{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5BWHFRB7AY2SG4WQPX2TSVK4JE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aab8e0ceda3e853af93bf3374a0ce315688e345f5c298fca67a66d0812364d65","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T09:18:09Z","title_canon_sha256":"d0899d1f4b25f3dc1776c5d6cd6991923820d256d928ba4f066312294e1741c1"},"schema_version":"1.0","source":{"id":"2410.05273","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05273","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05273v3","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05273","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"5BWHFRB7AY2S","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"5BWHFRB7AY2SG4WQ","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"5BWHFRB7","created_at":"2026-07-05T10:08:22Z"}],"graph_snapshots":[{"event_id":"sha256:2d8ea6ae0df5c146e2b40c48f1cef4f26cdd3b9d81d4a1367aef65c432b67bf5","target":"graph","created_at":"2026-07-05T10:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.05273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language-Action (VLA) models, leveraging powerful pre trained Vision-Language Models (VLMs) backends, have shown promise in robotic control due to their impressive generalization ability. However, the success comes at a cost. Their reliance on VLM backends with billions of parameters leads to high computational costs and inference latency, limiting the testing scenarios to mainly quasi-static tasks and hindering performance in dynamic tasks requiring rapid interactions. To address these limitations, this paper proposes HiRT, a Hierarchical Robot Transformer framework that enables ","authors_text":"Chengming Shi, Jianke Zhang, Jianyu Chen, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T09:18:09Z","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05273","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39ec56779a7d099ebc834c84f1213a7726167e5f445295f2d9111df4c03ae461","target":"record","created_at":"2026-07-05T10:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aab8e0ceda3e853af93bf3374a0ce315688e345f5c298fca67a66d0812364d65","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T09:18:09Z","title_canon_sha256":"d0899d1f4b25f3dc1776c5d6cd6991923820d256d928ba4f066312294e1741c1"},"schema_version":"1.0","source":{"id":"2410.05273","kind":"arxiv","version":3}},"canonical_sha256":"e86c72c43f06352372d07df539555c491d17669db48ef717b27b484e1425cd48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e86c72c43f06352372d07df539555c491d17669db48ef717b27b484e1425cd48","first_computed_at":"2026-07-05T10:08:22.360860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:22.360860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"28VstizMck8+TzAe43FqoUCgmMvf9GHvUgirOmBRMv1x5l++4zwo9padzB1OAMPFYCn5EBvFSkzjm4vE8BEKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:22.361328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05273","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39ec56779a7d099ebc834c84f1213a7726167e5f445295f2d9111df4c03ae461","sha256:2d8ea6ae0df5c146e2b40c48f1cef4f26cdd3b9d81d4a1367aef65c432b67bf5"],"state_sha256":"0e9c205c60943880972ae0b7d5525292be9ffa4191eafa9dce450e288133c111"}