{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R2PMCGZST4FQW6KHGS2VFQJXYI","short_pith_number":"pith:R2PMCGZS","schema_version":"1.0","canonical_sha256":"8e9ec11b329f0b0b794734b552c137c21ed5cf1d79c175a059675ab17699f657","source":{"kind":"arxiv","id":"2602.03983","version":3},"attestation_state":"computed","paper":{"title":"Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Huashuo Lei, Rex Ying, Tinglin Huang, Weikang Qiu","submitted_at":"2026-02-03T20:17:47Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language instructions, achieving strong performance and generalization across tasks. However, VLAs face two major challenges: a limited context window for input frames and inefficient inference due to the quadratic attention complexity and large parameter counts. To this end, we propose DySta, a framework that disentangles visual inputs into multi-level static and dynam"},"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":"2602.03983","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T20:17:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d30e86d7a8b500223298597555476438d55d670fb47e0a5d0ae9e65d9a95b0c7","abstract_canon_sha256":"321bbdf63d3047c0af0e8d671608516771cdc891155f0fc8ccfd4c3056f6bb60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:04.732196Z","signature_b64":"Pyat5UydbgSjXEnHNM+1F3vxg8mn1GfZaeU3GJl6G9fMctBb3SAIotZUr4+hv1/ugS/LIyHKtN4DOviI9p4gBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e9ec11b329f0b0b794734b552c137c21ed5cf1d79c175a059675ab17699f657","last_reissued_at":"2026-05-26T02:04:04.731235Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:04.731235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Huashuo Lei, Rex Ying, Tinglin Huang, Weikang Qiu","submitted_at":"2026-02-03T20:17:47Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language instructions, achieving strong performance and generalization across tasks. However, VLAs face two major challenges: a limited context window for input frames and inefficient inference due to the quadratic attention complexity and large parameter counts. To this end, we propose DySta, a framework that disentangles visual inputs into multi-level static and dynam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03983","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/2602.03983/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":"2602.03983","created_at":"2026-05-26T02:04:04.731365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03983v3","created_at":"2026-05-26T02:04:04.731365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03983","created_at":"2026-05-26T02:04:04.731365+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2PMCGZST4FQ","created_at":"2026-05-26T02:04:04.731365+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2PMCGZST4FQW6KH","created_at":"2026-05-26T02:04:04.731365+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2PMCGZS","created_at":"2026-05-26T02:04:04.731365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2603.15620","citing_title":"Towards Generalizable Robotic Manipulation in Dynamic Environments","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08340","citing_title":"PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI","json":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI.json","graph_json":"https://pith.science/api/pith-number/R2PMCGZST4FQW6KHGS2VFQJXYI/graph.json","events_json":"https://pith.science/api/pith-number/R2PMCGZST4FQW6KHGS2VFQJXYI/events.json","paper":"https://pith.science/paper/R2PMCGZS"},"agent_actions":{"view_html":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI","download_json":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI.json","view_paper":"https://pith.science/paper/R2PMCGZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03983&json=true","fetch_graph":"https://pith.science/api/pith-number/R2PMCGZST4FQW6KHGS2VFQJXYI/graph.json","fetch_events":"https://pith.science/api/pith-number/R2PMCGZST4FQW6KHGS2VFQJXYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI/action/storage_attestation","attest_author":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI/action/author_attestation","sign_citation":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI/action/citation_signature","submit_replication":"https://pith.science/pith/R2PMCGZST4FQW6KHGS2VFQJXYI/action/replication_record"}},"created_at":"2026-05-26T02:04:04.731365+00:00","updated_at":"2026-05-26T02:04:04.731365+00:00"}