{"id":"W4400685466","doi":"10.1145/3676961","title":"SimClone: Detecting Tabular Data Clones Using Value Similarity","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Computer science; Data mining; Header; Software; Visualization; clone (Java method); Similarity (geometry); Margin (machine learning); Artificial intelligence; Image (mathematics); Machine learning","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":[0.00823037,0.0002071071,0.000357821,0.0004695182,0.0002430826,0.0002642443,0.0009938305,0.0001527411,0.00008419241],"category_scores_gemma":[0.01169658,0.0001817136,0.00008206233,0.0007041742,0.00006942535,0.000524469,0.0001467479,0.0004616339,0.00002808117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003395427,"about_ca_system_score_gemma":0.00004291626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001510445,"about_ca_topic_score_gemma":0.0000259809,"domain_scores_codex":[0.9973462,0.000571167,0.0004746813,0.0008655053,0.0004214555,0.0003209665],"domain_scores_gemma":[0.9867738,0.01132839,0.00004939012,0.001677727,0.00005205554,0.0001185879],"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":[0.00004344147,0.00006273903,0.00007651959,0.0002268518,0.0003209446,0.00008698137,0.0008501557,0.1973781,0.001641472,0.003315311,0.0004023531,0.7955951],"study_design_scores_gemma":[0.0006260757,0.0002505069,0.0008104127,0.0002937964,0.0007064644,0.0002824617,0.001694612,0.6160517,0.005319016,0.03222547,0.3406005,0.001138913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01910254,0.001107575,0.9766895,0.0004775084,0.001892082,0.0001279322,0.0001900513,0.0004058137,0.000007009971],"genre_scores_gemma":[0.1206913,0.0001543094,0.8786013,0.0002118217,0.0001219512,0.00001045791,0.00001997458,0.00003265172,0.0001563012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7944562,"threshold_uncertainty_score":0.9966283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.549696504884526,"score_gpt":0.4849508565192975,"score_spread":0.06474564836522856,"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."}}