{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LLTACTSWTRF7P3W7CGDOWAXOOT","short_pith_number":"pith:LLTACTSW","schema_version":"1.0","canonical_sha256":"5ae6014e569c4bf7eedf1186eb02ee74d189634c1b139092e7e364a999fd1a12","source":{"kind":"arxiv","id":"2510.07869","version":4},"attestation_state":"computed","paper":{"title":"USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jian Wang, Junwen Gu, Laien Luo, Lianyi Yu, Luoyang Sun, Pengxuan Si, Shuang Qiu, Yukai Feng, Zhengxing Wu, Zhentao Zhang, Zhiheng Wu","submitted_at":"2025-10-09T07:19:29Z","abstract_excerpt":"Underwater environments pose unique challenges for robotic navigation and manipulation. While existing research has primarily focused on task-specific methods, studies on general-purpose intelligence for multi-task execution remain scarce. To address this gap, we propose a unified framework for general-purpose underwater robots that integrates perception and action driven by language instructions. First, we develop a data synthesis pipeline to construct USIM, a simulation-based dataset which comprises over 905K frames from 2275 trajectories, totaling approximately 25 hours of BlueROV2 interact"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.07869","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-09T07:19:29Z","cross_cats_sorted":[],"title_canon_sha256":"4e3916af98545fdbeafde4159c573941e3885e9ea38ac37f48b0c6be0dfebbd5","abstract_canon_sha256":"c5f64d1189916a04ff8d40dc25a05dcbe3d3f5385eed8498b78f707053d3d81d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:09.313138Z","signature_b64":"z1r4tAbcVdekwVoJ96ULtMQi5CZs2otEHJpAcA0ZuOwA/oUtRniHvCbBVDrD2VIzuIhKTMVqStnDFW/mLsGHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae6014e569c4bf7eedf1186eb02ee74d189634c1b139092e7e364a999fd1a12","last_reissued_at":"2026-05-25T02:02:09.312151Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:09.312151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jian Wang, Junwen Gu, Laien Luo, Lianyi Yu, Luoyang Sun, Pengxuan Si, Shuang Qiu, Yukai Feng, Zhengxing Wu, Zhentao Zhang, Zhiheng Wu","submitted_at":"2025-10-09T07:19:29Z","abstract_excerpt":"Underwater environments pose unique challenges for robotic navigation and manipulation. While existing research has primarily focused on task-specific methods, studies on general-purpose intelligence for multi-task execution remain scarce. To address this gap, we propose a unified framework for general-purpose underwater robots that integrates perception and action driven by language instructions. First, we develop a data synthesis pipeline to construct USIM, a simulation-based dataset which comprises over 905K frames from 2275 trajectories, totaling approximately 25 hours of BlueROV2 interact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07869","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.07869/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.07869","created_at":"2026-05-25T02:02:09.312281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.07869v4","created_at":"2026-05-25T02:02:09.312281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07869","created_at":"2026-05-25T02:02:09.312281+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLTACTSWTRF7","created_at":"2026-05-25T02:02:09.312281+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLTACTSWTRF7P3W7","created_at":"2026-05-25T02:02:09.312281+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLTACTSW","created_at":"2026-05-25T02:02:09.312281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT","json":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT.json","graph_json":"https://pith.science/api/pith-number/LLTACTSWTRF7P3W7CGDOWAXOOT/graph.json","events_json":"https://pith.science/api/pith-number/LLTACTSWTRF7P3W7CGDOWAXOOT/events.json","paper":"https://pith.science/paper/LLTACTSW"},"agent_actions":{"view_html":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT","download_json":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT.json","view_paper":"https://pith.science/paper/LLTACTSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.07869&json=true","fetch_graph":"https://pith.science/api/pith-number/LLTACTSWTRF7P3W7CGDOWAXOOT/graph.json","fetch_events":"https://pith.science/api/pith-number/LLTACTSWTRF7P3W7CGDOWAXOOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT/action/storage_attestation","attest_author":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT/action/author_attestation","sign_citation":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT/action/citation_signature","submit_replication":"https://pith.science/pith/LLTACTSWTRF7P3W7CGDOWAXOOT/action/replication_record"}},"created_at":"2026-05-25T02:02:09.312281+00:00","updated_at":"2026-05-25T02:02:09.312281+00:00"}