{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:553RN3Z4V5L2WQEFMXQBFXMAB2","short_pith_number":"pith:553RN3Z4","schema_version":"1.0","canonical_sha256":"ef7716ef3caf57ab408565e012dd800ea52666f80a555e935b4737db5c061a14","source":{"kind":"arxiv","id":"2301.04272","version":2},"attestation_state":"computed","paper":{"title":"Data Distillation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.LG","authors_text":"Julian McAuley, Noveen Sachdeva","submitted_at":"2023-01-11T02:25:10Z","abstract_excerpt":"The popularity of deep learning has led to the curation of a vast number of massive and multifarious datasets. Despite having close-to-human performance on individual tasks, training parameter-hungry models on large datasets poses multi-faceted problems such as (a) high model-training time; (b) slow research iteration; and (c) poor eco-sustainability. As an alternative, data distillation approaches aim to synthesize terse data summaries, which can serve as effective drop-in replacements of the original dataset for scenarios like model training, inference, architecture search, etc. In this surv"},"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":"2301.04272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T02:25:10Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"d7934aeed38cc37de7de423e9804fbb9a1e253941547cd84500347d94289060d","abstract_canon_sha256":"71945292840a376450ec637e07f4f755091d91f0c74eaff0a1bebab51924d833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:14.222966Z","signature_b64":"L0UE279xkTKFC7J0/mRXpJIAgE3rUYlLYCS2hTFTok55xkp8TAAtXaYgATu7Ii7Jqnvc3V1J/2B1O5AM+FEiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7716ef3caf57ab408565e012dd800ea52666f80a555e935b4737db5c061a14","last_reissued_at":"2026-07-05T06:54:14.222463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:14.222463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Distillation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.LG","authors_text":"Julian McAuley, Noveen Sachdeva","submitted_at":"2023-01-11T02:25:10Z","abstract_excerpt":"The popularity of deep learning has led to the curation of a vast number of massive and multifarious datasets. Despite having close-to-human performance on individual tasks, training parameter-hungry models on large datasets poses multi-faceted problems such as (a) high model-training time; (b) slow research iteration; and (c) poor eco-sustainability. As an alternative, data distillation approaches aim to synthesize terse data summaries, which can serve as effective drop-in replacements of the original dataset for scenarios like model training, inference, architecture search, etc. In this surv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04272","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/2301.04272/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":"2301.04272","created_at":"2026-07-05T06:54:14.222528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04272v2","created_at":"2026-07-05T06:54:14.222528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04272","created_at":"2026-07-05T06:54:14.222528+00:00"},{"alias_kind":"pith_short_12","alias_value":"553RN3Z4V5L2","created_at":"2026-07-05T06:54:14.222528+00:00"},{"alias_kind":"pith_short_16","alias_value":"553RN3Z4V5L2WQEF","created_at":"2026-07-05T06:54:14.222528+00:00"},{"alias_kind":"pith_short_8","alias_value":"553RN3Z4","created_at":"2026-07-05T06:54:14.222528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29837","citing_title":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21166","citing_title":"The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02081","citing_title":"ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11705","citing_title":"CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset Selection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":283,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2","json":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2.json","graph_json":"https://pith.science/api/pith-number/553RN3Z4V5L2WQEFMXQBFXMAB2/graph.json","events_json":"https://pith.science/api/pith-number/553RN3Z4V5L2WQEFMXQBFXMAB2/events.json","paper":"https://pith.science/paper/553RN3Z4"},"agent_actions":{"view_html":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2","download_json":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2.json","view_paper":"https://pith.science/paper/553RN3Z4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04272&json=true","fetch_graph":"https://pith.science/api/pith-number/553RN3Z4V5L2WQEFMXQBFXMAB2/graph.json","fetch_events":"https://pith.science/api/pith-number/553RN3Z4V5L2WQEFMXQBFXMAB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2/action/storage_attestation","attest_author":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2/action/author_attestation","sign_citation":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2/action/citation_signature","submit_replication":"https://pith.science/pith/553RN3Z4V5L2WQEFMXQBFXMAB2/action/replication_record"}},"created_at":"2026-07-05T06:54:14.222528+00:00","updated_at":"2026-07-05T06:54:14.222528+00:00"}