{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MNPLRDSGERGROFMYNEQFAN36LU","short_pith_number":"pith:MNPLRDSG","schema_version":"1.0","canonical_sha256":"635eb88e46244d171598692050377e5d243c2c558d70a99f6cfaa16eb4b72df8","source":{"kind":"arxiv","id":"2312.05598","version":2},"attestation_state":"computed","paper":{"title":"Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Chao, Lirui Zhao, Rongrong Ji, Yuxin Zhang","submitted_at":"2023-12-09T15:41:42Z","abstract_excerpt":"The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance. This paper attempts to mitigate this issue through an empirical study, which suggests that the synthetic datasets undergo an inductive bias towards the distillation model. Therefore, the evaluation model is strictly confined to having similar architectures of the distillation model. We propose a novel method of EvaLuation with distillation Feature (ELF), which utilizes features from intermediate layers of the distillation model for the cross-architecture evaluation. In this manner, th"},"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":"2312.05598","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-09T15:41:42Z","cross_cats_sorted":[],"title_canon_sha256":"9e87380dcec23ac61a53b47ecf38d05e29c194deeadbfffd5553cfaa14e8cd6a","abstract_canon_sha256":"965b6aacd098a1a980a91924ecf39844cc9e550e5feacca0f41f5c99cc8e3d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:44.888367Z","signature_b64":"YsDVAK2l0eAbkB5tGVtQJtVzA7/MG1if68L0uY06/V+ywnJRPAJ7wf4hC+MKOSEs72LM5Y0TlRGj12EM32X4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"635eb88e46244d171598692050377e5d243c2c558d70a99f6cfaa16eb4b72df8","last_reissued_at":"2026-07-05T08:36:44.887868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:44.887868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Chao, Lirui Zhao, Rongrong Ji, Yuxin Zhang","submitted_at":"2023-12-09T15:41:42Z","abstract_excerpt":"The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance. This paper attempts to mitigate this issue through an empirical study, which suggests that the synthetic datasets undergo an inductive bias towards the distillation model. Therefore, the evaluation model is strictly confined to having similar architectures of the distillation model. We propose a novel method of EvaLuation with distillation Feature (ELF), which utilizes features from intermediate layers of the distillation model for the cross-architecture evaluation. In this manner, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05598","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/2312.05598/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":"2312.05598","created_at":"2026-07-05T08:36:44.887922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05598v2","created_at":"2026-07-05T08:36:44.887922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05598","created_at":"2026-07-05T08:36:44.887922+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNPLRDSGERGR","created_at":"2026-07-05T08:36:44.887922+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNPLRDSGERGROFMY","created_at":"2026-07-05T08:36:44.887922+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNPLRDSG","created_at":"2026-07-05T08:36:44.887922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17245","citing_title":"Extending Dataset Pruning to Object Detection: A Variance-based Approach","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU","json":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU.json","graph_json":"https://pith.science/api/pith-number/MNPLRDSGERGROFMYNEQFAN36LU/graph.json","events_json":"https://pith.science/api/pith-number/MNPLRDSGERGROFMYNEQFAN36LU/events.json","paper":"https://pith.science/paper/MNPLRDSG"},"agent_actions":{"view_html":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU","download_json":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU.json","view_paper":"https://pith.science/paper/MNPLRDSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05598&json=true","fetch_graph":"https://pith.science/api/pith-number/MNPLRDSGERGROFMYNEQFAN36LU/graph.json","fetch_events":"https://pith.science/api/pith-number/MNPLRDSGERGROFMYNEQFAN36LU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU/action/storage_attestation","attest_author":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU/action/author_attestation","sign_citation":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU/action/citation_signature","submit_replication":"https://pith.science/pith/MNPLRDSGERGROFMYNEQFAN36LU/action/replication_record"}},"created_at":"2026-07-05T08:36:44.887922+00:00","updated_at":"2026-07-05T08:36:44.887922+00:00"}