{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007037363,0.000064834,0.0001058377,0.00002524422,0.00005046544,0.00003038099,0.0003410003,0.00003754812,0.00001308389],"category_scores_gemma":[0.0003911768,0.00005547574,0.000039437,0.00008218084,0.0000157672,0.0006435799,0.0001875886,0.00005068823,0.000003737615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000239653,"about_ca_system_score_gemma":0.0001046484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001284225,"about_ca_topic_score_gemma":0.000001187102,"domain_scores_codex":[0.9991031,0.00002784638,0.0002352413,0.0001447952,0.0002559038,0.0002330935],"domain_scores_gemma":[0.9989773,0.0004115027,0.0000716779,0.000286455,0.0001811544,0.00007187805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001728675,0.00003954387,0.000464216,0.0000161173,0.000006344381,6.356154e-8,0.0001171497,0.005246721,0.001084661,0.9902423,0.0000170722,0.002764075],"study_design_scores_gemma":[0.0001210862,0.00002770835,0.0003213754,0.00001244584,0.000006141002,0.00000276288,0.000008342165,0.9364751,0.002181124,0.06075902,0.00001668674,0.00006820608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01619702,0.00002150905,0.9821412,0.0004962735,0.0001427949,0.0001314489,0.000003989478,0.00003792195,0.0008278743],"genre_scores_gemma":[0.5930371,6.633624e-7,0.4068449,0.00004973507,0.00003278828,0.000007871974,0.000001794022,0.000001702181,0.00002340416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9312284,"threshold_uncertainty_score":0.2262235,"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."}}