{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O2NCWSI3ZA2QBPOOHZGMIBICBT","short_pith_number":"pith:O2NCWSI3","schema_version":"1.0","canonical_sha256":"769a2b491bc83500bdce3e4cc405020cc51d0260b9971acf5261163aebdeabb3","source":{"kind":"arxiv","id":"2304.10253","version":2},"attestation_state":"computed","paper":{"title":"Image retrieval outperforms diffusion models on data augmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chris Russell, Dominik Zietlow, Florian Wenzel, Francesco Locatello, Max F. Burg, Max Horn, Osama Makansi","submitted_at":"2023-04-20T12:21:30Z","abstract_excerpt":"Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it remains an open question to which extent these models contribute to downstream classification performance. In particular, it remains unclear if they generalize enough to improve over directly using the additional data of their pre-training process for augmentation. We systematically evaluate a range of existing methods to generate images from diffusion models"},"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":"2304.10253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:21:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"03319c4e7758f675243243ef927ebb13bb9cde7d1f8af7d26ddf23352bbb2f18","abstract_canon_sha256":"85974d5bcdb1fbce5025a94c6a96a585089d75149acc75000680b9b30ab784e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:26.214908Z","signature_b64":"es7zl8Qo5irImxYc4+9eKBSULbVB+r0kwu1ZvRWjElK1gZJq4jYglkW4AcROcMCFYqE45L3TOg1nYu25j4i0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"769a2b491bc83500bdce3e4cc405020cc51d0260b9971acf5261163aebdeabb3","last_reissued_at":"2026-07-05T07:18:26.214418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:26.214418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image retrieval outperforms diffusion models on data augmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chris Russell, Dominik Zietlow, Florian Wenzel, Francesco Locatello, Max F. Burg, Max Horn, Osama Makansi","submitted_at":"2023-04-20T12:21:30Z","abstract_excerpt":"Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it remains an open question to which extent these models contribute to downstream classification performance. In particular, it remains unclear if they generalize enough to improve over directly using the additional data of their pre-training process for augmentation. We systematically evaluate a range of existing methods to generate images from diffusion models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10253","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/2304.10253/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":"2304.10253","created_at":"2026-07-05T07:18:26.214476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10253v2","created_at":"2026-07-05T07:18:26.214476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10253","created_at":"2026-07-05T07:18:26.214476+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2NCWSI3ZA2Q","created_at":"2026-07-05T07:18:26.214476+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2NCWSI3ZA2QBPOO","created_at":"2026-07-05T07:18:26.214476+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2NCWSI3","created_at":"2026-07-05T07:18:26.214476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT","json":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT.json","graph_json":"https://pith.science/api/pith-number/O2NCWSI3ZA2QBPOOHZGMIBICBT/graph.json","events_json":"https://pith.science/api/pith-number/O2NCWSI3ZA2QBPOOHZGMIBICBT/events.json","paper":"https://pith.science/paper/O2NCWSI3"},"agent_actions":{"view_html":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT","download_json":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT.json","view_paper":"https://pith.science/paper/O2NCWSI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10253&json=true","fetch_graph":"https://pith.science/api/pith-number/O2NCWSI3ZA2QBPOOHZGMIBICBT/graph.json","fetch_events":"https://pith.science/api/pith-number/O2NCWSI3ZA2QBPOOHZGMIBICBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT/action/storage_attestation","attest_author":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT/action/author_attestation","sign_citation":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT/action/citation_signature","submit_replication":"https://pith.science/pith/O2NCWSI3ZA2QBPOOHZGMIBICBT/action/replication_record"}},"created_at":"2026-07-05T07:18:26.214476+00:00","updated_at":"2026-07-05T07:18:26.214476+00:00"}