{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MNYIM642Q6NTEYQ45RCQQABBMF","short_pith_number":"pith:MNYIM642","schema_version":"1.0","canonical_sha256":"6370867b9a879b32621cec4508002161774204fece8c271abdb2bc8885600ef0","source":{"kind":"arxiv","id":"2409.01410","version":1},"attestation_state":"computed","paper":{"title":"Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"cs.LG","authors_text":"Anthony Quinn, Fadwa Idlahcen, Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Yiran Chen, Yuanfang Peng","submitted_at":"2024-09-02T18:11:15Z","abstract_excerpt":"Dataset distillation (DD) is an increasingly important technique that focuses on constructing a synthetic dataset capable of capturing the core information in training data to achieve comparable performance in models trained on the latter. While DD has a wide range of applications, the theory supporting it is less well evolved. New methods of DD are compared on a common set of benchmarks, rather than oriented towards any particular learning task. In this work, we present a formal model of DD, arguing that a precise characterization of the underlying optimization problem must specify the infere"},"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":"2409.01410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T18:11:15Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"4ffcc48dd8836b3f82589b2913f1e8284684a4af3a3eda928fb5de375cf4c15d","abstract_canon_sha256":"9104e57c1abb6c897d4c4762694821d896fc43beb0f5d2426dc0b8874a3a1949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:28.744883Z","signature_b64":"EPt3il8fCEfMr/TfKwzm6RVbd9bmQl2amvKjwPj35QIfG/eU2Zx/eM5UUWtXKyFZNyAb0UyAFeMC6TkhLx+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6370867b9a879b32621cec4508002161774204fece8c271abdb2bc8885600ef0","last_reissued_at":"2026-07-05T09:02:28.744439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:28.744439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"cs.LG","authors_text":"Anthony Quinn, Fadwa Idlahcen, Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Yiran Chen, Yuanfang Peng","submitted_at":"2024-09-02T18:11:15Z","abstract_excerpt":"Dataset distillation (DD) is an increasingly important technique that focuses on constructing a synthetic dataset capable of capturing the core information in training data to achieve comparable performance in models trained on the latter. While DD has a wide range of applications, the theory supporting it is less well evolved. New methods of DD are compared on a common set of benchmarks, rather than oriented towards any particular learning task. In this work, we present a formal model of DD, arguing that a precise characterization of the underlying optimization problem must specify the infere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01410","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/2409.01410/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":"2409.01410","created_at":"2026-07-05T09:02:28.744497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01410v1","created_at":"2026-07-05T09:02:28.744497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01410","created_at":"2026-07-05T09:02:28.744497+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNYIM642Q6NT","created_at":"2026-07-05T09:02:28.744497+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNYIM642Q6NTEYQ4","created_at":"2026-07-05T09:02:28.744497+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNYIM642","created_at":"2026-07-05T09:02:28.744497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18358","citing_title":"CONCORD: Concept-Informed Diffusion for Dataset Distillation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF","json":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF.json","graph_json":"https://pith.science/api/pith-number/MNYIM642Q6NTEYQ45RCQQABBMF/graph.json","events_json":"https://pith.science/api/pith-number/MNYIM642Q6NTEYQ45RCQQABBMF/events.json","paper":"https://pith.science/paper/MNYIM642"},"agent_actions":{"view_html":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF","download_json":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF.json","view_paper":"https://pith.science/paper/MNYIM642","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01410&json=true","fetch_graph":"https://pith.science/api/pith-number/MNYIM642Q6NTEYQ45RCQQABBMF/graph.json","fetch_events":"https://pith.science/api/pith-number/MNYIM642Q6NTEYQ45RCQQABBMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF/action/storage_attestation","attest_author":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF/action/author_attestation","sign_citation":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF/action/citation_signature","submit_replication":"https://pith.science/pith/MNYIM642Q6NTEYQ45RCQQABBMF/action/replication_record"}},"created_at":"2026-07-05T09:02:28.744497+00:00","updated_at":"2026-07-05T09:02:28.744497+00:00"}