{"id":"W4360608324","doi":"10.21203/rs.3.rs-2705743/v1","title":"FAIR-ification of structured Head and Neck Cancer clinical data for multi-institutional collaboration and federated learning","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Research Data Management Practices","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Computer science; Interoperability; Annotation; Scalability; Information retrieval; SPARQL; Resource (disambiguation); Dashboard; Constraint (computer-aided design); Data science; World Wide Web; RDF; Database; Artificial intelligence; Semantic Web","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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.007769778,0.0001782421,0.0003272789,0.0004359987,0.0005999772,0.003195351,0.001970239,0.0002278344,0.000004149079],"category_scores_gemma":[0.01060133,0.0001616332,0.00003096256,0.0007584904,0.0003438556,0.00584575,0.008293064,0.001124206,0.000003144871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109813,"about_ca_system_score_gemma":0.001342999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009565518,"about_ca_topic_score_gemma":0.002210887,"domain_scores_codex":[0.9952677,0.001186689,0.0005420183,0.001432193,0.001167203,0.0004042264],"domain_scores_gemma":[0.9951538,0.001455279,0.000307478,0.001423072,0.001489462,0.0001708667],"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":[0.001461613,0.001161361,0.2281789,0.02157243,0.001863099,0.0001042155,0.002027604,0.01391006,0.002905487,0.2470722,0.03249817,0.4472448],"study_design_scores_gemma":[0.001086297,0.0002076253,0.1628874,0.0004868039,0.00001607377,0.000001019153,0.0003168581,0.8075073,0.0000807811,0.0009333082,0.02627181,0.0002047291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1310737,0.002768277,0.8430448,0.01268537,0.000770253,0.006071683,0.003249687,0.0002620089,0.00007425008],"genre_scores_gemma":[0.8378311,0.03029875,0.120786,0.00003117177,0.0004173047,0.0008612317,0.008207442,0.00005412665,0.001512872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7935972,"threshold_uncertainty_score":0.9997277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5524557591800002,"score_gpt":0.5829365234534151,"score_spread":0.03048076427341484,"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."}}