{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EII7SGHCXYLXCE6XMTRSKGU257","short_pith_number":"pith:EII7SGHC","schema_version":"1.0","canonical_sha256":"2211f918e2be177113d764e3251a9aefe858c427836927a4ea121dea92852fbd","source":{"kind":"arxiv","id":"2502.01189","version":4},"attestation_state":"computed","paper":{"title":"Compressed Image Generation with Denoising Diffusion Codebook Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IT","eess.SP","math.IT"],"primary_cat":"eess.IV","authors_text":"Guy Ohayon, Hila Manor, Michael Elad, Tomer Michaeli","submitted_at":"2025-02-03T09:25:57Z","abstract_excerpt":"We present a novel generative approach based on Denoising Diffusion Models (DDMs), which produces high-quality image samples along with their losslessly compressed bit-stream representations. This is obtained by replacing the standard Gaussian noise sampling in the reverse diffusion with a selection of noise samples from pre-defined codebooks of fixed iid Gaussian vectors. Surprisingly, we find that our method, termed Denoising Diffusion Codebook Model (DDCM), retains sample quality and diversity of standard DDMs, even for extremely small codebooks. We leverage DDCM and pick the noises from 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":"2502.01189","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-02-03T09:25:57Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","eess.SP","math.IT"],"title_canon_sha256":"1cabcdf3f1389b2f67549914a2b9d0761bfaa710d61ae2c20f8eefc548095422","abstract_canon_sha256":"2a9c30283d61fe278fabe29443fc9782752c635f7c986c2997ad48f22f42fd06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:00.752427Z","signature_b64":"vD8oeEDGLMvXsN4zLHM+2QIaUIrnql3vgkTjAhYI/XAcizKFSlcuMD1dmhf//A6N+aytkv5yo6+vsr6aXSN/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2211f918e2be177113d764e3251a9aefe858c427836927a4ea121dea92852fbd","last_reissued_at":"2026-07-05T11:44:00.751952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:00.751952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressed Image Generation with Denoising Diffusion Codebook Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IT","eess.SP","math.IT"],"primary_cat":"eess.IV","authors_text":"Guy Ohayon, Hila Manor, Michael Elad, Tomer Michaeli","submitted_at":"2025-02-03T09:25:57Z","abstract_excerpt":"We present a novel generative approach based on Denoising Diffusion Models (DDMs), which produces high-quality image samples along with their losslessly compressed bit-stream representations. This is obtained by replacing the standard Gaussian noise sampling in the reverse diffusion with a selection of noise samples from pre-defined codebooks of fixed iid Gaussian vectors. Surprisingly, we find that our method, termed Denoising Diffusion Codebook Model (DDCM), retains sample quality and diversity of standard DDMs, even for extremely small codebooks. We leverage DDCM and pick the noises from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01189","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/2502.01189/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":"2502.01189","created_at":"2026-07-05T11:44:00.752008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01189v4","created_at":"2026-07-05T11:44:00.752008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01189","created_at":"2026-07-05T11:44:00.752008+00:00"},{"alias_kind":"pith_short_12","alias_value":"EII7SGHCXYLX","created_at":"2026-07-05T11:44:00.752008+00:00"},{"alias_kind":"pith_short_16","alias_value":"EII7SGHCXYLXCE6X","created_at":"2026-07-05T11:44:00.752008+00:00"},{"alias_kind":"pith_short_8","alias_value":"EII7SGHC","created_at":"2026-07-05T11:44:00.752008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10450","citing_title":"Few-step Generative Models as Lossy Compression","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257","json":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257.json","graph_json":"https://pith.science/api/pith-number/EII7SGHCXYLXCE6XMTRSKGU257/graph.json","events_json":"https://pith.science/api/pith-number/EII7SGHCXYLXCE6XMTRSKGU257/events.json","paper":"https://pith.science/paper/EII7SGHC"},"agent_actions":{"view_html":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257","download_json":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257.json","view_paper":"https://pith.science/paper/EII7SGHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01189&json=true","fetch_graph":"https://pith.science/api/pith-number/EII7SGHCXYLXCE6XMTRSKGU257/graph.json","fetch_events":"https://pith.science/api/pith-number/EII7SGHCXYLXCE6XMTRSKGU257/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257/action/storage_attestation","attest_author":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257/action/author_attestation","sign_citation":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257/action/citation_signature","submit_replication":"https://pith.science/pith/EII7SGHCXYLXCE6XMTRSKGU257/action/replication_record"}},"created_at":"2026-07-05T11:44:00.752008+00:00","updated_at":"2026-07-05T11:44:00.752008+00:00"}