{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4FU37STXA2EQ2YRYTEBG5DSI3S","short_pith_number":"pith:4FU37STX","canonical_record":{"source":{"id":"1809.08386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-22T06:03:29Z","cross_cats_sorted":[],"title_canon_sha256":"e616b59855cf450a8283d27d4021e838c2b4e59bb7407d2ee495dd0db48c902e","abstract_canon_sha256":"aa5ff85e07ef7e3228640932915d1701d4f4a4ff6002da7846d56e5e1495e92c"},"schema_version":"1.0"},"canonical_sha256":"e169bfca7706890d623899026e8e48dca02895457bb3b13b6a52ae8541e1c224","source":{"kind":"arxiv","id":"1809.08386","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08386","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08386v1","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08386","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"4FU37STXA2EQ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4FU37STXA2EQ2YRY","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4FU37STX","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4FU37STXA2EQ2YRYTEBG5DSI3S","target":"record","payload":{"canonical_record":{"source":{"id":"1809.08386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-22T06:03:29Z","cross_cats_sorted":[],"title_canon_sha256":"e616b59855cf450a8283d27d4021e838c2b4e59bb7407d2ee495dd0db48c902e","abstract_canon_sha256":"aa5ff85e07ef7e3228640932915d1701d4f4a4ff6002da7846d56e5e1495e92c"},"schema_version":"1.0"},"canonical_sha256":"e169bfca7706890d623899026e8e48dca02895457bb3b13b6a52ae8541e1c224","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:08.664289Z","signature_b64":"IGuD2O0wBj7JAdxMTpoVr4pE1VLk/KalJszma7k+g9K51FDjWrDQpTq4ykrVeU5bEYuN4sTSZAjGdnVGYfATAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e169bfca7706890d623899026e8e48dca02895457bb3b13b6a52ae8541e1c224","last_reissued_at":"2026-05-18T00:05:08.663721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:08.663721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.08386","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lc6e5dtGfMCIXXp57c4ySZVJhJWsT3UuBIa/2RTtRvSPbe1W6hAH4y2WbCSZG6G/9lab3tIMt/Ya6bfNv+9nAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:59:21.113381Z"},"content_sha256":"2f7b19e3372deb780c3d181a57a49849a5a3359ec8a91e2c26daed04fb4696f0","schema_version":"1.0","event_id":"sha256:2f7b19e3372deb780c3d181a57a49849a5a3359ec8a91e2c26daed04fb4696f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4FU37STXA2EQ2YRYTEBG5DSI3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Byte-sized Approach to Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily Sheng, Prem Natarajan","submitted_at":"2018-09-22T06:03:29Z","abstract_excerpt":"In biomedical literature, it is common for entity boundaries to not align with word boundaries. Therefore, effective identification of entity spans requires approaches capable of considering tokens that are smaller than words. We introduce a novel, subword approach for named entity recognition (NER) that uses byte-pair encodings (BPE) in combination with convolutional and recurrent neural networks to produce byte-level tags of entities. We present experimental results on several standard biomedical datasets, namely the BioCreative VI Bio-ID, JNLPBA, and GENETAG datasets. We demonstrate competi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08386","kind":"arxiv","version":1},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UguqvQ4lZWAPiaTQDx9ZFAeupqqHhIagogVNAWaMaWH1MyjXW4uvO6a9dkNxAEydmFd7Skyw8CvL3s4ErtMcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:59:21.113720Z"},"content_sha256":"2a8142c47d997ff50015151d3adc43f96bfdff803937b950329465a52d608809","schema_version":"1.0","event_id":"sha256:2a8142c47d997ff50015151d3adc43f96bfdff803937b950329465a52d608809"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/bundle.json","state_url":"https://pith.science/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/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":"2026-06-29T17:59:21Z","links":{"resolver":"https://pith.science/pith/4FU37STXA2EQ2YRYTEBG5DSI3S","bundle":"https://pith.science/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/bundle.json","state":"https://pith.science/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FU37STXA2EQ2YRYTEBG5DSI3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4FU37STXA2EQ2YRYTEBG5DSI3S","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":"aa5ff85e07ef7e3228640932915d1701d4f4a4ff6002da7846d56e5e1495e92c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-22T06:03:29Z","title_canon_sha256":"e616b59855cf450a8283d27d4021e838c2b4e59bb7407d2ee495dd0db48c902e"},"schema_version":"1.0","source":{"id":"1809.08386","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08386","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08386v1","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08386","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"4FU37STXA2EQ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4FU37STXA2EQ2YRY","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4FU37STX","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:2a8142c47d997ff50015151d3adc43f96bfdff803937b950329465a52d608809","target":"graph","created_at":"2026-05-18T00:05:08Z","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"},"paper":{"abstract_excerpt":"In biomedical literature, it is common for entity boundaries to not align with word boundaries. Therefore, effective identification of entity spans requires approaches capable of considering tokens that are smaller than words. We introduce a novel, subword approach for named entity recognition (NER) that uses byte-pair encodings (BPE) in combination with convolutional and recurrent neural networks to produce byte-level tags of entities. We present experimental results on several standard biomedical datasets, namely the BioCreative VI Bio-ID, JNLPBA, and GENETAG datasets. We demonstrate competi","authors_text":"Emily Sheng, Prem Natarajan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-22T06:03:29Z","title":"A Byte-sized Approach to Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08386","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":"sha256:2f7b19e3372deb780c3d181a57a49849a5a3359ec8a91e2c26daed04fb4696f0","target":"record","created_at":"2026-05-18T00:05:08Z","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":"aa5ff85e07ef7e3228640932915d1701d4f4a4ff6002da7846d56e5e1495e92c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-22T06:03:29Z","title_canon_sha256":"e616b59855cf450a8283d27d4021e838c2b4e59bb7407d2ee495dd0db48c902e"},"schema_version":"1.0","source":{"id":"1809.08386","kind":"arxiv","version":1}},"canonical_sha256":"e169bfca7706890d623899026e8e48dca02895457bb3b13b6a52ae8541e1c224","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e169bfca7706890d623899026e8e48dca02895457bb3b13b6a52ae8541e1c224","first_computed_at":"2026-05-18T00:05:08.663721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:08.663721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IGuD2O0wBj7JAdxMTpoVr4pE1VLk/KalJszma7k+g9K51FDjWrDQpTq4ykrVeU5bEYuN4sTSZAjGdnVGYfATAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:08.664289Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.08386","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f7b19e3372deb780c3d181a57a49849a5a3359ec8a91e2c26daed04fb4696f0","sha256:2a8142c47d997ff50015151d3adc43f96bfdff803937b950329465a52d608809"],"state_sha256":"6f89a78b3cb21201efb9a8a8b18d25269ad5c1773c559ac0833b32bebfd3b1ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qu7VlhYmbtyx0YmnwzKATDQOao10rc49tKULbYd4zfIF740rj+MM3CRk0I638B6bIneQMnUg2o4Q2u62Dr8SBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T17:59:21.117842Z","bundle_sha256":"652ad09ee4d025a6e15dff2d43891219a49a88266dfe07b4dae09bba3274eac6"}}