{"id":"W4396674157","doi":"10.32920/25761534","title":"Methods and Datasets for Feature-based query refinement collection","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Query expansion; Web query classification; Web search query; Closeness; Sargable; Query optimization; Query language; Term (time); Vocabulary; RDF query language; Search engine; Mathematics","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":[0.004259112,0.002117253,0.001304024,0.005541867,0.001503244,0.002225621,0.004683947,0.002769795,0.02953405],"category_scores_gemma":[0.01498367,0.0007691244,0.002711261,0.005621111,0.000823099,0.001852726,0.002180635,0.00300917,0.0294831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001985518,"about_ca_system_score_gemma":0.00318671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01939177,"about_ca_topic_score_gemma":0.02094474,"domain_scores_codex":[0.9950877,0.0009618646,0.0008345952,0.001101071,0.001593609,0.0004211045],"domain_scores_gemma":[0.9936864,0.00144122,0.0003314477,0.002307814,0.001975112,0.0002579585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002061649,0.002731843,0.009557469,0.003388345,0.0003178946,0.0006753529,0.0002954395,0.02112695,0.008087238,0.007745316,0.5943501,0.3496625],"study_design_scores_gemma":[0.00198875,0.001323954,0.02352881,0.0007541753,0.000365928,0.001837033,0.001094862,0.1399074,0.02810342,0.01991775,0.7807317,0.0004463945],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.03703605,0.004895042,0.1410768,0.001987595,0.001689129,0.01558626,0.7361537,0.03477007,0.02680528],"genre_scores_gemma":[0.03738899,0.001077892,0.1636229,0.000727158,0.0001488217,0.01214196,0.7764499,0.0006743008,0.007768186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02953405,"threshold_uncertainty_score":0.0988012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05748325247809054,"score_gpt":0.3842360066330495,"score_spread":0.326752754154959,"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."}}