{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K5J2IOAJIZK66TM4RAM3PLPK3F","short_pith_number":"pith:K5J2IOAJ","canonical_record":{"source":{"id":"1701.09123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-01-31T16:36:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f6e22469e6ef8a8d0cb260c044623302966900f5e9ca0e35b95d46e6ba0288f","abstract_canon_sha256":"c720b94a9fd3cf6ebe335602681392a7726f3e4f0a7251917489312144d113d6"},"schema_version":"1.0"},"canonical_sha256":"5753a438094655ef4d9c8819b7adead944b017c177c01eea2d6190cc40b0e650","source":{"kind":"arxiv","id":"1701.09123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.09123","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1701.09123v1","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.09123","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"K5J2IOAJIZK6","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K5J2IOAJIZK66TM4","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K5J2IOAJ","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K5J2IOAJIZK66TM4RAM3PLPK3F","target":"record","payload":{"canonical_record":{"source":{"id":"1701.09123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-01-31T16:36:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f6e22469e6ef8a8d0cb260c044623302966900f5e9ca0e35b95d46e6ba0288f","abstract_canon_sha256":"c720b94a9fd3cf6ebe335602681392a7726f3e4f0a7251917489312144d113d6"},"schema_version":"1.0"},"canonical_sha256":"5753a438094655ef4d9c8819b7adead944b017c177c01eea2d6190cc40b0e650","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:33.616199Z","signature_b64":"TUyLgpiExVREF0VzSGYuFMq3wHhIVnIicEPJ2kd1f38+0cVK5R8YnXkrjx3SudLhL6DmZLIofjpGdIO1G0W+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5753a438094655ef4d9c8819b7adead944b017c177c01eea2d6190cc40b0e650","last_reissued_at":"2026-05-18T00:51:33.615548Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:33.615548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.09123","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":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1X+jx712pU/wnOsWzg2pxJbHw3BHmH26QpiSYH6BPHipzBUb3zmG2FvDgRwUI3+LrClN3byRxEcRNLxHb5oCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:36:38.321421Z"},"content_sha256":"6082b598a66b35aa4181b9326980a042e94c51c077463f9d73663cc05b0430a5","schema_version":"1.0","event_id":"sha256:6082b598a66b35aa4181b9326980a042e94c51c077463f9d73663cc05b0430a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K5J2IOAJIZK66TM4RAM3PLPK3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"German Rigau, Rodrigo Agerri","submitted_at":"2017-01-31T16:36:06Z","abstract_excerpt":"We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.09123","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":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNnuUDd0IC8oARy44AoPcAlcOYFo8GreCYd3FTcFO5FM/PPuckW9zGII3sPhTg1CI46vj1+Axtr/iW0CXwRKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:36:38.321763Z"},"content_sha256":"0d36ccbc642e1ffd02abc8af2fbe9bb17f01f2380045185ca0c247ed9a51fd00","schema_version":"1.0","event_id":"sha256:0d36ccbc642e1ffd02abc8af2fbe9bb17f01f2380045185ca0c247ed9a51fd00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/bundle.json","state_url":"https://pith.science/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/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":"2026-06-05T14:36:38Z","links":{"resolver":"https://pith.science/pith/K5J2IOAJIZK66TM4RAM3PLPK3F","bundle":"https://pith.science/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/bundle.json","state":"https://pith.science/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5J2IOAJIZK66TM4RAM3PLPK3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K5J2IOAJIZK66TM4RAM3PLPK3F","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":"c720b94a9fd3cf6ebe335602681392a7726f3e4f0a7251917489312144d113d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-01-31T16:36:06Z","title_canon_sha256":"0f6e22469e6ef8a8d0cb260c044623302966900f5e9ca0e35b95d46e6ba0288f"},"schema_version":"1.0","source":{"id":"1701.09123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.09123","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1701.09123v1","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.09123","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"K5J2IOAJIZK6","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K5J2IOAJIZK66TM4","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K5J2IOAJ","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:0d36ccbc642e1ffd02abc8af2fbe9bb17f01f2380045185ca0c247ed9a51fd00","target":"graph","created_at":"2026-05-18T00:51:33Z","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 present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results ar","authors_text":"German Rigau, Rodrigo Agerri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-01-31T16:36:06Z","title":"Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.09123","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":"sha256:6082b598a66b35aa4181b9326980a042e94c51c077463f9d73663cc05b0430a5","target":"record","created_at":"2026-05-18T00:51:33Z","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":"c720b94a9fd3cf6ebe335602681392a7726f3e4f0a7251917489312144d113d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-01-31T16:36:06Z","title_canon_sha256":"0f6e22469e6ef8a8d0cb260c044623302966900f5e9ca0e35b95d46e6ba0288f"},"schema_version":"1.0","source":{"id":"1701.09123","kind":"arxiv","version":1}},"canonical_sha256":"5753a438094655ef4d9c8819b7adead944b017c177c01eea2d6190cc40b0e650","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5753a438094655ef4d9c8819b7adead944b017c177c01eea2d6190cc40b0e650","first_computed_at":"2026-05-18T00:51:33.615548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:33.615548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TUyLgpiExVREF0VzSGYuFMq3wHhIVnIicEPJ2kd1f38+0cVK5R8YnXkrjx3SudLhL6DmZLIofjpGdIO1G0W+DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:33.616199Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.09123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6082b598a66b35aa4181b9326980a042e94c51c077463f9d73663cc05b0430a5","sha256:0d36ccbc642e1ffd02abc8af2fbe9bb17f01f2380045185ca0c247ed9a51fd00"],"state_sha256":"dad2bcf8e2095dc8e5829e6f8f19d84ccdf3d72e31c0d751aab7a39bb2d0b1f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EP0z6nOKMCMVm0HQAQJUmAtH+Jh60wE3JqPJZ90TJX5+fSlpY/vEau3tN7M7ByYWYKj4TMgyUJrd4zGCUD0PAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:36:38.323701Z","bundle_sha256":"3964f0dd2177b49ae547835f724738687d2e48e38150ace150746ff9259ddb35"}}