{"id":"W2124006395","doi":"10.3758/brm.42.2.393","title":"Exploring lexical co-occurrence space using HiDEx","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Representation (politics); Co-occurrence; Set (abstract data type); Space (punctuation); A priori and a posteriori; Semantic space; Lexical decision task; Natural language processing; Artificial intelligence; Basis (linear algebra); Semantic data model; Hyperspace; Mathematics; Cognition","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":[0.008494222,0.0001667457,0.0002239549,0.0003922172,0.0004140926,0.00038647,0.001821425,0.0001116897,0.00007310764],"category_scores_gemma":[0.001071243,0.0001611009,0.00008964767,0.0008114876,0.0002235734,0.001038944,0.0009058259,0.001721608,0.00005133874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008689293,"about_ca_system_score_gemma":0.0002970342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210237,"about_ca_topic_score_gemma":0.000008650139,"domain_scores_codex":[0.995764,0.001234082,0.0003019015,0.0007577005,0.001037146,0.0009051346],"domain_scores_gemma":[0.9970671,0.0007812361,0.00005130302,0.001431552,0.0002797777,0.0003890232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003983363,0.0001173607,0.004166203,0.00001627028,0.000003783574,0.00009664246,0.0007699186,0.00004003489,0.3933397,0.02626682,0.00008685322,0.5750925],"study_design_scores_gemma":[0.0009308129,0.0002210138,0.01987038,0.0001186364,0.00002434796,0.0003467642,0.0004939048,0.3266862,0.5877433,0.00729882,0.05487873,0.001387076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3813691,0.00002166278,0.6170408,0.0002220187,0.000702718,0.0002117689,0.000003043973,0.0001216044,0.0003072852],"genre_scores_gemma":[0.1980235,0.00001028229,0.8015417,0.00001306728,0.0001819388,0.0001256436,0.000001339221,0.00001301964,0.00008948203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5737054,"threshold_uncertainty_score":0.7479625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8360044474353515,"score_gpt":0.6474662355025267,"score_spread":0.1885382119328248,"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."}}