{"id":"W4411004979","doi":"10.26434/chemrxiv-2025-vfsvt","title":"Thermodynamics-informed machine learning for predicting temperature-dependent chemical properties","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Thermodynamics; Chemistry; Materials science; Physics","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"],"consensus_categories":[],"category_scores_codex":[0.00164282,0.0006642839,0.0008089555,0.0001626977,0.0004519286,0.0007506489,0.001711371,0.0006254752,0.0003288877],"category_scores_gemma":[0.00258036,0.0005493145,0.0002475119,0.0001503356,0.0002733002,0.0001958413,0.002032078,0.001289037,0.00005613701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003504368,"about_ca_system_score_gemma":0.0007149754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001188473,"about_ca_topic_score_gemma":0.00001988571,"domain_scores_codex":[0.9962255,0.0001693843,0.0008486158,0.001293442,0.0006317994,0.0008312443],"domain_scores_gemma":[0.9977988,0.0003006153,0.000594848,0.000859812,0.0002889959,0.0001569516],"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":[0.0001375314,0.00004972426,0.0006373171,0.001759254,0.00002610844,0.000002780581,0.00086439,0.01993431,0.976086,0.0001188745,0.0001297029,0.0002540533],"study_design_scores_gemma":[0.000548781,0.00005296306,0.00008522774,0.0009082825,0.00007633533,0.0000107661,0.000112701,0.165202,0.8308059,0.0005327553,0.0009477061,0.0007165705],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883001,0.0006443127,0.001675921,0.0004841172,0.00294564,0.001464567,0.0000726804,0.0009350666,0.003477551],"genre_scores_gemma":[0.9839163,0.00006658615,0.009429565,0.0001817202,0.0006037961,0.0007081014,0.0002013228,0.00007581372,0.004816763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1452801,"threshold_uncertainty_score":0.9996958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01719994124003566,"score_gpt":0.2647991897126163,"score_spread":0.2475992484725807,"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."}}