{"id":"W4414706768","doi":"10.1021/acs.jctc.5c00848","title":"Hammett-Inspired Product Baseline for Data-Efficient Δ-ML in Chemical Space","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"H2020 European Research Council; Vector Institute; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Baseline (sea); Chemical space; Product (mathematics); Space (punctuation); Solvation; Calibration; Computation; Data space","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":[],"consensus_categories":[],"category_scores_codex":[0.005599929,0.000102716,0.0002573713,0.0001001258,0.00004034444,0.00007851825,0.0003655559,0.00004349713,0.00002334901],"category_scores_gemma":[0.00272672,0.00008208174,0.00003216789,0.0001852162,0.0001321319,0.0001507225,0.0001459198,0.0001363464,0.000002096943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003827209,"about_ca_system_score_gemma":0.00008528302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000255333,"about_ca_topic_score_gemma":1.258098e-7,"domain_scores_codex":[0.9985994,0.0002666526,0.0004904135,0.0002730434,0.0002028092,0.0001676665],"domain_scores_gemma":[0.9985228,0.0008438022,0.0002757853,0.0001664022,0.0001373521,0.0000539104],"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":[0.0005587334,0.00009930602,0.00003576087,0.0000743592,0.000004162061,0.000002734287,0.0001036163,0.005382287,0.9805492,0.003176912,0.0002931085,0.009719868],"study_design_scores_gemma":[0.0008671444,0.00004485519,0.00008846816,0.0001420248,0.00002599508,0.00002980786,0.00003847933,0.1412675,0.8279449,0.029006,0.0004321089,0.0001126931],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8182961,0.0001667898,0.1799377,0.001040755,0.0003450659,0.0001310488,0.000006680571,0.00001343358,0.00006242711],"genre_scores_gemma":[0.9651786,0.000003227274,0.03445172,0.0001731112,0.0001537081,0.000003135663,0.00001013244,0.000005629895,0.0000207223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1526043,"threshold_uncertainty_score":0.3347196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01786731590718065,"score_gpt":0.3180066256402896,"score_spread":0.3001393097331089,"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."}}