{"id":"W4404971593","doi":"10.1007/978-3-031-78498-9_3","title":"ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Code (set theory); Programming language; Artificial intelligence; Natural language processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008067014,0.0003964939,0.0004264386,0.0004729604,0.0002382404,0.0007491521,0.0009876001,0.0002426539,0.000006289049],"category_scores_gemma":[0.0001206173,0.0003772549,0.000080711,0.0002652308,0.0003502328,0.0004434585,0.0006930606,0.0006742954,0.000009940319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002292111,"about_ca_system_score_gemma":0.0002845149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001162191,"about_ca_topic_score_gemma":0.00002904258,"domain_scores_codex":[0.9970775,0.00001792987,0.0004255689,0.001495248,0.0005104194,0.0004733149],"domain_scores_gemma":[0.99828,0.0007702063,0.0002056155,0.000393486,0.0002228537,0.0001278605],"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":[0.00001964294,0.00001108588,0.00004207028,0.0001889696,0.00003881244,0.00005009419,0.00420584,0.03411157,0.001207172,0.2449561,0.00001552476,0.7151532],"study_design_scores_gemma":[0.0003474754,0.0001339337,0.000009204273,0.0003411816,0.00001464413,0.00002779008,0.000001386566,0.8123918,0.0008619661,0.1840598,0.00144334,0.0003674205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002709074,0.0006482276,0.9949752,0.0008208947,0.001364342,0.0005933502,0.000006255255,0.0002127625,0.001108069],"genre_scores_gemma":[0.4222109,0.00006397133,0.573666,0.000885218,0.0005365042,0.0000391815,0.00001226625,0.00005935239,0.002526547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7782803,"threshold_uncertainty_score":0.9998679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02016555235156858,"score_gpt":0.2800862608764734,"score_spread":0.2599207085249048,"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."}}