{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2SFISY7IBIB4HICRLCYFRJU2PK","short_pith_number":"pith:2SFISY7I","schema_version":"1.0","canonical_sha256":"d48a8963e80a03c3a05158b058a69a7ab7e567697aa6bab9ddcd1f336ebe58cb","source":{"kind":"arxiv","id":"2510.17111","version":3},"attestation_state":"computed","paper":{"title":"Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aosheng Li, Jian Cheng, Qinghao Hu, Weifan Guan","submitted_at":"2025-10-20T02:59:45Z","abstract_excerpt":"Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due to their massive computational and memory demands, which conflict with the constraints of edge platforms such as on-board mobile manipulators that require real-time performance. Addressing this tension has become a central focus of recent research. In light of the growing efforts toward more efficient and scalable VLA systems, this survey provides a systema"},"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":"2510.17111","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-20T02:59:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"177db02e339337397fade987a995b5bf75422f8e504ebcf8d7d57c70509e39ff","abstract_canon_sha256":"299f48791424ac0c2918a400582ad5d024a6e3d1b127ba6b6a55761f508ea623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T12:02:52.841673Z","signature_b64":"jzCKaqIrCFkB5+WpxQkvWi4hiwigwhdrMW8WxrmC7JBlO1kruAWd4yCFAclEoCU6GlPcmhK68Ssl3NEbwS1JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d48a8963e80a03c3a05158b058a69a7ab7e567697aa6bab9ddcd1f336ebe58cb","last_reissued_at":"2026-06-01T12:02:52.840140Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T12:02:52.840140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aosheng Li, Jian Cheng, Qinghao Hu, Weifan Guan","submitted_at":"2025-10-20T02:59:45Z","abstract_excerpt":"Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due to their massive computational and memory demands, which conflict with the constraints of edge platforms such as on-board mobile manipulators that require real-time performance. Addressing this tension has become a central focus of recent research. In light of the growing efforts toward more efficient and scalable VLA systems, this survey provides a systema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17111","kind":"arxiv","version":3},"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/2510.17111/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":"2510.17111","created_at":"2026-06-01T12:02:52.840226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.17111v3","created_at":"2026-06-01T12:02:52.840226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17111","created_at":"2026-06-01T12:02:52.840226+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SFISY7IBIB4","created_at":"2026-06-01T12:02:52.840226+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SFISY7IBIB4HICR","created_at":"2026-06-01T12:02:52.840226+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SFISY7I","created_at":"2026-06-01T12:02:52.840226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18082","citing_title":"ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK","json":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK.json","graph_json":"https://pith.science/api/pith-number/2SFISY7IBIB4HICRLCYFRJU2PK/graph.json","events_json":"https://pith.science/api/pith-number/2SFISY7IBIB4HICRLCYFRJU2PK/events.json","paper":"https://pith.science/paper/2SFISY7I"},"agent_actions":{"view_html":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK","download_json":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK.json","view_paper":"https://pith.science/paper/2SFISY7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.17111&json=true","fetch_graph":"https://pith.science/api/pith-number/2SFISY7IBIB4HICRLCYFRJU2PK/graph.json","fetch_events":"https://pith.science/api/pith-number/2SFISY7IBIB4HICRLCYFRJU2PK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK/action/storage_attestation","attest_author":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK/action/author_attestation","sign_citation":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK/action/citation_signature","submit_replication":"https://pith.science/pith/2SFISY7IBIB4HICRLCYFRJU2PK/action/replication_record"}},"created_at":"2026-06-01T12:02:52.840226+00:00","updated_at":"2026-06-01T12:02:52.840226+00:00"}