{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FECHZO4DJ5YQY25V7BIUBMYYJD","short_pith_number":"pith:FECHZO4D","schema_version":"1.0","canonical_sha256":"29047cbb834f710c6bb5f85140b31848ee11edd5389ea69ec4ba0c51707522bf","source":{"kind":"arxiv","id":"2305.01975","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunming Rong, Herbert Woisetschlaeger, Jiahui Geng, Ruben Mayer, Sonja Schimmler, Yuandou Wang, Zhiming Zhao, Zongxiong Chen","submitted_at":"2023-05-03T08:41:37Z","abstract_excerpt":"Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density, dataset distillation offers a range of potential applications, including support for continual learning, neural architecture search, and privacy protection. Despite recent advances, we lack a holistic understanding of the approaches and applications. Our survey aims to bridge this gap by first proposing a taxonomy of dataset distillation, characterizing existing"},"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":"2305.01975","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T08:41:37Z","cross_cats_sorted":[],"title_canon_sha256":"84912feee79ddb56e99e40230b6583386911b92d2c2be20b0301b80b55f3f5ce","abstract_canon_sha256":"7138934184360b8a518f073c5889ef123062c73395b277758eb1f7ebbd311b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:19.863418Z","signature_b64":"uQeXawaAlNAOssCHxwwgY0aY5xjHxt0pUtmu8UhmYFOkkOOzI88BxjTC0HFpQLUj61/73QYgap0f1K1cfJ2qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29047cbb834f710c6bb5f85140b31848ee11edd5389ea69ec4ba0c51707522bf","last_reissued_at":"2026-07-05T06:44:19.862899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:19.862899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunming Rong, Herbert Woisetschlaeger, Jiahui Geng, Ruben Mayer, Sonja Schimmler, Yuandou Wang, Zhiming Zhao, Zongxiong Chen","submitted_at":"2023-05-03T08:41:37Z","abstract_excerpt":"Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density, dataset distillation offers a range of potential applications, including support for continual learning, neural architecture search, and privacy protection. Despite recent advances, we lack a holistic understanding of the approaches and applications. Our survey aims to bridge this gap by first proposing a taxonomy of dataset distillation, characterizing existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01975","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/2305.01975/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":"2305.01975","created_at":"2026-07-05T06:44:19.862968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01975v3","created_at":"2026-07-05T06:44:19.862968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01975","created_at":"2026-07-05T06:44:19.862968+00:00"},{"alias_kind":"pith_short_12","alias_value":"FECHZO4DJ5YQ","created_at":"2026-07-05T06:44:19.862968+00:00"},{"alias_kind":"pith_short_16","alias_value":"FECHZO4DJ5YQY25V","created_at":"2026-07-05T06:44:19.862968+00:00"},{"alias_kind":"pith_short_8","alias_value":"FECHZO4D","created_at":"2026-07-05T06:44:19.862968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05883","citing_title":"Geometry-Aware Dataset Condensation for Diffusion Model Training","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10666","citing_title":"Omnimodal Dataset Distillation via High-order Proxy Alignment","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD","json":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD.json","graph_json":"https://pith.science/api/pith-number/FECHZO4DJ5YQY25V7BIUBMYYJD/graph.json","events_json":"https://pith.science/api/pith-number/FECHZO4DJ5YQY25V7BIUBMYYJD/events.json","paper":"https://pith.science/paper/FECHZO4D"},"agent_actions":{"view_html":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD","download_json":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD.json","view_paper":"https://pith.science/paper/FECHZO4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01975&json=true","fetch_graph":"https://pith.science/api/pith-number/FECHZO4DJ5YQY25V7BIUBMYYJD/graph.json","fetch_events":"https://pith.science/api/pith-number/FECHZO4DJ5YQY25V7BIUBMYYJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD/action/storage_attestation","attest_author":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD/action/author_attestation","sign_citation":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD/action/citation_signature","submit_replication":"https://pith.science/pith/FECHZO4DJ5YQY25V7BIUBMYYJD/action/replication_record"}},"created_at":"2026-07-05T06:44:19.862968+00:00","updated_at":"2026-07-05T06:44:19.862968+00:00"}