{"paper":{"title":"Rethinking Representations for World-Action Modeling","arxiv_id":"2609.38163","primary_cat":"cs.CV","submitted_at":"2026-09-29T17:59:22+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":"World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"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":0.95,"id":"s1","own":true,"role":"result","text":"We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.48,"quantitative":false,"quantitative_p":0.34,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.95,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.01}},{"i":2,"p":0.86,"id":"s2","own":true,"role":"contribution","text":"These findings motivate ReWAM, a representation-centric world-action model built on pre-trained DINO features.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.68,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.13,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.86,"interpretation":0.01}},{"i":3,"p":0.96,"id":"s3","own":true,"role":"method","text":"Feature Calibration and a Temporal Representation Bottleneck organize these features into compact world states suited to dynamics modeling.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.77,"main_claim_p":0.08,"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":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"Action-Grounded Representation Shaping routes only action-loss gradients to the bottleneck, thereby letting the policy shape what the representation encodes while the world model learns how it evolves.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Without generative video pre-training, ReWAM achieves 93.6% success on RoboTwin 2.0.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.19,"quantitative":true,"quantitative_p":0.99,"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":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"On RoboDojo, it achieves an average score of 12.29 and a success rate of 8.28% using approximately 600 hours of embodied pre-training data.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.99,"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}}]},"compiled":{"main_claim":{"p":0.89,"text":"We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning.","location":"abstract s1","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":5555,"cost_usd_reported":0.0},"compiled_at":"2026-09-30","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.04,"states_limitation":0.5,"human_participants":0.03,"controlled_comparison":0.75,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.37,"mentions_code_or_data_availability":0.02},"evidential_basis":{"p":0.8,"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":0.8,"simulation_or_computation":0.2}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.9,"text":"These findings motivate ReWAM, a representation-centric world-action model built on pre-trained DINO features.","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":7,"sentences_in_abstract":7},"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"}}}