{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QO3ZYRTBNU63ZRVWTWNM2ZCDFT","short_pith_number":"pith:QO3ZYRTB","canonical_record":{"source":{"id":"1907.02679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T05:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"c4fd5288dc83bbfb65d068f419bbbdb9da491547cc324b5b275185776f1f9e7b","abstract_canon_sha256":"c25820eb438f2b7e14f15e8e8dab8ed5ff6664995d0300d0cfd4bf542c8e230b"},"schema_version":"1.0"},"canonical_sha256":"83b79c46616d3dbcc6b69d9acd64432ce6167ce424062a917d6496621427906d","source":{"kind":"arxiv","id":"1907.02679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02679","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02679v1","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02679","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"QO3ZYRTBNU63","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QO3ZYRTBNU63ZRVW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QO3ZYRTB","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QO3ZYRTBNU63ZRVWTWNM2ZCDFT","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T05:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"c4fd5288dc83bbfb65d068f419bbbdb9da491547cc324b5b275185776f1f9e7b","abstract_canon_sha256":"c25820eb438f2b7e14f15e8e8dab8ed5ff6664995d0300d0cfd4bf542c8e230b"},"schema_version":"1.0"},"canonical_sha256":"83b79c46616d3dbcc6b69d9acd64432ce6167ce424062a917d6496621427906d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:23.514429Z","signature_b64":"aArdbP5q2TVfF0TUM7T+CrA0DAYNNRZ/J42Rtjaz+kIHjcs1GlsE7nhQZHO1odFgCymS2y/7FXjZcToNp/llBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b79c46616d3dbcc6b69d9acd64432ce6167ce424062a917d6496621427906d","last_reissued_at":"2026-05-17T23:41:23.513783Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:23.513783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02679","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":"2026-05-17T23:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9t8MOqctQ97Br7d+h5oyu3T8we1VxAyo5ZqixSUpiaBJwv0WFWaix3wdy12W5IYV9PCWeVHmStUPa5t7QHSfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:14:17.019632Z"},"content_sha256":"14db43435090e87d24bc933906473e9e7fdbae67a5347d21cbb2ea48183dc19e","schema_version":"1.0","event_id":"sha256:14db43435090e87d24bc933906473e9e7fdbae67a5347d21cbb2ea48183dc19e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QO3ZYRTBNU63ZRVWTWNM2ZCDFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Camilo Thorne, Christian Druckenbrodt, Dat Quoc Nguyen, Karin Verspoor, Michelle Gregory, Saber A. Akhondi, Trevor Cohn, Zenan Zhai","submitted_at":"2019-07-05T05:19:46Z","abstract_excerpt":"Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in part to their structural and linguistic complexity. In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-level word representations and contextualized ELMo word representations for chemical patents. We compare word embeddings pre-trained on biomedical and chemical patent corpora. The effect of tokenizers optimized for the chemical domain on NER performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02679","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":"2026-05-17T23:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uct2F7u8PcKBSu1aFY3NdOY0CZV9SzqdIaJWVvxqW9kLESjEmEEAUa9hkPDYZE7FAC7MNn2zuXC9z6S5bzicCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:14:17.020424Z"},"content_sha256":"91a1310519b1a87e9403da59b6d8e4eaca329be8468d31d35a110a9810d4ab8c","schema_version":"1.0","event_id":"sha256:91a1310519b1a87e9403da59b6d8e4eaca329be8468d31d35a110a9810d4ab8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/bundle.json","state_url":"https://pith.science/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/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":"2026-05-26T06:14:17Z","links":{"resolver":"https://pith.science/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT","bundle":"https://pith.science/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/bundle.json","state":"https://pith.science/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QO3ZYRTBNU63ZRVWTWNM2ZCDFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QO3ZYRTBNU63ZRVWTWNM2ZCDFT","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":"c25820eb438f2b7e14f15e8e8dab8ed5ff6664995d0300d0cfd4bf542c8e230b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T05:19:46Z","title_canon_sha256":"c4fd5288dc83bbfb65d068f419bbbdb9da491547cc324b5b275185776f1f9e7b"},"schema_version":"1.0","source":{"id":"1907.02679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02679","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02679v1","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02679","created_at":"2026-05-17T23:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"QO3ZYRTBNU63","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QO3ZYRTBNU63ZRVW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QO3ZYRTB","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:91a1310519b1a87e9403da59b6d8e4eaca329be8468d31d35a110a9810d4ab8c","target":"graph","created_at":"2026-05-17T23:41:23Z","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":"Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in part to their structural and linguistic complexity. In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-level word representations and contextualized ELMo word representations for chemical patents. We compare word embeddings pre-trained on biomedical and chemical patent corpora. The effect of tokenizers optimized for the chemical domain on NER performance","authors_text":"Camilo Thorne, Christian Druckenbrodt, Dat Quoc Nguyen, Karin Verspoor, Michelle Gregory, Saber A. Akhondi, Trevor Cohn, Zenan Zhai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T05:19:46Z","title":"Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02679","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":"sha256:14db43435090e87d24bc933906473e9e7fdbae67a5347d21cbb2ea48183dc19e","target":"record","created_at":"2026-05-17T23:41:23Z","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":"c25820eb438f2b7e14f15e8e8dab8ed5ff6664995d0300d0cfd4bf542c8e230b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T05:19:46Z","title_canon_sha256":"c4fd5288dc83bbfb65d068f419bbbdb9da491547cc324b5b275185776f1f9e7b"},"schema_version":"1.0","source":{"id":"1907.02679","kind":"arxiv","version":1}},"canonical_sha256":"83b79c46616d3dbcc6b69d9acd64432ce6167ce424062a917d6496621427906d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83b79c46616d3dbcc6b69d9acd64432ce6167ce424062a917d6496621427906d","first_computed_at":"2026-05-17T23:41:23.513783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:23.513783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aArdbP5q2TVfF0TUM7T+CrA0DAYNNRZ/J42Rtjaz+kIHjcs1GlsE7nhQZHO1odFgCymS2y/7FXjZcToNp/llBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:23.514429Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14db43435090e87d24bc933906473e9e7fdbae67a5347d21cbb2ea48183dc19e","sha256:91a1310519b1a87e9403da59b6d8e4eaca329be8468d31d35a110a9810d4ab8c"],"state_sha256":"71214d2f88896b652901ab716d03452f64db7b236153a8f1758467bef59b8b64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdjQz+/7OljuUgiyDKlj/0ZEpVtdMyWxB3YpP9R7bbBphRnE7LfvW+h7Gj4dZnWFxLDOqoQ5rHcMY4Lq06TmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:14:17.024721Z","bundle_sha256":"a0732a4b12871471a0b1838dd5f8a2cf9d99e77f123b3ebc2e7f216769e8425d"}}