{"id":"W4310505686","doi":"10.5281/zenodo.7267245","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":2022,"lang":"en","type":"article","venue":"Data Archiving and Networked Services (DANS)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Conversation; Ground truth; Reuse; Computer science; Provenance; Natural language processing; Data science; Artificial intelligence; Linguistics; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.005203497,0.0002455713,0.0002507826,0.0002159702,0.001368146,0.00329681,0.004972546,0.00002999512,0.000001696003],"category_scores_gemma":[0.0003359081,0.0002150207,0.000008169834,0.0005563751,0.0000934335,0.03813025,0.02299696,0.0007927872,5.236034e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008438111,"about_ca_system_score_gemma":0.00005933408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009563136,"about_ca_topic_score_gemma":0.001760639,"domain_scores_codex":[0.9963901,0.0005816137,0.0003758707,0.00159885,0.0005176442,0.0005359171],"domain_scores_gemma":[0.9951248,0.001095412,0.0003525401,0.003279648,0.00004335663,0.0001042004],"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":[0.0008804853,0.000272513,0.01804221,0.002737138,0.0005506244,0.000209675,0.05050992,0.02760254,0.001535319,0.01893438,0.002206565,0.8765186],"study_design_scores_gemma":[0.0005945273,0.00004537223,0.004499045,0.0005936592,0.00003866098,0.00001902824,0.00652761,0.9806334,0.000006969146,0.003236127,0.003551523,0.0002541104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7900966,0.002285899,0.187995,0.01438061,0.0004881951,0.001272899,0.002996686,0.000196422,0.0002877082],"genre_scores_gemma":[0.9794245,0.00850143,0.005141932,0.0002573978,0.0001636192,0.00005000948,0.006426746,0.00002230164,0.00001208052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9530308,"threshold_uncertainty_score":0.9999319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2746835107824994,"score_gpt":0.3274123300538482,"score_spread":0.05272881927134881,"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."}}