{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MQ747VJBLP7OS5MWGVHF5ASQEX","short_pith_number":"pith:MQ747VJB","canonical_record":{"source":{"id":"1805.02023","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-05T08:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"03e41ca837e66ec267aa4e3272ad43931aa18d81a46eaa144dae135902650566","abstract_canon_sha256":"d5e4e2870a79eec86cacce0c9a56d65e1c902cf15e0e9ff046c3599626da2e16"},"schema_version":"1.0"},"canonical_sha256":"643fcfd5215bfee97596354e5e825025fb6d1321a652e92b1f9edc70603764c2","source":{"kind":"arxiv","id":"1805.02023","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.02023","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"1805.02023v4","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02023","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"MQ747VJBLP7O","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MQ747VJBLP7OS5MW","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MQ747VJB","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MQ747VJBLP7OS5MWGVHF5ASQEX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.02023","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-05T08:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"03e41ca837e66ec267aa4e3272ad43931aa18d81a46eaa144dae135902650566","abstract_canon_sha256":"d5e4e2870a79eec86cacce0c9a56d65e1c902cf15e0e9ff046c3599626da2e16"},"schema_version":"1.0"},"canonical_sha256":"643fcfd5215bfee97596354e5e825025fb6d1321a652e92b1f9edc70603764c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:27.954972Z","signature_b64":"odI993O/Sf4RwJCHf/e1l7FyK7IQTCq8wqE0vxOqTuj5Mq3zlORuCFE3lJpLNvxGD/44Mpukv4J6PyN4A0v5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643fcfd5215bfee97596354e5e825025fb6d1321a652e92b1f9edc70603764c2","last_reissued_at":"2026-05-18T00:11:27.954548Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:27.954548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.02023","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6CcdCq42C3m1VcJHQRSgCZouli/OoDasGNhtaOyd6N4rbf2GwTIN6afN1g0PZOrfW0bMX/tWF1XPsV0zTqkCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T17:05:31.857083Z"},"content_sha256":"d7312fc64d6507c55261ad39932d12abd48f409b849af88ec7291bbe6b534646","schema_version":"1.0","event_id":"sha256:d7312fc64d6507c55261ad39932d12abd48f409b849af88ec7291bbe6b534646"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MQ747VJBLP7OS5MWGVHF5ASQEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chinese NER Using Lattice LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Yang, Yue Zhang","submitted_at":"2018-05-05T08:48:32Z","abstract_excerpt":"We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information. Compared with word-based methods, lattice LSTM does not suffer from segmentation errors. Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results. Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02023","kind":"arxiv","version":4},"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":"2026-05-18T00:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/hFLNQu9zxOZJMY5/lawSa7cYtXVsU3nJgpq85cJvjnm4Bw4BBsVvWzfl5UM9z1OxQT8kmtyL0z1fVPrApiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T17:05:31.857511Z"},"content_sha256":"a0ef42e071a6e44beb429aed0d6a7619ee217ad87c96e8464a401722290f3775","schema_version":"1.0","event_id":"sha256:a0ef42e071a6e44beb429aed0d6a7619ee217ad87c96e8464a401722290f3775"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/bundle.json","state_url":"https://pith.science/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/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":"2026-08-02T17:05:31Z","links":{"resolver":"https://pith.science/pith/MQ747VJBLP7OS5MWGVHF5ASQEX","bundle":"https://pith.science/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/bundle.json","state":"https://pith.science/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQ747VJBLP7OS5MWGVHF5ASQEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MQ747VJBLP7OS5MWGVHF5ASQEX","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":"d5e4e2870a79eec86cacce0c9a56d65e1c902cf15e0e9ff046c3599626da2e16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-05T08:48:32Z","title_canon_sha256":"03e41ca837e66ec267aa4e3272ad43931aa18d81a46eaa144dae135902650566"},"schema_version":"1.0","source":{"id":"1805.02023","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.02023","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"1805.02023v4","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02023","created_at":"2026-05-18T00:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"MQ747VJBLP7O","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MQ747VJBLP7OS5MW","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MQ747VJB","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:a0ef42e071a6e44beb429aed0d6a7619ee217ad87c96e8464a401722290f3775","target":"graph","created_at":"2026-05-18T00:11:27Z","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":"We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information. Compared with word-based methods, lattice LSTM does not suffer from segmentation errors. Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results. Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baseline","authors_text":"Jie Yang, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-05T08:48:32Z","title":"Chinese NER Using Lattice LSTM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02023","kind":"arxiv","version":4},"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:d7312fc64d6507c55261ad39932d12abd48f409b849af88ec7291bbe6b534646","target":"record","created_at":"2026-05-18T00:11:27Z","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":"d5e4e2870a79eec86cacce0c9a56d65e1c902cf15e0e9ff046c3599626da2e16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-05T08:48:32Z","title_canon_sha256":"03e41ca837e66ec267aa4e3272ad43931aa18d81a46eaa144dae135902650566"},"schema_version":"1.0","source":{"id":"1805.02023","kind":"arxiv","version":4}},"canonical_sha256":"643fcfd5215bfee97596354e5e825025fb6d1321a652e92b1f9edc70603764c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"643fcfd5215bfee97596354e5e825025fb6d1321a652e92b1f9edc70603764c2","first_computed_at":"2026-05-18T00:11:27.954548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:27.954548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odI993O/Sf4RwJCHf/e1l7FyK7IQTCq8wqE0vxOqTuj5Mq3zlORuCFE3lJpLNvxGD/44Mpukv4J6PyN4A0v5Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:27.954972Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.02023","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7312fc64d6507c55261ad39932d12abd48f409b849af88ec7291bbe6b534646","sha256:a0ef42e071a6e44beb429aed0d6a7619ee217ad87c96e8464a401722290f3775"],"state_sha256":"64c8dcead009c31827b5c52297982ad1de9c184eb4faa16535cd58dbdb55eaa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BwgjruuNFAU+b+9i48f/he0XulsF4xJPm0XBDoxXxh+4bppQb51IaXBEvVd9Boul4CAaOukKQHiLHP7fdBqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T17:05:31.860996Z","bundle_sha256":"d52395af107249530880a98b5331f8ea59d8a8f5f6107d0811ad7cdfcce6f053"}}