{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LKJTVSILRR37N7WBAZLTSLZZ54","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":"a33d99d3947808249f3b1ebbcf9ecaca03937406b52f7a5f4b59b57424a31c3c","cross_cats_sorted":["cs.CV","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T14:52:46Z","title_canon_sha256":"524177fb2cdf079963651188e71af7d2553f9a638fa3057843a0a06713061eb3"},"schema_version":"1.0","source":{"id":"2206.02659","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02659","created_at":"2026-07-05T07:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02659v6","created_at":"2026-07-05T07:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02659","created_at":"2026-07-05T07:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"LKJTVSILRR37","created_at":"2026-07-05T07:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"LKJTVSILRR37N7WB","created_at":"2026-07-05T07:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"LKJTVSIL","created_at":"2026-07-05T07:27:22Z"}],"graph_snapshots":[{"event_id":"sha256:cf12bc1500b3619cd54286e836b2c4f71bcc8bf4b8aa512519f7eb0d92c73216","target":"graph","created_at":"2026-07-05T07:27:22Z","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/2206.02659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider fine-tuning a pretrained deep neural network on a target task. We study the generalization properties of fine-tuning to understand the problem of overfitting, which has often been observed (e.g., when the target dataset is small or when the training labels are noisy). Existing generalization measures for deep networks depend on notions such as distance from the initialization (i.e., the pretrained network) of the fine-tuned model and noise stability properties of deep networks. This paper identifies a Hessian-based distance measure through PAC-Bayesian analysis, which is shown to c","authors_text":"Dongyue Li, Haotian Ju, Hongyang R. Zhang","cross_cats":["cs.CV","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T14:52:46Z","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02659","kind":"arxiv","version":6},"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":"sha256:73eba9df2adec1a310cc912338f9c81520b146da88f22b1ab5ea4051867e378a","target":"record","created_at":"2026-07-05T07:27:22Z","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":"a33d99d3947808249f3b1ebbcf9ecaca03937406b52f7a5f4b59b57424a31c3c","cross_cats_sorted":["cs.CV","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T14:52:46Z","title_canon_sha256":"524177fb2cdf079963651188e71af7d2553f9a638fa3057843a0a06713061eb3"},"schema_version":"1.0","source":{"id":"2206.02659","kind":"arxiv","version":6}},"canonical_sha256":"5a933ac90b8c77f6fec10657392f39ef034a66c2e3a11c72005764e5a3c72502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a933ac90b8c77f6fec10657392f39ef034a66c2e3a11c72005764e5a3c72502","first_computed_at":"2026-07-05T07:27:22.782564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:22.782564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JsOCt7sI0nf/DTQbZeUOcp1o0VSMy874gT1zt9+uh+MbthNSxPPXI7QVKqsEZPPzDrbf0umb9rbkyyrjDfMJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:22.783047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02659","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73eba9df2adec1a310cc912338f9c81520b146da88f22b1ab5ea4051867e378a","sha256:cf12bc1500b3619cd54286e836b2c4f71bcc8bf4b8aa512519f7eb0d92c73216"],"state_sha256":"0345683d4f5590f11e4f9e6cef6bb1ba10229edddbdaa18cbb2733d685789daa"}