{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002117601,0.0007930955,0.001044459,0.0005263163,0.0004297475,0.00122096,0.002918219,0.001240869,0.003666982],"category_scores_gemma":[0.005539883,0.000445107,0.0007503257,0.0007796249,0.0009453367,0.002301735,0.002119089,0.002697786,0.001499379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008312521,"about_ca_system_score_gemma":0.00138649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001471947,"about_ca_topic_score_gemma":0.001802906,"domain_scores_codex":[0.9994197,0.000240786,0.00003425676,0.0001204755,0.00014219,0.0000426197],"domain_scores_gemma":[0.9985768,0.0006057075,0.00007892982,0.0004268652,0.0002430442,0.00006862154],"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":[0.0002184921,0.0001457339,0.0009865607,0.0002246503,0.00006461177,0.00009064857,0.00009464829,0.7560543,0.007731624,0.1233675,0.003845507,0.1071758],"study_design_scores_gemma":[0.000004954792,0.00003866983,0.00003713419,0.000004664915,0.000002576004,0.00001008982,0.0000040501,0.9824193,0.001180151,0.01550416,0.0007890983,0.000005120769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02008544,0.0003016455,0.9752635,0.0002794812,0.00006351887,0.00006118473,0.0003131877,0.001345668,0.002286462],"genre_scores_gemma":[0.418212,0.0004378541,0.5742719,0.0003406062,0.00007171342,0.0004368402,0.001449705,0.0005260986,0.004253384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003666982,"threshold_uncertainty_score":0.01226735,"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."}}