{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZPW3INEZIQ2IMTPWDKQFVUAUZ","short_pith_number":"pith:FZPW3INE","schema_version":"1.0","canonical_sha256":"2e5f6da1a4ca21a4326fb0d502d680a653b962cbf63b8fde32839ea17c726ce8","source":{"kind":"arxiv","id":"2506.08566","version":1},"attestation_state":"computed","paper":{"title":"Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erwei Yin, Jiawei Sun, Liang Xie, Yibo Cui, Yu Zhao","submitted_at":"2025-06-10T08:36:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.08566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T08:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"e731753f14d274acbe99c8288356ab86329c69585028beacf5ba969e0730451a","abstract_canon_sha256":"8fb774b33f4103f4196c9088b383251a4e7350a9e0be1e97c6f74a5fee6e6b86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:09.848250Z","signature_b64":"1LY4r3rNg6I3ZVLYZbkm9jsEN3uji70D0kxYVVpt982M10bTdPp9MQjcBdBTYWroiGBVdu2lTW6bXOB13I1dDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e5f6da1a4ca21a4326fb0d502d680a653b962cbf63b8fde32839ea17c726ce8","last_reissued_at":"2026-07-05T11:19:09.847783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:09.847783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erwei Yin, Jiawei Sun, Liang Xie, Yibo Cui, Yu Zhao","submitted_at":"2025-06-10T08:36:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08566","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.08566/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.08566","created_at":"2026-07-05T11:19:09.847834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08566v1","created_at":"2026-07-05T11:19:09.847834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08566","created_at":"2026-07-05T11:19:09.847834+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZPW3INEZIQ2","created_at":"2026-07-05T11:19:09.847834+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZPW3INEZIQ2IMTP","created_at":"2026-07-05T11:19:09.847834+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZPW3INE","created_at":"2026-07-05T11:19:09.847834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ","json":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ.json","graph_json":"https://pith.science/api/pith-number/FZPW3INEZIQ2IMTPWDKQFVUAUZ/graph.json","events_json":"https://pith.science/api/pith-number/FZPW3INEZIQ2IMTPWDKQFVUAUZ/events.json","paper":"https://pith.science/paper/FZPW3INE"},"agent_actions":{"view_html":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ","download_json":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ.json","view_paper":"https://pith.science/paper/FZPW3INE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08566&json=true","fetch_graph":"https://pith.science/api/pith-number/FZPW3INEZIQ2IMTPWDKQFVUAUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FZPW3INEZIQ2IMTPWDKQFVUAUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ/action/storage_attestation","attest_author":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ/action/author_attestation","sign_citation":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ/action/citation_signature","submit_replication":"https://pith.science/pith/FZPW3INEZIQ2IMTPWDKQFVUAUZ/action/replication_record"}},"created_at":"2026-07-05T11:19:09.847834+00:00","updated_at":"2026-07-05T11:19:09.847834+00:00"}