{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:L7RORUGQZGDEQNRZHX35NBTFWG","short_pith_number":"pith:L7RORUGQ","canonical_record":{"source":{"id":"2111.12292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T06:18:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ad90a4c4cc476017219aec3a507fff7fccd2b3b8608ca1c6536d2e32829a2b78","abstract_canon_sha256":"45227c8b1e95d423eb879fe382f65c5532d5b423b51233460fa8e7a17e793da3"},"schema_version":"1.0"},"canonical_sha256":"5fe2e8d0d0c9864836393df7d68665b1aaf1756149716814132f168257b4b0bd","source":{"kind":"arxiv","id":"2111.12292","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12292","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12292v2","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12292","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"L7RORUGQZGDE","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"L7RORUGQZGDEQNRZ","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"L7RORUGQ","created_at":"2026-07-05T04:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:L7RORUGQZGDEQNRZHX35NBTFWG","target":"record","payload":{"canonical_record":{"source":{"id":"2111.12292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T06:18:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ad90a4c4cc476017219aec3a507fff7fccd2b3b8608ca1c6536d2e32829a2b78","abstract_canon_sha256":"45227c8b1e95d423eb879fe382f65c5532d5b423b51233460fa8e7a17e793da3"},"schema_version":"1.0"},"canonical_sha256":"5fe2e8d0d0c9864836393df7d68665b1aaf1756149716814132f168257b4b0bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:34.526151Z","signature_b64":"MnnLgQQ6kIwsoAmaP2JhkyaTTFS/JWqWXTm1TTwBDRczsLgAqJC9kTYF/V1OHbK3qPKSDldnQEBbj5wMX5iODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe2e8d0d0c9864836393df7d68665b1aaf1756149716814132f168257b4b0bd","last_reissued_at":"2026-07-05T04:26:34.525573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:34.525573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.12292","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":"2026-07-05T04:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuRUEQXQposIWgi2W/4iyRS3aXKkIxXz6aOp6lne0x/tL9YpImQBG9kCwJBax+7QI0wk1JXnWkHXCOhKkmIWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:28:50.960375Z"},"content_sha256":"73c053e667a734af198c257d8dd25706ace6ad68d4117dd5fb843e694a9c044a","schema_version":"1.0","event_id":"sha256:73c053e667a734af198c257d8dd25706ace6ad68d4117dd5fb843e694a9c044a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:L7RORUGQZGDEQNRZHX35NBTFWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Fine-Tuning by Better Leveraging Pre-Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Antoni Chan, Hao Li, Qi Qian, Rong Jin, Xiangyang Ji, Yi Xu, Yuanhong Xu, Ziquan Liu","submitted_at":"2021-11-24T06:18:32Z","abstract_excerpt":"As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy once the number of training samples is increased in some vision tasks. In this work, we revisit this phenomenon from the perspective of generalization analysis by using excess risk bound which is popular in learning theory. The result reveals that the excess risk bound may have a weak depende"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12292","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/2111.12292/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":"2026-07-05T04:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqNCKIJSftF3ykT/09I+CSCJmThr5ldrAP3Wn6oVE0/2iNukTHlBVyVvlxabaF2oFpPcgx624TBbT0/ve1kQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:28:50.960883Z"},"content_sha256":"f9bd7fedb7f333228b909bdf9134b225d756e22bc87c200a70616f83e371f181","schema_version":"1.0","event_id":"sha256:f9bd7fedb7f333228b909bdf9134b225d756e22bc87c200a70616f83e371f181"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7RORUGQZGDEQNRZHX35NBTFWG/bundle.json","state_url":"https://pith.science/pith/L7RORUGQZGDEQNRZHX35NBTFWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7RORUGQZGDEQNRZHX35NBTFWG/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":"2026-08-06T01:28:50Z","links":{"resolver":"https://pith.science/pith/L7RORUGQZGDEQNRZHX35NBTFWG","bundle":"https://pith.science/pith/L7RORUGQZGDEQNRZHX35NBTFWG/bundle.json","state":"https://pith.science/pith/L7RORUGQZGDEQNRZHX35NBTFWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7RORUGQZGDEQNRZHX35NBTFWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L7RORUGQZGDEQNRZHX35NBTFWG","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":"45227c8b1e95d423eb879fe382f65c5532d5b423b51233460fa8e7a17e793da3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T06:18:32Z","title_canon_sha256":"ad90a4c4cc476017219aec3a507fff7fccd2b3b8608ca1c6536d2e32829a2b78"},"schema_version":"1.0","source":{"id":"2111.12292","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12292","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12292v2","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12292","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"L7RORUGQZGDE","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"L7RORUGQZGDEQNRZ","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"L7RORUGQ","created_at":"2026-07-05T04:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:f9bd7fedb7f333228b909bdf9134b225d756e22bc87c200a70616f83e371f181","target":"graph","created_at":"2026-07-05T04:26:34Z","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/2111.12292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy once the number of training samples is increased in some vision tasks. In this work, we revisit this phenomenon from the perspective of generalization analysis by using excess risk bound which is popular in learning theory. The result reveals that the excess risk bound may have a weak depende","authors_text":"Antoni Chan, Hao Li, Qi Qian, Rong Jin, Xiangyang Ji, Yi Xu, Yuanhong Xu, Ziquan Liu","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T06:18:32Z","title":"Improved Fine-Tuning by Better Leveraging Pre-Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12292","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":"sha256:73c053e667a734af198c257d8dd25706ace6ad68d4117dd5fb843e694a9c044a","target":"record","created_at":"2026-07-05T04:26:34Z","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":"45227c8b1e95d423eb879fe382f65c5532d5b423b51233460fa8e7a17e793da3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T06:18:32Z","title_canon_sha256":"ad90a4c4cc476017219aec3a507fff7fccd2b3b8608ca1c6536d2e32829a2b78"},"schema_version":"1.0","source":{"id":"2111.12292","kind":"arxiv","version":2}},"canonical_sha256":"5fe2e8d0d0c9864836393df7d68665b1aaf1756149716814132f168257b4b0bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fe2e8d0d0c9864836393df7d68665b1aaf1756149716814132f168257b4b0bd","first_computed_at":"2026-07-05T04:26:34.525573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:34.525573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MnnLgQQ6kIwsoAmaP2JhkyaTTFS/JWqWXTm1TTwBDRczsLgAqJC9kTYF/V1OHbK3qPKSDldnQEBbj5wMX5iODw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:34.526151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12292","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73c053e667a734af198c257d8dd25706ace6ad68d4117dd5fb843e694a9c044a","sha256:f9bd7fedb7f333228b909bdf9134b225d756e22bc87c200a70616f83e371f181"],"state_sha256":"7fbe9b6758beb74f565590a560f9f148b57efd4f49f0e1bfc55794186578bd31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzJmJqraqa6JYixs55CdMJ8C5PeUrMkeDXHoEOqLlz0ZeHi3ia1WU7CJx2cbuntX0AXB5hkEx6J2sshHBBfmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:28:50.966320Z","bundle_sha256":"e459c9057f4df5064adca24eaad2eeadb01591586d41f1901c718d099a8ad28e"}}