{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D2MUQIMGEAGZTERY3TSVDBBKA2","short_pith_number":"pith:D2MUQIMG","schema_version":"1.0","canonical_sha256":"1e99482186200d999238dce551842a06bba221f2257acb9b85733126bef65913","source":{"kind":"arxiv","id":"2407.03917","version":1},"attestation_state":"computed","paper":{"title":"Timestep-Aware Correction for Quantized Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Tian, Guang Dai, Haonan Lin, Jingdong Wang, Jun Chen, Yong Liu, Yuzhe Yao","submitted_at":"2024-07-04T13:22:31Z","abstract_excerpt":"Diffusion models have marked a significant breakthrough in the synthesis of semantically coherent images. However, their extensive noise estimation networks and the iterative generation process limit their wider application, particularly on resource-constrained platforms like mobile devices. Existing post-training quantization (PTQ) methods have managed to compress diffusion models to low precision. Nevertheless, due to the iterative nature of diffusion models, quantization errors tend to accumulate throughout the generation process. This accumulation of error becomes particularly problematic "},"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":"2407.03917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-04T13:22:31Z","cross_cats_sorted":[],"title_canon_sha256":"8628f231be458f057d02ae6da76c6c6a01b0e94cd127d2e85d838677bd1bd0f5","abstract_canon_sha256":"79aa7c2e63ad56821ac35a5f098d0fdaf4b9a0180693c44008294b8236832cef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:25.973621Z","signature_b64":"PWjJ3ZhIjrA8I40qFKhL8twN3swZ0bMxILtdyR2DqOKbsstr2DdlpAsEeenvgYLn3psUD076+dFpeeyjhqR+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e99482186200d999238dce551842a06bba221f2257acb9b85733126bef65913","last_reissued_at":"2026-07-05T08:40:25.973048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:25.973048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Timestep-Aware Correction for Quantized Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Tian, Guang Dai, Haonan Lin, Jingdong Wang, Jun Chen, Yong Liu, Yuzhe Yao","submitted_at":"2024-07-04T13:22:31Z","abstract_excerpt":"Diffusion models have marked a significant breakthrough in the synthesis of semantically coherent images. However, their extensive noise estimation networks and the iterative generation process limit their wider application, particularly on resource-constrained platforms like mobile devices. Existing post-training quantization (PTQ) methods have managed to compress diffusion models to low precision. Nevertheless, due to the iterative nature of diffusion models, quantization errors tend to accumulate throughout the generation process. This accumulation of error becomes particularly problematic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03917","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/2407.03917/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":"2407.03917","created_at":"2026-07-05T08:40:25.973118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03917v1","created_at":"2026-07-05T08:40:25.973118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03917","created_at":"2026-07-05T08:40:25.973118+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2MUQIMGEAGZ","created_at":"2026-07-05T08:40:25.973118+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2MUQIMGEAGZTERY","created_at":"2026-07-05T08:40:25.973118+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2MUQIMG","created_at":"2026-07-05T08:40:25.973118+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":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2","json":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2.json","graph_json":"https://pith.science/api/pith-number/D2MUQIMGEAGZTERY3TSVDBBKA2/graph.json","events_json":"https://pith.science/api/pith-number/D2MUQIMGEAGZTERY3TSVDBBKA2/events.json","paper":"https://pith.science/paper/D2MUQIMG"},"agent_actions":{"view_html":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2","download_json":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2.json","view_paper":"https://pith.science/paper/D2MUQIMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03917&json=true","fetch_graph":"https://pith.science/api/pith-number/D2MUQIMGEAGZTERY3TSVDBBKA2/graph.json","fetch_events":"https://pith.science/api/pith-number/D2MUQIMGEAGZTERY3TSVDBBKA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2/action/storage_attestation","attest_author":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2/action/author_attestation","sign_citation":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2/action/citation_signature","submit_replication":"https://pith.science/pith/D2MUQIMGEAGZTERY3TSVDBBKA2/action/replication_record"}},"created_at":"2026-07-05T08:40:25.973118+00:00","updated_at":"2026-07-05T08:40:25.973118+00:00"}