{"id":"W4387928928","doi":"10.48550/arxiv.2310.14252","title":"Proof of Irvine's Conjecture via Mechanized Guessing","year":2023,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Conjecture; Automated theorem proving; Mathematics; Gas meter prover; Calculus (dental); Discrete mathematics; Computer science; Mathematical economics; Algorithm; Mathematical proof; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005717108,0.0003767044,0.0006047739,0.0002386569,0.0001057036,0.0001226775,0.002498588,0.000418422,0.00006175316],"category_scores_gemma":[0.0003319026,0.000353116,0.000236204,0.0004997955,0.0001344725,0.0002152466,0.00315543,0.0007515325,0.0002736636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008079069,"about_ca_system_score_gemma":0.0002520146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002951974,"about_ca_topic_score_gemma":0.00007275979,"domain_scores_codex":[0.9972473,0.0001439426,0.0007272706,0.0009551446,0.0004833693,0.0004429202],"domain_scores_gemma":[0.9971099,0.0002293104,0.0005620118,0.001697906,0.0002954095,0.0001054241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001841606,0.001336303,0.194323,0.004120234,0.001694818,0.001068078,0.03559201,0.03762516,0.2116389,0.05118157,0.010968,0.4502678],"study_design_scores_gemma":[0.0001320054,0.0001225322,0.004667901,0.0007447026,0.00005599995,0.00001328847,0.000119434,0.08913471,0.7713709,0.1319617,0.0008200285,0.0008567891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2746302,0.0002366218,0.7191321,0.001603285,0.00301586,0.0004983342,0.000008246024,0.0005291016,0.0003463294],"genre_scores_gemma":[0.9825342,0.0000216055,0.01621473,0.0001594465,0.0002937555,0.00005676682,0.000012148,0.00005153258,0.0006557585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7079041,"threshold_uncertainty_score":0.9998921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1069590236617751,"score_gpt":0.3226974811790573,"score_spread":0.2157384575172823,"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."}}