{"id":"W4386566601","doi":"10.18653/v1/2023.findings-eacl.52","title":"Detecting Contextomized Quotes in News Headlines by Contrastive Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Institute for Basic Science; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Headline; Computer science; Context (archaeology); Credibility; Citation; Sign (mathematics); Matching (statistics); Embedding; Code (set theory); Domain (mathematical analysis); Appeal; Information retrieval; Natural language processing; Linguistics; Artificial intelligence; World Wide Web; History; Programming language; Political science; Mathematics; Philosophy; Epistemology","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":[0.000441283,0.00009806223,0.0001963733,0.0001220655,0.00007709223,0.0001024845,0.0003114405,0.00004504104,0.00001178585],"category_scores_gemma":[0.000490123,0.00008813965,0.00003646813,0.0004692267,0.0000131453,0.0002585295,0.0001575857,0.0001929282,0.00007648071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002818803,"about_ca_system_score_gemma":0.0000273789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008716626,"about_ca_topic_score_gemma":0.0005415626,"domain_scores_codex":[0.998898,0.00009800597,0.000248707,0.0003181304,0.0001365914,0.000300518],"domain_scores_gemma":[0.9991541,0.0005408834,0.00005366819,0.0001641894,0.00003723644,0.000049913],"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":[0.00006014945,0.00005909788,0.07064924,0.00003314733,0.00004390664,0.00008922284,0.008991616,0.03083511,0.04256025,0.01618258,0.001314753,0.8291809],"study_design_scores_gemma":[0.001104013,0.00002441364,0.0008157938,0.00002512546,0.000001032061,0.000001920153,0.001035689,0.9921539,0.002935814,0.001243909,0.0005147613,0.0001436227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3389345,0.00006584699,0.6585767,0.0008929406,0.0001487542,0.0001043734,2.0246e-7,0.0004921321,0.0007845927],"genre_scores_gemma":[0.991125,0.00001075997,0.007873786,0.0001806409,0.00003743869,0.00001355825,9.992226e-7,0.000007259205,0.0007505513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9613188,"threshold_uncertainty_score":0.3594231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709988059730311,"score_gpt":0.2776679070946935,"score_spread":0.2505680264973904,"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."}}