{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IF5O5EOC6STYVDI47SBHV6EE7Y","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":"d434d0b45b68864285b11d20d36303e8823c726c96f7e2a2df76986b5b27361a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-19T06:46:21Z","title_canon_sha256":"2cad2758dd37c9ba660076c1f8fe06a63df26e8b7542ed6064a478e29ba3a1b8"},"schema_version":"1.0","source":{"id":"2207.11201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.11201","created_at":"2026-07-05T04:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.11201v1","created_at":"2026-07-05T04:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11201","created_at":"2026-07-05T04:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"IF5O5EOC6STY","created_at":"2026-07-05T04:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"IF5O5EOC6STYVDI4","created_at":"2026-07-05T04:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"IF5O5EOC","created_at":"2026-07-05T04:42:44Z"}],"graph_snapshots":[{"event_id":"sha256:92fe6295c17d55c28134a115a667ed0e26596e57094d797256a790277f3e6ff3","target":"graph","created_at":"2026-07-05T04:42:44Z","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/2207.11201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path planning, which, however, has rarely been studied before in literature. In this article, we propose a Target-Driven Structured Transformer Planner (TD-STP) for long-horizon goal-guided and room layout-aware navigation. Specifically, we devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unex","authors_text":"Chen Gao, Haibing Ren, Huaxia Xia, Jinyu Chen, Lirong Yang, Si Liu, Wenguan Wang, Yusheng Zhao","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-19T06:46:21Z","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11201","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":"sha256:8678f276c3e396f273c8e3f9ea5d5770a9e1c29287297128af704e5951bd5ca1","target":"record","created_at":"2026-07-05T04:42:44Z","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":"d434d0b45b68864285b11d20d36303e8823c726c96f7e2a2df76986b5b27361a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-19T06:46:21Z","title_canon_sha256":"2cad2758dd37c9ba660076c1f8fe06a63df26e8b7542ed6064a478e29ba3a1b8"},"schema_version":"1.0","source":{"id":"2207.11201","kind":"arxiv","version":1}},"canonical_sha256":"417aee91c2f4a78a8d1cfc827af884fe2fbee6c05ca5f7502b638dfe7aaeb9ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"417aee91c2f4a78a8d1cfc827af884fe2fbee6c05ca5f7502b638dfe7aaeb9ee","first_computed_at":"2026-07-05T04:42:44.689374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:44.689374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g9YV4T4kioQMAtgZE48yEvdGg8LpL6T6wmaIaxxfjd3Oqf2cCwWhqP22frUrnrU5yoZy2s8funDsQnKlEfV8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:44.689855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.11201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8678f276c3e396f273c8e3f9ea5d5770a9e1c29287297128af704e5951bd5ca1","sha256:92fe6295c17d55c28134a115a667ed0e26596e57094d797256a790277f3e6ff3"],"state_sha256":"6849417d9bb17a7c384ccc7f1dfa80c8415e7984d39839a0a34182784adc731d"}