{"id":"W4393791072","doi":"10.5281/zenodo.3940706","title":"Multi-label Pathway Prediction based on Active Dataset Subsampling","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","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":[0.003617826,0.002446505,0.00184823,0.00311998,0.001234178,0.002079318,0.002782081,0.002659248,0.01073607],"category_scores_gemma":[0.009554281,0.0005897749,0.003781653,0.002367096,0.00087167,0.00150567,0.001913948,0.002369794,0.007412747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036961,"about_ca_system_score_gemma":0.002388078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008418516,"about_ca_topic_score_gemma":0.01484993,"domain_scores_codex":[0.9976504,0.000514067,0.0001433277,0.001049428,0.0004319756,0.0002108343],"domain_scores_gemma":[0.9963455,0.001709011,0.0001606453,0.001055202,0.0005104375,0.0002190878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004022165,0.001433061,0.03595658,0.005877458,0.002284088,0.001127677,0.0002336465,0.02965455,0.01982425,0.008619478,0.7323351,0.1586319],"study_design_scores_gemma":[0.00486616,0.001627379,0.05239267,0.001280951,0.003215192,0.003228202,0.0005784417,0.2711228,0.05049159,0.07284375,0.5378244,0.0005285449],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05209392,0.004009879,0.04508942,0.001139888,0.0008293545,0.0008779336,0.8763679,0.01439482,0.005196869],"genre_scores_gemma":[0.0418761,0.0005195776,0.04083752,0.0006031023,0.00007763164,0.0008228481,0.9122469,0.000640502,0.002375877],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01073607,"threshold_uncertainty_score":0.03591573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05767827187896028,"score_gpt":0.2859920711278265,"score_spread":0.2283137992488662,"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."}}