{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZUH35DDMASZKRRCRC5FOSK7WK","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":"239aa33acb08aa6ca0f864374a278707f3eeec86ac7e6eb863da4b2e58023f36","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T17:56:06Z","title_canon_sha256":"56a4a4a67b6587cbdd8a19f8fbe8c92b22a0fe49dbf9cc57b0b87b3c39f628ef"},"schema_version":"1.0","source":{"id":"2404.01365","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01365","created_at":"2026-07-05T08:54:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01365v3","created_at":"2026-07-05T08:54:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01365","created_at":"2026-07-05T08:54:09Z"},{"alias_kind":"pith_short_12","alias_value":"AZUH35DDMASZ","created_at":"2026-07-05T08:54:09Z"},{"alias_kind":"pith_short_16","alias_value":"AZUH35DDMASZKRRC","created_at":"2026-07-05T08:54:09Z"},{"alias_kind":"pith_short_8","alias_value":"AZUH35DD","created_at":"2026-07-05T08:54:09Z"}],"graph_snapshots":[{"event_id":"sha256:728c41796aada2320f1154c14f7c04c9c462a845d0d4fdbfb39dd60782d181b3","target":"graph","created_at":"2026-07-05T08:54:09Z","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/2404.01365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of transformer-based large language models (LLMs), they have been applied to many fields due to their remarkable utility, but this comes at a considerable computational cost at deployment. Fortunately, some methods such as pruning or constructing a mixture of experts (MoE) aim at exploiting sparsity in transformer feedforward (FF) blocks to gain boosts in speed and reduction in memory requirements. However, these techniques can be very costly and inflexible in practice, as they often require training or are restricted to specific types of architectures. To address this, we","authors_text":"Beidi Chen, Harry Dong, Yuejie Chi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T17:56:06Z","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01365","kind":"arxiv","version":3},"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":"sha256:36e864bfa8f3561abb87698f1dc514e080e69dbe526b573a26c9351755c79c78","target":"record","created_at":"2026-07-05T08:54:09Z","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":"239aa33acb08aa6ca0f864374a278707f3eeec86ac7e6eb863da4b2e58023f36","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T17:56:06Z","title_canon_sha256":"56a4a4a67b6587cbdd8a19f8fbe8c92b22a0fe49dbf9cc57b0b87b3c39f628ef"},"schema_version":"1.0","source":{"id":"2404.01365","kind":"arxiv","version":3}},"canonical_sha256":"06687df463602595462288ba57495fb290e2e627c782cff9448e5c38837da709","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06687df463602595462288ba57495fb290e2e627c782cff9448e5c38837da709","first_computed_at":"2026-07-05T08:54:09.280728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:09.280728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E3SNOIhf9BWrx2b3oLrIVqncAuJiHRUvzXJEHEzW/t++rULvyrcT93nOauAc5DuaSRHGgAFXQTnMvFnWk/hcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:09.281201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01365","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e864bfa8f3561abb87698f1dc514e080e69dbe526b573a26c9351755c79c78","sha256:728c41796aada2320f1154c14f7c04c9c462a845d0d4fdbfb39dd60782d181b3"],"state_sha256":"5996811fac9d76612ddf9a3a125a79f34e6b40e5a486e63e426b1da34d0f1d1e"}