{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VV2JY2O6PUWYJYL3LMJMMLDVET","short_pith_number":"pith:VV2JY2O6","canonical_record":{"source":{"id":"2312.02253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:35:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e2cc67c3caede9319cba25dfd382933a0b46d8ac5398c9a41dd6876188cc007a","abstract_canon_sha256":"978d25440148a4c5877efb00e06a85365183f92f86b5f1c12aabf7aca4544cf0"},"schema_version":"1.0"},"canonical_sha256":"ad749c69de7d2d84e17b5b12c62c7524d2f9865b5272bc6bd6abca0f7d8da7a2","source":{"kind":"arxiv","id":"2312.02253","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02253","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02253v2","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02253","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_12","alias_value":"VV2JY2O6PUWY","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_16","alias_value":"VV2JY2O6PUWYJYL3","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_8","alias_value":"VV2JY2O6","created_at":"2026-07-05T10:02:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VV2JY2O6PUWYJYL3LMJMMLDVET","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:35:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e2cc67c3caede9319cba25dfd382933a0b46d8ac5398c9a41dd6876188cc007a","abstract_canon_sha256":"978d25440148a4c5877efb00e06a85365183f92f86b5f1c12aabf7aca4544cf0"},"schema_version":"1.0"},"canonical_sha256":"ad749c69de7d2d84e17b5b12c62c7524d2f9865b5272bc6bd6abca0f7d8da7a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:42.450971Z","signature_b64":"lwy1QbI1mJRvbF2cOMxpQz5mMvJ+8pbxsnkudG3cPW58Tji1huyPjvP99H3wHnpnDCNBCMutAMkHF1x09/afDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad749c69de7d2d84e17b5b12c62c7524d2f9865b5272bc6bd6abca0f7d8da7a2","last_reissued_at":"2026-07-05T10:02:42.450520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:42.450520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02253","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ADzJA9NDSS8iE4h045RSixGcKgZif6lCE/ifpEbUl9nFMAF/WurlEhvMSzYMPDX05tlz+d0ZCqw9KbH7rvNwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:39:31.871367Z"},"content_sha256":"2c9692142476d904d7bd615d56bdf8045b00fb5fc2268f20a6b89a17ae7d7e6d","schema_version":"1.0","event_id":"sha256:2c9692142476d904d7bd615d56bdf8045b00fb5fc2268f20a6b89a17ae7d7e6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VV2JY2O6PUWYJYL3LMJMMLDVET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenchen Zhu, Fanyi Xiao, Raghuraman Krishnamoorthi, Sean Culatana, Yong Jae Lee, Zhuoran Yu","submitted_at":"2023-12-04T18:35:27Z","abstract_excerpt":"Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training images from the finetuned model can enhance an ImageNet classifier's performance. However, performance degrades as synthetic images outnumber real ones. In this paper, we explore whether generative fine-tuning is essential for this improvement and whether it is possible to further scale up training using more synthetic data. We present a new framework lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02253","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/2312.02253/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4CSOFeqEbV7yiZU0V6RtWdmgrTjR2u6URv8tDDfei65p7hhBVMUsnCxmj4YFwqfgJLn9CV0BDL/mqMHAzJWfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:39:31.872298Z"},"content_sha256":"12b9470f4522ea9421b5c0bf574573fca6d08dd7ab519452578e148ca5961ac5","schema_version":"1.0","event_id":"sha256:12b9470f4522ea9421b5c0bf574573fca6d08dd7ab519452578e148ca5961ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/bundle.json","state_url":"https://pith.science/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T23:39:31Z","links":{"resolver":"https://pith.science/pith/VV2JY2O6PUWYJYL3LMJMMLDVET","bundle":"https://pith.science/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/bundle.json","state":"https://pith.science/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VV2JY2O6PUWYJYL3LMJMMLDVET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VV2JY2O6PUWYJYL3LMJMMLDVET","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":"978d25440148a4c5877efb00e06a85365183f92f86b5f1c12aabf7aca4544cf0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:35:27Z","title_canon_sha256":"e2cc67c3caede9319cba25dfd382933a0b46d8ac5398c9a41dd6876188cc007a"},"schema_version":"1.0","source":{"id":"2312.02253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02253","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02253v2","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02253","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_12","alias_value":"VV2JY2O6PUWY","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_16","alias_value":"VV2JY2O6PUWYJYL3","created_at":"2026-07-05T10:02:42Z"},{"alias_kind":"pith_short_8","alias_value":"VV2JY2O6","created_at":"2026-07-05T10:02:42Z"}],"graph_snapshots":[{"event_id":"sha256:12b9470f4522ea9421b5c0bf574573fca6d08dd7ab519452578e148ca5961ac5","target":"graph","created_at":"2026-07-05T10:02:42Z","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/2312.02253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training images from the finetuned model can enhance an ImageNet classifier's performance. However, performance degrades as synthetic images outnumber real ones. In this paper, we explore whether generative fine-tuning is essential for this improvement and whether it is possible to further scale up training using more synthetic data. We present a new framework lever","authors_text":"Chenchen Zhu, Fanyi Xiao, Raghuraman Krishnamoorthi, Sean Culatana, Yong Jae Lee, Zhuoran Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:35:27Z","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02253","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":"sha256:2c9692142476d904d7bd615d56bdf8045b00fb5fc2268f20a6b89a17ae7d7e6d","target":"record","created_at":"2026-07-05T10:02:42Z","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":"978d25440148a4c5877efb00e06a85365183f92f86b5f1c12aabf7aca4544cf0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:35:27Z","title_canon_sha256":"e2cc67c3caede9319cba25dfd382933a0b46d8ac5398c9a41dd6876188cc007a"},"schema_version":"1.0","source":{"id":"2312.02253","kind":"arxiv","version":2}},"canonical_sha256":"ad749c69de7d2d84e17b5b12c62c7524d2f9865b5272bc6bd6abca0f7d8da7a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad749c69de7d2d84e17b5b12c62c7524d2f9865b5272bc6bd6abca0f7d8da7a2","first_computed_at":"2026-07-05T10:02:42.450520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:42.450520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lwy1QbI1mJRvbF2cOMxpQz5mMvJ+8pbxsnkudG3cPW58Tji1huyPjvP99H3wHnpnDCNBCMutAMkHF1x09/afDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:42.450971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c9692142476d904d7bd615d56bdf8045b00fb5fc2268f20a6b89a17ae7d7e6d","sha256:12b9470f4522ea9421b5c0bf574573fca6d08dd7ab519452578e148ca5961ac5"],"state_sha256":"093b92c23a4872cb10d4d6a45dec37b3951d1ce6173f6c180e5d459ba2ed52c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LENYytoKvBoPOHLj+NOtc0OjcKqhPAL2tQxMEgKvj8z04KGnv8DfCOOE81z0ndG9FSu3xp7Y6P7bvL545cQUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:39:31.878339Z","bundle_sha256":"4135e552a1ee4cf51a651f7a92077071609a9137ec90195e7e84908e46f021ee"}}