{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R6GACQN7Z5OB3VUCJ3UPDSCPXE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"54ca0fe4ce2caa61a65060b4168ab158bd5174b7e33e762d87bd51d7b1fab178","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-29T08:58:04Z","title_canon_sha256":"0a93a664eca161a8398332b68f6510332976170ad3ed037df33e364b10c27c11"},"schema_version":"1.0","source":{"id":"2607.26633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26633","created_at":"2026-07-30T01:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26633v1","created_at":"2026-07-30T01:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26633","created_at":"2026-07-30T01:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"R6GACQN7Z5OB","created_at":"2026-07-30T01:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"R6GACQN7Z5OB3VUC","created_at":"2026-07-30T01:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"R6GACQN7","created_at":"2026-07-30T01:21:38Z"}],"graph_snapshots":[{"event_id":"sha256:d5e157c94de0588598ffa28d064e7e7ec0c27cc88d417f6ade85fd4f10af1aef","target":"graph","created_at":"2026-07-30T01:21:38Z","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/2607.26633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern LLMs and their agentic applications are broadening the range of serving workloads, spanning context lengths from a few hundred tokens to hundreds of thousands. As these requests frequently interleave within the same serving window, LLM serving systems must handle highly heterogeneous mixed-length workloads. Such mixed-length workloads expose fundamental inefficiencies in GPU-centric serving architectures, whose throughput depends on large, memory-constrained batches. In this paper, we present NELSSA, an LLM serving system that integrates GPUs with real-world Processing-near-Memory (PNM)","authors_text":"Donguk Moon, Euiseok Kim, Guseul Heo, Hoshik Kim, Hyeongseok Gwak, Jongse Park, Junseok Lee, Kangkyu Park, Kwangsik Shin, Myunghyun Rhee, Seungyong Lee, Sookyung Choi, Youngpyo Joo, Yunseo Chun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-29T08:58:04Z","title":"NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26633","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":"sha256:702802e59e0c3a469584249795ecfdc433671b800878104f117e2f7a10704e65","target":"record","created_at":"2026-07-30T01:21:38Z","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":"54ca0fe4ce2caa61a65060b4168ab158bd5174b7e33e762d87bd51d7b1fab178","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-29T08:58:04Z","title_canon_sha256":"0a93a664eca161a8398332b68f6510332976170ad3ed037df33e364b10c27c11"},"schema_version":"1.0","source":{"id":"2607.26633","kind":"arxiv","version":1}},"canonical_sha256":"8f8c0141bfcf5c1dd6824ee8f1c84fb931c50e0e6e39de51b717831ad46327b9","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8c0141bfcf5c1dd6824ee8f1c84fb931c50e0e6e39de51b717831ad46327b9","first_computed_at":"2026-07-30T01:21:38.317044Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:21:38.317044Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:702802e59e0c3a469584249795ecfdc433671b800878104f117e2f7a10704e65","sha256:d5e157c94de0588598ffa28d064e7e7ec0c27cc88d417f6ade85fd4f10af1aef","sha256:172acc98a46bec08e26d94bd5690af3f924d2c35f7e10f7d05e717d9977d349a"],"state_sha256":"ce4992724e4285a2e2962031269ef5282c467152c8c3f606d7b1a241ab883617"}