{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SYPTGEY7KHAND4KL56ZOEJPGSZ","short_pith_number":"pith:SYPTGEY7","canonical_record":{"source":{"id":"2604.16993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T13:41:46Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"60c1322f248f585477ca30bb5ee6f773738350d477a800fbe0987b610c71cf83","abstract_canon_sha256":"ac9545e32c94c820bfe929af77533f790f58a9cca89a2e6260f2ead7699fda39"},"schema_version":"1.0"},"canonical_sha256":"961f33131f51c0d1f14befb2e225e696577e14fb03d8983811b195e1ec8ff322","source":{"kind":"arxiv","id":"2604.16993","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16993","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16993v2","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16993","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"SYPTGEY7KHAN","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"SYPTGEY7KHAND4KL","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"SYPTGEY7","created_at":"2026-07-02T01:17:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SYPTGEY7KHAND4KL56ZOEJPGSZ","target":"record","payload":{"canonical_record":{"source":{"id":"2604.16993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T13:41:46Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"60c1322f248f585477ca30bb5ee6f773738350d477a800fbe0987b610c71cf83","abstract_canon_sha256":"ac9545e32c94c820bfe929af77533f790f58a9cca89a2e6260f2ead7699fda39"},"schema_version":"1.0"},"canonical_sha256":"961f33131f51c0d1f14befb2e225e696577e14fb03d8983811b195e1ec8ff322","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:31.317829Z","signature_b64":"nFn3oLetaIJe83C9aEMiTHhvMck3zLbiuHyr1S0xYt75HJWjrnKJjXq6+/O+xwSnKTrDuu4Cp+FFEdI/HqIwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961f33131f51c0d1f14befb2e225e696577e14fb03d8983811b195e1ec8ff322","last_reissued_at":"2026-07-02T01:17:31.317449Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:31.317449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.16993","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":"2026-07-02T01:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqFPSzu77FgevAIkyrmKBvJkOrjPi+QPRTiv/Z2s727IypZoWCXDiCA/mzTEokT7isVUvEGdyry3YV0qz0rxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T09:31:08.365546Z"},"content_sha256":"8de307c2126bfc4d3d19a7d80b96fa8f5ae39f36f52a8e6ad60aa5efa354e782","schema_version":"1.0","event_id":"sha256:8de307c2126bfc4d3d19a7d80b96fa8f5ae39f36f52a8e6ad60aa5efa354e782"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SYPTGEY7KHAND4KL56ZOEJPGSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals.","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Jiawen Wen, Penglei Sun, Suixuan Qiu, Weisheng Xu, Wenjie Zhang, Xiaofei Yang, Xiaowen Chu","submitted_at":"2026-04-18T13:41:46Z","abstract_excerpt":"As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a \"goal-driven trap\", prioritizing physical geometry (\"can I go?\") over semantic rules (\"may I go?\"), frequently overlooking subtle regulatory constraints. To bridge this gap, we establish Rule-VLN, the first large-scale urban benchmark for rule-compliant navigation. Spanning a massive 29k-node environment, it injects 177 diverse regulatory categories into 8k constrained nodes across fo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 177 injected regulatory categories and the coarse-to-fine VLM perception in SNRM accurately capture and interpret real-world semantic and behavioral constraints in a zero-shot manner without domain-specific fine-tuning or additional supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"97874106a3b60e225dfadccf103fc5531da9af28abd310de2b1080450f3e8bc7"},"source":{"id":"2604.16993","kind":"arxiv","version":2},"verdict":{"id":"a2eeabda-b463-4617-9906-524dea7ee88d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:52:20.124678Z","strongest_claim":"Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%.","one_line_summary":"Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 177 injected regulatory categories and the coarse-to-fine VLM perception in SNRM accurately capture and interpret real-world semantic and behavioral constraints in a zero-shot manner without domain-specific fine-tuning or additional supervision.","pith_extraction_headline":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.16993/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":"a2eeabda-b463-4617-9906-524dea7ee88d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Z68Gs1F1Kx+CYqAXjA+HAvl+Itk5UI0QjugiAT8Q1Dz05CounjUYwMKbopLrzBPhsC63ZUFTNaNSlhzEh0iDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T09:31:08.366042Z"},"content_sha256":"4623f0b43bc48dd32eb7b71795b02a4bdbbf0aeebcd830d77332ab9ebee3d1ec","schema_version":"1.0","event_id":"sha256:4623f0b43bc48dd32eb7b71795b02a4bdbbf0aeebcd830d77332ab9ebee3d1ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/bundle.json","state_url":"https://pith.science/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/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":"2026-07-17T09:31:08Z","links":{"resolver":"https://pith.science/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ","bundle":"https://pith.science/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/bundle.json","state":"https://pith.science/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYPTGEY7KHAND4KL56ZOEJPGSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SYPTGEY7KHAND4KL56ZOEJPGSZ","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":"ac9545e32c94c820bfe929af77533f790f58a9cca89a2e6260f2ead7699fda39","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T13:41:46Z","title_canon_sha256":"60c1322f248f585477ca30bb5ee6f773738350d477a800fbe0987b610c71cf83"},"schema_version":"1.0","source":{"id":"2604.16993","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16993","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16993v2","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16993","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"SYPTGEY7KHAN","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"SYPTGEY7KHAND4KL","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"SYPTGEY7","created_at":"2026-07-02T01:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:4623f0b43bc48dd32eb7b71795b02a4bdbbf0aeebcd830d77332ab9ebee3d1ec","target":"graph","created_at":"2026-07-02T01:17:31Z","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":"Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 177 injected regulatory categories and the coarse-to-fine VLM perception in SNRM accurately capture and interpret real-world semantic and behavioral constraints in a zero-shot manner without domain-specific fine-tuning or additional supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals."}],"snapshot_sha256":"97874106a3b60e225dfadccf103fc5531da9af28abd310de2b1080450f3e8bc7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.16993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a \"goal-driven trap\", prioritizing physical geometry (\"can I go?\") over semantic rules (\"may I go?\"), frequently overlooking subtle regulatory constraints. To bridge this gap, we establish Rule-VLN, the first large-scale urban benchmark for rule-compliant navigation. Spanning a massive 29k-node environment, it injects 177 diverse regulatory categories into 8k constrained nodes across fo","authors_text":"Jiawen Wen, Penglei Sun, Suixuan Qiu, Weisheng Xu, Wenjie Zhang, Xiaofei Yang, Xiaowen Chu","cross_cats":["cs.CV","cs.RO"],"headline":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T13:41:46Z","title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.16993","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T06:52:20.124678Z","id":"a2eeabda-b463-4617-9906-524dea7ee88d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Rule-VLN adds 177 regulatory categories to a 29k-node urban graph to test whether navigation agents can obey semantic rules instead of only reaching goals.","strongest_claim":"Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%.","weakest_assumption":"That the 177 injected regulatory categories and the coarse-to-fine VLM perception in SNRM accurately capture and interpret real-world semantic and behavioral constraints in a zero-shot manner without domain-specific fine-tuning or additional supervision."}},"verdict_id":"a2eeabda-b463-4617-9906-524dea7ee88d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8de307c2126bfc4d3d19a7d80b96fa8f5ae39f36f52a8e6ad60aa5efa354e782","target":"record","created_at":"2026-07-02T01:17:31Z","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":"ac9545e32c94c820bfe929af77533f790f58a9cca89a2e6260f2ead7699fda39","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T13:41:46Z","title_canon_sha256":"60c1322f248f585477ca30bb5ee6f773738350d477a800fbe0987b610c71cf83"},"schema_version":"1.0","source":{"id":"2604.16993","kind":"arxiv","version":2}},"canonical_sha256":"961f33131f51c0d1f14befb2e225e696577e14fb03d8983811b195e1ec8ff322","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"961f33131f51c0d1f14befb2e225e696577e14fb03d8983811b195e1ec8ff322","first_computed_at":"2026-07-02T01:17:31.317449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:31.317449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nFn3oLetaIJe83C9aEMiTHhvMck3zLbiuHyr1S0xYt75HJWjrnKJjXq6+/O+xwSnKTrDuu4Cp+FFEdI/HqIwDQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:31.317829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.16993","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8de307c2126bfc4d3d19a7d80b96fa8f5ae39f36f52a8e6ad60aa5efa354e782","sha256:4623f0b43bc48dd32eb7b71795b02a4bdbbf0aeebcd830d77332ab9ebee3d1ec"],"state_sha256":"d5e948ae5299fb04ddf4dfed8c20f5aafeebe61c23130da29aac1f8ddcc756b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZ3ZIPS148rvf/QdpEvV1/N124Aj0vP5EbvVmtJFQp/oYN69E4GouF+kU3GkGc41hbrudXN5zmWKHV3GFUfCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T09:31:08.368498Z","bundle_sha256":"7b1895b1879dcc8cecab6264de1a1be76c08081631edb76baaa4a56895779ccd"}}