{"id":"W4309221281","doi":"10.21203/rs.3.rs-2260181/v1","title":"Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Association Nationale de la Recherche et de la Technologie","keywords":"Workflow; Computer science; Consistency (knowledge bases); Scale (ratio); Sample (material); Information extraction; Artificial intelligence; Population; Natural language processing; Information retrieval; Database; Data mining; Geography; Cartography; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007455476,0.0001606774,0.0003160276,0.0004621871,0.001881815,0.0007264795,0.0006223497,0.0003733102,0.01343037],"category_scores_gemma":[0.000987454,0.0001614382,0.0002792812,0.0008475303,0.0001787916,0.0004981149,0.001106989,0.00184211,0.0002258585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009966476,"about_ca_system_score_gemma":0.00123088,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2483142,"about_ca_topic_score_gemma":0.1710896,"domain_scores_codex":[0.9920509,0.003824491,0.0004560815,0.0004469175,0.002640605,0.0005809393],"domain_scores_gemma":[0.9970469,0.001363897,0.0001973759,0.0003634426,0.0007890103,0.0002393609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003266659,0.0009594437,0.05732769,0.0003181785,0.000394743,0.0000499453,0.1264453,0.005299329,0.00003858492,0.01676613,0.06527556,0.7267984],"study_design_scores_gemma":[0.0002489874,0.00004707308,0.1253927,0.00006831264,0.00003262933,2.824091e-7,0.03334559,0.006313118,0.000009183441,0.0477876,0.7864517,0.0003028534],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7648937,0.001564127,0.0767688,0.01098966,0.002949738,0.002630461,0.001542413,0.000562071,0.138099],"genre_scores_gemma":[0.9706786,0.001295001,0.008416745,0.000182228,0.002516266,0.0006165538,0.005573786,0.00002669036,0.01069409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7264956,"threshold_uncertainty_score":0.9994176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1050366162942268,"score_gpt":0.4819845324814767,"score_spread":0.3769479161872499,"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."}}