{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A6OQBC7NJPZOTMFTGSPIKXR6Q4","short_pith_number":"pith:A6OQBC7N","schema_version":"1.0","canonical_sha256":"079d008bed4bf2e9b0b3349e855e3e8714b3533c49e035770b5a4046ac816447","source":{"kind":"arxiv","id":"2503.08007","version":1},"attestation_state":"computed","paper":{"title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Pengxiang Ding, Wenxuan Song, Xinyang Tong, Xuelian Cheng, Zongyuan Ge","submitted_at":"2025-03-11T03:13:45Z","abstract_excerpt":"Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic experts (MoRE), for quadruped robots that aim to introduce reinforcement learning (RL) for fine-tuning large-scale VLA models with a large amount of mixed-quality data. MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model (MLLM), forming a sparse-activated mixture-of-experts model. This design en"},"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":"2503.08007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-11T03:13:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf4d876a39058d4cd9e16b60f8eb661e7dde6a5d8090599b4cadfbcc59f1e3b9","abstract_canon_sha256":"683509dc521b5dfd8304e24542c3c189011249eecb81e36ef2f3d8a9e1e6fca4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:48.690690Z","signature_b64":"4fwVvrBYKs3oQHimNF1OuEaFYuVjSO9lN/xW3zdUuFZvG5Plz5ibDsa5DlyBq/DDDQW+KMYI/0tdQ1es460SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079d008bed4bf2e9b0b3349e855e3e8714b3533c49e035770b5a4046ac816447","last_reissued_at":"2026-07-05T10:28:48.690112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:48.690112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Pengxiang Ding, Wenxuan Song, Xinyang Tong, Xuelian Cheng, Zongyuan Ge","submitted_at":"2025-03-11T03:13:45Z","abstract_excerpt":"Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic experts (MoRE), for quadruped robots that aim to introduce reinforcement learning (RL) for fine-tuning large-scale VLA models with a large amount of mixed-quality data. MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model (MLLM), forming a sparse-activated mixture-of-experts model. This design en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08007","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/2503.08007/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":"2503.08007","created_at":"2026-07-05T10:28:48.690176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08007v1","created_at":"2026-07-05T10:28:48.690176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08007","created_at":"2026-07-05T10:28:48.690176+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6OQBC7NJPZO","created_at":"2026-07-05T10:28:48.690176+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6OQBC7NJPZOTMFT","created_at":"2026-07-05T10:28:48.690176+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6OQBC7N","created_at":"2026-07-05T10:28:48.690176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.18085","citing_title":"Continually Evolving Skill Knowledge in Vision Language Action Model","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4","json":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4.json","graph_json":"https://pith.science/api/pith-number/A6OQBC7NJPZOTMFTGSPIKXR6Q4/graph.json","events_json":"https://pith.science/api/pith-number/A6OQBC7NJPZOTMFTGSPIKXR6Q4/events.json","paper":"https://pith.science/paper/A6OQBC7N"},"agent_actions":{"view_html":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4","download_json":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4.json","view_paper":"https://pith.science/paper/A6OQBC7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08007&json=true","fetch_graph":"https://pith.science/api/pith-number/A6OQBC7NJPZOTMFTGSPIKXR6Q4/graph.json","fetch_events":"https://pith.science/api/pith-number/A6OQBC7NJPZOTMFTGSPIKXR6Q4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4/action/storage_attestation","attest_author":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4/action/author_attestation","sign_citation":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4/action/citation_signature","submit_replication":"https://pith.science/pith/A6OQBC7NJPZOTMFTGSPIKXR6Q4/action/replication_record"}},"created_at":"2026-07-05T10:28:48.690176+00:00","updated_at":"2026-07-05T10:28:48.690176+00:00"}