{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:C74GPJVQZ2H3JCKPPK2A3PSAIG","short_pith_number":"pith:C74GPJVQ","canonical_record":{"source":{"id":"2101.01039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-01-04T15:56:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f2b2ad0221baf6046a913e6f93d4deade320b475f34ef08e1c595dfc87c7a47","abstract_canon_sha256":"d83ac4dc90dde6558f75c7dc74c9163847698ade5e9098ad45cb38a1fb1f2507"},"schema_version":"1.0"},"canonical_sha256":"17f867a6b0ce8fb4894f7ab40dbe4041894fb7ac35fd664852cc1409a221c636","source":{"kind":"arxiv","id":"2101.01039","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01039","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01039v3","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01039","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"C74GPJVQZ2H3","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"C74GPJVQZ2H3JCKP","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"C74GPJVQ","created_at":"2026-07-05T02:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:C74GPJVQZ2H3JCKPPK2A3PSAIG","target":"record","payload":{"canonical_record":{"source":{"id":"2101.01039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-01-04T15:56:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f2b2ad0221baf6046a913e6f93d4deade320b475f34ef08e1c595dfc87c7a47","abstract_canon_sha256":"d83ac4dc90dde6558f75c7dc74c9163847698ade5e9098ad45cb38a1fb1f2507"},"schema_version":"1.0"},"canonical_sha256":"17f867a6b0ce8fb4894f7ab40dbe4041894fb7ac35fd664852cc1409a221c636","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:54.633194Z","signature_b64":"hVCZVZBwmQhcwNB28olF0z5cyVah8GyUHmB65bxhZBKeqzRALMEZknsg3AyGUGHGM4U9fcpM+4Y01LMfflehDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f867a6b0ce8fb4894f7ab40dbe4041894fb7ac35fd664852cc1409a221c636","last_reissued_at":"2026-07-05T02:21:54.632675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:54.632675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.01039","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/MWfiopldnqQpJVitRRLloPC11n2lkUKxUmm8afXm3oxeb8Sft1e9VKb7DT7eWwLi+KTha6OlwlTvzTCLOdFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:33:11.675487Z"},"content_sha256":"89190565c6ec8ff21eac6ea0d04c4800b9903ca8111d45f2a4423ed0964bc245","schema_version":"1.0","event_id":"sha256:89190565c6ec8ff21eac6ea0d04c4800b9903ca8111d45f2a4423ed0964bc245"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:C74GPJVQZ2H3JCKPPK2A3PSAIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving reference mining in patents with BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ken Voskuil, Suzan Verberne","submitted_at":"2021-01-04T15:56:21Z","abstract_excerpt":"In this paper we address the challenge of extracting scientific references from patents. We approach the problem as a sequence labelling task and investigate the merits of BERT models to the extraction of these long sequences. References in patents to scientific literature are relevant to study the connection between science and industry. Most prior work only uses the front-page citations for this analysis, which are provided in the metadata of patent archives. In this paper we build on prior work using Conditional Random Fields (CRF) and Flair for reference extraction. We improve the quality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01039","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/2101.01039/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rR7NOb8aqRBC7UmiPalhgerY+vEc6hbdYgNNonVUoK4AqXBThhCTj97+w+ZR7RW38jakvJXNuApFPlyZ2YcPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:33:11.676036Z"},"content_sha256":"31fd4279e6d25242bb6dfa7e049e3265be5061d3a56d11cdd704761bd06c8a55","schema_version":"1.0","event_id":"sha256:31fd4279e6d25242bb6dfa7e049e3265be5061d3a56d11cdd704761bd06c8a55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/bundle.json","state_url":"https://pith.science/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/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":"2026-08-05T09:33:11Z","links":{"resolver":"https://pith.science/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG","bundle":"https://pith.science/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/bundle.json","state":"https://pith.science/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C74GPJVQZ2H3JCKPPK2A3PSAIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:C74GPJVQZ2H3JCKPPK2A3PSAIG","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":"d83ac4dc90dde6558f75c7dc74c9163847698ade5e9098ad45cb38a1fb1f2507","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-01-04T15:56:21Z","title_canon_sha256":"4f2b2ad0221baf6046a913e6f93d4deade320b475f34ef08e1c595dfc87c7a47"},"schema_version":"1.0","source":{"id":"2101.01039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01039","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01039v3","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01039","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"C74GPJVQZ2H3","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"C74GPJVQZ2H3JCKP","created_at":"2026-07-05T02:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"C74GPJVQ","created_at":"2026-07-05T02:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:31fd4279e6d25242bb6dfa7e049e3265be5061d3a56d11cdd704761bd06c8a55","target":"graph","created_at":"2026-07-05T02:21:54Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.01039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we address the challenge of extracting scientific references from patents. We approach the problem as a sequence labelling task and investigate the merits of BERT models to the extraction of these long sequences. References in patents to scientific literature are relevant to study the connection between science and industry. Most prior work only uses the front-page citations for this analysis, which are provided in the metadata of patent archives. In this paper we build on prior work using Conditional Random Fields (CRF) and Flair for reference extraction. We improve the quality ","authors_text":"Ken Voskuil, Suzan Verberne","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-01-04T15:56:21Z","title":"Improving reference mining in patents with BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01039","kind":"arxiv","version":3},"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":"sha256:89190565c6ec8ff21eac6ea0d04c4800b9903ca8111d45f2a4423ed0964bc245","target":"record","created_at":"2026-07-05T02:21:54Z","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":"d83ac4dc90dde6558f75c7dc74c9163847698ade5e9098ad45cb38a1fb1f2507","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-01-04T15:56:21Z","title_canon_sha256":"4f2b2ad0221baf6046a913e6f93d4deade320b475f34ef08e1c595dfc87c7a47"},"schema_version":"1.0","source":{"id":"2101.01039","kind":"arxiv","version":3}},"canonical_sha256":"17f867a6b0ce8fb4894f7ab40dbe4041894fb7ac35fd664852cc1409a221c636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17f867a6b0ce8fb4894f7ab40dbe4041894fb7ac35fd664852cc1409a221c636","first_computed_at":"2026-07-05T02:21:54.632675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:54.632675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVCZVZBwmQhcwNB28olF0z5cyVah8GyUHmB65bxhZBKeqzRALMEZknsg3AyGUGHGM4U9fcpM+4Y01LMfflehDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:54.633194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.01039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89190565c6ec8ff21eac6ea0d04c4800b9903ca8111d45f2a4423ed0964bc245","sha256:31fd4279e6d25242bb6dfa7e049e3265be5061d3a56d11cdd704761bd06c8a55"],"state_sha256":"856059421204b81b6c7bc9e9ff549ff41465f7366c0043c94ba5a51075562c46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qn03gs4xtTC3SjyotuaRJd+//VbgxAYCjYTqWCT8hs5SZTMgZALhLGanBREsUS+QTmSBdiV1mZk/8LWqIK3VCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:33:11.680886Z","bundle_sha256":"b19cc254ab392edff7cb150250def71493d98b9ed44e52645192903ae92f1067"}}