{"paper":{"title":"InternW0-$\\Delta$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data","arxiv_id":"2609.31394","primary_cat":"cs.RO","submitted_at":"2026-09-25T15:24:25+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 (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.09,"main_claim_p":0.04,"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":0.61,"id":"s1","own":false,"role":"background","text":"A central challenge is to integrate priors from large-scale pretrained models---including visual dynamics, scene semantics, geometry, and motion---into a unified framework for robot action generation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.39,"method":0.0,"result":0.0,"background":0.61,"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 InternW0-$\\Delta$, a unified WAM pretrained on a heterogeneous corpus that outperforms prior methods across simulation benchmarks and real-robot platforms.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.76,"quantitative":true,"quantitative_p":0.89,"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":0.89,"id":"s3","own":true,"role":"method","text":"InternW0-$\\Delta$ combines pretrained visual dynamics, scene-level semantics, 4D geometric and motion priors, and action generation within a Mixture-of-Transformers (MoT) framework.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.89,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.11,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"A pretrained video expert and an action expert interact under semantic guidance from a frozen VLM, while a pretrained 4D foundation model injects geometric and motion priors through training-only distillation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.82,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"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":0.62,"id":"s5","own":true,"role":"contribution","text":"We further introduce Causal Imprint, which learns future-relevant scene changes from training-only future supervision and provides predictive representations directly to the action expert without future-video rollout at inference.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.38,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.62,"interpretation":0.0}},{"i":6,"p":0.96,"id":"s6","own":true,"role":"method","text":"For large-scale joint training, we construct a heterogeneous corpus of robot demonstrations, UMI data, egocentric human demonstrations, and Ego2Robot data, curated and aligned under a common state-action representation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.08,"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":7,"p":0.37,"id":"s7","own":true,"role":"method","text":"The resulting corpus contains over 20K hours of processed training data, to our knowledge the largest open-source corpus of its kind.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.93,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.37,"result":0.27,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.35,"interpretation":0.01}},{"i":8,"p":0.91,"id":"s8","own":true,"role":"result","text":"We pretrain InternW0-$\\Delta$ on this corpus and demonstrate strong performance across simulation benchmarks and real-robot platforms.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.38,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.91,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.07,"interpretation":0.0}},{"i":9,"p":0.67,"id":"s9","own":true,"role":"future_work","text":"We will open source the training code, model weights, infrastructure, data-processing pipeline, and processed data where licenses permit.","hedge":{"p":0.76,"label":"asserted"},"own_p":0.54,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.0,"limitation":0.01,"future_work":0.67,"contribution":0.3,"interpretation":0.0}},{"i":10,"p":0.69,"id":"s10","own":false,"role":"future_work","text":"Project page: https://internrobotics.github.io/InternW0-Delta/","hedge":{"p":0.82,"label":"unclear"},"own_p":0.27,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.06,"limitation":0.0,"future_work":0.69,"contribution":0.23,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.97,"text":"We introduce InternW0-$\\Delta$, a unified WAM pretrained on a heterogeneous corpus that outperforms prior methods across simulation benchmarks and real-robot platforms.","location":"abstract s2","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":8334,"cost_usd_reported":0.0},"compiled_at":"2026-09-28","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.15,"states_limitation":0.46,"human_participants":0.23,"controlled_comparison":0.44,"randomized_assignment":0.01,"states_quantitative_result":0.93,"compares_with_prior_results":0.91,"mentions_code_or_data_availability":0.94},"evidential_basis":{"p":0.84,"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":0.84,"simulation_or_computation":0.16}},"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":0.89,"text":"We introduce InternW0-$\\Delta$, a unified WAM pretrained on a heterogeneous corpus that outperforms prior methods across simulation benchmarks and real-robot platforms.","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"}}}