{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003119233,0.00009592898,0.000129253,0.0006927421,0.000257915,0.0002547985,0.001449704,0.00004740469,0.00006474848],"category_scores_gemma":[0.001274879,0.0000717592,0.00001580637,0.0004992987,0.0002176439,0.0007504484,0.002118489,0.0006179149,0.000002616277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002180471,"about_ca_system_score_gemma":0.0006153823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006602029,"about_ca_topic_score_gemma":0.00001419269,"domain_scores_codex":[0.9974119,0.00004574061,0.0004962487,0.0002053694,0.001592754,0.0002480069],"domain_scores_gemma":[0.998866,0.0003372581,0.0001035656,0.0001162362,0.0004935688,0.00008335788],"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":[0.0004021094,0.000259667,0.1463953,0.0001709933,0.00005424229,0.000005239389,0.02348832,0.0003253802,0.001104348,0.7229816,0.0001740826,0.1046387],"study_design_scores_gemma":[0.007198982,0.0008324922,0.226992,0.00182102,0.000002724776,0.0003463748,0.03136195,0.5517266,0.03313332,0.1362372,0.00927196,0.001075257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984257,0.00002069147,0.0006684463,0.01098664,0.0001643445,0.0003019812,0.000006421874,0.00001701563,0.003577456],"genre_scores_gemma":[0.9970775,0.00007956249,0.002572173,0.0001728489,0.000009004812,0.00004446941,0.000003903605,0.000001980975,0.00003852046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5867444,"threshold_uncertainty_score":0.2926255,"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."}}