{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JZPGHDHF6JLFZFC4MDZAPLGYD","short_pith_number":"pith:3JZPGHDH","schema_version":"1.0","canonical_sha256":"da72f31c672f92b2e4a2e307903d66c0e0362a175dc1938bc1c575fba96c5bb4","source":{"kind":"arxiv","id":"2407.11162","version":1},"attestation_state":"computed","paper":{"title":"Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yifei Wang","submitted_at":"2024-07-15T18:33:20Z","abstract_excerpt":"Diffusion models (DMs) have emerged as powerful generative models for solving inverse problems, offering a good approximation of prior distributions of real-world image data. Typically, diffusion models rely on large-scale clean signals to accurately learn the score functions of ground truth clean image distributions. However, such a requirement for large amounts of clean data is often impractical in real-world applications, especially in fields where data samples are expensive to obtain. To address this limitation, in this work, we introduce \\emph{FlowDiff}, a novel joint training paradigm th"},"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":"2407.11162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T18:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"f38fdf5c9ff09790590c9cf1345b64ef46c28a29013bcc5753c54503b7266e2e","abstract_canon_sha256":"b41a3299bd5ba1a2305117f372a39fce3973bb3e89c0568a5fcf0cb2df8ef807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:19.846686Z","signature_b64":"gIIRTXkvyG+85Gw1DNNipXr9eCwZsCqiohYEc4yaSt+Ti7iCJbk7Le8845P9Z05ecLpVBBbpHK59oTPp06ZdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da72f31c672f92b2e4a2e307903d66c0e0362a175dc1938bc1c575fba96c5bb4","last_reissued_at":"2026-07-05T08:44:19.846180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:19.846180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yifei Wang","submitted_at":"2024-07-15T18:33:20Z","abstract_excerpt":"Diffusion models (DMs) have emerged as powerful generative models for solving inverse problems, offering a good approximation of prior distributions of real-world image data. Typically, diffusion models rely on large-scale clean signals to accurately learn the score functions of ground truth clean image distributions. However, such a requirement for large amounts of clean data is often impractical in real-world applications, especially in fields where data samples are expensive to obtain. To address this limitation, in this work, we introduce \\emph{FlowDiff}, a novel joint training paradigm th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11162","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/2407.11162/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":"2407.11162","created_at":"2026-07-05T08:44:19.846238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11162v1","created_at":"2026-07-05T08:44:19.846238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11162","created_at":"2026-07-05T08:44:19.846238+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JZPGHDHF6JL","created_at":"2026-07-05T08:44:19.846238+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JZPGHDHF6JLFZFC","created_at":"2026-07-05T08:44:19.846238+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JZPGHDH","created_at":"2026-07-05T08:44:19.846238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD","json":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD.json","graph_json":"https://pith.science/api/pith-number/3JZPGHDHF6JLFZFC4MDZAPLGYD/graph.json","events_json":"https://pith.science/api/pith-number/3JZPGHDHF6JLFZFC4MDZAPLGYD/events.json","paper":"https://pith.science/paper/3JZPGHDH"},"agent_actions":{"view_html":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD","download_json":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD.json","view_paper":"https://pith.science/paper/3JZPGHDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11162&json=true","fetch_graph":"https://pith.science/api/pith-number/3JZPGHDHF6JLFZFC4MDZAPLGYD/graph.json","fetch_events":"https://pith.science/api/pith-number/3JZPGHDHF6JLFZFC4MDZAPLGYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD/action/storage_attestation","attest_author":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD/action/author_attestation","sign_citation":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD/action/citation_signature","submit_replication":"https://pith.science/pith/3JZPGHDHF6JLFZFC4MDZAPLGYD/action/replication_record"}},"created_at":"2026-07-05T08:44:19.846238+00:00","updated_at":"2026-07-05T08:44:19.846238+00:00"}