{"paper":{"title":"EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent","arxiv_id":"2607.13792","primary_cat":"cs.CV","submitted_at":"2026-07-15T12:55:35+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":"Most daily activities are inherently procedural.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.01,"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":1.0,"id":"s1","own":false,"role":"gap","text":"However, existing evaluations for egocentric video understanding seldom address procedural understanding and largely overlook complex key-step-level reasoning under the widely used video question answering (VQA) paradigm for MLLMs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.19,"role_probabilities":{"gap":1.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.85,"id":"s2","own":false,"role":"background","text":"Such capabilities are crucial for building procedural AI assistants deployable on wearable devices.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.05,"method":0.0,"result":0.0,"background":0.85,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.1}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"contribution","text":"To bridge this gap, we introduce the Egocentric Procedural Understanding VQA task (EgoProceVQA), which systematically evaluates egocentric procedural reasoning abilities of current MLLMs and agents through six types of key-step-centric questions.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.94,"main_claim_p":0.07,"quantitative":true,"quantitative_p":0.82,"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":4,"p":0.56,"id":"s4","own":true,"role":"contribution","text":"Furthermore, we develop EgoProceGen, a data generation platform that efficiently constructs QA data tailored to different question types.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.44,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.56,"interpretation":0.0}},{"i":5,"p":0.58,"id":"s5","own":true,"role":"contribution","text":"Based on this platform, we build a benchmark with 3,600 questions, four common procedural scenarios, and 31 everyday procedural tasks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.42,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.58,"interpretation":0.0}},{"i":6,"p":0.97,"id":"s6","own":true,"role":"result","text":"Evaluations on EgoProceVQA show that existing MLLMs and agents still have substantial room for improvement in procedural understanding.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.26,"quantitative":false,"quantitative_p":0.16,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.97,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.03}},{"i":7,"p":0.95,"id":"s7","own":true,"role":"contribution","text":"Therefore, we further propose EgoProceAgent, a self-skill-exploration agentic framework.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.92,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":8,"p":0.96,"id":"s8","own":true,"role":"method","text":"We design a generic tool library for procedural understanding and a standardized sub-skill library shared across tools and models, enabling self-exploration without ground-truth supervision.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.96,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":9,"p":0.95,"id":"s9","own":true,"role":"result","text":"By exploring how to compose and select sub-skills, the agent discovers effective skill strategies for diverse problems, and attains state-of-the-art performance among open-source models on multiple tasks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.27,"quantitative":true,"quantitative_p":0.77,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.95,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":10,"p":0.87,"id":"s10","own":true,"role":"contribution","text":"Together, our benchmark, generation platform, and agentic framework establish a unified foundation for EgoProceVQA.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.87,"interpretation":0.13}},{"i":11,"p":0.67,"id":"s11","own":false,"role":"contribution","text":"Project page: https://z1oong.github.io/EgoProceVQA/.","hedge":{"p":0.76,"label":"unclear"},"own_p":0.36,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.04,"limitation":0.0,"future_work":0.27,"contribution":0.67,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.48,"text":"Together, our benchmark, generation platform, and agentic framework establish a unified foundation for EgoProceVQA.","location":"abstract s10","hedge_strength":{"p":1.0,"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":8851,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.21,"states_limitation":0.13,"human_participants":0.11,"controlled_comparison":0.31,"randomized_assignment":0.01,"states_quantitative_result":0.93,"compares_with_prior_results":0.81,"mentions_code_or_data_availability":0.63},"evidential_basis":{"p":0.98,"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":0.98,"simulation_or_computation":0.02}},"contribution_type":{"p":0.92,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.08,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.92,"position_or_commentary":0.0}},"contribution_statement":{"p":0.95,"text":"To bridge this gap, we introduce the Egocentric Procedural Understanding VQA task (EgoProceVQA), which systematically evaluates egocentric procedural reasoning abilities of current MLLMs and agents through six types of key-step-centric questions.","location":"abstract s3"}},"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":12,"sentences_in_abstract":12},"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"}}}