{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5EQXW344N7BLC3O3MXJZ7AL7EI","short_pith_number":"pith:5EQXW344","schema_version":"1.0","canonical_sha256":"e9217b6f9c6fc2b16ddb65d39f817f22155daa29efb6a62e04f4ebd6b632f843","source":{"kind":"arxiv","id":"2401.15422","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Data Augmentation in Large Model Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chenlu Guo, Xu Wang, Yi Chang, Yuan Wu, Yue Zhou","submitted_at":"2024-01-27T14:19:33Z","abstract_excerpt":"Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of these large models necessitates vast quantities of high-quality data, and with continuous updates to these models, the existing reservoir of high-quality data may soon be depleted. This challenge has catalyzed a surge in research focused on data augmentation methods. Leveraging large models, these data augmentation techniques have outperformed traditional appro"},"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":"2401.15422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-27T14:19:33Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"13bdb821af32190cd2ae434049f4c11034b95bcbf2a10260bbf8a2ec007ddf27","abstract_canon_sha256":"67a44451f91fa0eb243a5a22493ae4af6b2244c7f93a191abe666b25d70c9659"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:38.674552Z","signature_b64":"Y399qjIl6ojNWU92kShE0AK8AVT1dUSc/GFnfOCBr+VnlDQVHTYHueT0YY95uJsSw37TUurt3Rsk33MheujECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9217b6f9c6fc2b16ddb65d39f817f22155daa29efb6a62e04f4ebd6b632f843","last_reissued_at":"2026-07-05T07:51:38.674089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:38.674089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Data Augmentation in Large Model Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chenlu Guo, Xu Wang, Yi Chang, Yuan Wu, Yue Zhou","submitted_at":"2024-01-27T14:19:33Z","abstract_excerpt":"Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of these large models necessitates vast quantities of high-quality data, and with continuous updates to these models, the existing reservoir of high-quality data may soon be depleted. This challenge has catalyzed a surge in research focused on data augmentation methods. Leveraging large models, these data augmentation techniques have outperformed traditional appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15422","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/2401.15422/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":"2401.15422","created_at":"2026-07-05T07:51:38.674144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15422v2","created_at":"2026-07-05T07:51:38.674144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15422","created_at":"2026-07-05T07:51:38.674144+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EQXW344N7BL","created_at":"2026-07-05T07:51:38.674144+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EQXW344N7BLC3O3","created_at":"2026-07-05T07:51:38.674144+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EQXW344","created_at":"2026-07-05T07:51:38.674144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00378","citing_title":"NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI","json":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI.json","graph_json":"https://pith.science/api/pith-number/5EQXW344N7BLC3O3MXJZ7AL7EI/graph.json","events_json":"https://pith.science/api/pith-number/5EQXW344N7BLC3O3MXJZ7AL7EI/events.json","paper":"https://pith.science/paper/5EQXW344"},"agent_actions":{"view_html":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI","download_json":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI.json","view_paper":"https://pith.science/paper/5EQXW344","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15422&json=true","fetch_graph":"https://pith.science/api/pith-number/5EQXW344N7BLC3O3MXJZ7AL7EI/graph.json","fetch_events":"https://pith.science/api/pith-number/5EQXW344N7BLC3O3MXJZ7AL7EI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI/action/storage_attestation","attest_author":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI/action/author_attestation","sign_citation":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI/action/citation_signature","submit_replication":"https://pith.science/pith/5EQXW344N7BLC3O3MXJZ7AL7EI/action/replication_record"}},"created_at":"2026-07-05T07:51:38.674144+00:00","updated_at":"2026-07-05T07:51:38.674144+00:00"}