{"id":"W4287887877","doi":"10.18653/v1/2022.trustnlp-1","title":"Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022)","year":2022,"lang":"en","type":"paratext","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Compute Canada","keywords":"Computer science; Trustworthiness; Natural language processing; Programming language; Artificial intelligence; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01742047,0.002088082,0.002524771,0.002787197,0.001802955,0.007641892,0.003947844,0.004060876,0.05866119],"category_scores_gemma":[0.02671073,0.001314738,0.00232963,0.002358071,0.002679898,0.01447407,0.008034586,0.005790608,0.02784462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003298962,"about_ca_system_score_gemma":0.005154011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01095205,"about_ca_topic_score_gemma":0.01391826,"domain_scores_codex":[0.9899419,0.004902082,0.000819233,0.001802299,0.001981275,0.0005532837],"domain_scores_gemma":[0.9801322,0.009109948,0.000455895,0.004817494,0.003888581,0.001595951],"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":[0.0008785479,0.0004886313,0.0008818611,0.001071357,0.0002122784,0.0007971139,0.001294424,0.003960596,0.007578726,0.01841988,0.5679107,0.3965059],"study_design_scores_gemma":[0.0001628944,0.0002464549,0.001863282,0.000556674,0.0001448164,0.0007205583,0.0008416544,0.05014184,0.007348693,0.05509755,0.8827629,0.0001127244],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01927589,0.02650328,0.7949615,0.05089091,0.01683082,0.001589012,0.0121448,0.02602843,0.05177539],"genre_scores_gemma":[0.1007068,0.0189817,0.5770739,0.01000467,0.005978538,0.002283578,0.0854334,0.0144271,0.1851103],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.05866119,"threshold_uncertainty_score":0.1962413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0125641609925274,"score_gpt":0.2608450258984049,"score_spread":0.2482808649058775,"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."}}