{"id":"W3193852816","doi":"10.1016/j.knosys.2021.107382","title":"Con2Vec: Learning embedding representations for contrast sets","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Contrast (vision); Embedding; Artificial intelligence; Feature vector; Computer science; Set (abstract data type); Similarity (geometry); Pattern recognition (psychology); Support vector machine; Vector space; Feature (linguistics); Mathematics; Image (mathematics)","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":[0.001297907,0.002523321,0.001354551,0.001736266,0.0005663505,0.001604729,0.001781001,0.001268542,0.004505109],"category_scores_gemma":[0.004069778,0.0005382187,0.00111673,0.002442836,0.0005243661,0.002452088,0.001847748,0.002905217,0.00305177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007492697,"about_ca_system_score_gemma":0.001270842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004810147,"about_ca_topic_score_gemma":0.007686334,"domain_scores_codex":[0.9990676,0.000186494,0.00006098679,0.0003030793,0.0002802013,0.000101664],"domain_scores_gemma":[0.998893,0.0003656555,0.00008323042,0.0002725868,0.0003203573,0.00006529617],"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":[0.0003785794,0.0004906894,0.001595951,0.0003278648,0.0002193586,0.00009703197,0.0001107055,0.02924679,0.01253814,0.00782306,0.06359708,0.8835748],"study_design_scores_gemma":[0.00006999567,0.0002193532,0.001210672,0.00007586605,0.00007411618,0.0001513215,0.00009823641,0.9502134,0.01537304,0.01872259,0.01374626,0.00004519881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02653419,0.001632314,0.9500711,0.0005609628,0.0006470598,0.0002192462,0.004444315,0.01392138,0.001969465],"genre_scores_gemma":[0.2528062,0.001629278,0.710155,0.0005332947,0.0004173322,0.0007462325,0.02387547,0.001453455,0.008383713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004810147,"threshold_uncertainty_score":0.01507103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03885619592808201,"score_gpt":0.3398254438502533,"score_spread":0.3009692479221713,"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."}}