{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:USFPRWVH7HBYDP4EL4DVH2WK53","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":"1283c3cc5c5c4a8e20ad868a2d05aee94caf711ba37b8416e85bda7583bbfa62","cross_cats_sorted":["cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-31T16:02:31Z","title_canon_sha256":"d4090143408101eb8085eefb3bf51a2eb5c52370fb011a93fb8c7342cdba69a0"},"schema_version":"1.0","source":{"id":"2607.29575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29575","created_at":"2026-08-03T01:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29575v1","created_at":"2026-08-03T01:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29575","created_at":"2026-08-03T01:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"USFPRWVH7HBY","created_at":"2026-08-03T01:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"USFPRWVH7HBYDP4E","created_at":"2026-08-03T01:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"USFPRWVH","created_at":"2026-08-03T01:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:68c612ac4f1ce3e7728efd96219e2757fe6ae5b5a9976bac90af38a1c4a170f3","target":"graph","created_at":"2026-08-03T01:39:06Z","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/2607.29575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) serving commonly increases batch size to improve throughput, but performance eventually reaches a deployment-dependent plateau beyond which larger batches provide marginal gains while increasing latency and GPU memory consumption. Previous studies have attributed this behavior to HBM/DRAM bandwidth limitations, but the underlying causes have primarily been supported by conceptual arguments or high-level performance observations. As our first contribution, we present a detailed GPU characterization using hardware profiling techniques, demonstrating that throughput sat","authors_text":"Chen Wang, Ferran Agullo, Jordi Torres, Josep Ll. Berral, Pol G.Recasens, Yue Zhu","cross_cats":["cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-31T16:02:31Z","title":"SLIM: Saturation-Aware Lightweight Performance Modeling for LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29575","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":"sha256:43f800d6371c856bacb58353593f633e7575e6887692d015d6d3e5b7d0e5e916","target":"record","created_at":"2026-08-03T01:39:06Z","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":"1283c3cc5c5c4a8e20ad868a2d05aee94caf711ba37b8416e85bda7583bbfa62","cross_cats_sorted":["cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-31T16:02:31Z","title_canon_sha256":"d4090143408101eb8085eefb3bf51a2eb5c52370fb011a93fb8c7342cdba69a0"},"schema_version":"1.0","source":{"id":"2607.29575","kind":"arxiv","version":1}},"canonical_sha256":"a48af8daa7f9c381bf845f0753eacaeefc87d163e1664d69f016141f7a7f2717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a48af8daa7f9c381bf845f0753eacaeefc87d163e1664d69f016141f7a7f2717","first_computed_at":"2026-08-03T01:39:06.178514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:39:06.178514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8OeeYu7aeYovXt/k0DdiUY21V4PmFlM8hIUme0GhKxyenjJ/Ui8yysWlo/ovTPyowBLxOydCIQ/E2xE9EnaZBg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:39:06.180267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43f800d6371c856bacb58353593f633e7575e6887692d015d6d3e5b7d0e5e916","sha256:68c612ac4f1ce3e7728efd96219e2757fe6ae5b5a9976bac90af38a1c4a170f3"],"state_sha256":"33ce69ab48b8488c27712eb1a9614835d5dd14184208f7c16feadbb2543b16e2"}