{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZNWBM4BDS5ECJIDKAS5UTFFQLG","short_pith_number":"pith:ZNWBM4BD","canonical_record":{"source":{"id":"2411.16158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T07:34:53Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"fb35a29a4d7a0c0efeafae0149c39e79e1d344e664e3e9b4aa08d4f26c394159","abstract_canon_sha256":"8009938b94d19ad87edf263b38f47fdc08574c320f37b89e285c431eab622a82"},"schema_version":"1.0"},"canonical_sha256":"cb6c167023974824a06a04bb4994b059b3bad1d24b75ee1249d4c5b9ae3c11e7","source":{"kind":"arxiv","id":"2411.16158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16158","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16158v1","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16158","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZNWBM4BDS5EC","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZNWBM4BDS5ECJIDK","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZNWBM4BD","created_at":"2026-07-05T09:40:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZNWBM4BDS5ECJIDKAS5UTFFQLG","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T07:34:53Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"fb35a29a4d7a0c0efeafae0149c39e79e1d344e664e3e9b4aa08d4f26c394159","abstract_canon_sha256":"8009938b94d19ad87edf263b38f47fdc08574c320f37b89e285c431eab622a82"},"schema_version":"1.0"},"canonical_sha256":"cb6c167023974824a06a04bb4994b059b3bad1d24b75ee1249d4c5b9ae3c11e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:05.332254Z","signature_b64":"z1fvsPOyVXYj2oXJeIqYlg7JugNX4rCp1ozgmSRroanHpKM4mhUWtEYL2fXGEkbVus5I+OVY8u8IMlq/SwI9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb6c167023974824a06a04bb4994b059b3bad1d24b75ee1249d4c5b9ae3c11e7","last_reissued_at":"2026-07-05T09:40:05.331812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:05.331812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16158","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s0YYJG3G9FMFC8+7Glhti50P62X5dO1VOO1GYDlJ2hAE6cxrbghYPtE80SJLiAI+qYc0Jql5qk1QjSgG9fW1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:08:09.433274Z"},"content_sha256":"212a08effc22ae4f3a6a2d1d4c790837bc15e5a174defd3974b646aff26840ee","schema_version":"1.0","event_id":"sha256:212a08effc22ae4f3a6a2d1d4c790837bc15e5a174defd3974b646aff26840ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZNWBM4BDS5ECJIDKAS5UTFFQLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MixPE: Quantization and Hardware Co-design for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.LG","authors_text":"Bei Yu, Hui-Ling Zhen, Lancheng Zou, Mingxuan Yuan, Mingzi Wang, Wulong Liu, Yu Zhang","submitted_at":"2024-11-25T07:34:53Z","abstract_excerpt":"Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a promising solution, and state-of-the-art quantization algorithms for LLMs introduce the need for mixed-precision matrix multiplication (mpGEMM), where lower-precision weights are multiplied with higher-precision activations. Despite its benefits, current hardware accelerators such as GPUs and TPUs lack native support for efficient mpGEMM, leading to inefficient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16158","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.16158/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLWgRXjQ6N2u5xW5KzyYU4mSe1Ja3PXQxV3kjoIVFykJA96tcFpfCiG+vKJT3WMREE2lpzeXsSK7j9+sG5j3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:08:09.433794Z"},"content_sha256":"f8a74fb1a63c0caeaad3229e763966ffef36e86becc109f6d12956d4e5b195fb","schema_version":"1.0","event_id":"sha256:f8a74fb1a63c0caeaad3229e763966ffef36e86becc109f6d12956d4e5b195fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/bundle.json","state_url":"https://pith.science/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T12:08:09Z","links":{"resolver":"https://pith.science/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG","bundle":"https://pith.science/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/bundle.json","state":"https://pith.science/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNWBM4BDS5ECJIDKAS5UTFFQLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZNWBM4BDS5ECJIDKAS5UTFFQLG","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":"8009938b94d19ad87edf263b38f47fdc08574c320f37b89e285c431eab622a82","cross_cats_sorted":["cs.AI","cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T07:34:53Z","title_canon_sha256":"fb35a29a4d7a0c0efeafae0149c39e79e1d344e664e3e9b4aa08d4f26c394159"},"schema_version":"1.0","source":{"id":"2411.16158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16158","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16158v1","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16158","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZNWBM4BDS5EC","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZNWBM4BDS5ECJIDK","created_at":"2026-07-05T09:40:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZNWBM4BD","created_at":"2026-07-05T09:40:05Z"}],"graph_snapshots":[{"event_id":"sha256:f8a74fb1a63c0caeaad3229e763966ffef36e86becc109f6d12956d4e5b195fb","target":"graph","created_at":"2026-07-05T09:40:05Z","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/2411.16158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a promising solution, and state-of-the-art quantization algorithms for LLMs introduce the need for mixed-precision matrix multiplication (mpGEMM), where lower-precision weights are multiplied with higher-precision activations. Despite its benefits, current hardware accelerators such as GPUs and TPUs lack native support for efficient mpGEMM, leading to inefficient","authors_text":"Bei Yu, Hui-Ling Zhen, Lancheng Zou, Mingxuan Yuan, Mingzi Wang, Wulong Liu, Yu Zhang","cross_cats":["cs.AI","cs.AR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T07:34:53Z","title":"MixPE: Quantization and Hardware Co-design for Efficient LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16158","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":"sha256:212a08effc22ae4f3a6a2d1d4c790837bc15e5a174defd3974b646aff26840ee","target":"record","created_at":"2026-07-05T09:40:05Z","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":"8009938b94d19ad87edf263b38f47fdc08574c320f37b89e285c431eab622a82","cross_cats_sorted":["cs.AI","cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T07:34:53Z","title_canon_sha256":"fb35a29a4d7a0c0efeafae0149c39e79e1d344e664e3e9b4aa08d4f26c394159"},"schema_version":"1.0","source":{"id":"2411.16158","kind":"arxiv","version":1}},"canonical_sha256":"cb6c167023974824a06a04bb4994b059b3bad1d24b75ee1249d4c5b9ae3c11e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb6c167023974824a06a04bb4994b059b3bad1d24b75ee1249d4c5b9ae3c11e7","first_computed_at":"2026-07-05T09:40:05.331812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:05.331812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1fvsPOyVXYj2oXJeIqYlg7JugNX4rCp1ozgmSRroanHpKM4mhUWtEYL2fXGEkbVus5I+OVY8u8IMlq/SwI9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:05.332254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:212a08effc22ae4f3a6a2d1d4c790837bc15e5a174defd3974b646aff26840ee","sha256:f8a74fb1a63c0caeaad3229e763966ffef36e86becc109f6d12956d4e5b195fb"],"state_sha256":"9b8976e57d45b614c52e8c785e3fdab7d680dea498805bd641a920f33445e6dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTARJPzGaX9bKCxzdZlYMGs+tcGo9JeeCxG7oU0IpoZh/pso2TXgOmYVon7Oe5ab6kFhl01qPpsicCQhwmJKCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:08:09.439603Z","bundle_sha256":"765dd20ff11ba9f8bd7f215af3544adffa465be4abac37f7bfb38e30f7af9faf"}}