{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ENPNPDUFLG3SVW2SPDNUVOI45Y","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":"16db4500351188381b7761816997a8d5fe4ef1c0d0769b9916ca86197a3c3556","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-10T17:57:03Z","title_canon_sha256":"6f84d9a748a391e5266bff9b91b8c524f34de7a8e67c6590b6b0e823ee4cf7b1"},"schema_version":"1.0","source":{"id":"2006.05987","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05987","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05987v3","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05987","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"ENPNPDUFLG3S","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"ENPNPDUFLG3SVW2S","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"ENPNPDUF","created_at":"2026-07-05T02:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:bc4f33581f8868f0b583941aaa22fa777c75626aced965be019c67f149569c86","target":"graph","created_at":"2026-07-05T02:22:16Z","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/2006.05987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is a study of fine-tuning of BERT contextual representations, with focus on commonly observed instabilities in few-sample scenarios. We identify several factors that cause this instability: the common use of a non-standard optimization method with biased gradient estimation; the limited applicability of significant parts of the BERT network for down-stream tasks; and the prevalent practice of using a pre-determined, and small number of training iterations. We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instabili","authors_text":"Arzoo Katiyar, Felix Wu, Kilian Q. Weinberger, Tianyi Zhang, Yoav Artzi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-10T17:57:03Z","title":"Revisiting Few-sample BERT Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05987","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":"sha256:56d7f06063b8af02a028282818d9ad4b0383bafeb6f7c6caadf1550d9129572b","target":"record","created_at":"2026-07-05T02:22:16Z","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":"16db4500351188381b7761816997a8d5fe4ef1c0d0769b9916ca86197a3c3556","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-10T17:57:03Z","title_canon_sha256":"6f84d9a748a391e5266bff9b91b8c524f34de7a8e67c6590b6b0e823ee4cf7b1"},"schema_version":"1.0","source":{"id":"2006.05987","kind":"arxiv","version":3}},"canonical_sha256":"235ed78e8559b72adb5278db4ab91cee060c48f122170203659932ad6699c3c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"235ed78e8559b72adb5278db4ab91cee060c48f122170203659932ad6699c3c6","first_computed_at":"2026-07-05T02:22:16.377416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:16.377416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W+wPLxwiEOO8lp3Kp6Q0l4vj4fKDbuFrgp8LiGvE2iV2EdVsS8z30k8C66dGHO+0S/lHD+6GWZfwgJj0rYD9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:16.377809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05987","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56d7f06063b8af02a028282818d9ad4b0383bafeb6f7c6caadf1550d9129572b","sha256:bc4f33581f8868f0b583941aaa22fa777c75626aced965be019c67f149569c86"],"state_sha256":"1005bbb25c759085719a5efdefb72a95e3e4c6ce0fe7c0198dbe6b60e289c830"}