{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MF2ZQSQAPRTOO2R6QD4DWBUZFE","short_pith_number":"pith:MF2ZQSQA","schema_version":"1.0","canonical_sha256":"6175984a007c66e76a3e80f83b06992930a2ab97d1274aae0df029c187dfbe65","source":{"kind":"arxiv","id":"2505.20897","version":2},"attestation_state":"computed","paper":{"title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Dong An, Dong Wang, Li Zhang, Pengyuan Wu, Pingrui Zhang, Xuelong Li, Yan Ding, Yifei Su, Zhigang Wang","submitted_at":"2025-05-27T08:40:20Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) requires the agent to navigate by following natural instructions under partial observability, making it difficult to align perception with language. Recent methods mitigate this by imagining future scenes, yet they rely on vision-based synthesis, leading to high computational cost and redundant details. To this end, we propose to adaptively imagine key environmental semantics via \\textit{language} form, enabling a more reliable and efficient strategy. Specifically, we introduce a novel Adaptive Text Dreamer (ATD), a dual-branch self-guided imagination polic"},"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":"2505.20897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T08:40:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"510647e7d825275b4c0cc0b3a59e32eb6d0b125177522aaadf3a2dbc6cb28f00","abstract_canon_sha256":"6736fd435fb70159885892f34964d0144d9a283a50a272f217d97eff1a3359fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:11.198846Z","signature_b64":"r7bHNS/hdH+e0nPx46g2/6i4pQFSYDamVKdkMiQUDVvo/FXH8EmgORKepMUAl++QfV1Sfyas1OifyPy1um1fAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6175984a007c66e76a3e80f83b06992930a2ab97d1274aae0df029c187dfbe65","last_reissued_at":"2026-07-05T11:25:11.198343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:11.198343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Dong An, Dong Wang, Li Zhang, Pengyuan Wu, Pingrui Zhang, Xuelong Li, Yan Ding, Yifei Su, Zhigang Wang","submitted_at":"2025-05-27T08:40:20Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) requires the agent to navigate by following natural instructions under partial observability, making it difficult to align perception with language. Recent methods mitigate this by imagining future scenes, yet they rely on vision-based synthesis, leading to high computational cost and redundant details. To this end, we propose to adaptively imagine key environmental semantics via \\textit{language} form, enabling a more reliable and efficient strategy. Specifically, we introduce a novel Adaptive Text Dreamer (ATD), a dual-branch self-guided imagination polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20897","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/2505.20897/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":"2505.20897","created_at":"2026-07-05T11:25:11.198404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20897v2","created_at":"2026-07-05T11:25:11.198404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20897","created_at":"2026-07-05T11:25:11.198404+00:00"},{"alias_kind":"pith_short_12","alias_value":"MF2ZQSQAPRTO","created_at":"2026-07-05T11:25:11.198404+00:00"},{"alias_kind":"pith_short_16","alias_value":"MF2ZQSQAPRTOO2R6","created_at":"2026-07-05T11:25:11.198404+00:00"},{"alias_kind":"pith_short_8","alias_value":"MF2ZQSQA","created_at":"2026-07-05T11:25:11.198404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17982","citing_title":"Mitigating Multimodal Hallucination via Phase-wise Self-reward","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE","json":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE.json","graph_json":"https://pith.science/api/pith-number/MF2ZQSQAPRTOO2R6QD4DWBUZFE/graph.json","events_json":"https://pith.science/api/pith-number/MF2ZQSQAPRTOO2R6QD4DWBUZFE/events.json","paper":"https://pith.science/paper/MF2ZQSQA"},"agent_actions":{"view_html":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE","download_json":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE.json","view_paper":"https://pith.science/paper/MF2ZQSQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20897&json=true","fetch_graph":"https://pith.science/api/pith-number/MF2ZQSQAPRTOO2R6QD4DWBUZFE/graph.json","fetch_events":"https://pith.science/api/pith-number/MF2ZQSQAPRTOO2R6QD4DWBUZFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE/action/storage_attestation","attest_author":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE/action/author_attestation","sign_citation":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE/action/citation_signature","submit_replication":"https://pith.science/pith/MF2ZQSQAPRTOO2R6QD4DWBUZFE/action/replication_record"}},"created_at":"2026-07-05T11:25:11.198404+00:00","updated_at":"2026-07-05T11:25:11.198404+00:00"}