{"id":"W4281610263","doi":"10.4230/lipics.itp.2023.12","title":"Lessons for Interactive Theorem Proving Researchers from a Survey of Coq Users","year":2023,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Prevention of Organ Failure","funders":"","keywords":"Mathematical proof; Proof assistant; Computer science; Software engineering; Programming language; Plug-in; Software; Process (computing); Proof of concept; Operating system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02550761,0.0003583463,0.000562401,0.003737232,0.002355289,0.005167339,0.001453288,0.001860246,0.005034897],"category_scores_gemma":[0.1175053,0.0005957579,0.0005479105,0.006851171,0.002224541,0.01127865,0.003929341,0.002290486,0.0009762304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00197478,"about_ca_system_score_gemma":0.002013966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01302091,"about_ca_topic_score_gemma":0.01325789,"domain_scores_codex":[0.9771292,0.01477315,0.001198173,0.001804154,0.002671117,0.002424323],"domain_scores_gemma":[0.8029748,0.1652651,0.007252628,0.005947532,0.013189,0.005370876],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003323318,0.0004070072,0.4023689,0.0009030306,0.00005544635,0.0007062348,0.3841063,0.0001706392,0.0008969401,0.005011354,0.02671646,0.1783254],"study_design_scores_gemma":[0.00007575569,0.0005031292,0.3332658,0.001205505,0.00006740332,0.0009147708,0.5821779,0.001609266,0.0008193898,0.005905326,0.07331289,0.000142938],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9395307,0.002812601,0.004518404,0.04111314,0.0001081323,0.0001199765,0.0008447771,0.0001581043,0.01079428],"genre_scores_gemma":[0.9908214,0.001496962,0.001730715,0.004005577,0.0001099465,0.0001635301,0.0004148716,0.00008826441,0.001168717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9744924,"threshold_uncertainty_score":0.1348988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1046349544622271,"score_gpt":0.323948681985571,"score_spread":0.2193137275233439,"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."}}