{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6JXJ2BTPLSEKH3Z4GFMUVBGIYP","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":"69dcd65af3c76b96d5aa29498775d826f248c08ef6a7a58d407f57ce1c825e54","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T02:25:12Z","title_canon_sha256":"00f2efc7124f0c6efe28f878ce715513cd71cd1d647c9cf3f8d9fc180071536d"},"schema_version":"1.0","source":{"id":"2210.02871","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02871","created_at":"2026-07-05T06:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02871v3","created_at":"2026-07-05T06:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02871","created_at":"2026-07-05T06:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"6JXJ2BTPLSEK","created_at":"2026-07-05T06:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"6JXJ2BTPLSEKH3Z4","created_at":"2026-07-05T06:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"6JXJ2BTP","created_at":"2026-07-05T06:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:f3b817c8b6d3b95b7a4cce09e77821acf2a345f4a8d329f1ddcb220c788dc847","target":"graph","created_at":"2026-07-05T06:18:59Z","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/2210.02871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing tasks. However, direct fine-tuning of the pre-trained model may be suboptimal if there exist large discrepancies across data domains for pre-training and fine-tuning. To tackle this issue, several previous studies have proposed further pre-training strategies, where we continue to pre-train the model on the target unlabeled dataset before fine-tuning. Howev","authors_text":"Juho Lee, Kenji Kawaguchi, Minki Kang, Seanie Lee, Sung Ju Hwang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T02:25:12Z","title":"Self-Distillation for Further Pre-training of Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02871","kind":"arxiv","version":3},"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":"sha256:1615fca0d439614c9c1a659abe4d7d0ef0e8f2c7d40e5fe76d0f05dc47a48ac2","target":"record","created_at":"2026-07-05T06:18:59Z","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":"69dcd65af3c76b96d5aa29498775d826f248c08ef6a7a58d407f57ce1c825e54","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T02:25:12Z","title_canon_sha256":"00f2efc7124f0c6efe28f878ce715513cd71cd1d647c9cf3f8d9fc180071536d"},"schema_version":"1.0","source":{"id":"2210.02871","kind":"arxiv","version":3}},"canonical_sha256":"f26e9d066f5c88a3ef3c31594a84c8c3daaede4455fdb0c41a3a27c8933e11b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f26e9d066f5c88a3ef3c31594a84c8c3daaede4455fdb0c41a3a27c8933e11b0","first_computed_at":"2026-07-05T06:18:59.889612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:59.889612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GlhX/y8FJtJItuhzbzOpJRqg34rlXdSJJuPOcVBbB3kka85uhSepsGKO5vMAlyi//NaFnIIr6yit0gtJU2JpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:59.890072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02871","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1615fca0d439614c9c1a659abe4d7d0ef0e8f2c7d40e5fe76d0f05dc47a48ac2","sha256:f3b817c8b6d3b95b7a4cce09e77821acf2a345f4a8d329f1ddcb220c788dc847"],"state_sha256":"28e3e73a5daaf6259e396902e4bd076c34a22d9b163272da5f97d43d930a23ab"}