{"id":"W3085586451","doi":"10.5281/zenodo.3993874","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":"Text and Document Classification Technologies","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003959824,0.0003017038,0.0002394376,0.0004947011,0.001677184,0.001578735,0.004161377,0.000191161,0.001429824],"category_scores_gemma":[0.001116289,0.0003122716,0.00005599091,0.0008946725,0.0001477611,0.0005320784,0.00234841,0.0007763964,0.01502236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002430286,"about_ca_system_score_gemma":0.00001644454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034633,"about_ca_topic_score_gemma":3.389466e-7,"domain_scores_codex":[0.9972971,0.0002981184,0.0003565243,0.001006325,0.0006511496,0.0003907973],"domain_scores_gemma":[0.9975129,0.00006782523,0.0003042376,0.001625048,0.000304335,0.0001856371],"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":[0.00003056631,0.0002289676,6.770343e-8,0.00005375682,0.00002335961,0.00001388869,0.00004822587,0.00002693628,0.0002412551,0.000482024,0.9334885,0.06536239],"study_design_scores_gemma":[0.0006186935,0.0003951429,0.00002818205,0.00004900415,0.00001302423,0.000009673514,0.00004249991,0.01767688,0.0003740101,0.00005511946,0.9804662,0.0002715801],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00000428866,0.00001285625,0.08649176,0.0009410853,0.0002105646,0.0004883004,0.9095118,0.001926752,0.0004125924],"genre_scores_gemma":[0.0003522844,0.00007350104,0.004015889,0.0003902733,0.000102873,2.798365e-7,0.9945873,0.0004337707,0.00004385379],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08507548,"threshold_uncertainty_score":0.9999329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0849203007829528,"score_gpt":0.2799977735206358,"score_spread":0.195077472737683,"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."}}