{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZ5KO2DBMT7TA5B4BBHEQ7L4NU","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":"ae5d18b547e621ec0b9aae9c6ee5f79ac23ffe4824b94ab20ec33ac2065e18d3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T07:45:22Z","title_canon_sha256":"e32faae417e6e91cc1b1163ff790c03e2f5ab79af89ec3091641450284781414"},"schema_version":"1.0","source":{"id":"2402.14866","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14866","created_at":"2026-07-05T08:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14866v2","created_at":"2026-07-05T08:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14866","created_at":"2026-07-05T08:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"PZ5KO2DBMT7T","created_at":"2026-07-05T08:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"PZ5KO2DBMT7TA5B4","created_at":"2026-07-05T08:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"PZ5KO2DB","created_at":"2026-07-05T08:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:97fe4803a70689f0296f0d20b3fdb3123b68316b2d393531d84942a20812f421","target":"graph","created_at":"2026-07-05T08:08:21Z","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/2402.14866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have greatly advanced the natural language processing paradigm. However, the high computational load and huge model sizes pose a grand challenge for deployment on edge devices. To this end, we propose APTQ (Attention-aware Post-Training Mixed-Precision Quantization) for LLMs, which considers not only the second-order information of each layer's weights, but also, for the first time, the nonlinear effect of attention outputs on the entire model. We leverage the Hessian trace as a sensitivity metric for mixed-precision quantization, ensuring an informed precision red","authors_text":"Hantao Huang, Hao Yu, Hong Huang, Ngai Wong, Yupeng Su, Ziyi Guan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T07:45:22Z","title":"APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14866","kind":"arxiv","version":2},"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":"sha256:5bda7ee557353055ab5187c9a41187b3445a4272a772bfad7f55d2ede83a1ec7","target":"record","created_at":"2026-07-05T08:08:21Z","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":"ae5d18b547e621ec0b9aae9c6ee5f79ac23ffe4824b94ab20ec33ac2065e18d3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T07:45:22Z","title_canon_sha256":"e32faae417e6e91cc1b1163ff790c03e2f5ab79af89ec3091641450284781414"},"schema_version":"1.0","source":{"id":"2402.14866","kind":"arxiv","version":2}},"canonical_sha256":"7e7aa7686164ff30743c084e487d7c6d02f3259f8997a801a230a2ed25f96c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e7aa7686164ff30743c084e487d7c6d02f3259f8997a801a230a2ed25f96c7a","first_computed_at":"2026-07-05T08:08:21.000796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:21.000796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/UMSZxy5Zo3W9jHwkB79OwYCK3CHIEpX+Xt4xEMh5M7sHPDsg26+istLf76KVTwEQtcofNHgjAPTi32UUmrRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:21.001285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14866","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bda7ee557353055ab5187c9a41187b3445a4272a772bfad7f55d2ede83a1ec7","sha256:97fe4803a70689f0296f0d20b3fdb3123b68316b2d393531d84942a20812f421"],"state_sha256":"0e6d2c25d9a7a74f55930e15421e2bbe59abd2b8bc750dae9ad1daf5bded801c"}