{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":476,"total_is_capped":false,"direct_labels_cover":3,"predictions_cover":476,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"8f8a0ffd912f","filters":{"topic":"Multimodal Machine Learning Applications"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.06664802413473758,"gpt":0.2082971016600826,"spread":0.141649077525345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001368005,0.0001082612,0.00008155902,0.00009946906,0.0001422026,0.0001040355,0.0002222409,0.00004209315,0.000004290949],"category_scores_gemma":[0.0000135803,0.0001083492,0.00002174418,0.0003659019,0.00006743395,0.0007717867,0.0001175983,0.0001177764,0.00005563188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006273077,"about_ca_system_score_gemma":0.00003012166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002911866,"about_ca_topic_score_gemma":0.00005265166,"domain_scores_codex":[0.9991837,0.00008010042,0.00007481401,0.0004377884,0.00007375015,0.0001498543],"domain_scores_gemma":[0.9993771,0.0000206665,0.00007385798,0.0002710008,0.0001212499,0.0001360721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001471928,0.0005047251,0.4063665,0.00004064613,0.0001032744,0.0002956705,0.001439944,0.2617693,0.05902739,0.2514403,0.0007745034,0.01809062],"study_design_scores_gemma":[0.000488962,0.0001067686,0.05233017,0.000003246952,0.00001497827,0.0000230044,0.00004328764,0.9462836,0.0001225617,0.0004003482,0.00004715925,0.0001358899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5765283,0.000003825287,0.4227819,0.0001702366,0.00003051764,0.00008192445,5.614042e-7,0.00009355377,0.0003091355],"genre_scores_gemma":[0.9933254,0.000003450248,0.006261299,0.00005233362,0.00005189813,9.563591e-7,0.00001289173,0.000008030492,0.0002837159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6845143,"threshold_uncertainty_score":0.4418352,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0244207246769013,"gpt":0.3090277660838301,"spread":0.2846070414069288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001023543,0.0004558201,0.0004707855,0.0002799727,0.0005583891,0.000858435,0.0008490751,0.0002618916,0.000009357163],"category_scores_gemma":[0.0001708306,0.0004457223,0.00006360257,0.0001076763,0.000134093,0.0004082855,0.002742137,0.001068683,0.00001188748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001449758,"about_ca_system_score_gemma":0.0002247531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003569749,"about_ca_topic_score_gemma":0.00005453394,"domain_scores_codex":[0.9973148,0.0002240084,0.0004180397,0.001160658,0.0004801172,0.0004023956],"domain_scores_gemma":[0.998151,0.000292673,0.0002892672,0.0007726559,0.0001782976,0.0003161027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003278217,0.0003801357,0.01073684,0.001268522,0.0008519614,0.00004478917,0.116401,0.008964827,0.00820666,0.2122914,0.129091,0.5117301],"study_design_scores_gemma":[0.0007954944,0.000121305,0.003749087,0.0003981614,0.00009660522,0.00006788321,0.001837261,0.9268277,0.0006957258,0.02071525,0.04289559,0.001799975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1203548,0.002174529,0.8447673,0.006594077,0.0006695795,0.001019005,0.00005371554,0.001419443,0.02294753],"genre_scores_gemma":[0.8711296,0.000152503,0.1234353,0.00073606,0.0001755393,0.0002914602,0.00008987161,0.00006028272,0.003929331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9178628,"threshold_uncertainty_score":0.9997994,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04609872896526987,"gpt":0.3260767922855972,"spread":0.2799780633203274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003468585,0.0002067997,0.0001963688,0.0001152631,0.0004481112,0.0003173928,0.001525077,0.0000685353,0.0001188867],"category_scores_gemma":[0.0002640809,0.0001479082,0.00006308209,0.0007622186,0.0004312138,0.0003860132,0.0003194869,0.0003297485,0.0001989608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003928176,"about_ca_system_score_gemma":0.0001051827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001916777,"about_ca_topic_score_gemma":0.00001814917,"domain_scores_codex":[0.998299,0.0000204324,0.0003555027,0.0005274765,0.0004557873,0.0003418054],"domain_scores_gemma":[0.9983221,0.00007173513,0.0003638454,0.0003094499,0.0008377718,0.00009513875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003514455,0.00008446487,0.001604464,0.000009754689,0.00001436856,2.925658e-7,0.001157453,0.0001347776,0.04061963,0.9385958,0.00009859842,0.01764531],"study_design_scores_gemma":[0.00004515216,0.000457464,0.004813696,0.0002380336,0.00001391737,0.00001583259,0.0002458824,0.5578782,0.3977966,0.03798752,0.0002096214,0.0002980561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.791002,0.00000525676,0.1764717,0.0035432,0.0001937428,0.0004150138,0.000004005978,0.0002335005,0.02813152],"genre_scores_gemma":[0.9699196,0.000002113445,0.02927673,0.0003045298,0.0001581832,0.00005089476,9.207471e-7,0.00001531782,0.0002716628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9006082,"threshold_uncertainty_score":0.6031523,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02787362915645639,"gpt":0.3174627048172625,"spread":0.2895890756608062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000626336,0.0002520614,0.0002463579,0.0001634419,0.001244463,0.0008596668,0.001062092,0.00007984553,0.00002892274],"category_scores_gemma":[0.000279546,0.0002275133,0.0000366057,0.0002524838,0.0001778479,0.0007444028,0.0001878681,0.0004966368,0.0001075767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003630924,"about_ca_system_score_gemma":0.00006321509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001324254,"about_ca_topic_score_gemma":0.0001388594,"domain_scores_codex":[0.9981601,0.0001549385,0.0002519235,0.0007103377,0.0003553819,0.0003672889],"domain_scores_gemma":[0.9984518,0.0001834392,0.0003805966,0.0006169328,0.0001943262,0.0001728983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003173514,0.00008369167,0.01316881,0.00002542888,0.000006593769,0.000006132066,0.000181331,0.006134303,0.0009051012,0.0001397232,0.0001005673,0.9792166],"study_design_scores_gemma":[0.0004832665,0.0001487627,0.4356905,0.0000413508,0.000005365518,0.000008241107,0.000002077804,0.5535587,0.0002460062,0.0003438167,0.009217295,0.00025461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07983875,0.002077023,0.8894681,0.005824118,0.0003878857,0.0003202073,0.000008739545,0.000881897,0.02119322],"genre_scores_gemma":[0.9829352,0.000116251,0.01571555,0.0001337862,0.0001214128,0.00002280873,0.00001076809,0.0000254822,0.0009186745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978962,"threshold_uncertainty_score":0.9571533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05364504113686984,"gpt":0.2721015833326518,"spread":0.2184565421957819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001737518,0.00009927893,0.00008602525,0.00004359493,0.000100677,0.0001700968,0.0006514225,0.00004011915,0.00003102961],"category_scores_gemma":[0.0001573386,0.00008709614,0.00002263113,0.000243386,0.00001715946,0.0004048717,0.0002205726,0.0001652223,0.0000841919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000427815,"about_ca_system_score_gemma":0.00006080805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008014744,"about_ca_topic_score_gemma":0.00001373262,"domain_scores_codex":[0.9990841,0.00004663747,0.0001468775,0.000298987,0.0002194558,0.0002039861],"domain_scores_gemma":[0.9991681,0.0000459589,0.00006069779,0.0004357616,0.00007060624,0.0002188892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008782599,0.0001664712,0.1433324,0.00001951631,0.00004657258,0.00001625023,0.006366433,0.00602422,0.0639423,0.274059,0.1415468,0.3644712],"study_design_scores_gemma":[0.0008543529,0.00008275752,0.002639114,0.00002530433,0.00000581225,0.00004566377,0.0003628123,0.9424486,0.01356776,0.01223302,0.0270967,0.0006381651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1526503,0.00003605978,0.8389517,0.00299369,0.00009229914,0.0001130836,0.000002306081,0.0005633858,0.004597207],"genre_scores_gemma":[0.7728828,1.496458e-7,0.2263172,0.0005680012,0.00004049879,0.000008729146,0.000006698652,0.000007490547,0.0001683585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9364243,"threshold_uncertainty_score":0.3551678,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01089575007474679,"gpt":0.2662476004378025,"spread":0.2553518503630557,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001500912,0.00008428649,0.00007893376,0.00004892536,0.00008259195,0.00008399296,0.0007169112,0.00003029439,0.00003032177],"category_scores_gemma":[0.00003634868,0.00007145514,0.00003743605,0.0001541385,0.00001713286,0.0002859687,0.0001832396,0.0001229495,0.0002705897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001018537,"about_ca_system_score_gemma":0.000007926905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008235057,"about_ca_topic_score_gemma":0.00001410481,"domain_scores_codex":[0.999245,0.00005451794,0.0001056727,0.0002716456,0.0001416961,0.0001814237],"domain_scores_gemma":[0.9991466,0.00009147134,0.00003159834,0.0006228224,0.00002638298,0.00008115872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001069642,0.00004994291,0.00093445,0.000004032237,0.000004287358,0.000001132075,0.0009539542,0.06250409,0.002272264,0.7228141,0.0003093662,0.2101513],"study_design_scores_gemma":[0.0001447503,0.00001437434,0.006258309,9.470389e-7,9.198017e-7,0.000004027199,0.000006841958,0.9885727,0.0002587165,0.004288763,0.0003542945,0.0000953834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09422432,0.000007836963,0.8721488,0.001838371,0.00005554808,0.00007592882,3.430251e-7,0.0005399801,0.03110884],"genre_scores_gemma":[0.8101186,1.886415e-7,0.1887715,0.0006362746,0.00004553354,0.00001569526,0.00000161259,0.000006104719,0.0004045282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9260686,"threshold_uncertainty_score":0.3477973,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4143372677061843,"gpt":0.2670283867265147,"spread":0.1473088809796696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002963753,0.00007613286,0.0000737406,0.00007188523,0.0001040817,0.00006881995,0.0007982947,0.00002187119,4.398487e-7],"category_scores_gemma":[0.00006297644,0.00008982278,0.00001393985,0.0002282285,0.00003062182,0.002354234,0.0005721406,0.00007490896,0.000010664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003903787,"about_ca_system_score_gemma":0.00003041515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003135443,"about_ca_topic_score_gemma":0.00001407675,"domain_scores_codex":[0.9992381,0.00003302083,0.00006261292,0.0004899461,0.00003554271,0.000140823],"domain_scores_gemma":[0.9988728,0.00006626145,0.00004293379,0.0008240041,0.00007390001,0.0001201522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000015211,0.00003762898,0.00145771,0.0000176767,0.00001373074,0.00001318548,0.0004711199,0.2112447,0.0003221234,0.7798377,0.0001104361,0.006458814],"study_design_scores_gemma":[0.0002956872,0.00002131546,0.0008913057,0.000007493421,0.000007883396,0.000002769667,0.00005179897,0.9743403,0.00004271058,0.02384051,0.0003950604,0.0001031576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.245121,0.00000989836,0.754043,0.0001578185,0.00004465641,0.000106081,0.000005056726,0.0001459853,0.0003665392],"genre_scores_gemma":[0.9342812,0.00001741808,0.0655719,0.00002017975,0.00002660055,0.000001909434,0.00001071554,0.000006677922,0.00006334646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7630956,"threshold_uncertainty_score":0.3662867,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01567864347003803,"gpt":0.3060882820700778,"spread":0.2904096386000397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006322796,0.0004744319,0.0003795231,0.0003156116,0.0002439174,0.0005556248,0.002883633,0.0003624742,0.0001450081],"category_scores_gemma":[0.0001791252,0.0003840553,0.0001947671,0.0001644786,0.00006288561,0.0002613806,0.002280578,0.001007208,0.0004917232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002490915,"about_ca_system_score_gemma":0.0002266461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003162954,"about_ca_topic_score_gemma":0.0000816303,"domain_scores_codex":[0.997022,0.0002348273,0.0004759811,0.001306965,0.0005515497,0.0004086853],"domain_scores_gemma":[0.9966599,0.0005544597,0.000352294,0.002057219,0.0001520703,0.0002240993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001444303,0.002154664,0.06905757,0.0004082856,0.0002713988,0.00004278789,0.007818857,0.06443337,0.02850789,0.1777022,0.00188493,0.6475736],"study_design_scores_gemma":[0.0004279029,0.00006800256,0.05263166,0.0005660036,0.00001388876,0.000001403087,0.000005467159,0.9142219,0.002644395,0.0282244,0.0006813738,0.0005135887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126869,0.0000846128,0.8741885,0.00188644,0.0007044218,0.0003501824,0.00002434466,0.001144791,0.008929728],"genre_scores_gemma":[0.860045,0.000004256573,0.1383842,0.0002478975,0.0006217635,0.0001321066,0.00002846002,0.00004149052,0.0004948179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8497885,"threshold_uncertainty_score":0.9998611,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02535626076205967,"gpt":0.2773558627617337,"spread":0.251999601999674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001318937,0.0001128393,0.00009819648,0.00006702275,0.0002512418,0.0002036792,0.0006556194,0.00004318705,0.00003243295],"category_scores_gemma":[0.00002954538,0.00009913033,0.00003810195,0.0003737005,0.00009232351,0.0003804652,0.0002759082,0.0001361975,0.0001912764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002434834,"about_ca_system_score_gemma":0.00002165499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003555948,"about_ca_topic_score_gemma":0.00002476698,"domain_scores_codex":[0.9990237,0.00004010686,0.0001448019,0.0003360452,0.000199878,0.0002554109],"domain_scores_gemma":[0.9990783,0.0001118277,0.00006653936,0.0006240971,0.00004234955,0.00007689294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003679318,0.0002105795,0.02341356,0.00001066179,0.00002290794,0.000002633155,0.001825455,0.001126631,0.008126544,0.08564276,0.0002277945,0.8793868],"study_design_scores_gemma":[0.0001945597,0.0001821619,0.01684016,0.000009617223,0.000003064101,0.0000118534,0.00003634639,0.9718024,0.003568216,0.002802652,0.004293582,0.0002554047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.255824,0.000003490022,0.7325773,0.0005699139,0.00008702365,0.0001516774,2.787678e-7,0.001000911,0.009785373],"genre_scores_gemma":[0.858601,2.225498e-7,0.1405256,0.0002119339,0.0001435313,0.00003249056,0.000001226413,0.00001212847,0.0004717753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9706758,"threshold_uncertainty_score":0.4042418,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04201553110016543,"gpt":0.3481929253520091,"spread":0.3061773942518437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004735292,0.0001586609,0.0001821918,0.0001244988,0.0001366598,0.0002211631,0.001079666,0.0000724551,0.00002521988],"category_scores_gemma":[0.0007166441,0.0001184636,0.00006216276,0.0003865473,0.00007435679,0.0002787598,0.000299934,0.000213129,0.0001303038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003168616,"about_ca_system_score_gemma":0.00003754468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000071697,"about_ca_topic_score_gemma":0.000005881065,"domain_scores_codex":[0.9986644,0.00001191124,0.0003336774,0.0004887627,0.0002853388,0.0002159507],"domain_scores_gemma":[0.9987778,0.0001916451,0.0002203697,0.0002936944,0.0004355276,0.00008093542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006673208,0.00005309563,0.0002481207,0.00002704873,0.000003739282,1.905445e-8,0.002359251,0.0000441323,0.2908931,0.5551559,0.00004714804,0.1511018],"study_design_scores_gemma":[0.00005187383,0.0003429388,0.003903779,0.0001772233,0.000006165286,0.000001671138,0.0004379546,0.530439,0.4277703,0.03657014,0.000110492,0.0001884757],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8068361,0.000007464449,0.1826206,0.006686264,0.0002138905,0.001210176,0.000007692051,0.00009591871,0.002321842],"genre_scores_gemma":[0.9749306,0.000003208197,0.02439341,0.0002531785,0.00003751437,0.00003596656,8.660089e-7,0.00001114255,0.0003341539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5303949,"threshold_uncertainty_score":0.4830806,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03467305324326582,"gpt":0.2914807309224713,"spread":0.2568076776792055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001598557,0.0001013386,0.000150354,0.0000778757,0.00005827844,0.0001341338,0.0002637617,0.00005863995,0.00002371997],"category_scores_gemma":[0.00009292857,0.00008621168,0.00002534277,0.000245666,0.00003436148,0.0004537012,0.0001807377,0.0001974552,0.00001779517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002386241,"about_ca_system_score_gemma":0.00003174603,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131833,"about_ca_topic_score_gemma":0.0003293597,"domain_scores_codex":[0.9991281,0.00005951701,0.0002386699,0.0002716206,0.0001352332,0.0001668465],"domain_scores_gemma":[0.9994229,0.00009264296,0.000082946,0.0003117643,0.00004768318,0.00004206787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001282946,0.0004414339,0.3448424,0.0001516091,0.00004389466,0.000008452717,0.04384996,0.007412512,0.01207548,0.06864105,0.0004542721,0.5220661],"study_design_scores_gemma":[0.0005080694,0.00007846687,0.6498637,0.0001012292,0.00000763195,0.0000100929,0.0003554249,0.3361834,0.001394134,0.0108812,0.0003860701,0.0002306106],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551668,0.00009424034,0.2423448,0.00114789,0.00006085684,0.0002490835,3.309542e-7,0.00007755071,0.0008584856],"genre_scores_gemma":[0.8276151,0.00002341639,0.1719897,0.000166369,0.00003841679,0.0000310991,6.803372e-7,0.000005287536,0.0001299236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5218355,"threshold_uncertainty_score":0.993388,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07866269093093313,"gpt":0.2518239291440776,"spread":0.1731612382131444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006072483,0.0002829709,0.0002485923,0.0001770285,0.0003264047,0.0001560817,0.001114449,0.0002593742,0.000009537492],"category_scores_gemma":[0.00005393492,0.0003616142,0.0001723624,0.0003976646,0.00008414117,0.0004656004,0.0005704619,0.0004974554,0.00003365419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003264789,"about_ca_system_score_gemma":0.0002738279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005470171,"about_ca_topic_score_gemma":0.00006755615,"domain_scores_codex":[0.9979219,0.0002549743,0.0002188206,0.001100764,0.0001272713,0.0003762988],"domain_scores_gemma":[0.9981185,0.0001322763,0.0003026957,0.0008020978,0.0004075805,0.0002368961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003530966,0.00008801043,0.01209403,0.0000315068,0.00002016596,0.000006445151,0.00002412599,0.9044352,0.00005246185,0.08226984,0.0001545192,0.0007883992],"study_design_scores_gemma":[0.0005545948,0.0001058237,0.03855866,0.00004512476,0.00004234132,0.000001810433,0.000007294917,0.940523,0.000005287149,0.01956489,0.0002456321,0.0003456037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3418358,0.00001475883,0.6566499,0.0001829101,0.0004376906,0.0004053479,0.00001557245,0.0003594302,0.00009863407],"genre_scores_gemma":[0.9685286,0.00000262812,0.0304556,0.00009486452,0.000343492,0.00001263759,0.0003600616,0.00002373984,0.0001784003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6266928,"threshold_uncertainty_score":0.9998836,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; University of Waterloo","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Cognitive science; Psychology; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.04329207881041666,"gpt":0.3393487419959848,"spread":0.2960566631855682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003138123,0.0001933609,0.0001659252,0.0001663144,0.0003612673,0.0005087583,0.0004141594,0.00007712817,0.00002577766],"category_scores_gemma":[0.0001356761,0.0001657222,0.00007664437,0.0003329183,0.00006452441,0.0004072683,0.0003228272,0.0002072311,0.00001982744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452827,"about_ca_system_score_gemma":0.00005914657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003425523,"about_ca_topic_score_gemma":0.00004901454,"domain_scores_codex":[0.9985488,0.00003763948,0.0002209618,0.0006926687,0.0001670203,0.0003328894],"domain_scores_gemma":[0.9988267,0.0005391802,0.00004711848,0.0004030674,0.00004444684,0.000139417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000133776,0.0001013912,0.001025481,0.0001204586,0.00009322617,0.00001633035,0.007511381,0.001918972,0.008016533,0.9368691,0.002436196,0.04187749],"study_design_scores_gemma":[0.0004130539,0.00004208295,0.001721348,0.00008872141,0.000007339887,0.00001283891,0.0002952841,0.9903998,0.0002446013,0.005010615,0.001534922,0.000229365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005412483,0.0004617868,0.9851009,0.006652568,0.0002281198,0.0004777848,0.000009739605,0.0006145946,0.001042037],"genre_scores_gemma":[0.5672937,0.00001137191,0.4319476,0.0001117008,0.00006791369,0.0001308077,0.000007979491,0.00001615856,0.00041281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9884809,"threshold_uncertainty_score":0.6757956,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01003198278439735,"gpt":0.2815968184575066,"spread":0.2715648356731092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003694295,0.0002931294,0.0003222998,0.0001604899,0.0005778088,0.00123737,0.00135726,0.00009239544,0.0002801265],"category_scores_gemma":[0.0002279465,0.0003002574,0.00006668489,0.0007357721,0.0003145655,0.0008504343,0.0006379909,0.0004269632,0.0003979857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004610964,"about_ca_system_score_gemma":0.0001672677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005798887,"about_ca_topic_score_gemma":0.0006568564,"domain_scores_codex":[0.9973624,0.0001269367,0.0003849529,0.001065767,0.0005393709,0.0005205125],"domain_scores_gemma":[0.998044,0.0001485743,0.0002608821,0.0007912835,0.0005075181,0.0002477865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002513836,0.0002386063,0.008211326,0.00005392958,0.00002939594,0.00005651906,0.0006470091,0.00004335191,0.01158254,0.01556618,0.0006872564,0.9628587],"study_design_scores_gemma":[0.0008213702,0.0006566258,0.2024756,0.0002719724,0.00001371052,0.0002458565,0.00001948426,0.7900173,0.001544168,0.001395001,0.001980978,0.0005579694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2423177,0.0000848574,0.7523491,0.001368191,0.0001424522,0.000364636,0.00000825354,0.0006299616,0.002734854],"genre_scores_gemma":[0.9070306,0.00002058191,0.09171885,0.0004589644,0.0001298263,0.00005221535,0.00001191207,0.0000339715,0.0005430511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9623008,"threshold_uncertainty_score":0.9999449,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03048174510081268,"gpt":0.3389131894072359,"spread":0.3084314443064232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003059074,0.0001214165,0.0001870597,0.00008671702,0.0001665792,0.0002139759,0.001368323,0.0001096593,0.00001136339],"category_scores_gemma":[0.0001580651,0.000120053,0.0001484276,0.00002931367,0.00004137576,0.0001399677,0.0009683971,0.0002164257,0.00002584392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000292669,"about_ca_system_score_gemma":0.00007789709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00100949,"about_ca_topic_score_gemma":0.00001475656,"domain_scores_codex":[0.9990524,0.00002509878,0.000225501,0.0004270556,0.0001423595,0.0001275608],"domain_scores_gemma":[0.9978032,0.00007690203,0.0004517857,0.0013894,0.0002390256,0.00003967511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001295694,0.0003235655,0.01967358,0.001203472,0.0001950079,0.0000021925,0.0008385649,0.01069447,0.01766307,0.7724034,0.003404959,0.1735848],"study_design_scores_gemma":[0.000243254,0.00002056824,0.1406588,0.0001197209,0.00002120667,0.000002924102,0.00000510322,0.804517,0.0007646256,0.05286277,0.0005458796,0.0002380618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01778905,0.00001917225,0.9722703,0.001693464,0.0002338651,0.0004761588,0.0000111671,0.0001634473,0.007343364],"genre_scores_gemma":[0.5884904,0.000002587861,0.4106475,0.00001279622,0.00005162035,0.0001541202,0.00003254537,0.000007499466,0.0006009349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7938226,"threshold_uncertainty_score":0.4895618,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05085603367949731,"gpt":0.2937594390146995,"spread":0.2429034053352022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957853,0.0001885012,0.0001654244,0.0001000487,0.0002923767,0.0002587122,0.001541168,0.00004763782,0.00007672366],"category_scores_gemma":[0.0002455769,0.0001053771,0.00006966459,0.0005313052,0.0002799639,0.0004938535,0.0003321489,0.000182876,0.0002410354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000471017,"about_ca_system_score_gemma":0.00006829986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006174154,"about_ca_topic_score_gemma":0.000006898375,"domain_scores_codex":[0.9983716,0.00001978829,0.0003757595,0.0004888818,0.0004341989,0.0003097699],"domain_scores_gemma":[0.9985126,0.00008541869,0.000316476,0.0004007908,0.0005941935,0.00009052127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009600783,0.00008342704,0.0008255178,0.000007732024,0.00001106123,2.066533e-7,0.0002740649,0.00001889268,0.4297092,0.5332761,0.00005358721,0.0357306],"study_design_scores_gemma":[0.00006760168,0.0001567251,0.002149968,0.0003224641,0.00001953539,0.00001188372,0.0001509321,0.1255988,0.8098933,0.0612125,0.00009694558,0.0003193583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4194016,0.000004246828,0.5598478,0.01202518,0.0001607896,0.0004507,0.000005529188,0.0001917544,0.007912401],"genre_scores_gemma":[0.9397037,0.000005368086,0.05968139,0.0001239099,0.00004416889,0.0000516675,2.268129e-7,0.00001273135,0.0003768132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5203021,"threshold_uncertainty_score":0.4297155,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01302205938873805,"gpt":0.2537439968164512,"spread":0.2407219374277132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001092246,0.0001056166,0.00009000828,0.0001965081,0.0001570138,0.00006506983,0.001064958,0.00006687192,0.0001151219],"category_scores_gemma":[0.00001295256,0.000104081,0.00007970755,0.0006365663,0.00002362798,0.0001864428,0.00001139038,0.0003659791,0.001233457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000153891,"about_ca_system_score_gemma":0.0000259695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000976817,"about_ca_topic_score_gemma":0.00001476568,"domain_scores_codex":[0.9991487,0.00003644581,0.0001251948,0.0003090932,0.0002072486,0.0001733274],"domain_scores_gemma":[0.9982659,0.0002155042,0.00003843966,0.001370213,0.00004065158,0.00006925305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003034145,0.000979653,0.01668819,0.00005754883,0.0001670077,0.000008001141,0.001401181,0.02694159,0.003366309,0.6787952,0.0006052093,0.2709598],"study_design_scores_gemma":[0.002763243,0.0009527609,0.2585534,0.00009767459,0.00006677191,0.00010503,0.00009541184,0.4757195,0.005804475,0.1514427,0.1025968,0.001802337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05737826,0.0000105898,0.9353188,0.004316165,0.0002425323,0.0001981294,0.000005811386,0.0004186365,0.002111081],"genre_scores_gemma":[0.9571373,0.0000140847,0.04161813,0.0008827762,0.00001149027,0.0000331557,0.000002403083,0.00001094262,0.0002897508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.899759,"threshold_uncertainty_score":0.9995442,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01403630361228849,"gpt":0.278239799894357,"spread":0.2642034962820686,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002863624,0.0001397957,0.0001404137,0.0000969527,0.0001789236,0.0007444764,0.001266937,0.00004479757,0.00008534519],"category_scores_gemma":[0.0001759498,0.000123247,0.00003959706,0.0004199969,0.00003134013,0.0007604406,0.0004359979,0.0001891203,0.002018638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002679085,"about_ca_system_score_gemma":0.00001718835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002359081,"about_ca_topic_score_gemma":0.00004259805,"domain_scores_codex":[0.9987152,0.00006484717,0.0001766812,0.0005131864,0.0002433764,0.000286729],"domain_scores_gemma":[0.9985259,0.0001454573,0.00009071299,0.0009662744,0.0001008244,0.0001708084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003258308,0.0001089155,0.01374765,0.00002518561,0.00001128882,0.000003116602,0.001629475,0.001276156,0.007295511,0.368326,0.00306516,0.6045083],"study_design_scores_gemma":[0.0002621009,0.00006691987,0.4217831,0.0001017738,0.000004425691,0.00001021841,0.0001049228,0.5208066,0.001534723,0.005516618,0.04933788,0.000470692],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04864777,0.00001790707,0.9250543,0.008688069,0.0002621109,0.000176019,6.261333e-7,0.000535679,0.01661749],"genre_scores_gemma":[0.8285489,0.000004854735,0.1684018,0.001901356,0.00006736811,0.00003975551,0.000001843173,0.00001053643,0.001023533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7799011,"threshold_uncertainty_score":0.9987584,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03439024797878233,"gpt":0.3264412100324542,"spread":0.2920509620536719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009117155,0.0003896211,0.0003962401,0.0003597082,0.001055059,0.0008326814,0.0009489253,0.0001227464,0.0007739217],"category_scores_gemma":[0.0000510013,0.0004004747,0.0002045095,0.0004817372,0.00009146509,0.0005154152,0.0006113024,0.0007279167,0.0002586124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001008564,"about_ca_system_score_gemma":0.00008053974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001447064,"about_ca_topic_score_gemma":0.00001557296,"domain_scores_codex":[0.9965428,0.0004558158,0.0005904011,0.001220293,0.0007019428,0.0004888052],"domain_scores_gemma":[0.9978715,0.0004890683,0.0003623997,0.000753598,0.0002879748,0.000235526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002102397,0.000495816,0.002233502,0.0000938766,0.00005334415,0.00002502774,0.001131958,0.0008315018,0.005460713,0.001172657,0.005133914,0.9831575],"study_design_scores_gemma":[0.002652379,0.001570998,0.03714852,0.0001139557,0.00002778954,0.0001019096,0.0001020817,0.9497818,0.0008196452,0.003096568,0.003813624,0.0007707585],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4102937,0.00002858537,0.5840504,0.003054244,0.001019537,0.0007496413,0.0002072467,0.0003365198,0.0002601201],"genre_scores_gemma":[0.9874263,0.000024654,0.007792443,0.003156452,0.0003643972,0.0003236913,0.0004684079,0.00004390033,0.0003997702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9823867,"threshold_uncertainty_score":0.9998447,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05285417320652501,"gpt":0.2337116258580682,"spread":0.1808574526515432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002006846,0.0003216632,0.000299168,0.0001979547,0.0006893737,0.0004391092,0.002117399,0.00022015,0.00004264593],"category_scores_gemma":[0.00005388876,0.0003486453,0.0001233753,0.0002298771,0.0001453016,0.0004386484,0.0017657,0.0008925571,0.0001478013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566191,"about_ca_system_score_gemma":0.0002706126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001454975,"about_ca_topic_score_gemma":0.00006614381,"domain_scores_codex":[0.9980289,0.0001232294,0.0001457171,0.001210743,0.0001224641,0.0003689716],"domain_scores_gemma":[0.997435,0.00007984824,0.0004496947,0.001668538,0.000180188,0.0001867314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002000257,0.00008283249,0.03017268,0.00003578438,0.0001258741,0.0002739914,0.0002814419,0.690859,0.00009063642,0.27703,0.0002450563,0.0007827737],"study_design_scores_gemma":[0.0004304944,0.00004510262,0.03615764,0.0001346629,0.00005143475,0.00001572931,0.00001653582,0.9560599,0.00006828194,0.006033161,0.00052157,0.0004655364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4417124,0.0000119611,0.5522514,0.0001492212,0.0001194895,0.0001917948,0.00001061301,0.000313867,0.005239246],"genre_scores_gemma":[0.9759834,0.00001276917,0.02126639,0.00008607025,0.0001253247,0.000005629673,0.00006141516,0.00002736985,0.002431653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.534271,"threshold_uncertainty_score":0.9998965,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04285904995147653,"gpt":0.3168681275049487,"spread":0.2740090775534722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006912344,0.0003377423,0.0003678318,0.0002647771,0.001028188,0.0005861594,0.0005260672,0.00007798632,0.0001531096],"category_scores_gemma":[0.00001829564,0.0003329201,0.0001021569,0.0002545267,0.00007934779,0.0003878876,0.0005616833,0.0005084338,0.00003028885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007116452,"about_ca_system_score_gemma":0.000052477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580945,"about_ca_topic_score_gemma":0.00001398406,"domain_scores_codex":[0.9972237,0.0004038999,0.0004622325,0.001033601,0.0005248436,0.0003517469],"domain_scores_gemma":[0.9983299,0.0005113318,0.0002563226,0.0004847668,0.0002175214,0.0002001943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001212503,0.0005931449,0.0003029587,0.0001873852,0.00004934161,0.00002555839,0.004028605,0.002944027,0.003209634,0.007885403,0.001020152,0.9796326],"study_design_scores_gemma":[0.001195047,0.0009089281,0.002789415,0.0001406432,0.00001837397,0.00006951799,0.00007815531,0.9791534,0.0001214669,0.01443998,0.0006448157,0.0004402839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2280766,0.00004746883,0.7679021,0.00194782,0.0004727478,0.0007839287,0.0001853678,0.0002374167,0.0003465938],"genre_scores_gemma":[0.973434,0.00002601114,0.02317881,0.002361622,0.0002028375,0.000329462,0.0003895497,0.00002894611,0.00004871916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9791923,"threshold_uncertainty_score":0.9999123,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1770216083512234,"gpt":0.3854094199385489,"spread":0.2083878115873254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008427287,0.0007957345,0.002097961,0.0004325797,0.0006460798,0.0004362991,0.004868736,0.0002861104,0.00001384495],"category_scores_gemma":[0.00529073,0.0007241679,0.0006846554,0.002458938,0.00007845651,0.0001568771,0.002484916,0.002233828,0.0039974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001989538,"about_ca_system_score_gemma":0.0002034215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002204839,"about_ca_topic_score_gemma":0.0000074895,"domain_scores_codex":[0.9902976,0.005446617,0.001196107,0.001664183,0.0006402469,0.0007552553],"domain_scores_gemma":[0.9904139,0.00506504,0.001167485,0.003019392,0.0001355225,0.0001986776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[9.431405e-8,0.00003721167,0.00001564476,0.01651076,0.00008384608,0.00001277342,0.00006745695,0.0009154077,2.738168e-8,0.001484805,0.0002949756,0.980577],"study_design_scores_gemma":[0.000209262,0.0001228636,0.0008468081,0.1054464,0.0003707503,0.0001209954,0.000007399732,0.202739,1.386088e-7,0.0004508384,0.6877186,0.00196696],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[8.06847e-7,0.7312114,0.2647992,0.0002717553,0.0002520596,0.0009254103,0.000002560606,0.001630609,0.0009062338],"genre_scores_gemma":[0.00003768383,0.9500902,0.04859335,0.00009699634,0.0002774606,0.0001697473,0.0002464404,0.0001612646,0.0003268627],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.97861,"threshold_uncertainty_score":0.999521,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0710747672886309,"gpt":0.3634047171561183,"spread":0.2923299498674874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000287964,0.0001274886,0.0001085284,0.00009282581,0.000582697,0.0002263832,0.0004142841,0.00006306942,0.0002699076],"category_scores_gemma":[0.0001546237,0.0001238534,0.00005467257,0.0003819583,0.00004399486,0.0007900406,0.0001752234,0.0003531706,0.001748038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005827864,"about_ca_system_score_gemma":0.00001819839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001057226,"about_ca_topic_score_gemma":0.00002876762,"domain_scores_codex":[0.9987851,0.0001215091,0.0002316644,0.0004410784,0.0001885081,0.0002321695],"domain_scores_gemma":[0.9991288,0.0001496516,0.0001293286,0.0003773304,0.0001648544,0.00005008341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000280692,0.0003818993,0.009094944,0.00004457332,0.0000891814,0.000006128615,0.01197382,0.003149186,0.1178313,0.1003146,0.002924233,0.754162],"study_design_scores_gemma":[0.0009875519,0.0006357144,0.02402682,0.0001598354,0.00002944742,0.0000888283,0.0003765786,0.8044469,0.078698,0.05607014,0.03343181,0.001048301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2022516,0.000004648016,0.7369472,0.0004939369,0.0002061147,0.0001188074,2.458295e-7,0.0006881724,0.05928927],"genre_scores_gemma":[0.8975622,0.000002460417,0.1013808,0.000326576,0.0002284657,0.0000282214,0.00001400951,0.00001336778,0.0004439506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8012978,"threshold_uncertainty_score":0.9990292,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006586964800575043,"gpt":0.2454334821047727,"spread":0.2388465173041977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001139236,0.00006365353,0.00006520495,0.00005004354,0.00005995167,0.00008846414,0.0004379412,0.00002639751,0.0002301032],"category_scores_gemma":[0.00003002766,0.00005682588,0.00002848067,0.0001957186,0.000007739642,0.0001918922,0.0001311156,0.00009698366,0.003221887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001993836,"about_ca_system_score_gemma":0.00002482774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000473485,"about_ca_topic_score_gemma":0.00001104481,"domain_scores_codex":[0.9993631,0.000024736,0.0001025213,0.0002517932,0.0001219739,0.0001358585],"domain_scores_gemma":[0.9992315,0.00008986589,0.00003664234,0.000549151,0.00004074727,0.00005209167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003050367,0.00007791683,0.119528,0.00001104085,0.00001736489,0.000002610351,0.0005393172,0.01295349,0.01307644,0.7853515,0.0009416072,0.06749777],"study_design_scores_gemma":[0.0002846242,0.00003079301,0.1273171,0.000006482419,0.000001952875,0.000009771913,0.00001436133,0.8645836,0.00090239,0.002710887,0.00397612,0.0001618629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4485532,0.00000764057,0.5285959,0.001727882,0.00008513165,0.0001203927,2.420581e-7,0.0003946368,0.02051498],"genre_scores_gemma":[0.8618779,5.109484e-7,0.1354336,0.0002977483,0.00002140912,0.0000106997,0.000001627779,0.000004656339,0.002351843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8516302,"threshold_uncertainty_score":0.9975542,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06834906582068068,"gpt":0.3139618964753935,"spread":0.2456128306547128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005272002,0.0001714128,0.0002208156,0.00005674926,0.0004268131,0.0003203001,0.001383534,0.00006003985,0.00002882635],"category_scores_gemma":[0.000799697,0.0001471762,0.0001383776,0.0007704102,0.0001098653,0.0002679992,0.0003746224,0.0002748625,0.00005053754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003957254,"about_ca_system_score_gemma":0.0001167643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007888712,"about_ca_topic_score_gemma":0.00001915699,"domain_scores_codex":[0.9983254,0.00001965627,0.0004549139,0.0005324559,0.0003056232,0.0003619149],"domain_scores_gemma":[0.9981371,0.0002416546,0.0003456316,0.000360653,0.0008440656,0.00007086856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009515898,0.00005393675,0.000608468,0.00003891681,0.00001207639,2.253762e-7,0.0004266479,0.001670928,0.02226585,0.9482062,0.0001172778,0.02658995],"study_design_scores_gemma":[0.00002904377,0.00006025186,0.001198987,0.0002655203,0.00001541216,0.000009451949,0.000175054,0.5208595,0.1272972,0.3495454,0.0003327804,0.0002113836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1138726,0.00005744657,0.8662571,0.01183012,0.0006104794,0.0006800652,0.0000041546,0.0002191642,0.0064689],"genre_scores_gemma":[0.9385877,0.000008178519,0.06062012,0.0004062097,0.0001445403,0.00008765005,0.000001003471,0.00001337016,0.0001312894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8247151,"threshold_uncertainty_score":0.6001673,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004933358070285787,"gpt":0.2197907985611784,"spread":0.2148574404908927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0002159153,0.0002072696,0.0002913158,0.0001992398,0.00251901,0.0001392062,0.00247177,0.0001617163,0.0001255995],"category_scores_gemma":[0.00004920734,0.0002791127,0.0001516592,0.0002777124,0.0002349543,0.001309381,0.001552559,0.0002876486,0.00007654855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002241393,"about_ca_system_score_gemma":0.00008072499,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00702558,"about_ca_topic_score_gemma":0.0002091945,"domain_scores_codex":[0.9984644,0.00007379826,0.0001237039,0.0005644919,0.0003442523,0.0004293554],"domain_scores_gemma":[0.9980677,0.00006504744,0.0005153177,0.001005868,0.0001123671,0.0002336518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002293473,0.0007099233,0.1412209,0.0002963029,0.0003488076,0.0005105957,0.1065426,0.001230999,0.155465,0.02605749,0.005298958,0.5620891],"study_design_scores_gemma":[0.003210115,0.0002975276,0.4960124,0.0001608773,0.00009991091,0.00004916498,0.00701933,0.4790473,0.002387152,0.0003802349,0.01020965,0.00112637],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8791468,0.0001025819,0.09786056,0.002276576,0.00005390453,0.0001718389,0.00001528169,0.0002586246,0.02011385],"genre_scores_gemma":[0.9641384,0.00001681191,0.03131691,0.00005249636,0.00002840841,3.247657e-7,0.0000108427,0.00001807797,0.00441767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5609628,"threshold_uncertainty_score":0.9999661,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03075027110620818,"gpt":0.3548092531981962,"spread":0.324058982091988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007824943,0.00008625643,0.0000992411,0.00002377348,0.0001202577,0.00009780205,0.0003372112,0.00003870448,0.0000332153],"category_scores_gemma":[0.0001485629,0.00008617806,0.0000456831,0.0002413702,0.00002703375,0.0003268663,0.00009374151,0.00008600225,0.00006150166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001997848,"about_ca_system_score_gemma":0.00002720636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001899888,"about_ca_topic_score_gemma":0.000003736307,"domain_scores_codex":[0.999135,0.00004676664,0.0001674452,0.000378728,0.0001288124,0.0001433185],"domain_scores_gemma":[0.9993877,0.000150987,0.00006978777,0.0001990592,0.0000903627,0.0001021335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003871203,0.0001163332,0.01365061,0.00005996279,0.00004583801,0.000003440662,0.009004581,0.03789169,0.02734868,0.5804636,0.006242948,0.3251336],"study_design_scores_gemma":[0.0003428822,0.00009086822,0.006132839,0.000004489925,0.000003400581,0.00000144379,0.00006659039,0.9833768,0.006880946,0.0005651856,0.002413057,0.0001214727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01214875,0.00001204638,0.97425,0.01195062,0.00007455575,0.000366606,0.000002348929,0.0005355134,0.0006595608],"genre_scores_gemma":[0.9031045,8.9715e-7,0.09531502,0.001237277,0.0001261193,0.00009134454,0.00002312587,0.000008528144,0.00009316869],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9454851,"threshold_uncertainty_score":0.3514239,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02768488918146487,"gpt":0.3282548674715134,"spread":0.3005699782900486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00020174,0.0001025452,0.0001061394,0.00004420563,0.001496436,0.0009013761,0.001418671,0.00003903906,0.0000334293],"category_scores_gemma":[0.0002082736,0.00009137729,0.000072038,0.00004144368,0.00009413022,0.0005013316,0.000350448,0.0001867596,0.00007610101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002370214,"about_ca_system_score_gemma":0.00005780723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005107936,"about_ca_topic_score_gemma":0.00005821522,"domain_scores_codex":[0.9990401,0.00002622664,0.0001464605,0.0003819419,0.0001525611,0.0002526661],"domain_scores_gemma":[0.9984697,0.0001515159,0.0001021303,0.001096014,0.00007748668,0.0001031302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001175183,0.0001226195,0.03875121,0.00003539657,0.00003233525,0.000005471302,0.0008305429,0.003228399,0.001451502,0.6891409,0.004046845,0.262343],"study_design_scores_gemma":[0.0002864368,0.00003062767,0.08705708,0.000004754797,0.000002801445,0.00001015281,0.000004375968,0.8919718,0.0001027474,0.01119841,0.009198098,0.0001326983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03400122,0.000008598921,0.9479759,0.01277819,0.0002027497,0.0002354243,0.000002838672,0.0002679084,0.004527127],"genre_scores_gemma":[0.8228649,3.337487e-7,0.1757898,0.0005402896,0.0001136264,0.0001011818,0.000003303623,0.00000881838,0.0005777269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8887434,"threshold_uncertainty_score":0.9998035,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02946545474529133,"gpt":0.2846817826453462,"spread":0.2552163279000548,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001216215,0.0001179198,0.0001198992,0.00005534158,0.00008135938,0.0001477075,0.0006024246,0.00005537568,0.0002555057],"category_scores_gemma":[0.00002904965,0.0001066589,0.00002863135,0.0002300282,0.00001169254,0.0002497513,0.0001879004,0.0001466901,0.002612676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003296661,"about_ca_system_score_gemma":0.00004245673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001642553,"about_ca_topic_score_gemma":0.00003816807,"domain_scores_codex":[0.998941,0.00005071438,0.0001616919,0.0004353916,0.0002225443,0.0001886251],"domain_scores_gemma":[0.998952,0.0000822061,0.00006432086,0.0007617981,0.00005900262,0.00008069291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001607373,0.0004879145,0.03189452,0.0000157457,0.0001169657,0.000005691195,0.003419706,0.07869617,0.1717818,0.6279227,0.01290231,0.07274039],"study_design_scores_gemma":[0.0003660475,0.00002536936,0.01662214,0.000004263477,0.000003778744,0.000001798305,0.00000776158,0.981055,0.0003746978,0.0009270826,0.000467238,0.0001448218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4215956,0.00001838355,0.5740039,0.0016068,0.0001669136,0.0001872275,0.00001068985,0.000267554,0.002142948],"genre_scores_gemma":[0.870343,3.481547e-7,0.1275678,0.0006418661,0.0001059157,0.00002568932,0.00005208155,0.00001019015,0.001253045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9023588,"threshold_uncertainty_score":0.9981639,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01616013985227046,"gpt":0.2839327377264118,"spread":0.2677725978741414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002417722,0.0002174082,0.0002733742,0.0003651164,0.0003359616,0.0001442815,0.0005433855,0.00007487475,0.0001074476],"category_scores_gemma":[0.000005384775,0.0001988314,0.0001142073,0.001720973,0.00009437478,0.0002392601,0.00001222981,0.0003420204,0.00004674466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002973251,"about_ca_system_score_gemma":0.00000858589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002779562,"about_ca_topic_score_gemma":0.002309388,"domain_scores_codex":[0.9982785,0.0001629902,0.0004051382,0.0006089643,0.0002458394,0.0002985589],"domain_scores_gemma":[0.9989727,0.0001451883,0.0001395394,0.0005465619,0.0000776681,0.0001183878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001084032,0.0001415441,0.009928109,0.000005418719,0.00008394192,0.000001604555,0.000324743,0.5291747,0.0002561298,0.0002207446,0.00002212678,0.4598301],"study_design_scores_gemma":[0.00009952492,0.0000955713,0.01220112,0.00001507205,0.00007392499,0.000003656947,0.000009011502,0.984057,0.002931359,0.0002243448,0.00008551925,0.0002038715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0105527,0.00009691096,0.9881208,0.000675112,0.0001693686,0.0001687701,0.000004912766,0.000120803,0.00009060722],"genre_scores_gemma":[0.9909095,0.0000852666,0.008346792,0.0004950365,0.00003537604,0.00003641626,0.00001314127,0.00001298427,0.00006546466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803568,"threshold_uncertainty_score":0.8108109,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06806887872685286,"gpt":0.3226548770219884,"spread":0.2545859982951356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001438612,0.0002198218,0.0002928567,0.0002797194,0.0003333049,0.0001408871,0.003792818,0.00005184806,0.0002373109],"category_scores_gemma":[0.0007432603,0.0001849174,0.0001571977,0.0008305204,0.0002065114,0.000387788,0.00152816,0.0005343712,0.00002008647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252312,"about_ca_system_score_gemma":0.0001366588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001988351,"about_ca_topic_score_gemma":0.0000805459,"domain_scores_codex":[0.9970998,0.00006994529,0.0008302303,0.000557697,0.001189873,0.000252476],"domain_scores_gemma":[0.9973458,0.0002625229,0.0008364739,0.0004417466,0.001037119,0.00007636206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001138495,0.0004937642,0.0008779544,0.00002668179,0.00004359282,5.121116e-7,0.004407074,0.01824323,0.01855159,0.9407126,0.0001370585,0.01639207],"study_design_scores_gemma":[0.00005685314,0.0002122189,0.01801511,0.00009044784,0.000006923699,0.000007574803,0.0004266881,0.8683635,0.02715075,0.08542056,0.00004281114,0.0002065563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7610486,0.00005234881,0.1949646,0.01877477,0.001392664,0.00138333,0.0002346389,0.0002895969,0.02185937],"genre_scores_gemma":[0.9951455,0.000009845175,0.004325453,0.0001707131,0.00003273653,0.0001095392,0.000007494324,0.00001629149,0.0001824262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8552921,"threshold_uncertainty_score":0.7540712,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06767699411909972,"gpt":0.3792622694143057,"spread":0.311585275295206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007505734,0.0003494691,0.0003194645,0.0004510579,0.0009597972,0.0004408958,0.0003407559,0.0001225089,0.000136582],"category_scores_gemma":[0.0000359179,0.0003767992,0.00009791808,0.0003551563,0.00005932809,0.0005189896,0.0002685702,0.000544189,0.00006086493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212741,"about_ca_system_score_gemma":0.0001017516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088998,"about_ca_topic_score_gemma":0.00004015421,"domain_scores_codex":[0.9973435,0.0005316333,0.0004614732,0.001012059,0.0003157188,0.000335585],"domain_scores_gemma":[0.9981999,0.000692323,0.0002794839,0.0003452573,0.0002907616,0.0001922204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008627146,0.0005197531,0.0008585485,0.00009068382,0.0000173579,0.000003479862,0.0007407886,0.001861133,0.003872856,0.0005009706,0.0002989216,0.9911492],"study_design_scores_gemma":[0.00166736,0.0009836555,0.01862545,0.0001184405,0.00001900683,0.00003182911,0.00004761305,0.9752714,0.0007562657,0.0007486386,0.00128644,0.0004439069],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3285006,0.00003887999,0.6688764,0.0007310643,0.0007533727,0.0006632897,0.00004130839,0.000255765,0.0001393436],"genre_scores_gemma":[0.9798418,0.00002087996,0.0185441,0.0004319355,0.0002611229,0.0005071588,0.0002903282,0.00003430702,0.00006838775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9907053,"threshold_uncertainty_score":0.9998684,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02246753577189608,"gpt":0.3164347830586666,"spread":0.2939672472867705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007806464,0.0000334236,0.00004467212,0.00001988404,0.0001447041,0.00007675336,0.0006466645,0.00001631404,0.00001837117],"category_scores_gemma":[0.00008482007,0.000028134,0.00002124502,0.00002163602,0.00002119255,0.0002266605,0.0001443736,0.00005273579,0.00003359522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006051852,"about_ca_system_score_gemma":0.00001385771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001139589,"about_ca_topic_score_gemma":0.00005086774,"domain_scores_codex":[0.9996668,0.0000123636,0.00006703525,0.0001124533,0.00008545526,0.00005596232],"domain_scores_gemma":[0.9992081,0.00001423648,0.00008196318,0.0006492967,0.00002912286,0.00001728778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003491461,0.00005843146,0.008285578,0.000007286211,0.00001680187,0.000002337075,0.001518068,0.0005307376,0.2692534,0.4413786,0.00126748,0.2776778],"study_design_scores_gemma":[0.0002168923,0.00001054198,0.09975242,0.000001512885,0.000001614029,0.000001335685,0.000005742515,0.8805943,0.01890002,0.000172519,0.0002848238,0.00005824633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5391355,0.00002622411,0.4420946,0.002196226,0.0004060755,0.0000984804,8.490501e-7,0.0001016466,0.0159404],"genre_scores_gemma":[0.9201492,3.43185e-7,0.07928457,0.00004331332,0.00009899986,0.000003171241,0.000001948725,0.000001671361,0.0004167521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8800636,"threshold_uncertainty_score":0.1722725,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1648509459164146,"gpt":0.2514998793910733,"spread":0.08664893347465866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006548253,0.0004122606,0.000475376,0.0005586247,0.0002105747,0.0001559725,0.001568424,0.0003380669,0.00003263798],"category_scores_gemma":[0.0006125689,0.0004830219,0.0001782664,0.0006204281,0.00007887473,0.0003464748,0.001625415,0.002519021,0.0003169868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000277364,"about_ca_system_score_gemma":0.0001208665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004433926,"about_ca_topic_score_gemma":0.0007317598,"domain_scores_codex":[0.9964796,0.0004882275,0.0004090064,0.002007398,0.0001955402,0.0004202613],"domain_scores_gemma":[0.9967374,0.0004581427,0.0006993539,0.001743141,0.0001912429,0.0001707698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001852569,0.0001409404,0.1524258,0.00004285411,0.00004178154,0.0005796374,0.0004216142,0.7417468,0.00002837796,0.09458916,0.00001421479,0.009950292],"study_design_scores_gemma":[0.0004543219,0.000088505,0.1659942,0.0001210569,0.0000161516,0.000027554,0.00004633778,0.8134295,0.00001906223,0.01877719,0.0006203203,0.0004057327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7718166,0.0002766151,0.2036183,0.001915607,0.0003042618,0.0009852329,0.000001964926,0.001000913,0.0200805],"genre_scores_gemma":[0.9959579,0.0004260723,0.001751087,0.00003212019,0.00006425404,0.00001837549,0.00005558328,0.00003785294,0.001656731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2241413,"threshold_uncertainty_score":0.9997822,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04774393774670666,"gpt":0.3167447715831568,"spread":0.2690008338364502,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003300525,0.0001734391,0.0001472843,0.0001297704,0.000525368,0.0002409745,0.001234201,0.00007083367,0.00003629797],"category_scores_gemma":[0.0003923741,0.0001217028,0.00005396737,0.0008920235,0.000351119,0.0004102221,0.0002062249,0.0003509525,0.0001062049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000466385,"about_ca_system_score_gemma":0.0000512651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001194435,"about_ca_topic_score_gemma":0.00006991549,"domain_scores_codex":[0.9985198,0.00002252535,0.0003368224,0.0004463032,0.0004187365,0.0002557656],"domain_scores_gemma":[0.9984748,0.0001220671,0.0003450099,0.0002764773,0.0007171959,0.00006441605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007017404,0.00003736128,0.006326217,0.0000135666,0.00001066862,1.02758e-7,0.001682347,0.0001380551,0.03518647,0.8257719,0.000002928281,0.1307602],"study_design_scores_gemma":[0.00003353711,0.000329199,0.02537529,0.00007713203,0.00001097316,0.00001023555,0.0001673112,0.5554467,0.3068952,0.1114423,0.00001681365,0.0001953078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7075831,0.000003385019,0.2861,0.001190766,0.0001736593,0.0003075876,5.225205e-7,0.0001489172,0.004492107],"genre_scores_gemma":[0.9887968,7.539192e-7,0.01091812,0.00008588975,0.0001138055,0.00002940811,2.606652e-7,0.0000118541,0.00004307351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7143297,"threshold_uncertainty_score":0.4962895,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03235914812416576,"gpt":0.2967623643262253,"spread":0.2644032162020595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000245506,0.00008252144,0.00007041152,0.00007097811,0.00054655,0.0001338766,0.0004981143,0.00001893769,0.0001661716],"category_scores_gemma":[0.00004315937,0.0000859488,0.00005072829,0.0002257438,0.00001209776,0.0002970802,0.0001931682,0.0001206614,0.00003276299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000663836,"about_ca_system_score_gemma":0.0000458713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006318132,"about_ca_topic_score_gemma":0.00004742044,"domain_scores_codex":[0.999063,0.00006963436,0.0001703468,0.0003501666,0.0001889272,0.0001578902],"domain_scores_gemma":[0.9993415,0.00006145578,0.00007198153,0.0004144759,0.00006327958,0.0000472328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001035612,0.0002436962,0.0005415227,0.000009545901,0.0000149911,0.000001286513,0.0009935611,0.08021183,0.243684,0.4146238,0.01616547,0.2434999],"study_design_scores_gemma":[0.0003132151,0.00006950128,0.001660176,1.668971e-7,0.000002299385,0.000005080138,0.00002800183,0.9797021,0.001225865,0.000999782,0.01588216,0.0001116938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0280522,0.00000543365,0.9637879,0.004855834,0.0001911768,0.0005338856,0.000007937034,0.0003031775,0.002262459],"genre_scores_gemma":[0.6091956,3.588262e-7,0.3889669,0.0004690054,0.0001060274,0.0005703252,0.00006771179,0.000007527573,0.000616512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8994902,"threshold_uncertainty_score":0.4203676,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008055523171589318,"gpt":0.2765739735873576,"spread":0.2685184504157683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005886242,0.00008944797,0.0001238455,0.00004327286,0.0001271694,0.00007115437,0.0003492979,0.0000453024,0.00002280786],"category_scores_gemma":[0.00004541126,0.00008082426,0.00006841204,0.0001514176,0.00002493208,0.0002846224,0.00009344351,0.0001210104,0.000182026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004201294,"about_ca_system_score_gemma":0.00002673545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006684647,"about_ca_topic_score_gemma":0.000003264457,"domain_scores_codex":[0.9991221,0.00009169721,0.0001335054,0.0003243239,0.0001299956,0.0001983409],"domain_scores_gemma":[0.9991749,0.0001679274,0.000109925,0.0004143359,0.00008729158,0.00004560047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005546223,0.00006780414,0.01020494,0.00007999597,0.00003315942,0.000001004158,0.0003004818,0.0490354,0.00126451,0.8085345,0.001431838,0.1289909],"study_design_scores_gemma":[0.001250174,0.0000506514,0.03448919,0.00003800031,0.000006406041,0.00000429505,0.00001139033,0.9571294,0.00007886586,0.005313473,0.001471117,0.0001570266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09566401,0.0001163159,0.8979897,0.00164883,0.000365731,0.001032062,5.162516e-7,0.0004137666,0.002769082],"genre_scores_gemma":[0.7321036,0.000001116668,0.2659923,0.0001440032,0.0001303241,0.0002643103,0.000009067346,0.000009380643,0.001345894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.908094,"threshold_uncertainty_score":0.3295918,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01768662620118641,"gpt":0.293410836131722,"spread":0.2757242099305356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002020448,0.00009108106,0.0001468885,0.00007495482,0.000269062,0.0003567939,0.0008044482,0.00004553928,0.0000108863],"category_scores_gemma":[0.0001179839,0.00008211179,0.00002155164,0.00008188362,0.00005619489,0.0003428973,0.0003717657,0.00006908405,0.00002261182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001904335,"about_ca_system_score_gemma":0.00002873353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003860651,"about_ca_topic_score_gemma":0.00006977852,"domain_scores_codex":[0.9991533,0.000050226,0.0001903351,0.0002983418,0.0001749669,0.0001328983],"domain_scores_gemma":[0.9987137,0.00008758599,0.0001836369,0.0008189118,0.0001003512,0.00009584566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000927416,0.0001292749,0.02643525,0.00006736848,0.00004275984,0.000002649314,0.001273597,0.3702055,0.00476227,0.5719841,0.0002447258,0.02484323],"study_design_scores_gemma":[0.0002034197,0.00004880041,0.109107,0.00001472585,0.000004263599,0.000004049466,0.000009353226,0.8900375,0.0001188863,0.0001547099,0.0001995491,0.00009776052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03874923,0.000009674429,0.95287,0.001055582,0.000119068,0.0002933745,0.000003554414,0.0001037722,0.006795742],"genre_scores_gemma":[0.8526888,0.000004306224,0.1469848,0.00004516368,0.00003351991,0.00003084437,0.000004645758,0.000006606255,0.0002013047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8139395,"threshold_uncertainty_score":0.5836174,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04293762358184849,"gpt":0.2187895967167586,"spread":0.1758519731349101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002175456,0.0001686464,0.0002287882,0.0001675628,0.00005369518,0.00005210332,0.001067853,0.0001325016,0.00001061433],"category_scores_gemma":[0.0000854295,0.0001918049,0.0000537116,0.0003835782,0.0001104133,0.0001596455,0.001973654,0.0003746343,0.00002638846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005135785,"about_ca_system_score_gemma":0.0001166819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00142833,"about_ca_topic_score_gemma":0.00001523748,"domain_scores_codex":[0.998952,0.00007371599,0.0001230187,0.0006256586,0.00006663814,0.0001590234],"domain_scores_gemma":[0.9984983,0.00008302104,0.0002136592,0.0008853775,0.0002003129,0.0001193696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004444786,0.0003764197,0.04947312,0.0005757859,0.0002709498,0.0002614516,0.007324167,0.3523428,0.002649399,0.5705364,0.002320845,0.01382428],"study_design_scores_gemma":[0.0004988124,0.00004485555,0.01205891,0.00007255447,0.00005445427,0.00000679981,0.0001750201,0.9543968,0.0004957439,0.03145226,0.0003204414,0.0004233553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.640139,0.0001049424,0.3554484,0.0001723544,0.00006992414,0.0001593389,0.00001498758,0.0001712668,0.00371973],"genre_scores_gemma":[0.9840917,0.00003556773,0.0151493,0.00002700852,0.00002194725,7.535943e-7,0.000008479735,0.0000106303,0.0006545961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6020541,"threshold_uncertainty_score":0.7821577,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02151848015296971,"gpt":0.2306801638018164,"spread":0.2091616836488467,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005074481,0.00006502328,0.00007512975,0.00003098642,0.00005329308,0.0000942912,0.0002352343,0.00001879805,0.00002299103],"category_scores_gemma":[0.00004005272,0.00005276104,0.00002025218,0.0002210148,0.00002541778,0.0005460928,0.0001019772,0.000104625,0.0000429244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000103671,"about_ca_system_score_gemma":0.00002012112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001326254,"about_ca_topic_score_gemma":0.000009978121,"domain_scores_codex":[0.9994017,0.00002401041,0.0001202115,0.0002231324,0.0001305803,0.0001003767],"domain_scores_gemma":[0.999495,0.00004829224,0.00008371355,0.0002444726,0.00006926609,0.00005926794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003159955,0.00009973404,0.07565247,0.0001126125,0.00004642368,0.00001079917,0.004245131,0.01830934,0.7046508,0.05215101,0.0006430107,0.1440471],"study_design_scores_gemma":[0.000170175,0.00007446202,0.03275616,0.000006250559,0.000004864803,0.000003710882,0.00001300769,0.961164,0.005432217,0.0000544487,0.0002176592,0.0001030183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2538826,0.000001427526,0.7418215,0.003819544,0.000006841958,0.00007567948,5.743877e-7,0.0001408808,0.0002509436],"genre_scores_gemma":[0.5794617,1.276269e-7,0.4200208,0.0004724909,0.00001548153,0.000005890048,0.000001270851,0.000004101037,0.0000181172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9428547,"threshold_uncertainty_score":0.2151533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08715630185034338,"gpt":0.3538858751306011,"spread":0.2667295732802577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004929177,0.000245819,0.0002882202,0.0000954405,0.0005195398,0.000536513,0.002146723,0.00009639983,0.00004631963],"category_scores_gemma":[0.001437951,0.0002037562,0.0001945738,0.0007608861,0.0002626716,0.0004341514,0.0004278013,0.0005293433,0.000111715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003718014,"about_ca_system_score_gemma":0.00007875161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007948207,"about_ca_topic_score_gemma":0.000003170936,"domain_scores_codex":[0.9979155,0.00002344784,0.000560823,0.0006738601,0.000427754,0.0003986089],"domain_scores_gemma":[0.998218,0.0002557271,0.0004752457,0.0001938287,0.0006972151,0.0001599816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007289013,0.00007099651,0.002376638,0.00005135041,0.00001519859,1.196468e-7,0.002369402,0.0005097835,0.03775868,0.8646373,0.00003611,0.09210156],"study_design_scores_gemma":[0.00009037555,0.0006694672,0.00168868,0.0001055395,0.00001499486,0.000002812546,0.0008073371,0.7202037,0.1855938,0.08999804,0.0004590502,0.0003662363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5575172,0.00001566281,0.4240799,0.01359325,0.0002728197,0.0009360551,0.000005160762,0.000344264,0.003235617],"genre_scores_gemma":[0.9925161,0.000005850614,0.00655402,0.0005792797,0.0001390671,0.0001025759,0.000001096955,0.00002144407,0.00008054553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7746392,"threshold_uncertainty_score":0.8308936,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1113495865189584,"gpt":0.3552552529180734,"spread":0.243905666399115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003744293,0.0000656692,0.00008046762,0.00002802435,0.0009009818,0.0002600389,0.001615726,0.00002022406,0.000004360403],"category_scores_gemma":[0.0002856451,0.0000442639,0.00006180679,0.00003776593,0.00007204304,0.0002648079,0.0002771536,0.0001071551,0.00001601034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001246815,"about_ca_system_score_gemma":0.00003592113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003708315,"about_ca_topic_score_gemma":0.0003734181,"domain_scores_codex":[0.9994282,0.0000255641,0.0001535565,0.0001994646,0.00006780204,0.000125404],"domain_scores_gemma":[0.9982496,0.0002276908,0.0002219286,0.001197805,0.00006975943,0.0000332247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002219208,0.0000186323,0.01357456,0.000008156625,0.000009831423,2.933557e-7,0.0004610635,0.0003034215,0.0005751383,0.9693827,0.0009176383,0.01474637],"study_design_scores_gemma":[0.0004952208,0.00006078444,0.1360507,0.00005463753,0.00001200019,0.00001844004,0.0001048496,0.7720634,0.001491864,0.07114102,0.01826028,0.0002468245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06062602,0.00001040651,0.9189081,0.01705117,0.000119237,0.0002278382,0.000001036679,0.00008518566,0.002971032],"genre_scores_gemma":[0.8784928,4.508827e-7,0.1208906,0.0001579074,0.00005252926,0.00005498311,0.000001025634,0.000005333683,0.0003444495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8982416,"threshold_uncertainty_score":0.6929714,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02537338834740047,"gpt":0.2891620705912578,"spread":0.2637886822438573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001234534,0.0001287095,0.0001420996,0.0000406328,0.0001810833,0.0003067927,0.0008424226,0.00005459286,0.000046774],"category_scores_gemma":[0.0001169433,0.0001186125,0.00005976784,0.0004969091,0.00005685582,0.0002820235,0.0003122117,0.0002781668,0.0001754962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003745094,"about_ca_system_score_gemma":0.00009633759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003704775,"about_ca_topic_score_gemma":0.000004326676,"domain_scores_codex":[0.9988601,0.00007359175,0.0001778645,0.0004102443,0.0002580533,0.0002201219],"domain_scores_gemma":[0.9991488,0.00009133463,0.00006984823,0.0004302537,0.0000833603,0.000176419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006973465,0.0001377321,0.002013477,0.00005047703,0.00006376734,0.00004471069,0.001713206,0.004004004,0.8084535,0.1762035,0.002856308,0.004389589],"study_design_scores_gemma":[0.0004251315,0.00005629977,0.01178825,0.000007306841,0.000007838754,0.00001898197,0.00001787888,0.9642376,0.02023223,0.001403085,0.001553233,0.0002521429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0818961,0.0000249579,0.8997451,0.01370239,0.00006229103,0.0001785613,0.000001384913,0.0006399483,0.003749234],"genre_scores_gemma":[0.5711157,6.701746e-7,0.4262591,0.002489288,0.00006741518,7.411192e-7,0.000002515573,0.000009027533,0.00005556189],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9602336,"threshold_uncertainty_score":0.4836876,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"University of Johannesburg","keywords":"Computer science; Management science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02134894238762933,"gpt":0.3679048077687132,"spread":0.3465558653810838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007336382,0.0003330289,0.001327436,0.000213541,0.0001163342,0.00004248703,0.0007485139,0.0001395985,0.000007829877],"category_scores_gemma":[0.0006446288,0.0003007152,0.0002492042,0.0007152905,0.0001117653,0.000312831,0.001383108,0.0006498307,0.00000349835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003675765,"about_ca_system_score_gemma":0.0004808676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008425879,"about_ca_topic_score_gemma":0.00001058028,"domain_scores_codex":[0.9969787,0.0009225166,0.000699694,0.0007632137,0.0002465637,0.0003893323],"domain_scores_gemma":[0.9979339,0.0004924323,0.0003337568,0.001101333,0.00007685003,0.00006174391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001126296,0.0002522263,0.0001918546,0.3341057,0.00004251283,0.000006969096,0.0008605773,0.0002626256,1.093101e-7,0.03122244,0.00005352695,0.6330003],"study_design_scores_gemma":[0.0002410549,0.00003510347,0.0006446444,0.04427492,0.0001768814,0.000004378282,0.0003471844,0.00913708,1.737625e-7,0.004117423,0.9405468,0.0004743488],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002039214,0.9719272,0.02567493,0.0003700305,0.00002218134,0.001644003,0.00003874309,0.000044513,0.0002580147],"genre_scores_gemma":[0.0006421635,0.9974589,0.00102113,0.00005792085,0.000008939631,0.0003678037,0.00007997834,0.00001390287,0.0003492839],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9404933,"threshold_uncertainty_score":0.9999445,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06370869466700849,"gpt":0.2035532282945449,"spread":0.1398445336275364,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001619413,0.0002417709,0.0002095029,0.000154831,0.0002258811,0.0002035963,0.001254442,0.0001563818,0.00001934126],"category_scores_gemma":[0.00002702244,0.0002575861,0.00008694136,0.0003863338,0.00007491822,0.0003134948,0.001175722,0.0005996337,0.0001821446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001901865,"about_ca_system_score_gemma":0.0002017059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004533947,"about_ca_topic_score_gemma":0.0001712272,"domain_scores_codex":[0.9983744,0.0001438181,0.0001426572,0.001012618,0.0001035542,0.0002229545],"domain_scores_gemma":[0.9979794,0.00006961229,0.0002503272,0.001277966,0.0002613375,0.0001613752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005532394,0.00006166842,0.01417032,0.00001042478,0.0000666783,0.00004726203,0.0001691571,0.9610744,0.0004565601,0.02295208,0.0002336206,0.0007523384],"study_design_scores_gemma":[0.0003127639,0.00002254956,0.0164797,0.00004638234,0.00005938028,0.000002646532,0.00003807092,0.9695531,0.00003093435,0.01301615,0.0001127341,0.0003256115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4405344,0.00002098646,0.5578642,0.0001761746,0.00009452077,0.0001468002,0.00002522364,0.0002696523,0.0008680313],"genre_scores_gemma":[0.9408504,0.00001154278,0.05816986,0.00004471229,0.0001087148,0.000003817993,0.0001099624,0.00001807437,0.0006829158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.500316,"threshold_uncertainty_score":0.9999877,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Ground; Transformer; Task (project management); Computer science; Engineering; Electrical engineering; Systems engineering; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.1171326450951862,"gpt":0.2384591119005074,"spread":0.1213264668053212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003338521,0.0004480102,0.0004918115,0.0004624802,0.0003672726,0.0003927623,0.002439064,0.0003349241,0.00001802665],"category_scores_gemma":[0.00005538058,0.0005816605,0.0002943728,0.001239526,0.00005797171,0.0004224318,0.00126012,0.001240549,0.000113892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004579193,"about_ca_system_score_gemma":0.000224581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001885845,"about_ca_topic_score_gemma":0.0001106412,"domain_scores_codex":[0.9966491,0.0002221589,0.0003147085,0.002042614,0.000189391,0.0005820206],"domain_scores_gemma":[0.9976081,0.000102455,0.0002002687,0.001526568,0.0001749634,0.0003876019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003840444,0.001459894,0.006769865,0.0004239581,0.0003746314,0.0001337391,0.004736285,0.7989318,0.002442363,0.1732944,0.00003935804,0.0113552],"study_design_scores_gemma":[0.0005456803,0.00003814145,0.009403799,0.0001246749,0.00007357481,0.000008114811,0.0002863908,0.9878785,0.0001874536,0.0004437067,0.000291622,0.0007183229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3116747,0.00002010597,0.6842224,0.0001109732,0.000167404,0.0004800976,0.000005491342,0.0004055996,0.002913259],"genre_scores_gemma":[0.8859056,0.000027254,0.1132716,0.0001512324,0.00006957598,0.00001378302,0.00004794824,0.00003945392,0.0004735777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5742308,"threshold_uncertainty_score":0.9996635,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02133016029766966,"gpt":0.2892003363021184,"spread":0.2678701760044487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000150633,0.00004588727,0.00008031131,0.00005600639,0.00005292165,0.00002729599,0.0002322124,0.00001974946,0.000007550742],"category_scores_gemma":[0.00003948042,0.00003946204,0.00001452927,0.000391893,0.00002632219,0.00007670403,0.0002158509,0.00005154388,0.00007893367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003403041,"about_ca_system_score_gemma":0.000009781977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002961861,"about_ca_topic_score_gemma":0.00002197495,"domain_scores_codex":[0.9995325,0.00002637363,0.00009453137,0.0001477654,0.00009164859,0.0001071999],"domain_scores_gemma":[0.9994084,0.0001993032,0.00003479341,0.000292625,0.00002324435,0.0000416486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000002477637,0.0001219431,0.4028257,0.00007048716,0.00002894874,0.00000747284,0.002155651,0.002114405,0.008187233,0.4752185,0.00906972,0.1001974],"study_design_scores_gemma":[0.0001324082,0.00003399568,0.7197753,0.000007808515,0.000002030778,0.00000318042,0.00002163342,0.2682069,0.003745627,0.006826419,0.001161111,0.00008361696],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9333084,0.00003864672,0.05411417,0.005578033,0.00005784137,0.0001570875,0.000003168275,0.0006598709,0.006082814],"genre_scores_gemma":[0.9903898,0.00000707445,0.009271326,0.0000783957,0.000008272894,0.00001132332,0.000003199955,0.000003002557,0.0002275521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4683921,"threshold_uncertainty_score":0.1609215,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.09663262041000328,"gpt":0.3077191104554348,"spread":0.2110864900454315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003293297,0.0002551606,0.0002613881,0.00008300995,0.0003818216,0.0003085366,0.001751733,0.00009285558,0.00001646889],"category_scores_gemma":[0.0006803833,0.0002014992,0.0001648416,0.0009198263,0.0002138519,0.0003130485,0.0002643566,0.0003379356,0.00001433429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002952904,"about_ca_system_score_gemma":0.00005300487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003973966,"about_ca_topic_score_gemma":0.00001401336,"domain_scores_codex":[0.9980345,0.00003286628,0.0005435964,0.000695923,0.0003489804,0.0003441428],"domain_scores_gemma":[0.9982093,0.0001241078,0.0004155723,0.0002919149,0.0008118959,0.0001471987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004292617,0.00008360852,0.0001831717,0.00003410744,0.00001551065,9.515139e-8,0.001172544,0.06415281,0.02691992,0.8618849,0.0001087651,0.04540166],"study_design_scores_gemma":[0.00003516171,0.0002320866,0.0001558626,0.00002256013,0.00001450451,0.000001198388,0.00005887227,0.8891553,0.04297586,0.06714015,0.00001671713,0.0001917499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03771889,0.00002386481,0.9464791,0.01339174,0.0002602946,0.001467639,0.000004490745,0.0001542659,0.0004996851],"genre_scores_gemma":[0.9661045,0.000008962849,0.03232658,0.0009528251,0.0002667656,0.000307176,0.000003597214,0.00001752153,0.00001207446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9283856,"threshold_uncertainty_score":0.8216898,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Suite; Benchmarking; Computer science; Transformer; Benchmark (surveying); Artificial intelligence; Machine learning; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01244723705163878,"gpt":0.2729188266178351,"spread":0.2604715895661963,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001595608,0.00008695674,0.00009895159,0.00004411011,0.0001390901,0.0000849604,0.0003375235,0.00003252722,0.00009814283],"category_scores_gemma":[0.00004821744,0.00007886214,0.00009379714,0.0003371341,0.00001661302,0.0000680282,0.00005305467,0.00008213604,0.0000458914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002689847,"about_ca_system_score_gemma":0.00007512095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000064298,"about_ca_topic_score_gemma":0.00003879851,"domain_scores_codex":[0.9991223,0.00002481041,0.0001405915,0.0003424987,0.0001467148,0.0002231405],"domain_scores_gemma":[0.9992895,0.000162047,0.00002685036,0.0003450742,0.00009485837,0.00008170234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001899379,0.0006396228,0.009915725,0.00014795,0.00008095326,0.00002183178,0.003083067,0.02052997,0.004288178,0.3579328,0.00257798,0.600763],"study_design_scores_gemma":[0.0007355427,0.00003625973,0.04470792,0.00001266568,0.000009816151,0.00001720825,0.00003646801,0.9414935,0.003013979,0.0008547575,0.008859206,0.0002227395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03569816,0.00006766748,0.9485661,0.005039262,0.0001013446,0.000265831,0.000003314661,0.0001704285,0.01008792],"genre_scores_gemma":[0.8682486,0.00000240168,0.1306392,0.0003848316,0.00002823182,0.0001225803,0.00001012949,0.000006758588,0.0005571714],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9209635,"threshold_uncertainty_score":0.3215905,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06700293859533554,"gpt":0.3442383981747281,"spread":0.2772354595793926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004243244,0.0003068807,0.0003374388,0.0001971756,0.000157916,0.000296749,0.001399312,0.0002236722,0.00003309067],"category_scores_gemma":[0.0001407822,0.0002570375,0.00008808001,0.000276822,0.0000827414,0.0004656917,0.001870189,0.0006787761,0.00007447344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006990036,"about_ca_system_score_gemma":0.0001696244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002884282,"about_ca_topic_score_gemma":0.000309775,"domain_scores_codex":[0.9979433,0.0001401944,0.0004036775,0.0008402628,0.0003179571,0.0003545527],"domain_scores_gemma":[0.998193,0.0002932828,0.0001970462,0.001195092,0.00005953613,0.0000620307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001462614,0.00002306969,0.005675936,0.00005665001,0.0000143699,0.000003869693,0.002070409,0.003431979,0.00006396157,0.9869326,0.0001112448,0.001614388],"study_design_scores_gemma":[0.0002621368,0.00001664775,0.01034317,0.000500086,0.000006872469,0.000005010865,0.0002288809,0.07070447,0.0002023983,0.9157521,0.001361605,0.0006166389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004818693,0.0002002274,0.9581795,0.007230123,0.0006044444,0.0003436718,0.000004882517,0.000674422,0.027944],"genre_scores_gemma":[0.8392356,0.00007596705,0.1597973,0.0001278443,0.000120268,0.0001572455,0.000005314136,0.00002306475,0.0004573595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8344169,"threshold_uncertainty_score":0.9999882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}