{"paper":{"title":"Towards Predictive, Aligned, and Scalable Robot Learning","arxiv_id":"2607.11270","primary_cat":"cs.RO","submitted_at":"2026-07-13T08:53:34+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":"Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"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":0.93,"id":"s1","own":true,"role":"contribution","text":"We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.07,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.93,"interpretation":0.0}},{"i":2,"p":0.5,"id":"s2","own":true,"role":"method","text":"The learned latent world dynamics capture physically grounded visual transitions, naturally encoding future possibilities and providing a unified substrate for cross-modal alignment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.81,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.5,"result":0.06,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.12,"interpretation":0.32}},{"i":3,"p":0.64,"id":"s3","own":true,"role":"method","text":"This formulation enables predictive reasoning akin to world modelling while remaining lightweight and focused on physical dynamics relevant to control.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.5,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.64,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.24,"interpretation":0.12}},{"i":4,"p":0.35,"id":"s4","own":false,"role":"contribution","text":"Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space.","hedge":{"p":0.87,"label":"asserted"},"own_p":0.31,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.03,"method":0.32,"result":0.01,"background":0.13,"limitation":0.0,"future_work":0.0,"contribution":0.35,"interpretation":0.16}},{"i":5,"p":0.69,"id":"s5","own":true,"role":"gap","text":"We observe that standard reconstruction-based action tokenization objectives induce representations biased toward low-level signal fidelity, leading to misalignment between reconstruction quality and downstream control performance.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.83,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.19,"role_probabilities":{"gap":0.69,"method":0.0,"result":0.18,"background":0.07,"limitation":0.05,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":6,"p":0.92,"id":"s6","own":true,"role":"method","text":"To address this limitation, we propose a multi-stage modality pre-alignment strategy in which action representations are progressively aligned with latent world dynamics, vision, and language.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.83,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.92,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.08,"interpretation":0.0}},{"i":7,"p":0.83,"id":"s7","own":true,"role":"method","text":"This process enforces cross-modal consistency, promotes abstraction, and induces a structured latent space for predictive reasoning.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.72,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.83,"result":0.02,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.07,"interpretation":0.08}},{"i":8,"p":0.91,"id":"s8","own":true,"role":"contribution","text":"We provide a systematic empirical study of latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization.","hedge":{"p":0.79,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.09,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.91,"interpretation":0.0}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines, with gains on challenging real-world tasks requiring temporal reasoning, physical understanding, or high control complexity, including long-horizon and dexterous manipulation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.27,"quantitative":true,"quantitative_p":0.9,"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":10,"p":1.0,"id":"s10","own":false,"role":"interpretation","text":"These findings suggest that structured multimodal alignment and predictive reasoning are fundamental principles for advancing embodied intelligence.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.48,"main_claim_p":0.84,"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":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":0.95,"text":"These findings suggest that structured multimodal alignment and predictive reasoning are fundamental principles for advancing embodied intelligence.","location":"abstract s10","hedge_strength":{"p":1.0,"label":"hedged possibility"}},"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":8210,"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":0.05,"states_limitation":0.4,"human_participants":0.05,"controlled_comparison":0.91,"randomized_assignment":0.01,"states_quantitative_result":0.06,"compares_with_prior_results":0.97,"mentions_code_or_data_availability":0.03},"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":0.91,"text":"We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.","location":"abstract s1"}},"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"}}}