{"id":"W4284686595","doi":"10.1145/3477495.3531717","title":"Another Look at Information Retrieval as Statistical Translation","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Ranking (information retrieval); Simple (philosophy); Information retrieval; Transformer; Statistical model; Replication (statistics); Machine learning; Natural language processing","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":[0.004636724,0.001278606,0.001475038,0.004568147,0.001386359,0.007522444,0.001799544,0.004073195,0.009380486],"category_scores_gemma":[0.0172652,0.0007565608,0.001785935,0.005036436,0.008723887,0.02736923,0.003080634,0.007595626,0.003944972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003423024,"about_ca_system_score_gemma":0.001438122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00408143,"about_ca_topic_score_gemma":0.002224917,"domain_scores_codex":[0.9968687,0.001479564,0.0001429057,0.0006552513,0.0006899333,0.0001635532],"domain_scores_gemma":[0.9917663,0.005171953,0.0003470581,0.001603132,0.0008897721,0.0002217392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001043544,0.00008061753,0.0004834238,0.0003332949,0.00007291374,0.00007091982,0.0003975207,0.005008546,0.001226115,0.8952377,0.02782285,0.06916177],"study_design_scores_gemma":[0.00006092545,0.0001841852,0.000612321,0.0002516778,0.0000520876,0.0003098978,0.0002324288,0.03981252,0.002048861,0.8284407,0.1279055,0.0000888826],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01213127,0.1053618,0.6365465,0.1516387,0.00453037,0.0001499521,0.001128799,0.001979446,0.08653304],"genre_scores_gemma":[0.476286,0.06418786,0.2996032,0.05589426,0.02117787,0.0004749868,0.001928055,0.001940196,0.07850763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009380486,"threshold_uncertainty_score":0.03138089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08262252473725214,"score_gpt":0.3256112026135011,"score_spread":0.2429886778762489,"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."}}