{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:45M2N62OPEAO6OJHA2TMFH3R2E","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":"fae982f4303cb4d29ce2311c788b3ab9cf7289c3c14f7e05582f7dbcc0e24a29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T17:59:29Z","title_canon_sha256":"200f670f58b397f45de0035841a74a798b51469366f9491054a348de7e6c1398"},"schema_version":"1.0","source":{"id":"2407.10969","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10969","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10969v3","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10969","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"45M2N62OPEAO","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_16","alias_value":"45M2N62OPEAO6OJH","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_8","alias_value":"45M2N62O","created_at":"2026-07-05T08:47:54Z"}],"graph_snapshots":[{"event_id":"sha256:11964ae11fdcbbf5496a544cfe2b18206d07fd8468afc2b2702e35cf3030f584","target":"graph","created_at":"2026-07-05T08:47:54Z","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/2407.10969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is achieved by applying top-K sparsification to the activations and the straight-through-estimator to the training. We also introduce Block Q-Sparse for batch training and inference. The key results from this work are, (1) Q-Sparse can achieve results comparable to those of baseline LLMs while being much more efficient at inference time; (2) We present an inferen","authors_text":"Furu Wei, Hongyu Wang, Ruiping Wang, Shuming Ma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T17:59:29Z","title":"Q-Sparse: All Large Language Models can be Fully Sparsely-Activated"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10969","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":"sha256:53f069f9dc8d961c4e64ff060a3a909c1dad1bdc632f77359b241da6735fea67","target":"record","created_at":"2026-07-05T08:47:54Z","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":"fae982f4303cb4d29ce2311c788b3ab9cf7289c3c14f7e05582f7dbcc0e24a29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T17:59:29Z","title_canon_sha256":"200f670f58b397f45de0035841a74a798b51469366f9491054a348de7e6c1398"},"schema_version":"1.0","source":{"id":"2407.10969","kind":"arxiv","version":3}},"canonical_sha256":"e759a6fb4e7900ef392706a6c29f71d1192d8adb2e6ab2eef5ce025e7b60b3dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e759a6fb4e7900ef392706a6c29f71d1192d8adb2e6ab2eef5ce025e7b60b3dc","first_computed_at":"2026-07-05T08:47:54.623213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:54.623213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IqrFS/aUCC9dmTORvTOYF6uXXLmnXoZrm5BZNdmwqb8YJZH7MLscWliIWWvz5dvNwsGUsXebrcOeHp4GL1JOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:54.623672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10969","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53f069f9dc8d961c4e64ff060a3a909c1dad1bdc632f77359b241da6735fea67","sha256:11964ae11fdcbbf5496a544cfe2b18206d07fd8468afc2b2702e35cf3030f584"],"state_sha256":"57b1b1e9b1a6c894b14e868f1eeec712b8eff95a12ee530abb691a93276894d8"}