{"id":"W4283450505","doi":"","title":"Sharing HTR datasets with standardized metadata: the HTR-United initiative","year":2022,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Metadata; Computer science; World Wide Web; Information retrieval; Data science","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02116443,0.0004394621,0.0004369737,0.0005352483,0.001269704,0.01109412,0.01484023,0.0001064449,0.0002073322],"category_scores_gemma":[0.004236431,0.0003473163,0.0001374957,0.001777066,0.0003643255,0.01025248,0.03160556,0.001817262,0.00002133223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002704657,"about_ca_system_score_gemma":0.000617367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002257688,"about_ca_topic_score_gemma":0.001969861,"domain_scores_codex":[0.9831015,0.01215779,0.000580508,0.001739898,0.001814077,0.0006062288],"domain_scores_gemma":[0.9825295,0.004242928,0.0009955937,0.01048177,0.001531284,0.0002189847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006724487,0.0005620252,0.0007296365,0.0002124163,0.0007653579,0.0001023828,0.007707073,0.0004778273,0.00009813721,0.9691719,0.01020451,0.009901466],"study_design_scores_gemma":[0.001471703,0.000002939467,0.002915666,0.0009909788,0.0001955834,0.00002541321,0.0008257342,0.04928338,0.003209579,0.007376118,0.932645,0.001057897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003599571,0.0006347997,0.920662,0.03414467,0.0002200569,0.00129505,0.002006745,0.000392526,0.03704457],"genre_scores_gemma":[0.2921571,0.01011397,0.594068,0.002916888,0.0001226193,0.002402489,0.05626201,0.0003029747,0.04165398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9617958,"threshold_uncertainty_score":0.9998979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07233787372278151,"score_gpt":0.3178392181969567,"score_spread":0.2455013444741752,"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."}}