{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F2USP5ADKK2D6HGE4J7HMH6F6H","short_pith_number":"pith:F2USP5AD","schema_version":"1.0","canonical_sha256":"2ea927f40352b43f1cc4e27e761fc5f1d502ea4018ac841c2421dd635094b1c0","source":{"kind":"arxiv","id":"2605.19728","version":1},"attestation_state":"computed","paper":{"title":"Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdul Mohaimen Al Radi, Kunyang Li, Mubarak Shah, Yu Tian, Yuzhang Shang","submitted_at":"2026-05-19T12:02:17Z","abstract_excerpt":"Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural language rather than low-level control signals. This limitation is especially pronounced for aerial flight, where motion occurs in unconstrained 6-DoF space and small errors in ego-motion can produce large trajectory drift. Generating aerial videos that follow fine-grained inertial actions can support scalable training and evaluation of aerial agents by providing a controllable proxy for real-world or expensive simulation data. To address this "},"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":"2605.19728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T12:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"85c9a8deda7ffbdd156340d97df77554fd60843d2c4fa882607e8f38c148f74a","abstract_canon_sha256":"fe8649307e2765618644ff7889e065b8d9913f4fdf0b7898c63435c39ab97d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:11.286208Z","signature_b64":"53Anr8zLSGtuy4vK98YWZQWE8RG+MriUxBCsfQZtjC7RGlkcO+msfpqbfOAUfkX5qx1NFrraskYwdDarp5LgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea927f40352b43f1cc4e27e761fc5f1d502ea4018ac841c2421dd635094b1c0","last_reissued_at":"2026-05-20T01:06:11.285494Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:11.285494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdul Mohaimen Al Radi, Kunyang Li, Mubarak Shah, Yu Tian, Yuzhang Shang","submitted_at":"2026-05-19T12:02:17Z","abstract_excerpt":"Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural language rather than low-level control signals. This limitation is especially pronounced for aerial flight, where motion occurs in unconstrained 6-DoF space and small errors in ego-motion can produce large trajectory drift. Generating aerial videos that follow fine-grained inertial actions can support scalable training and evaluation of aerial agents by providing a controllable proxy for real-world or expensive simulation data. To address this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19728","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/2605.19728/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":"2605.19728","created_at":"2026-05-20T01:06:11.285617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19728v1","created_at":"2026-05-20T01:06:11.285617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19728","created_at":"2026-05-20T01:06:11.285617+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2USP5ADKK2D","created_at":"2026-05-20T01:06:11.285617+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2USP5ADKK2D6HGE","created_at":"2026-05-20T01:06:11.285617+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2USP5AD","created_at":"2026-05-20T01:06:11.285617+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/F2USP5ADKK2D6HGE4J7HMH6F6H","json":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H.json","graph_json":"https://pith.science/api/pith-number/F2USP5ADKK2D6HGE4J7HMH6F6H/graph.json","events_json":"https://pith.science/api/pith-number/F2USP5ADKK2D6HGE4J7HMH6F6H/events.json","paper":"https://pith.science/paper/F2USP5AD"},"agent_actions":{"view_html":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H","download_json":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H.json","view_paper":"https://pith.science/paper/F2USP5AD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19728&json=true","fetch_graph":"https://pith.science/api/pith-number/F2USP5ADKK2D6HGE4J7HMH6F6H/graph.json","fetch_events":"https://pith.science/api/pith-number/F2USP5ADKK2D6HGE4J7HMH6F6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H/action/storage_attestation","attest_author":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H/action/author_attestation","sign_citation":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H/action/citation_signature","submit_replication":"https://pith.science/pith/F2USP5ADKK2D6HGE4J7HMH6F6H/action/replication_record"}},"created_at":"2026-05-20T01:06:11.285617+00:00","updated_at":"2026-05-20T01:06:11.285617+00:00"}