{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009272474,0.0005330004,0.001077409,0.0005735258,0.0005382607,0.0004363426,0.002225926,0.0004152596,0.000511526],"category_scores_gemma":[0.006556502,0.0005520961,0.000120672,0.001010682,0.001152902,0.0005048954,0.003190957,0.0006042807,0.00007674642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004272143,"about_ca_system_score_gemma":0.0008134968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005538883,"about_ca_topic_score_gemma":0.0001301818,"domain_scores_codex":[0.9927496,0.0008903761,0.001097902,0.004007881,0.0004470107,0.0008072875],"domain_scores_gemma":[0.9954193,0.000476273,0.001315043,0.002119948,0.0005106633,0.0001587782],"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":[0.0002122584,0.00008664942,0.01043843,0.0003660292,0.00001298301,0.00001281969,0.0006097851,0.3748899,0.6079593,0.005397545,0.00000377779,0.0000105105],"study_design_scores_gemma":[0.0006477512,0.0001145341,0.0219968,0.001077807,0.00009042183,0.000003036983,0.0002274052,0.1086163,0.77266,0.09381481,0.000008493324,0.0007426339],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774368,0.00004940354,0.01678547,0.0002260589,0.002912216,0.001170619,0.001018929,0.0003897366,0.00001069713],"genre_scores_gemma":[0.9844565,0.0000375541,0.01467997,0.00002668412,0.0003091739,0.00002025082,0.0001905748,0.000078639,0.0002005935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2662736,"threshold_uncertainty_score":0.999693,"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."}}