{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2WXA7UBH567NHS2LWFKAD4NFB","short_pith_number":"pith:M2WXA7UB","schema_version":"1.0","canonical_sha256":"66ad707e813f7df69e5a5d8aa00f8d2870ede2a72f4ea84476bd296336b7a49c","source":{"kind":"arxiv","id":"2401.04585","version":3},"attestation_state":"computed","paper":{"title":"EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianquan Li, Junrui Xiao, Mengjuan Chen, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2024-01-09T14:42:49Z","abstract_excerpt":"Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce model complexity, and post-training quantization (PTQ), which does not require fine-tuning, is highly promising for compressing and accelerating diffusion models. Unfortunately, we find that due to the highly dynamic activations, existing PTQ methods suffer from distribution mismatch issues at both calibration sample level and reconstruction output level, whic"},"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":"2401.04585","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T14:42:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a9e9c973c2bb8301a6a0f088d892d094ede18686f46392f799d22cf98549944","abstract_canon_sha256":"bbfab3deb0cf6fab8e37aecc73cd70e58ef8e5e79c2431762f7fef1024091210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:00.257614Z","signature_b64":"00U76dh5IDpRRaCDkj+hQw7K07kly8IYfC1lFRmzjgbaL/u2o6aKblBWBcl7gd8//GgFA18Sqpdc6Fit+4PuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ad707e813f7df69e5a5d8aa00f8d2870ede2a72f4ea84476bd296336b7a49c","last_reissued_at":"2026-07-05T11:25:00.257176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:00.257176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianquan Li, Junrui Xiao, Mengjuan Chen, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2024-01-09T14:42:49Z","abstract_excerpt":"Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce model complexity, and post-training quantization (PTQ), which does not require fine-tuning, is highly promising for compressing and accelerating diffusion models. Unfortunately, we find that due to the highly dynamic activations, existing PTQ methods suffer from distribution mismatch issues at both calibration sample level and reconstruction output level, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04585","kind":"arxiv","version":3},"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/2401.04585/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":"2401.04585","created_at":"2026-07-05T11:25:00.257224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04585v3","created_at":"2026-07-05T11:25:00.257224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04585","created_at":"2026-07-05T11:25:00.257224+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2WXA7UBH567","created_at":"2026-07-05T11:25:00.257224+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2WXA7UBH567NHS2","created_at":"2026-07-05T11:25:00.257224+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2WXA7UB","created_at":"2026-07-05T11:25:00.257224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22011","citing_title":"Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB","json":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB.json","graph_json":"https://pith.science/api/pith-number/M2WXA7UBH567NHS2LWFKAD4NFB/graph.json","events_json":"https://pith.science/api/pith-number/M2WXA7UBH567NHS2LWFKAD4NFB/events.json","paper":"https://pith.science/paper/M2WXA7UB"},"agent_actions":{"view_html":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB","download_json":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB.json","view_paper":"https://pith.science/paper/M2WXA7UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04585&json=true","fetch_graph":"https://pith.science/api/pith-number/M2WXA7UBH567NHS2LWFKAD4NFB/graph.json","fetch_events":"https://pith.science/api/pith-number/M2WXA7UBH567NHS2LWFKAD4NFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB/action/storage_attestation","attest_author":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB/action/author_attestation","sign_citation":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB/action/citation_signature","submit_replication":"https://pith.science/pith/M2WXA7UBH567NHS2LWFKAD4NFB/action/replication_record"}},"created_at":"2026-07-05T11:25:00.257224+00:00","updated_at":"2026-07-05T11:25:00.257224+00:00"}