{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ROBZ2NOMSVW3WRB7FXW27HFXLW","short_pith_number":"pith:ROBZ2NOM","schema_version":"1.0","canonical_sha256":"8b839d35cc956dbb443f2dedaf9cb75db5e6e4faf0512e5b6563a002a439d109","source":{"kind":"arxiv","id":"1603.01354","version":5},"attestation_state":"computed","paper":{"title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Xuezhe Ma","submitted_at":"2016-03-04T05:55:02Z","abstract_excerpt":"State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling task"},"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":"1603.01354","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-04T05:55:02Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"1aa71c9a914b2bb75e2bf625b91bfaa6e5b5d3b7fa711f1d954a16e98fed088b","abstract_canon_sha256":"d764034fa5c17733a510a2a0e0282c216136eb79dd794aeb8208871cd228fa49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:23.495897Z","signature_b64":"AF6y1Q6150Wl6m23Fcmh9ASPtwj3XO1HzmGCt75zvUrQeYrZRRO8eK2R3Pp2VWWMNRmNi3cBhI3637xA106qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b839d35cc956dbb443f2dedaf9cb75db5e6e4faf0512e5b6563a002a439d109","last_reissued_at":"2026-05-18T01:13:23.495405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:23.495405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Xuezhe Ma","submitted_at":"2016-03-04T05:55:02Z","abstract_excerpt":"State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01354","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":""},"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":"1603.01354","created_at":"2026-05-18T01:13:23.495483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.01354v5","created_at":"2026-05-18T01:13:23.495483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01354","created_at":"2026-05-18T01:13:23.495483+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROBZ2NOMSVW3","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROBZ2NOMSVW3WRB7","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROBZ2NOM","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":166,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09427","citing_title":"ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW","json":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW.json","graph_json":"https://pith.science/api/pith-number/ROBZ2NOMSVW3WRB7FXW27HFXLW/graph.json","events_json":"https://pith.science/api/pith-number/ROBZ2NOMSVW3WRB7FXW27HFXLW/events.json","paper":"https://pith.science/paper/ROBZ2NOM"},"agent_actions":{"view_html":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW","download_json":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW.json","view_paper":"https://pith.science/paper/ROBZ2NOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.01354&json=true","fetch_graph":"https://pith.science/api/pith-number/ROBZ2NOMSVW3WRB7FXW27HFXLW/graph.json","fetch_events":"https://pith.science/api/pith-number/ROBZ2NOMSVW3WRB7FXW27HFXLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW/action/storage_attestation","attest_author":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW/action/author_attestation","sign_citation":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW/action/citation_signature","submit_replication":"https://pith.science/pith/ROBZ2NOMSVW3WRB7FXW27HFXLW/action/replication_record"}},"created_at":"2026-05-18T01:13:23.495483+00:00","updated_at":"2026-05-18T01:13:23.495483+00:00"}