{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005181415,0.001625996,0.001345139,0.003335192,0.001246962,0.003544767,0.003514678,0.001681301,0.2142576],"category_scores_gemma":[0.03943354,0.001194538,0.002081439,0.007164583,0.0006581333,0.002065542,0.002751207,0.002814134,0.1514857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009904748,"about_ca_system_score_gemma":0.003105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03824925,"about_ca_topic_score_gemma":0.05417537,"domain_scores_codex":[0.9975266,0.0007236775,0.0003707731,0.000615048,0.0004831446,0.0002808148],"domain_scores_gemma":[0.9868065,0.004565773,0.0007920398,0.005061225,0.002345436,0.000429055],"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":[0.00004589705,0.00001376435,0.00117404,0.0003179097,0.00005497575,0.00002032862,0.00007741852,0.0001924278,0.00005598942,0.0007589668,0.9938035,0.003484837],"study_design_scores_gemma":[0.0003975769,0.00001681395,0.005879289,0.0002220074,0.00005087984,0.00005482552,0.0001594098,0.0006685156,0.0002354602,0.002867611,0.9893784,0.00006903601],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001891277,0.00002965579,0.0006564851,0.0001709398,0.00009819034,0.00004258628,0.9968092,0.001057313,0.0009464723],"genre_scores_gemma":[0.001725059,0.00005240309,0.003911126,0.0001371003,0.00003987636,0.0007333634,0.9898472,0.001153805,0.002400034],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2142576,"threshold_uncertainty_score":0.716763,"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."}}