{"id":"W4417043386","doi":"10.1145/3779428","title":"Learning Context-aware Term Importance for Query Performance Prediction","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Query expansion; Relevance (law); Task (project management); Term (time); Query optimization; Term Discrimination; Web query classification; Performance prediction; Rank (graph theory)","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":[0.0002138059,0.0001243493,0.0001698917,0.0005081121,0.0004254245,0.00009441238,0.0004161157,0.0001856253,0.000006355324],"category_scores_gemma":[0.00003243847,0.0001105826,0.00004655817,0.0005257794,0.00007401734,0.0003269658,0.00001890179,0.0002948213,0.00001144598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006928001,"about_ca_system_score_gemma":0.00005567699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001365427,"about_ca_topic_score_gemma":0.000006151529,"domain_scores_codex":[0.9990276,0.0000185849,0.0003549892,0.0002577081,0.0001162578,0.0002248515],"domain_scores_gemma":[0.9992033,0.00008756859,0.00008210228,0.0004049541,0.0001847073,0.00003736626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004573149,0.0001028322,0.01601468,0.0003097105,0.00007834353,0.000002271583,0.0003844093,0.0007460405,0.000337163,0.05555798,0.0001691436,0.9262517],"study_design_scores_gemma":[0.003280916,0.005177956,0.009414244,0.00169725,0.0001590167,0.0003114628,0.008080696,0.6202923,0.1194349,0.005864753,0.2248738,0.001412658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08289073,0.0002018808,0.9141906,0.0009996528,0.0006513917,0.0005454293,0.00001141668,0.0003893516,0.000119537],"genre_scores_gemma":[0.9964768,0.0003056447,0.0006715396,0.00006108845,0.00001128101,0.0003233473,0.000005046758,0.000005227122,0.002140061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.924839,"threshold_uncertainty_score":0.4509428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01809151885803668,"score_gpt":0.2647543154083037,"score_spread":0.2466627965502671,"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."}}