{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SLOQYERK24JWE3YJNJ5HQEU5OZ","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":"82f1ae514c88363647c8b000e1faf3386dd97387ef611a4b2cb6612222c207a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T21:47:57Z","title_canon_sha256":"c867a888aaa20b33c3f81dcef656f7e7d6d711d081f3b8ef5284ba319f5335e0"},"schema_version":"1.0","source":{"id":"2407.14679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14679","created_at":"2026-07-05T09:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14679v2","created_at":"2026-07-05T09:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14679","created_at":"2026-07-05T09:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"SLOQYERK24JW","created_at":"2026-07-05T09:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"SLOQYERK24JWE3YJ","created_at":"2026-07-05T09:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"SLOQYERK","created_at":"2026-07-05T09:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:205dd0b7ededcf38d7708df8b475458a5bead71a5f58e31091f2b7e82ffe7cab","target":"graph","created_at":"2026-07-05T09:30:49Z","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/2407.14679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and then re-training it with a fraction (<3%) of the original training data can be a suitable alternative to repeated, full retraining. To this end, we develop a set of practical and effective compression best practices for LLMs that combine depth, width, attention and MLP pruning with knowledge distillation-based retraining; we arrive at these best practices throu","authors_text":"Bryan Catanzaro, Jan Kautz, Marcin Chochowski, Mohammad Shoeybi, Mostofa Patwary, Pavlo Molchanov, Raviraj Joshi, Saurav Muralidharan, Sharath Turuvekere Sreenivas","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T21:47:57Z","title":"Compact Language Models via Pruning and Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14679","kind":"arxiv","version":2},"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:fad6aeb9be37f28dea997eb82f7f37d376eadc27199eab6c1ba9dc273655682a","target":"record","created_at":"2026-07-05T09:30:49Z","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":"82f1ae514c88363647c8b000e1faf3386dd97387ef611a4b2cb6612222c207a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T21:47:57Z","title_canon_sha256":"c867a888aaa20b33c3f81dcef656f7e7d6d711d081f3b8ef5284ba319f5335e0"},"schema_version":"1.0","source":{"id":"2407.14679","kind":"arxiv","version":2}},"canonical_sha256":"92dd0c122ad713626f096a7a78129d7671e678d3b3bb4b3ad61802b1d364326b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92dd0c122ad713626f096a7a78129d7671e678d3b3bb4b3ad61802b1d364326b","first_computed_at":"2026-07-05T09:30:49.436523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:49.436523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qARTv8XZoC1KEd/S0XmzbM/7WaCAUDp5bgpOtDL6ZKhuwKve0wKFGBGwWJRsNIXP9LtoZQ5zCHqGr+VD8GZqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:49.437017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fad6aeb9be37f28dea997eb82f7f37d376eadc27199eab6c1ba9dc273655682a","sha256:205dd0b7ededcf38d7708df8b475458a5bead71a5f58e31091f2b7e82ffe7cab"],"state_sha256":"6c50e90f4221b531b39f07975972f81aff0768e21783a4e544b7b57e99825d16"}