{"id":"W4386740911","doi":"10.1038/s41597-023-02501-8","title":"Shared metadata for data-centric materials science","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Horizon 2020 Framework Programme; Humboldt-Universität zu Berlin; Engineering and Physical Sciences Research Council; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Metadata; Computer science; Interoperability; Workflow; Data sharing; Data science; Data curation; Big data; World Wide Web; Database; Data mining","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","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.03236642,0.000315086,0.0004373139,0.000716158,0.002128334,0.007375696,0.02501749,0.00006993082,0.002205753],"category_scores_gemma":[0.008895224,0.0002689718,0.00002918359,0.004129492,0.002174952,0.009623286,0.01759927,0.0001020077,0.005882768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006902215,"about_ca_system_score_gemma":0.000874906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001444419,"about_ca_topic_score_gemma":0.00003312259,"domain_scores_codex":[0.9916163,0.0002015484,0.0007908579,0.004020783,0.001907965,0.001462533],"domain_scores_gemma":[0.9855716,0.0003402712,0.0004037995,0.01302256,0.0003423562,0.0003193761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000181369,0.00003156755,0.00004228374,0.00006404156,0.000003209666,0.000005941239,0.00005320933,0.00005768156,0.8188085,0.001205665,0.1791677,0.0005420858],"study_design_scores_gemma":[0.0008558225,0.00006463435,0.002085101,0.00009527429,0.00009678635,0.00003154299,0.0001573342,0.1136385,0.4530991,0.002431235,0.4264461,0.0009985371],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6639616,0.0001991492,0.02135682,0.002321542,0.05005785,0.003046911,0.2557602,0.002521385,0.0007745288],"genre_scores_gemma":[0.5554418,0.00003737464,0.2314668,0.0005690343,0.001861543,0.0002763725,0.1846428,0.0002335143,0.02547081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3657094,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1475997373575138,"score_gpt":0.3791868367131539,"score_spread":0.2315870993556401,"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."}}