{"id":"W4387595926","doi":"10.48550/arxiv.2310.07044","title":"Reproducibility in Computational Materials Science: Lessons from 'A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials'","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Field (mathematics); Code (set theory); Set (abstract data type); Data science; Action (physics); Software engineering; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1117142,0.001143255,0.001502739,0.003196812,0.00292027,0.008896142,0.008580787,0.004282312,0.002375436],"category_scores_gemma":[0.4473775,0.001548456,0.002101345,0.005529099,0.01791606,0.03047241,0.007680546,0.01125625,0.001254203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0027561,"about_ca_system_score_gemma":0.00908035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004145082,"about_ca_topic_score_gemma":0.002426373,"domain_scores_codex":[0.9404211,0.03206542,0.004922745,0.006672171,0.0149667,0.0009518535],"domain_scores_gemma":[0.4424162,0.3135013,0.01949736,0.195584,0.0260868,0.002914406],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002887386,0.0003272061,0.01869274,0.0009015512,0.000175349,0.0006953203,0.005626761,0.04817165,0.003076967,0.6321511,0.02354855,0.2663441],"study_design_scores_gemma":[0.00006578249,0.000104357,0.003179034,0.0003405342,0.00005314309,0.0004226308,0.0005247502,0.1462002,0.009198659,0.8022847,0.0374423,0.0001839303],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03596539,0.00242926,0.9091157,0.04029686,0.0008015636,0.0002104296,0.0005067888,0.004216228,0.006457763],"genre_scores_gemma":[0.2981248,0.002615703,0.6900582,0.002160402,0.0007858574,0.0004780832,0.0007864024,0.002968262,0.002022319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8882858,"threshold_uncertainty_score":0.590808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.106293496403786,"score_gpt":0.2561704710328834,"score_spread":0.1498769746290974,"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."}}