{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZUZD3XLBDB3VCUI47VX3GNR4Z5","short_pith_number":"pith:ZUZD3XLB","schema_version":"1.0","canonical_sha256":"cd323ddd61187751511cfd6fb3363ccf459cc722723fe234660965577f904b26","source":{"kind":"arxiv","id":"2602.20200","version":2},"attestation_state":"computed","paper":{"title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Bing Hu, Dongmei Jiang, Gongwei Chen, Jianye Hao, Liqiang Nie, Pengwei Xie, Rui Shao, Zaijing Li","submitted_at":"2026-02-22T15:39:34Z","abstract_excerpt":"Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a Vision-Language backbone for perception and understanding, together with a generative policy for action generation. However, its performance is increasingly bottlenecked by the action generation proceess. (i) Low inference efficiency. A pronounced distributional gap between isotropic noise priors and target action distributions, which increases denoising steps and the incidence of infeasible samples. (ii) Poor robustness. Existing policies condition solel"},"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":"2602.20200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-22T15:39:34Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8ad353eda73529d9b8b987957904cff07e5bcc9a34c33923a12d66e7e60dabe3","abstract_canon_sha256":"3ed8bbfeffc2d474887cb741bb33d24e51d901f05fe326e7bac9b34d711099af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:26.466834Z","signature_b64":"Db8MEtjbG7WuE31afFlwyehxEBAWhK+UIAgm50OU6uG3/5eCVFpJPaTCQQiAl0cTaSMfMmROj9Eo8Mrx8khOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd323ddd61187751511cfd6fb3363ccf459cc722723fe234660965577f904b26","last_reissued_at":"2026-05-20T00:04:26.465959Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:26.465959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Bing Hu, Dongmei Jiang, Gongwei Chen, Jianye Hao, Liqiang Nie, Pengwei Xie, Rui Shao, Zaijing Li","submitted_at":"2026-02-22T15:39:34Z","abstract_excerpt":"Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a Vision-Language backbone for perception and understanding, together with a generative policy for action generation. However, its performance is increasingly bottlenecked by the action generation proceess. (i) Low inference efficiency. A pronounced distributional gap between isotropic noise priors and target action distributions, which increases denoising steps and the incidence of infeasible samples. (ii) Poor robustness. Existing policies condition solel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.20200","kind":"arxiv","version":2},"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/2602.20200/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":"2602.20200","created_at":"2026-05-20T00:04:26.466091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.20200v2","created_at":"2026-05-20T00:04:26.466091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.20200","created_at":"2026-05-20T00:04:26.466091+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUZD3XLBDB3V","created_at":"2026-05-20T00:04:26.466091+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUZD3XLBDB3VCUI4","created_at":"2026-05-20T00:04:26.466091+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUZD3XLB","created_at":"2026-05-20T00:04:26.466091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05126","citing_title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5","json":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5.json","graph_json":"https://pith.science/api/pith-number/ZUZD3XLBDB3VCUI47VX3GNR4Z5/graph.json","events_json":"https://pith.science/api/pith-number/ZUZD3XLBDB3VCUI47VX3GNR4Z5/events.json","paper":"https://pith.science/paper/ZUZD3XLB"},"agent_actions":{"view_html":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5","download_json":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5.json","view_paper":"https://pith.science/paper/ZUZD3XLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.20200&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUZD3XLBDB3VCUI47VX3GNR4Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUZD3XLBDB3VCUI47VX3GNR4Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5/action/storage_attestation","attest_author":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5/action/author_attestation","sign_citation":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5/action/citation_signature","submit_replication":"https://pith.science/pith/ZUZD3XLBDB3VCUI47VX3GNR4Z5/action/replication_record"}},"created_at":"2026-05-20T00:04:26.466091+00:00","updated_at":"2026-05-20T00:04:26.466091+00:00"}