{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NRNTBIZDNRFGDHWOZAR7H5QNHG","short_pith_number":"pith:NRNTBIZD","canonical_record":{"source":{"id":"2504.16516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T08:41:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de53bb09af90b4bda7ad735534bcff470f15ae814e1cc04546345539a5b4d0ac","abstract_canon_sha256":"0790071da1111074629f8f98e2ef673824b24b34b0b71353865cac267be9a9bc"},"schema_version":"1.0"},"canonical_sha256":"6c5b30a3236c4a619ecec823f3f60d39af68626dee8abe883419083c33d95bcc","source":{"kind":"arxiv","id":"2504.16516","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16516","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16516v2","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16516","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_12","alias_value":"NRNTBIZDNRFG","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_16","alias_value":"NRNTBIZDNRFGDHWO","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_8","alias_value":"NRNTBIZD","created_at":"2026-07-05T10:53:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NRNTBIZDNRFGDHWOZAR7H5QNHG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T08:41:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de53bb09af90b4bda7ad735534bcff470f15ae814e1cc04546345539a5b4d0ac","abstract_canon_sha256":"0790071da1111074629f8f98e2ef673824b24b34b0b71353865cac267be9a9bc"},"schema_version":"1.0"},"canonical_sha256":"6c5b30a3236c4a619ecec823f3f60d39af68626dee8abe883419083c33d95bcc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:55.162492Z","signature_b64":"uY/rO4dHOP05umFhXNGj/JTcUzoHQhoWrVVHfeiRnNrHZgC4l5BqKvmCQul43mwAyIpRv+TA0znZo8Bih7HgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c5b30a3236c4a619ecec823f3f60d39af68626dee8abe883419083c33d95bcc","last_reissued_at":"2026-07-05T10:53:55.161890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:55.161890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16516","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":"2026-07-05T10:53:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luWkBQtOe9M0ySHl6XMmn6mj2qt9fqi4o8kf6VDO84LErzOFuShxjHbRTWsAvhmHylAWdJRRlFp6TvmxGBmOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:28:44.847865Z"},"content_sha256":"891c37d89e3cf9fca3acc6afb837f18ea83872bc38cb482b2c35026e2a8fa238","schema_version":"1.0","event_id":"sha256:891c37d89e3cf9fca3acc6afb837f18ea83872bc38cb482b2c35026e2a8fa238"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NRNTBIZDNRFGDHWOZAR7H5QNHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Chuan Qin, Junrong Yue, Wenxin Zhang, Xiaomin Lie, Xinlei Yu, Yifan Zhang, Zhendong Zhao","submitted_at":"2025-04-23T08:41:27Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) aims to enable embodied agents to follow natural language instructions and reach target locations in real-world environments. While prior methods often rely on either global scene representations or object-level features, these approaches are insufficient for capturing the complex interactions across modalities required for accurate navigation. In this paper, we propose a Multi-level Fusion and Reasoning Architecture (MFRA) to enhance the agent's ability to reason over visual observations, language instructions and navigation history. Specifically, MFRA int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16516","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/2504.16516/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":"2026-07-05T10:53:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jN1fDf7yVmlg6apa9lKtXOHf5suifmgaM9YWaiRD6R5h3jQfmmfWIb+GC+X9xFRZPhrxVmR1MnNxtXJ/LstkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:28:44.848385Z"},"content_sha256":"8095cf4cec530606dfdd19df46b76777239bab760a46938a4d025313c2d92a28","schema_version":"1.0","event_id":"sha256:8095cf4cec530606dfdd19df46b76777239bab760a46938a4d025313c2d92a28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/bundle.json","state_url":"https://pith.science/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/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":"2026-08-18T23:28:44Z","links":{"resolver":"https://pith.science/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG","bundle":"https://pith.science/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/bundle.json","state":"https://pith.science/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRNTBIZDNRFGDHWOZAR7H5QNHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NRNTBIZDNRFGDHWOZAR7H5QNHG","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":"0790071da1111074629f8f98e2ef673824b24b34b0b71353865cac267be9a9bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T08:41:27Z","title_canon_sha256":"de53bb09af90b4bda7ad735534bcff470f15ae814e1cc04546345539a5b4d0ac"},"schema_version":"1.0","source":{"id":"2504.16516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16516","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16516v2","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16516","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_12","alias_value":"NRNTBIZDNRFG","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_16","alias_value":"NRNTBIZDNRFGDHWO","created_at":"2026-07-05T10:53:55Z"},{"alias_kind":"pith_short_8","alias_value":"NRNTBIZD","created_at":"2026-07-05T10:53:55Z"}],"graph_snapshots":[{"event_id":"sha256:8095cf4cec530606dfdd19df46b76777239bab760a46938a4d025313c2d92a28","target":"graph","created_at":"2026-07-05T10:53:55Z","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/2504.16516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Navigation (VLN) aims to enable embodied agents to follow natural language instructions and reach target locations in real-world environments. While prior methods often rely on either global scene representations or object-level features, these approaches are insufficient for capturing the complex interactions across modalities required for accurate navigation. In this paper, we propose a Multi-level Fusion and Reasoning Architecture (MFRA) to enhance the agent's ability to reason over visual observations, language instructions and navigation history. Specifically, MFRA int","authors_text":"Bo Li, Chuan Qin, Junrong Yue, Wenxin Zhang, Xiaomin Lie, Xinlei Yu, Yifan Zhang, Zhendong Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T08:41:27Z","title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16516","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":"sha256:891c37d89e3cf9fca3acc6afb837f18ea83872bc38cb482b2c35026e2a8fa238","target":"record","created_at":"2026-07-05T10:53:55Z","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":"0790071da1111074629f8f98e2ef673824b24b34b0b71353865cac267be9a9bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T08:41:27Z","title_canon_sha256":"de53bb09af90b4bda7ad735534bcff470f15ae814e1cc04546345539a5b4d0ac"},"schema_version":"1.0","source":{"id":"2504.16516","kind":"arxiv","version":2}},"canonical_sha256":"6c5b30a3236c4a619ecec823f3f60d39af68626dee8abe883419083c33d95bcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c5b30a3236c4a619ecec823f3f60d39af68626dee8abe883419083c33d95bcc","first_computed_at":"2026-07-05T10:53:55.161890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:55.161890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uY/rO4dHOP05umFhXNGj/JTcUzoHQhoWrVVHfeiRnNrHZgC4l5BqKvmCQul43mwAyIpRv+TA0znZo8Bih7HgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:55.162492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891c37d89e3cf9fca3acc6afb837f18ea83872bc38cb482b2c35026e2a8fa238","sha256:8095cf4cec530606dfdd19df46b76777239bab760a46938a4d025313c2d92a28"],"state_sha256":"153195e8aae49b24447721dbf5c89bda702c18ee5f03a6168315af9c989a5329"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CB50etVP1n5/67CJfgVBPYGNSAnV9kwITpBbEakt/e2rAZYdB47r1FfZaHkHDz8nRdjud2IZJE78REA9JWKMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:28:44.852343Z","bundle_sha256":"b6993ecf80b45bb710ea6f3aa3338917a3ba476ad96b33e062c84024c71ab226"}}