{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005859773,0.0001989041,0.0003671627,0.0006242357,0.0001395526,0.0006840596,0.001726445,0.00006692384,0.00003681645],"category_scores_gemma":[0.0001079745,0.0001275649,0.0002499584,0.002287972,0.00004239302,0.001177084,0.0002037943,0.0005194322,0.00001003793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001757261,"about_ca_system_score_gemma":0.00006806203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002304733,"about_ca_topic_score_gemma":0.0000519764,"domain_scores_codex":[0.9980704,0.00006281732,0.0005814262,0.0003364097,0.0007112022,0.0002378135],"domain_scores_gemma":[0.998509,0.0001550667,0.0002366776,0.0005579186,0.0003301773,0.0002110814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001001519,0.0004221101,0.0002983251,0.0001305625,0.002510901,0.001558896,0.002415398,0.004503796,0.006473224,0.01680713,0.8913528,0.07342674],"study_design_scores_gemma":[0.0008892948,0.001468531,0.000763793,0.001838414,0.004510544,0.001736273,0.0004541016,0.7957964,0.01291506,0.04517534,0.1330928,0.001359483],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008780443,0.00287544,0.9241002,0.06262686,0.001007375,0.0001121929,0.0001643358,0.0002092008,0.0001239562],"genre_scores_gemma":[0.3870582,0.0002316127,0.6003385,0.00893847,0.002669629,0.000002772979,0.0001187699,0.00002285041,0.0006192107],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7912926,"threshold_uncertainty_score":0.6596403,"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."}}