{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QOKQ75EHAUJPLUDMT7ETCGPOTZ","short_pith_number":"pith:QOKQ75EH","schema_version":"1.0","canonical_sha256":"83950ff4870512f5d06c9fc93119ee9e48a041b9f591ac98aabf740c628af044","source":{"kind":"arxiv","id":"2505.18399","version":1},"attestation_state":"computed","paper":{"title":"Taming Diffusion for Dataset Distillation with High Representativeness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Lin Zhao, Pu Zhao, Xiaolin Xu, Xinru Jiang, Xue Lin, Yanzhi Wang, Yushu Wu","submitted_at":"2025-05-23T22:05:59Z","abstract_excerpt":"Recent deep learning models demand larger datasets, driving the need for dataset distillation to create compact, cost-efficient datasets while maintaining performance. Due to the powerful image generation capability of diffusion, it has been introduced to this field for generating distilled images. In this paper, we systematically investigate issues present in current diffusion-based dataset distillation methods, including inaccurate distribution matching, distribution deviation with random noise, and separate sampling. Building on this, we propose D^3HR, a novel diffusion-based framework to g"},"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":"2505.18399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T22:05:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9dee57013f3e766ba368987752b77a021103220c9faa10e032760dcf6633751","abstract_canon_sha256":"6a9dae14eaf0115eb3d6f5632cdfae45b8c9db5aae512dbfe160e1d2227a8c8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:45.817086Z","signature_b64":"4rKwo1lOV4NwCseSBcjnQEqxiA2deRSFb3kfXEgyI+ui5w1mRbU0UgD7jMZV8jOEEkL2zNWYdNQf2MQWKKvMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83950ff4870512f5d06c9fc93119ee9e48a041b9f591ac98aabf740c628af044","last_reissued_at":"2026-07-05T11:08:45.816658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:45.816658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming Diffusion for Dataset Distillation with High Representativeness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Lin Zhao, Pu Zhao, Xiaolin Xu, Xinru Jiang, Xue Lin, Yanzhi Wang, Yushu Wu","submitted_at":"2025-05-23T22:05:59Z","abstract_excerpt":"Recent deep learning models demand larger datasets, driving the need for dataset distillation to create compact, cost-efficient datasets while maintaining performance. Due to the powerful image generation capability of diffusion, it has been introduced to this field for generating distilled images. In this paper, we systematically investigate issues present in current diffusion-based dataset distillation methods, including inaccurate distribution matching, distribution deviation with random noise, and separate sampling. Building on this, we propose D^3HR, a novel diffusion-based framework to g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18399","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/2505.18399/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":"2505.18399","created_at":"2026-07-05T11:08:45.816714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18399v1","created_at":"2026-07-05T11:08:45.816714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18399","created_at":"2026-07-05T11:08:45.816714+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOKQ75EHAUJP","created_at":"2026-07-05T11:08:45.816714+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOKQ75EHAUJPLUDM","created_at":"2026-07-05T11:08:45.816714+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOKQ75EH","created_at":"2026-07-05T11:08:45.816714+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/QOKQ75EHAUJPLUDMT7ETCGPOTZ","json":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ.json","graph_json":"https://pith.science/api/pith-number/QOKQ75EHAUJPLUDMT7ETCGPOTZ/graph.json","events_json":"https://pith.science/api/pith-number/QOKQ75EHAUJPLUDMT7ETCGPOTZ/events.json","paper":"https://pith.science/paper/QOKQ75EH"},"agent_actions":{"view_html":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ","download_json":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ.json","view_paper":"https://pith.science/paper/QOKQ75EH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18399&json=true","fetch_graph":"https://pith.science/api/pith-number/QOKQ75EHAUJPLUDMT7ETCGPOTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QOKQ75EHAUJPLUDMT7ETCGPOTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ/action/storage_attestation","attest_author":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ/action/author_attestation","sign_citation":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ/action/citation_signature","submit_replication":"https://pith.science/pith/QOKQ75EHAUJPLUDMT7ETCGPOTZ/action/replication_record"}},"created_at":"2026-07-05T11:08:45.816714+00:00","updated_at":"2026-07-05T11:08:45.816714+00:00"}