{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F6CZUWXOEAXQNX4V77PXSCMTQW","short_pith_number":"pith:F6CZUWXO","schema_version":"1.0","canonical_sha256":"2f859a5aee202f06df95ffdf79099385a6c34c481b9d6e485ad7a5dfeba1b521","source":{"kind":"arxiv","id":"2407.14041","version":2},"attestation_state":"computed","paper":{"title":"Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyi Xiong, Lichen Bai, Zeke Xie, Zipeng Qi","submitted_at":"2024-07-19T05:36:22Z","abstract_excerpt":"Diffusion models that can generate high-quality data from randomly sampled Gaussian noises have become the mainstream generative method in both academia and industry. Are randomly sampled Gaussian noises equally good for diffusion models? While a large body of works tried to understand and improve diffusion models, previous works overlooked the possibility to select or optimize the sampled noise the possibility of selecting or optimizing sampled noises for improving diffusion models. In this paper, we mainly made three contributions. First, we report that not all noises are created equally for"},"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":"2407.14041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T05:36:22Z","cross_cats_sorted":[],"title_canon_sha256":"b1301af9190055a0ec1cb72a49507d6f802e7c07242b5b56bc804f8439e5a14a","abstract_canon_sha256":"98abcd97f542db24ee58edfaa7cafba8e4d03aef0b141b759354bcfd6006398d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:10.711416Z","signature_b64":"g3X3KI2XiRiv1KF+592gJUVzxlF1BINVdoExidkH1cKSRx6/lM5VlinmvFo3iJSGtpzMfY7OlvaH9RTclfBzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f859a5aee202f06df95ffdf79099385a6c34c481b9d6e485ad7a5dfeba1b521","last_reissued_at":"2026-07-05T08:49:10.710937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:10.710937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyi Xiong, Lichen Bai, Zeke Xie, Zipeng Qi","submitted_at":"2024-07-19T05:36:22Z","abstract_excerpt":"Diffusion models that can generate high-quality data from randomly sampled Gaussian noises have become the mainstream generative method in both academia and industry. Are randomly sampled Gaussian noises equally good for diffusion models? While a large body of works tried to understand and improve diffusion models, previous works overlooked the possibility to select or optimize the sampled noise the possibility of selecting or optimizing sampled noises for improving diffusion models. In this paper, we mainly made three contributions. First, we report that not all noises are created equally for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14041","kind":"arxiv","version":2},"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/2407.14041/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":"2407.14041","created_at":"2026-07-05T08:49:10.710996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14041v2","created_at":"2026-07-05T08:49:10.710996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14041","created_at":"2026-07-05T08:49:10.710996+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6CZUWXOEAXQ","created_at":"2026-07-05T08:49:10.710996+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6CZUWXOEAXQNX4V","created_at":"2026-07-05T08:49:10.710996+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6CZUWXO","created_at":"2026-07-05T08:49:10.710996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29319","citing_title":"FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25547","citing_title":"TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30991","citing_title":"Parallel Tempering Initial Sampling in Inference-Time Reward Alignment","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15115","citing_title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09732","citing_title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19532","citing_title":"Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15757","citing_title":"You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11311","citing_title":"Couple to Control: Joint Initial Noise Design in Diffusion Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08144","citing_title":"NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08054","citing_title":"Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW","json":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW.json","graph_json":"https://pith.science/api/pith-number/F6CZUWXOEAXQNX4V77PXSCMTQW/graph.json","events_json":"https://pith.science/api/pith-number/F6CZUWXOEAXQNX4V77PXSCMTQW/events.json","paper":"https://pith.science/paper/F6CZUWXO"},"agent_actions":{"view_html":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW","download_json":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW.json","view_paper":"https://pith.science/paper/F6CZUWXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14041&json=true","fetch_graph":"https://pith.science/api/pith-number/F6CZUWXOEAXQNX4V77PXSCMTQW/graph.json","fetch_events":"https://pith.science/api/pith-number/F6CZUWXOEAXQNX4V77PXSCMTQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW/action/storage_attestation","attest_author":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW/action/author_attestation","sign_citation":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW/action/citation_signature","submit_replication":"https://pith.science/pith/F6CZUWXOEAXQNX4V77PXSCMTQW/action/replication_record"}},"created_at":"2026-07-05T08:49:10.710996+00:00","updated_at":"2026-07-05T08:49:10.710996+00:00"}