{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KSMSYT3JCXXEAP6S3VAR6L5PHL","short_pith_number":"pith:KSMSYT3J","schema_version":"1.0","canonical_sha256":"54992c4f6915ee403fd2dd411f2faf3ac0b92964227539fe42989eb16edb030d","source":{"kind":"arxiv","id":"2412.06413","version":2},"attestation_state":"computed","paper":{"title":"World-Consistent Data Generation for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Fang, Di Huang, Jiaming Guo, Qi Guo, Rui Zhang, Shaohui Peng, Shuo Wang, Xing Hu, Xishan Zhang, Yanyang Yan, Yu Zhong, Zihao Zhang","submitted_at":"2024-12-09T11:40:54Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and "},"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":"2412.06413","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T11:40:54Z","cross_cats_sorted":[],"title_canon_sha256":"9d43f6acf1df3a0f3888a315a34cfc40b65fb7a83a0bd7c06a0a3ce4f59e2fa7","abstract_canon_sha256":"7df51e3dee458f760b38a653c1b4455f81e1a2914e1ac6e1af7efaee9cd46413"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:45.491818Z","signature_b64":"Ze1f/h9Kfg1mklUe7Uy2cs7YZtCUrJ0hwGA+nW20R4mXlJSkJtFhcC/wrxoMwiqlMaqHLikpwq8ICfZA6+uQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54992c4f6915ee403fd2dd411f2faf3ac0b92964227539fe42989eb16edb030d","last_reissued_at":"2026-07-05T11:26:45.491198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:45.491198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World-Consistent Data Generation for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Fang, Di Huang, Jiaming Guo, Qi Guo, Rui Zhang, Shaohui Peng, Shuo Wang, Xing Hu, Xishan Zhang, Yanyang Yan, Yu Zhong, Zihao Zhang","submitted_at":"2024-12-09T11:40:54Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06413","kind":"arxiv","version":2},"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/2412.06413/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":"2412.06413","created_at":"2026-07-05T11:26:45.491269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06413v2","created_at":"2026-07-05T11:26:45.491269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06413","created_at":"2026-07-05T11:26:45.491269+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSMSYT3JCXXE","created_at":"2026-07-05T11:26:45.491269+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSMSYT3JCXXEAP6S","created_at":"2026-07-05T11:26:45.491269+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSMSYT3J","created_at":"2026-07-05T11:26:45.491269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18223","citing_title":"Instruction-as-State: Environment-Guided and State-Conditioned Semantic Understanding for Embodied Navigation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL","json":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL.json","graph_json":"https://pith.science/api/pith-number/KSMSYT3JCXXEAP6S3VAR6L5PHL/graph.json","events_json":"https://pith.science/api/pith-number/KSMSYT3JCXXEAP6S3VAR6L5PHL/events.json","paper":"https://pith.science/paper/KSMSYT3J"},"agent_actions":{"view_html":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL","download_json":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL.json","view_paper":"https://pith.science/paper/KSMSYT3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06413&json=true","fetch_graph":"https://pith.science/api/pith-number/KSMSYT3JCXXEAP6S3VAR6L5PHL/graph.json","fetch_events":"https://pith.science/api/pith-number/KSMSYT3JCXXEAP6S3VAR6L5PHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL/action/storage_attestation","attest_author":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL/action/author_attestation","sign_citation":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL/action/citation_signature","submit_replication":"https://pith.science/pith/KSMSYT3JCXXEAP6S3VAR6L5PHL/action/replication_record"}},"created_at":"2026-07-05T11:26:45.491269+00:00","updated_at":"2026-07-05T11:26:45.491269+00:00"}