{"paper":{"title":"Gnomon4D: Learning Where and When to Focus for Geometric Motion-Grounded World-Action Modeling","arxiv_id":"2611.02474","primary_cat":"cs.CV","submitted_at":"2026-11-02T03:45:07+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) use video-generation priors to jointly predict future observations and robot actions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"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":0.73,"id":"s1","own":false,"role":"gap","text":"Yet RGB futures entangle physical state changes with appearance, while frame-wise depth and point maps lack temporal correspondence.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.1,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.73,"method":0.0,"result":0.0,"background":0.27,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.82,"id":"s2","own":false,"role":"gap","text":"Existing 4D approaches either keep motion implicit in visual features or translate predicted traces into actions through a separate interface.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.82,"method":0.0,"result":0.0,"background":0.18,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.96,"id":"s3","own":true,"role":"contribution","text":"We present Gnomon4D, a WAM that jointly generates future video, robot actions, and GeoDelta, a video-aligned 4D geometric motion field encoding the cross-frame image-plane displacement and depth change of embodiment and object points.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.14,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.96,"interpretation":0.0}},{"i":4,"p":0.83,"id":"s4","own":true,"role":"method","text":"By placing embodiment motion and object responses in a shared space, GeoDelta exposes their motion relations to the action expert at inference.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.81,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.83,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.08,"interpretation":0.09}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"method","text":"Interaction-Salient Attention (InSAttn) uses these relations to focus spatial readout on task-relevant interaction regions, while Transition-Anchored Aggregation (TransAgg) aggregates evidence around changes in their relative motion, such as grasp and release.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"method","text":"GeoDelta describes surface motion independently of embodiment-specific controls, providing a shared human--robot quasi-action for action-free pretraining on EgoManip-5000H followed by robot mid-training on Robot-30H.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.66,"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":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"Gnomon4D leads on RoboTwin~2.0, VLABench, and RoboDojo, and outperforms the strongest real-robot baseline by 7.0 and 16.0 percentage points under in-distribution and out-of-distribution settings, respectively.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.78,"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}}]},"compiled":{"main_claim":{"p":1.0,"text":"Gnomon4D leads on RoboTwin~2.0, VLABench, and RoboDojo, and outperforms the strongest real-robot baseline by 7.0 and 16.0 percentage points under in-distribution and out-of-distribution settings, respectively.","location":"abstract s7","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":6470,"cost_usd_reported":0.0},"compiled_at":"2026-11-03","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.11,"states_limitation":0.1,"human_participants":0.11,"controlled_comparison":0.94,"randomized_assignment":0.01,"states_quantitative_result":0.99,"compares_with_prior_results":0.97,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.87,"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":0.87,"simulation_or_computation":0.13}},"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":1.0,"text":"We present Gnomon4D, a WAM that jointly generates future video, robot actions, and GeoDelta, a video-aligned 4D geometric motion field encoding the cross-frame image-plane displacement and depth change of embodiment and object points.","location":"abstract s3"}},"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":8,"sentences_in_abstract":8},"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"}}}