{"id":"W7080455324","doi":"10.7910/dvn/sghzj8","title":"Replication Data for: Dissecting Corporate Culture Using Generative AI","year":2025,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Replication (statistics); Generative grammar; Data bank; Generative model","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":[],"consensus_categories":[],"category_scores_codex":[0.001741092,0.001820418,0.001121224,0.002794547,0.001228027,0.002252334,0.003308298,0.001937296,0.1010561],"category_scores_gemma":[0.01005529,0.0007296281,0.001484457,0.005101229,0.0005345938,0.001452603,0.002380495,0.002086712,0.1286512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201188,"about_ca_system_score_gemma":0.002309554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02525716,"about_ca_topic_score_gemma":0.05426816,"domain_scores_codex":[0.9986619,0.0002811663,0.0001404904,0.0003951155,0.0003329148,0.0001885362],"domain_scores_gemma":[0.9952291,0.001201698,0.0003318752,0.001636115,0.001201998,0.0003993315],"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":[0.00003429567,0.00001589934,0.0005840624,0.000225504,0.00001446896,0.000009546079,0.0000297718,0.0001179943,0.0000637915,0.000373698,0.9970714,0.001459553],"study_design_scores_gemma":[0.0003322177,0.0000236484,0.005603298,0.0002209199,0.00003269666,0.00004516418,0.0002183032,0.0005245018,0.0005334092,0.002480303,0.989939,0.00004652937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001788731,0.00003496264,0.0001314861,0.00008769838,0.00004061241,0.00001519443,0.9982165,0.0004986257,0.0007960838],"genre_scores_gemma":[0.0005250908,0.00002647222,0.000477039,0.00005015282,0.00001029228,0.0001261424,0.9977107,0.0001274737,0.0009466036],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1010561,"threshold_uncertainty_score":0.3380665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07322227792207892,"score_gpt":0.3107881112096639,"score_spread":0.237565833287585,"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."}}