{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FVHZZ3YNBLD4YGBE74KGBTMSBW","short_pith_number":"pith:FVHZZ3YN","schema_version":"1.0","canonical_sha256":"2d4f9cef0d0ac7cc1824ff1460cd920d99f118a5b3349eaf6177f900a9fcecc8","source":{"kind":"arxiv","id":"2410.03190","version":3},"attestation_state":"computed","paper":{"title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Lin, Lijuan Wang, Qiang Qiu, Ze Wang, Zhengyuan Yang, Zicheng Liu, Zichen Miao","submitted_at":"2024-10-04T07:05:16Z","abstract_excerpt":"Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive; the distillation training usually re"},"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":"2410.03190","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T07:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"4d11902b41da5f9c38383df8be4e0ff41a3ea0abfa1adb6a5af8d98f56cb8e88","abstract_canon_sha256":"ed6879c5fbe0d815b11cb4817c85033ffeb165bbd832f09382b3b8e52cefe3d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:51.558929Z","signature_b64":"yBTACxScEWGNfZMicu/VEfhWoWTeLP+NjZJ5/ruHXn6h81ZOAMrEUjIkhinqp/kc2gkXYUDcvraBCX6fRmRhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d4f9cef0d0ac7cc1824ff1460cd920d99f118a5b3349eaf6177f900a9fcecc8","last_reissued_at":"2026-07-05T10:22:51.558205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:51.558205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Lin, Lijuan Wang, Qiang Qiu, Ze Wang, Zhengyuan Yang, Zicheng Liu, Zichen Miao","submitted_at":"2024-10-04T07:05:16Z","abstract_excerpt":"Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive; the distillation training usually re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03190","kind":"arxiv","version":3},"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/2410.03190/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":"2410.03190","created_at":"2026-07-05T10:22:51.558289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03190v3","created_at":"2026-07-05T10:22:51.558289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03190","created_at":"2026-07-05T10:22:51.558289+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVHZZ3YNBLD4","created_at":"2026-07-05T10:22:51.558289+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVHZZ3YNBLD4YGBE","created_at":"2026-07-05T10:22:51.558289+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVHZZ3YN","created_at":"2026-07-05T10:22:51.558289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09433","citing_title":"Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW","json":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW.json","graph_json":"https://pith.science/api/pith-number/FVHZZ3YNBLD4YGBE74KGBTMSBW/graph.json","events_json":"https://pith.science/api/pith-number/FVHZZ3YNBLD4YGBE74KGBTMSBW/events.json","paper":"https://pith.science/paper/FVHZZ3YN"},"agent_actions":{"view_html":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW","download_json":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW.json","view_paper":"https://pith.science/paper/FVHZZ3YN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03190&json=true","fetch_graph":"https://pith.science/api/pith-number/FVHZZ3YNBLD4YGBE74KGBTMSBW/graph.json","fetch_events":"https://pith.science/api/pith-number/FVHZZ3YNBLD4YGBE74KGBTMSBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW/action/storage_attestation","attest_author":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW/action/author_attestation","sign_citation":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW/action/citation_signature","submit_replication":"https://pith.science/pith/FVHZZ3YNBLD4YGBE74KGBTMSBW/action/replication_record"}},"created_at":"2026-07-05T10:22:51.558289+00:00","updated_at":"2026-07-05T10:22:51.558289+00:00"}