{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003774125,0.00009400131,0.0001319018,0.0001264136,0.000270589,0.0001112245,0.0001356377,0.00005530862,0.00002602477],"category_scores_gemma":[0.00008940964,0.00008510433,0.00001508632,0.001226329,0.00004127034,0.0005496311,0.0001527107,0.00006990531,0.00004203023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001773947,"about_ca_system_score_gemma":0.00004924515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005908966,"about_ca_topic_score_gemma":0.001567923,"domain_scores_codex":[0.9990527,0.0001396555,0.0001755489,0.0002809376,0.0001657153,0.0001854342],"domain_scores_gemma":[0.9992852,0.0001084483,0.00007093218,0.0003425641,0.0001456082,0.000047282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004482325,0.0007547144,0.003853338,0.0001987554,0.0002395136,0.0002272738,0.01642489,0.001096871,0.5280141,0.1385136,0.2971051,0.01312362],"study_design_scores_gemma":[0.003803678,0.002083325,0.03305551,0.0001923881,0.0001085957,0.0001253342,0.006373506,0.164119,0.6339132,0.01145967,0.1434942,0.001271584],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5873771,0.00009422781,0.3998731,0.003365906,0.0003308155,0.0006789447,0.003178192,0.001230393,0.003871332],"genre_scores_gemma":[0.9760858,0.00008318624,0.020323,0.000276901,0.00002991922,0.00002111644,0.00111197,0.00001144807,0.00205667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3887087,"threshold_uncertainty_score":0.3470454,"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."}}