{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFAY3UHDOT22WPM6RW76G2CNFL","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":"9954bd74493cbee4f189f61d088ed18035ad14cf6113d67e1aeca1aab568a174","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-09T23:52:57Z","title_canon_sha256":"0912ba169957e106143c0939871b33b362a8ad04e2713d21a82e34716be3470b"},"schema_version":"1.0","source":{"id":"2607.08993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08993","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08993v1","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08993","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"NFAY3UHDOT22","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"NFAY3UHDOT22WPM6","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"NFAY3UHD","created_at":"2026-07-13T00:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:2695838ae09120f65a2ddb2bd3d3bee7b202ef3e5940692e68c4c0f9b0603f9d","target":"graph","created_at":"2026-07-13T00:17:32Z","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/2607.08993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) scale, their memory and computation demands have grown substantially, making weight-only quantization a widely adopted technique for reducing model size with minimal accuracy loss. However, on current GPUs, CUDA-core-based dequantization introduces substantial instruction overhead, on-chip traffic, and pipeline stalls, making it a major bottleneck for high-throughput, cloud-scale LLM serving. To address these limitations, we propose StreamDQ, a lightweight architectural enhancement that enables on-the-fly dequantization in the memory subsystem for high-throughpu","authors_text":"Daegun Yoon, Hoshik Kim, Hyeonseok Ju, Ieryung Park, Joonseop Sim, Minki Jeong, Nameun Kang, Seungyong Lee, Soohong Ahn, Youngpyo Joo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-09T23:52:57Z","title":"StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08993","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:c6104a35f6decfb5ecf81ad28a2d80ae5037b13ad67b48c783055c203589f5bf","target":"record","created_at":"2026-07-13T00:17:32Z","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":"9954bd74493cbee4f189f61d088ed18035ad14cf6113d67e1aeca1aab568a174","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-09T23:52:57Z","title_canon_sha256":"0912ba169957e106143c0939871b33b362a8ad04e2713d21a82e34716be3470b"},"schema_version":"1.0","source":{"id":"2607.08993","kind":"arxiv","version":1}},"canonical_sha256":"69418dd0e374f5ab3d9e8dbfe3684d2acf4a8a0ebdc5292fcf7a8eed64d01aab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69418dd0e374f5ab3d9e8dbfe3684d2acf4a8a0ebdc5292fcf7a8eed64d01aab","first_computed_at":"2026-07-13T00:17:32.774503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:32.774503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zAdK8SAyL6Nj65d1mvwYT7S4NdNhpmJHC6/pbSvc3nJYf52Fz6z28YAX8QKJRxUrxOuLd0oG/c/Dw3M0ox9TDw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:32.775881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6104a35f6decfb5ecf81ad28a2d80ae5037b13ad67b48c783055c203589f5bf","sha256:2695838ae09120f65a2ddb2bd3d3bee7b202ef3e5940692e68c4c0f9b0603f9d"],"state_sha256":"f7916c829a8648c462ddd9f001edf6294fb02fd736164b5fe5d4e0afe19bd515"}