{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFGC6MXMPJDEMP7VSBMLZCS6MM","short_pith_number":"pith:RFGC6MXM","schema_version":"1.0","canonical_sha256":"894c2f32ec7a46463ff59058bc8a5e631133638fd62176550770f353c3779c0f","source":{"kind":"arxiv","id":"2407.01521","version":3},"attestation_state":"computed","paper":{"title":"Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Bingliang Zhang, Chenlin Meng, Julius Berner, Wenda Chu, Yang Song","submitted_at":"2024-07-01T17:59:23Z","abstract_excerpt":"Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifical"},"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":"2407.01521","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T17:59:23Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5303bca396e3ee3eac7c3903b953382142484fe4ae111fb98b2841ade57f6259","abstract_canon_sha256":"31d38fc2b6cb228de927dc79a82c86e3b71c89a21fea851bb8bac2f4ab931c06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:40.535761Z","signature_b64":"z/vtAsYV3A7hRpz2+XHevdPTSfR6oXYfFPz9sUKYRpevP14hj5Kgsc3ZBbpKEtC1M/QQPlNiB2fiqUTQLeHuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894c2f32ec7a46463ff59058bc8a5e631133638fd62176550770f353c3779c0f","last_reissued_at":"2026-07-05T11:54:40.535153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:40.535153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Bingliang Zhang, Chenlin Meng, Julius Berner, Wenda Chu, Yang Song","submitted_at":"2024-07-01T17:59:23Z","abstract_excerpt":"Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01521","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/2407.01521/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":"2407.01521","created_at":"2026-07-05T11:54:40.535222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01521v3","created_at":"2026-07-05T11:54:40.535222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01521","created_at":"2026-07-05T11:54:40.535222+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFGC6MXMPJDE","created_at":"2026-07-05T11:54:40.535222+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFGC6MXMPJDEMP7V","created_at":"2026-07-05T11:54:40.535222+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFGC6MXM","created_at":"2026-07-05T11:54:40.535222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06624","citing_title":"Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17353","citing_title":"Dual Ascent Diffusion for Inverse Problems","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07150","citing_title":"FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04189","citing_title":"Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solvers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05520","citing_title":"Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM","json":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM.json","graph_json":"https://pith.science/api/pith-number/RFGC6MXMPJDEMP7VSBMLZCS6MM/graph.json","events_json":"https://pith.science/api/pith-number/RFGC6MXMPJDEMP7VSBMLZCS6MM/events.json","paper":"https://pith.science/paper/RFGC6MXM"},"agent_actions":{"view_html":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM","download_json":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM.json","view_paper":"https://pith.science/paper/RFGC6MXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01521&json=true","fetch_graph":"https://pith.science/api/pith-number/RFGC6MXMPJDEMP7VSBMLZCS6MM/graph.json","fetch_events":"https://pith.science/api/pith-number/RFGC6MXMPJDEMP7VSBMLZCS6MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM/action/storage_attestation","attest_author":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM/action/author_attestation","sign_citation":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM/action/citation_signature","submit_replication":"https://pith.science/pith/RFGC6MXMPJDEMP7VSBMLZCS6MM/action/replication_record"}},"created_at":"2026-07-05T11:54:40.535222+00:00","updated_at":"2026-07-05T11:54:40.535222+00:00"}