{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4OQRHN7EPJBFWBLDVS66DYIHL","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":"bbc0ae8bac50932764ea53bc1d2017225df8260564b34b31bea6344b96341147","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:53:58Z","title_canon_sha256":"d1a1b1b3839365a67b94141564158f2b8f4d8c1c9ac447af91b113515219a8cd"},"schema_version":"1.0","source":{"id":"2210.05497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05497","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05497v1","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05497","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"O4OQRHN7EPJB","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"O4OQRHN7EPJBFWBL","created_at":"2026-07-05T05:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"O4OQRHN7","created_at":"2026-07-05T05:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:33f51dc67cd4d5970f101b8b7dc13cdbe908e405a32acceed4475fbe5c301110","target":"graph","created_at":"2026-07-05T05:05:17Z","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/2210.05497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model generalization. However, SAM adds a perturbation to each model parameter equally (but not all parameters contribute equally to the optimization of training), which we argue is sub-optimal and will lead to excessive computation. In this paper, we propose a novel optimization procedure, namely FSAM, which introduces a Fisher mask to improve the efficiency and per","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Li Shen, Peng Mi, Qihuang Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:53:58Z","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05497","kind":"arxiv","version":1},"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:f149f8e14f1e0dc6b91bd25e5b12cb4b6fdc0f73f19841ba6b8a312cc00fcfa4","target":"record","created_at":"2026-07-05T05:05:17Z","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":"bbc0ae8bac50932764ea53bc1d2017225df8260564b34b31bea6344b96341147","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T14:53:58Z","title_canon_sha256":"d1a1b1b3839365a67b94141564158f2b8f4d8c1c9ac447af91b113515219a8cd"},"schema_version":"1.0","source":{"id":"2210.05497","kind":"arxiv","version":1}},"canonical_sha256":"771d089dbf23d212d82b1d65ef0f083afc5c82b52083f9b469672c31138d4ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"771d089dbf23d212d82b1d65ef0f083afc5c82b52083f9b469672c31138d4ba9","first_computed_at":"2026-07-05T05:05:17.379974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:17.379974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qPi/3+k6aaFXhIkbfzsno4LBmVYPJWLl1nuwBat229WUaYL0sUaCvIO4SDB8cIxiW/dfZWetWySuZVHF8xzaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:17.380471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f149f8e14f1e0dc6b91bd25e5b12cb4b6fdc0f73f19841ba6b8a312cc00fcfa4","sha256:33f51dc67cd4d5970f101b8b7dc13cdbe908e405a32acceed4475fbe5c301110"],"state_sha256":"445c421fe4b9d45582f4a9db47c2c4f8293e247e3137fa2abf268e9e32fdb921"}