{"id":"W2398442511","doi":"","title":"Machine Learning for Information Retrieval: TREC 2009 Web, Relevance Feedback and Legal Tracks.","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Relevance feedback; Relevance (law); Computer science; Information retrieval; World Wide Web; Artificial intelligence; Image retrieval","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":[],"consensus_categories":[],"category_scores_codex":[0.003173672,0.0001052813,0.0001814984,0.0001732066,0.0001803023,0.0006147524,0.0003092523,0.00004993737,0.000183562],"category_scores_gemma":[0.003520231,0.00007716325,0.00005311215,0.0003988157,0.00003504058,0.002679839,0.00005995881,0.0001140278,0.0002248213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001822802,"about_ca_system_score_gemma":0.00002314093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003016735,"about_ca_topic_score_gemma":0.00005640371,"domain_scores_codex":[0.9983076,0.00007626349,0.0005466231,0.000239,0.0006288133,0.0002016396],"domain_scores_gemma":[0.9987825,0.0005257687,0.0001881278,0.0002826978,0.0001408484,0.00008009064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002421247,0.00003717405,0.00008000543,0.0000108947,0.000006842722,9.87466e-7,0.0002850381,0.0002157685,0.00008644323,0.05673041,0.08507188,0.8572325],"study_design_scores_gemma":[0.0007054399,0.0002261705,0.002613352,0.000006472336,0.000007339423,0.000003164736,0.0004890845,0.02156846,0.0001523891,0.008920125,0.9651879,0.0001200696],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1077946,0.001348038,0.4328487,0.06740305,0.001234219,0.002771115,0.0003973062,0.0007671136,0.3854358],"genre_scores_gemma":[0.9291316,0.000366998,0.008621317,0.005664079,0.00008429572,0.000005135883,0.0001223857,0.00000643761,0.0559978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.880116,"threshold_uncertainty_score":0.5928072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06583608472360887,"score_gpt":0.3616941536988756,"score_spread":0.2958580689752668,"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."}}