement":null},{"id":"W7126165022","doi":"10.21428/594757db.b52553ec","title":"Taxonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Context (archaeology); Biodiversity; Closed captioning; Taxonomic rank; Matching (statistics); Interpretability; Contextual image classification; Convolutional neural network","score_opus":0.01547139791379805,"score_gpt":0.30211488575979084,"score_spread":0.2866434878459928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126165022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025281452,0.00006227492,0.96791416,0.0026901325,0.00016630978,0.0008186679,0.000005094708,0.00025666764,0.0028052423],"genre_scores_gemma":[0.5622157,0.0000036486736,0.4366599,0.0001595896,0.000020653157,0.00046969528,0.000012784726,0.0000071398563,0.00045091554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897546,0.00003697672,0.00024778294,0.00046474324,0.000052758503,0.0002223012],"domain_scores_gemma":[0.9987887,0.0005105002,0.00011844961,0.00039914192,0.00013313734,0.00005006136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038980824,0.00012314331,0.00015854632,0.00012969942,0.00046264994,0.00034215234,0.00032801778,0.000055524393,0.0000058485944],"category_scores_gemma":[0.00032802334,0.00012788296,0.00005411528,0.00017741922,0.00005083371,0.00038937115,0.00014363247,0.000107562635,0.0000067473693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032390406,0.000049173374,0.004022855,0.000099167584,0.00004251782,1.8805505e-7,0.0005327055,0.00070545176,0.01270816,0.9088528,0.0032263696,0.069728196],"study_design_scores_gemma":[0.00069359085,0.000037703398,0.00730025,0.00007440389,0.00001489687,0.0000031331592,0.00019327825,0.98081964,0.0007911661,0.004618683,0.005308033,0.00014522142],"about_ca_topic_score_codex":0.000119090386,"about_ca_topic_score_gemma":0.000019465047,"teacher_disagreement_score":0.98011416,"about_ca_system_score_codex":0.00006798773,"about_ca_system_score_gemma":0.000071494,"threshold_uncertainty_score":0.5214916},"labels":[],"label_agreement":null},{"id":"W7126258716","doi":"10.1145/3785987.3786101","title":"Automating Classroom Observation: AI-Enabled Behavior Monitoring for Adaptive Educational Management","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Robustness (evolution); Natural language understanding; Perception; Recall; Adaptive learning; Transformer; On the fly","score_opus":0.03428215026433837,"score_gpt":0.34611824780998585,"score_spread":0.31183609754564745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126258716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028049564,0.0001783824,0.9319311,0.02358953,0.0022617218,0.0032686875,0.000012015296,0.00039349694,0.010315503],"genre_scores_gemma":[0.51872706,0.00000857176,0.46039298,0.00043472185,0.0002770439,0.0032567123,0.00001785957,0.000020127634,0.016864905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659127,0.00012406484,0.0009159234,0.001216426,0.00048685496,0.00066545623],"domain_scores_gemma":[0.99695927,0.00069919997,0.00034949972,0.0011348755,0.00070210325,0.00015505108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061380945,0.00042096333,0.0003450854,0.00039930988,0.00129731,0.00075671973,0.0014950559,0.00016813475,0.00013868195],"category_scores_gemma":[0.00013291648,0.0004797973,0.00020825154,0.0015653229,0.000071369584,0.000790701,0.00071392185,0.0004377726,0.00011241525],"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":[0.000015016671,0.00053887954,0.09554134,0.00021687715,0.00015416149,9.448101e-7,0.00034901962,0.0040082764,0.00020639374,0.64363354,0.0013574817,0.25397804],"study_design_scores_gemma":[0.00062082586,0.000048493832,0.4944024,0.00023180948,0.0001321777,0.0000011183381,0.00013161545,0.4962604,0.000263663,0.0063797426,0.0012372555,0.0002904756],"about_ca_topic_score_codex":0.00032897235,"about_ca_topic_score_gemma":0.0000096246,"teacher_disagreement_score":0.6372538,"about_ca_system_score_codex":0.00056750467,"about_ca_system_score_gemma":0.0005319989,"threshold_uncertainty_score":0.9997654},"labels":[],"label_agreement":null},{"id":"W7126429335","doi":"10.18653/v1/2024.findings-eacl.14","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","year":2024,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Canadian Institute for Advanced Research; Nvidia","keywords":"Closed captioning; Robustness (evolution); Image (mathematics); Image processing; Pattern recognition (psychology)","score_opus":0.05109654786901989,"score_gpt":0.3427500987957064,"score_spread":0.2916535509266865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126429335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30868486,0.00033198082,0.68286633,0.00074198097,0.00049924565,0.0006304924,0.000016278145,0.0000857576,0.006143033],"genre_scores_gemma":[0.9339515,0.00002164584,0.06566802,0.000009124821,0.00007593081,0.000053997355,0.000014968166,0.00001817556,0.00018661642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99586517,0.0010246729,0.00077223504,0.00065615115,0.0014588363,0.00022294075],"domain_scores_gemma":[0.99545616,0.0004979314,0.00043261106,0.0020855973,0.0014569929,0.0000707093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004429057,0.00020722553,0.00024126974,0.00053672056,0.00021829251,0.00030607608,0.002168872,0.00014985679,0.00031631824],"category_scores_gemma":[0.0011697275,0.00016170986,0.00011394211,0.0040442334,0.00020954042,0.0010528882,0.00050124555,0.0004270756,0.00001519711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000299458,0.0002363919,0.00050087157,0.00029375468,0.000043441923,2.2199853e-7,0.0025501875,0.1989894,0.015794285,0.12175657,0.00007357453,0.65975827],"study_design_scores_gemma":[0.0001913708,0.00008405143,0.16376783,0.00014662712,0.000110404486,0.000003308273,0.00013259832,0.8298213,0.004279813,0.0013012659,0.000025059848,0.00013638016],"about_ca_topic_score_codex":0.00088426395,"about_ca_topic_score_gemma":0.000064422165,"teacher_disagreement_score":0.6596219,"about_ca_system_score_codex":0.00018544095,"about_ca_system_score_gemma":0.00048795805,"threshold_uncertainty_score":0.65943366},"labels":[],"label_agreement":null},{"id":"W7126440079","doi":"10.21428/594757db.dd360009","title":"Multi-modal News Understanding with Professionally LabelledVideos (ReutersViLNews)","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Thomson Reuters (Canada); Vector Institute; University of British Columbia","funders":"","keywords":"Event (particle physics); Context (archaeology); Subject (documents); Action (physics); Benchmark (surveying); Domain (mathematical analysis); Big data","score_opus":0.04817114733350052,"score_gpt":0.31169287511279403,"score_spread":0.2635217277792935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126440079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042744484,0.000080638194,0.9728669,0.014460618,0.00021583628,0.00032988063,0.0000016205229,0.0012179953,0.006552048],"genre_scores_gemma":[0.67214197,0.0000036844988,0.32464507,0.00045230705,0.000044976383,0.00005538275,0.0000027739866,0.000018331555,0.0026355071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985582,0.000063200045,0.00018595076,0.00058717525,0.00031304747,0.00029239457],"domain_scores_gemma":[0.99904555,0.00021263512,0.000037329453,0.00054181967,0.00003582212,0.000126836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019989006,0.00017579205,0.00012839721,0.00016753214,0.0002250725,0.00036832542,0.0007026484,0.000059905622,0.00009182169],"category_scores_gemma":[0.000025604966,0.00012134437,0.00004861158,0.00065187895,0.00004499778,0.0005003326,0.0002601195,0.00033154004,0.000412223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009983613,0.00012607686,0.0050726305,0.00007490595,0.000073948555,0.000054655735,0.0016231107,0.0015035685,0.0026236882,0.9752685,0.003902484,0.0096664615],"study_design_scores_gemma":[0.00036020164,0.000070859205,0.0038259951,0.00017585575,0.000010754933,0.00003936328,0.00019059818,0.9869746,0.00015687656,0.003477723,0.0043987297,0.00031844826],"about_ca_topic_score_codex":0.0003556396,"about_ca_topic_score_gemma":0.00025626554,"teacher_disagreement_score":0.985471,"about_ca_system_score_codex":0.00014599261,"about_ca_system_score_gemma":0.00017992551,"threshold_uncertainty_score":0.529843},"labels":[],"label_agreement":null},{"id":"W7130595512","doi":"10.1109/fllm67465.2025.11391205","title":"Multi-modal Causal RAG for Aviation Accident Analysis and Risk Prediction","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Aviation; Accident (philosophy); Pipeline (software); Topic model; Aviation accident; Aviation safety; Upload; Causal analysis","score_opus":0.010943431764660986,"score_gpt":0.30692521164738124,"score_spread":0.29598177988272023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130595512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15563577,0.00015463118,0.8405712,0.0017460808,0.0003667669,0.0011034834,0.00004713164,0.00020265579,0.0001722592],"genre_scores_gemma":[0.81427795,0.00016423933,0.1833677,0.00011201742,0.0000766876,0.00028741377,0.00005433417,0.000010364213,0.0016492975],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972122,0.00024420436,0.00071337644,0.0011566341,0.00028641877,0.0003872203],"domain_scores_gemma":[0.99765575,0.00054881506,0.00038688045,0.0008969674,0.00035410412,0.00015746175],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009870811,0.0002978726,0.00039929565,0.0008426176,0.0008776814,0.00055939716,0.00054099446,0.00021003904,0.000050019575],"category_scores_gemma":[0.0004736317,0.00030569397,0.00025361925,0.0024038416,0.00007820351,0.00047743088,0.00039079523,0.00035391742,0.000021501777],"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":[0.0000266001,0.00021816262,0.8571357,0.000027111639,0.0010615335,2.2084026e-7,0.0005998405,0.020996518,0.0003411554,0.008371983,0.0001672958,0.111053884],"study_design_scores_gemma":[0.0006808115,0.000045182762,0.48902038,0.000008632528,0.0010180793,4.35964e-7,0.000018840365,0.50828123,0.00015392053,0.00047930086,0.000176671,0.00011654494],"about_ca_topic_score_codex":0.0075892964,"about_ca_topic_score_gemma":0.002004429,"teacher_disagreement_score":0.6586422,"about_ca_system_score_codex":0.00017057528,"about_ca_system_score_gemma":0.00014895014,"threshold_uncertainty_score":0.9999395},"labels":[],"label_agreement":null},{"id":"W7131068881","doi":"10.1109/iccvw69036.2025.00121","title":"MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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; Montreal Neurological Institute and Hospital","funders":"","keywords":"Segmentation; Image segmentation; Encoder; Scale-space segmentation; Segmentation-based object categorization; Feature (linguistics); Generalization; Scalability","score_opus":0.006658952244160694,"score_gpt":0.35728470193251877,"score_spread":0.3506257496883581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131068881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111116886,0.00011376135,0.84245276,0.03545017,0.00032405576,0.00096814893,0.000016636903,0.00043406093,0.009123502],"genre_scores_gemma":[0.74414814,0.000018490711,0.24191244,0.00622679,0.00007355612,0.00015506784,0.00002019646,0.000024404108,0.007420892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952041,0.0002959335,0.00085856265,0.0014755056,0.001269049,0.00089688593],"domain_scores_gemma":[0.99722403,0.000393072,0.00018379826,0.0014035264,0.00024551037,0.00055005617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016937107,0.00044825606,0.00042642627,0.00044370923,0.0006127075,0.00048821152,0.0020901172,0.00023852609,0.00091163616],"category_scores_gemma":[0.0008867178,0.00044923957,0.00016028534,0.0017040978,0.00008948991,0.0005921172,0.0014622449,0.00075049105,0.00047945886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104735045,0.001441625,0.0010819389,0.00039575173,0.00023881161,0.00005840193,0.05402619,0.10016912,0.114717446,0.07436544,0.012330465,0.64107007],"study_design_scores_gemma":[0.0007008685,0.000042771695,0.0033395078,0.0002123911,0.000028111099,0.0000036160102,0.0004508588,0.98374367,0.010080168,0.0007031236,0.0002794149,0.0004154733],"about_ca_topic_score_codex":0.00088698335,"about_ca_topic_score_gemma":0.00016745848,"teacher_disagreement_score":0.88357455,"about_ca_system_score_codex":0.00026910807,"about_ca_system_score_gemma":0.0007646031,"threshold_uncertainty_score":0.9997959},"labels":[],"label_agreement":null},{"id":"W7131081286","doi":"10.1109/iccvw69036.2025.00476","title":"A Survey on Vision-Language-Action Models for Autonomous Driving","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"McGill University","funders":"","keywords":"TRACE (psycholinguistics); Control (management); Measure (data warehouse); Natural (archaeology); Natural language","score_opus":0.03708258920698129,"score_gpt":0.3680725928216169,"score_spread":0.3309900036146356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131081286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030866338,0.00010022777,0.9535888,0.0038431487,0.00088777684,0.0012085388,0.000023272736,0.00040394292,0.009077942],"genre_scores_gemma":[0.942978,0.000011301745,0.046904992,0.0008223006,0.000075172065,0.0002143942,0.00003247546,0.00002555132,0.008935814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971109,0.00032715622,0.0005683304,0.0011784164,0.00028522633,0.0005299451],"domain_scores_gemma":[0.996149,0.0018099943,0.00021257861,0.0014098058,0.00027239628,0.00014623713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013371534,0.00034190546,0.00034742514,0.0003976889,0.00070454646,0.0006292738,0.0011415133,0.00019280892,0.000072991184],"category_scores_gemma":[0.00050633616,0.0003490397,0.00017492952,0.0010231113,0.00006149602,0.00049048936,0.00041100988,0.00042889692,0.00014276945],"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":[0.000038135102,0.0004318872,0.0013398502,0.000055624678,0.00006062534,7.629461e-7,0.00086068094,0.2386874,0.0004979923,0.09479668,0.0029478457,0.6602825],"study_design_scores_gemma":[0.0004929795,0.00017820853,0.11912636,0.000092782626,0.000015648151,6.443271e-7,0.000028134395,0.87575287,0.00031594638,0.0031316255,0.0005876096,0.0002771731],"about_ca_topic_score_codex":0.007229091,"about_ca_topic_score_gemma":0.0009903371,"teacher_disagreement_score":0.91211164,"about_ca_system_score_codex":0.00027096237,"about_ca_system_score_gemma":0.00037031682,"threshold_uncertainty_score":0.99989617},"labels":[],"label_agreement":null},{"id":"W7131093438","doi":"10.1109/iccvw69036.2025.00221","title":"Refining Naive Annotations with Limited Expert Guidance for Semantic Segmentation: A Case Study on Underwater Echograms","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Fisheries and Oceans Canada; Canadian Water Network; ASL Environmental Sciences (Canada); University of Victoria","funders":"Alliance de recherche numérique du Canada","keywords":"Metadata; Annotation; Ground truth; Context (archaeology); Intersection (aeronautics); Artificial neural network; Segmentation; Convolutional neural network; Domain (mathematical analysis)","score_opus":0.042033903670718034,"score_gpt":0.3603349623937063,"score_spread":0.3183010587229883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131093438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24790944,0.00005967782,0.7400578,0.007649149,0.00022711522,0.0024886339,0.000009485103,0.00032464173,0.0012740436],"genre_scores_gemma":[0.83388233,0.000002623474,0.15931743,0.0020291072,0.000057573925,0.0022719502,0.000018530776,0.00003642009,0.002384041],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626374,0.00033791322,0.0008124395,0.0015276478,0.0004432334,0.00061504834],"domain_scores_gemma":[0.9963455,0.0010455172,0.000324477,0.0014968256,0.00062256056,0.00016508174],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00054274173,0.00052477967,0.00042978697,0.0004955216,0.0015739463,0.00084917014,0.00077566924,0.00011663135,0.000029810088],"category_scores_gemma":[0.000121629266,0.0004491143,0.00012470431,0.002136581,0.00013435453,0.00044573887,0.00026070199,0.00040712405,0.000057174977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094420597,0.016043212,0.13518788,0.0005767862,0.002884595,0.0020347645,0.15930936,0.135719,0.0036054696,0.061597783,0.004350996,0.47774595],"study_design_scores_gemma":[0.005990595,0.003587765,0.015684819,0.00053648755,0.0002419883,0.00031328734,0.02354443,0.946811,0.0010745967,0.00038121082,0.00085387763,0.0009799222],"about_ca_topic_score_codex":0.0042367363,"about_ca_topic_score_gemma":0.0010939519,"teacher_disagreement_score":0.811092,"about_ca_system_score_codex":0.0002238845,"about_ca_system_score_gemma":0.0002865911,"threshold_uncertainty_score":0.99979603},"labels":[],"label_agreement":null},{"id":"W7131095609","doi":"10.1109/iccvw69036.2025.00782","title":"DIVE-Doc: Downscaling Foundational Image Visual Encoder into Hierarchical Architecture for DocVQA","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Encoder; Distillation; Image (mathematics); Code (set theory); Architecture; Forcing (mathematics); Visualization","score_opus":0.008780846628456837,"score_gpt":0.339472735249167,"score_spread":0.33069188862071014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131095609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010303631,0.00011340366,0.9176798,0.06234746,0.0008716757,0.0015218066,0.000024584924,0.00036377096,0.006773873],"genre_scores_gemma":[0.5230602,0.000006886087,0.47179118,0.002091038,0.0004057877,0.00039194545,0.00006752516,0.000028528031,0.0021569077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99522,0.00033110543,0.0010150357,0.0017950126,0.0006996749,0.00093914376],"domain_scores_gemma":[0.99557626,0.0021885403,0.00024779545,0.001103828,0.0005406053,0.00034296783],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009295727,0.0006038227,0.0005475817,0.0005885296,0.0016329875,0.0012878532,0.0020964865,0.00030808413,0.0005037093],"category_scores_gemma":[0.0008658842,0.00057385984,0.00044041188,0.0013640512,0.00078835065,0.00050618243,0.0015084097,0.0012295131,0.0002599783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011844092,0.0005842585,0.0016329227,0.00025860989,0.00018530716,0.0000029714756,0.0019265906,0.008915856,0.0069136266,0.583182,0.0016435019,0.39463595],"study_design_scores_gemma":[0.0013072857,0.00015510501,0.010068924,0.00010178562,0.00006627353,0.000009479687,0.00004803015,0.82739735,0.0010423341,0.13391595,0.025309935,0.0005775594],"about_ca_topic_score_codex":0.0011423801,"about_ca_topic_score_gemma":0.0001534322,"teacher_disagreement_score":0.8184815,"about_ca_system_score_codex":0.0002378159,"about_ca_system_score_gemma":0.000864368,"threshold_uncertainty_score":0.9997489},"labels":[],"label_agreement":null},{"id":"W7133067082","doi":"","title":""Flobject" Analysis: Learning about Static Images from Motion","year":2011,"lang":"en","type":"dissertation","venue":"TSpace","topic":"Multimodal Machine Learning Applications","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":"Generalization; Unsupervised learning; Motion (physics); Pattern recognition (psychology); Representation (politics); Image (mathematics); Object (grammar); Pyramid (geometry); Field (mathematics)","score_opus":0.013653236677320619,"score_gpt":0.32381778625437724,"score_spread":0.31016454957705664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133067082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36413366,0.001004427,0.5992907,0.00042671218,0.0008963313,0.00069333456,0.000023739176,0.0015399149,0.031991165],"genre_scores_gemma":[0.88991004,0.00010914203,0.06179925,0.000084260224,0.00018069202,0.00021196771,0.0023999857,0.000090030335,0.045214653],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970134,0.0003323012,0.00047889145,0.00115228,0.00056496105,0.00045820329],"domain_scores_gemma":[0.9972418,0.00025985134,0.0007582122,0.0013007818,0.0002611747,0.00017817807],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033870433,0.00048630266,0.00063067663,0.0006663311,0.00035038963,0.00036829294,0.0013847706,0.00031008842,0.00044303449],"category_scores_gemma":[0.00023880594,0.00051263976,0.0003191333,0.0014894767,0.000034206387,0.0002991543,0.00013133184,0.0011089531,0.00087629934],"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":[0.00021352718,0.001316742,0.06931888,0.00085134263,0.008528893,0.00012470075,0.31650448,0.076671235,0.017390128,0.024703417,0.0035127257,0.48086393],"study_design_scores_gemma":[0.00061169796,0.00011837026,0.60862225,0.00022104953,0.0018395209,0.0000026057958,0.003505055,0.37336624,0.0025432347,0.005601567,0.0019534251,0.0016149775],"about_ca_topic_score_codex":0.01799922,"about_ca_topic_score_gemma":0.0009086395,"teacher_disagreement_score":0.53930336,"about_ca_system_score_codex":0.00009778893,"about_ca_system_score_gemma":0.0001309879,"threshold_uncertainty_score":0.99990165},"labels":[],"label_agreement":null},{"id":"W7134188119","doi":"10.1109/bigdata66926.2025.11400804","title":"The Hybrid Deployment Architecture for Explainable and Robust Video Understanding","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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","funders":"","keywords":"Software deployment; Architecture; Key (lock); Systems architecture; Domain (mathematical analysis); Robustness (evolution)","score_opus":0.031838450459745475,"score_gpt":0.2813186936731368,"score_spread":0.2494802432133913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134188119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019538044,0.0015733592,0.93896526,0.05089388,0.00034415929,0.0014066151,0.000005070227,0.00015654793,0.004701331],"genre_scores_gemma":[0.91098756,0.00030236263,0.08322408,0.0010999804,0.00007343473,0.00044080164,0.0000024803496,0.000022877157,0.0038464142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978484,0.00012773403,0.00038146338,0.0008009236,0.00021971647,0.00062175805],"domain_scores_gemma":[0.9967576,0.0019744602,0.0001289048,0.00092257233,0.00008546249,0.00013098979],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008696969,0.00027665021,0.00021659936,0.00014236355,0.0028280017,0.0011760319,0.0009797073,0.00006095822,0.000011224566],"category_scores_gemma":[0.00025829548,0.00020250179,0.00010062254,0.00046419937,0.00021855923,0.0001550713,0.0007129163,0.00036547842,0.0000067012616],"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":[0.00003353654,0.00005110233,0.00038768843,0.00010041229,0.000082801416,0.0000011176168,0.00042518027,0.03811314,0.000118607015,0.8607072,0.009403765,0.09057545],"study_design_scores_gemma":[0.0006643664,0.00008846119,0.00045541502,0.00008366269,0.00004158083,0.00001037781,0.0003736965,0.82671237,0.0006391647,0.12889363,0.041798837,0.00023843712],"about_ca_topic_score_codex":0.00033782137,"about_ca_topic_score_gemma":0.00015298267,"teacher_disagreement_score":0.9090338,"about_ca_system_score_codex":0.00027966665,"about_ca_system_score_gemma":0.00019617837,"threshold_uncertainty_score":0.9998608},"labels":[],"label_agreement":null},{"id":"W7137029536","doi":"10.1109/itsc60802.2025.11423805","title":"Adver-City: Open-Source Multi-Modal Dataset for Collaborative Perception Under Adverse Weather Conditions","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"","keywords":"Perception; Adverse weather; Climate change; Nowcasting","score_opus":0.039672793922927586,"score_gpt":0.37323132760810146,"score_spread":0.33355853368517385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7137029536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057291044,0.00005118312,0.95775384,0.015733317,0.0005542593,0.0052958066,0.009720392,0.00024820506,0.004913894],"genre_scores_gemma":[0.7595656,0.000035292203,0.19523993,0.006626919,0.00012287618,0.0019252973,0.0060227234,0.00006278423,0.030398568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956383,0.00046567663,0.0008681632,0.0018739277,0.0003826596,0.00077123486],"domain_scores_gemma":[0.9955705,0.0007683202,0.00040434106,0.0021749516,0.0007726445,0.0003092564],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00081942114,0.0006202443,0.0006104497,0.00040843993,0.001955941,0.0009612625,0.0032404035,0.00034062206,0.0018558506],"category_scores_gemma":[0.0002717153,0.00064834004,0.00019055743,0.0020728528,0.0004384142,0.0016877463,0.0022368624,0.0006006044,0.0007661135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041980852,0.0062163947,0.006124635,0.00028874897,0.0012115792,0.0000060356538,0.0075190435,0.088741936,0.008832278,0.53088874,0.2851702,0.064580604],"study_design_scores_gemma":[0.0047690338,0.0001900891,0.04648556,0.0001227657,0.00020124721,0.0000045826396,0.002704038,0.7846826,0.00014998145,0.0024675343,0.1574665,0.0007561023],"about_ca_topic_score_codex":0.003152357,"about_ca_topic_score_gemma":0.00095012423,"teacher_disagreement_score":0.76251394,"about_ca_system_score_codex":0.0004606303,"about_ca_system_score_gemma":0.0011286341,"threshold_uncertainty_score":0.9995968},"labels":[],"label_agreement":null},{"id":"W7143420289","doi":"10.47363/jaicc/icaicc/2025(4)17","title":"The Wisdom of Fusion: In-depth Analysis and Future Outlook of Visual Multimodal Technologies","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence & Cloud Computing","topic":"Multimodal Machine Learning Applications","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":"Focus (optics); Variety (cybernetics); Presentation (obstetrics); Cognitive neuroscience of visual object recognition; Segmentation; Deep learning; Multimodality; Multimodal learning","score_opus":0.015573289620855942,"score_gpt":0.32937919495661067,"score_spread":0.3138059053357547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143420289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56121594,0.00227146,0.43178558,0.0035564771,0.0008676346,0.00021713122,0.0000016374315,0.000024415462,0.000059739144],"genre_scores_gemma":[0.97446215,0.0006754759,0.024502525,0.000026114129,0.00031169577,0.0000018507619,4.0083694e-7,0.000011704676,0.000008074026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943393,0.0004592826,0.0033871576,0.00054965966,0.0007410353,0.0005235722],"domain_scores_gemma":[0.9928661,0.0020665773,0.0030870591,0.0007465654,0.0011433116,0.000090371796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033980962,0.00037605417,0.0011432082,0.0014237665,0.00054339255,0.00024415078,0.0021919438,0.00029679644,0.000008564315],"category_scores_gemma":[0.0009883657,0.0002955666,0.0005108947,0.005736623,0.0010156623,0.00020786944,0.0011959053,0.0014676726,0.0000021660032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001320444,0.00040055253,0.028945208,0.000082132385,0.00042211317,0.0000098908695,0.0034915775,0.0541744,0.0020449762,0.029178465,0.00000548531,0.8811132],"study_design_scores_gemma":[0.00011530101,0.00037858178,0.039043125,0.000420496,0.00031729473,0.00001541768,0.0077583087,0.9264006,0.015900038,0.009332138,0.00009493433,0.00022374437],"about_ca_topic_score_codex":0.000522629,"about_ca_topic_score_gemma":0.000238079,"teacher_disagreement_score":0.8808894,"about_ca_system_score_codex":0.000112490874,"about_ca_system_score_gemma":0.00042270657,"threshold_uncertainty_score":0.99994963},"labels":[],"label_agreement":null},{"id":"W7154561671","doi":"10.1109/imc-ssgp67001.2025.11473981","title":"4LM: Local Lightweight LLMs for Image Captioning on Embedded Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Closed captioning; Image (mathematics); Image processing; Key (lock); Component (thermodynamics)","score_opus":0.011642461619575056,"score_gpt":0.30496486969592274,"score_spread":0.2933224080763477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154561671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021740417,0.00031887193,0.93716186,0.0060744197,0.0019630073,0.0019355102,0.000018057377,0.0005001124,0.049854144],"genre_scores_gemma":[0.9027859,0.000015259971,0.076986626,0.00076028873,0.00027079237,0.0007110432,0.00001863587,0.00003675796,0.0184147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960405,0.00029936765,0.0009125255,0.001483851,0.00045689626,0.000806839],"domain_scores_gemma":[0.9961069,0.0011188352,0.00029830274,0.0017545244,0.0004798549,0.00024154875],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010799236,0.00049740507,0.00054179836,0.00045226933,0.0010568327,0.0012349788,0.0016666279,0.00028024006,0.0001117601],"category_scores_gemma":[0.0002662444,0.0004719641,0.00026987278,0.0011724415,0.00020281594,0.00041204251,0.00043202963,0.00058168516,0.00087714207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004043895,0.00037963854,0.00012429216,0.0003119276,0.00011536763,0.0000047232215,0.0007902531,0.034656215,0.0014039623,0.8971856,0.008885352,0.056102205],"study_design_scores_gemma":[0.0009629607,0.00018633856,0.0007578136,0.00035807758,0.00005677789,0.000007885706,0.00022835648,0.9780952,0.0018199926,0.0016120208,0.01545369,0.00046093867],"about_ca_topic_score_codex":0.0011767971,"about_ca_topic_score_gemma":0.000019620913,"teacher_disagreement_score":0.94343895,"about_ca_system_score_codex":0.00033332076,"about_ca_system_score_gemma":0.00037554422,"threshold_uncertainty_score":0.9999008},"labels":[],"label_agreement":null},{"id":"W7160014773","doi":"10.1109/iccv51701.2025.00237","title":"FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Beijing Municipal Commission of Education; National Natural Science Foundation of China","keywords":"Key (lock); Identification (biology); Feature (linguistics); Set (abstract data type); Term (time)","score_opus":0.015915098965143006,"score_gpt":0.3358294414760369,"score_spread":0.3199143425108939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160014773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025521247,0.00028377958,0.93926376,0.009317064,0.0003489855,0.0026477831,0.00002238641,0.00069865986,0.021896336],"genre_scores_gemma":[0.879244,0.000016183127,0.10072838,0.0010966492,0.00011456596,0.00047389916,0.00004836205,0.00005091708,0.018227007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957261,0.00023864154,0.000922815,0.001658718,0.000427958,0.0010257327],"domain_scores_gemma":[0.9972165,0.0005696351,0.00031126686,0.0011899442,0.00043384702,0.00027880762],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076380785,0.0006026554,0.00059941073,0.00039722893,0.001303236,0.0015938694,0.0015731333,0.00027295758,0.00014478304],"category_scores_gemma":[0.00026671588,0.00059031765,0.0002841759,0.0016148959,0.00021602707,0.000858164,0.0010156861,0.00063947483,0.00016087273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014997082,0.00084332353,0.00053286296,0.0008408906,0.00047950048,0.000011732003,0.013458896,0.16152917,0.026369397,0.57744753,0.0036407758,0.21469596],"study_design_scores_gemma":[0.001188574,0.00016605078,0.00055273407,0.00023464208,0.0000695293,0.0000026674466,0.00038866544,0.9858811,0.0028537202,0.0073454063,0.000701895,0.0006150185],"about_ca_topic_score_codex":0.0014822641,"about_ca_topic_score_gemma":0.000075712414,"teacher_disagreement_score":0.8537228,"about_ca_system_score_codex":0.00018338788,"about_ca_system_score_gemma":0.0005431935,"threshold_uncertainty_score":0.99999696},"labels":[],"label_agreement":null},{"id":"W7160028952","doi":"10.1109/iccv51701.2025.00749","title":"OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Object (grammar); Object detection; Feature (linguistics); Pattern recognition (psychology); Viola–Jones object detection framework","score_opus":0.020977677567380806,"score_gpt":0.31158699577160637,"score_spread":0.2906093182042256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160028952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025694104,0.00021611048,0.9481561,0.008409378,0.0012500066,0.005204727,0.000037367772,0.00016806665,0.010864105],"genre_scores_gemma":[0.89261544,0.00004465476,0.09923925,0.0021848173,0.00009074596,0.0013760797,0.00001800803,0.00004063911,0.004390377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994469,0.00030247858,0.0014636747,0.002152819,0.0005706909,0.0010413664],"domain_scores_gemma":[0.9960339,0.0011743847,0.00036462737,0.0019532905,0.00026153278,0.00021226694],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001825396,0.00065229693,0.0008529633,0.00059656973,0.00069133315,0.0020830312,0.0026458509,0.00030718755,0.000048971055],"category_scores_gemma":[0.00052862964,0.00065813476,0.00032559602,0.0017911826,0.00021977792,0.0011775835,0.0026466171,0.00065721205,0.000061989325],"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":[0.0009589805,0.0072318045,0.016055856,0.0011654006,0.0009111638,0.000030168461,0.0020567745,0.04649833,0.08450943,0.46459532,0.001102346,0.37488443],"study_design_scores_gemma":[0.0039844913,0.0004718751,0.06502189,0.00045229722,0.00013067543,0.00002265235,0.00016794834,0.912612,0.010544781,0.002454775,0.0033347106,0.0008018607],"about_ca_topic_score_codex":0.0075625773,"about_ca_topic_score_gemma":0.00277759,"teacher_disagreement_score":0.8669213,"about_ca_system_score_codex":0.0008548202,"about_ca_system_score_gemma":0.0012689538,"threshold_uncertainty_score":0.999587},"labels":[],"label_agreement":null},{"id":"W7160031978","doi":"10.1109/iccv51701.2025.00592","title":"Mamba-3VL: Taming State Space Model for 3D Vision Language Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"State (computer science); Space (punctuation); Feature (linguistics); Natural language; State space; Key (lock)","score_opus":0.009304892235748189,"score_gpt":0.32582369203578365,"score_spread":0.31651879980003544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160031978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029746609,0.00032775966,0.9540683,0.006126215,0.0002555196,0.0010644547,0.000012641322,0.0005597489,0.007838739],"genre_scores_gemma":[0.57627225,0.000023967812,0.36794344,0.00042325896,0.00003825312,0.000102893515,0.0000118514845,0.000029365448,0.05515472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677205,0.00019068742,0.00059765566,0.0012566992,0.0003734729,0.0008094224],"domain_scores_gemma":[0.997479,0.0006746566,0.00028136384,0.0011253043,0.0002471783,0.00019247831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009916323,0.00041997986,0.00040320345,0.00038875398,0.0009683607,0.0006907484,0.0012027966,0.00015873727,0.000060765287],"category_scores_gemma":[0.00044463272,0.00043547753,0.00019689195,0.0009901637,0.00009179532,0.00051436725,0.0009788261,0.00079364807,0.00015884922],"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":[0.000024848043,0.00012506677,0.00057165377,0.00015343001,0.000036691472,0.0000024535016,0.004591024,0.5857268,0.004156822,0.030857533,0.0006646968,0.373089],"study_design_scores_gemma":[0.00081426516,0.000105713814,0.0014270957,0.0001669106,0.00003672857,0.0000018684934,0.0001886751,0.9906565,0.00074744044,0.0016095313,0.0038245437,0.00042071735],"about_ca_topic_score_codex":0.0011058081,"about_ca_topic_score_gemma":0.00009182787,"teacher_disagreement_score":0.5861249,"about_ca_system_score_codex":0.00017018645,"about_ca_system_score_gemma":0.0003245979,"threshold_uncertainty_score":0.9998097},"labels":[],"label_agreement":null},{"id":"W7160043273","doi":"10.1109/iccv51701.2025.02161","title":"DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Segmentation; Adaptation (eye); Feature (linguistics); Pattern recognition (psychology); Image segmentation","score_opus":0.01516478191265817,"score_gpt":0.3258266459429268,"score_spread":0.31066186403026863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160043273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018988779,0.00010450989,0.9697817,0.008146793,0.0002826342,0.001470364,0.000045219786,0.00010166657,0.0010783203],"genre_scores_gemma":[0.6089035,0.000015374719,0.38909882,0.00046573655,0.000036547466,0.00021844637,0.000016454444,0.00001086278,0.0012342382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790597,0.0001435726,0.0006905586,0.00073419977,0.0002462137,0.00027949628],"domain_scores_gemma":[0.9928783,0.0055020954,0.00047778653,0.00057377823,0.00048490244,0.0000831259],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048593903,0.0002666361,0.00035456428,0.00029022797,0.0002774164,0.00021517264,0.0005120467,0.00018311836,0.00014238678],"category_scores_gemma":[0.0017853619,0.00027562128,0.000115025716,0.0006889032,0.00013818574,0.00063482445,0.00033112854,0.00033761517,0.000053189273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009392822,0.00041582188,0.005749661,0.00024137166,0.00013643925,2.5008194e-7,0.0052927104,0.005744482,0.008757288,0.3214874,0.00036132603,0.65171933],"study_design_scores_gemma":[0.00070048234,0.00025341968,0.02962432,0.00027016393,0.000104949984,0.0000011633945,0.0003083951,0.9137884,0.011118741,0.04307138,0.0005173143,0.00024130098],"about_ca_topic_score_codex":0.0008765281,"about_ca_topic_score_gemma":0.000017074623,"teacher_disagreement_score":0.90804386,"about_ca_system_score_codex":0.00010789772,"about_ca_system_score_gemma":0.00020882112,"threshold_uncertainty_score":0.9999696},"labels":[],"label_agreement":null},{"id":"W7160112519","doi":"10.1109/iccv51701.2025.00687","title":"Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Context (archaeology); Modular design; Automated reasoning; Physical system; Knowledge representation and reasoning","score_opus":0.016075970502646243,"score_gpt":0.35030521424483335,"score_spread":0.3342292437421871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160112519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029494708,0.000535662,0.96179,0.0043722196,0.00027549302,0.001611757,0.000017910317,0.00025041334,0.0016518387],"genre_scores_gemma":[0.6051801,0.000009109139,0.39310116,0.00091299525,0.0001656254,0.00029861098,0.0000069380926,0.000027006457,0.00029844866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639577,0.00021536581,0.0006182816,0.00151213,0.0004181631,0.0008402748],"domain_scores_gemma":[0.99599636,0.0015867761,0.00023019183,0.0017900867,0.00022188088,0.00017470821],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051875267,0.00050444214,0.00069795904,0.00023143861,0.00039626617,0.0005452982,0.0016799889,0.0002833195,0.000016463597],"category_scores_gemma":[0.0005606337,0.00052862294,0.00034147588,0.0018420393,0.00016492672,0.0007939067,0.00077176245,0.0010765191,0.000050417144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026227717,0.0004778944,0.00007504213,0.00006217775,0.00003332601,0.0000018555537,0.005503271,0.2147885,0.00016610237,0.50799644,0.0000871295,0.27078205],"study_design_scores_gemma":[0.000798014,0.000111100635,0.00039629746,0.00062792195,0.000026771015,6.7669714e-7,0.0004366922,0.7166174,0.00037215513,0.2801959,0.000069074056,0.00034798073],"about_ca_topic_score_codex":0.0013444668,"about_ca_topic_score_gemma":0.000043726966,"teacher_disagreement_score":0.5756854,"about_ca_system_score_codex":0.00020378364,"about_ca_system_score_gemma":0.00031110778,"threshold_uncertainty_score":0.9997165},"labels":[],"label_agreement":null},{"id":"W7160147334","doi":"10.1109/iccv51701.2025.00072","title":"PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spurious relationship; Projection (relational algebra); Embedding; Noise (video); Computation","score_opus":0.022203687657010328,"score_gpt":0.35456226915590394,"score_spread":0.33235858149889363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160147334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41834763,0.00022333633,0.5657507,0.002337588,0.00018583088,0.0013265781,0.000002338326,0.00037620417,0.0114497505],"genre_scores_gemma":[0.86353505,0.000033117987,0.13362952,0.0003813019,0.0000687518,0.00024991206,0.0000095283285,0.000038982518,0.0020538224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533397,0.0003136245,0.0010417874,0.0017939921,0.00055337226,0.0009632463],"domain_scores_gemma":[0.9970685,0.0005105345,0.00036912397,0.0016865096,0.0001820494,0.00018328127],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009865486,0.0005492704,0.00057144556,0.001271239,0.0005926806,0.0007987339,0.0012334785,0.00023587217,0.00005117807],"category_scores_gemma":[0.0003250526,0.0004991234,0.000118212396,0.003988654,0.000119092525,0.0011856417,0.00074695324,0.0009159502,0.00004666807],"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":[0.00006732713,0.0008854383,0.0022792413,0.00015864211,0.00007340688,0.000040582745,0.011744582,0.7231546,0.006331975,0.017232707,0.0007306945,0.23730078],"study_design_scores_gemma":[0.00108954,0.00024903344,0.0071887495,0.001163652,0.000036330508,0.0000658075,0.0005340129,0.9858041,0.0020563419,0.0012281,0.00005523194,0.0005291028],"about_ca_topic_score_codex":0.028880898,"about_ca_topic_score_gemma":0.000477758,"teacher_disagreement_score":0.44518742,"about_ca_system_score_codex":0.0005348159,"about_ca_system_score_gemma":0.00076784275,"threshold_uncertainty_score":0.999746},"labels":[],"label_agreement":null},{"id":"W7160163144","doi":"10.1109/iccv51701.2025.01747","title":"LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graph; Image (mathematics); Laplacian matrix; Laplace operator; Image editing; Pattern recognition (psychology)","score_opus":0.0174265668069709,"score_gpt":0.3409412574415373,"score_spread":0.3235146906345664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160163144","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":[0.0074204844,0.00020186577,0.9607194,0.013331393,0.002822164,0.002711008,0.000046410867,0.00092063594,0.011826611],"genre_scores_gemma":[0.4841209,0.000034038352,0.50394535,0.001516378,0.000613717,0.00090296176,0.00011915921,0.00006701912,0.008680458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941354,0.00036069818,0.0016872628,0.0019890876,0.0005738951,0.0012536856],"domain_scores_gemma":[0.99493754,0.00090482715,0.00068111037,0.0017623157,0.0013926387,0.00032156814],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021029613,0.00070843706,0.00082240056,0.00069202896,0.0017526927,0.002090799,0.0022762772,0.00043740388,0.0002922307],"category_scores_gemma":[0.0012490195,0.00074467214,0.0006671858,0.0025817777,0.00054114545,0.0010650204,0.0008799863,0.00073800853,0.00031882917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009924992,0.0027682136,0.018033398,0.0027184414,0.001424863,0.000028945662,0.0017133529,0.13114579,0.02115561,0.34205547,0.11109804,0.36686537],"study_design_scores_gemma":[0.006939005,0.00009159369,0.007980313,0.00026847658,0.00013701369,0.000008725529,0.000076043725,0.966659,0.002351064,0.006692597,0.008133111,0.0006630517],"about_ca_topic_score_codex":0.0010353789,"about_ca_topic_score_gemma":0.000037243433,"teacher_disagreement_score":0.83551323,"about_ca_system_score_codex":0.00023147288,"about_ca_system_score_gemma":0.0004113632,"threshold_uncertainty_score":0.9995469},"labels":[],"label_agreement":null}]}