{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MZTA6KIODO2KIGLCYKRR63ZGQ5","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":"11272b6061856850e65bb1b67cd8a52f5b649995ac11e97fb67a0ee1691e608b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:36:51Z","title_canon_sha256":"6775b1ed98cea0f41edd075cc4e8c052145f022cd57d67fea5e8a635c5d6ffe8"},"schema_version":"1.0","source":{"id":"2606.21633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21633","created_at":"2026-06-23T01:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21633v1","created_at":"2026-06-23T01:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21633","created_at":"2026-06-23T01:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"MZTA6KIODO2K","created_at":"2026-06-23T01:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"MZTA6KIODO2KIGLC","created_at":"2026-06-23T01:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"MZTA6KIO","created_at":"2026-06-23T01:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:12245d4299261e1528fab517c657862bb7797ae1eeb9a235e12af3a6210fbb3c","target":"graph","created_at":"2026-06-23T01:13:17Z","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/2606.21633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still grows linearly with context, limiting throughput at long contexts. KV cache offloading to host DRAM alleviates this memory pressure, but the limited PCIe bandwidth necessitates recalling only a sparse subset of KV entries. In block dLLMs, the relevant KV entries remain consistent across denoising steps within a block, enabling high-accuracy selection by identifying the top-k entries once and reusing them throughout all denoising steps. This proper","authors_text":"Doyeon Kim, Ion Stoica, Jae W. Lee, Jongseok Park, Omin Kwon, Seung Yul Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:36:51Z","title":"HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21633","kind":"arxiv","version":1},"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":"sha256:7ef3e0d3a713718d72eac053e127df15806de0f58f55d3bd25f4b81dcec423d6","target":"record","created_at":"2026-06-23T01:13:17Z","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":"11272b6061856850e65bb1b67cd8a52f5b649995ac11e97fb67a0ee1691e608b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:36:51Z","title_canon_sha256":"6775b1ed98cea0f41edd075cc4e8c052145f022cd57d67fea5e8a635c5d6ffe8"},"schema_version":"1.0","source":{"id":"2606.21633","kind":"arxiv","version":1}},"canonical_sha256":"66660f290e1bb4a41962c2a31f6f268740a63fd807f132e9274372009e4db82a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66660f290e1bb4a41962c2a31f6f268740a63fd807f132e9274372009e4db82a","first_computed_at":"2026-06-23T01:13:17.398024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:17.398024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DUzOmLL7/D1S0HdoGTyMl2gXqHzloPUFY42tIh4v4+0Oiz0aGASgvRJLJsnXJOdowXNFgj0ZeEsexSZMXeRFAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:17.398561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ef3e0d3a713718d72eac053e127df15806de0f58f55d3bd25f4b81dcec423d6","sha256:12245d4299261e1528fab517c657862bb7797ae1eeb9a235e12af3a6210fbb3c"],"state_sha256":"8c329c19ed0f143b604b809a10424da28ef09700f3156a86fecd6b39a00fc34d"}