{"id":"W4412376926","doi":"10.1145/3726302.3730287","title":"Accelerating Listwise Reranking: Reproducing and Enhancing FIRST","year":2025,"lang":"en","type":"article","venue":"","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003314608,0.002040264,0.001706273,0.002221073,0.0008286676,0.002096943,0.002463614,0.001532092,0.006194493],"category_scores_gemma":[0.01740228,0.000567336,0.0009841139,0.001829206,0.0009778547,0.004943065,0.001860397,0.002534573,0.006262705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001093953,"about_ca_system_score_gemma":0.002843594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006089563,"about_ca_topic_score_gemma":0.01697368,"domain_scores_codex":[0.9979988,0.0006295465,0.0001166627,0.0004006823,0.0006051243,0.0002492289],"domain_scores_gemma":[0.9922022,0.003755399,0.0003907104,0.002044628,0.001333083,0.0002740106],"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":[0.0005785336,0.0004385797,0.004721368,0.0006456302,0.0001657088,0.0003159143,0.0003823518,0.192605,0.02023884,0.02448579,0.04305928,0.712363],"study_design_scores_gemma":[0.00008380672,0.0002577722,0.0004143809,0.00003660547,0.00004196217,0.000218618,0.00008462447,0.9544824,0.01481645,0.02258225,0.006937152,0.00004398222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07139549,0.001854571,0.8872895,0.0008815501,0.0004076295,0.0002918753,0.001125599,0.02968335,0.007070409],"genre_scores_gemma":[0.4602199,0.0007155234,0.5179608,0.0006583098,0.0003913307,0.0002966089,0.003626012,0.002178636,0.01395282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006194493,"threshold_uncertainty_score":0.02072269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01555097952192798,"score_gpt":0.246274644480496,"score_spread":0.2307236649585681,"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."}}