{"id":"W1480224957","doi":"","title":"Overview of the TREC 2009 Legal Track","year":2009,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Computer science; Task (project management); Track (disk drive); Relevance (law); Information retrieval; Relevance feedback; World Wide Web; Multimedia; Human–computer interaction; Artificial intelligence; Image retrieval; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000392306,0.00004893656,0.00008766414,0.0000129368,0.0002109619,0.00002883516,0.0003560463,0.00005252833,0.001833489],"category_scores_gemma":[0.0001609502,0.00003163982,0.00009180466,0.000295111,0.000270295,0.0001668355,0.0000124993,0.00006699359,0.0001012364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002953644,"about_ca_system_score_gemma":0.0001112223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004410393,"about_ca_topic_score_gemma":0.007652488,"domain_scores_codex":[0.9991583,0.0001054307,0.0001750375,0.00009584017,0.0002900641,0.0001753724],"domain_scores_gemma":[0.999603,0.00006321433,0.00005617568,0.000176167,0.0000584954,0.00004291454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002801334,0.0000509097,0.0002663289,0.000001158852,0.000002140129,4.30068e-7,0.002603704,0.00001171662,0.0003096322,0.9219722,0.006261133,0.06851791],"study_design_scores_gemma":[0.00003788601,0.00006549777,0.005245864,0.00003252794,0.00001434696,6.485586e-7,0.003194832,0.00006897057,0.02411166,0.07295317,0.8941213,0.0001532652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1008264,0.0003267921,0.0001044059,0.01444081,0.0003664173,0.0001946185,0.000002101224,0.00005476295,0.8836836],"genre_scores_gemma":[0.983428,0.0000896604,0.0001400131,0.001098373,0.0001320875,8.226686e-7,1.00349e-7,0.00000215982,0.01510875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8878602,"threshold_uncertainty_score":0.999079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1200512811546943,"score_gpt":0.408854654768629,"score_spread":0.2888033736139347,"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."}}