{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3S7CATW2EZ53OLE3NSAIJTRCQH","short_pith_number":"pith:3S7CATW2","canonical_record":{"source":{"id":"2601.20309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-28T07:01:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"95444d2bcc4a327711855c0c507cd61acd7919e7c31760459a49ceba0e1c1cb0","abstract_canon_sha256":"eb54d30f0c668eb57544e840d29ab3097b67531bc5646563bff4a72505d6e220"},"schema_version":"1.0"},"canonical_sha256":"dcbe204eda267bb72c9b6c8084ce2281f756d19349783555a6c3767588a40f05","source":{"kind":"arxiv","id":"2601.20309","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.20309","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2601.20309v2","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20309","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"3S7CATW2EZ53","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"3S7CATW2EZ53OLE3","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"3S7CATW2","created_at":"2026-05-20T01:05:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3S7CATW2EZ53OLE3NSAIJTRCQH","target":"record","payload":{"canonical_record":{"source":{"id":"2601.20309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-28T07:01:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"95444d2bcc4a327711855c0c507cd61acd7919e7c31760459a49ceba0e1c1cb0","abstract_canon_sha256":"eb54d30f0c668eb57544e840d29ab3097b67531bc5646563bff4a72505d6e220"},"schema_version":"1.0"},"canonical_sha256":"dcbe204eda267bb72c9b6c8084ce2281f756d19349783555a6c3767588a40f05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:07.088971Z","signature_b64":"z7z5ZLG28Ds0ZU/PLKzzrAG9JYi6Gh3t6apkyX+TolWLW12nMx1JuTcUgJpg+Sood5tAuBA9Qo5KT+yz5y+hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbe204eda267bb72c9b6c8084ce2281f756d19349783555a6c3767588a40f05","last_reissued_at":"2026-05-20T01:05:07.087917Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:07.087917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.20309","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVRTtVAbgHCUVqIB6HXqmFUYIPEqRDTz1JII0oExE/BVMJRn4BxUesm3V0BYQxdDaXR8b6NxGmohev9kMIsZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:50:19.637963Z"},"content_sha256":"c8e368da7fdf57c8429287c3b96717c64440d3a4adfd0cfe2d51bd8dddb957b8","schema_version":"1.0","event_id":"sha256:c8e368da7fdf57c8429287c3b96717c64440d3a4adfd0cfe2d51bd8dddb957b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3S7CATW2EZ53OLE3NSAIJTRCQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Jiahuan Yu, Mingtao Hu, Minjia Zhang, Zichao Lin","submitted_at":"2026-01-28T07:01:46Z","abstract_excerpt":"Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems often suffer severe head-of-line (HOL) blocking. While prior work explored PCIe-based offloading, these approaches cannot sustain responsiveness under high request rates, often failing to meet tight Time-To-First-Token (TTFT) and Time-Between-Tokens (TBT) SLOs. We present SuperInfer, a high-performance LLM inference system designed for emerging Superchips (e.g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20309","kind":"arxiv","version":2},"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/2601.20309/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eya/BsCC16A2tzjncWrgpL2xqtvACuAT/dyGnLVz+fZvG2Gmgq2nYZgU88w/QHNWjMtNxM1awHbg5u3zHDkKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:50:19.638764Z"},"content_sha256":"99cacfafdc9ef93c110b9cea53e1474dc73fa28c0cd20a3d43324f88d306605c","schema_version":"1.0","event_id":"sha256:99cacfafdc9ef93c110b9cea53e1474dc73fa28c0cd20a3d43324f88d306605c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/bundle.json","state_url":"https://pith.science/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T00:50:19Z","links":{"resolver":"https://pith.science/pith/3S7CATW2EZ53OLE3NSAIJTRCQH","bundle":"https://pith.science/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/bundle.json","state":"https://pith.science/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3S7CATW2EZ53OLE3NSAIJTRCQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3S7CATW2EZ53OLE3NSAIJTRCQH","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":"eb54d30f0c668eb57544e840d29ab3097b67531bc5646563bff4a72505d6e220","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-28T07:01:46Z","title_canon_sha256":"95444d2bcc4a327711855c0c507cd61acd7919e7c31760459a49ceba0e1c1cb0"},"schema_version":"1.0","source":{"id":"2601.20309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.20309","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2601.20309v2","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20309","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"3S7CATW2EZ53","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"3S7CATW2EZ53OLE3","created_at":"2026-05-20T01:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"3S7CATW2","created_at":"2026-05-20T01:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:99cacfafdc9ef93c110b9cea53e1474dc73fa28c0cd20a3d43324f88d306605c","target":"graph","created_at":"2026-05-20T01:05:07Z","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/2601.20309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems often suffer severe head-of-line (HOL) blocking. While prior work explored PCIe-based offloading, these approaches cannot sustain responsiveness under high request rates, often failing to meet tight Time-To-First-Token (TTFT) and Time-Between-Tokens (TBT) SLOs. We present SuperInfer, a high-performance LLM inference system designed for emerging Superchips (e.g","authors_text":"Jiahuan Yu, Mingtao Hu, Minjia Zhang, Zichao Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-28T07:01:46Z","title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20309","kind":"arxiv","version":2},"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:c8e368da7fdf57c8429287c3b96717c64440d3a4adfd0cfe2d51bd8dddb957b8","target":"record","created_at":"2026-05-20T01:05:07Z","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":"eb54d30f0c668eb57544e840d29ab3097b67531bc5646563bff4a72505d6e220","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-28T07:01:46Z","title_canon_sha256":"95444d2bcc4a327711855c0c507cd61acd7919e7c31760459a49ceba0e1c1cb0"},"schema_version":"1.0","source":{"id":"2601.20309","kind":"arxiv","version":2}},"canonical_sha256":"dcbe204eda267bb72c9b6c8084ce2281f756d19349783555a6c3767588a40f05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcbe204eda267bb72c9b6c8084ce2281f756d19349783555a6c3767588a40f05","first_computed_at":"2026-05-20T01:05:07.087917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:07.087917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z7z5ZLG28Ds0ZU/PLKzzrAG9JYi6Gh3t6apkyX+TolWLW12nMx1JuTcUgJpg+Sood5tAuBA9Qo5KT+yz5y+hBg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:07.088971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.20309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8e368da7fdf57c8429287c3b96717c64440d3a4adfd0cfe2d51bd8dddb957b8","sha256:99cacfafdc9ef93c110b9cea53e1474dc73fa28c0cd20a3d43324f88d306605c"],"state_sha256":"7976804086e5266902bf9ce91b7e25450c4e6ba07cdd1840a47a577fcefd3d5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PnakvOTFKGmY6axp27hLWqPjlkKg6/C1WfIkX0dQhzPrJI6SCHdmQINq+UitiQjOfA+WXcJqeGz7cKEqdT/GDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T00:50:19.642607Z","bundle_sha256":"9dd3e02f09cec14ae2fd38bf6efca149395b229dd8b0a9ea24363008bdccc283"}}