{"id":"W2995917016","doi":"10.1017/s0956796819000170","title":"POPLMark reloaded: Mechanizing proofs by logical relations","year":2019,"lang":"en","type":"article","venue":"Journal of Functional Programming","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Mathematical proof; Computer science; Metatheory; Programming language; Proof assistant; Abstract syntax; Functional programming; Semantics (computer science); 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":[],"consensus_categories":[],"category_scores_codex":[0.001191961,0.0001782399,0.0002947752,0.0001840445,0.0002002074,0.0003080565,0.0005228351,0.0001435387,0.0001045616],"category_scores_gemma":[0.0001517831,0.000136144,0.0002318616,0.0005002338,0.00003180427,0.0009352335,0.0001260693,0.000490545,0.0002226365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313335,"about_ca_system_score_gemma":0.0001559636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009438595,"about_ca_topic_score_gemma":0.000001393799,"domain_scores_codex":[0.9977785,0.0001122864,0.000664253,0.0002951603,0.0007847899,0.00036498],"domain_scores_gemma":[0.9983836,0.0001643065,0.000618247,0.0002610337,0.0003955662,0.0001772332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001048205,0.0006191479,0.01801708,0.00008031868,0.0002878214,0.00008901103,0.0005539591,0.0005746268,0.005778226,0.7384123,0.02360836,0.2118744],"study_design_scores_gemma":[0.002236452,0.002147365,0.002553473,0.00007132203,0.00007336464,0.002012306,0.0004379583,0.005438785,0.0009299159,0.07021078,0.913143,0.0007452344],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007405157,0.00113783,0.9829104,0.00139162,0.002778895,0.00037935,4.238797e-7,0.0001320006,0.003864331],"genre_scores_gemma":[0.9738715,0.000007619713,0.02304823,0.0001525876,0.0004139065,0.00001066492,0.000004655471,0.000014639,0.002476258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9664663,"threshold_uncertainty_score":0.5551792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02365988379521138,"score_gpt":0.2329471454006798,"score_spread":0.2092872616054684,"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."}}