{"id":"W3037779358","doi":"10.1609/aaai.v34i10.7264","title":"Literature Mining for Incorporating Inductive Bias in Biomedical Prediction Tasks (Student Abstract)","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Leverage (statistics); Inductive bias; Computer science; Machine learning; Relevance (law); Task (project management); Artificial intelligence; Multi-task learning; Feature (linguistics); Training set; Data mining; Data science; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02444465,0.0007783745,0.001364855,0.005980645,0.001217113,0.002841866,0.002671336,0.002034845,0.002790756],"category_scores_gemma":[0.1097824,0.0007550234,0.001411738,0.005105735,0.001172715,0.00430863,0.003878794,0.002258078,0.001600924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101018,"about_ca_system_score_gemma":0.002478845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001307672,"about_ca_topic_score_gemma":0.003326838,"domain_scores_codex":[0.9917823,0.00415394,0.0008108036,0.001312451,0.001728481,0.0002119952],"domain_scores_gemma":[0.9004195,0.07959782,0.005262465,0.007074961,0.006623769,0.001021463],"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":[0.0008574481,0.0007853141,0.0482285,0.001267074,0.0006471438,0.0006578852,0.0006929018,0.05996486,0.008056351,0.03191496,0.02974049,0.817187],"study_design_scores_gemma":[0.000174879,0.0001809089,0.005807608,0.0003789176,0.0001799975,0.0005010393,0.0001562226,0.8333941,0.01057869,0.1379568,0.01060761,0.00008323811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05524185,0.00157767,0.930488,0.005204334,0.0003543773,0.0003252141,0.001453408,0.002859867,0.00249523],"genre_scores_gemma":[0.3657462,0.0006956308,0.6258029,0.001606986,0.0007995995,0.0005531561,0.002826811,0.0002810315,0.001687833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02444465,"threshold_uncertainty_score":0.1292772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1364435877900705,"score_gpt":0.338468309210084,"score_spread":0.2020247214200135,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}