{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7YBO6BSORZBM5NQNJOGTYRFIW3","short_pith_number":"pith:7YBO6BSO","schema_version":"1.0","canonical_sha256":"fe02ef064e8e42ceb60d4b8d3c44a8b6e660f022b5c7bfaa9854635f2fb75256","source":{"kind":"arxiv","id":"2509.09560","version":1},"attestation_state":"computed","paper":{"title":"Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ao Xu, Haibin Lin, Han Zhao, Minyi Guo, Ningxin Zheng, Quan Chen, Shulai Zhang, Weihao Cui, Xin Liu","submitted_at":"2025-09-11T15:51:43Z","abstract_excerpt":"Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary \"thinking\" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism "},"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":"2509.09560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-11T15:51:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d733dcdceeae10109eaed79b924033b09011269639f5e2be3d5d3a575c77d303","abstract_canon_sha256":"b30150ad5abfdf73c99c845d14ac263231f28369b2bffd62ef8316201726e982"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:38.226473Z","signature_b64":"mIF67mnQdKeE7wdUd+IdMw9KmVsvzGGHfOrAC3AArW7U0DsxjTrKIvwftd2EvHDyd70RCg7nuyoPyPUmwSVRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe02ef064e8e42ceb60d4b8d3c44a8b6e660f022b5c7bfaa9854635f2fb75256","last_reissued_at":"2026-07-05T12:09:38.225924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:38.225924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ao Xu, Haibin Lin, Han Zhao, Minyi Guo, Ningxin Zheng, Quan Chen, Shulai Zhang, Weihao Cui, Xin Liu","submitted_at":"2025-09-11T15:51:43Z","abstract_excerpt":"Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary \"thinking\" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09560","kind":"arxiv","version":1},"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/2509.09560/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":"2509.09560","created_at":"2026-07-05T12:09:38.225987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09560v1","created_at":"2026-07-05T12:09:38.225987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09560","created_at":"2026-07-05T12:09:38.225987+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YBO6BSORZBM","created_at":"2026-07-05T12:09:38.225987+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YBO6BSORZBM5NQN","created_at":"2026-07-05T12:09:38.225987+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YBO6BSO","created_at":"2026-07-05T12:09:38.225987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01581","citing_title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3","json":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3.json","graph_json":"https://pith.science/api/pith-number/7YBO6BSORZBM5NQNJOGTYRFIW3/graph.json","events_json":"https://pith.science/api/pith-number/7YBO6BSORZBM5NQNJOGTYRFIW3/events.json","paper":"https://pith.science/paper/7YBO6BSO"},"agent_actions":{"view_html":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3","download_json":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3.json","view_paper":"https://pith.science/paper/7YBO6BSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09560&json=true","fetch_graph":"https://pith.science/api/pith-number/7YBO6BSORZBM5NQNJOGTYRFIW3/graph.json","fetch_events":"https://pith.science/api/pith-number/7YBO6BSORZBM5NQNJOGTYRFIW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3/action/storage_attestation","attest_author":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3/action/author_attestation","sign_citation":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3/action/citation_signature","submit_replication":"https://pith.science/pith/7YBO6BSORZBM5NQNJOGTYRFIW3/action/replication_record"}},"created_at":"2026-07-05T12:09:38.225987+00:00","updated_at":"2026-07-05T12:09:38.225987+00:00"}