{"id":"W4360799893","doi":"10.5281/zenodo.10804745","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":"Faculty Digital Archive (New York University Florence)","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; Provenance; Artificial intelligence; Speech recognition; Psychology; Engineering; Communication; Geology","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":[0.1377166,0.0009171737,0.0009506615,0.009218995,0.009374781,0.02162377,0.005285915,0.004158297,0.003719344],"category_scores_gemma":[0.3049044,0.001607939,0.001271278,0.01103181,0.01542757,0.05774694,0.02352512,0.005858053,0.002111426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006129089,"about_ca_system_score_gemma":0.01644148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009761514,"about_ca_topic_score_gemma":0.01315806,"domain_scores_codex":[0.8910977,0.06866346,0.009616308,0.010493,0.01790192,0.002227501],"domain_scores_gemma":[0.5984111,0.1442889,0.02316539,0.1832491,0.04653699,0.004348413],"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":[0.0003842947,0.0002215186,0.02224609,0.001489855,0.0001516541,0.001370404,0.2375821,0.004819853,0.008768556,0.1893758,0.01424479,0.5193449],"study_design_scores_gemma":[0.00006390866,0.0002580198,0.007052023,0.003986525,0.0001910211,0.001274655,0.08963182,0.01204326,0.02426225,0.3820379,0.478795,0.0004036699],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08733346,0.003857064,0.8130779,0.05037686,0.001345771,0.001113708,0.001542039,0.003764016,0.03758917],"genre_scores_gemma":[0.3838918,0.002042786,0.5930998,0.002327208,0.0004656572,0.0006985341,0.002035965,0.002193349,0.01324489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9947141,"threshold_uncertainty_score":0.7283237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3832035130446835,"score_gpt":0.3216727170267064,"score_spread":0.06153079601797717,"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."}}