{"id":"W4284708021","doi":"10.1145/3477495.3531853","title":"Neural Query Synthesis and Domain-Specific Ranking Templates for Multi-Stage Clinical Trial Matching","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Computer science; Matching (statistics); Pipeline (software); Pointwise; Relevance (law); Sentence; Domain (mathematical analysis); Artificial intelligence; Information retrieval; Data mining","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":[0.004123355,0.000113422,0.0001783533,0.0004151101,0.0004237643,0.0004348685,0.001347389,0.00005056936,0.00001789975],"category_scores_gemma":[0.001250265,0.0000919721,0.00003787638,0.0002434761,0.00009540515,0.0009573555,0.001524347,0.0004544709,0.000001388906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001307925,"about_ca_system_score_gemma":0.0001842302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009432563,"about_ca_topic_score_gemma":0.000001171558,"domain_scores_codex":[0.9976654,0.00004402346,0.0007548843,0.0002608042,0.001017999,0.0002568726],"domain_scores_gemma":[0.9980773,0.0009126015,0.0002924003,0.0001332823,0.0005173892,0.00006707448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0170716,0.0004129845,0.02488993,0.0002953166,0.0001074583,0.000002013651,0.01431235,0.0002489921,0.000910794,0.8342423,0.0004620635,0.1070442],"study_design_scores_gemma":[0.07779231,0.002640961,0.06615838,0.001173656,0.000009957202,0.00008080506,0.02326272,0.5859744,0.02097605,0.1244068,0.09562229,0.001901718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820114,0.00001468768,0.01395438,0.00222422,0.000535121,0.000762095,0.00001278288,0.00002513621,0.0004601944],"genre_scores_gemma":[0.9398965,0.00004635361,0.05969419,0.0001073784,0.00003862015,0.000137102,0.000004101102,0.000004579294,0.00007114342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7098355,"threshold_uncertainty_score":0.4193447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3008790373450523,"score_gpt":0.4115527108054265,"score_spread":0.1106736734603742,"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."}}