{"paper":{"title":"Beyond Prediction Gain: LASR as a Metric for Action-Grounded Latents in World Models","arxiv_id":"2611.17775","primary_cat":"cs.RO","submitted_at":"2026-11-13T05:35:37+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 models that support planning, control, and interpretable reasoning require latent representations that genuinely encode action.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.06,"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":0.74,"id":"s1","own":false,"role":"background","text":"Yet the large-scale video data from which such models are learned overwhelmingly lack action annotations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.26,"method":0.0,"result":0.0,"background":0.74,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":false,"role":"background","text":"Latent-action models infer action-like variables from observation sequences, enabling action-aware learning from unlabeled videos or trajectories.","hedge":{"p":0.99,"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":3,"p":0.74,"id":"s3","own":false,"role":"gap","text":"A fundamental concern, however, remains: a latent that improves future prediction may simply encode the current state, episode progress, task identity, or other predictive shortcuts.","hedge":{"p":0.93,"label":"hedged_possibility"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.74,"method":0.0,"result":0.0,"background":0.26,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.95,"id":"s4","own":false,"role":"gap","text":"Existing evaluation practices---reconstruction loss, rollout fidelity, action recovery, or downstream performance---cannot isolate this distinction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.11,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.95,"method":0.0,"result":0.0,"background":0.05,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":0.95,"id":"s5","own":true,"role":"contribution","text":"We introduce the Latent Action Support Ratio (LASR), a dimensionless metric that measures, under offline evaluation on held-out data, whether a learned latent provides predictive support for action-related targets beyond the current state and non-action alternatives.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.3,"quantitative":false,"quantitative_p":0.17,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":6,"p":0.76,"id":"s6","own":true,"role":"method","text":"LASR provides two complementary summaries: GeoLASR captures typical support, while WorstLASR identifies the weakest case.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.27,"role_probabilities":{"gap":0.0,"method":0.76,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.24,"interpretation":0.0}},{"i":7,"p":0.98,"id":"s7","own":true,"role":"method","text":"We instantiate the LASR benchmark with recorded actions and corresponding physical state changes as targets, episode-held-out splits, one predictor type for all comparisons, and positive and negative controls.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.95,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.18,"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":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Experiments on recorded robot manipulation data and a matched multi-task panel demonstrate that LASR detects known action information, rejects representative non-action shortcuts, and enables graded comparisons among imperfect latent representations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.34,"quantitative":false,"quantitative_p":0.36,"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":9,"p":0.63,"id":"s9","own":true,"role":"result","text":"We further use LASR to train and audit a lightweight residual adapter, obtaining descriptively better point estimates whose uncertainty is assessed with paired comparisons.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.96,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.38,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.63,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.32,"interpretation":0.0}},{"i":10,"p":0.58,"id":"s10","own":true,"role":"interpretation","text":"LASR thus provides a principled offline protocol for measuring action-related predictive support in world-model latents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.81,"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":0.42,"interpretation":0.58}}]},"compiled":{"main_claim":{"p":0.83,"text":"LASR thus provides a principled offline protocol for measuring action-related predictive support in world-model latents.","location":"abstract s10","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":8209,"cost_usd_reported":0.0},"compiled_at":"2026-11-16","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.1,"states_limitation":0.33,"human_participants":0.05,"controlled_comparison":0.96,"randomized_assignment":0.02,"states_quantitative_result":0.07,"compares_with_prior_results":0.8,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.92,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.06,"observation_or_experiment":0.92,"simulation_or_computation":0.02}},"contribution_type":{"p":0.99,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.99,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.01,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We introduce the Latent Action Support Ratio (LASR), a dimensionless metric that measures, under offline evaluation on held-out data, whether a learned latent provides predictive support for action-related targets beyond the current state and non-action alternatives.","location":"abstract s5"}},"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"}}}