{"id":"W133424112","doi":"10.1007/978-3-642-30353-1_29","title":"Text Similarity Using Google Tri-grams","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Similarity (geometry); Artificial intelligence; Set (abstract data type); Natural language processing; Word (group theory); n-gram; Data set; Information retrieval; Language model; Mathematics; Image (mathematics)","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":[0.001282658,0.0006215673,0.0006361182,0.000687962,0.0003546849,0.0006391721,0.004218102,0.0004871048,0.00004214246],"category_scores_gemma":[0.00009020306,0.0005879994,0.0001885618,0.000606815,0.0005199625,0.001075516,0.002260661,0.00114597,0.00006597276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005144762,"about_ca_system_score_gemma":0.0006103607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007494743,"about_ca_topic_score_gemma":0.00004831786,"domain_scores_codex":[0.9952985,0.0000484951,0.0006359269,0.001725602,0.001205243,0.001086206],"domain_scores_gemma":[0.9966301,0.0003334979,0.0003313614,0.00218886,0.0002110834,0.0003051354],"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":[0.000002479947,0.00003371794,0.0001185807,0.00003508123,0.000009878052,0.00004536309,0.0006571984,0.04544223,0.0002413942,0.02214083,0.000009215502,0.931264],"study_design_scores_gemma":[0.0002006139,0.00004946514,0.00004758022,0.000228068,0.000011521,0.00009870289,1.008408e-7,0.9005431,0.0008683149,0.09468456,0.002529775,0.000738204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000255414,0.001150783,0.9920049,0.0004455066,0.002836258,0.0003586589,0.000003471319,0.0002248723,0.002720184],"genre_scores_gemma":[0.1912668,0.00003511812,0.8056622,0.001553413,0.001165078,0.000004215409,0.000002633751,0.00004624308,0.0002642289],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9305258,"threshold_uncertainty_score":0.9996572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04910519520628955,"score_gpt":0.2708755699584219,"score_spread":0.2217703747521324,"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."}}