{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDXXFYPIIFD3SWJQM5264TSOW7","short_pith_number":"pith:MDXXFYPI","schema_version":"1.0","canonical_sha256":"60ef72e1e84147b959306775ee4e4eb7df023d8dd9a31dd4d7ca3bd9823ad30e","source":{"kind":"arxiv","id":"2406.04284","version":2},"attestation_state":"computed","paper":{"title":"What is Dataset Distillation Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Olga Russakovsky, William Yang, Ye Zhu, Zhiwei Deng","submitted_at":"2024-06-06T17:28:56Z","abstract_excerpt":"Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information from the original dataset. While distilled data can be used to train high performing models, little is understood about how the information is stored. In this study, we posit and answer three questions about the behavior, representativeness, and point-wise information content of distilled data. We reveal distilled data cannot serve as a substitute for real data during training outside the standard evaluation setting"},"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":"2406.04284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:28:56Z","cross_cats_sorted":[],"title_canon_sha256":"5d08c1274004f06b6dc1e8ca889fcf560cac70c98a0e420a8280b6eb096f15ba","abstract_canon_sha256":"477ca7afb3f064d43511ca2a90ebecfb690db09a02de19f3403d941f0b3d577d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:55.339823Z","signature_b64":"joBXX4GXmTyti0ctuHJ/OO/V1AMIJt/A+w21dJjMzQ+QWbwSOdZxMTWZDMex/YntwYvndw3mZBQc/zoAo04NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60ef72e1e84147b959306775ee4e4eb7df023d8dd9a31dd4d7ca3bd9823ad30e","last_reissued_at":"2026-07-05T08:46:55.339258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:55.339258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is Dataset Distillation Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Olga Russakovsky, William Yang, Ye Zhu, Zhiwei Deng","submitted_at":"2024-06-06T17:28:56Z","abstract_excerpt":"Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information from the original dataset. While distilled data can be used to train high performing models, little is understood about how the information is stored. In this study, we posit and answer three questions about the behavior, representativeness, and point-wise information content of distilled data. We reveal distilled data cannot serve as a substitute for real data during training outside the standard evaluation setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04284","kind":"arxiv","version":2},"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/2406.04284/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":"2406.04284","created_at":"2026-07-05T08:46:55.339330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04284v2","created_at":"2026-07-05T08:46:55.339330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04284","created_at":"2026-07-05T08:46:55.339330+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDXXFYPIIFD3","created_at":"2026-07-05T08:46:55.339330+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDXXFYPIIFD3SWJQ","created_at":"2026-07-05T08:46:55.339330+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDXXFYPI","created_at":"2026-07-05T08:46:55.339330+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21705","citing_title":"Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7","json":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7.json","graph_json":"https://pith.science/api/pith-number/MDXXFYPIIFD3SWJQM5264TSOW7/graph.json","events_json":"https://pith.science/api/pith-number/MDXXFYPIIFD3SWJQM5264TSOW7/events.json","paper":"https://pith.science/paper/MDXXFYPI"},"agent_actions":{"view_html":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7","download_json":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7.json","view_paper":"https://pith.science/paper/MDXXFYPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04284&json=true","fetch_graph":"https://pith.science/api/pith-number/MDXXFYPIIFD3SWJQM5264TSOW7/graph.json","fetch_events":"https://pith.science/api/pith-number/MDXXFYPIIFD3SWJQM5264TSOW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7/action/storage_attestation","attest_author":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7/action/author_attestation","sign_citation":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7/action/citation_signature","submit_replication":"https://pith.science/pith/MDXXFYPIIFD3SWJQM5264TSOW7/action/replication_record"}},"created_at":"2026-07-05T08:46:55.339330+00:00","updated_at":"2026-07-05T08:46:55.339330+00:00"}