{"id":"W3176912690","doi":"10.7910/dvn/g98bqg","title":"CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing","year":2021,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Social media; Computer science; Data science; Political science; Business; World Wide Web; Marketing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001897091,0.0003282855,0.0004362479,0.0004197414,0.002979893,0.001343531,0.001471244,0.0007499094,0.007712793],"category_scores_gemma":[0.001620886,0.000376193,0.0001935924,0.0006778233,0.0002088649,0.003715115,0.0004743213,0.0006340785,0.002923895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003477573,"about_ca_system_score_gemma":0.001132259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002010857,"about_ca_topic_score_gemma":0.006193745,"domain_scores_codex":[0.9968427,0.0004365086,0.000881337,0.0004350723,0.0008517902,0.0005525476],"domain_scores_gemma":[0.9969694,0.0003417781,0.0008366668,0.001135146,0.0005466018,0.000170402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001023898,0.00007245968,8.39078e-7,0.00009798187,0.00006266865,0.000002001012,0.004322056,0.000003004798,3.086403e-7,0.002985812,0.9837674,0.008675178],"study_design_scores_gemma":[0.0004169957,0.00001112058,0.00003010629,0.00008550439,0.0002744963,0.000001599631,0.01553622,0.0001093554,4.743395e-7,0.0004611913,0.9826578,0.0004151582],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000008553088,0.00001975384,0.0004052802,0.0002889139,0.000985102,0.0004256118,0.996379,0.00008691454,0.001400855],"genre_scores_gemma":[0.0002907377,0.0007374148,0.001023649,0.0003962285,0.0007419835,0.0001464075,0.9966168,0.00001858533,0.00002818443],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01121416,"threshold_uncertainty_score":0.999869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03225268753770763,"score_gpt":0.3070516844936019,"score_spread":0.2747989969558943,"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."}}