{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HF7D7DODZPYDF3WJWUTWGVXFRG","short_pith_number":"pith:HF7D7DOD","schema_version":"1.0","canonical_sha256":"397e3f8dc3cbf032eec9b5276356e58989c39584ac9337eb1502681eeffd6b5a","source":{"kind":"arxiv","id":"2603.06136","version":2},"attestation_state":"computed","paper":{"title":"Cross-Resolution Distribution Matching for Diffusion Distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyang Chen, Haonan Xu, Hongpeng Pan, Xinyu Duan, Yang Yang, Zhefeng Wang","submitted_at":"2026-03-06T10:45:07Z","abstract_excerpt":"Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation can further accelerate inference, but it suffers noticeable quality degradation due to cross-resolution distribution gaps. We propose Cross-Resolution Distribution Matching Distillation (RMD), a novel distillation framework that bridges cross-resolution distribution gaps for high-fidelity, few-step multi-resolution cascaded inference. Specifically, RMD divides"},"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":"2603.06136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T10:45:07Z","cross_cats_sorted":[],"title_canon_sha256":"1454e8361694c36b266741c301a60e7f86a47480f345ede332250723d251233b","abstract_canon_sha256":"7399d31f99ad94b75fee6875ac1d937430d35db080af5a72c2a67d1d3857e685"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:48.407079Z","signature_b64":"Nb+jrnf++/wAztR4oCdyqEUhQ6vJ6R/+Q/HmykKUjgflcgAwgnF+/BmL/lJ+NbmFzK49aENl2Td7EpVIDMWJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"397e3f8dc3cbf032eec9b5276356e58989c39584ac9337eb1502681eeffd6b5a","last_reissued_at":"2026-07-01T01:17:48.406544Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:48.406544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Resolution Distribution Matching for Diffusion Distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyang Chen, Haonan Xu, Hongpeng Pan, Xinyu Duan, Yang Yang, Zhefeng Wang","submitted_at":"2026-03-06T10:45:07Z","abstract_excerpt":"Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation can further accelerate inference, but it suffers noticeable quality degradation due to cross-resolution distribution gaps. We propose Cross-Resolution Distribution Matching Distillation (RMD), a novel distillation framework that bridges cross-resolution distribution gaps for high-fidelity, few-step multi-resolution cascaded inference. Specifically, RMD divides"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06136","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/2603.06136/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":"2603.06136","created_at":"2026-07-01T01:17:48.406609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06136v2","created_at":"2026-07-01T01:17:48.406609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06136","created_at":"2026-07-01T01:17:48.406609+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF7D7DODZPYD","created_at":"2026-07-01T01:17:48.406609+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF7D7DODZPYDF3WJ","created_at":"2026-07-01T01:17:48.406609+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF7D7DOD","created_at":"2026-07-01T01:17:48.406609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06376","citing_title":"Continuous-Time Distribution Matching for Few-Step Diffusion Distillation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG","json":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG.json","graph_json":"https://pith.science/api/pith-number/HF7D7DODZPYDF3WJWUTWGVXFRG/graph.json","events_json":"https://pith.science/api/pith-number/HF7D7DODZPYDF3WJWUTWGVXFRG/events.json","paper":"https://pith.science/paper/HF7D7DOD"},"agent_actions":{"view_html":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG","download_json":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG.json","view_paper":"https://pith.science/paper/HF7D7DOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06136&json=true","fetch_graph":"https://pith.science/api/pith-number/HF7D7DODZPYDF3WJWUTWGVXFRG/graph.json","fetch_events":"https://pith.science/api/pith-number/HF7D7DODZPYDF3WJWUTWGVXFRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG/action/storage_attestation","attest_author":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG/action/author_attestation","sign_citation":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG/action/citation_signature","submit_replication":"https://pith.science/pith/HF7D7DODZPYDF3WJWUTWGVXFRG/action/replication_record"}},"created_at":"2026-07-01T01:17:48.406609+00:00","updated_at":"2026-07-01T01:17:48.406609+00:00"}