{"id":"W4399732990","doi":"10.22148/001c.116372","title":"Neither Corpus Nor Edition: Building a Pipeline to Make Data Analysis Possible on Medieval Arabic Commentary Traditions","year":2024,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Macro; Suite; Python (programming language); Macro level; Software; Representation (politics); Pipeline (software); Arabic; Natural language processing; Information retrieval; Artificial intelligence; Programming language; Linguistics; History","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003198577,0.001757866,0.001210205,0.004917697,0.002103821,0.00422042,0.001974647,0.001030116,0.01871981],"category_scores_gemma":[0.01460813,0.001556232,0.001897388,0.003615659,0.00151736,0.006454154,0.005946978,0.003042593,0.02561128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001621744,"about_ca_system_score_gemma":0.005366513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01323028,"about_ca_topic_score_gemma":0.01502272,"domain_scores_codex":[0.9977118,0.0003560547,0.0001893024,0.0008975534,0.0006489524,0.0001963345],"domain_scores_gemma":[0.9953501,0.001630792,0.0002609639,0.001057646,0.001245799,0.0004547859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001006585,0.0003942575,0.009581625,0.001653133,0.0002926344,0.00114997,0.006580974,0.005161832,0.04938792,0.01444225,0.3231137,0.5872352],"study_design_scores_gemma":[0.0003107877,0.0004159285,0.02921794,0.0005926526,0.0002127316,0.00120668,0.004572414,0.1578067,0.09340655,0.06108109,0.6506872,0.0004893877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02778457,0.000874502,0.4894799,0.00198243,0.0005171628,0.001538454,0.06993705,0.3930276,0.01485839],"genre_scores_gemma":[0.06663406,0.0005698718,0.7583896,0.0008426003,0.000179562,0.001799689,0.1318983,0.02743125,0.01225505],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01871981,"threshold_uncertainty_score":0.06262392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04664510234599157,"score_gpt":0.3418212453957643,"score_spread":0.2951761430497727,"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."}}