{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XKOUHUPNIDIHFZOSBHLEZBDFHD","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":"62f38261a58dc36e4e81c68f799cf2b6f76ab74acd121a0164a0a9f8b6bc6932","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T10:18:46Z","title_canon_sha256":"85cdbcd6e078bef0bf6955ea0a759a3228acf010674331698a8cde5397b5a6aa"},"schema_version":"1.0","source":{"id":"2605.19634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19634","created_at":"2026-05-20T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19634v1","created_at":"2026-05-20T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19634","created_at":"2026-05-20T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"XKOUHUPNIDIH","created_at":"2026-05-20T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"XKOUHUPNIDIHFZOS","created_at":"2026-05-20T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"XKOUHUPN","created_at":"2026-05-20T01:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:b4a3732f14537aa3cb98401635ddd89a521abe2a55df18c4ae7eddfc704f1ccf","target":"graph","created_at":"2026-05-20T01:05:55Z","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/2605.19634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language navigation (VLN) requires an embodied agent to ground natural-language instructions into executable navigation actions in unseen environments. Existing zero-shot methods typically rely on additional waypoint prediction modules, which often entangle high-level directional reasoning with fine-grained local grounding, leading to error-prone and unstable decisions. In this paper, we propose P2DNav, a hierarchical framework for zero-shot vision-and-language navigation. P2DNav consists of three core components: Panorama-to-Downview (P2D), Sliding-Window Dialogue Memory (SDM), and","authors_text":"Chengju Liu, Haojie Dai, Jinlong Li, Kai Sheng, Liuyi Wang, Qijun Chen, Yongrui Qin, Zongtao He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T10:18:46Z","title":"P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19634","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":"sha256:4b2c89fc2f92e9d97c460d0477ad53c3db2552d1e28dd1f17fb85ecaf975af4c","target":"record","created_at":"2026-05-20T01:05:55Z","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":"62f38261a58dc36e4e81c68f799cf2b6f76ab74acd121a0164a0a9f8b6bc6932","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T10:18:46Z","title_canon_sha256":"85cdbcd6e078bef0bf6955ea0a759a3228acf010674331698a8cde5397b5a6aa"},"schema_version":"1.0","source":{"id":"2605.19634","kind":"arxiv","version":1}},"canonical_sha256":"ba9d43d1ed40d072e5d209d64c846538f06cfa740bb365d05a0eddeecaa99baf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba9d43d1ed40d072e5d209d64c846538f06cfa740bb365d05a0eddeecaa99baf","first_computed_at":"2026-05-20T01:05:55.236676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:55.236676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sQ8uxNBjko93RQATZLD4on8DPfvAMSfo9ZJNZVMulm4va5YbvM/Rjv8wSMlHy7c2NQKmwLPfuhiX8YDetaTpCg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:55.237277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b2c89fc2f92e9d97c460d0477ad53c3db2552d1e28dd1f17fb85ecaf975af4c","sha256:b4a3732f14537aa3cb98401635ddd89a521abe2a55df18c4ae7eddfc704f1ccf"],"state_sha256":"8e9b0285715a2f88d681452574d7d40cab1891e35cafa0c11db5d0ac1ed86bd7"}