{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AJBHNBRH7K4YYJBCWXW4GAE7CV","short_pith_number":"pith:AJBHNBRH","schema_version":"1.0","canonical_sha256":"0242768627fab98c2422b5edc3009f15478c9bc4029a2d96332269b2a0fba113","source":{"kind":"arxiv","id":"2608.03682","version":1},"attestation_state":"computed","paper":{"title":"PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Chenghua Wang, Daliang Xu, Dongqi Cai, Duojin Sun, Haoze Qian, Hao Zhang, Huaiyuan Zhang, Jinshuo Cui, Kezhao Zhao, Longxi Gao, Mengwei Xu, Rongjie Yi, Tianyue Zhang, Weikai Xie, Xiyuan Tan, Xuanzhe Liu, Yingying Qin, Yiwen Lu, Yuan Yao, Yuezhi Zu, Yunhan Guo, Ziqi Guo","submitted_at":"2026-08-04T13:53:48Z","abstract_excerpt":"Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Although these settings share the same checkpoint and action semantics, they often rely on separate inference programs. To unify them, we build PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and output logic in model adapters while sharing graph execution, kernels, memory management, and parallel services. The same codebase runs vision-language-act"},"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":"2608.03682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T13:53:48Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f8c30293b8d9486ea07d8354b43c596f1f5fa70b9f089b13b6742df87cfa47aa","abstract_canon_sha256":"e8f2e23d6c3b9e277bde9d830076b3f001f237b5fbb83ecd6f2ce7a668a55094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:53.102240Z","signature_b64":"TAyJUsBunb3rtRo7hpcr4ckrGrMLNaNma5NoxU+qfgd0JeGQ6o/Bv9oHMs+usvAB29f/E3t6gjKpNaEeo9IfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0242768627fab98c2422b5edc3009f15478c9bc4029a2d96332269b2a0fba113","last_reissued_at":"2026-08-05T01:36:53.100814Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:53.100814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Chenghua Wang, Daliang Xu, Dongqi Cai, Duojin Sun, Haoze Qian, Hao Zhang, Huaiyuan Zhang, Jinshuo Cui, Kezhao Zhao, Longxi Gao, Mengwei Xu, Rongjie Yi, Tianyue Zhang, Weikai Xie, Xiyuan Tan, Xuanzhe Liu, Yingying Qin, Yiwen Lu, Yuan Yao, Yuezhi Zu, Yunhan Guo, Ziqi Guo","submitted_at":"2026-08-04T13:53:48Z","abstract_excerpt":"Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Although these settings share the same checkpoint and action semantics, they often rely on separate inference programs. To unify them, we build PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and output logic in model adapters while sharing graph execution, kernels, memory management, and parallel services. The same codebase runs vision-language-act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03682","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/2608.03682/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":"2608.03682","created_at":"2026-08-05T01:36:53.101244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03682v1","created_at":"2026-08-05T01:36:53.101244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03682","created_at":"2026-08-05T01:36:53.101244+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJBHNBRH7K4Y","created_at":"2026-08-05T01:36:53.101244+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJBHNBRH7K4YYJBC","created_at":"2026-08-05T01:36:53.101244+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJBHNBRH","created_at":"2026-08-05T01:36:53.101244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV","json":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV.json","graph_json":"https://pith.science/api/pith-number/AJBHNBRH7K4YYJBCWXW4GAE7CV/graph.json","events_json":"https://pith.science/api/pith-number/AJBHNBRH7K4YYJBCWXW4GAE7CV/events.json","paper":"https://pith.science/paper/AJBHNBRH"},"agent_actions":{"view_html":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV","download_json":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV.json","view_paper":"https://pith.science/paper/AJBHNBRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03682&json=true","fetch_graph":"https://pith.science/api/pith-number/AJBHNBRH7K4YYJBCWXW4GAE7CV/graph.json","fetch_events":"https://pith.science/api/pith-number/AJBHNBRH7K4YYJBCWXW4GAE7CV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV/action/storage_attestation","attest_author":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV/action/author_attestation","sign_citation":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV/action/citation_signature","submit_replication":"https://pith.science/pith/AJBHNBRH7K4YYJBCWXW4GAE7CV/action/replication_record"}},"created_at":"2026-08-05T01:36:53.101244+00:00","updated_at":"2026-08-05T01:36:53.101244+00:00"}