{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SGPA7DUHMJGUCHX6HHVC3H563Y","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":"e43e8bfa38eeda05efe6b040c3822da6680ddca22f6104fba05b13a312bb5e0d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T20:50:14Z","title_canon_sha256":"4ad77d25e64e8d938b0f7c4974d0cff79c2cada46b74136cbdac11f98c7a25f1"},"schema_version":"1.0","source":{"id":"1908.05344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05344","created_at":"2026-07-04T23:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05344v1","created_at":"2026-07-04T23:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05344","created_at":"2026-07-04T23:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"SGPA7DUHMJGU","created_at":"2026-07-04T23:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"SGPA7DUHMJGUCHX6","created_at":"2026-07-04T23:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"SGPA7DUH","created_at":"2026-07-04T23:56:50Z"}],"graph_snapshots":[{"event_id":"sha256:9a17cf320266323fcd75f38a81260001ef357fcc9d181a5437d5ce8efb4ddb8c","target":"graph","created_at":"2026-07-04T23:56:50Z","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/1908.05344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Taking word sequences as the input, typical named entity recognition (NER) models neglect errors from pre-processing (e.g., tokenization). However, these errors can influence the model performance greatly, especially for noisy texts like tweets. Here, we introduce Neural-Char-CRF, a raw-to-end framework that is more robust to pre-processing errors. It takes raw character sequences as inputs and makes end-to-end predictions. Word embedding and contextualized representation models are further tailored to capture textual signals for each character instead of each word. Our model neither requires ","authors_text":"Dandong Yin, Heng Ji, Jiawei Han, Jingbo Shang, Liyuan Liu, Shaowen Wang, Xiang Ren, Zihan Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T20:50:14Z","title":"Raw-to-End Name Entity Recognition in Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05344","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":"sha256:99a0592ac04b4eb3c47b66b7b7dd1995a07c1635c0cfc0fc5c265748f6781358","target":"record","created_at":"2026-07-04T23:56:50Z","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":"e43e8bfa38eeda05efe6b040c3822da6680ddca22f6104fba05b13a312bb5e0d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T20:50:14Z","title_canon_sha256":"4ad77d25e64e8d938b0f7c4974d0cff79c2cada46b74136cbdac11f98c7a25f1"},"schema_version":"1.0","source":{"id":"1908.05344","kind":"arxiv","version":1}},"canonical_sha256":"919e0f8e87624d411efe39ea2d9fbede21bce817e355470d6b0a6c31c63d95da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"919e0f8e87624d411efe39ea2d9fbede21bce817e355470d6b0a6c31c63d95da","first_computed_at":"2026-07-04T23:56:50.598228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:56:50.598228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQVsPfnV8cKGyV8ymKwhFI+js1Si02qL0G/B73SIPfCMAXe+pd5ZBejf8E1jUKgAh9LVu8K3Vp/YKiYVpZmhDw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:56:50.598605Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99a0592ac04b4eb3c47b66b7b7dd1995a07c1635c0cfc0fc5c265748f6781358","sha256:9a17cf320266323fcd75f38a81260001ef357fcc9d181a5437d5ce8efb4ddb8c"],"state_sha256":"5aaf215da67bbe7a54919be0d11619f7d43d9bc3a0a88d4f91c0fe83b2b7c929"}