{"id":"W7116404342","doi":"10.71781/33991","title":"Unified scientific knowledge representation for large language models","year":2025,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; McGill University","keywords":"Scientific education; Sociology of scientific knowledge; Philosophy of science; Representation (politics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003225613,0.001354723,0.00116297,0.0033333,0.0008899689,0.005139248,0.002758971,0.001843768,0.01167769],"category_scores_gemma":[0.014896,0.001099952,0.003975919,0.003163028,0.0006410503,0.004662198,0.002660419,0.002197461,0.004866413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002368416,"about_ca_system_score_gemma":0.003076898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01279366,"about_ca_topic_score_gemma":0.02100902,"domain_scores_codex":[0.9972624,0.001129542,0.0003552294,0.0004166056,0.0007043034,0.0001319973],"domain_scores_gemma":[0.9933222,0.004124895,0.0003626462,0.001195226,0.0008626169,0.0001323507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004274922,0.0001838278,0.0017112,0.001327457,0.0003989972,0.0004407536,0.0007024129,0.315273,0.003978677,0.2153042,0.04160357,0.4186485],"study_design_scores_gemma":[0.00004455806,0.0000255862,0.0001485291,0.00007712678,0.0000667278,0.00007178359,0.00006873549,0.8849818,0.001695158,0.09007069,0.02271942,0.00002990437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003206085,0.0006343286,0.9683183,0.000467486,0.00007819887,0.000153117,0.004311596,0.02064917,0.002181695],"genre_scores_gemma":[0.1193186,0.001024677,0.8526345,0.0002756372,0.0001016082,0.0008653386,0.01995985,0.001675239,0.004144595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01279366,"threshold_uncertainty_score":0.03906572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05174770621590646,"score_gpt":0.397470139594615,"score_spread":0.3457224333787086,"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."}}