{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4VEGZFNTOR2UMZCWP5XPK6BUVQ","short_pith_number":"pith:4VEGZFNT","canonical_record":{"source":{"id":"2604.21363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"5f32a143e15598b52a5ca30d548fbcd0014db9680435f45fe14b6b3ab2f1e744","abstract_canon_sha256":"3a1198714a4b77e49e8a36c00772ee2a025dd1bff69581e2af3cd4f82da41369"},"schema_version":"1.0"},"canonical_sha256":"e5486c95b374754664567f6ef57834ac0ffa1198553b2870800eb355074947ca","source":{"kind":"arxiv","id":"2604.21363","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.21363","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2604.21363v2","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21363","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"4VEGZFNTOR2U","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"4VEGZFNTOR2UMZCW","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"4VEGZFNT","created_at":"2026-05-20T00:03:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4VEGZFNTOR2UMZCWP5XPK6BUVQ","target":"record","payload":{"canonical_record":{"source":{"id":"2604.21363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"5f32a143e15598b52a5ca30d548fbcd0014db9680435f45fe14b6b3ab2f1e744","abstract_canon_sha256":"3a1198714a4b77e49e8a36c00772ee2a025dd1bff69581e2af3cd4f82da41369"},"schema_version":"1.0"},"canonical_sha256":"e5486c95b374754664567f6ef57834ac0ffa1198553b2870800eb355074947ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:12.290487Z","signature_b64":"Jqd/cq+ug0R4Caa4+bvg9KOWDF05nBfDeeCpJ2AJWc5GqtJJLSljpiFCaynpLZNDgwwqgYt7gfiN4qLQE/UfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5486c95b374754664567f6ef57834ac0ffa1198553b2870800eb355074947ca","last_reissued_at":"2026-05-20T00:03:12.289492Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:12.289492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.21363","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":"2026-05-20T00:03:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDFo2YYrTEWKOZ2S7WLhm9MP1PUslDumP7O7J0KdY95tTQmkRTpS+OIB7OzHqErMbIJGFP/s61m40D9AePaxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:44:59.852544Z"},"content_sha256":"55d1a78638b35fa877b317c26ce72f5a018677e57f4ebdc5beae43b9ef9b36fb","schema_version":"1.0","event_id":"sha256:55d1a78638b35fa877b317c26ce72f5a018677e57f4ebdc5beae43b9ef9b36fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4VEGZFNTOR2UMZCWP5XPK6BUVQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chen Wang, Denan Liang, Kuan Xu, Lihua Xie, Ruimeng Liu, Shenghai Yuan, Tongxing Jin, Yizhuo Yang","submitted_at":"2026-04-23T07:27:00Z","abstract_excerpt":"Bridging the gap between embodied intelligence and embedded deployment remains a key challenge in intelligent robotic systems, where perception, reasoning, and planning must operate under strict constraints on computation, memory, energy, and real-time execution. In vision-and-language navigation (VLN), existing approaches often face a trade-off between reasoning capability and deployment efficiency on real-world platforms. In this paper, we present a deployable embodied VLN system that achieves both high efficiency and strong high-level reasoning on real-world robots. The system is decomposed"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments in both simulation and real-world robotic platforms demonstrate improved navigation success and efficiency over existing VLN approaches, while maintaining real-time performance on resource-constrained hardware.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Decoupling the system into asynchronous modules and decomposing the cognitive memory graph into subgraphs for VLM reasoning will preserve necessary information and avoid latency that harms performance in changing real-world environments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A modular VLN architecture builds a cognitive memory graph, decomposes it for VLM reasoning, and solves a weighted traveling repairman problem for context-aware exploration to achieve real-time performance and higher success on embedded hardware.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ce199f84a74a9bc3577c8e6fd78f32004ef45947805319b353887bc9775bc5a0"},"source":{"id":"2604.21363","kind":"arxiv","version":2},"verdict":{"id":"089e1121-538f-4678-b6d7-693f76a2d63a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T22:06:31.798863Z","strongest_claim":"Extensive experiments in both simulation and real-world robotic platforms demonstrate improved navigation success and efficiency over existing VLN approaches, while maintaining real-time performance on resource-constrained hardware.","one_line_summary":"A modular VLN architecture builds a cognitive memory graph, decomposes it for VLM reasoning, and solves a weighted traveling repairman problem for context-aware exploration to achieve real-time performance and higher success on embedded hardware.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Decoupling the system into asynchronous modules and decomposing the cognitive memory graph into subgraphs for VLM reasoning will preserve necessary information and avoid latency that harms performance in changing real-world environments.","pith_extraction_headline":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.21363/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":"089e1121-538f-4678-b6d7-693f76a2d63a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XLfgGE7bqqExtTg31HO3yY87w4dJCYiioDqoNia/mgXUCrXn8KOUM87MkBehd4hcJeXWWL6vPFQdskpnN3bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:44:59.853441Z"},"content_sha256":"560e3c7f4a04deed47e9a84b0fd1efa54ed31ca27bf3686fc81fdf08b1509ae7","schema_version":"1.0","event_id":"sha256:560e3c7f4a04deed47e9a84b0fd1efa54ed31ca27bf3686fc81fdf08b1509ae7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/bundle.json","state_url":"https://pith.science/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/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":"2026-05-26T14:44:59Z","links":{"resolver":"https://pith.science/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ","bundle":"https://pith.science/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/bundle.json","state":"https://pith.science/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VEGZFNTOR2UMZCWP5XPK6BUVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4VEGZFNTOR2UMZCWP5XPK6BUVQ","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":"3a1198714a4b77e49e8a36c00772ee2a025dd1bff69581e2af3cd4f82da41369","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:27:00Z","title_canon_sha256":"5f32a143e15598b52a5ca30d548fbcd0014db9680435f45fe14b6b3ab2f1e744"},"schema_version":"1.0","source":{"id":"2604.21363","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.21363","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2604.21363v2","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21363","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"4VEGZFNTOR2U","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"4VEGZFNTOR2UMZCW","created_at":"2026-05-20T00:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"4VEGZFNT","created_at":"2026-05-20T00:03:12Z"}],"graph_snapshots":[{"event_id":"sha256:560e3c7f4a04deed47e9a84b0fd1efa54ed31ca27bf3686fc81fdf08b1509ae7","target":"graph","created_at":"2026-05-20T00:03:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments in both simulation and real-world robotic platforms demonstrate improved navigation success and efficiency over existing VLN approaches, while maintaining real-time performance on resource-constrained hardware."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Decoupling the system into asynchronous modules and decomposing the cognitive memory graph into subgraphs for VLM reasoning will preserve necessary information and avoid latency that harms performance in changing real-world environments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A modular VLN architecture builds a cognitive memory graph, decomposes it for VLM reasoning, and solves a weighted traveling repairman problem for context-aware exploration to achieve real-time performance and higher success on embedded hardware."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots."}],"snapshot_sha256":"ce199f84a74a9bc3577c8e6fd78f32004ef45947805319b353887bc9775bc5a0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.21363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bridging the gap between embodied intelligence and embedded deployment remains a key challenge in intelligent robotic systems, where perception, reasoning, and planning must operate under strict constraints on computation, memory, energy, and real-time execution. In vision-and-language navigation (VLN), existing approaches often face a trade-off between reasoning capability and deployment efficiency on real-world platforms. In this paper, we present a deployable embodied VLN system that achieves both high efficiency and strong high-level reasoning on real-world robots. The system is decomposed","authors_text":"Chen Wang, Denan Liang, Kuan Xu, Lihua Xie, Ruimeng Liu, Shenghai Yuan, Tongxing Jin, Yizhuo Yang","cross_cats":[],"headline":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:27:00Z","title":"A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.21363","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T22:06:31.798863Z","id":"089e1121-538f-4678-b6d7-693f76a2d63a","model_set":{"reader":"grok-4.3"},"one_line_summary":"A modular VLN architecture builds a cognitive memory graph, decomposes it for VLM reasoning, and solves a weighted traveling repairman problem for context-aware exploration to achieve real-time performance and higher success on embedded hardware.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A modular vision-language navigation system separates sensing from reasoning to run efficiently on real robots.","strongest_claim":"Extensive experiments in both simulation and real-world robotic platforms demonstrate improved navigation success and efficiency over existing VLN approaches, while maintaining real-time performance on resource-constrained hardware.","weakest_assumption":"Decoupling the system into asynchronous modules and decomposing the cognitive memory graph into subgraphs for VLM reasoning will preserve necessary information and avoid latency that harms performance in changing real-world environments."}},"verdict_id":"089e1121-538f-4678-b6d7-693f76a2d63a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55d1a78638b35fa877b317c26ce72f5a018677e57f4ebdc5beae43b9ef9b36fb","target":"record","created_at":"2026-05-20T00:03:12Z","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":"3a1198714a4b77e49e8a36c00772ee2a025dd1bff69581e2af3cd4f82da41369","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:27:00Z","title_canon_sha256":"5f32a143e15598b52a5ca30d548fbcd0014db9680435f45fe14b6b3ab2f1e744"},"schema_version":"1.0","source":{"id":"2604.21363","kind":"arxiv","version":2}},"canonical_sha256":"e5486c95b374754664567f6ef57834ac0ffa1198553b2870800eb355074947ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5486c95b374754664567f6ef57834ac0ffa1198553b2870800eb355074947ca","first_computed_at":"2026-05-20T00:03:12.289492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:12.289492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jqd/cq+ug0R4Caa4+bvg9KOWDF05nBfDeeCpJ2AJWc5GqtJJLSljpiFCaynpLZNDgwwqgYt7gfiN4qLQE/UfAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:12.290487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.21363","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55d1a78638b35fa877b317c26ce72f5a018677e57f4ebdc5beae43b9ef9b36fb","sha256:560e3c7f4a04deed47e9a84b0fd1efa54ed31ca27bf3686fc81fdf08b1509ae7"],"state_sha256":"4093de798447350f6d159fda54bfbf3c2cbb8736e89ee11175ca610c04fbab3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uqUGbkHKssbf+Fa/fbDmT8SzoGlm1rZ+ajtxmJ8WO+zYRKTRm7i3vkaD+j8H25QbIhtfWWTJJ0uvo1aWKKbDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:44:59.857806Z","bundle_sha256":"9e1aec6a19768c395ca9bd6ec6c7277a1f0fbd4582768201d763f316ed2522d9"}}