{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001445796,0.002037956,0.001550336,0.001243769,0.0007856042,0.001996115,0.003491181,0.002162272,0.01141128],"category_scores_gemma":[0.005938935,0.0007679592,0.001473349,0.001312151,0.001279398,0.004924031,0.005181912,0.004223741,0.005734984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008855319,"about_ca_system_score_gemma":0.001618742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00334482,"about_ca_topic_score_gemma":0.00814426,"domain_scores_codex":[0.9987819,0.0002979304,0.0000524233,0.00042253,0.000322714,0.0001226064],"domain_scores_gemma":[0.9981698,0.0007010417,0.00006666615,0.0006188376,0.0003444879,0.00009925009],"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":[0.0005054309,0.0003120588,0.000624015,0.0003243914,0.0001022856,0.0001385181,0.000150666,0.06135852,0.0163703,0.05180774,0.03402302,0.834283],"study_design_scores_gemma":[0.00004539577,0.0001226165,0.0001590708,0.00003827348,0.00002503438,0.00009003592,0.00004124913,0.9233314,0.01039671,0.05557176,0.01014986,0.0000285372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007556358,0.0005057066,0.9782997,0.0002088708,0.0002651851,0.0001095046,0.0004888813,0.008750153,0.003815629],"genre_scores_gemma":[0.1828413,0.0005514224,0.7903306,0.00055556,0.0002935835,0.0004620047,0.004350928,0.002529961,0.01808466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01141128,"threshold_uncertainty_score":0.03817451,"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."}}