{"id":"W4392910228","doi":"10.46298/jdmdh.10403","title":"Exploring Data Provenance in Handwritten Text Recognition Infrastructure: Sharing and Reusing Ground Truth Data, Referencing Models, and Acknowledging Contributions. Starting the Conversation on How We Could Get It Done","year":2024,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Conversation; Ground truth; Reuse; Provenance; Computer science; Natural language processing; Artificial intelligence; Linguistics; Engineering; Geology; Philosophy","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":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.1208475,0.0009528724,0.0009480806,0.008774965,0.008615511,0.02051342,0.005146106,0.00443366,0.003964064],"category_scores_gemma":[0.3070134,0.001556907,0.001349388,0.01021246,0.01494214,0.05838966,0.02388536,0.006101493,0.002212277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005608904,"about_ca_system_score_gemma":0.01521038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008733978,"about_ca_topic_score_gemma":0.0123382,"domain_scores_codex":[0.9046659,0.06023973,0.00799027,0.009406211,0.01552585,0.00217196],"domain_scores_gemma":[0.6136292,0.1441497,0.02350303,0.1681485,0.04616965,0.004399866],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004901526,0.0002618553,0.02764613,0.001639182,0.0001798846,0.001748602,0.223014,0.005844741,0.008992393,0.2335556,0.01488023,0.4817472],"study_design_scores_gemma":[0.00006180987,0.0002575799,0.006776614,0.003721126,0.0001960944,0.001324597,0.0804686,0.01417001,0.02274277,0.4680932,0.401806,0.0003815137],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0865043,0.003468381,0.823488,0.04668201,0.001330318,0.001043614,0.001580721,0.003038085,0.03286453],"genre_scores_gemma":[0.404315,0.001836351,0.5742006,0.00248382,0.0004473657,0.0006849903,0.002207689,0.001909561,0.01191464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9948539,"threshold_uncertainty_score":0.6391101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5182855834595688,"score_gpt":0.373077971203399,"score_spread":0.1452076122561697,"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."}}