{"id":"W4310382841","doi":"10.26434/chemrxiv-2022-hxvcc","title":"Augmenting Polymer Datasets by Iterative Rearrangement","year":2022,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Natural Resources Canada; National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Representation (politics); Property (philosophy); Sequence (biology); Embedding; Computer science; Artificial intelligence; Machine learning; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001320221,0.001023893,0.0006767365,0.0009011028,0.0003778849,0.0009394707,0.001593949,0.001172972,0.003374455],"category_scores_gemma":[0.006781049,0.0004224378,0.0009193198,0.001350674,0.0007156937,0.002677642,0.001371879,0.001969005,0.001410604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005066601,"about_ca_system_score_gemma":0.0007986166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001399624,"about_ca_topic_score_gemma":0.001649208,"domain_scores_codex":[0.9992734,0.0002056201,0.00004626904,0.0001960208,0.0002254884,0.00005326189],"domain_scores_gemma":[0.996824,0.001199903,0.0002385553,0.00127399,0.0003831511,0.00008032453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001674727,0.001353732,0.01920332,0.001177149,0.0002718047,0.0006068736,0.0002311489,0.5093336,0.1569902,0.01389799,0.02242675,0.2728328],"study_design_scores_gemma":[0.00008992612,0.0004868872,0.00326406,0.00003413992,0.00006036456,0.0001941847,0.00007597647,0.8478643,0.1151759,0.01380802,0.01887993,0.00006632507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7718789,0.001302992,0.1913664,0.001326019,0.0002842443,0.0002393776,0.01334831,0.01267467,0.007579108],"genre_scores_gemma":[0.7920484,0.0006612351,0.1770885,0.0003215286,0.00006444049,0.0004540854,0.02633487,0.0005283699,0.002498673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003374455,"threshold_uncertainty_score":0.0112887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01832672389010697,"score_gpt":0.2938586503568738,"score_spread":0.2755319264667668,"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."}}