{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G5YKEWUEF5SEVUMEVAJR4TVIHU","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":"4d6db4a1386bff9e2b514743a5297628ca56c278a0b7471e8b8e1f31c0160913","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-26T02:37:41Z","title_canon_sha256":"5cb0e558a0200435ecb0622bed62f5d7fdbaf92e567e89a2fad1f83357ba4211"},"schema_version":"1.0","source":{"id":"2409.17481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17481","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17481v2","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17481","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"G5YKEWUEF5SE","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_16","alias_value":"G5YKEWUEF5SEVUME","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_8","alias_value":"G5YKEWUE","created_at":"2026-07-05T09:45:55Z"}],"graph_snapshots":[{"event_id":"sha256:2a38d3ea206cedcdc89bbfbce13f0f3b6902dc9eb2a259bc65747f7ce29e63b0","target":"graph","created_at":"2026-07-05T09:45:55Z","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/2409.17481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy. This work introduces MaskLLM, a learnable pruning method that establishes Semi-structured (or ``N:M'') Sparsity in LLMs, aimed at reducing computational overhead during inference. Instead of developing a new importance criterion, MaskLLM explicitly models N:M patterns as a learnable distribution through Gumbel Softmax sampling. This approach facilitates end-to-end training on large-scale datasets and offers two notable advantages: 1) High-quality Masks - our metho","authors_text":"Gongfan Fang, Greg Heinrich, Hongxu Yin, Jan Kautz, Jeff Pool, Pavlo Molchanov, Saurav Muralidharan, Xinchao Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-26T02:37:41Z","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17481","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:db3998e1b7f0ab47c9483bf45b092f2bd4fe6db8b226568282d7ee159508d0b0","target":"record","created_at":"2026-07-05T09:45:55Z","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":"4d6db4a1386bff9e2b514743a5297628ca56c278a0b7471e8b8e1f31c0160913","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-26T02:37:41Z","title_canon_sha256":"5cb0e558a0200435ecb0622bed62f5d7fdbaf92e567e89a2fad1f83357ba4211"},"schema_version":"1.0","source":{"id":"2409.17481","kind":"arxiv","version":2}},"canonical_sha256":"3770a25a842f644ad184a8131e4ea83d249a57ec9cb214e956b39232dbd8df1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3770a25a842f644ad184a8131e4ea83d249a57ec9cb214e956b39232dbd8df1e","first_computed_at":"2026-07-05T09:45:55.278361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:55.278361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQHvhYmNaz1pcrIz5SKANwm20Kmy0QQDasY8OoPLagOQdV55kfWUk2gCAo1zDV0m6ORK3HADvNRKsBtKBwx9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:55.278875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3998e1b7f0ab47c9483bf45b092f2bd4fe6db8b226568282d7ee159508d0b0","sha256:2a38d3ea206cedcdc89bbfbce13f0f3b6902dc9eb2a259bc65747f7ce29e63b0"],"state_sha256":"cdaf658dc32e5c06167a053e0544505c643b7695d500ab6a156737286646183d"}