{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HLJDHEBSC2KEJP6TW2SS7IOVKO","short_pith_number":"pith:HLJDHEBS","schema_version":"1.0","canonical_sha256":"3ad2339032169444bfd3b6a52fa1d5538f7b1ee07a0002d3c98e25f94dc8634b","source":{"kind":"arxiv","id":"2508.09444","version":1},"attestation_state":"computed","paper":{"title":"DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Gongwei Chen, Haoxiang Shi, Liqiang Nie, Xiang Deng, Yaowei Wang, Zaijing Li","submitted_at":"2025-08-13T02:51:43Z","abstract_excerpt":"Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a navigation planner suggests the intermediate goals in the high-level action space. However, this two-stage decomposition framework suffers from: (1) global sub-optimization due to the proxy objective in each stage, and (2) a performance bottleneck caused by the strong reliance on the q"},"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":"2508.09444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-13T02:51:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f234db774fda0f16bdd490298ec94d34ec408623b117e883fce59ace96f348a6","abstract_canon_sha256":"245e0a5e1833b56afc6a8651658af2b04e40d62c49cb51b703c6589a0328c153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:14.835133Z","signature_b64":"9jmdaasAFnCX0C6jneBAxmkFEp/z0qccq3Xp3cNBw+ScZz0bZmPceMa5j6v9Zn1IbT6bRwR253PfndNsbLKFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ad2339032169444bfd3b6a52fa1d5538f7b1ee07a0002d3c98e25f94dc8634b","last_reissued_at":"2026-07-05T11:53:14.834627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:14.834627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Gongwei Chen, Haoxiang Shi, Liqiang Nie, Xiang Deng, Yaowei Wang, Zaijing Li","submitted_at":"2025-08-13T02:51:43Z","abstract_excerpt":"Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a navigation planner suggests the intermediate goals in the high-level action space. However, this two-stage decomposition framework suffers from: (1) global sub-optimization due to the proxy objective in each stage, and (2) a performance bottleneck caused by the strong reliance on the q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09444","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/2508.09444/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":"2508.09444","created_at":"2026-07-05T11:53:14.834691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09444v1","created_at":"2026-07-05T11:53:14.834691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09444","created_at":"2026-07-05T11:53:14.834691+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLJDHEBSC2KE","created_at":"2026-07-05T11:53:14.834691+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLJDHEBSC2KEJP6T","created_at":"2026-07-05T11:53:14.834691+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLJDHEBS","created_at":"2026-07-05T11:53:14.834691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11762","citing_title":"NavOL: Navigation Policy with Online Imitation Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07038","citing_title":"Learning Material-Aware Hamiltonian Risk Fields for Safe Navigation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07038","citing_title":"Learning Material-Aware Hamiltonian Risk Fields for Safe Navigation","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO","json":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO.json","graph_json":"https://pith.science/api/pith-number/HLJDHEBSC2KEJP6TW2SS7IOVKO/graph.json","events_json":"https://pith.science/api/pith-number/HLJDHEBSC2KEJP6TW2SS7IOVKO/events.json","paper":"https://pith.science/paper/HLJDHEBS"},"agent_actions":{"view_html":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO","download_json":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO.json","view_paper":"https://pith.science/paper/HLJDHEBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09444&json=true","fetch_graph":"https://pith.science/api/pith-number/HLJDHEBSC2KEJP6TW2SS7IOVKO/graph.json","fetch_events":"https://pith.science/api/pith-number/HLJDHEBSC2KEJP6TW2SS7IOVKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO/action/storage_attestation","attest_author":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO/action/author_attestation","sign_citation":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO/action/citation_signature","submit_replication":"https://pith.science/pith/HLJDHEBSC2KEJP6TW2SS7IOVKO/action/replication_record"}},"created_at":"2026-07-05T11:53:14.834691+00:00","updated_at":"2026-07-05T11:53:14.834691+00:00"}