{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NLM3GQ4URS46LXYEWY5MQQINLP","short_pith_number":"pith:NLM3GQ4U","schema_version":"1.0","canonical_sha256":"6ad9b343948cb9e5df04b63ac8410d5bd149d68350abbc0bbdda4003be101101","source":{"kind":"arxiv","id":"2308.04020","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Augmentation with Large-scale Unconditional Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haomiao Ni, Jiarong Ye, Peng Jin, Sharon X. Huang, Yuan Xue","submitted_at":"2023-08-08T03:34:04Z","abstract_excerpt":"Deep learning based medical image recognition systems often require a substantial amount of training data with expert annotations, which can be expensive and time-consuming to obtain. Recently, synthetic augmentation techniques have been proposed to mitigate the issue by generating realistic images conditioned on class labels. However, the effectiveness of these methods heavily depends on the representation capability of the trained generative model, which cannot be guaranteed without sufficient labeled training data. To further reduce the dependency on annotated data, we propose a synthetic a"},"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":"2308.04020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-08T03:34:04Z","cross_cats_sorted":[],"title_canon_sha256":"c5ce9b15bb34bddbbe7bcc2e8d4329480b350f18dacd3ba6f82e8931b0656171","abstract_canon_sha256":"073584aee1e7f827c21e0a4cf0dddf3008f4adf0cbadacd41a09c2bcad4e0a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:21.106655Z","signature_b64":"n4GG8bTq+pB6PE97UZ4zi5kGax7BwT2yqbmcZU4NW5E4yjetUN8JAtKiVaQ9/bMUuaIK2GH44/TG/Cb+IDl+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad9b343948cb9e5df04b63ac8410d5bd149d68350abbc0bbdda4003be101101","last_reissued_at":"2026-07-05T06:39:21.106182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:21.106182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Augmentation with Large-scale Unconditional Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haomiao Ni, Jiarong Ye, Peng Jin, Sharon X. Huang, Yuan Xue","submitted_at":"2023-08-08T03:34:04Z","abstract_excerpt":"Deep learning based medical image recognition systems often require a substantial amount of training data with expert annotations, which can be expensive and time-consuming to obtain. Recently, synthetic augmentation techniques have been proposed to mitigate the issue by generating realistic images conditioned on class labels. However, the effectiveness of these methods heavily depends on the representation capability of the trained generative model, which cannot be guaranteed without sufficient labeled training data. To further reduce the dependency on annotated data, we propose a synthetic a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04020","kind":"arxiv","version":1},"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/2308.04020/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":"2308.04020","created_at":"2026-07-05T06:39:21.106238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04020v1","created_at":"2026-07-05T06:39:21.106238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04020","created_at":"2026-07-05T06:39:21.106238+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLM3GQ4URS46","created_at":"2026-07-05T06:39:21.106238+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLM3GQ4URS46LXYE","created_at":"2026-07-05T06:39:21.106238+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLM3GQ4U","created_at":"2026-07-05T06:39:21.106238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17975","citing_title":"Enabling PSO-Secure Synthetic Data Sharing Using Diversity-Aware Diffusion Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP","json":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP.json","graph_json":"https://pith.science/api/pith-number/NLM3GQ4URS46LXYEWY5MQQINLP/graph.json","events_json":"https://pith.science/api/pith-number/NLM3GQ4URS46LXYEWY5MQQINLP/events.json","paper":"https://pith.science/paper/NLM3GQ4U"},"agent_actions":{"view_html":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP","download_json":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP.json","view_paper":"https://pith.science/paper/NLM3GQ4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04020&json=true","fetch_graph":"https://pith.science/api/pith-number/NLM3GQ4URS46LXYEWY5MQQINLP/graph.json","fetch_events":"https://pith.science/api/pith-number/NLM3GQ4URS46LXYEWY5MQQINLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP/action/storage_attestation","attest_author":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP/action/author_attestation","sign_citation":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP/action/citation_signature","submit_replication":"https://pith.science/pith/NLM3GQ4URS46LXYEWY5MQQINLP/action/replication_record"}},"created_at":"2026-07-05T06:39:21.106238+00:00","updated_at":"2026-07-05T06:39:21.106238+00:00"}