{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CLSO7ZPKJQCX2IAROA6ZVNLHAG","short_pith_number":"pith:CLSO7ZPK","schema_version":"1.0","canonical_sha256":"12e4efe5ea4c057d2011703d9ab56701a9e6c44a813c44acd2e63fbf8893f56d","source":{"kind":"arxiv","id":"2607.06706","version":1},"attestation_state":"computed","paper":{"title":"Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chanoh Park, Donghee Noh, Hea-Min Lee, Ho Seok Ahn, Inkyu Sa","submitted_at":"2026-07-07T18:24:09Z","abstract_excerpt":"Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly to the red building directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with 7 degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robo"},"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":"2607.06706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-07T18:24:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"533455667b45d47a6d1b05ec0267e6f129778e1a2745d71b182c3d3f31dfb7fb","abstract_canon_sha256":"99a52877129997d8411115c716a0dc729cb85de36432218d5fef1e18cf225eac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:24.005436Z","signature_b64":"iNKTuYB5XEM/3MXnEareCzKmBiQK8B6Y8xHxONzmOPZYq/0WacQKY8kJAJDRNhV6ARseEb1TLnskwskjDViyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12e4efe5ea4c057d2011703d9ab56701a9e6c44a813c44acd2e63fbf8893f56d","last_reissued_at":"2026-07-09T00:19:24.004987Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:24.004987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chanoh Park, Donghee Noh, Hea-Min Lee, Ho Seok Ahn, Inkyu Sa","submitted_at":"2026-07-07T18:24:09Z","abstract_excerpt":"Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly to the red building directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with 7 degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06706","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/2607.06706/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":"2607.06706","created_at":"2026-07-09T00:19:24.005050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06706v1","created_at":"2026-07-09T00:19:24.005050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06706","created_at":"2026-07-09T00:19:24.005050+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLSO7ZPKJQCX","created_at":"2026-07-09T00:19:24.005050+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLSO7ZPKJQCX2IAR","created_at":"2026-07-09T00:19:24.005050+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLSO7ZPK","created_at":"2026-07-09T00:19:24.005050+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/CLSO7ZPKJQCX2IAROA6ZVNLHAG","json":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG.json","graph_json":"https://pith.science/api/pith-number/CLSO7ZPKJQCX2IAROA6ZVNLHAG/graph.json","events_json":"https://pith.science/api/pith-number/CLSO7ZPKJQCX2IAROA6ZVNLHAG/events.json","paper":"https://pith.science/paper/CLSO7ZPK"},"agent_actions":{"view_html":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG","download_json":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG.json","view_paper":"https://pith.science/paper/CLSO7ZPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06706&json=true","fetch_graph":"https://pith.science/api/pith-number/CLSO7ZPKJQCX2IAROA6ZVNLHAG/graph.json","fetch_events":"https://pith.science/api/pith-number/CLSO7ZPKJQCX2IAROA6ZVNLHAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG/action/storage_attestation","attest_author":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG/action/author_attestation","sign_citation":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG/action/citation_signature","submit_replication":"https://pith.science/pith/CLSO7ZPKJQCX2IAROA6ZVNLHAG/action/replication_record"}},"created_at":"2026-07-09T00:19:24.005050+00:00","updated_at":"2026-07-09T00:19:24.005050+00:00"}