{"paper":{"title":"$\\mu_0$: A Scalable 3D Interaction-Trace World Model","arxiv_id":"2606.13769","primary_cat":"cs.RO","submitted_at":"2026-06-11T17:59:56+00:00","version_compiled":"v3"},"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 v3","sentences":[{"i":0,"p":0.98,"id":"s0","own":false,"role":"background","text":"World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.1,"main_claim_p":0.16,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":1,"p":0.77,"id":"s1","own":false,"role":"background","text":"Pixel-space video models provide broad visual priors but expend model capacity on dense appearance reconstruction, while direct action models require embodiment-specific labels that hinder scalability.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.29,"role_probabilities":{"gap":0.23,"method":0.0,"result":0.0,"background":0.77,"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 present $\\mu_0$, a scalable world model based on 3D traces.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.05,"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":0.73,"id":"s3","own":true,"role":"method","text":"Rather than predicting dense pixels or directly modeling actions, $\\mu_0$ forecasts smooth 3D trajectories for salient interaction points such as objects, tools, hands, and contact regions, yielding a compact, embodiment-agnostic motion interface.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.77,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.16,"role_probabilities":{"gap":0.0,"method":0.73,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.27,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"method","text":"To enable training from diverse video sources, our TraceExtract system automatically extracts 3D supervision by selecting keypoints, constructing globally aligned traces, and associating motion segments with hierarchical language captions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"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":1.0,"id":"s5","own":true,"role":"method","text":"This TraceExtract supervision pretrains $\\mu_0$ by combining a pretrained vision-language backbone with a modular trace expert, which represents each query via B-spline control points and predicts future traces.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"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":"Experiments show that $\\mu_0$ outperforms baselines in both 2D and 3D trace prediction, including trace prediction models and tokenized VLM methods.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.92,"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":7,"p":0.51,"id":"s7","own":true,"role":"interpretation","text":"Because $\\mu_0$ is frozen and reusable, it can be paired with action experts for downstream robot embodiments.","hedge":{"p":0.75,"label":"asserted"},"own_p":0.52,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.13,"result":0.1,"background":0.0,"limitation":0.0,"future_work":0.03,"contribution":0.23,"interpretation":0.51}},{"i":8,"p":0.99,"id":"s8","own":true,"role":"result","text":"Despite action-free pretraining, the resulting trace-conditioned policies achieve performance competitive with VLA models pretrained with action supervision, such as $\\pi_0$.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.91,"main_claim_p":0.17,"quantitative":true,"quantitative_p":0.84,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"interpretation","text":"These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.86,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.","location":"abstract s9","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":7634,"cost_usd_reported":0.0},"compiled_at":"2026-10-22","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.17,"human_participants":0.05,"controlled_comparison":0.93,"randomized_assignment":0.01,"states_quantitative_result":0.06,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.99,"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":0.99,"simulation_or_computation":0.01}},"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":0.84,"text":"We present $\\mu_0$, a scalable world model based on 3D traces.","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 v3"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"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"}}}