{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00344014,0.0001920566,0.0002423827,0.0004447706,0.000351121,0.01759966,0.003299101,0.0000357486,0.000001583462],"category_scores_gemma":[0.002423241,0.0001523287,0.00001316465,0.0003085408,0.000136134,0.2038663,0.006392448,0.0006116889,0.00000109334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001294898,"about_ca_system_score_gemma":0.0001513234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004400302,"about_ca_topic_score_gemma":0.0001243198,"domain_scores_codex":[0.9977111,0.0001100453,0.0005382451,0.000734024,0.0005814972,0.0003251158],"domain_scores_gemma":[0.9965087,0.001187015,0.0004457112,0.00163023,0.0001659838,0.00006234945],"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":[0.0002270673,0.0001108907,0.0007111778,0.00130078,0.000518868,0.000535071,0.02173737,0.0002424033,0.0001672999,0.04171383,0.007090257,0.925645],"study_design_scores_gemma":[0.001109105,0.0002731113,0.0008716537,0.006784629,0.000130093,0.0002364449,0.03820325,0.9148959,0.00004684715,0.01111917,0.02580512,0.0005246853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6941439,0.01035454,0.2615125,0.02406758,0.001660892,0.001035623,0.004780882,0.000212003,0.002232062],"genre_scores_gemma":[0.9879782,0.005518936,0.005112689,0.00007129106,0.0003070719,0.000004623175,0.0009487867,0.00001934818,0.00003903412],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9251203,"threshold_uncertainty_score":0.9834202,"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."}}