{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K3IQLLTSL4GJCTFIYYUCBYMC3","short_pith_number":"pith:7K3IQLLT","schema_version":"1.0","canonical_sha256":"fab6882d7392f8648a65463141070c16e849344c8051005391e8fa2172288806","source":{"kind":"arxiv","id":"2501.13349","version":2},"attestation_state":"computed","paper":{"title":"MSF: Efficient Diffusion Model Via Multi-Scale Latent Factorize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haohang Xu, Longyu Chen, Shuangrui Ding, Yichen Zhang, Zhipeng Zhang","submitted_at":"2025-01-23T03:18:23Z","abstract_excerpt":"While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy inputs. This contrasts with signal processing techniques, such as Fourier and wavelet analyses, which often employ hierarchical decompositions. Inspired by such principles, particularly the idea of signal separation, we introduce a diffusion framework leveraging multi-scale latent factorization. Our framework uniquely decomposes the denoising target, typically l"},"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":"2501.13349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T03:18:23Z","cross_cats_sorted":[],"title_canon_sha256":"0e29a72554691bba509da406854922de134ca03f4d703fcf624abbf32238bcea","abstract_canon_sha256":"6673efbb4b0cdd567cf2bdc29340cf02883cf5d28a10913200d945f6412034d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:05.885976Z","signature_b64":"6kpSd6VNTx2yzvg/Smooxokt1gVA5uTjoJ1Mp7A8cu/FDeFmWSXZmc3PLjjNvsns1xVikFXCs/hPn9W/3JC7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab6882d7392f8648a65463141070c16e849344c8051005391e8fa2172288806","last_reissued_at":"2026-07-05T11:29:05.885359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:05.885359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSF: Efficient Diffusion Model Via Multi-Scale Latent Factorize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haohang Xu, Longyu Chen, Shuangrui Ding, Yichen Zhang, Zhipeng Zhang","submitted_at":"2025-01-23T03:18:23Z","abstract_excerpt":"While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy inputs. This contrasts with signal processing techniques, such as Fourier and wavelet analyses, which often employ hierarchical decompositions. Inspired by such principles, particularly the idea of signal separation, we introduce a diffusion framework leveraging multi-scale latent factorization. Our framework uniquely decomposes the denoising target, typically l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13349","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/2501.13349/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":"2501.13349","created_at":"2026-07-05T11:29:05.885484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13349v2","created_at":"2026-07-05T11:29:05.885484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13349","created_at":"2026-07-05T11:29:05.885484+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K3IQLLTSL4G","created_at":"2026-07-05T11:29:05.885484+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K3IQLLTSL4GJCTF","created_at":"2026-07-05T11:29:05.885484+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K3IQLLT","created_at":"2026-07-05T11:29:05.885484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3","json":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3.json","graph_json":"https://pith.science/api/pith-number/7K3IQLLTSL4GJCTFIYYUCBYMC3/graph.json","events_json":"https://pith.science/api/pith-number/7K3IQLLTSL4GJCTFIYYUCBYMC3/events.json","paper":"https://pith.science/paper/7K3IQLLT"},"agent_actions":{"view_html":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3","download_json":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3.json","view_paper":"https://pith.science/paper/7K3IQLLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13349&json=true","fetch_graph":"https://pith.science/api/pith-number/7K3IQLLTSL4GJCTFIYYUCBYMC3/graph.json","fetch_events":"https://pith.science/api/pith-number/7K3IQLLTSL4GJCTFIYYUCBYMC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3/action/storage_attestation","attest_author":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3/action/author_attestation","sign_citation":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3/action/citation_signature","submit_replication":"https://pith.science/pith/7K3IQLLTSL4GJCTFIYYUCBYMC3/action/replication_record"}},"created_at":"2026-07-05T11:29:05.885484+00:00","updated_at":"2026-07-05T11:29:05.885484+00:00"}