{"id":"W4313227384","doi":"10.1109/focs54457.2022.00111","title":"Separations in Proof Complexity and TFNP","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS)","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Unary operation; Mathematical proof; Resolution (logic); Oracle; Combinatorics; Computer science; Discrete mathematics; Algorithm; Mathematics; Theoretical computer science; Artificial intelligence; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001408926,0.0002357595,0.0003213037,0.001049689,0.001610409,0.0003599842,0.00251211,0.00003539619,0.00005782904],"category_scores_gemma":[0.00002463221,0.0002636326,0.00009642275,0.003784694,0.001068687,0.001667084,0.001497199,0.0004188936,0.00001219393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002159199,"about_ca_system_score_gemma":0.0004239977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001179325,"about_ca_topic_score_gemma":0.00008090653,"domain_scores_codex":[0.9965552,0.0002159517,0.000569802,0.0009545374,0.001184356,0.0005201533],"domain_scores_gemma":[0.998162,0.0002153435,0.0002342482,0.0009638749,0.0002479324,0.0001766029],"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":[0.00003276159,0.00158442,0.00133578,0.00003622735,0.00002901239,0.00002248708,0.008841531,0.0581397,0.003257105,0.8911904,0.002365106,0.03316548],"study_design_scores_gemma":[0.001050866,0.001521262,0.01038762,0.00004044158,0.00001061672,0.0001085864,0.0003062891,0.9087114,0.002628727,0.06318285,0.01131612,0.0007351924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2829482,0.00007490212,0.6992304,0.00859194,0.004035916,0.001221788,0.0002305839,0.0002806207,0.003385676],"genre_scores_gemma":[0.9610404,0.00001136098,0.03797115,0.0005755664,0.0001015921,0.0001163038,0.00001131922,0.00001162854,0.0001606783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8505718,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02592606288442114,"score_gpt":0.285306659503105,"score_spread":0.2593805966186838,"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."}}