{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J5X5264S22JOMXQRSKOPYEJ2ZI","short_pith_number":"pith:J5X5264S","canonical_record":{"source":{"id":"2506.07533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T08:16:24Z","cross_cats_sorted":[],"title_canon_sha256":"303325c930e76839c5a1ed1c3926d8ac878d5303271284ea5792fdb86cce9dfd","abstract_canon_sha256":"74cc58c52284e79bb84a47f3b360a0584278617ae83a2cfcc6292aa88199e6a1"},"schema_version":"1.0"},"canonical_sha256":"4f6fdd7b92d692e65e11929cfc113aca264b9666414e551019a821b53ac622a7","source":{"kind":"arxiv","id":"2506.07533","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07533","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07533v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07533","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"J5X5264S22JO","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"J5X5264S22JOMXQR","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"J5X5264S","created_at":"2026-07-05T11:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J5X5264S22JOMXQRSKOPYEJ2ZI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T08:16:24Z","cross_cats_sorted":[],"title_canon_sha256":"303325c930e76839c5a1ed1c3926d8ac878d5303271284ea5792fdb86cce9dfd","abstract_canon_sha256":"74cc58c52284e79bb84a47f3b360a0584278617ae83a2cfcc6292aa88199e6a1"},"schema_version":"1.0"},"canonical_sha256":"4f6fdd7b92d692e65e11929cfc113aca264b9666414e551019a821b53ac622a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.925806Z","signature_b64":"n1njeBO51b3LP+xM+ARyJ8z5RX64FZqAPEGhA3iUnrLrS0Gq0RptzTqZdAi5XS21QEGguzdFKWDbiffiT78IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f6fdd7b92d692e65e11929cfc113aca264b9666414e551019a821b53ac622a7","last_reissued_at":"2026-07-05T11:18:28.925296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.925296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07533","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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgmVYKBPW1zJTIu6buZ/fO2E7DQYckenFg3tng3P0VYcvsvx2imr3NtRxUmQKGPpRG6jAyfksJ7fy/XqAeU+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:19:59.840819Z"},"content_sha256":"879069738d7d916ab93c38552bf5ff2e2709ae81117feec5b4dcba61ca89c8b8","schema_version":"1.0","event_id":"sha256:879069738d7d916ab93c38552bf5ff2e2709ae81117feec5b4dcba61ca89c8b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J5X5264S22JOMXQRSKOPYEJ2ZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhang, HaoCheng Lu, Jianzong Wang, Jiguang Wan, Kai Lu, Wei Tao, Xiaoyang Qu","submitted_at":"2025-06-09T08:16:24Z","abstract_excerpt":"One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization methods cannot take both effectiveness and efficiency into account. In this paper, we propose MoQAE, a novel mixed-precision quantization method via mixture of quantization-aware experts. First, we view different quantization bit-width configurations as experts and use the traditional mixture of exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07533","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/2506.07533/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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFTMf/9qNVZDfsjY+NixpriTnanYJTTruJwpSMJVb/duCPe0uIUCvKeeM99hFQEnQWoSbqqNhcETGM0Rd4s2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:19:59.842360Z"},"content_sha256":"7c7298fbebf252f2e5a4fbcf39945542b2bd2b96283e9292e633ecd958095357","schema_version":"1.0","event_id":"sha256:7c7298fbebf252f2e5a4fbcf39945542b2bd2b96283e9292e633ecd958095357"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/bundle.json","state_url":"https://pith.science/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/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":"2026-08-19T07:19:59Z","links":{"resolver":"https://pith.science/pith/J5X5264S22JOMXQRSKOPYEJ2ZI","bundle":"https://pith.science/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/bundle.json","state":"https://pith.science/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5X5264S22JOMXQRSKOPYEJ2ZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5X5264S22JOMXQRSKOPYEJ2ZI","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":"74cc58c52284e79bb84a47f3b360a0584278617ae83a2cfcc6292aa88199e6a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T08:16:24Z","title_canon_sha256":"303325c930e76839c5a1ed1c3926d8ac878d5303271284ea5792fdb86cce9dfd"},"schema_version":"1.0","source":{"id":"2506.07533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07533","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07533v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07533","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"J5X5264S22JO","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"J5X5264S22JOMXQR","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"J5X5264S","created_at":"2026-07-05T11:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:7c7298fbebf252f2e5a4fbcf39945542b2bd2b96283e9292e633ecd958095357","target":"graph","created_at":"2026-07-05T11:18:28Z","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/2506.07533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization methods cannot take both effectiveness and efficiency into account. In this paper, we propose MoQAE, a novel mixed-precision quantization method via mixture of quantization-aware experts. First, we view different quantization bit-width configurations as experts and use the traditional mixture of exp","authors_text":"Bin Zhang, HaoCheng Lu, Jianzong Wang, Jiguang Wan, Kai Lu, Wei Tao, Xiaoyang Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T08:16:24Z","title":"MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07533","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":"sha256:879069738d7d916ab93c38552bf5ff2e2709ae81117feec5b4dcba61ca89c8b8","target":"record","created_at":"2026-07-05T11:18:28Z","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":"74cc58c52284e79bb84a47f3b360a0584278617ae83a2cfcc6292aa88199e6a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T08:16:24Z","title_canon_sha256":"303325c930e76839c5a1ed1c3926d8ac878d5303271284ea5792fdb86cce9dfd"},"schema_version":"1.0","source":{"id":"2506.07533","kind":"arxiv","version":1}},"canonical_sha256":"4f6fdd7b92d692e65e11929cfc113aca264b9666414e551019a821b53ac622a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f6fdd7b92d692e65e11929cfc113aca264b9666414e551019a821b53ac622a7","first_computed_at":"2026-07-05T11:18:28.925296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:28.925296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n1njeBO51b3LP+xM+ARyJ8z5RX64FZqAPEGhA3iUnrLrS0Gq0RptzTqZdAi5XS21QEGguzdFKWDbiffiT78IDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:28.925806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879069738d7d916ab93c38552bf5ff2e2709ae81117feec5b4dcba61ca89c8b8","sha256:7c7298fbebf252f2e5a4fbcf39945542b2bd2b96283e9292e633ecd958095357"],"state_sha256":"67895dad7d2f8c22030fd37e72a1a7f574c9b208ae39c83145091292429c9fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2BM6HWW97SvbQWi/kSU+nk9gfrMsr48P8w0Z+Rfy4kkWRX3uZIfnNC3mxZqRrFZ8/DW1FCo0yokWt4v4T8BCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:19:59.853953Z","bundle_sha256":"5535d1bbe136b20cc17f281d87ce36c25849aea8116b965a2db05ce600f8db6e"}}