{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y44ARQ3A7R37MA3UJEILH3MPVI","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":"e99aa1cd8c245f0ea8b4888e3476b82b9ce925ca8218363fbb03e6441197ee21","cross_cats_sorted":["cs.CL","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T17:06:30Z","title_canon_sha256":"5c8632ad6e4918920dd9f0671be888426f33eb3e25a3d96ee4a0a4c10b024aea"},"schema_version":"1.0","source":{"id":"2501.06589","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06589","created_at":"2026-07-05T11:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06589v5","created_at":"2026-07-05T11:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06589","created_at":"2026-07-05T11:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y44ARQ3A7R37","created_at":"2026-07-05T11:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y44ARQ3A7R37MA3U","created_at":"2026-07-05T11:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y44ARQ3A","created_at":"2026-07-05T11:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:57a02b24863b64d2c1bb0cf3c7c28e7a5749d6b7507ed9c3dabd7d6d487010c1","target":"graph","created_at":"2026-07-05T11:24:12Z","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/2501.06589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition computation across multiple devices, reducing memory load and computation time. However, using model parallelism necessitates communication of information between GPUs, which has been a major bottleneck and limits the gains obtained by scaling up the number of devices. We introduce Ladder Residual, a simple architectural modification applicable to all residual-based","authors_text":"Ben Athiwaratkun, Jonathan Ragan-Kelley, Jue Wang, Mayank Mishra, Muru Zhang, Shuaiwen Leon Song, Tri Dao, William Brandon, Yoon Kim, Zhongzhu Zhou","cross_cats":["cs.CL","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T17:06:30Z","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06589","kind":"arxiv","version":5},"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:f2a5760f2e5d3c587ce271cd38c12ee7699a92989837c17cb7731f740fae7688","target":"record","created_at":"2026-07-05T11:24:12Z","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":"e99aa1cd8c245f0ea8b4888e3476b82b9ce925ca8218363fbb03e6441197ee21","cross_cats_sorted":["cs.CL","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T17:06:30Z","title_canon_sha256":"5c8632ad6e4918920dd9f0671be888426f33eb3e25a3d96ee4a0a4c10b024aea"},"schema_version":"1.0","source":{"id":"2501.06589","kind":"arxiv","version":5}},"canonical_sha256":"c73808c360fc77f603744910b3ed8faa0396346407aff1d37b969020be0b9b9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c73808c360fc77f603744910b3ed8faa0396346407aff1d37b969020be0b9b9d","first_computed_at":"2026-07-05T11:24:12.550086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:12.550086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfn8Wh+kJAxaKyuONRcTGmQm2Kq91Y9RQKrAR4qu/kVTloJVviUogk62Zl0xe90YxV+z5kZZALgmw6IKmUrnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:12.550654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06589","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2a5760f2e5d3c587ce271cd38c12ee7699a92989837c17cb7731f740fae7688","sha256:57a02b24863b64d2c1bb0cf3c7c28e7a5749d6b7507ed9c3dabd7d6d487010c1"],"state_sha256":"243856b8d945caea1e73d1a0c8ba81833adc279b5e830ecec2678bc3559ed527"}