{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EVCIHUNAHUED2ZRMZCKKTM2TWF","short_pith_number":"pith:EVCIHUNA","schema_version":"1.0","canonical_sha256":"254483d1a03d083d662cc894a9b353b179e586b0ca08cddcffab0a1ffb4661a2","source":{"kind":"arxiv","id":"2302.04867","version":4},"attestation_state":"computed","paper":{"title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jie Zhou, Jiwen Lu, Lujia Bai, Wenliang Zhao, Yongming Rao","submitted_at":"2023-02-09T18:59:48Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have demonstrated a very promising ability in high-resolution image synthesis. However, sampling from a pre-trained DPM is time-consuming due to the multiple evaluations of the denoising network, making it more and more important to accelerate the sampling of DPMs. Despite recent progress in designing fast samplers, existing methods still cannot generate satisfying images in many applications where fewer steps (e.g., $<$10) are favored. In this paper, we develop a unified corrector (UniC) that can be applied after any existing DPM sampler to increase the o"},"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":"2302.04867","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T18:59:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0fb0fe491a099c19920093f330a493427233d6fecc82622c641787d4094da0f6","abstract_canon_sha256":"4e3decbfa01e88040baf0e8d924bdbc29e3742a65b0c718c8d3fb118aa9bc1d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:39.304166Z","signature_b64":"QURV+eh8g3eW+EpXWB43hIlAxhj5g+8UoMZkRyhAx+AfCPmO6YXZVQzkRHgIeb+c+zD5lM7LusF0eOT8O+JmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"254483d1a03d083d662cc894a9b353b179e586b0ca08cddcffab0a1ffb4661a2","last_reissued_at":"2026-07-05T07:01:39.303644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:39.303644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jie Zhou, Jiwen Lu, Lujia Bai, Wenliang Zhao, Yongming Rao","submitted_at":"2023-02-09T18:59:48Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have demonstrated a very promising ability in high-resolution image synthesis. However, sampling from a pre-trained DPM is time-consuming due to the multiple evaluations of the denoising network, making it more and more important to accelerate the sampling of DPMs. Despite recent progress in designing fast samplers, existing methods still cannot generate satisfying images in many applications where fewer steps (e.g., $<$10) are favored. In this paper, we develop a unified corrector (UniC) that can be applied after any existing DPM sampler to increase the o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04867","kind":"arxiv","version":4},"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/2302.04867/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":"2302.04867","created_at":"2026-07-05T07:01:39.303715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04867v4","created_at":"2026-07-05T07:01:39.303715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04867","created_at":"2026-07-05T07:01:39.303715+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVCIHUNAHUED","created_at":"2026-07-05T07:01:39.303715+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVCIHUNAHUED2ZRM","created_at":"2026-07-05T07:01:39.303715+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVCIHUNA","created_at":"2026-07-05T07:01:39.303715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2304.09479","citing_title":"DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14189","citing_title":"Improved Techniques for Training Consistency Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12116","citing_title":"Neural CDEs as Correctors for Learned Time Series Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13592","citing_title":"Image Diffusion Preview with Consistency Solver","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26244","citing_title":"MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12668","citing_title":"OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08329","citing_title":"DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF","json":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF.json","graph_json":"https://pith.science/api/pith-number/EVCIHUNAHUED2ZRMZCKKTM2TWF/graph.json","events_json":"https://pith.science/api/pith-number/EVCIHUNAHUED2ZRMZCKKTM2TWF/events.json","paper":"https://pith.science/paper/EVCIHUNA"},"agent_actions":{"view_html":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF","download_json":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF.json","view_paper":"https://pith.science/paper/EVCIHUNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04867&json=true","fetch_graph":"https://pith.science/api/pith-number/EVCIHUNAHUED2ZRMZCKKTM2TWF/graph.json","fetch_events":"https://pith.science/api/pith-number/EVCIHUNAHUED2ZRMZCKKTM2TWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF/action/storage_attestation","attest_author":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF/action/author_attestation","sign_citation":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF/action/citation_signature","submit_replication":"https://pith.science/pith/EVCIHUNAHUED2ZRMZCKKTM2TWF/action/replication_record"}},"created_at":"2026-07-05T07:01:39.303715+00:00","updated_at":"2026-07-05T07:01:39.303715+00:00"}