{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGWHYKC3DEFJWS5H646RPHWWBZ","short_pith_number":"pith:BGWHYKC3","schema_version":"1.0","canonical_sha256":"09ac7c285b190a9b4ba7f73d179ed60e771f4d2001aecac218aa4e0ccb96b976","source":{"kind":"arxiv","id":"2503.09203","version":1},"attestation_state":"computed","paper":{"title":"MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Canjun Yang, Ignacio Carlucho, Mingwei Lin, Shuguang Chu, Yutong Li, Yvan R. Petillot, Zebin Huang","submitted_at":"2025-03-12T09:47:58Z","abstract_excerpt":"This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250,000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles (UUVs), multiple propulsion systems, and a set of predefined t"},"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":"2503.09203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-12T09:47:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"822598e850973d5dcf76c3125a56cdf4c59fe6b87dd851106c8699550d2383ca","abstract_canon_sha256":"d5e8f00cdec05c352de4d4abc5064b89563aff4e075201b1c4b238b7d1a89c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:51.429354Z","signature_b64":"wEAvEq3tW4VB4VlgC437kp5ELVlsK7Wb+EUfo8RaihZb/NkAIxTgfsGR3VRSdXlxerR5G0ckX8o+rEubhKIDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ac7c285b190a9b4ba7f73d179ed60e771f4d2001aecac218aa4e0ccb96b976","last_reissued_at":"2026-07-05T10:29:51.428835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:51.428835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Canjun Yang, Ignacio Carlucho, Mingwei Lin, Shuguang Chu, Yutong Li, Yvan R. Petillot, Zebin Huang","submitted_at":"2025-03-12T09:47:58Z","abstract_excerpt":"This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250,000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles (UUVs), multiple propulsion systems, and a set of predefined t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09203","kind":"arxiv","version":1},"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/2503.09203/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":"2503.09203","created_at":"2026-07-05T10:29:51.428902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09203v1","created_at":"2026-07-05T10:29:51.428902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09203","created_at":"2026-07-05T10:29:51.428902+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGWHYKC3DEFJ","created_at":"2026-07-05T10:29:51.428902+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGWHYKC3DEFJWS5H","created_at":"2026-07-05T10:29:51.428902+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGWHYKC3","created_at":"2026-07-05T10:29:51.428902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08598","citing_title":"Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ","json":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ.json","graph_json":"https://pith.science/api/pith-number/BGWHYKC3DEFJWS5H646RPHWWBZ/graph.json","events_json":"https://pith.science/api/pith-number/BGWHYKC3DEFJWS5H646RPHWWBZ/events.json","paper":"https://pith.science/paper/BGWHYKC3"},"agent_actions":{"view_html":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ","download_json":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ.json","view_paper":"https://pith.science/paper/BGWHYKC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09203&json=true","fetch_graph":"https://pith.science/api/pith-number/BGWHYKC3DEFJWS5H646RPHWWBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BGWHYKC3DEFJWS5H646RPHWWBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ/action/storage_attestation","attest_author":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ/action/author_attestation","sign_citation":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ/action/citation_signature","submit_replication":"https://pith.science/pith/BGWHYKC3DEFJWS5H646RPHWWBZ/action/replication_record"}},"created_at":"2026-07-05T10:29:51.428902+00:00","updated_at":"2026-07-05T10:29:51.428902+00:00"}