{"id":"W4389246169","doi":"10.26434/chemrxiv-2023-sw9kv","title":"Informative Training Data for Efficient Property Prediction in Metal-Organic Frameworks by Active Learning","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"Agence Nationale de la Recherche","keywords":"Property (philosophy); Computer science; Partition (number theory); Tree (set theory); Machine learning; Regression; Set (abstract data type); Artificial intelligence; Class (philosophy); Training set; Data mining; Feature (linguistics); Limiting; Measure (data warehouse); Mathematics; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.004279593,0.0004955833,0.0007476347,0.0002331304,0.000313174,0.0004485452,0.002200961,0.000772076,0.0005066023],"category_scores_gemma":[0.004855935,0.0003877492,0.00009047187,0.0004172379,0.0002521272,0.0004697487,0.003073274,0.002159509,0.0002367978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002884105,"about_ca_system_score_gemma":0.0003823582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000150351,"about_ca_topic_score_gemma":0.0000190611,"domain_scores_codex":[0.9958977,0.0003109642,0.0008854439,0.001470224,0.0006436306,0.0007920621],"domain_scores_gemma":[0.9971069,0.0005172695,0.0007801717,0.001296611,0.0001640529,0.0001349731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001665826,0.0001522813,0.0003297128,0.0009860661,0.0000639367,0.000006452821,0.01845483,0.2318279,0.7416728,0.00005355698,0.00386386,0.002422092],"study_design_scores_gemma":[0.0009067694,0.0001660606,0.001424082,0.001162757,0.0001045604,0.000005914621,0.002847416,0.8418254,0.1451788,0.0008242493,0.004526776,0.001027208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9277418,0.0000842191,0.06356612,0.0005720465,0.003572461,0.002195125,0.0005751121,0.0009347927,0.0007582817],"genre_scores_gemma":[0.9835247,0.00002474381,0.01130868,0.0001094963,0.0003263222,0.0006747047,0.002168156,0.0001357452,0.001727402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6099976,"threshold_uncertainty_score":0.9998574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05782182830932876,"score_gpt":0.3068086629101242,"score_spread":0.2489868346007954,"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."}}