{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2FPFM4RMVXQ6LZUH5B7F3RXWS","short_pith_number":"pith:O2FPFM4R","schema_version":"1.0","canonical_sha256":"768af2b391656f0f2f343f43f2ee37b49e39fb146cd33913a263bbcf2aeae88d","source":{"kind":"arxiv","id":"2411.09502","version":5},"attestation_state":"computed","paper":{"title":"Golden Noise for Diffusion Models: A Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Han, Lichen Bai, Shitong Shao, Shufei Zhang, Zeke Xie, Zhiqiang Xu, Zikai Zhou","submitted_at":"2024-11-14T15:13:13Z","abstract_excerpt":"Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment and higher human preference than others, we still lack a machine learning framework to obtain those golden noises. To learn golden noises for diffusion sampling, we mainly make three contributions in this paper. First, we identify a new concept termed the \\textit{noise prompt}, which aims at turning a random Gaussian noise into a golden noise by ad"},"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":"2411.09502","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T15:13:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1c3446f1ff98af8d6a3f5abf312948a23673f6e232f327c45d2c086c0ba600fb","abstract_canon_sha256":"f7beb410413a670ec9684ae124b0030df97f8b9d1934fc1dd469209d647207fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:25.403532Z","signature_b64":"daMsLm+7XVy9LF5VH3wd5eahFd1aYJEZHCnHD37kVAPCRq2jeD5lLo891JONcy54/+JbfoCJIKL5rXV5L4/fBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768af2b391656f0f2f343f43f2ee37b49e39fb146cd33913a263bbcf2aeae88d","last_reissued_at":"2026-07-05T11:38:25.402937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:25.402937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Golden Noise for Diffusion Models: A Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Han, Lichen Bai, Shitong Shao, Shufei Zhang, Zeke Xie, Zhiqiang Xu, Zikai Zhou","submitted_at":"2024-11-14T15:13:13Z","abstract_excerpt":"Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment and higher human preference than others, we still lack a machine learning framework to obtain those golden noises. To learn golden noises for diffusion sampling, we mainly make three contributions in this paper. First, we identify a new concept termed the \\textit{noise prompt}, which aims at turning a random Gaussian noise into a golden noise by ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09502","kind":"arxiv","version":5},"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/2411.09502/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":"2411.09502","created_at":"2026-07-05T11:38:25.403004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09502v5","created_at":"2026-07-05T11:38:25.403004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09502","created_at":"2026-07-05T11:38:25.403004+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2FPFM4RMVXQ","created_at":"2026-07-05T11:38:25.403004+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2FPFM4RMVXQ6LZU","created_at":"2026-07-05T11:38:25.403004+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2FPFM4R","created_at":"2026-07-05T11:38:25.403004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01743","citing_title":"InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09732","citing_title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06165","citing_title":"Reflective Flow Sampling Enhancement","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25314","citing_title":"Golden RPG: Confidence-Adaptive Region-Aware Noise for Compositional Text-to-Image Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS","json":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS.json","graph_json":"https://pith.science/api/pith-number/O2FPFM4RMVXQ6LZUH5B7F3RXWS/graph.json","events_json":"https://pith.science/api/pith-number/O2FPFM4RMVXQ6LZUH5B7F3RXWS/events.json","paper":"https://pith.science/paper/O2FPFM4R"},"agent_actions":{"view_html":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS","download_json":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS.json","view_paper":"https://pith.science/paper/O2FPFM4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09502&json=true","fetch_graph":"https://pith.science/api/pith-number/O2FPFM4RMVXQ6LZUH5B7F3RXWS/graph.json","fetch_events":"https://pith.science/api/pith-number/O2FPFM4RMVXQ6LZUH5B7F3RXWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS/action/storage_attestation","attest_author":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS/action/author_attestation","sign_citation":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS/action/citation_signature","submit_replication":"https://pith.science/pith/O2FPFM4RMVXQ6LZUH5B7F3RXWS/action/replication_record"}},"created_at":"2026-07-05T11:38:25.403004+00:00","updated_at":"2026-07-05T11:38:25.403004+00:00"}