{"id":"W4415312099","doi":"10.48550/arxiv.2506.14598","title":"Learning From the Past with Cascading Eligibility Traces","year":2025,"lang":"en","type":"preprint","venue":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Nvidia; National Science Foundation","keywords":"Cascade; Work (physics); Information cascade; Reentry; Set (abstract data type); Basis (linear algebra)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00158613,0.0006713463,0.0007312852,0.001085866,0.0004484562,0.001358396,0.00152698,0.001017025,0.003682046],"category_scores_gemma":[0.01126446,0.0005645827,0.001021609,0.0008442111,0.001763296,0.003643507,0.001832983,0.002309294,0.0004194018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005558,"about_ca_system_score_gemma":0.001037618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005022112,"about_ca_topic_score_gemma":0.006158039,"domain_scores_codex":[0.9992717,0.0001768121,0.00007277089,0.0002254706,0.0001722747,0.00008105439],"domain_scores_gemma":[0.9941646,0.0037989,0.0006208352,0.0007701281,0.0003528026,0.0002926067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001624005,0.00007710524,0.002575891,0.0000947166,0.00006513316,0.0002453362,0.0002641148,0.8339149,0.002794344,0.1135896,0.0006982136,0.04551823],"study_design_scores_gemma":[0.000006490983,0.00001499794,0.0001156538,0.000005752986,0.000006336769,0.00002020537,0.000007798048,0.9349644,0.0004625668,0.06415631,0.0002319441,0.000007536656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08883749,0.000152622,0.9075246,0.0004277637,0.00004352382,0.00005009905,0.0001828675,0.0008016517,0.001979379],"genre_scores_gemma":[0.925463,0.0002472101,0.06976394,0.0001053094,0.00003851535,0.0001297991,0.0002257531,0.000116226,0.003910415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005022112,"threshold_uncertainty_score":0.01231766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03615657059625891,"score_gpt":0.2838743034496096,"score_spread":0.2477177328533507,"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."}}