{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CXEUDAICF5PS24K3KLMOV2PVI","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":"11cdca20960f8ae982c40498b4728339cb73b57c26ce59f5fe3fe444015a4b26","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T02:40:07Z","title_canon_sha256":"943939c83fbf34b3977b885012382ef4f393da0c7e9cc276874b3e3e09b05c23"},"schema_version":"1.0","source":{"id":"2507.21450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21450","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21450v1","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21450","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"3CXEUDAICF5P","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"3CXEUDAICF5PS24K","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"3CXEUDAI","created_at":"2026-07-05T11:45:00Z"}],"graph_snapshots":[{"event_id":"sha256:2d5e45417e60d5392bc395014c99a2a03b0a5715246fd93718af1adc554a4fe0","target":"graph","created_at":"2026-07-05T11:45:00Z","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/2507.21450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Navigation (VLN) typically requires agents to navigate to specified objects or remote regions in unknown scenes by obeying linguistic commands. Such tasks require organizing historical visual observations for linguistic grounding, which is critical for long-sequence navigational decisions. However, current agents suffer from overly detailed scene representation and ambiguous vision-language alignment, which weaken their comprehension of navigation-friendly high-level scene priors and easily lead to behaviors that violate linguistic commands. To tackle these issues, we propose a","authors_text":"Bolei Chen, Jianxin Wang, Jiaxu Kang, Ping Zhong, Qi Wu, Yifei Wang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T02:40:07Z","title":"Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21450","kind":"arxiv","version":1},"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":"sha256:86e9a0fba4f7ed19ed708c4a2110e9a95c261389e715bb65aa796a963bceabab","target":"record","created_at":"2026-07-05T11:45:00Z","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":"11cdca20960f8ae982c40498b4728339cb73b57c26ce59f5fe3fe444015a4b26","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T02:40:07Z","title_canon_sha256":"943939c83fbf34b3977b885012382ef4f393da0c7e9cc276874b3e3e09b05c23"},"schema_version":"1.0","source":{"id":"2507.21450","kind":"arxiv","version":1}},"canonical_sha256":"d8ae4a0c08117af96b8ada96c7574faa044c9053bbdd82325d37a420611cebc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8ae4a0c08117af96b8ada96c7574faa044c9053bbdd82325d37a420611cebc7","first_computed_at":"2026-07-05T11:45:00.078295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:00.078295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QDsG+fv+Kb8Mo86SNng0b/yHK0Yr6G4KyxCVRv7ZivQZwu8Mc9suVt616SEWf3fciiTxJLp83hWoKCsAkSPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:00.078723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86e9a0fba4f7ed19ed708c4a2110e9a95c261389e715bb65aa796a963bceabab","sha256:2d5e45417e60d5392bc395014c99a2a03b0a5715246fd93718af1adc554a4fe0"],"state_sha256":"b77056d23ab0a47b59082cd97e6b0213112ad05dda0066195bfbe4c4d89166ca"}