{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FU5ZF6UDJGSMJAD6FCNO4EGW7C","short_pith_number":"pith:FU5ZF6UD","canonical_record":{"source":{"id":"2412.04453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f08bdd47958755ab5ae5006f28e0301391b35c6dddc6633a3ebc66a22c23b5c9","abstract_canon_sha256":"d2ae6a848dd8698001749dd085901d8d05b5f937084dad3434d976cdf75a7f05"},"schema_version":"1.0"},"canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","source":{"kind":"arxiv","id":"2412.04453","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04453","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04453v2","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04453","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"FU5ZF6UDJGSM","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"FU5ZF6UDJGSMJAD6","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"FU5ZF6UD","created_at":"2026-07-05T10:15:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FU5ZF6UDJGSMJAD6FCNO4EGW7C","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f08bdd47958755ab5ae5006f28e0301391b35c6dddc6633a3ebc66a22c23b5c9","abstract_canon_sha256":"d2ae6a848dd8698001749dd085901d8d05b5f937084dad3434d976cdf75a7f05"},"schema_version":"1.0"},"canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:23.554060Z","signature_b64":"5ViAIY6VK6NdJ5bR3G7XTm8CJNcAaP+0vltmnItsFZVFz9RTJ1aMb3kcGFZDSuN/456/UJNF9oiNWdGgfcqfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","last_reissued_at":"2026-07-05T10:15:23.553445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:23.553445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04453","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjvVJBrzE0wpM3cblH5DTYiQXBkkHBiFvy1odxSa17bMX8FIDMj1njCbLgRBG6S1CuBHQXZex2ITA0McjIq3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:46:59.950866Z"},"content_sha256":"c8e47a779ad14f0e0262763ff94b78ff0bbf625b13ff16348dd630a06cb45834","schema_version":"1.0","event_id":"sha256:c8e47a779ad14f0e0262763ff94b78ff0bbf625b13ff16348dd630a06cb45834"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FU5ZF6UDJGSMJAD6FCNO4EGW7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"An-Chieh Cheng, Erdem B{\\i}y{\\i}k, Hongxu Yin, Jan Kautz, Sifei Liu, Xiaolong Wang, Xueyan Zou, Yandong Ji, Zaitian Gongye, Zhaojing Yang","submitted_at":"2024-12-05T18:58:17Z","abstract_excerpt":"This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes. However, it is non-trivial to translate human language instructions all the way to low-level leg joint actions. We propose NaVILA, a 2-level framework that unifies a Vision-Language-Action model (VLA) with locomotion skills. Instead of directly predicting low-level actions from VLA, NaVILA first generates mid-level actions with spatial information in the fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04453","kind":"arxiv","version":2},"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/2412.04453/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcRVWvWa+KLSFbRITPPoGIVzi876+Ang1URzYxH4H/vXedy12cVfLYpoPH6H2q1YOJe8zeCGHMlERxjZicJjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:46:59.951299Z"},"content_sha256":"097e348ae70deb3d5d6270481763afe62f2b050948035d1102d42e7c9a5ba660","schema_version":"1.0","event_id":"sha256:097e348ae70deb3d5d6270481763afe62f2b050948035d1102d42e7c9a5ba660"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/bundle.json","state_url":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T02:46:59Z","links":{"resolver":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C","bundle":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/bundle.json","state":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FU5ZF6UDJGSMJAD6FCNO4EGW7C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d2ae6a848dd8698001749dd085901d8d05b5f937084dad3434d976cdf75a7f05","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","title_canon_sha256":"f08bdd47958755ab5ae5006f28e0301391b35c6dddc6633a3ebc66a22c23b5c9"},"schema_version":"1.0","source":{"id":"2412.04453","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04453","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04453v2","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04453","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"FU5ZF6UDJGSM","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"FU5ZF6UDJGSMJAD6","created_at":"2026-07-05T10:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"FU5ZF6UD","created_at":"2026-07-05T10:15:23Z"}],"graph_snapshots":[{"event_id":"sha256:097e348ae70deb3d5d6270481763afe62f2b050948035d1102d42e7c9a5ba660","target":"graph","created_at":"2026-07-05T10:15:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.04453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes. However, it is non-trivial to translate human language instructions all the way to low-level leg joint actions. We propose NaVILA, a 2-level framework that unifies a Vision-Language-Action model (VLA) with locomotion skills. Instead of directly predicting low-level actions from VLA, NaVILA first generates mid-level actions with spatial information in the fo","authors_text":"An-Chieh Cheng, Erdem B{\\i}y{\\i}k, Hongxu Yin, Jan Kautz, Sifei Liu, Xiaolong Wang, Xueyan Zou, Yandong Ji, Zaitian Gongye, Zhaojing Yang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04453","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8e47a779ad14f0e0262763ff94b78ff0bbf625b13ff16348dd630a06cb45834","target":"record","created_at":"2026-07-05T10:15:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d2ae6a848dd8698001749dd085901d8d05b5f937084dad3434d976cdf75a7f05","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","title_canon_sha256":"f08bdd47958755ab5ae5006f28e0301391b35c6dddc6633a3ebc66a22c23b5c9"},"schema_version":"1.0","source":{"id":"2412.04453","kind":"arxiv","version":2}},"canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","first_computed_at":"2026-07-05T10:15:23.553445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:23.553445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ViAIY6VK6NdJ5bR3G7XTm8CJNcAaP+0vltmnItsFZVFz9RTJ1aMb3kcGFZDSuN/456/UJNF9oiNWdGgfcqfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:23.554060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04453","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8e47a779ad14f0e0262763ff94b78ff0bbf625b13ff16348dd630a06cb45834","sha256:097e348ae70deb3d5d6270481763afe62f2b050948035d1102d42e7c9a5ba660"],"state_sha256":"590f9aa9a518d4bb97873eb462356ad99de6982ee8a2833f9784e4426f8da264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0ByFcawM8n576rRSOfOQNjafdyOFdvdjfyaj0SapA7TKLmPsxQe3iXR8Q1OUd+wAHtyCMwz7/TP9kL+zq3jDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:46:59.955000Z","bundle_sha256":"01fe7829c9697d7091b6822b167a066dd10cf9cef8197426be88fb1941a514fb"}}