{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CMC432PVIOF67H6OOROOHYURAC","short_pith_number":"pith:CMC432PV","schema_version":"1.0","canonical_sha256":"1305cde9f5438bef9fce745ce3e291009f5c31adfd9753607993d4201cb059c8","source":{"kind":"arxiv","id":"2312.03526","version":2},"attestation_state":"computed","paper":{"title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bei Shi, Daiwei Yu, Peng Sun, Tao Lin","submitted_at":"2023-12-06T14:40:05Z","abstract_excerpt":"Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands. Dataset distillation, as a recent emerging strategy, aims to compress real-world datasets for efficient training. However, this line of research currently struggle with large-scale and high-resolution datasets, hindering its practicality and feasibility. To this end, we re-examine the existing dataset distillation methods and identify three properties required for large-scale real-world applications, namely, realism, diversity, and efficiency. A"},"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":"2312.03526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T14:40:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58bb2fd854613c3e4fb3240cb6e05d4da99e98f5f7d8a618f577111ae4862fcc","abstract_canon_sha256":"9ed9236cfd8488c9891d68cc9412174c371c94f3e297eff2cf986453a3bf3aa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:47.531476Z","signature_b64":"HBlfNy71tSGEOy2er0KNxDzkOiPSpaSulaTMsVIl0Kr1xj6dx6am62Tgx/+1H0UYCxHSf9Lt96MQvAbQwscJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1305cde9f5438bef9fce745ce3e291009f5c31adfd9753607993d4201cb059c8","last_reissued_at":"2026-07-05T07:57:47.530892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:47.530892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bei Shi, Daiwei Yu, Peng Sun, Tao Lin","submitted_at":"2023-12-06T14:40:05Z","abstract_excerpt":"Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands. Dataset distillation, as a recent emerging strategy, aims to compress real-world datasets for efficient training. However, this line of research currently struggle with large-scale and high-resolution datasets, hindering its practicality and feasibility. To this end, we re-examine the existing dataset distillation methods and identify three properties required for large-scale real-world applications, namely, realism, diversity, and efficiency. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03526","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/2312.03526/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":"2312.03526","created_at":"2026-07-05T07:57:47.530950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03526v2","created_at":"2026-07-05T07:57:47.530950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03526","created_at":"2026-07-05T07:57:47.530950+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMC432PVIOF6","created_at":"2026-07-05T07:57:47.530950+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMC432PVIOF67H6O","created_at":"2026-07-05T07:57:47.530950+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMC432PV","created_at":"2026-07-05T07:57:47.530950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00916","citing_title":"Condensing Large-Scale Datasets Directly with Minimal Information Loss","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC","json":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC.json","graph_json":"https://pith.science/api/pith-number/CMC432PVIOF67H6OOROOHYURAC/graph.json","events_json":"https://pith.science/api/pith-number/CMC432PVIOF67H6OOROOHYURAC/events.json","paper":"https://pith.science/paper/CMC432PV"},"agent_actions":{"view_html":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC","download_json":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC.json","view_paper":"https://pith.science/paper/CMC432PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03526&json=true","fetch_graph":"https://pith.science/api/pith-number/CMC432PVIOF67H6OOROOHYURAC/graph.json","fetch_events":"https://pith.science/api/pith-number/CMC432PVIOF67H6OOROOHYURAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC/action/storage_attestation","attest_author":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC/action/author_attestation","sign_citation":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC/action/citation_signature","submit_replication":"https://pith.science/pith/CMC432PVIOF67H6OOROOHYURAC/action/replication_record"}},"created_at":"2026-07-05T07:57:47.530950+00:00","updated_at":"2026-07-05T07:57:47.530950+00:00"}