{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001813057,0.0004517039,0.0004811202,0.0001007752,0.0004799732,0.0006512472,0.001726734,0.0001452443,0.04035354],"category_scores_gemma":[0.0001835646,0.0004439148,0.0001044922,0.0001623833,0.0001985131,0.0001987022,0.004500847,0.0006770546,0.0005323906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002066349,"about_ca_system_score_gemma":0.0001253936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003214955,"about_ca_topic_score_gemma":0.000003095638,"domain_scores_codex":[0.9961532,0.0004088263,0.000574145,0.001352365,0.0008794263,0.0006319818],"domain_scores_gemma":[0.9978205,0.00009609688,0.0005859814,0.001300217,0.00004452467,0.0001527118],"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":[0.00001741972,0.00007189622,0.0002640635,0.0001434769,0.00001326623,0.00001720108,0.0005299388,0.0004670024,0.9292932,0.00009033919,0.06896303,0.0001291346],"study_design_scores_gemma":[0.0003000243,0.00005113321,0.0001900737,0.0001189165,0.00004862764,0.000006980452,0.0001353423,0.001038961,0.9212506,0.0002824958,0.07578185,0.0007949656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838712,0.001220321,0.0009312335,0.0009574124,0.004372933,0.0006471584,0.00114538,0.0003954874,0.006458833],"genre_scores_gemma":[0.9600832,0.0001022728,0.01266465,0.002055062,0.001051849,0.001163592,0.008335196,0.0002213985,0.01432271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03982114,"threshold_uncertainty_score":0.9998013,"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."}}