{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P4GUNJ2ZIR5ZBHVODMM6GOWR3C","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":"50f37e9d3db00d86cd07b4cf00b81c2534d66b83b28026a6d8e96608985305f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T16:03:32Z","title_canon_sha256":"93ad91e60e417f78d87d738cb280baf48b2bc6835befc7ed5312b8dba6851fec"},"schema_version":"1.0","source":{"id":"2405.03594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03594","created_at":"2026-07-05T08:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03594v1","created_at":"2026-07-05T08:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03594","created_at":"2026-07-05T08:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"P4GUNJ2ZIR5Z","created_at":"2026-07-05T08:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"P4GUNJ2ZIR5ZBHVO","created_at":"2026-07-05T08:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"P4GUNJ2Z","created_at":"2026-07-05T08:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:5c72b8746b5f37fe6ceb4034b8464444637c5f06a9a38ebfb4458cbcf6a43fc6","target":"graph","created_at":"2026-07-05T08:16:04Z","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/2405.03594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that achieve full accuracy recovery for fine-tuning tasks at up to 70% sparsity. We achieve this for the LLaMA-2 7B model by combining the SparseGPT one-shot pruning method and sparse pretraining of those models on a subset of the SlimPajama dataset mixed with a Python subset of The Stack dataset. We exhibit training acceleration due to sparsity on Cerebras CS-3 chi","authors_text":"Abhay Gupta, Abhinav Agarwalla, Alexandre Marques, Dan Alistarh, Eldar Kurtic, Kevin Leong, Mahmoud Salem, Mark Kurtz, Michael Goin, Sean Lie, Shubhra Pandit, Tuan Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T16:03:32Z","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03594","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:e6cb4661df58855647ecd15b5e514f4b8f9e182220c5ed3ae98f85d62dde8f0f","target":"record","created_at":"2026-07-05T08:16:04Z","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":"50f37e9d3db00d86cd07b4cf00b81c2534d66b83b28026a6d8e96608985305f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-06T16:03:32Z","title_canon_sha256":"93ad91e60e417f78d87d738cb280baf48b2bc6835befc7ed5312b8dba6851fec"},"schema_version":"1.0","source":{"id":"2405.03594","kind":"arxiv","version":1}},"canonical_sha256":"7f0d46a759447b909eae1b19e33ad1d8866f4fbaa12d466eddc6814c83ed3ab3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f0d46a759447b909eae1b19e33ad1d8866f4fbaa12d466eddc6814c83ed3ab3","first_computed_at":"2026-07-05T08:16:04.960763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:04.960763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5q4mAm2zh8suOqgI+6IXeHr3bPbrIfVFLRa27VMNMfEwZokThAggfZx82Y3SIMMXz925g++0iDDmtpq8ztQLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:04.961251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6cb4661df58855647ecd15b5e514f4b8f9e182220c5ed3ae98f85d62dde8f0f","sha256:5c72b8746b5f37fe6ceb4034b8464444637c5f06a9a38ebfb4458cbcf6a43fc6"],"state_sha256":"4d0cd1076ea1d5bdb87096e461c70e671e52594e805f5bc6d270f69a7e9b3f80"}