{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FZPW3INEZIQ2IMTPWDKQFVUAUZ","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":"8fb774b33f4103f4196c9088b383251a4e7350a9e0be1e97c6f74a5fee6e6b86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T08:36:51Z","title_canon_sha256":"e731753f14d274acbe99c8288356ab86329c69585028beacf5ba969e0730451a"},"schema_version":"1.0","source":{"id":"2506.08566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08566","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08566v1","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08566","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"FZPW3INEZIQ2","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"FZPW3INEZIQ2IMTP","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"FZPW3INE","created_at":"2026-07-05T11:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:f1f120769559347afac601a6a0cd486a7923ef8943151d3ccc64e34bf79573d9","target":"graph","created_at":"2026-07-05T11:19:09Z","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/2506.08566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Navigation (VLN) enables intelligent agents to navigate environments by integrating visual perception and natural language instructions, yet faces significant challenges due to the scarcity of fine-grained cross-modal alignment annotations. Existing datasets primarily focus on global instruction-trajectory matching, neglecting sub-instruction-level and entity-level alignments critical for accurate navigation action decision-making. To address this limitation, we propose FCA-NIG, a generative framework that automatically constructs navigation instructions with dual-level fine-gr","authors_text":"Erwei Yin, Jiawei Sun, Liang Xie, Yibo Cui, Yu Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T08:36:51Z","title":"Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08566","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:f50a1450625a760ef4a939ebd3771120c5ebc10750a9d0ced76d1e4670c72d51","target":"record","created_at":"2026-07-05T11:19:09Z","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":"8fb774b33f4103f4196c9088b383251a4e7350a9e0be1e97c6f74a5fee6e6b86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T08:36:51Z","title_canon_sha256":"e731753f14d274acbe99c8288356ab86329c69585028beacf5ba969e0730451a"},"schema_version":"1.0","source":{"id":"2506.08566","kind":"arxiv","version":1}},"canonical_sha256":"2e5f6da1a4ca21a4326fb0d502d680a653b962cbf63b8fde32839ea17c726ce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e5f6da1a4ca21a4326fb0d502d680a653b962cbf63b8fde32839ea17c726ce8","first_computed_at":"2026-07-05T11:19:09.847783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:09.847783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1LY4r3rNg6I3ZVLYZbkm9jsEN3uji70D0kxYVVpt982M10bTdPp9MQjcBdBTYWroiGBVdu2lTW6bXOB13I1dDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:09.848250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f50a1450625a760ef4a939ebd3771120c5ebc10750a9d0ced76d1e4670c72d51","sha256:f1f120769559347afac601a6a0cd486a7923ef8943151d3ccc64e34bf79573d9"],"state_sha256":"903f1369451e1abd30f61784d97fa1bf4756999d9d274c70c04008f0794b6406"}