{"id":"W4412756801","doi":"10.26434/chemrxiv-2025-4pk4w","title":"Semantically-Linked Ontological Knowledge Extraction Graph For Domain-Specific Knowledge Discovery In Scientific Literature","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Dalhousie University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Killam Trusts; Dalhousie University","keywords":"Knowledge graph; Knowledge extraction; Computer science; Domain knowledge; Information retrieval; Graph; Scientific discovery; Data science; Domain (mathematical analysis); Natural language processing; Knowledge management; Artificial intelligence; Theoretical computer science; Psychology; Mathematics; Cognitive science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002375563,0.001001771,0.0007375284,0.01698119,0.002014607,0.002993831,0.001346211,0.001352942,0.004168524],"category_scores_gemma":[0.01524123,0.0006061029,0.002717492,0.01358401,0.001080609,0.004513101,0.004417974,0.00148192,0.002113889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001793216,"about_ca_system_score_gemma":0.006126973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009874437,"about_ca_topic_score_gemma":0.01690888,"domain_scores_codex":[0.9970394,0.0007104161,0.0004186901,0.0006187437,0.001092908,0.0001198349],"domain_scores_gemma":[0.992834,0.003338408,0.0008115701,0.001168554,0.001616604,0.0002308544],"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":[0.0002526885,0.0003125102,0.00796571,0.00364148,0.0004550593,0.00203786,0.004421762,0.03881351,0.0154411,0.3699583,0.0513042,0.5053959],"study_design_scores_gemma":[0.00007728718,0.00007787441,0.003493962,0.001051117,0.0004654994,0.0009343846,0.00131404,0.1461974,0.0160595,0.5086326,0.3215293,0.0001670043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01027383,0.0007979989,0.9587498,0.001573777,0.0001433474,0.0007020462,0.01280151,0.006477818,0.008479916],"genre_scores_gemma":[0.05095812,0.00124795,0.9143445,0.0004681271,0.00005631586,0.0008112582,0.02918552,0.0006148164,0.002313356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01698119,"threshold_uncertainty_score":0.01963389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04222315872290627,"score_gpt":0.318109664136733,"score_spread":0.2758865054138268,"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."}}