{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002600953,0.0002958899,0.000463237,0.000264048,0.0006721825,0.00244372,0.001922043,0.0002372714,0.005432349],"category_scores_gemma":[0.0005635864,0.0002856243,0.00009808652,0.0004655837,0.00005019754,0.0006794769,0.0003277835,0.000163069,0.0009620871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008103631,"about_ca_system_score_gemma":0.0007085133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001526777,"about_ca_topic_score_gemma":0.00169764,"domain_scores_codex":[0.9971564,0.0002258349,0.0005321311,0.001236572,0.0003593966,0.000489713],"domain_scores_gemma":[0.9980829,0.0002088993,0.0004292967,0.000849205,0.0003428221,0.00008685934],"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":[0.0003370749,0.0002170193,0.000009270128,0.0003739592,0.00001597002,0.000006728779,0.01830463,0.001497212,0.9522392,0.002018525,0.006723428,0.01825697],"study_design_scores_gemma":[0.001491621,0.00009843886,0.0001265542,0.000748576,0.0001659765,0.000002711296,0.007167035,0.05090243,0.879361,0.003137134,0.05583828,0.0009602174],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.8590611,0.0002695312,0.003040548,0.00005587398,0.007135449,0.002382169,0.000723932,0.00002138437,0.12731],"genre_scores_gemma":[0.3217224,0.000005492554,0.0385915,0.00002365578,0.0002453088,0.0004413246,0.00629906,0.00005931844,0.6326119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5373387,"threshold_uncertainty_score":0.9999596,"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."}}