{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6JPH3JL4WYL3F7YJJTB4RJAVOM","short_pith_number":"pith:6JPH3JL4","schema_version":"1.0","canonical_sha256":"f25e7da57cb617b2ff094cc3c8a4157321537e943448f8a8ff4176f6299941ac","source":{"kind":"arxiv","id":"2507.18569","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andy J. Ma, Jian-Huang Lai, Shanchuan Lin, Xiaohua Xie, Xing Wang, Xin Xia, Xuefeng Xiao, Yanzuo Lu, Yuxi Ren","submitted_at":"2025-07-24T16:45:05Z","abstract_excerpt":"Distribution Matching Distillation (DMD) is a promising score distillation technique that compresses pre-trained teacher diffusion models into efficient one-step or multi-step student generators. Nevertheless, its reliance on the reverse Kullback-Leibler (KL) divergence minimization potentially induces mode collapse (or mode-seeking) in certain applications. To circumvent this inherent drawback, we propose Adversarial Distribution Matching (ADM), a novel framework that leverages diffusion-based discriminators to align the latent predictions between real and fake score estimators for score dist"},"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":"2507.18569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T16:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"6896ee87f4822d671478b8b142a88c00ebfe27b02def65bca6998306f3a6fae7","abstract_canon_sha256":"c1c75406d4ee9d209e55dfb6d0a8a6cc2f3f3dae0c705b62a8066ac426b5d5c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:50.211635Z","signature_b64":"unXPJJT2oN4BffeMeomOr3Zvc63eYr5A5v9cSqUK1/PhsEuvmYBaskKBaWsMFqbKdb9A2V3z/1S/hf0WGd6uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f25e7da57cb617b2ff094cc3c8a4157321537e943448f8a8ff4176f6299941ac","last_reissued_at":"2026-07-05T11:42:50.211225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:50.211225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andy J. Ma, Jian-Huang Lai, Shanchuan Lin, Xiaohua Xie, Xing Wang, Xin Xia, Xuefeng Xiao, Yanzuo Lu, Yuxi Ren","submitted_at":"2025-07-24T16:45:05Z","abstract_excerpt":"Distribution Matching Distillation (DMD) is a promising score distillation technique that compresses pre-trained teacher diffusion models into efficient one-step or multi-step student generators. Nevertheless, its reliance on the reverse Kullback-Leibler (KL) divergence minimization potentially induces mode collapse (or mode-seeking) in certain applications. To circumvent this inherent drawback, we propose Adversarial Distribution Matching (ADM), a novel framework that leverages diffusion-based discriminators to align the latent predictions between real and fake score estimators for score dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18569","kind":"arxiv","version":1},"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/2507.18569/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":"2507.18569","created_at":"2026-07-05T11:42:50.211277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18569v1","created_at":"2026-07-05T11:42:50.211277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18569","created_at":"2026-07-05T11:42:50.211277+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JPH3JL4WYL3","created_at":"2026-07-05T11:42:50.211277+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JPH3JL4WYL3F7YJ","created_at":"2026-07-05T11:42:50.211277+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JPH3JL4","created_at":"2026-07-05T11:42:50.211277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21982","citing_title":"CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation","ref_index":16,"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":54,"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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04018","citing_title":"1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20427","citing_title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","ref_index":13,"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":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM","json":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM.json","graph_json":"https://pith.science/api/pith-number/6JPH3JL4WYL3F7YJJTB4RJAVOM/graph.json","events_json":"https://pith.science/api/pith-number/6JPH3JL4WYL3F7YJJTB4RJAVOM/events.json","paper":"https://pith.science/paper/6JPH3JL4"},"agent_actions":{"view_html":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM","download_json":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM.json","view_paper":"https://pith.science/paper/6JPH3JL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18569&json=true","fetch_graph":"https://pith.science/api/pith-number/6JPH3JL4WYL3F7YJJTB4RJAVOM/graph.json","fetch_events":"https://pith.science/api/pith-number/6JPH3JL4WYL3F7YJJTB4RJAVOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM/action/storage_attestation","attest_author":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM/action/author_attestation","sign_citation":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM/action/citation_signature","submit_replication":"https://pith.science/pith/6JPH3JL4WYL3F7YJJTB4RJAVOM/action/replication_record"}},"created_at":"2026-07-05T11:42:50.211277+00:00","updated_at":"2026-07-05T11:42:50.211277+00:00"}