{"id":"W180888214","doi":"","title":"Evaluating Distributional Models of Semantics for Syntactically Invariant Inference","year":2012,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Distributional semantics; Phrase; Inference; Natural language processing; Invariant (physics); Artificial intelligence; Lemma (botany); Semantics (computer science); Sentence; Focus (optics); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01420415,0.001104513,0.001516946,0.002334206,0.0009665756,0.00372525,0.002282375,0.001894108,0.003342522],"category_scores_gemma":[0.04666892,0.0005550914,0.001591346,0.001737867,0.001792664,0.01126571,0.003376919,0.00319791,0.0009221156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002178404,"about_ca_system_score_gemma":0.001726417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003982431,"about_ca_topic_score_gemma":0.006436245,"domain_scores_codex":[0.9917203,0.005185267,0.0004346685,0.001139901,0.001209975,0.0003098601],"domain_scores_gemma":[0.9634428,0.0292273,0.001038719,0.003562927,0.002043665,0.000684542],"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":[0.001854268,0.0008392187,0.02220652,0.0007667299,0.0006529712,0.000260198,0.001048703,0.36831,0.01090936,0.1479297,0.006236262,0.438986],"study_design_scores_gemma":[0.00002214182,0.00008942528,0.0007501675,0.00001864077,0.00003380578,0.00003981281,0.00008322096,0.9350096,0.001937744,0.06161746,0.0003807731,0.00001708586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.176293,0.0006915925,0.814588,0.00112756,0.00008615578,0.0001447319,0.0005041534,0.002180626,0.004384081],"genre_scores_gemma":[0.8559792,0.0002623661,0.1399748,0.0001918823,0.0001120365,0.0001460612,0.001941719,0.0002974583,0.001094562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01420415,"threshold_uncertainty_score":0.07511967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.176781258763585,"score_gpt":0.3826369719767289,"score_spread":0.2058557132131439,"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."}}