{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005588403,0.0001184905,0.0001529628,0.00009268792,0.0004096419,0.0004170983,0.0003973589,0.00004869831,0.00001955977],"category_scores_gemma":[0.0004237743,0.00009942144,0.00003413171,0.0003843795,0.00002544888,0.0003870754,0.0004763052,0.0001213601,0.00001458321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003284734,"about_ca_system_score_gemma":0.00006140222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008381641,"about_ca_topic_score_gemma":0.0002225274,"domain_scores_codex":[0.9987879,0.00003027666,0.0002131725,0.0006247778,0.00009676487,0.0002470804],"domain_scores_gemma":[0.9990711,0.000172833,0.00005099113,0.0005794298,0.00007388596,0.00005177995],"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":[0.000006510259,0.00007847618,0.01680483,0.0002011116,0.00004028872,0.00003134232,0.009312278,0.00005905938,0.006675115,0.8245808,0.00587869,0.1363315],"study_design_scores_gemma":[0.003447779,0.0003588623,0.06247231,0.001913893,0.00008162989,0.0001741013,0.001120305,0.3987532,0.307656,0.08071382,0.1406325,0.002675534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08375058,0.001372246,0.5812376,0.002732028,0.0008154137,0.0002023995,1.272424e-7,0.0005631949,0.3293264],"genre_scores_gemma":[0.9559646,0.00002980613,0.03689327,0.0004641001,0.000104647,0.000008239273,3.257831e-7,0.000004510618,0.006530558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.872214,"threshold_uncertainty_score":0.4054289,"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."}}