{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KWQPZJNO4GCSRFXBT4VSLWHOQ5","short_pith_number":"pith:KWQPZJNO","schema_version":"1.0","canonical_sha256":"55a0fca5aee1852896e19f2b25d8ee8772927942d276d9eca1be361a3ae4cc54","source":{"kind":"arxiv","id":"2209.06950","version":8},"attestation_state":"computed","paper":{"title":"Lossy Image Compression with Conditional Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Ruihan Yang, Stephan Mandt","submitted_at":"2022-09-14T21:53:27Z","abstract_excerpt":"This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to "},"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":"2209.06950","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-09-14T21:53:27Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"3d7059637f0c67091800e8e46c00fd4e7890f30d4513735bfdbc9b5f15205add","abstract_canon_sha256":"25cfd073b62c6fe18c6dcbd568bdd4f8ce30bebf08d99e716f80c6f38b49babc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:25.087996Z","signature_b64":"Ot0aMaaWx/eUOTUfd1ibJVVsO+FGrXJ0XLTzGHysb7jaV20Y5wzWqQw+8tUENl6AWnGB9wLsRERp/iQAwqY/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55a0fca5aee1852896e19f2b25d8ee8772927942d276d9eca1be361a3ae4cc54","last_reissued_at":"2026-07-05T07:29:25.087529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:25.087529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lossy Image Compression with Conditional Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Ruihan Yang, Stephan Mandt","submitted_at":"2022-09-14T21:53:27Z","abstract_excerpt":"This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06950","kind":"arxiv","version":8},"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/2209.06950/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":"2209.06950","created_at":"2026-07-05T07:29:25.087584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06950v8","created_at":"2026-07-05T07:29:25.087584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06950","created_at":"2026-07-05T07:29:25.087584+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWQPZJNO4GCS","created_at":"2026-07-05T07:29:25.087584+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWQPZJNO4GCSRFXB","created_at":"2026-07-05T07:29:25.087584+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWQPZJNO","created_at":"2026-07-05T07:29:25.087584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13366","citing_title":"Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26571","citing_title":"GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08633","citing_title":"Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5","json":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5.json","graph_json":"https://pith.science/api/pith-number/KWQPZJNO4GCSRFXBT4VSLWHOQ5/graph.json","events_json":"https://pith.science/api/pith-number/KWQPZJNO4GCSRFXBT4VSLWHOQ5/events.json","paper":"https://pith.science/paper/KWQPZJNO"},"agent_actions":{"view_html":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5","download_json":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5.json","view_paper":"https://pith.science/paper/KWQPZJNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06950&json=true","fetch_graph":"https://pith.science/api/pith-number/KWQPZJNO4GCSRFXBT4VSLWHOQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/KWQPZJNO4GCSRFXBT4VSLWHOQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5/action/storage_attestation","attest_author":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5/action/author_attestation","sign_citation":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5/action/citation_signature","submit_replication":"https://pith.science/pith/KWQPZJNO4GCSRFXBT4VSLWHOQ5/action/replication_record"}},"created_at":"2026-07-05T07:29:25.087584+00:00","updated_at":"2026-07-05T07:29:25.087584+00:00"}