{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TTDVUJLLAJC4EZ546FZKT5NJ6A","short_pith_number":"pith:TTDVUJLL","schema_version":"1.0","canonical_sha256":"9cc75a256b0245c267bcf172a9f5a9f03059569191622c92dadcd3ed753f30d4","source":{"kind":"arxiv","id":"2211.15736","version":3},"attestation_state":"computed","paper":{"title":"Post-training Quantization on Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingzhe Wu, Bin Xie, Yan Yan, Yuzhang Shang, Zhihang Yuan","submitted_at":"2022-11-28T19:33:39Z","abstract_excerpt":"Denoising diffusion (score-based) generative models have recently achieved significant accomplishments in generating realistic and diverse data. These approaches define a forward diffusion process for transforming data into noise and a backward denoising process for sampling data from noise. Unfortunately, the generation process of current denoising diffusion models is notoriously slow due to the lengthy iterative noise estimations, which rely on cumbersome neural networks. It prevents the diffusion models from being widely deployed, especially on edge devices. Previous works accelerate the ge"},"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":"2211.15736","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T19:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"3ef60cffc66ee464d176ce5a02f0686bb9e835a802f4d70973f6f48df94c5926","abstract_canon_sha256":"9d5c6a7c55ea061d680a499af82b633db2dac45f5f24aa50349722b822320752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:43.231994Z","signature_b64":"5sjzSlO9LryrsE8hUOi5jB1gZ5CJftt8vpBPFzZ4tgEuCnchaXZnPQLmRdchBNUSFOm/nT8Xqs/tSCcs72ILBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc75a256b0245c267bcf172a9f5a9f03059569191622c92dadcd3ed753f30d4","last_reissued_at":"2026-07-05T05:51:43.231547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:43.231547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-training Quantization on Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingzhe Wu, Bin Xie, Yan Yan, Yuzhang Shang, Zhihang Yuan","submitted_at":"2022-11-28T19:33:39Z","abstract_excerpt":"Denoising diffusion (score-based) generative models have recently achieved significant accomplishments in generating realistic and diverse data. These approaches define a forward diffusion process for transforming data into noise and a backward denoising process for sampling data from noise. Unfortunately, the generation process of current denoising diffusion models is notoriously slow due to the lengthy iterative noise estimations, which rely on cumbersome neural networks. It prevents the diffusion models from being widely deployed, especially on edge devices. Previous works accelerate the ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15736","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/2211.15736/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":"2211.15736","created_at":"2026-07-05T05:51:43.231605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15736v3","created_at":"2026-07-05T05:51:43.231605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15736","created_at":"2026-07-05T05:51:43.231605+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTDVUJLLAJC4","created_at":"2026-07-05T05:51:43.231605+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTDVUJLLAJC4EZ54","created_at":"2026-07-05T05:51:43.231605+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTDVUJLL","created_at":"2026-07-05T05:51:43.231605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06916","citing_title":"FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A","json":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A.json","graph_json":"https://pith.science/api/pith-number/TTDVUJLLAJC4EZ546FZKT5NJ6A/graph.json","events_json":"https://pith.science/api/pith-number/TTDVUJLLAJC4EZ546FZKT5NJ6A/events.json","paper":"https://pith.science/paper/TTDVUJLL"},"agent_actions":{"view_html":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A","download_json":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A.json","view_paper":"https://pith.science/paper/TTDVUJLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15736&json=true","fetch_graph":"https://pith.science/api/pith-number/TTDVUJLLAJC4EZ546FZKT5NJ6A/graph.json","fetch_events":"https://pith.science/api/pith-number/TTDVUJLLAJC4EZ546FZKT5NJ6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A/action/storage_attestation","attest_author":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A/action/author_attestation","sign_citation":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A/action/citation_signature","submit_replication":"https://pith.science/pith/TTDVUJLLAJC4EZ546FZKT5NJ6A/action/replication_record"}},"created_at":"2026-07-05T05:51:43.231605+00:00","updated_at":"2026-07-05T05:51:43.231605+00:00"}