{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y2XSUUWDRSYT7B62SZCSUMER2F","short_pith_number":"pith:Y2XSUUWD","schema_version":"1.0","canonical_sha256":"c6af2a52c38cb13f87da96452a3091d15b454045935608cc9d3efe73b4b04136","source":{"kind":"arxiv","id":"2410.15919","version":2},"attestation_state":"computed","paper":{"title":"Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingao Xiao, Yang He","submitted_at":"2024-10-21T11:49:10Z","abstract_excerpt":"In ImageNet-condensation, the storage for auxiliary soft labels exceeds that of the condensed dataset by over 30 times. However, are large-scale soft labels necessary for large-scale dataset distillation? In this paper, we first discover that the high within-class similarity in condensed datasets necessitates the use of large-scale soft labels. This high within-class similarity can be attributed to the fact that previous methods use samples from different classes to construct a single batch for batch normalization (BN) matching. To reduce the within-class similarity, we introduce class-wise su"},"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":"2410.15919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T11:49:10Z","cross_cats_sorted":[],"title_canon_sha256":"5c31f441dfa3b1aaa02782ace005049fca0e49f3cfb6dba0996a4f95db2956a9","abstract_canon_sha256":"9299964c4857a7afedf8eb9f805ac55b29944c12a9b41b3d8c8a819671572c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:22.524073Z","signature_b64":"wCSQaowcAYclJGYIluqOiE5FfBlHN0gNkjHaJavB7D33sMPfWJ9MetkvtHKkVBYAGB1Dw0u8nvVCn1EZN+TzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6af2a52c38cb13f87da96452a3091d15b454045935608cc9d3efe73b4b04136","last_reissued_at":"2026-07-05T09:30:22.523605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:22.523605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingao Xiao, Yang He","submitted_at":"2024-10-21T11:49:10Z","abstract_excerpt":"In ImageNet-condensation, the storage for auxiliary soft labels exceeds that of the condensed dataset by over 30 times. However, are large-scale soft labels necessary for large-scale dataset distillation? In this paper, we first discover that the high within-class similarity in condensed datasets necessitates the use of large-scale soft labels. This high within-class similarity can be attributed to the fact that previous methods use samples from different classes to construct a single batch for batch normalization (BN) matching. To reduce the within-class similarity, we introduce class-wise su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15919","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/2410.15919/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":"2410.15919","created_at":"2026-07-05T09:30:22.523660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15919v2","created_at":"2026-07-05T09:30:22.523660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15919","created_at":"2026-07-05T09:30:22.523660+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2XSUUWDRSYT","created_at":"2026-07-05T09:30:22.523660+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2XSUUWDRSYT7B62","created_at":"2026-07-05T09:30:22.523660+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2XSUUWD","created_at":"2026-07-05T09:30:22.523660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03877","citing_title":"DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F","json":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F.json","graph_json":"https://pith.science/api/pith-number/Y2XSUUWDRSYT7B62SZCSUMER2F/graph.json","events_json":"https://pith.science/api/pith-number/Y2XSUUWDRSYT7B62SZCSUMER2F/events.json","paper":"https://pith.science/paper/Y2XSUUWD"},"agent_actions":{"view_html":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F","download_json":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F.json","view_paper":"https://pith.science/paper/Y2XSUUWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15919&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2XSUUWDRSYT7B62SZCSUMER2F/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2XSUUWDRSYT7B62SZCSUMER2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F/action/storage_attestation","attest_author":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F/action/author_attestation","sign_citation":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F/action/citation_signature","submit_replication":"https://pith.science/pith/Y2XSUUWDRSYT7B62SZCSUMER2F/action/replication_record"}},"created_at":"2026-07-05T09:30:22.523660+00:00","updated_at":"2026-07-05T09:30:22.523660+00:00"}