{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TQJBMRB4SFUCXB3A46ISFL2E23","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":"4ed47c1de3770551a4f7dceae1ab386077aa8551fff5307efc1c1dbdcaed49cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-18T19:17:57Z","title_canon_sha256":"c6d8d3a05ab4aaf864ab5369bedd48c10a948b7d4cdc1b3e7c57995a407d922f"},"schema_version":"1.0","source":{"id":"1911.07883","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.07883","created_at":"2026-07-05T00:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"1911.07883v4","created_at":"2026-07-05T00:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07883","created_at":"2026-07-05T00:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"TQJBMRB4SFUC","created_at":"2026-07-05T00:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"TQJBMRB4SFUCXB3A","created_at":"2026-07-05T00:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"TQJBMRB4","created_at":"2026-07-05T00:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:92a5a25f3c05d02d4fbaf66b5de222c7b1108a5c90af839319d0b39698708498","target":"graph","created_at":"2026-07-05T00:51:53Z","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/1911.07883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit the vision and language features in cross-modal grounding. However, the VLN task remains challenging, since previous works have neglected the rich semantic information contained in the environment (such as implicit navigation graphs or sub-trajectory semantics). In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-su","authors_text":"Fengda Zhu, Xiaodan Liang, Xiaojun Chang, Yi Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-18T19:17:57Z","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07883","kind":"arxiv","version":4},"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:d64afdfe8faf3a16ec24d4db370bbfa0210fc5033ca2f98e51a0ec3fdcab4f97","target":"record","created_at":"2026-07-05T00:51:53Z","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":"4ed47c1de3770551a4f7dceae1ab386077aa8551fff5307efc1c1dbdcaed49cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-18T19:17:57Z","title_canon_sha256":"c6d8d3a05ab4aaf864ab5369bedd48c10a948b7d4cdc1b3e7c57995a407d922f"},"schema_version":"1.0","source":{"id":"1911.07883","kind":"arxiv","version":4}},"canonical_sha256":"9c1216443c91682b8760e79122af44d6dfab3db430e39e33fd56d24317efcc97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c1216443c91682b8760e79122af44d6dfab3db430e39e33fd56d24317efcc97","first_computed_at":"2026-07-05T00:51:53.429487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:53.429487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6IRCTbIBGGg1FLB0HRQoAmXr4HryRfyRo5DTupm7HgLmV2T9T+5bW3yHyQjGU3++qx7Y7R38PhrkrilMUw0iBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:53.429938Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.07883","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d64afdfe8faf3a16ec24d4db370bbfa0210fc5033ca2f98e51a0ec3fdcab4f97","sha256:92a5a25f3c05d02d4fbaf66b5de222c7b1108a5c90af839319d0b39698708498"],"state_sha256":"bbf2218fc22b61476ddc0f8192d1919f7b7cf1a1970395aa344d2abeb49da7d5"}