{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01301709,0.001953546,0.001875487,0.00360999,0.0008885768,0.003984291,0.00164205,0.002768813,0.009102009],"category_scores_gemma":[0.07121853,0.0004150787,0.001512287,0.002476372,0.001035724,0.008162241,0.004226947,0.001528998,0.007107525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009697367,"about_ca_system_score_gemma":0.0007400933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003741716,"about_ca_topic_score_gemma":0.00227376,"domain_scores_codex":[0.9732682,0.0155405,0.001316702,0.005473114,0.003729731,0.0006716669],"domain_scores_gemma":[0.9379063,0.05054773,0.002415656,0.004829553,0.00299987,0.001300831],"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":[0.004123202,0.002117258,0.08665517,0.002214707,0.001063286,0.0005528625,0.006171295,0.02988418,0.02689528,0.004956307,0.03212857,0.8032379],"study_design_scores_gemma":[0.0007866385,0.005242489,0.240819,0.0003880256,0.0005646084,0.001863149,0.005140484,0.6326829,0.03441034,0.03386372,0.04345235,0.0007862964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8705073,0.003967926,0.07553446,0.0008104858,0.0003869638,0.0006948,0.003292767,0.009993534,0.03481174],"genre_scores_gemma":[0.9639702,0.0004975667,0.02533995,0.0002466528,0.000116793,0.0003320642,0.004940808,0.0003825691,0.004173423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01301709,"threshold_uncertainty_score":0.06884176,"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."}}