{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WCHUSX74MHKDXI27ZLYQNAXYZH","short_pith_number":"pith:WCHUSX74","schema_version":"1.0","canonical_sha256":"b08f495ffc61d43ba35fcaf10682f8c9d95fd5a7edec5ad6838144855a68a86f","source":{"kind":"arxiv","id":"2201.06503","version":3},"attestation_state":"computed","paper":{"title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Zhang, Chongxuan Li, Fan Bao, Jun Zhu","submitted_at":"2022-01-17T16:28:12Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) represent a class of powerful generative models. Despite their success, the inference of DPMs is expensive since it generally needs to iterate over thousands of timesteps. A key problem in the inference is to estimate the variance in each timestep of the reverse process. In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w.r.t. its score function. Building upon it, we propose Analytic-DPM, a training-free inference framework that estimates the analytic"},"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":"2201.06503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T16:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"00ac24122395598d918a9a7a8ee9548af8e3ebf1124eeb300bd44fe56a8f604d","abstract_canon_sha256":"b2ec6ddafedfdb423903fab868beb564383154b8babfc08b6a23d86c2604a7f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:52.262521Z","signature_b64":"cOnL5Ddf/VtKlMhDI7q3ehODPQGtdeEiYRudLkMlPFm02uNAx4LoUbE9BqoXLm88U5M/nDQkf0R4nLBg9LZTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b08f495ffc61d43ba35fcaf10682f8c9d95fd5a7edec5ad6838144855a68a86f","last_reissued_at":"2026-07-05T04:19:52.262049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:52.262049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Zhang, Chongxuan Li, Fan Bao, Jun Zhu","submitted_at":"2022-01-17T16:28:12Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) represent a class of powerful generative models. Despite their success, the inference of DPMs is expensive since it generally needs to iterate over thousands of timesteps. A key problem in the inference is to estimate the variance in each timestep of the reverse process. In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w.r.t. its score function. Building upon it, we propose Analytic-DPM, a training-free inference framework that estimates the analytic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06503","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/2201.06503/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":"2201.06503","created_at":"2026-07-05T04:19:52.262101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06503v3","created_at":"2026-07-05T04:19:52.262101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06503","created_at":"2026-07-05T04:19:52.262101+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCHUSX74MHKD","created_at":"2026-07-05T04:19:52.262101+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCHUSX74MHKDXI27","created_at":"2026-07-05T04:19:52.262101+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCHUSX74","created_at":"2026-07-05T04:19:52.262101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23627","citing_title":"Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2304.09479","citing_title":"DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2505.02242","citing_title":"Sampling-Aware Quantization for Diffusion Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16879","citing_title":"Towards Generalized Image Manipulation Localization via Score-based Model","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16344","citing_title":"Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13592","citing_title":"Image Diffusion Preview with Consistency Solver","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26503","citing_title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00329","citing_title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH","json":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH.json","graph_json":"https://pith.science/api/pith-number/WCHUSX74MHKDXI27ZLYQNAXYZH/graph.json","events_json":"https://pith.science/api/pith-number/WCHUSX74MHKDXI27ZLYQNAXYZH/events.json","paper":"https://pith.science/paper/WCHUSX74"},"agent_actions":{"view_html":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH","download_json":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH.json","view_paper":"https://pith.science/paper/WCHUSX74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06503&json=true","fetch_graph":"https://pith.science/api/pith-number/WCHUSX74MHKDXI27ZLYQNAXYZH/graph.json","fetch_events":"https://pith.science/api/pith-number/WCHUSX74MHKDXI27ZLYQNAXYZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH/action/storage_attestation","attest_author":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH/action/author_attestation","sign_citation":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH/action/citation_signature","submit_replication":"https://pith.science/pith/WCHUSX74MHKDXI27ZLYQNAXYZH/action/replication_record"}},"created_at":"2026-07-05T04:19:52.262101+00:00","updated_at":"2026-07-05T04:19:52.262101+00:00"}