{"paper":{"title":"Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation","arxiv_id":"2610.38199","primary_cat":"cs.RO","submitted_at":"2026-10-28T02:49:53+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":"Behavior Cloning has demonstrated promising generalization capabilities for robotic manipulation in terrestrial environments.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.04,"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":0.8,"id":"s1","own":false,"role":"gap","text":"However, marine visual distortions and dynamic currents create a severe domain shift that remains a key bottleneck in adapting generalist architectures to underwater field manipulation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.11,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.8,"method":0.0,"result":0.0,"background":0.2,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.97,"id":"s2","own":true,"role":"method","text":"To address this, 1616 episodes of underwater manipulation data were collected in calm and turbulent waters and were used to train 14 generalist Vision-Language-Action (VLA) models (DynamicVLA) with varying proprioception observation configurations.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.96,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.98,"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":3,"p":1.0,"id":"s3","own":true,"role":"result","text":"Across three tasks on 1260 gradable on-hardware rollouts in a pool, 10 models outperformed the baseline, with the highest-performing model achieving a 93.3% overall success rate, including partial successes.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.32,"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":4,"p":0.66,"id":"s4","own":true,"role":"contribution","text":"Results are also introduced from a case study evaluating the performance of a single-task Action Chunking Transformer (ACT) and a generalist VLA (SmolVLA) policy for two tasks in marine archaeology and conservation: grasping and mooring.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.94,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.52,"role_probabilities":{"gap":0.0,"method":0.29,"result":0.05,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.66,"interpretation":0.0}},{"i":5,"p":0.95,"id":"s5","own":true,"role":"method","text":"Experiments are performed on an ROV on and around the WWII wreck Coralita X127 and at Manoel Island Marina, Malta.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.92,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.3,"role_probabilities":{"gap":0.0,"method":0.95,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Across 748 collected episodes and 508 gradable on-hardware rollouts, the ACT policy substantially outperformed SmolVLA (47.9% vs. 7.9% pooled success rate), earning a 66.7% success rate on the most successful task at the marine archaeological site.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.17,"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":7,"p":0.86,"id":"s7","own":true,"role":"contribution","text":"To enable further contributions to embodied intelligence in marine field robotics, the BLUEMBODIED KIT used to collect data, train models, and deploy policies on the ROV has been open sourced.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.13,"contribution":0.86,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.73,"text":"Across three tasks on 1260 gradable on-hardware rollouts in a pool, 10 models outperformed the baseline, with the highest-performing model achieving a 93.3% overall success rate, including partial successes.","location":"abstract s3","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":6615,"cost_usd_reported":0.0},"compiled_at":"2026-10-30","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.45,"human_participants":0.06,"controlled_comparison":0.94,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.97,"mentions_code_or_data_availability":0.94},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.74,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.21,"empirical_study":0.74,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.05,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"To address this, 1616 episodes of underwater manipulation data were collected in calm and turbulent waters and were used to train 14 generalist Vision-Language-Action (VLA) models (DynamicVLA) with varying proprioception observation configurations.","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":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"}}}