{"id":"W4393486226","doi":"10.5281/zenodo.10119773","title":"Benchmarks for POPL'24 Paper \"Commutativity Simplifies Proofs of Parameterized Programs\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Parameterized complexity; Mathematical proof; Commutative property; Programming language; Computer science; Mathematics; Algorithm; Discrete mathematics","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00151065,0.0003373184,0.000517708,0.0003290398,0.00123311,0.001486338,0.003524682,0.0002445143,0.0004478838],"category_scores_gemma":[0.001075653,0.0003120229,0.0001952068,0.0008886418,0.0002477386,0.0004107397,0.002813154,0.0004305841,0.002484512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020968,"about_ca_system_score_gemma":0.00001934808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001703961,"about_ca_topic_score_gemma":0.00000665792,"domain_scores_codex":[0.9967278,0.0006092019,0.0005919761,0.0008107211,0.0006320646,0.0006282695],"domain_scores_gemma":[0.9969904,0.0001462811,0.0004923887,0.001418286,0.0007665625,0.0001861175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000373581,0.0002169919,5.007152e-7,0.0005732886,0.0001037198,0.00001175163,0.0003299571,0.000004216707,0.00007422987,0.004564283,0.9426131,0.05147066],"study_design_scores_gemma":[0.000527548,0.0007411627,0.00001895906,0.00003218787,0.0000325457,0.00003379393,0.00008222184,0.0001942778,0.00005595999,0.002955964,0.994996,0.0003294412],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001219539,0.0003944309,0.09074358,0.001121926,0.00200352,0.007659037,0.8891999,0.003115447,0.005640225],"genre_scores_gemma":[0.005160775,0.0000994485,0.001423659,0.0000689075,0.0001918017,0.00000221606,0.9918041,0.000766689,0.0004824112],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1026042,"threshold_uncertainty_score":0.9999332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06007767842485172,"score_gpt":0.2778392554667943,"score_spread":0.2177615770419425,"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."}}