{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OJVTGUDZOXMTOZ5HZE5GWSDNKU","short_pith_number":"pith:OJVTGUDZ","canonical_record":{"source":{"id":"2406.00800","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T17:00:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e51caf049a25511f401e184a3583028c7a716befe41e56aba775b0482bb9a290","abstract_canon_sha256":"ab181a02aa941b0ad3ab68930f51ab1fc33b2da54665633778a81892795c7d1e"},"schema_version":"1.0"},"canonical_sha256":"726b33507975d93767a7c93a6b486d552f8e2871f6b917c11627bf8b76d704ff","source":{"kind":"arxiv","id":"2406.00800","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00800","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00800v2","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00800","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"OJVTGUDZOXMT","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"OJVTGUDZOXMTOZ5H","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"OJVTGUDZ","created_at":"2026-07-05T09:21:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OJVTGUDZOXMTOZ5HZE5GWSDNKU","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00800","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T17:00:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e51caf049a25511f401e184a3583028c7a716befe41e56aba775b0482bb9a290","abstract_canon_sha256":"ab181a02aa941b0ad3ab68930f51ab1fc33b2da54665633778a81892795c7d1e"},"schema_version":"1.0"},"canonical_sha256":"726b33507975d93767a7c93a6b486d552f8e2871f6b917c11627bf8b76d704ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:44.894815Z","signature_b64":"/owL15+xVoTD5IkUYBbABg+zzFx57DfUcGgH5VeBgUJpLinyTFw20lC+1N+AtEQseSqeiIkubGIAfZIb6Gh+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"726b33507975d93767a7c93a6b486d552f8e2871f6b917c11627bf8b76d704ff","last_reissued_at":"2026-07-05T09:21:44.894325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:44.894325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00800","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfiNlLDy2Jg0itpRCQl9JgRF+n1/JjEnN1icTS8gSCjl37XovOyLJm+fM2yaIpOU5xE35TuJG6vCAYP7QZfbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:17:48.313876Z"},"content_sha256":"ff465260473e5b45182ae8cbf556a2df13e901ba2a07f972c168d8a2b0a9f22d","schema_version":"1.0","event_id":"sha256:ff465260473e5b45182ae8cbf556a2df13e901ba2a07f972c168d8a2b0a9f22d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OJVTGUDZOXMTOZ5HZE5GWSDNKU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aozhong Zhang, Naigang Wang, Penghang Yin, Xin Li, Yanxia Deng, Zi Yang","submitted_at":"2024-06-02T17:00:02Z","abstract_excerpt":"In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For each linear layer, we adjust the pre-trained floating-point weights by solving an $\\ell_\\infty$-regularized optimization problem. This process greatly diminishes the maximum magnitude of the weights and smooths out outliers, while preserving the layer's output. The preprocessed weights are centered more towards zero, which facilitates the subsequent quantization process. To implement MagR, we address the $\\ell_\\inft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00800","kind":"arxiv","version":2},"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/2406.00800/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":"2026-07-05T09:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJwOUaGAqpNklDhMxYLw/QgLmm0D6v7MJFINapNkN5FdpOOnXYGs6jKpILit1D/8aKnDQcScgoeCu//nN2SMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:17:48.314378Z"},"content_sha256":"e760daaad8c83367c77d43d3021a50ed3791fec5e7e9bf65c8cb51d453659bf0","schema_version":"1.0","event_id":"sha256:e760daaad8c83367c77d43d3021a50ed3791fec5e7e9bf65c8cb51d453659bf0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/bundle.json","state_url":"https://pith.science/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/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":"2026-08-11T02:17:48Z","links":{"resolver":"https://pith.science/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU","bundle":"https://pith.science/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/bundle.json","state":"https://pith.science/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJVTGUDZOXMTOZ5HZE5GWSDNKU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJVTGUDZOXMTOZ5HZE5GWSDNKU","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":"ab181a02aa941b0ad3ab68930f51ab1fc33b2da54665633778a81892795c7d1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T17:00:02Z","title_canon_sha256":"e51caf049a25511f401e184a3583028c7a716befe41e56aba775b0482bb9a290"},"schema_version":"1.0","source":{"id":"2406.00800","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00800","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00800v2","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00800","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"OJVTGUDZOXMT","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"OJVTGUDZOXMTOZ5H","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"OJVTGUDZ","created_at":"2026-07-05T09:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:e760daaad8c83367c77d43d3021a50ed3791fec5e7e9bf65c8cb51d453659bf0","target":"graph","created_at":"2026-07-05T09:21:44Z","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/2406.00800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For each linear layer, we adjust the pre-trained floating-point weights by solving an $\\ell_\\infty$-regularized optimization problem. This process greatly diminishes the maximum magnitude of the weights and smooths out outliers, while preserving the layer's output. The preprocessed weights are centered more towards zero, which facilitates the subsequent quantization process. To implement MagR, we address the $\\ell_\\inft","authors_text":"Aozhong Zhang, Naigang Wang, Penghang Yin, Xin Li, Yanxia Deng, Zi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T17:00:02Z","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00800","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:ff465260473e5b45182ae8cbf556a2df13e901ba2a07f972c168d8a2b0a9f22d","target":"record","created_at":"2026-07-05T09:21:44Z","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":"ab181a02aa941b0ad3ab68930f51ab1fc33b2da54665633778a81892795c7d1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T17:00:02Z","title_canon_sha256":"e51caf049a25511f401e184a3583028c7a716befe41e56aba775b0482bb9a290"},"schema_version":"1.0","source":{"id":"2406.00800","kind":"arxiv","version":2}},"canonical_sha256":"726b33507975d93767a7c93a6b486d552f8e2871f6b917c11627bf8b76d704ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"726b33507975d93767a7c93a6b486d552f8e2871f6b917c11627bf8b76d704ff","first_computed_at":"2026-07-05T09:21:44.894325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:44.894325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/owL15+xVoTD5IkUYBbABg+zzFx57DfUcGgH5VeBgUJpLinyTFw20lC+1N+AtEQseSqeiIkubGIAfZIb6Gh+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:44.894815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00800","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff465260473e5b45182ae8cbf556a2df13e901ba2a07f972c168d8a2b0a9f22d","sha256:e760daaad8c83367c77d43d3021a50ed3791fec5e7e9bf65c8cb51d453659bf0"],"state_sha256":"7ba0479462329310cfe7c5bab11d2b58f219baac1b9a7d156c4ca013283fbd56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCWnblll3agVLOaZG29iTdUR56SnfuODAtRcZrZyUbuFNeRxqJoFgVQ2MLZ2cjWDm6PYcd+21Ijnv3bmK9nUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:17:48.319888Z","bundle_sha256":"de06758ca5421511a6b426820d66def5bfb0576da6be8710ae22ed3720cb6832"}}