{"id":"W4391013074","doi":"10.48550/arxiv.2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; McGill University; DeepMind; Nvidia","keywords":"Bridging (networking); State (computer science); Computer science; Algorithm; Computer security","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":[0.002069223,0.0004844079,0.0007840027,0.0007117596,0.0004527311,0.001850934,0.001724731,0.00150949,0.002437014],"category_scores_gemma":[0.0126539,0.000532565,0.0006938012,0.0006522118,0.00212476,0.005032836,0.002176618,0.002354433,0.000306646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001385138,"about_ca_system_score_gemma":0.0009820163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003080161,"about_ca_topic_score_gemma":0.003022869,"domain_scores_codex":[0.9993051,0.0003398144,0.00003451412,0.0001376994,0.0001244138,0.00005842763],"domain_scores_gemma":[0.9947236,0.004011862,0.0004015284,0.0004426226,0.0002425922,0.0001778696],"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":[0.00003384683,0.00003337338,0.001165699,0.00008542665,0.0000410131,0.00009023007,0.0005094891,0.5457731,0.0006271328,0.4196297,0.00143381,0.03057712],"study_design_scores_gemma":[0.000003502797,0.000004918718,0.00006095721,0.00001013234,0.00000348766,0.000007848464,0.00002138494,0.8489602,0.0001104104,0.1503232,0.0004896247,0.000004380326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01873049,0.0002257886,0.9761159,0.00134066,0.00002734243,0.00002259662,0.00007269222,0.0002033942,0.00326112],"genre_scores_gemma":[0.7905242,0.0005107281,0.2043497,0.0004579644,0.000112297,0.0001893098,0.0002176461,0.0001675336,0.003470486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003080161,"threshold_uncertainty_score":0.01094323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1209434695660798,"score_gpt":0.201324250554225,"score_spread":0.08038078098814515,"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."}}