{"id":"W4383180909","doi":"10.5281/zenodo.8116009","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":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Conversation; Ground truth; Computer science; Natural language processing; Reuse; Speech recognition; Artificial intelligence; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.1213987,0.001036445,0.001002124,0.00856771,0.00778121,0.02083542,0.005155151,0.004538507,0.003808621],"category_scores_gemma":[0.2884485,0.001682144,0.001383554,0.01004305,0.01372881,0.05676782,0.02416874,0.006114346,0.002566953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005053526,"about_ca_system_score_gemma":0.01406244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00766602,"about_ca_topic_score_gemma":0.009929421,"domain_scores_codex":[0.9058638,0.05630523,0.008368394,0.01014072,0.01713497,0.002186794],"domain_scores_gemma":[0.6192451,0.1254024,0.02074585,0.1853992,0.04482873,0.004378522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000536159,0.0002515853,0.02052672,0.001744833,0.0001891722,0.00165221,0.1701221,0.006852891,0.01235841,0.2291255,0.01544533,0.5411951],"study_design_scores_gemma":[0.00006649497,0.0002541072,0.005902722,0.003302084,0.000198084,0.001375302,0.05210938,0.01392538,0.02971649,0.4580261,0.4347198,0.0004041443],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06038233,0.003371421,0.86928,0.03318162,0.00114735,0.0008487609,0.001436603,0.0038211,0.02653081],"genre_scores_gemma":[0.3269538,0.002031797,0.6503023,0.001997001,0.0004600038,0.0006240213,0.002614366,0.002717389,0.01229941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9948449,"threshold_uncertainty_score":0.6420252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4138588806698587,"score_gpt":0.3364620657001128,"score_spread":0.07739681496974593,"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."}}