{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SB7CTHUACDZUPEW2OQYZO5SEO6","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":"a47336d76e9713ae3bbc33aedbf493b22b1c5b06b0a394173e7417af12eef5ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T10:35:30Z","title_canon_sha256":"b501f725ae55aed6742c37cded894d4b2e2f3c5249ba1e8e6587cfae27256152"},"schema_version":"1.0","source":{"id":"2409.11057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11057","created_at":"2026-07-05T09:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11057v1","created_at":"2026-07-05T09:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11057","created_at":"2026-07-05T09:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"SB7CTHUACDZU","created_at":"2026-07-05T09:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"SB7CTHUACDZUPEW2","created_at":"2026-07-05T09:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"SB7CTHUA","created_at":"2026-07-05T09:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:83ab35dbd7cdc5fbd37197bcb78ec236694405543dd187d716edf7267535e7cc","target":"graph","created_at":"2026-07-05T09:08:01Z","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/2409.11057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The bottleneck associated with the key-value(KV) cache presents a significant challenge during the inference processes of large language models. While depth pruning accelerates inference, it requires extensive recovery training, which can take up to two weeks. On the other hand, width pruning retains much of the performance but offers slight speed gains. To tackle these challenges, we propose KVPruner to improve model efficiency while maintaining performance. Our method uses global perplexity-based analysis to determine the importance ratio for each block and provides multiple strategies to pr","authors_text":"Bo Lv, Quan Zhou, Xuanang Ding, Yan Wang, Zeming Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T10:35:30Z","title":"KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11057","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":"sha256:0a8b73e94abc59f77f7e66940d03cd16547b8a9eb8834898a6de660fb5817b11","target":"record","created_at":"2026-07-05T09:08:01Z","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":"a47336d76e9713ae3bbc33aedbf493b22b1c5b06b0a394173e7417af12eef5ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T10:35:30Z","title_canon_sha256":"b501f725ae55aed6742c37cded894d4b2e2f3c5249ba1e8e6587cfae27256152"},"schema_version":"1.0","source":{"id":"2409.11057","kind":"arxiv","version":1}},"canonical_sha256":"907e299e8010f34792da743197764477947045862968ee879c1dd996620c7087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"907e299e8010f34792da743197764477947045862968ee879c1dd996620c7087","first_computed_at":"2026-07-05T09:08:01.198101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:01.198101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2DGYdJgFxcKQCy1qwzzHZ0obmhcoZay2Ypyg5p4nCZ0CFCMHbhvoOu2HK1wh3qmU7yCAAlirl9oty+qIPhkyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:01.198599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a8b73e94abc59f77f7e66940d03cd16547b8a9eb8834898a6de660fb5817b11","sha256:83ab35dbd7cdc5fbd37197bcb78ec236694405543dd187d716edf7267535e7cc"],"state_sha256":"5c43fc22834562663dc61552f7e2379134a4e93ca9a2a21d43da599a209c752e"}