{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5BWHFRB7AY2SG4WQPX2TSVK4JE","short_pith_number":"pith:5BWHFRB7","schema_version":"1.0","canonical_sha256":"e86c72c43f06352372d07df539555c491d17669db48ef717b27b484e1425cd48","source":{"kind":"arxiv","id":"2410.05273","version":3},"attestation_state":"computed","paper":{"title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengming Shi, Jianke Zhang, Jianyu Chen, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","submitted_at":"2024-09-12T09:18:09Z","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 "},"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":"2410.05273","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T09:18:09Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d0899d1f4b25f3dc1776c5d6cd6991923820d256d928ba4f066312294e1741c1","abstract_canon_sha256":"aab8e0ceda3e853af93bf3374a0ce315688e345f5c298fca67a66d0812364d65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:22.361328Z","signature_b64":"28VstizMck8+TzAe43FqoUCgmMvf9GHvUgirOmBRMv1x5l++4zwo9padzB1OAMPFYCn5EBvFSkzjm4vE8BEKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e86c72c43f06352372d07df539555c491d17669db48ef717b27b484e1425cd48","last_reissued_at":"2026-07-05T10:08:22.360860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:22.360860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengming Shi, Jianke Zhang, Jianyu Chen, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","submitted_at":"2024-09-12T09:18:09Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05273","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/2410.05273/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":"2410.05273","created_at":"2026-07-05T10:08:22.360917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05273v3","created_at":"2026-07-05T10:08:22.360917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05273","created_at":"2026-07-05T10:08:22.360917+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BWHFRB7AY2S","created_at":"2026-07-05T10:08:22.360917+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BWHFRB7AY2SG4WQ","created_at":"2026-07-05T10:08:22.360917+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BWHFRB7","created_at":"2026-07-05T10:08:22.360917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08359","citing_title":"FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05377","citing_title":"Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25800","citing_title":"ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01088","citing_title":"ROSA: A Robotics Foundation Model Serving System for Robot Factories","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14803","citing_title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE","json":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE.json","graph_json":"https://pith.science/api/pith-number/5BWHFRB7AY2SG4WQPX2TSVK4JE/graph.json","events_json":"https://pith.science/api/pith-number/5BWHFRB7AY2SG4WQPX2TSVK4JE/events.json","paper":"https://pith.science/paper/5BWHFRB7"},"agent_actions":{"view_html":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE","download_json":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE.json","view_paper":"https://pith.science/paper/5BWHFRB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05273&json=true","fetch_graph":"https://pith.science/api/pith-number/5BWHFRB7AY2SG4WQPX2TSVK4JE/graph.json","fetch_events":"https://pith.science/api/pith-number/5BWHFRB7AY2SG4WQPX2TSVK4JE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE/action/storage_attestation","attest_author":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE/action/author_attestation","sign_citation":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE/action/citation_signature","submit_replication":"https://pith.science/pith/5BWHFRB7AY2SG4WQPX2TSVK4JE/action/replication_record"}},"created_at":"2026-07-05T10:08:22.360917+00:00","updated_at":"2026-07-05T10:08:22.360917+00:00"}