{"id":"W1777006545","doi":"10.1111/j.1756-8765.2010.01108.x","title":"Comparing Methods for Single Paragraph Similarity Analysis","year":2010,"lang":"en","type":"article","venue":"Topics in Cognitive Science","topic":"Topic Modeling","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"Defence Research and Development Canada","keywords":"Paragraph; Computer science; Natural language processing; Artificial intelligence; Similarity (geometry); Word (group theory); Focus (optics); Semantic similarity; Vector space model; Simple (philosophy); Domain (mathematical analysis); Information retrieval; Linguistics; Mathematics; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002663097,0.0001153622,0.0002367963,0.0005345154,0.0002395627,0.0002532857,0.001248927,0.00005747801,0.00000710862],"category_scores_gemma":[0.001078642,0.0001141179,0.0000956429,0.002739231,0.0003442757,0.0005918653,0.0003745205,0.0002787223,0.000001810841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003699286,"about_ca_system_score_gemma":0.0001227768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005566777,"about_ca_topic_score_gemma":0.0002132548,"domain_scores_codex":[0.998297,0.00006123554,0.0002571729,0.0006966739,0.0002660198,0.0004219028],"domain_scores_gemma":[0.9985278,0.0004742319,0.00008332025,0.0004855912,0.0003213692,0.0001077033],"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":[0.00001049078,0.0002720314,0.1228959,0.00002041284,0.00006202272,0.000008826829,0.002075661,0.0008181948,0.05614874,0.2476825,0.000005986679,0.5699993],"study_design_scores_gemma":[0.0003248014,0.00003672849,0.0481782,0.00001240922,0.00003941005,0.000003317025,0.00006723918,0.8765512,0.0305274,0.04361786,0.0003871907,0.0002542538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2195244,0.00002402124,0.7744665,0.0002048526,0.0004644598,0.0001667616,0.000001134737,0.00004914844,0.005098823],"genre_scores_gemma":[0.5975857,9.485488e-7,0.4021789,0.000154512,0.0000364214,0.00001631338,5.57608e-7,0.00000181774,0.00002483504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.875733,"threshold_uncertainty_score":0.4653592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.149237096773703,"score_gpt":0.4262469145196294,"score_spread":0.2770098177459264,"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."}}