{"id":"W2478941700","doi":"10.1075/cilt.309.18isl","title":"Semantic similarity of short texts","year":2009,"lang":"en","type":"article","venue":"Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory","topic":"Topic Modeling","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Semantic similarity; Natural language processing; Similarity (geometry); Artificial intelligence; Word (group theory); Sentence; Variety (cybernetics); Focus (optics); Representation (politics); Matching (statistics); Longest common subsequence problem; Information retrieval; String metric; Pattern matching; String searching algorithm; Mathematics; Algorithm","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":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01202223,0.0003721897,0.0008268156,0.0005750928,0.0002361636,0.00004018408,0.002379484,0.00007262182,0.00001184857],"category_scores_gemma":[0.0143919,0.0002921823,0.00009882783,0.0007148638,0.004974879,0.0002382521,0.0006011899,0.0004461973,0.000002077307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003069684,"about_ca_system_score_gemma":0.0003020439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000221884,"about_ca_topic_score_gemma":0.00001978088,"domain_scores_codex":[0.9959119,0.0008177491,0.001111329,0.0008030303,0.0007642187,0.0005917986],"domain_scores_gemma":[0.9956554,0.002197202,0.0003438421,0.001254522,0.0004638564,0.00008517312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001263812,0.0002031953,0.0003305494,0.0002409398,0.00001508785,0.00003566582,0.1376202,0.0000567774,0.00008904577,0.8500642,0.00005037743,0.01116759],"study_design_scores_gemma":[0.0003591809,0.0003836003,0.001075387,0.0009508581,0.00005871592,0.00003375179,0.004865928,0.0009890991,0.0001868892,0.9842605,0.006415453,0.0004206371],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.391213,0.4117324,0.04791377,0.0007730417,0.04752577,0.002768003,0.000035155,0.0004257203,0.09761316],"genre_scores_gemma":[0.995027,0.001272824,0.002864933,0.0001322482,0.0003264861,0.00001427174,8.173964e-7,0.000009766248,0.0003516356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.603814,"threshold_uncertainty_score":0.999953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04907162359263313,"score_gpt":0.3432709032750194,"score_spread":0.2941992796823862,"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."}}