{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DTIS3R4SNP2OKSIOHAAVEFI3GM","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":"4e6974c50d641a8935c4d44308c3f96bcbeea0f7e196a4efd9f9987f3a9d55f0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:45:51Z","title_canon_sha256":"7cd6f52e2b3613c7a51e6d5c6d257b1ceb412abdbde9d8bc4141c31b98d0d64b"},"schema_version":"1.0","source":{"id":"2402.03804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03804","created_at":"2026-07-05T07:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03804v1","created_at":"2026-07-05T07:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03804","created_at":"2026-07-05T07:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"DTIS3R4SNP2O","created_at":"2026-07-05T07:41:58Z"},{"alias_kind":"pith_short_16","alias_value":"DTIS3R4SNP2OKSIO","created_at":"2026-07-05T07:41:58Z"},{"alias_kind":"pith_short_8","alias_value":"DTIS3R4S","created_at":"2026-07-05T07:41:58Z"}],"graph_snapshots":[{"event_id":"sha256:209d982a5dc9abd295cff2fcbfce6baa1d955709f61bd65facfafce369a8583b","target":"graph","created_at":"2026-07-05T07:41:58Z","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/2402.03804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse computation offers a compelling solution for the inference of Large Language Models (LLMs) in low-resource scenarios by dynamically skipping the computation of inactive neurons. While traditional approaches focus on ReLU-based LLMs, leveraging zeros in activation values, we broaden the scope of sparse LLMs beyond zero activation values. We introduce a general method that defines neuron activation through neuron output magnitudes and a tailored magnitude threshold, demonstrating that non-ReLU LLMs also exhibit sparse activation. To find the most efficient activation function for sparse c","authors_text":"Chaojun Xiao, Chenyang Song, Guanghui Yu, Maosong Sun, Xu Han, Yankai Lin, Yixin Song, Zeyu Mi, Zhengyan Zhang, Zhiyuan Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:45:51Z","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03804","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":"sha256:1388ed6d610412c88fc3103aa69634e8c02e43adf02a885c4527245da844c22e","target":"record","created_at":"2026-07-05T07:41:58Z","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":"4e6974c50d641a8935c4d44308c3f96bcbeea0f7e196a4efd9f9987f3a9d55f0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T08:45:51Z","title_canon_sha256":"7cd6f52e2b3613c7a51e6d5c6d257b1ceb412abdbde9d8bc4141c31b98d0d64b"},"schema_version":"1.0","source":{"id":"2402.03804","kind":"arxiv","version":1}},"canonical_sha256":"1cd12dc7926bf4e5490e380152151b3319b8ee24b8a52b5083e69c6b7e046584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cd12dc7926bf4e5490e380152151b3319b8ee24b8a52b5083e69c6b7e046584","first_computed_at":"2026-07-05T07:41:58.982095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:58.982095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5pKCEjWf7uq/brjxYcRTJmdmvwqfxLH7HNNrboufHncC4TbIH+dxFU+HbeAQm4DvRzV523gpaCsIXxMrQKGUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:58.982458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1388ed6d610412c88fc3103aa69634e8c02e43adf02a885c4527245da844c22e","sha256:209d982a5dc9abd295cff2fcbfce6baa1d955709f61bd65facfafce369a8583b"],"state_sha256":"2460f528c3a719a280b4aeeac7bf4e7120ded753560b594c14b0dc6879f2ef2c"}