{"paper":{"title":"AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies","arxiv_id":"2608.29937","primary_cat":"cs.AI","submitted_at":"2026-08-30T18:09:17+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":"Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"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":0.62,"id":"s1","own":false,"role":"gap","text":"LaWAM established this formulation, but its original presentation left the world model, multimodal backbone, and deployment checkpoint tightly coupled.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.62,"method":0.0,"result":0.0,"background":0.38,"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 AcrossWAM1.0, a modularization and scaling study of this latent world-action stack.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.85,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.04,"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":0.87,"id":"s3","own":true,"role":"method","text":"Rather than presenting latent subgoals as a new algorithm, we make the module boundary explicit: a policy adapter produces latent-action and action-generation contexts; a retained latent world decoder grounds the predicted transition in the current scene;and a flow-matching expert generates continuous action chunks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.87,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.13,"interpretation":0.0}},{"i":4,"p":0.56,"id":"s4","own":true,"role":"contribution","text":"We further separate training-only teachers from the inference graph and provide a verifiable deployment export.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.06,"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":1.0,"id":"s5","own":true,"role":"result","text":"On 2,000 paired LIBERO episodes, replacing a Qwen3-VL-2B backbone with Qwen3.5-0.8B yields 97.45% success versus 98.00% for the 2B model (a-0.55percentage-point difference; exact McNemarp=0.266).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.11,"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":0.78,"id":"s6","own":true,"role":"interpretation","text":"This does not prove equivalence, but it meets a prespecified two-point retention criterion.","hedge":{"p":0.77,"label":"asserted"},"own_p":0.82,"main_claim_p":0.07,"quantitative":true,"quantitative_p":0.85,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.01,"background":0.0,"limitation":0.21,"future_work":0.0,"contribution":0.0,"interpretation":0.78}},{"i":7,"p":0.98,"id":"s7","own":true,"role":"result","text":"The compact, inference-reachable checkpoint contains 1,472.6M unique parameters, 42.4% fewer than the original 2B policy, while all retained tensors are bitwise identical to the source checkpoint.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":8,"p":0.84,"id":"s8","own":true,"role":"limitation","text":"Cross-family execution is additionally checked with a MiniCPM-V adapter smoke test; closed-loop cross-family transfer remains an open evaluation.","hedge":{"p":0.92,"label":"asserted"},"own_p":0.89,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.03,"background":0.0,"limitation":0.84,"future_work":0.1,"contribution":0.02,"interpretation":0.0}},{"i":9,"p":0.99,"id":"s9","own":true,"role":"contribution","text":"AcrossWAM1.0 therefore contributes an auditable software and evaluation boundary for compact latent world-action policies, distinct from LaWAM's original latent-subgoal contribution.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.79,"main_claim_p":0.82,"quantitative":false,"quantitative_p":0.24,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.99,"interpretation":0.01}}]},"compiled":{"main_claim":{"p":1.0,"text":"AcrossWAM1.0 therefore contributes an auditable software and evaluation boundary for compact latent world-action policies, distinct from LaWAM's original latent-subgoal contribution.","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":7751,"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":0.06,"states_limitation":0.96,"human_participants":0.06,"controlled_comparison":0.84,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.93,"mentions_code_or_data_availability":0.16},"evidential_basis":{"p":0.88,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.03,"observation_or_experiment":0.88,"simulation_or_computation":0.09}},"contribution_type":{"p":0.98,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.98,"empirical_study":0.02,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.75,"text":"We introduce AcrossWAM1.0, a modularization and scaling study of this latent world-action stack.","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":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"}}}