{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EQXW344N7BLC3O3MXJZ7AL7EI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"67a44451f91fa0eb243a5a22493ae4af6b2244c7f93a191abe666b25d70c9659","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-27T14:19:33Z","title_canon_sha256":"13bdb821af32190cd2ae434049f4c11034b95bcbf2a10260bbf8a2ec007ddf27"},"schema_version":"1.0","source":{"id":"2401.15422","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15422","created_at":"2026-07-05T07:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15422v2","created_at":"2026-07-05T07:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15422","created_at":"2026-07-05T07:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"5EQXW344N7BL","created_at":"2026-07-05T07:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"5EQXW344N7BLC3O3","created_at":"2026-07-05T07:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"5EQXW344","created_at":"2026-07-05T07:51:38Z"}],"graph_snapshots":[{"event_id":"sha256:6f334c425093c9459f5593f41936ed5396685019b75807e2f3fa8ab02cc2f0d1","target":"graph","created_at":"2026-07-05T07:51:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.15422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenlu Guo, Xu Wang, Yi Chang, Yuan Wu, Yue Zhou","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-27T14:19:33Z","title":"A Survey on Data Augmentation in Large Model Era"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15422","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5425b626d2a37b8839e560060b4e4bb2b3e742b513036a6cfe078bff790b8416","target":"record","created_at":"2026-07-05T07:51:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"67a44451f91fa0eb243a5a22493ae4af6b2244c7f93a191abe666b25d70c9659","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-27T14:19:33Z","title_canon_sha256":"13bdb821af32190cd2ae434049f4c11034b95bcbf2a10260bbf8a2ec007ddf27"},"schema_version":"1.0","source":{"id":"2401.15422","kind":"arxiv","version":2}},"canonical_sha256":"e9217b6f9c6fc2b16ddb65d39f817f22155daa29efb6a62e04f4ebd6b632f843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9217b6f9c6fc2b16ddb65d39f817f22155daa29efb6a62e04f4ebd6b632f843","first_computed_at":"2026-07-05T07:51:38.674089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:38.674089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y399qjIl6ojNWU92kShE0AK8AVT1dUSc/GFnfOCBr+VnlDQVHTYHueT0YY95uJsSw37TUurt3Rsk33MheujECw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:38.674552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15422","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5425b626d2a37b8839e560060b4e4bb2b3e742b513036a6cfe078bff790b8416","sha256:6f334c425093c9459f5593f41936ed5396685019b75807e2f3fa8ab02cc2f0d1"],"state_sha256":"253b79764697c7ba711a3ae04418deee558eb555802d500def244411376bcd73"}