{"id":"W4385570854","doi":"10.18653/v1/2023.acl-long.370","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created through Human-Machine Collaboration","year":2023,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Advanced Institute of Science and Technology; Institute for Basic Science; Seoul National University","keywords":"Square (algebra); Alice (programming language); Volume (thermodynamics); Scale (ratio); Computer science; Library science; Geography; Cartography; Mathematics; Physics; Programming language; Geometry","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":[0.004707684,0.001694228,0.0009820547,0.004125945,0.001332168,0.001641231,0.001997194,0.003476116,0.006283462],"category_scores_gemma":[0.02557185,0.0004944321,0.001011414,0.002730062,0.0009533223,0.002165495,0.005052792,0.001715901,0.01365995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007914652,"about_ca_system_score_gemma":0.001290798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004957021,"about_ca_topic_score_gemma":0.0131909,"domain_scores_codex":[0.9924917,0.003905926,0.0006110905,0.00119548,0.001448589,0.0003471689],"domain_scores_gemma":[0.9714364,0.01493394,0.001909372,0.005361098,0.004449986,0.001909125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003346452,0.002232116,0.06822654,0.003994658,0.0006770835,0.001812039,0.008231701,0.002422244,0.01790608,0.001830278,0.784099,0.1052218],"study_design_scores_gemma":[0.001355781,0.001759456,0.3656229,0.0007535716,0.0003745108,0.003168618,0.01422371,0.03096432,0.01939023,0.007571948,0.5540977,0.000717246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2931884,0.002960961,0.01975696,0.00239067,0.001087288,0.00216561,0.6495817,0.01603271,0.01283561],"genre_scores_gemma":[0.1368367,0.0003908124,0.03016517,0.0008735028,0.0003091535,0.002293539,0.8217787,0.0007653615,0.006587032],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.006283462,"threshold_uncertainty_score":0.02489686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01797182839056671,"score_gpt":0.3065850354769433,"score_spread":0.2886132070863766,"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."}}