{"id":"W1505951874","doi":"10.48550/arxiv.cs/0412024","title":"Human-Level Performance on Word Analogy Questions by Latent Relational Analysis","year":2004,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Analogy; Word (group theory); Computer science; Natural language processing; Linguistics; Psychology; Cognitive psychology; Philosophy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003043764,0.0002947465,0.0003820354,0.0004345167,0.0002711031,0.00008480313,0.001096419,0.0002905029,0.00006599562],"category_scores_gemma":[0.00003118848,0.0003033973,0.0002470305,0.000623179,0.00005355303,0.0002042872,0.0007596398,0.000843388,0.0001862092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000329088,"about_ca_system_score_gemma":0.0002005576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002978942,"about_ca_topic_score_gemma":0.0001038368,"domain_scores_codex":[0.9976631,0.00008037721,0.0005151533,0.0009634421,0.0004330772,0.0003448189],"domain_scores_gemma":[0.9980826,0.00004673891,0.0002699471,0.001341964,0.0001398693,0.0001188592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000002380695,0.000118624,0.3854078,0.00002721782,0.0003664432,0.000009879532,0.0002706531,0.5944181,0.00006309059,0.01728572,0.0002209778,0.001809051],"study_design_scores_gemma":[0.000189684,0.00003289901,0.8488886,0.00008220552,0.0001354025,0.000002404567,0.000002154473,0.1479366,0.00006506988,0.001984425,0.0003163304,0.0003641926],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6299484,0.0001063132,0.3678595,0.0008888283,0.0003494083,0.0001147504,0.00001586919,0.0001392167,0.0005777662],"genre_scores_gemma":[0.9851003,0.0000433485,0.01271701,0.0003493208,0.0001495398,0.00004469565,0.0001325418,0.00001538074,0.00144791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4634808,"threshold_uncertainty_score":0.9999418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1067159162861817,"score_gpt":0.2968550252287323,"score_spread":0.1901391089425506,"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."}}