{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKKQZM2WI5XMXQ3TFAAEON3UMR","short_pith_number":"pith:ZKKQZM2W","schema_version":"1.0","canonical_sha256":"ca950cb356476ecbc3732800473774645fe69656f01f510f264ab865ee63763a","source":{"kind":"arxiv","id":"2411.12523","version":3},"attestation_state":"computed","paper":{"title":"Data Pruning in Generative Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiangtao Wang, Rania Briq, Stefan Kesselheim","submitted_at":"2024-11-19T14:13:25Z","abstract_excerpt":"Data pruning is the problem of identifying a core subset that is most beneficial to training and discarding the remainder. While pruning strategies are well studied for discriminative models like those used in classification, little research has gone into their application to generative models. Generative models aim to estimate the underlying distribution of the data, so presumably they should benefit from larger datasets. In this work we aim to shed light on the accuracy of this statement, specifically answer the question of whether data pruning for generative diffusion models could have a po"},"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":"2411.12523","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T14:13:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e76b523ec99718a7b63451650ab639081cf071fdbab5275335f6b24dc86ba032","abstract_canon_sha256":"4efd391a51a7a6ccd60c61a5b9f4b380bf14754ed429c5f9912c4b1da92869c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:25.746716Z","signature_b64":"GsO1PZb+cNlP/mFxlRQK/1tonaJHLGR6lbTkUjFYynE22FMg8iD43j9UrFcHP67DAAa8JpqpybRORq1fNhy4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca950cb356476ecbc3732800473774645fe69656f01f510f264ab865ee63763a","last_reissued_at":"2026-07-05T10:31:25.745684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:25.745684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Pruning in Generative Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiangtao Wang, Rania Briq, Stefan Kesselheim","submitted_at":"2024-11-19T14:13:25Z","abstract_excerpt":"Data pruning is the problem of identifying a core subset that is most beneficial to training and discarding the remainder. While pruning strategies are well studied for discriminative models like those used in classification, little research has gone into their application to generative models. Generative models aim to estimate the underlying distribution of the data, so presumably they should benefit from larger datasets. In this work we aim to shed light on the accuracy of this statement, specifically answer the question of whether data pruning for generative diffusion models could have a po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12523","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/2411.12523/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":"2411.12523","created_at":"2026-07-05T10:31:25.745834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12523v3","created_at":"2026-07-05T10:31:25.745834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12523","created_at":"2026-07-05T10:31:25.745834+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKKQZM2WI5XM","created_at":"2026-07-05T10:31:25.745834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKKQZM2WI5XMXQ3T","created_at":"2026-07-05T10:31:25.745834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKKQZM2W","created_at":"2026-07-05T10:31:25.745834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16079","citing_title":"The Amazing Stability of Flow Matching","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR","json":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR.json","graph_json":"https://pith.science/api/pith-number/ZKKQZM2WI5XMXQ3TFAAEON3UMR/graph.json","events_json":"https://pith.science/api/pith-number/ZKKQZM2WI5XMXQ3TFAAEON3UMR/events.json","paper":"https://pith.science/paper/ZKKQZM2W"},"agent_actions":{"view_html":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR","download_json":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR.json","view_paper":"https://pith.science/paper/ZKKQZM2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12523&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKKQZM2WI5XMXQ3TFAAEON3UMR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKKQZM2WI5XMXQ3TFAAEON3UMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR/action/storage_attestation","attest_author":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR/action/author_attestation","sign_citation":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR/action/citation_signature","submit_replication":"https://pith.science/pith/ZKKQZM2WI5XMXQ3TFAAEON3UMR/action/replication_record"}},"created_at":"2026-07-05T10:31:25.745834+00:00","updated_at":"2026-07-05T10:31:25.745834+00:00"}