{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQWYR4N6RH56QNJIORXBNOLDFU","short_pith_number":"pith:VQWYR4N6","schema_version":"1.0","canonical_sha256":"ac2d88f1be89fbe83528746e16b9632d202e55dd805e65bba09f14a2f6ce0d99","source":{"kind":"arxiv","id":"2305.10769","version":5},"attestation_state":"computed","paper":{"title":"Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huanran Chen, Lujun Li, Shitong Shao, Shouyi Yin, Xu Dai, Yang Hu","submitted_at":"2023-05-18T07:23:12Z","abstract_excerpt":"Diffusion Probability Models (DPMs) have made impressive advancements in various machine learning domains. However, achieving high-quality synthetic samples typically involves performing a large number of sampling steps, which impedes the possibility of real-time sample synthesis. Traditional accelerated sampling algorithms via knowledge distillation rely on pre-trained model weights and discrete time step scenarios, necessitating additional training sessions to achieve their goals. To address these issues, we propose the Catch-Up Distillation (CUD), which encourages the current moment output "},"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":"2305.10769","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T07:23:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f6a98d749990e81de8dba726bb8f7f206ff73a9322b83f2706229364c2f90272","abstract_canon_sha256":"dd55995ea7304c3067965662519219de18bbddc131e18c0caf55dfed54a5928d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:29.232580Z","signature_b64":"bE0G8uvRIxK33i1F+mV+ppnh1Oh2snPnAXpyU8n4C6BcpurNF13ln8lez4kMl8AAQSKH++wFPPr+GvatLUAHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2d88f1be89fbe83528746e16b9632d202e55dd805e65bba09f14a2f6ce0d99","last_reissued_at":"2026-07-05T09:48:29.232091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:29.232091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huanran Chen, Lujun Li, Shitong Shao, Shouyi Yin, Xu Dai, Yang Hu","submitted_at":"2023-05-18T07:23:12Z","abstract_excerpt":"Diffusion Probability Models (DPMs) have made impressive advancements in various machine learning domains. However, achieving high-quality synthetic samples typically involves performing a large number of sampling steps, which impedes the possibility of real-time sample synthesis. Traditional accelerated sampling algorithms via knowledge distillation rely on pre-trained model weights and discrete time step scenarios, necessitating additional training sessions to achieve their goals. To address these issues, we propose the Catch-Up Distillation (CUD), which encourages the current moment output "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10769","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/2305.10769/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":"2305.10769","created_at":"2026-07-05T09:48:29.232148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10769v5","created_at":"2026-07-05T09:48:29.232148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10769","created_at":"2026-07-05T09:48:29.232148+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQWYR4N6RH56","created_at":"2026-07-05T09:48:29.232148+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQWYR4N6RH56QNJI","created_at":"2026-07-05T09:48:29.232148+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQWYR4N6","created_at":"2026-07-05T09:48:29.232148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"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}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU","json":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU.json","graph_json":"https://pith.science/api/pith-number/VQWYR4N6RH56QNJIORXBNOLDFU/graph.json","events_json":"https://pith.science/api/pith-number/VQWYR4N6RH56QNJIORXBNOLDFU/events.json","paper":"https://pith.science/paper/VQWYR4N6"},"agent_actions":{"view_html":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU","download_json":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU.json","view_paper":"https://pith.science/paper/VQWYR4N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10769&json=true","fetch_graph":"https://pith.science/api/pith-number/VQWYR4N6RH56QNJIORXBNOLDFU/graph.json","fetch_events":"https://pith.science/api/pith-number/VQWYR4N6RH56QNJIORXBNOLDFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU/action/storage_attestation","attest_author":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU/action/author_attestation","sign_citation":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU/action/citation_signature","submit_replication":"https://pith.science/pith/VQWYR4N6RH56QNJIORXBNOLDFU/action/replication_record"}},"created_at":"2026-07-05T09:48:29.232148+00:00","updated_at":"2026-07-05T09:48:29.232148+00:00"}