{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZTVKZSMR24CMI7B2ZPC7UWUOLD","short_pith_number":"pith:ZTVKZSMR","canonical_record":{"source":{"id":"2012.05426","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T02:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"560b05c5e11ecc4cb6af663e2967e3de097ed21707b6b853935c06190436f559","abstract_canon_sha256":"0e8d5ccdb25a3043513222573b8314d72433dcdb06f2dd23f7b704fb41d95feb"},"schema_version":"1.0"},"canonical_sha256":"cceaacc991d704c47c3acbc5fa5a8e58f9c77d83a190834d275f0bf8a2ca85b5","source":{"kind":"arxiv","id":"2012.05426","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05426","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05426v5","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05426","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZTVKZSMR24CM","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZTVKZSMR24CMI7B2","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZTVKZSMR","created_at":"2026-07-05T02:24:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZTVKZSMR24CMI7B2ZPC7UWUOLD","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05426","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T02:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"560b05c5e11ecc4cb6af663e2967e3de097ed21707b6b853935c06190436f559","abstract_canon_sha256":"0e8d5ccdb25a3043513222573b8314d72433dcdb06f2dd23f7b704fb41d95feb"},"schema_version":"1.0"},"canonical_sha256":"cceaacc991d704c47c3acbc5fa5a8e58f9c77d83a190834d275f0bf8a2ca85b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:12.550077Z","signature_b64":"Ax0PWLEBKvQZI87D+ZKjoYNa3ACE0BA0e/tVDO5NzjiutjuLnQ3oN0mHrafJvavV1zgRuCb1EO7OsptDWazHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cceaacc991d704c47c3acbc5fa5a8e58f9c77d83a190834d275f0bf8a2ca85b5","last_reissued_at":"2026-07-05T02:24:12.549609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:12.549609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05426","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbNTfz5Yo0ZG0DxR47Z9Upf/zNCLRDz5BynK5f1pOsN/N/7vXcS1pTTK5cnQE7JTnLdlUZ+6mLI/6pieD4CUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:08:05.707801Z"},"content_sha256":"42a9552246a5c18088e2e4b19bc4273e75315c607a7500e7ce26d7d6ab683e2a","schema_version":"1.0","event_id":"sha256:42a9552246a5c18088e2e4b19bc4273e75315c607a7500e7ce26d7d6ab683e2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZTVKZSMR24CMI7B2ZPC7UWUOLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lemao Liu, Shuming Shi, Yangming Li","submitted_at":"2020-12-10T02:53:59Z","abstract_excerpt":"In many scenarios, named entity recognition (NER) models severely suffer from unlabeled entity problem, where the entities of a sentence may not be fully annotated. Through empirical studies performed on synthetic datasets, we find two causes of performance degradation. One is the reduction of annotated entities and the other is treating unlabeled entities as negative instances. The first cause has less impact than the second one and can be mitigated by adopting pretraining language models. The second cause seriously misguides a model in training and greatly affects its performances. Based on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05426","kind":"arxiv","version":5},"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/2012.05426/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":"2026-07-05T02:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TRAWt0CYRWs7z8kzqQ6Fd++FhiPb2UyKo3P4KQPR7loip74QhE2sGsdLmYoK4DDU9z/Gt5A/donki+l9CFSwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:08:05.708365Z"},"content_sha256":"5ad0935a64e143ce6380418dd8d7a254874655cb324525b195baf1d365c1590c","schema_version":"1.0","event_id":"sha256:5ad0935a64e143ce6380418dd8d7a254874655cb324525b195baf1d365c1590c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/bundle.json","state_url":"https://pith.science/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/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":"2026-08-18T23:08:05Z","links":{"resolver":"https://pith.science/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD","bundle":"https://pith.science/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/bundle.json","state":"https://pith.science/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTVKZSMR24CMI7B2ZPC7UWUOLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZTVKZSMR24CMI7B2ZPC7UWUOLD","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":"0e8d5ccdb25a3043513222573b8314d72433dcdb06f2dd23f7b704fb41d95feb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T02:53:59Z","title_canon_sha256":"560b05c5e11ecc4cb6af663e2967e3de097ed21707b6b853935c06190436f559"},"schema_version":"1.0","source":{"id":"2012.05426","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05426","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05426v5","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05426","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZTVKZSMR24CM","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZTVKZSMR24CMI7B2","created_at":"2026-07-05T02:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZTVKZSMR","created_at":"2026-07-05T02:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:5ad0935a64e143ce6380418dd8d7a254874655cb324525b195baf1d365c1590c","target":"graph","created_at":"2026-07-05T02:24:12Z","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/2012.05426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many scenarios, named entity recognition (NER) models severely suffer from unlabeled entity problem, where the entities of a sentence may not be fully annotated. Through empirical studies performed on synthetic datasets, we find two causes of performance degradation. One is the reduction of annotated entities and the other is treating unlabeled entities as negative instances. The first cause has less impact than the second one and can be mitigated by adopting pretraining language models. The second cause seriously misguides a model in training and greatly affects its performances. Based on ","authors_text":"Lemao Liu, Shuming Shi, Yangming Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T02:53:59Z","title":"Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05426","kind":"arxiv","version":5},"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":"sha256:42a9552246a5c18088e2e4b19bc4273e75315c607a7500e7ce26d7d6ab683e2a","target":"record","created_at":"2026-07-05T02:24:12Z","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":"0e8d5ccdb25a3043513222573b8314d72433dcdb06f2dd23f7b704fb41d95feb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T02:53:59Z","title_canon_sha256":"560b05c5e11ecc4cb6af663e2967e3de097ed21707b6b853935c06190436f559"},"schema_version":"1.0","source":{"id":"2012.05426","kind":"arxiv","version":5}},"canonical_sha256":"cceaacc991d704c47c3acbc5fa5a8e58f9c77d83a190834d275f0bf8a2ca85b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cceaacc991d704c47c3acbc5fa5a8e58f9c77d83a190834d275f0bf8a2ca85b5","first_computed_at":"2026-07-05T02:24:12.549609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:12.549609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ax0PWLEBKvQZI87D+ZKjoYNa3ACE0BA0e/tVDO5NzjiutjuLnQ3oN0mHrafJvavV1zgRuCb1EO7OsptDWazHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:12.550077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05426","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a9552246a5c18088e2e4b19bc4273e75315c607a7500e7ce26d7d6ab683e2a","sha256:5ad0935a64e143ce6380418dd8d7a254874655cb324525b195baf1d365c1590c"],"state_sha256":"c23addd3258bff35dc601913aece44a39c1014a88d98282e7293d73d3e9330d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DjWRy4sF2N4sQCHDn2ga2/p91iI9rtcMDhHjFm9hy3xslRCVJKvbj6nJMhOmrkSv07Lb4RntOo5xtGE6GU9TDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:08:05.712809Z","bundle_sha256":"6b1528a209605728e99e3fea50a5ebfa591a6198b1590a0df4ab03ff361cd04a"}}