{"id":"W4394352598","doi":"10.6084/m9.figshare.13368924","title":"Topic Modeling on Triage Notes With Semiorthogonal Nonnegative Matrix Factorization","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Factorization; Triage; Matrix (chemical analysis); Matrix decomposition; Algebra over a field; Computer science; Mathematics; Algorithm; Physics; Pure mathematics; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005474563,0.0003489238,0.000357056,0.0001489949,0.0001275141,0.0003295895,0.0009738714,0.0002815507,0.009973002],"category_scores_gemma":[0.0007344047,0.0003025164,0.00009657432,0.0003194908,0.000002864178,0.0003053163,0.0003785477,0.0005353829,0.0004693168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001008246,"about_ca_system_score_gemma":0.0003337003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002872693,"about_ca_topic_score_gemma":0.00004433467,"domain_scores_codex":[0.9979109,0.000085225,0.0003074886,0.0008078091,0.0005839397,0.0003046409],"domain_scores_gemma":[0.9980915,0.0002937634,0.0002164957,0.001065997,0.0002325738,0.00009970229],"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":[0.000005502221,0.00003092969,8.577983e-7,0.0002141236,0.00003009317,0.00009900402,0.0000591711,0.02660057,0.000001332471,0.00004275603,0.9718277,0.001087973],"study_design_scores_gemma":[0.0005228367,0.0001262039,0.000008300911,0.004988499,0.00002380751,0.00001897772,0.00001235082,0.3578222,0.0001247376,0.0001164046,0.6354578,0.0007779034],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000007123839,0.0001123725,0.04367055,0.00008182599,0.0001945073,0.0002570303,0.9555364,0.00009357501,0.00004661699],"genre_scores_gemma":[0.0003756354,0.000007464486,0.003407999,0.0001869636,0.0004380903,0.000105811,0.9953895,0.00001791842,0.00007062608],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3363699,"threshold_uncertainty_score":0.9999427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06542650446239814,"score_gpt":0.2910039415851521,"score_spread":0.2255774371227539,"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."}}