{"id":"W4250772288","doi":"10.18653/v1/2021.trustnlp-1","title":"Proceedings of the First Workshop on Trustworthy Natural Language Processing","year":2021,"lang":"en","type":"paratext","venue":"","topic":"Access Control and Trust","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Center for Cognitive Computing Systems Research","keywords":"Computer science; Trustworthiness; Natural (archaeology); Natural language processing; Artificial intelligence; Computer security; History; Archaeology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002369005,0.0002280431,0.0003859811,0.00006604887,0.0006812889,0.0003086804,0.000783235,0.0003386586,0.002832243],"category_scores_gemma":[0.000210641,0.0001398463,0.0002189071,0.0006955183,0.0002828448,0.000198238,0.0001396112,0.0006208413,0.0001656374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008715859,"about_ca_system_score_gemma":0.0003801617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007046241,"about_ca_topic_score_gemma":0.00318536,"domain_scores_codex":[0.9983121,0.00002476932,0.0002651831,0.0003560699,0.0006763215,0.0003656009],"domain_scores_gemma":[0.9990728,0.0001029747,0.0003394705,0.0001356294,0.0002898473,0.00005929792],"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":[0.00008994226,0.0002075572,0.0009041811,0.000671133,0.0001663898,0.000007912844,0.03240411,0.00002125498,0.00003030983,0.010029,0.7952596,0.1602086],"study_design_scores_gemma":[0.0003829268,0.00001342515,0.0008158109,0.001404062,0.0000791622,0.000001100523,0.02387798,0.00008431014,0.00020027,0.00004134935,0.9726466,0.0004530232],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.006682049,0.007783971,0.000002132771,0.004300576,0.001745625,0.0003847661,0.00001011242,0.00004005493,0.9790507],"genre_scores_gemma":[0.5836773,0.0001783911,0.00001992029,0.00057713,0.0009475639,0.00002098962,0.000007416073,0.00001735733,0.4145539],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5769953,"threshold_uncertainty_score":0.9980793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01309172166009172,"score_gpt":0.2976962105360751,"score_spread":0.2846044888759834,"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."}}