{"id":"W4409109802","doi":"10.26434/chemrxiv-2025-n1b4l","title":"Learning Advance: Robotics-LLM Guided Hypotheses Generation for the Discovery of Chemical Knowledge","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"","keywords":"Artificial intelligence; Robotics; Computer science; Knowledge extraction; Data science; Knowledge management; Robot","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003326352,0.000214714,0.0003595382,0.00006084168,0.00009392031,0.0001641536,0.00137152,0.0001969978,0.000001622743],"category_scores_gemma":[0.0009318725,0.0001543911,0.0002232791,0.000138343,0.0001128284,0.0001502141,0.00119783,0.0003074626,0.000002545171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005160913,"about_ca_system_score_gemma":0.0002664696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001035035,"about_ca_topic_score_gemma":0.000003696,"domain_scores_codex":[0.9987237,0.00004293974,0.0003584693,0.0005106085,0.000142767,0.0002215044],"domain_scores_gemma":[0.9978412,0.0008759156,0.0002287726,0.0008318713,0.0001997135,0.00002247259],"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":[0.00008279407,0.0009577695,0.002739591,0.004480522,0.0009709104,0.000007716643,0.007260755,0.1782327,0.3080007,0.2988538,0.03698546,0.1614274],"study_design_scores_gemma":[0.0003371772,0.00004102535,0.0002287928,0.0002816946,0.00008904096,0.000002686083,0.00009119078,0.438433,0.5465931,0.01094626,0.002599251,0.0003567924],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03708807,0.004090588,0.9532683,0.001272983,0.001840347,0.000523344,0.000002532079,0.0001521051,0.001761653],"genre_scores_gemma":[0.9178669,0.0003666794,0.07774056,0.00009752279,0.0005453071,0.0001767945,0.00002040471,0.0000146199,0.003171205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8807788,"threshold_uncertainty_score":0.6295888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06695955676635396,"score_gpt":0.3163774114699487,"score_spread":0.2494178547035948,"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."}}