{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YBBQQLGEXL4V7U4LIL277GGITV","short_pith_number":"pith:YBBQQLGE","canonical_record":{"source":{"id":"2110.05892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T11:06:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88c4172c2559a6b2edc8e76e7ec472c6af6ee545c20988710ec436d9921f93a3","abstract_canon_sha256":"c955cb2ec47d83c7aa133f6f3175d0b968a5f22fff866d7419e53e25a6df40fe"},"schema_version":"1.0"},"canonical_sha256":"c043082cc4baf95fd38b42f5ff98c89d706cdd279fe1b659038f2e426e332dfb","source":{"kind":"arxiv","id":"2110.05892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05892","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05892v1","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05892","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"YBBQQLGEXL4V","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"YBBQQLGEXL4V7U4L","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"YBBQQLGE","created_at":"2026-07-05T03:22:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YBBQQLGEXL4V7U4LIL277GGITV","target":"record","payload":{"canonical_record":{"source":{"id":"2110.05892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T11:06:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88c4172c2559a6b2edc8e76e7ec472c6af6ee545c20988710ec436d9921f93a3","abstract_canon_sha256":"c955cb2ec47d83c7aa133f6f3175d0b968a5f22fff866d7419e53e25a6df40fe"},"schema_version":"1.0"},"canonical_sha256":"c043082cc4baf95fd38b42f5ff98c89d706cdd279fe1b659038f2e426e332dfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:08.165520Z","signature_b64":"ndiqdf25UQO2WHQGDJTqcYd/zegE3sF+peSkidAEH6/HIYmxzh5Tv1Y/7rNbCF2A33CyM84oIiS24vPFLpGmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c043082cc4baf95fd38b42f5ff98c89d706cdd279fe1b659038f2e426e332dfb","last_reissued_at":"2026-07-05T03:22:08.165082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:08.165082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.05892","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":"2026-07-05T03:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QYy8n0WWorgxCiAyvkgVtIm8H84rCmfcRGBxZG30D84m4fMxUJza3JatRju1DeUrJk/qThkgVnHyObRQGfKQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T03:14:34.474778Z"},"content_sha256":"d5f8709e74a3f7d1ca9f6e06afd59d489a489423b3da7b117281968cc5387780","schema_version":"1.0","event_id":"sha256:d5f8709e74a3f7d1ca9f6e06afd59d489a489423b3da7b117281968cc5387780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YBBQQLGEXL4V7U4LIL277GGITV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigation on Data Adaptation Techniques for Neural Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Dugast, David Thulke, Evgeniia Tokarchuk, Hermann Ney, Weiyue Wang","submitted_at":"2021-10-12T11:06:03Z","abstract_excerpt":"Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05892","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.05892/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":"2026-07-05T03:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqT1T1Wfo7N0oWpI48DiUrdHXvsx0NpXPFNYF2WO3Y+kLWxIH5+yOsD4zLavvAzhhwxiAC3Tm5UuhtQgtdkdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T03:14:34.475146Z"},"content_sha256":"d4e8147c07339f423f4ca46eeeccc2300019f3535d24d573f5172b2e71d75328","schema_version":"1.0","event_id":"sha256:d4e8147c07339f423f4ca46eeeccc2300019f3535d24d573f5172b2e71d75328"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBBQQLGEXL4V7U4LIL277GGITV/bundle.json","state_url":"https://pith.science/pith/YBBQQLGEXL4V7U4LIL277GGITV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBBQQLGEXL4V7U4LIL277GGITV/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":"2026-07-19T03:14:34Z","links":{"resolver":"https://pith.science/pith/YBBQQLGEXL4V7U4LIL277GGITV","bundle":"https://pith.science/pith/YBBQQLGEXL4V7U4LIL277GGITV/bundle.json","state":"https://pith.science/pith/YBBQQLGEXL4V7U4LIL277GGITV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBBQQLGEXL4V7U4LIL277GGITV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YBBQQLGEXL4V7U4LIL277GGITV","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":"c955cb2ec47d83c7aa133f6f3175d0b968a5f22fff866d7419e53e25a6df40fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T11:06:03Z","title_canon_sha256":"88c4172c2559a6b2edc8e76e7ec472c6af6ee545c20988710ec436d9921f93a3"},"schema_version":"1.0","source":{"id":"2110.05892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05892","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05892v1","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05892","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"YBBQQLGEXL4V","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"YBBQQLGEXL4V7U4L","created_at":"2026-07-05T03:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"YBBQQLGE","created_at":"2026-07-05T03:22:08Z"}],"graph_snapshots":[{"event_id":"sha256:d4e8147c07339f423f4ca46eeeccc2300019f3535d24d573f5172b2e71d75328","target":"graph","created_at":"2026-07-05T03:22:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.05892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks.","authors_text":"Christian Dugast, David Thulke, Evgeniia Tokarchuk, Hermann Ney, Weiyue Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T11:06:03Z","title":"Investigation on Data Adaptation Techniques for Neural Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05892","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:d5f8709e74a3f7d1ca9f6e06afd59d489a489423b3da7b117281968cc5387780","target":"record","created_at":"2026-07-05T03:22:08Z","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":"c955cb2ec47d83c7aa133f6f3175d0b968a5f22fff866d7419e53e25a6df40fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T11:06:03Z","title_canon_sha256":"88c4172c2559a6b2edc8e76e7ec472c6af6ee545c20988710ec436d9921f93a3"},"schema_version":"1.0","source":{"id":"2110.05892","kind":"arxiv","version":1}},"canonical_sha256":"c043082cc4baf95fd38b42f5ff98c89d706cdd279fe1b659038f2e426e332dfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c043082cc4baf95fd38b42f5ff98c89d706cdd279fe1b659038f2e426e332dfb","first_computed_at":"2026-07-05T03:22:08.165082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:08.165082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndiqdf25UQO2WHQGDJTqcYd/zegE3sF+peSkidAEH6/HIYmxzh5Tv1Y/7rNbCF2A33CyM84oIiS24vPFLpGmDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:08.165520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5f8709e74a3f7d1ca9f6e06afd59d489a489423b3da7b117281968cc5387780","sha256:d4e8147c07339f423f4ca46eeeccc2300019f3535d24d573f5172b2e71d75328"],"state_sha256":"5feddfceb81901458ea0e53cb9b0e9bdef56c13ab2e3f9c6bffbc1418719ba5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhQta7Wbxq/HKB6TOdhnhxPg6T+Tn0F63345hvOHlF+ORyFmfRRmIEmtbR/w5UVTpV8W5LeR4zEp0EoisAOIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T03:14:34.477269Z","bundle_sha256":"10dbf2980b3a3e1257455404bbcbfbc82650e4268890c6df0117f08a40315b7e"}}