{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6NZQAQFXDLSVGJ6JKLAQNTUC5O","short_pith_number":"pith:6NZQAQFX","schema_version":"1.0","canonical_sha256":"f3730040b71ae55327c952c106ce82eb905be9e080a3584a729d23c0df63a24d","source":{"kind":"arxiv","id":"2606.18209","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Mehra, Joshua Kimball, Trisha Mittal","submitted_at":"2026-06-16T17:37:49Z","abstract_excerpt":"Dataset distillation (DD) has emerged as a prominent approach in data centric machine learning, aiming to synthesize compact training sets for efficient training by compressing the information in large datasets into a small number of synthetic samples. However, DD methods are often evaluated under inconsistent evaluation protocols, ranging from standard ERM to single/multi-teacher supervision, making it difficult to isolate the effectiveness of distilled data from evaluation. Moreover, many prior methods claim that DD outperforms data pruning approaches such as coreset selection (CS), based on"},"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":"2606.18209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T17:37:49Z","cross_cats_sorted":[],"title_canon_sha256":"afef38891d23751cc72554e7f7b54651910e8a3ae495fbd4e4672cc8a2503fee","abstract_canon_sha256":"799beb6fc0583ac44c8e1b958c872c1d5087995f410d22c9a02fd6a4715c9075"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:51.139030Z","signature_b64":"NvowPIN0aCi1kUIwQvT1+mL7BKlcZWT/Unh14o+CbDPcb/lYdSwwnv6rXYWrd0ZshCTSDBzth8jwz0YQBJ0qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3730040b71ae55327c952c106ce82eb905be9e080a3584a729d23c0df63a24d","last_reissued_at":"2026-06-19T16:10:51.138673Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:51.138673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Mehra, Joshua Kimball, Trisha Mittal","submitted_at":"2026-06-16T17:37:49Z","abstract_excerpt":"Dataset distillation (DD) has emerged as a prominent approach in data centric machine learning, aiming to synthesize compact training sets for efficient training by compressing the information in large datasets into a small number of synthetic samples. However, DD methods are often evaluated under inconsistent evaluation protocols, ranging from standard ERM to single/multi-teacher supervision, making it difficult to isolate the effectiveness of distilled data from evaluation. Moreover, many prior methods claim that DD outperforms data pruning approaches such as coreset selection (CS), based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18209","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/2606.18209/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":"2606.18209","created_at":"2026-06-19T16:10:51.138735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18209v1","created_at":"2026-06-19T16:10:51.138735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18209","created_at":"2026-06-19T16:10:51.138735+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NZQAQFXDLSV","created_at":"2026-06-19T16:10:51.138735+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NZQAQFXDLSVGJ6J","created_at":"2026-06-19T16:10:51.138735+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NZQAQFX","created_at":"2026-06-19T16:10:51.138735+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/6NZQAQFXDLSVGJ6JKLAQNTUC5O","json":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O.json","graph_json":"https://pith.science/api/pith-number/6NZQAQFXDLSVGJ6JKLAQNTUC5O/graph.json","events_json":"https://pith.science/api/pith-number/6NZQAQFXDLSVGJ6JKLAQNTUC5O/events.json","paper":"https://pith.science/paper/6NZQAQFX"},"agent_actions":{"view_html":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O","download_json":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O.json","view_paper":"https://pith.science/paper/6NZQAQFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18209&json=true","fetch_graph":"https://pith.science/api/pith-number/6NZQAQFXDLSVGJ6JKLAQNTUC5O/graph.json","fetch_events":"https://pith.science/api/pith-number/6NZQAQFXDLSVGJ6JKLAQNTUC5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O/action/storage_attestation","attest_author":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O/action/author_attestation","sign_citation":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O/action/citation_signature","submit_replication":"https://pith.science/pith/6NZQAQFXDLSVGJ6JKLAQNTUC5O/action/replication_record"}},"created_at":"2026-06-19T16:10:51.138735+00:00","updated_at":"2026-06-19T16:10:51.138735+00:00"}