{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GIALSZ3KMW7CCKZMUFYVG7KUS3","short_pith_number":"pith:GIALSZ3K","schema_version":"1.0","canonical_sha256":"3200b9676a65be212b2ca171537d5496d705dae1dfba377df2d048b21e6e1225","source":{"kind":"arxiv","id":"2302.14416","version":3},"attestation_state":"computed","paper":{"title":"DREAM: Efficient Dataset Distillation by Representative Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Kai Wang, Wei Jiang, Yang You, Yanqing Liu, Zheng Zhu","submitted_at":"2023-02-28T08:48:45Z","abstract_excerpt":"Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by matching synthetic images and the original ones regarding gradients, embedding distributions, or training trajectories. Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.\n  We argue that random sampling overlooks the evenness of the selected sample distribution, which may res"},"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":"2302.14416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T08:48:45Z","cross_cats_sorted":[],"title_canon_sha256":"58ef2023850bf9836e6d7a41a0504706aac648dc9f891be3ac146531a2ff7a54","abstract_canon_sha256":"f39a7c7c3262a9437696f50128fa813dd08e1636f64a2e60f163651c9e5cc782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:00.809441Z","signature_b64":"nnlrdqr9lb04R+oAQ8QqHo0a/IXCMEYOwL0pzVouUM379nIvtFx2LcgG0RxnY+Wz0hEuFyTUTbOV/koF0VP7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3200b9676a65be212b2ca171537d5496d705dae1dfba377df2d048b21e6e1225","last_reissued_at":"2026-07-05T06:46:00.808945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:00.808945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DREAM: Efficient Dataset Distillation by Representative Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Kai Wang, Wei Jiang, Yang You, Yanqing Liu, Zheng Zhu","submitted_at":"2023-02-28T08:48:45Z","abstract_excerpt":"Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by matching synthetic images and the original ones regarding gradients, embedding distributions, or training trajectories. Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.\n  We argue that random sampling overlooks the evenness of the selected sample distribution, which may res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14416","kind":"arxiv","version":3},"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/2302.14416/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":"2302.14416","created_at":"2026-07-05T06:46:00.809006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14416v3","created_at":"2026-07-05T06:46:00.809006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14416","created_at":"2026-07-05T06:46:00.809006+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIALSZ3KMW7C","created_at":"2026-07-05T06:46:00.809006+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIALSZ3KMW7CCKZM","created_at":"2026-07-05T06:46:00.809006+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIALSZ3K","created_at":"2026-07-05T06:46:00.809006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00916","citing_title":"Condensing Large-Scale Datasets Directly with Minimal Information Loss","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23482","citing_title":"Multimodal Distribution Matching for Vision-Language Dataset Distillation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":280,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3","json":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3.json","graph_json":"https://pith.science/api/pith-number/GIALSZ3KMW7CCKZMUFYVG7KUS3/graph.json","events_json":"https://pith.science/api/pith-number/GIALSZ3KMW7CCKZMUFYVG7KUS3/events.json","paper":"https://pith.science/paper/GIALSZ3K"},"agent_actions":{"view_html":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3","download_json":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3.json","view_paper":"https://pith.science/paper/GIALSZ3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14416&json=true","fetch_graph":"https://pith.science/api/pith-number/GIALSZ3KMW7CCKZMUFYVG7KUS3/graph.json","fetch_events":"https://pith.science/api/pith-number/GIALSZ3KMW7CCKZMUFYVG7KUS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3/action/storage_attestation","attest_author":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3/action/author_attestation","sign_citation":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3/action/citation_signature","submit_replication":"https://pith.science/pith/GIALSZ3KMW7CCKZMUFYVG7KUS3/action/replication_record"}},"created_at":"2026-07-05T06:46:00.809006+00:00","updated_at":"2026-07-05T06:46:00.809006+00:00"}