{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6X2QZWE5ZZL62SYD3UH34KGXWS","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":"7d295c834c66301f3392e651a10b07e09d12294c26d05039ada8f14370cdf4b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T17:19:56Z","title_canon_sha256":"1f5cfc68597bd570889adef84c760b8a91733d28b40e60cb5dee9e3e8c5ce7fa"},"schema_version":"1.0","source":{"id":"2109.05003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05003","created_at":"2026-07-05T03:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05003v1","created_at":"2026-07-05T03:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05003","created_at":"2026-07-05T03:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"6X2QZWE5ZZL6","created_at":"2026-07-05T03:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"6X2QZWE5ZZL62SYD","created_at":"2026-07-05T03:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"6X2QZWE5","created_at":"2026-07-05T03:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:4b9b1406a3c89cc246cf4ecfc52e5b09009e5537f44c4a17778bd67367202782","target":"graph","created_at":"2026-07-05T03:13:18Z","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/2109.05003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data","authors_text":"Heng Ji, Jiawei Han, Jiaxin Huang, Xuan Wang, Yu Meng, Yunyi Zhang, Yu Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T17:19:56Z","title":"Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05003","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:f14a2a8208a3a3fd05b15739c6b5674eccce53939d720040599f421ae604b5b5","target":"record","created_at":"2026-07-05T03:13:18Z","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":"7d295c834c66301f3392e651a10b07e09d12294c26d05039ada8f14370cdf4b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T17:19:56Z","title_canon_sha256":"1f5cfc68597bd570889adef84c760b8a91733d28b40e60cb5dee9e3e8c5ce7fa"},"schema_version":"1.0","source":{"id":"2109.05003","kind":"arxiv","version":1}},"canonical_sha256":"f5f50cd89dce57ed4b03dd0fbe28d7b4aa04ac8902138ce92c4699216384ccf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5f50cd89dce57ed4b03dd0fbe28d7b4aa04ac8902138ce92c4699216384ccf9","first_computed_at":"2026-07-05T03:13:18.325618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:18.325618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"geR42qzJJ2OZ7BEpHE6tD9JcmhPiJg6qJTvvt7Y468d//xFVcxmOXwlt6P4P4wlBmnZyBT6sWBjABnQY4e8PCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:18.326134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f14a2a8208a3a3fd05b15739c6b5674eccce53939d720040599f421ae604b5b5","sha256:4b9b1406a3c89cc246cf4ecfc52e5b09009e5537f44c4a17778bd67367202782"],"state_sha256":"397c2f229ad91f79c0f3a9f383fbeb98edf5246d7dc3cf47b71940b70e35f7fa"}