{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VQ4F3AILVE2DU6HCUWGWGROTEH","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":"db7598967e1adb9be3d40d795cf7a681c678cad9d8a268d373ffe1392e1e5af1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T07:37:43Z","title_canon_sha256":"c3e4c408baecfb3605d020e2712ea8a71a7de1f2f38596ede9f32b1c0d0430cd"},"schema_version":"1.0","source":{"id":"2108.13655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13655","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13655v2","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13655","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"VQ4F3AILVE2D","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"VQ4F3AILVE2DU6HC","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"VQ4F3AIL","created_at":"2026-07-05T04:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:51f5bd0b290f6bd9cee5037a5dc2df21567a39476eec923798da0455429c297f","target":"graph","created_at":"2026-07-05T04:06:16Z","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/2108.13655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as NER, data augmentation methods often suffer from token-label misalignment, which leads to unsatsifactory performance. In this work, we propose Masked Entity Language Modeling (MELM) as a novel data augmentation framework for low-resource NER. To alleviate the token-label misalignment issue, we explicitly inject NER labels into sentence context, and thus the fine-tuned MELM is able to predict masked entity tokens by explicitly conditioning on their labels. Th","authors_text":"Chunyan Miao, Erik Cambria, Lidong Bing, Luo Si, Ran Zhou, Ruidan He, Xin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T07:37:43Z","title":"MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13655","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":"sha256:2734920c1fe79011eb286d611b43ebdacb27a9f72ef7e51ec0b2dbdd144da655","target":"record","created_at":"2026-07-05T04:06:16Z","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":"db7598967e1adb9be3d40d795cf7a681c678cad9d8a268d373ffe1392e1e5af1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T07:37:43Z","title_canon_sha256":"c3e4c408baecfb3605d020e2712ea8a71a7de1f2f38596ede9f32b1c0d0430cd"},"schema_version":"1.0","source":{"id":"2108.13655","kind":"arxiv","version":2}},"canonical_sha256":"ac385d810ba9343a78e2a58d6345d321c538018bff6d5684c37da7bf397e07c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac385d810ba9343a78e2a58d6345d321c538018bff6d5684c37da7bf397e07c8","first_computed_at":"2026-07-05T04:06:16.618874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:16.618874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pbvj01Qy0gMMjOB53B0z2+v45FV5PeBDx79YKgDA1SKclpHd1igasxd491MgilcsplfCVfyXPN4ErBj0IL62Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:16.619617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2734920c1fe79011eb286d611b43ebdacb27a9f72ef7e51ec0b2dbdd144da655","sha256:51f5bd0b290f6bd9cee5037a5dc2df21567a39476eec923798da0455429c297f"],"state_sha256":"08f2af99139233f8a5bcf24d0dfce8dc046d4b29e080e8b67c2166e96c1f0a36"}