{"id":"W2955707177","doi":"10.3758/s13428-019-01268-4","title":"The Semantic Librarian: A search engine built from vector-space models of semantics","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Computer science; Semantics (computer science); Space (punctuation); Cognition; Semantic space; Information retrieval; Cognitive science; Human–computer interaction; Artificial intelligence; World Wide Web; Data science; Psychology; Programming language","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":[0.007408937,0.0002351281,0.0004873817,0.0004621074,0.0002818813,0.0003517965,0.003656354,0.0001616141,0.00004662821],"category_scores_gemma":[0.0004218239,0.0001748656,0.000213643,0.002188457,0.0003188889,0.0009445429,0.00205601,0.001039412,0.0000494464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038058,"about_ca_system_score_gemma":0.0002825544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005347918,"about_ca_topic_score_gemma":0.00002166505,"domain_scores_codex":[0.993459,0.002727685,0.0004992436,0.0007647766,0.00165798,0.0008912919],"domain_scores_gemma":[0.9923239,0.003767405,0.000126293,0.002914193,0.0006557446,0.0002124081],"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":[0.0000577977,0.0004856666,0.004547156,0.00008012207,0.0001509008,0.00007376271,0.002132133,0.001243316,0.4308785,0.2161933,0.0006396927,0.3435177],"study_design_scores_gemma":[0.0004125534,0.0003298783,0.00545064,0.00009828412,0.00003903493,0.000008376853,0.0002872468,0.4345159,0.488997,0.06659176,0.002852804,0.0004164787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08234625,0.0007260222,0.9138719,0.001260134,0.0001261918,0.0008830118,0.000005583328,0.0002241598,0.0005566858],"genre_scores_gemma":[0.4113713,0.0001850372,0.5872989,0.000009133648,0.00003918291,0.00009068807,0.000003141036,0.00003163178,0.0009709609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4332726,"threshold_uncertainty_score":0.7130813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1924456178434242,"score_gpt":0.5118749448262684,"score_spread":0.3194293269828442,"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."}}