{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5Z2V4HENCS7XYRF7XIKYKLLNJY","short_pith_number":"pith:5Z2V4HEN","schema_version":"1.0","canonical_sha256":"ee755e1c8d14bf7c44bfba15852d6d4e0328935fcb7fbc71e9915a284894c8b6","source":{"kind":"arxiv","id":"2403.19140","version":2},"attestation_state":"computed","paper":{"title":"QNCD: Quantization Noise Correction for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengjie Zang, Huanpeng Chu, Kun Yuan, Wei Wu","submitted_at":"2024-03-28T04:24:56Z","abstract_excerpt":"Diffusion models have revolutionized image synthesis, setting new benchmarks in quality and creativity. However, their widespread adoption is hindered by the intensive computation required during the iterative denoising process. Post-training quantization (PTQ) presents a solution to accelerate sampling, aibeit at the expense of sample quality, extremely in low-bit settings. Addressing this, our study introduces a unified Quantization Noise Correction Scheme (QNCD), aimed at minishing quantization noise throughout the sampling process. We identify two primary quantization challenges: intra and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.19140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T04:24:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d6438aba1718a6660b020d8740c846c584fe87b1e81198be670a919f2df9512","abstract_canon_sha256":"a7d9242ff82189e1828aa533929170d977477bb6e9f5390c611d2f7592ee5eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:24.329491Z","signature_b64":"IPykbwrWgbWh7oJxGTq2e1jfLTHSOH0Rivx2H6RGOH7UQea/pDm50Su04FQA2P/KeUlLI+F5kEAfO3BoVx7PCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee755e1c8d14bf7c44bfba15852d6d4e0328935fcb7fbc71e9915a284894c8b6","last_reissued_at":"2026-07-05T09:08:24.328967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:24.328967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QNCD: Quantization Noise Correction for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengjie Zang, Huanpeng Chu, Kun Yuan, Wei Wu","submitted_at":"2024-03-28T04:24:56Z","abstract_excerpt":"Diffusion models have revolutionized image synthesis, setting new benchmarks in quality and creativity. However, their widespread adoption is hindered by the intensive computation required during the iterative denoising process. Post-training quantization (PTQ) presents a solution to accelerate sampling, aibeit at the expense of sample quality, extremely in low-bit settings. Addressing this, our study introduces a unified Quantization Noise Correction Scheme (QNCD), aimed at minishing quantization noise throughout the sampling process. We identify two primary quantization challenges: intra and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19140","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/2403.19140/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.19140","created_at":"2026-07-05T09:08:24.329031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19140v2","created_at":"2026-07-05T09:08:24.329031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19140","created_at":"2026-07-05T09:08:24.329031+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z2V4HENCS7X","created_at":"2026-07-05T09:08:24.329031+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z2V4HENCS7XYRF7","created_at":"2026-07-05T09:08:24.329031+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z2V4HEN","created_at":"2026-07-05T09:08:24.329031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14908","citing_title":"CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY","json":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY.json","graph_json":"https://pith.science/api/pith-number/5Z2V4HENCS7XYRF7XIKYKLLNJY/graph.json","events_json":"https://pith.science/api/pith-number/5Z2V4HENCS7XYRF7XIKYKLLNJY/events.json","paper":"https://pith.science/paper/5Z2V4HEN"},"agent_actions":{"view_html":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY","download_json":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY.json","view_paper":"https://pith.science/paper/5Z2V4HEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19140&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z2V4HENCS7XYRF7XIKYKLLNJY/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z2V4HENCS7XYRF7XIKYKLLNJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY/action/storage_attestation","attest_author":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY/action/author_attestation","sign_citation":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY/action/citation_signature","submit_replication":"https://pith.science/pith/5Z2V4HENCS7XYRF7XIKYKLLNJY/action/replication_record"}},"created_at":"2026-07-05T09:08:24.329031+00:00","updated_at":"2026-07-05T09:08:24.329031+00:00"}