{"id":"W4390870134","doi":"10.5281/zenodo.7267244","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":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Conversation; Ground truth; Computer science; Reuse; Natural language processing; Artificial intelligence; Speech recognition; Information retrieval; Psychology; Engineering; Communication","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":[0.1404762,0.0009893747,0.001022608,0.009679024,0.008480022,0.022122,0.005511987,0.004733194,0.003793234],"category_scores_gemma":[0.3300218,0.001696089,0.001367739,0.01130212,0.01612735,0.05882445,0.02466581,0.006213894,0.002461331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006033514,"about_ca_system_score_gemma":0.01686555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008516375,"about_ca_topic_score_gemma":0.01072542,"domain_scores_codex":[0.880531,0.07472587,0.01038278,0.01209484,0.01988822,0.002377414],"domain_scores_gemma":[0.5651061,0.1545172,0.02368481,0.2016989,0.0502454,0.004747672],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000433923,0.0002147806,0.0206563,0.001778972,0.0001808527,0.001524796,0.2067821,0.005643725,0.01032896,0.2382199,0.01433325,0.4999025],"study_design_scores_gemma":[0.0000592069,0.0002191904,0.005966154,0.003696452,0.0001872689,0.001218327,0.06127933,0.01136945,0.02351718,0.4526432,0.4394805,0.0003636238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06783073,0.004067678,0.8449136,0.04382728,0.001269634,0.001007085,0.001515102,0.003520599,0.03204831],"genre_scores_gemma":[0.3588165,0.002335267,0.6170833,0.002448774,0.0004891789,0.0007506185,0.002478567,0.002470622,0.01312718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.994488,"threshold_uncertainty_score":0.7429183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2350168687793714,"score_gpt":0.326371422619764,"score_spread":0.0913545538403926,"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."}}