{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J5UJ3XEIDXAMLLMANXPYGBIQ5O","short_pith_number":"pith:J5UJ3XEI","schema_version":"1.0","canonical_sha256":"4f689ddc881dc0c5ad806ddf830510eb86cf0f60adeb501fb250794f58683c86","source":{"kind":"arxiv","id":"2303.04707","version":2},"attestation_state":"computed","paper":{"title":"DiM: Distilling Dataset into Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jianyang Gu, Kai Wang, Wei Jiang, Yang You, Zheng Zhu","submitted_at":"2023-03-08T16:48:24Z","abstract_excerpt":"Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider application: i). the synthetic images perform poorly on large architectures; ii). they need to be re-optimized when the distillation ratio changes; iii). the limited diversity restricts the performance when the distillation ratio is large. In this paper, we propose a novel distillation scheme to \\textbf{D}istill information of large train sets \\textbf{i}nto generati"},"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":"2303.04707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T16:48:24Z","cross_cats_sorted":[],"title_canon_sha256":"0c362e3474eceafa969072faf14ebb101bb2b56aac8eb3bcf5142bd8c73a8d3f","abstract_canon_sha256":"bcc72961721cd015fe60b94e2350e52a7fbb041100ea924fa7397013bc24a5bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:30.332184Z","signature_b64":"k0L1QCFEQesoRHb+VhzLOMtA5tVTybU96HROkomLJBXmMt/xbg0E01SnYd+XsNHTgiCaU1JEKswAzDT1o8fnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f689ddc881dc0c5ad806ddf830510eb86cf0f60adeb501fb250794f58683c86","last_reissued_at":"2026-07-05T06:59:30.331735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:30.331735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiM: Distilling Dataset into Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jianyang Gu, Kai Wang, Wei Jiang, Yang You, Zheng Zhu","submitted_at":"2023-03-08T16:48:24Z","abstract_excerpt":"Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider application: i). the synthetic images perform poorly on large architectures; ii). they need to be re-optimized when the distillation ratio changes; iii). the limited diversity restricts the performance when the distillation ratio is large. In this paper, we propose a novel distillation scheme to \\textbf{D}istill information of large train sets \\textbf{i}nto generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04707","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/2303.04707/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":"2303.04707","created_at":"2026-07-05T06:59:30.331790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04707v2","created_at":"2026-07-05T06:59:30.331790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04707","created_at":"2026-07-05T06:59:30.331790+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5UJ3XEIDXAM","created_at":"2026-07-05T06:59:30.331790+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5UJ3XEIDXAMLLMA","created_at":"2026-07-05T06:59:30.331790+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5UJ3XEI","created_at":"2026-07-05T06:59:30.331790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18012","citing_title":"SAS: Semantic-aware Sampling for Generative Dataset Distillation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17421","citing_title":"Diffusion Models as Dataset Distillation Priors","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O","json":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O.json","graph_json":"https://pith.science/api/pith-number/J5UJ3XEIDXAMLLMANXPYGBIQ5O/graph.json","events_json":"https://pith.science/api/pith-number/J5UJ3XEIDXAMLLMANXPYGBIQ5O/events.json","paper":"https://pith.science/paper/J5UJ3XEI"},"agent_actions":{"view_html":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O","download_json":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O.json","view_paper":"https://pith.science/paper/J5UJ3XEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04707&json=true","fetch_graph":"https://pith.science/api/pith-number/J5UJ3XEIDXAMLLMANXPYGBIQ5O/graph.json","fetch_events":"https://pith.science/api/pith-number/J5UJ3XEIDXAMLLMANXPYGBIQ5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O/action/storage_attestation","attest_author":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O/action/author_attestation","sign_citation":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O/action/citation_signature","submit_replication":"https://pith.science/pith/J5UJ3XEIDXAMLLMANXPYGBIQ5O/action/replication_record"}},"created_at":"2026-07-05T06:59:30.331790+00:00","updated_at":"2026-07-05T06:59:30.331790+00:00"}