{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H7DKFFH4XCRZDJMMLTG2Y6FB6E","short_pith_number":"pith:H7DKFFH4","schema_version":"1.0","canonical_sha256":"3fc6a294fcb8a391a58c5ccdac78a1f10dec479f6cd8a9e4fecb9c6c6d4ea94f","source":{"kind":"arxiv","id":"2606.01205","version":1},"attestation_state":"computed","paper":{"title":"ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingxi Liu, Jiankun Yang, Jiawei Huang, Jinqiang Cui, Shihao Xia, Xuchen Liu","submitted_at":"2026-05-31T12:39:44Z","abstract_excerpt":"Vision-language navigation (VLN) for UAVs demands grounding free-form instructions into 6-DoF flight under partial observability. While Vision-Language-Action (VLA) models excel at semantic reasoning, they suffer from brittleness due to geometric inconsistency and dynamics mismatch. To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. Instead of direct regression, ImagineUAV employs a latent video diffusion model to generate instruction-conditioned future observations, explicitly imagining environmental evolution, from which 6-DoF m"},"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":"2606.01205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-31T12:39:44Z","cross_cats_sorted":[],"title_canon_sha256":"a55938f8b7fbaefaa2f91c2fee2b7cc88b4bb144e21a568b1d11e6fe0ecd718f","abstract_canon_sha256":"2ec6a771219698540c6ed3c594da703c29ca3b2608d15f8703482d8aca494974"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:26.787827Z","signature_b64":"uBc5gX4ab95jZln2MvS43kiE2wUpZfl0UAeykVML57WAqHzpp66ydW9JlvMSW62Hb3Fdil/jx8bdABMNd/PVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fc6a294fcb8a391a58c5ccdac78a1f10dec479f6cd8a9e4fecb9c6c6d4ea94f","last_reissued_at":"2026-06-02T02:04:26.787408Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:26.787408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingxi Liu, Jiankun Yang, Jiawei Huang, Jinqiang Cui, Shihao Xia, Xuchen Liu","submitted_at":"2026-05-31T12:39:44Z","abstract_excerpt":"Vision-language navigation (VLN) for UAVs demands grounding free-form instructions into 6-DoF flight under partial observability. While Vision-Language-Action (VLA) models excel at semantic reasoning, they suffer from brittleness due to geometric inconsistency and dynamics mismatch. To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. Instead of direct regression, ImagineUAV employs a latent video diffusion model to generate instruction-conditioned future observations, explicitly imagining environmental evolution, from which 6-DoF m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01205","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/2606.01205/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":"2606.01205","created_at":"2026-06-02T02:04:26.787470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01205v1","created_at":"2026-06-02T02:04:26.787470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01205","created_at":"2026-06-02T02:04:26.787470+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7DKFFH4XCRZ","created_at":"2026-06-02T02:04:26.787470+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7DKFFH4XCRZDJMM","created_at":"2026-06-02T02:04:26.787470+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7DKFFH4","created_at":"2026-06-02T02:04:26.787470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E","json":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E.json","graph_json":"https://pith.science/api/pith-number/H7DKFFH4XCRZDJMMLTG2Y6FB6E/graph.json","events_json":"https://pith.science/api/pith-number/H7DKFFH4XCRZDJMMLTG2Y6FB6E/events.json","paper":"https://pith.science/paper/H7DKFFH4"},"agent_actions":{"view_html":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E","download_json":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E.json","view_paper":"https://pith.science/paper/H7DKFFH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01205&json=true","fetch_graph":"https://pith.science/api/pith-number/H7DKFFH4XCRZDJMMLTG2Y6FB6E/graph.json","fetch_events":"https://pith.science/api/pith-number/H7DKFFH4XCRZDJMMLTG2Y6FB6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E/action/storage_attestation","attest_author":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E/action/author_attestation","sign_citation":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E/action/citation_signature","submit_replication":"https://pith.science/pith/H7DKFFH4XCRZDJMMLTG2Y6FB6E/action/replication_record"}},"created_at":"2026-06-02T02:04:26.787470+00:00","updated_at":"2026-06-02T02:04:26.787470+00:00"}