{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VAP6Z7XDXHLTPWHHAEPILMNOWG","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":"decf9bbb4df982eb42ce0fc1a15608e975abf85af6550489f15c0e3075c5e4af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T20:50:08Z","title_canon_sha256":"f19ddcf0995c5b9ee2fa5fd7c41a5706243f5e5bbb9cb7456c88c4a04a9c3c0a"},"schema_version":"1.0","source":{"id":"2504.21174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21174","created_at":"2026-07-05T10:55:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21174v1","created_at":"2026-07-05T10:55:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21174","created_at":"2026-07-05T10:55:58Z"},{"alias_kind":"pith_short_12","alias_value":"VAP6Z7XDXHLT","created_at":"2026-07-05T10:55:58Z"},{"alias_kind":"pith_short_16","alias_value":"VAP6Z7XDXHLTPWHH","created_at":"2026-07-05T10:55:58Z"},{"alias_kind":"pith_short_8","alias_value":"VAP6Z7XD","created_at":"2026-07-05T10:55:58Z"}],"graph_snapshots":[{"event_id":"sha256:c379fc11c8da14ae11e31f9d71fea52bc6faa969a742da102f38f30cebdd593c","target":"graph","created_at":"2026-07-05T10:55:58Z","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/2504.21174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning drives a new wave in computing systems and triggers the automation of increasingly complex problems. In particular, Large Language Models (LLMs) have significantly advanced cognitive tasks, often matching or even surpassing human-level performance. However, their extensive parameters result in high computational costs and slow inference, posing challenges for deployment in resource-limited settings. Among the strategies to overcome the aforementioned challenges, pruning emerges as a successful mechanism since it reduces model size while maintaining predictive ability. In this pap","authors_text":"Anna Helena Reali Costa, Artur Jordao, Bruno Lopes Yamamoto, Edson Bollis, Leandro Giusti Mugnaini, Lucas Lauton de Alcantara, Lucas Pellicer, Victor Zacarias","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T20:50:08Z","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21174","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:b6f5617f8462cada981ce97b5e8c97ff92a14945756721a6b8c66489bb33df5c","target":"record","created_at":"2026-07-05T10:55:58Z","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":"decf9bbb4df982eb42ce0fc1a15608e975abf85af6550489f15c0e3075c5e4af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T20:50:08Z","title_canon_sha256":"f19ddcf0995c5b9ee2fa5fd7c41a5706243f5e5bbb9cb7456c88c4a04a9c3c0a"},"schema_version":"1.0","source":{"id":"2504.21174","kind":"arxiv","version":1}},"canonical_sha256":"a81fecfee3b9d737d8e7011e85b1aeb1970acfd2ad980548f06e91582549b0b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a81fecfee3b9d737d8e7011e85b1aeb1970acfd2ad980548f06e91582549b0b3","first_computed_at":"2026-07-05T10:55:58.430288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:58.430288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rz2yAB7QumAXD+nv752N8+jXeih8/zlzIqO3YVgKjcHMPGQkkQn5QVyCCHJ9wbHrPGRdbHouN3TDT5vqNRvtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:58.430770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f5617f8462cada981ce97b5e8c97ff92a14945756721a6b8c66489bb33df5c","sha256:c379fc11c8da14ae11e31f9d71fea52bc6faa969a742da102f38f30cebdd593c"],"state_sha256":"08908ffb8717a2100b25562ffdb8dd95aeaab1653cc932b1de4710a226c49f32"}