{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L2AOD3VNBVJGGD2ZIOC3RYM7OJ","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":"37ff4caaab9b802689b826e751669515e543202235d4a3720d050a9a7985e819","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T03:05:59Z","title_canon_sha256":"bce68f596ac4773ead120397fef47a572b92f040d41927fd90359f71683565e5"},"schema_version":"1.0","source":{"id":"2405.18721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18721","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18721v2","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18721","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"L2AOD3VNBVJG","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"L2AOD3VNBVJGGD2Z","created_at":"2026-07-05T08:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"L2AOD3VN","created_at":"2026-07-05T08:27:49Z"}],"graph_snapshots":[{"event_id":"sha256:4a4362e95ea4db9b19fdf6309933435729df66d47b87f5dde51b6be7886622f5","target":"graph","created_at":"2026-07-05T08:27:49Z","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/2405.18721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn from limited navigation data and lack sufficient open-world alignment knowledge. In this work, we propose a new VLN paradigm, called COrrectable LaNdmark DiScOvery via Large ModEls (CONSOLE). In CONSOLE, we cast VLN as an open-world sequen","authors_text":"Bingqian Lin, Hang Xu, Jianzhuang Liu, Shikui Ma, Xiaodan Liang, Yi Zhu, Yunshuang Nie, Ziming Wei","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T03:05:59Z","title":"Correctable Landmark Discovery via Large Models for Vision-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18721","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":"sha256:042e0b215441192fc09ae90a7fe6f77598fc651f797eb7dd5f30be744a465971","target":"record","created_at":"2026-07-05T08:27:49Z","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":"37ff4caaab9b802689b826e751669515e543202235d4a3720d050a9a7985e819","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T03:05:59Z","title_canon_sha256":"bce68f596ac4773ead120397fef47a572b92f040d41927fd90359f71683565e5"},"schema_version":"1.0","source":{"id":"2405.18721","kind":"arxiv","version":2}},"canonical_sha256":"5e80e1eead0d52630f594385b8e19f724a70e94451a9e5ba7b4d16e8745f631a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e80e1eead0d52630f594385b8e19f724a70e94451a9e5ba7b4d16e8745f631a","first_computed_at":"2026-07-05T08:27:49.134142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:49.134142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRPmQ6LjBDcu6kiTJKz1ZRYvPjew7a1LTpO+zR1hOUp4Ovo4R3Rn7FRfhpQqlNQQDIhcYmctxFh1Lo2bvQw8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:49.134688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:042e0b215441192fc09ae90a7fe6f77598fc651f797eb7dd5f30be744a465971","sha256:4a4362e95ea4db9b19fdf6309933435729df66d47b87f5dde51b6be7886622f5"],"state_sha256":"01b22327c1baed0327e8d761adc2ded43c962a2a90ec4779bacfefad20d50eb5"}