{"id":"W2096565906","doi":"","title":"Alignment-Based Discriminative String Similarity","year":2007,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Discriminative model; Coreference; Artificial intelligence; Computer science; Substring; String metric; Similarity (geometry); Character (mathematics); Natural language processing; Longest common subsequence problem; String (physics); Word (group theory); Pattern recognition (psychology); Transliteration; Heuristic; String searching algorithm; Mathematics; Pattern matching; Resolution (logic); Algorithm; Set (abstract data type)","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"],"consensus_categories":[],"category_scores_codex":[0.001767842,0.0000954509,0.0001281573,0.00007461118,0.000236727,0.00006207456,0.000590612,0.00006804157,3.179561e-7],"category_scores_gemma":[0.01115894,0.00008052967,0.0001038899,0.0002699594,0.00002553938,0.00004011754,0.0001401127,0.0001189502,4.31109e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003126034,"about_ca_system_score_gemma":0.0001006165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001443478,"about_ca_topic_score_gemma":0.000006401025,"domain_scores_codex":[0.9986812,0.00005412094,0.0003449237,0.0001759115,0.0005483596,0.0001954224],"domain_scores_gemma":[0.9960378,0.001865358,0.0006803975,0.0001589809,0.001228894,0.00002860524],"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":[0.00001793994,0.0001201039,0.01440984,0.00009839574,0.00005125125,9.584106e-7,0.000540001,0.03079733,0.0003517079,0.9508581,0.0009003515,0.001854038],"study_design_scores_gemma":[0.0006834052,0.00007447046,0.00689848,0.0002026356,0.00005455118,5.160374e-7,0.00004679305,0.2728774,0.0717092,0.6446496,0.002502135,0.0003008987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001355758,0.00005870457,0.9961205,0.000482007,0.0006019163,0.0002101979,0.00002537581,0.0001409256,0.001004591],"genre_scores_gemma":[0.5739122,9.164423e-8,0.425802,0.0001284454,0.00009099129,0.000002477214,0.000008945046,0.000005015394,0.0000498364],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5725564,"threshold_uncertainty_score":0.9971705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01628738332415331,"score_gpt":0.2953723765151392,"score_spread":0.2790849931909859,"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."}}