{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YCVQO2E4A5HRLCRDIFQXLC7OXE","short_pith_number":"pith:YCVQO2E4","schema_version":"1.0","canonical_sha256":"c0ab07689c074f158a234161758beeb926087d8b078a7fb39173562158f36dbd","source":{"kind":"arxiv","id":"2312.14457","version":6},"attestation_state":"computed","paper":{"title":"QUAR-VLA: Vision-Language-Action Model for Quadruped Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Min Zhang, Ningxi Yang, Pengxiang Ding, Siteng Huang, Wenjie Zhang, Wenxuan Song","submitted_at":"2023-12-22T06:15:03Z","abstract_excerpt":"The important manifestation of robot intelligence is the ability to naturally interact and autonomously make decisions. Traditional approaches to robot control often compartmentalize perception, planning, and decision-making, simplifying system design but limiting the synergy between different information streams. This compartmentalization poses challenges in achieving seamless autonomous reasoning, decision-making, and action execution. To address these limitations, a novel paradigm, named Vision-Language-Action tasks for QUAdruped Robots (QUAR-VLA), has been introduced in this paper. This ap"},"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":"2312.14457","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-22T06:15:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3be0b128829990134987bb6e8c59b960410b1d63dd07c74e022c72ab361797b8","abstract_canon_sha256":"0ccadd1bb701603f8cd1512c971666bfb7936017f80893b18be6dcf3d7c2b559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:01.758574Z","signature_b64":"zLac9GTOghavVa5D+njAkGqzn9nF7jZ6chK0+VvcVVS3YHOPB1TtpAvhKq7VH7+r56iA5PNasSkDWhMvmxvzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ab07689c074f158a234161758beeb926087d8b078a7fb39173562158f36dbd","last_reissued_at":"2026-07-05T10:09:01.758113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:01.758113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QUAR-VLA: Vision-Language-Action Model for Quadruped Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Min Zhang, Ningxi Yang, Pengxiang Ding, Siteng Huang, Wenjie Zhang, Wenxuan Song","submitted_at":"2023-12-22T06:15:03Z","abstract_excerpt":"The important manifestation of robot intelligence is the ability to naturally interact and autonomously make decisions. Traditional approaches to robot control often compartmentalize perception, planning, and decision-making, simplifying system design but limiting the synergy between different information streams. This compartmentalization poses challenges in achieving seamless autonomous reasoning, decision-making, and action execution. To address these limitations, a novel paradigm, named Vision-Language-Action tasks for QUAdruped Robots (QUAR-VLA), has been introduced in this paper. This ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14457","kind":"arxiv","version":6},"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/2312.14457/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":"2312.14457","created_at":"2026-07-05T10:09:01.758169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14457v6","created_at":"2026-07-05T10:09:01.758169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14457","created_at":"2026-07-05T10:09:01.758169+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCVQO2E4A5HR","created_at":"2026-07-05T10:09:01.758169+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCVQO2E4A5HRLCRD","created_at":"2026-07-05T10:09:01.758169+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCVQO2E4","created_at":"2026-07-05T10:09:01.758169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09268","citing_title":"GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE","json":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE.json","graph_json":"https://pith.science/api/pith-number/YCVQO2E4A5HRLCRDIFQXLC7OXE/graph.json","events_json":"https://pith.science/api/pith-number/YCVQO2E4A5HRLCRDIFQXLC7OXE/events.json","paper":"https://pith.science/paper/YCVQO2E4"},"agent_actions":{"view_html":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE","download_json":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE.json","view_paper":"https://pith.science/paper/YCVQO2E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14457&json=true","fetch_graph":"https://pith.science/api/pith-number/YCVQO2E4A5HRLCRDIFQXLC7OXE/graph.json","fetch_events":"https://pith.science/api/pith-number/YCVQO2E4A5HRLCRDIFQXLC7OXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE/action/storage_attestation","attest_author":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE/action/author_attestation","sign_citation":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE/action/citation_signature","submit_replication":"https://pith.science/pith/YCVQO2E4A5HRLCRDIFQXLC7OXE/action/replication_record"}},"created_at":"2026-07-05T10:09:01.758169+00:00","updated_at":"2026-07-05T10:09:01.758169+00:00"}