{"id":"W6891260444","doi":"10.3886/e233003v1","title":"[Replication package for] Reconstructing history: Using language to estimate religious spread","year":2025,"lang":"en","type":"dataset","venue":"ICPSR Data Holdings","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Islam; Judaism; Buddhism; Natural language; English language; Replication (statistics)","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001991227,0.0009049743,0.001017406,0.001083227,0.0002798324,0.0003098579,0.004611948,0.0005157854,0.000107943],"category_scores_gemma":[0.009194514,0.001093341,0.0001611066,0.0006944675,0.0001664802,0.0008147471,0.00282559,0.0007403573,0.0005124377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002461435,"about_ca_system_score_gemma":0.0008409186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005056031,"about_ca_topic_score_gemma":0.0004860081,"domain_scores_codex":[0.993961,0.0001136197,0.001039619,0.003263641,0.0006109699,0.001011161],"domain_scores_gemma":[0.9822775,0.0004109723,0.001246246,0.01541828,0.0002553998,0.0003916528],"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":[0.0001077906,0.00004094291,0.00002867854,0.00070426,0.0001120634,0.00005585512,0.0001018774,0.00001954788,0.006512762,0.00002115699,0.9898589,0.002436183],"study_design_scores_gemma":[0.0004658457,0.00003068351,0.000005017944,0.001405828,0.000773693,0.00007594477,0.00006246575,0.000987113,0.0007656348,0.00006410837,0.9943211,0.001042545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002224698,0.00206225,0.001148618,0.0001074592,0.001945736,0.002001468,0.9899082,0.0005470896,0.00005450944],"genre_scores_gemma":[0.00003562858,0.0001023723,0.03356504,0.0004884603,0.0005781888,0.0001754167,0.9646612,0.0002043598,0.0001893631],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03241642,"threshold_uncertainty_score":0.9991516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07704159917902528,"score_gpt":0.3866983327889822,"score_spread":0.3096567336099569,"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."}}