{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006457169,0.001760782,0.001481493,0.00245771,0.0007054271,0.002049467,0.003296319,0.001820962,0.005486295],"category_scores_gemma":[0.02055857,0.0007481516,0.002168123,0.00142515,0.002316318,0.002528834,0.003947296,0.00300213,0.001439096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001624843,"about_ca_system_score_gemma":0.003027511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002353933,"about_ca_topic_score_gemma":0.00324464,"domain_scores_codex":[0.9967105,0.00157254,0.0001986131,0.0006097706,0.000782693,0.0001258629],"domain_scores_gemma":[0.9897422,0.007497652,0.00058151,0.001139186,0.0007841864,0.0002553526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004872986,0.0004302155,0.003441735,0.001162208,0.0004107859,0.0003162957,0.0004378782,0.4271637,0.008161128,0.1148177,0.007412655,0.4357584],"study_design_scores_gemma":[0.00004677529,0.0001250607,0.0002336793,0.00005161608,0.00003414931,0.00004998553,0.00003477251,0.8867152,0.003863036,0.1043233,0.004502709,0.00001976002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003166185,0.0002106993,0.9933862,0.0004353862,0.00002613386,0.0001220986,0.0001982783,0.001359986,0.001095064],"genre_scores_gemma":[0.1069353,0.0003012668,0.8895009,0.0004168745,0.0000804227,0.0006495384,0.0009430574,0.0001931947,0.0009794931],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006457169,"threshold_uncertainty_score":0.03414917,"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."}}