{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VBPHCONBR6XUYGXMQOIWT7R26M","short_pith_number":"pith:VBPHCONB","canonical_record":{"source":{"id":"2509.02512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T17:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"703f591fe75c22fc88704ed9d67c56282db04c95ecc95cf82b8706bb4490c4b7","abstract_canon_sha256":"6585e987056ecc01d78361b5255375ea495f0e8d3c8f0f28bb0006c376445050"},"schema_version":"1.0"},"canonical_sha256":"a85e7139a18faf4c1aec839169fe3af30abf9c3f05a73a1a4c1564cca20236c9","source":{"kind":"arxiv","id":"2509.02512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02512","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02512v1","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02512","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"VBPHCONBR6XU","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"VBPHCONBR6XUYGXM","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"VBPHCONB","created_at":"2026-07-05T12:03:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VBPHCONBR6XUYGXMQOIWT7R26M","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T17:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"703f591fe75c22fc88704ed9d67c56282db04c95ecc95cf82b8706bb4490c4b7","abstract_canon_sha256":"6585e987056ecc01d78361b5255375ea495f0e8d3c8f0f28bb0006c376445050"},"schema_version":"1.0"},"canonical_sha256":"a85e7139a18faf4c1aec839169fe3af30abf9c3f05a73a1a4c1564cca20236c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:39.888520Z","signature_b64":"HAb1UqlGWAfxBnk8NhBW8abntudmI53+ecy2WqHa9rX2w92f1qRDhzAOdgxDO8X9Gz1p5uTAiws8GTl/ZECJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85e7139a18faf4c1aec839169fe3af30abf9c3f05a73a1a4c1564cca20236c9","last_reissued_at":"2026-07-05T12:03:39.888020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:39.888020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02512","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":"2026-07-05T12:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ZhH0Wgs489P3bBd2dQhCFLFxs5jtB38qWv21pTBWKDnJLWtp1UQpg+LYG5wdDon2OaQGHngFRHz+H9/cYrHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:30:46.141973Z"},"content_sha256":"448dd41e9d98d96856aa08ff97600ce6baba7fa1f2da7fbb27ba4162e289da8e","schema_version":"1.0","event_id":"sha256:448dd41e9d98d96856aa08ff97600ce6baba7fa1f2da7fbb27ba4162e289da8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VBPHCONBR6XUYGXMQOIWT7R26M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoPEQ: Mixture of Mixed Precision Quantized Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Ye, Krishna Teja Chitty-Venkata, Murali Emani","submitted_at":"2025-09-02T17:04:59Z","abstract_excerpt":"Large Language and Vision Models using a Mixture-of-Experts (MoE) architecture pose significant challenges for deployment due to their computational and memory demands. Mixed Precision Quantization assigns different precisions to different layers of an LLM/VLM based on layer sensitivity and importance within the model. In this work, we propose a Post Training Quantization algorithm, MoPEQ, that assigns optimal bit width to each expert. Our method balances accuracy and model size by analyzing each expert's sensitivity using Hessian trace approximation instead of relying on the activation freque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02512","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/2509.02512/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":"2026-07-05T12:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QYzGGQ/2p3+2byRzK5mvzQtgl3Mp9rVcsa/omKZGLZvrTX+PmdGpgaqzL3zObRjXOEEZTtcI4DBrC/FLPVtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:30:46.142918Z"},"content_sha256":"d00abaf946e692b502e9c197bbae79cfa9e384e26806415c75b1918cb658dae6","schema_version":"1.0","event_id":"sha256:d00abaf946e692b502e9c197bbae79cfa9e384e26806415c75b1918cb658dae6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBPHCONBR6XUYGXMQOIWT7R26M/bundle.json","state_url":"https://pith.science/pith/VBPHCONBR6XUYGXMQOIWT7R26M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBPHCONBR6XUYGXMQOIWT7R26M/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":"2026-08-16T00:30:46Z","links":{"resolver":"https://pith.science/pith/VBPHCONBR6XUYGXMQOIWT7R26M","bundle":"https://pith.science/pith/VBPHCONBR6XUYGXMQOIWT7R26M/bundle.json","state":"https://pith.science/pith/VBPHCONBR6XUYGXMQOIWT7R26M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBPHCONBR6XUYGXMQOIWT7R26M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBPHCONBR6XUYGXMQOIWT7R26M","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":"6585e987056ecc01d78361b5255375ea495f0e8d3c8f0f28bb0006c376445050","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T17:04:59Z","title_canon_sha256":"703f591fe75c22fc88704ed9d67c56282db04c95ecc95cf82b8706bb4490c4b7"},"schema_version":"1.0","source":{"id":"2509.02512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02512","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02512v1","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02512","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"VBPHCONBR6XU","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"VBPHCONBR6XUYGXM","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"VBPHCONB","created_at":"2026-07-05T12:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:d00abaf946e692b502e9c197bbae79cfa9e384e26806415c75b1918cb658dae6","target":"graph","created_at":"2026-07-05T12:03:39Z","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/2509.02512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language and Vision Models using a Mixture-of-Experts (MoE) architecture pose significant challenges for deployment due to their computational and memory demands. Mixed Precision Quantization assigns different precisions to different layers of an LLM/VLM based on layer sensitivity and importance within the model. In this work, we propose a Post Training Quantization algorithm, MoPEQ, that assigns optimal bit width to each expert. Our method balances accuracy and model size by analyzing each expert's sensitivity using Hessian trace approximation instead of relying on the activation freque","authors_text":"Jie Ye, Krishna Teja Chitty-Venkata, Murali Emani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T17:04:59Z","title":"MoPEQ: Mixture of Mixed Precision Quantized Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02512","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":"sha256:448dd41e9d98d96856aa08ff97600ce6baba7fa1f2da7fbb27ba4162e289da8e","target":"record","created_at":"2026-07-05T12:03:39Z","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":"6585e987056ecc01d78361b5255375ea495f0e8d3c8f0f28bb0006c376445050","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T17:04:59Z","title_canon_sha256":"703f591fe75c22fc88704ed9d67c56282db04c95ecc95cf82b8706bb4490c4b7"},"schema_version":"1.0","source":{"id":"2509.02512","kind":"arxiv","version":1}},"canonical_sha256":"a85e7139a18faf4c1aec839169fe3af30abf9c3f05a73a1a4c1564cca20236c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a85e7139a18faf4c1aec839169fe3af30abf9c3f05a73a1a4c1564cca20236c9","first_computed_at":"2026-07-05T12:03:39.888020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:39.888020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAb1UqlGWAfxBnk8NhBW8abntudmI53+ecy2WqHa9rX2w92f1qRDhzAOdgxDO8X9Gz1p5uTAiws8GTl/ZECJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:39.888520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:448dd41e9d98d96856aa08ff97600ce6baba7fa1f2da7fbb27ba4162e289da8e","sha256:d00abaf946e692b502e9c197bbae79cfa9e384e26806415c75b1918cb658dae6"],"state_sha256":"0d0f6469cd8dacc74d809cd39f652b4cc05168306fae0f2c84999a3b74f42d58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D8Vb2MXVe60hru7xEdsukZbz0KTJf491XEmey2v0sBUaRLaI0zDpRAoRanlJSrfMAxA/g8uW9Cyj52vjvvwDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T00:30:46.149378Z","bundle_sha256":"d32a7c1b3e39c3dd3a469bde2049fe7d51e98dc09cdff16ef3e860142c37d299"}}