{"id":"W4400681662","doi":"10.1109/saner60148.2024.00019","title":"Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Refining (metallurgy); Computer science; Artificial intelligence; Materials science; Metallurgy","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":[],"consensus_categories":[],"category_scores_codex":[0.0001852031,0.0001050972,0.00008535217,0.0001109631,0.0001194868,0.0003779027,0.0003363302,0.00006839936,0.00001190623],"category_scores_gemma":[0.0000758463,0.00007190619,0.00003431821,0.0003848456,0.00002212774,0.0003834781,0.00007477697,0.0002066683,0.00002347383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461773,"about_ca_system_score_gemma":0.00004187892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000440278,"about_ca_topic_score_gemma":0.00009795502,"domain_scores_codex":[0.9990889,0.00001753368,0.0001270135,0.0004583616,0.0001401138,0.0001680051],"domain_scores_gemma":[0.9993466,0.0001061679,0.0000367338,0.0003957392,0.00006240825,0.00005236089],"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":[0.00004872732,0.00003348702,0.000130334,0.0001133331,0.00002476703,0.000007284653,0.0002567859,0.0001334053,0.1662572,0.2063005,0.001284362,0.6254098],"study_design_scores_gemma":[0.0005348207,0.0006796033,0.004372288,0.0001043073,0.00002798956,0.000312801,0.00003923094,0.800808,0.01069614,0.002726376,0.1792588,0.0004396676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008588016,0.00004383293,0.9849412,0.003868406,0.0001097058,0.0001133837,0.000009214004,0.0009980005,0.001328227],"genre_scores_gemma":[0.8897953,0.00000123917,0.1090653,0.0002014408,0.00006308753,0.00003502454,0.00002592461,0.00001284666,0.0007998146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8812073,"threshold_uncertainty_score":0.3644124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007164724710223737,"score_gpt":0.2590984125606616,"score_spread":0.2519336878504378,"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."}}