{"id":"W6947354216","doi":"10.3886/e233003","title":"[Replication package for] Reconstructing history: Using language to estimate religious spread","year":2025,"lang":"en","type":"dataset","venue":"ICPSR Data Holdings","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"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":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004987314,0.0003267992,0.0003283306,0.0001018193,0.0001708282,0.0001048498,0.001698604,0.0002000036,0.00702749],"category_scores_gemma":[0.001137237,0.0003628517,0.00007137167,0.0002516065,0.0001303474,0.0002915682,0.001743488,0.0002204693,0.0003451938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002367103,"about_ca_system_score_gemma":0.00005779543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003297473,"about_ca_topic_score_gemma":0.0006880591,"domain_scores_codex":[0.9975467,0.00002763717,0.0003776079,0.001290351,0.000305311,0.0004524085],"domain_scores_gemma":[0.9953733,0.00008578758,0.0003166743,0.004007576,0.00002050652,0.0001961591],"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":[0.00001794873,0.00002308033,0.0001147775,0.00009349902,0.00001188791,0.00000898535,0.00004261647,0.000004646831,0.001683916,0.00001509643,0.9963514,0.001632133],"study_design_scores_gemma":[0.0001692483,0.00001632479,0.00008093303,0.0001273915,0.0001110237,0.00001377914,0.0001551441,0.0001726198,0.0003080043,0.00001771303,0.9984506,0.0003771675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005774851,0.0003420749,0.0004335618,0.0002452378,0.0008885539,0.0006533507,0.9911473,0.00009949324,0.0004156142],"genre_scores_gemma":[0.00009032585,0.0001841385,0.001873961,0.000826541,0.0001054842,0.00006430992,0.9965537,0.00002069073,0.00028087],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.006682296,"threshold_uncertainty_score":0.9998823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07157594431711464,"score_gpt":0.3511725278553943,"score_spread":0.2795965835382797,"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."}}