{"id":"W2510135622","doi":"10.48550/arxiv.1608.07738","title":"Testing APSyn against Vector Cosine on Similarity Estimation","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; University of Oxford; University of Wisconsin-Madison","keywords":"Cosine similarity; Similarity (geometry); Computer science; Discrete cosine transform; Estimation; Artificial intelligence; Pattern recognition (psychology); Algorithm; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002682513,0.0003034605,0.0002753856,0.0002149186,0.0001798398,0.0001252631,0.001495942,0.000259187,0.000008585076],"category_scores_gemma":[0.0002395234,0.0003114236,0.0001167988,0.0003541381,0.0000563562,0.0003525709,0.001423496,0.0004897808,0.0001145309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003583778,"about_ca_system_score_gemma":0.0001929824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004008845,"about_ca_topic_score_gemma":0.000006141568,"domain_scores_codex":[0.9980302,0.0001123164,0.0002135637,0.00116596,0.0001328357,0.0003450815],"domain_scores_gemma":[0.9976918,0.0002808382,0.0002690965,0.001426447,0.0001837362,0.0001481589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001698019,0.0001032591,0.001944678,0.00010036,0.00004651244,0.0002464507,0.0001069197,0.7893631,0.000273501,0.1887257,0.0002157424,0.01885676],"study_design_scores_gemma":[0.0003029667,0.00003409146,0.001719146,0.0003653255,0.00001598185,0.000001658528,0.000003486138,0.9528027,0.0002107657,0.04410967,0.00008200515,0.0003521519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.168809,0.000009450981,0.8234939,0.0002974396,0.0005433853,0.0002232194,0.00001122238,0.0004130556,0.006199343],"genre_scores_gemma":[0.9811764,0.000007702255,0.01810202,0.0002084014,0.0001306473,8.958061e-7,0.000008448744,0.0000166968,0.0003487928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8123674,"threshold_uncertainty_score":0.9999338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1181623652735462,"score_gpt":0.2010710518645653,"score_spread":0.08290868659101915,"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."}}