{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X6YBNSU4BCFQNNSPI7HTSJPWAQ","short_pith_number":"pith:X6YBNSU4","schema_version":"1.0","canonical_sha256":"bfb016ca9c088b06b64f47cf3925f6041d172d80edb1b39757841792ee782206","source":{"kind":"arxiv","id":"1908.08676","version":3},"attestation_state":"computed","paper":{"title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leyang Cui, Yue Zhang","submitted_at":"2019-08-23T05:55:46Z","abstract_excerpt":"CRF has been used as a powerful model for statistical sequence labeling. For neural sequence labeling, however, BiLSTM-CRF does not always lead to better results compared with BiLSTM-softmax local classification. This can be because the simple Markov label transition model of CRF does not give much information gain over strong neural encoding. For better representing label sequences, we investigate a hierarchically-refined label attention network, which explicitly leverages label embeddings and captures potential long-term label dependency by giving each word incrementally refined label distri"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1908.08676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-23T05:55:46Z","cross_cats_sorted":[],"title_canon_sha256":"258f1278e99d0c2a7959fcf8f06d50840f8197d14ef7d6078b040529a2b6525f","abstract_canon_sha256":"af777fb7d199f959bffdcccf90ef83786414f2df1ccfe50fc5ae011292248bd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:39.014887Z","signature_b64":"RhTTmW4k9U9dpo44oyktbkmdFUiSgp+afktDnL/Eqxtd9yB5wtpK1wZs9fIWhdaQP5fobCwlc6NPRdWX9E0MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb016ca9c088b06b64f47cf3925f6041d172d80edb1b39757841792ee782206","last_reissued_at":"2026-07-05T00:17:39.014405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:39.014405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leyang Cui, Yue Zhang","submitted_at":"2019-08-23T05:55:46Z","abstract_excerpt":"CRF has been used as a powerful model for statistical sequence labeling. For neural sequence labeling, however, BiLSTM-CRF does not always lead to better results compared with BiLSTM-softmax local classification. This can be because the simple Markov label transition model of CRF does not give much information gain over strong neural encoding. For better representing label sequences, we investigate a hierarchically-refined label attention network, which explicitly leverages label embeddings and captures potential long-term label dependency by giving each word incrementally refined label distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08676","kind":"arxiv","version":3},"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/1908.08676/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.08676","created_at":"2026-07-05T00:17:39.014464+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08676v3","created_at":"2026-07-05T00:17:39.014464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08676","created_at":"2026-07-05T00:17:39.014464+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6YBNSU4BCFQ","created_at":"2026-07-05T00:17:39.014464+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6YBNSU4BCFQNNSP","created_at":"2026-07-05T00:17:39.014464+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6YBNSU4","created_at":"2026-07-05T00:17:39.014464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ","json":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ.json","graph_json":"https://pith.science/api/pith-number/X6YBNSU4BCFQNNSPI7HTSJPWAQ/graph.json","events_json":"https://pith.science/api/pith-number/X6YBNSU4BCFQNNSPI7HTSJPWAQ/events.json","paper":"https://pith.science/paper/X6YBNSU4"},"agent_actions":{"view_html":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ","download_json":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ.json","view_paper":"https://pith.science/paper/X6YBNSU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08676&json=true","fetch_graph":"https://pith.science/api/pith-number/X6YBNSU4BCFQNNSPI7HTSJPWAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/X6YBNSU4BCFQNNSPI7HTSJPWAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ/action/storage_attestation","attest_author":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ/action/author_attestation","sign_citation":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ/action/citation_signature","submit_replication":"https://pith.science/pith/X6YBNSU4BCFQNNSPI7HTSJPWAQ/action/replication_record"}},"created_at":"2026-07-05T00:17:39.014464+00:00","updated_at":"2026-07-05T00:17:39.014464+00:00"}