{"id":"W7106012457","doi":"10.5281/zenodo.17625452","title":"Petro Naft AI Corpus","year":2025,"lang":"en","type":"dataset","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"","keywords":"Metadata; Snapshot (computer storage); The Internet; Domain (mathematical analysis); Data dictionary; Metadata repository","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001347763,0.002494802,0.001667959,0.005389052,0.001938211,0.00328359,0.002804877,0.002336417,0.125976],"category_scores_gemma":[0.006096626,0.0007103697,0.001104684,0.006785242,0.0008095009,0.002682677,0.00321786,0.00231569,0.2006851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037985,"about_ca_system_score_gemma":0.002905619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02661422,"about_ca_topic_score_gemma":0.04592937,"domain_scores_codex":[0.9983042,0.0003714402,0.0001618718,0.0004808816,0.000481019,0.0002005634],"domain_scores_gemma":[0.9975026,0.0006833479,0.0001492655,0.0006282448,0.0007880422,0.0002484803],"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":[0.00006170856,0.00001824284,0.0001742516,0.0003833158,0.00001432278,0.00004230612,0.00003342033,0.0001073038,0.0001836079,0.0007158844,0.9943709,0.003894784],"study_design_scores_gemma":[0.0001017614,0.00001565289,0.001943654,0.0001887634,0.00002380471,0.0001483529,0.0001301674,0.0004710681,0.0004879936,0.001505114,0.9949571,0.00002658371],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0008320865,0.0004029112,0.0003658286,0.0002889942,0.0002185666,0.00003145598,0.9873437,0.001518429,0.008998061],"genre_scores_gemma":[0.0008661459,0.00008774902,0.0004699205,0.00005704756,0.00002515354,0.0000754108,0.9955139,0.0002208707,0.002683752],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.874024,"threshold_uncertainty_score":0.4214317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03111927402659847,"score_gpt":0.3561690631414897,"score_spread":0.3250497891148912,"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."}}