{"paper":{"title":"DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision","arxiv_id":"2610.19118","primary_cat":"cs.CL","submitted_at":"2026-10-13T19:52:14+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.74,"id":"s1","own":false,"role":"background","text":"As these models are increasingly used for automated decision-making, understanding their reliability under adversarial manipulation becomes critical.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.26,"method":0.0,"result":0.0,"background":0.74,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":true,"role":"contribution","text":"We introduce DecisionRobust, a benchmark for systematically evaluating the robustness of decision models across textual and visual inputs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":3,"p":0.63,"id":"s3","own":true,"role":"method","text":"Our benchmark covers practical decision-making scenarios and a diverse suite of attacks, including semantics-preserving text perturbations, image perturbations, and prompt injection in both modalities.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.82,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.63,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.37,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"method","text":"We curate evaluation sets through external validity checks and cross-model candidate selection.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"method","text":"We evaluate 30 model configurations on text tasks and 17 on vision tasks, including 24 and 12 held-out models, respectively, that are excluded from candidate selection.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":6,"p":0.9,"id":"s6","own":true,"role":"result","text":"Our experiments reveal several key findings.","hedge":{"p":0.52,"label":"asserted"},"own_p":0.57,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.9,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.03}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"First, attacks expose vulnerabilities beyond the models used for construction and selection, although optimized image perturbations transfer weakly to many targets even with multiple surrogates.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.19,"quantitative":true,"quantitative_p":0.72,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.94,"id":"s8","own":true,"role":"result","text":"Second, relative model robustness varies across tasks and attack types, and resistance to input perturbations does not necessarily imply resistance to prompt injection.","hedge":{"p":0.92,"label":"asserted"},"own_p":0.91,"main_claim_p":0.22,"quantitative":false,"quantitative_p":0.41,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.94,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.06}},{"i":9,"p":0.95,"id":"s9","own":true,"role":"result","text":"Third, label-consistency checks substantially reduce measured attack success across text and image settings, highlighting the importance of validating apparent failures.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.28,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.95,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.05}},{"i":10,"p":0.94,"id":"s10","own":false,"role":"contribution","text":"The benchmark is available at https://yifan-lan.github.io/DecisionRobust/.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.47,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.05,"contribution":0.94,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.41,"text":"Second, relative model robustness varies across tasks and attack types, and resistance to input perturbations does not necessarily imply resistance to prompt injection.","location":"abstract s8","hedge_strength":{"p":0.92,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":8110,"cost_usd_reported":0.0},"compiled_at":"2026-10-15","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.73,"human_participants":0.11,"controlled_comparison":0.18,"randomized_assignment":0.02,"states_quantitative_result":0.86,"compares_with_prior_results":0.29,"mentions_code_or_data_availability":0.93},"evidential_basis":{"p":1.0,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":1.0,"simulation_or_computation":0.0}},"contribution_type":{"p":1.0,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":1.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We introduce DecisionRobust, a benchmark for systematically evaluating the robustness of decision models across textual and visual inputs.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":11,"sentences_in_abstract":11},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}