{"id":"W4396773622","doi":"10.1145/3663758","title":"Separations in Proof Complexity and TFNP","year":2024,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Burden of proof; Proof complexity; Proof of concept; Computer science; Mathematics; Mathematical proof; Political science; Geometry; Law","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":[0.003421465,0.0005059145,0.0007063225,0.001379359,0.001340938,0.004526386,0.001721217,0.001426339,0.01379738],"category_scores_gemma":[0.02516522,0.000684218,0.00157099,0.001695175,0.006063657,0.01415371,0.003715676,0.004875564,0.001196706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004126797,"about_ca_system_score_gemma":0.001936857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002682473,"about_ca_topic_score_gemma":0.001290835,"domain_scores_codex":[0.9941744,0.002080172,0.0004039163,0.001264481,0.00143549,0.000641642],"domain_scores_gemma":[0.9719889,0.02230297,0.001077421,0.002772311,0.001200526,0.0006578903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006609811,0.00001964023,0.000407705,0.0000994431,0.00001232166,0.00005899303,0.000204346,0.00523592,0.0003557759,0.9776527,0.001220908,0.0146661],"study_design_scores_gemma":[0.00002224855,0.00001937716,0.0002116584,0.00002766559,0.00001075819,0.000119789,0.00006058646,0.01605735,0.00070907,0.9770607,0.005687416,0.00001356793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1342745,0.003105215,0.7425483,0.01013129,0.0002470835,0.0001437353,0.0007602801,0.001693043,0.1070966],"genre_scores_gemma":[0.8687733,0.001372053,0.116724,0.000747433,0.0002983839,0.0002342752,0.0007253402,0.0003107564,0.0108143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01379738,"threshold_uncertainty_score":0.04615682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06437713282790664,"score_gpt":0.3118255689888662,"score_spread":0.2474484361609596,"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."}}