{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.004293625,0.0001388104,0.0001330405,0.0003773588,0.00173347,0.008293637,0.002950431,0.00003650322,0.00002473955],"category_scores_gemma":[0.004477649,0.0001279236,0.000007900444,0.001080347,0.000109867,0.03163547,0.01131961,0.0004618424,0.00008283607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000148594,"about_ca_system_score_gemma":0.00001098053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005732797,"about_ca_topic_score_gemma":0.000008156372,"domain_scores_codex":[0.9974924,0.0004232272,0.0002532416,0.0009355202,0.0004797201,0.0004158959],"domain_scores_gemma":[0.9976771,0.0002320582,0.0001833625,0.001547343,0.0002664076,0.0000937462],"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":[0.000201007,0.0001065258,0.00006854746,0.0005972197,0.00014058,0.00009435561,0.01020001,0.001433017,0.003077923,0.07946493,0.03473673,0.8698791],"study_design_scores_gemma":[0.001038864,0.0001131501,0.001744965,0.0004471351,0.00002007319,0.00003088344,0.004366862,0.8299944,0.0001343859,0.004799511,0.1570068,0.0003029252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3290371,0.0007314142,0.5492125,0.1031224,0.0006105337,0.003850913,0.001966704,0.002464323,0.009004151],"genre_scores_gemma":[0.9892063,0.005120545,0.001359509,0.000120076,0.0001112366,5.46862e-7,0.003762722,0.000226775,0.00009234303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8695762,"threshold_uncertainty_score":0.9995661,"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."}}