{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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","author_layer_release":"2026-06-26"},"query_hash":"6fa7af046c3f","filters":{"venue":"Biomedical Informatics Insights"}},"results":[{"id":"W2053479646","doi":"10.4137/bii.s4706","title":"Suicide Note Classification Using Natural Language Processing: A Content Analysis","year":2010,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"Mental Health via Writing","field":"Psychology","cited_by":239,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor; Windsor Clinical Research","funders":"U.S. National Library of Medicine","keywords":"Categorization; Mental health; Suicide prevention; Psychology; Occupational safety and health; Human factors and ergonomics; Injury prevention; Poison control; Suicide attempt; Artificial intelligence; Psychiatry; Machine learning; Medicine; Medical emergency; Computer science","authors":[{"name":"John Pestian","is_ca":false},{"name":"Henry A. Nasrallah","is_ca":false},{"name":"Paweł Matykiewicz","is_ca":false},{"name":"Aurora J. Bennett","is_ca":false},{"name":"Antoon A. Leenaars","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1168740545948059,"gpt":0.42183088917571,"spread":0.3049568345809041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003013259,0.0003370111,0.0003556376,0.005296305,0.0005034102,0.001341285,0.0004358312,0.0004378331,0.001308664],"category_scores_gemma":[0.01666204,0.0001200664,0.0005039827,0.002482611,0.0005955021,0.001314583,0.0008556593,0.0004160756,0.0004285852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009984619,"about_ca_system_score_gemma":0.0008317505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002499124,"about_ca_topic_score_gemma":0.002301503,"domain_scores_codex":[0.9972205,0.00151552,0.0003754884,0.0002833846,0.0005006844,0.000104316],"domain_scores_gemma":[0.9763925,0.01853574,0.001115011,0.0007584412,0.003029708,0.0001684714],"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":[0.001490574,0.001220988,0.2126012,0.001579415,0.0002426729,0.0009352569,0.01605997,0.004271101,0.03445453,0.003089389,0.004974515,0.7190804],"study_design_scores_gemma":[0.0002448742,0.001802946,0.6187309,0.0007341261,0.0006229633,0.00266657,0.02984262,0.252802,0.05767485,0.01196434,0.02256361,0.0003502129],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9175465,0.0003898874,0.07375561,0.0004910936,0.00005301616,0.00154744,0.002295669,0.0004695933,0.003451162],"genre_scores_gemma":[0.8420543,0.0002914726,0.1519458,0.000120557,0.00006849241,0.00105397,0.003419182,0.00004292949,0.001003374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005296305,"threshold_uncertainty_score":0.01593578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117808614","doi":"10.4137/bii.s8933","title":"Binary Classifiers and Latent Sequence Models for Emotion Detection in Suicide Notes","year":2012,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sentence; Computer science; Classifier (UML); Artificial intelligence; Task (project management); Margin (machine learning); Binary classification; Sequence (biology); Natural language processing; Sentiment analysis; Machine learning; Support vector machine","authors":[{"name":"Colin Cherry","is_ca":true},{"name":"Saif M. Mohammad","is_ca":true},{"name":"Berry de Bruijn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09195606268752786,"gpt":0.304605320211808,"spread":0.2126492575242801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00261791,0.0007213885,0.0007856562,0.001419649,0.0005934043,0.001277196,0.001225404,0.001111441,0.002391613],"category_scores_gemma":[0.009657689,0.0003703322,0.0009413007,0.0009919736,0.0005062027,0.002212982,0.0007293719,0.002413878,0.001774448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001244769,"about_ca_system_score_gemma":0.0007526517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004543944,"about_ca_topic_score_gemma":0.005283236,"domain_scores_codex":[0.9986666,0.0006358516,0.00008763015,0.0002869467,0.0002055952,0.0001173275],"domain_scores_gemma":[0.9950814,0.003577006,0.0004587801,0.0002496119,0.0005214544,0.0001116485],"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":[0.001074783,0.0007160247,0.01459794,0.0003698688,0.0001798314,0.0002811807,0.0006934914,0.2913152,0.0117892,0.04935958,0.01471897,0.6149039],"study_design_scores_gemma":[0.00001245979,0.00002711039,0.0007512504,0.00001434886,0.000008520281,0.00001680835,0.00002600521,0.980565,0.0006653126,0.01720821,0.0006954662,0.000009527732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05315231,0.001096096,0.940527,0.001239786,0.0001534277,0.0001090577,0.0006947313,0.001126291,0.001901347],"genre_scores_gemma":[0.6989214,0.0008935559,0.2892873,0.0003932342,0.000402165,0.0004565487,0.003535247,0.000184127,0.005926393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004543944,"threshold_uncertainty_score":0.01384503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2592357996","doi":"10.1177/1178222616685880","title":"Using Electronic Medical Record to Identify Patients With Dyslipidemia in Primary Care Settings: International Classification of Disease Code Matters From One Region to a National Database","year":2017,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Newfoundland and Labrador Centre for Applied Health Research; Memorial University of Newfoundland","funders":"","keywords":"Dyslipidemia; Primary care; Code (set theory); Disease; Database; Medicine; Electronic medical record; Diagnosis code; Family medicine; Computer science; Environmental health; Internal medicine; Programming language","authors":[{"name":"Justin D. Oake","is_ca":true},{"name":"Erfan Aref‐Eshghi","is_ca":true},{"name":"Marshall Godwin","is_ca":true},{"name":"Kayla Collins","is_ca":true},{"name":"Kris Aubrey‐Bassler","is_ca":true},{"name":"Pauline Duke","is_ca":true},{"name":"Masoud Mahdavian","is_ca":true},{"name":"Shabnam Asghari","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1969904572469815,"gpt":0.4538241114220723,"spread":0.2568336541750909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004432759,0.0002272105,0.0005289168,0.00309863,0.0003419686,0.001440319,0.0005298801,0.0003951369,0.001035081],"category_scores_gemma":[0.02864802,0.0001462677,0.0003274266,0.004301971,0.0002439254,0.0006665161,0.0007708453,0.0004075871,0.0002391363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047752,"about_ca_system_score_gemma":0.001632536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03890543,"about_ca_topic_score_gemma":0.06457014,"domain_scores_codex":[0.9941934,0.001795909,0.0008894086,0.0008399228,0.001977109,0.0003043145],"domain_scores_gemma":[0.9773949,0.006910788,0.009301117,0.00129308,0.004407417,0.0006926752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005113794,0.00002289149,0.9952377,0.00004452302,0.00004684851,0.00002119872,0.00007133735,0.00002651977,0.00006649017,0.00001428082,0.00042541,0.003971707],"study_design_scores_gemma":[0.00001149708,0.00004774462,0.9984599,0.00005993532,0.00004548443,0.0001148709,0.0001752773,0.0004910487,0.00009834986,0.00001518574,0.0004768332,0.000003778868],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874172,0.0009414827,0.0006175119,0.000495539,0.00004909302,0.0001672026,0.007485749,0.00003161958,0.002794668],"genre_scores_gemma":[0.9910238,0.0003952618,0.001715485,0.0002163294,0.00004939395,0.00009619824,0.006201969,0.000004331202,0.0002972854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03890543,"threshold_uncertainty_score":0.07735795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1875130055","doi":"10.4137/bii.s2222","title":"Avoiding Pitfalls in the Statistical Analysis of Heterogeneous Tumors","year":2009,"lang":"en","type":"article","venue":"Biomedical Informatics Insights","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University Health Network","funders":"National Cancer Institute","keywords":"Context (archaeology); Computer science; Feature (linguistics); Focus (optics); Sample (material); Data science; Biology","authors":[{"name":"David Axelrod","is_ca":false},{"name":"Naomi Miller","is_ca":true},{"name":"Judith‐Anne W. Chapman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01683642819409829,"gpt":0.2720042407984965,"spread":0.2551678126043982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4070199,0.001451822,0.003935678,0.005361806,0.0030403,0.004697219,0.003648388,0.002982296,0.0007044885],"category_scores_gemma":[0.6250923,0.001417455,0.002738876,0.005256308,0.01152235,0.004523257,0.00409932,0.009495991,0.00036858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001941728,"about_ca_system_score_gemma":0.003011131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001910474,"about_ca_topic_score_gemma":0.002240248,"domain_scores_codex":[0.6545992,0.2874433,0.02210318,0.01170225,0.02288733,0.00126475],"domain_scores_gemma":[0.1936093,0.7191088,0.01625661,0.05055321,0.01913223,0.001339876],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002881289,0.0003439055,0.1317529,0.003203179,0.004438386,0.004157431,0.007725779,0.03673587,0.008123346,0.14236,0.01914178,0.6391363],"study_design_scores_gemma":[0.0004900167,0.001649835,0.06210238,0.00158297,0.00120887,0.004135632,0.001802413,0.2569652,0.01508916,0.6346767,0.01992494,0.0003719555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02541168,0.001903066,0.9656599,0.004431465,0.0004575105,0.0005243566,0.0001209335,0.0007423374,0.000748737],"genre_scores_gemma":[0.2839805,0.0005915447,0.7080162,0.004388717,0.0007654423,0.001161537,0.0002084415,0.0004270213,0.0004604939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.59298,"threshold_uncertainty_score":0.73125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}