{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FNIKXE2PMVMVJFU2KSXDVONDCD","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":"b5369134005290f1e1761bfe8b39732518f7c887861cb906563b99873ecf83bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T13:28:15Z","title_canon_sha256":"117225284ea0b8405df07d2f16de42fcb0fe41ffe9749942021ebd8c0044f16f"},"schema_version":"1.0","source":{"id":"2412.17560","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17560","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17560v4","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17560","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"FNIKXE2PMVMV","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"FNIKXE2PMVMVJFU2","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"FNIKXE2P","created_at":"2026-07-05T11:43:59Z"}],"graph_snapshots":[{"event_id":"sha256:7567d39dfbaf45d127dbac75ddede32e65e61faec31df9d152d2aee0cd0364b9","target":"graph","created_at":"2026-07-05T11:43:59Z","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/2412.17560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper presents Group Quantization and Sparse Acceleration (GQSA), a novel compression technique tailored for LLMs. Traditional methods typically focus exclusively on either quantization or sparsification, but relying on a single strategy often results in significant performance loss at high compression rates. In contrast, GQSA integrates quantization and sparsification in a tightly coupled manner, leveraging GPU-friendly structured group sparsity and quantization for efficient acceler","authors_text":"Chao Zeng, Fangmin Chen, Lean Fu, Shu Yang, Songwei Liu, Xing Mei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T13:28:15Z","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17560","kind":"arxiv","version":4},"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":"sha256:6066303c6a203a59a8f7f67a39b8aa950736e8fbeae0e7d890545106ec82d1a9","target":"record","created_at":"2026-07-05T11:43:59Z","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":"b5369134005290f1e1761bfe8b39732518f7c887861cb906563b99873ecf83bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T13:28:15Z","title_canon_sha256":"117225284ea0b8405df07d2f16de42fcb0fe41ffe9749942021ebd8c0044f16f"},"schema_version":"1.0","source":{"id":"2412.17560","kind":"arxiv","version":4}},"canonical_sha256":"2b50ab934f655954969a54ae3ab9a310cc6da34d21fcdf884b5ab600c9ae2a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b50ab934f655954969a54ae3ab9a310cc6da34d21fcdf884b5ab600c9ae2a38","first_computed_at":"2026-07-05T11:43:59.987570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:59.987570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9NbpSEVmap7Q7jPmNIsRD7f1c42DEN8oc6E0CBz+ciB57QrHikeeiRmq7hkps3m4OzQj/UswuFScBOdxz3NZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:59.988058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17560","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6066303c6a203a59a8f7f67a39b8aa950736e8fbeae0e7d890545106ec82d1a9","sha256:7567d39dfbaf45d127dbac75ddede32e65e61faec31df9d152d2aee0cd0364b9"],"state_sha256":"8e53aaf63fc7bdb84efa3e5817e904b1dd6af20dae0a906cd9045f036f258fe9"}