{"id":"W4284706463","doi":"10.1145/3477495.3531898","title":"Inconsistent Ranking Assumptions in Medical Search and Their Downstream Consequences","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":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"National Science Foundation","keywords":"Downstream (manufacturing); Ranking (information retrieval); Relevance (law); Computer science; Point (geometry); Machine learning; Confidence interval; Artificial intelligence; Information retrieval; Data mining; Statistics; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04506032,0.0009331271,0.003434242,0.00348263,0.003027041,0.005646696,0.005674736,0.006935849,0.007723524],"category_scores_gemma":[0.284901,0.002172173,0.001616345,0.003911017,0.008157579,0.01805217,0.006284143,0.0109092,0.0023639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003000656,"about_ca_system_score_gemma":0.002098006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004908707,"about_ca_topic_score_gemma":0.00312836,"domain_scores_codex":[0.9723092,0.01393944,0.001839198,0.003971446,0.006592947,0.001347715],"domain_scores_gemma":[0.7492411,0.199804,0.01553176,0.02126181,0.0121869,0.001974387],"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":[0.0007141292,0.0003082161,0.01756456,0.0004721968,0.0001756017,0.001327948,0.00128122,0.06489401,0.001118914,0.8247494,0.01340532,0.07398855],"study_design_scores_gemma":[0.00009631099,0.00005976573,0.001895061,0.00007468964,0.00002858534,0.0003686826,0.0001408443,0.1109493,0.0006542891,0.8844479,0.001220516,0.00006398873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1915566,0.004629949,0.6997485,0.05916243,0.0004370142,0.0003450756,0.001687959,0.001424803,0.04100768],"genre_scores_gemma":[0.9094504,0.00142146,0.07711493,0.003829171,0.0009613264,0.0003779701,0.001155305,0.0003761429,0.005313267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04506032,"threshold_uncertainty_score":0.2383046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09496922730706166,"score_gpt":0.3320899544838965,"score_spread":0.2371207271768349,"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."}}