{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7C6JUVT5X4HDURTAACI2WU7KVG","short_pith_number":"pith:7C6JUVT5","canonical_record":{"source":{"id":"2208.14536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T20:45:54Z","cross_cats_sorted":[],"title_canon_sha256":"c00ef74bfebeebf02ac92effda392f4c3e4a0877f8131019ed98d7e3a1e9a0bf","abstract_canon_sha256":"a2c9efd59bd14a5f7c877d943b3b960313a16cadbdc444bc443da49272eedcc5"},"schema_version":"1.0"},"canonical_sha256":"f8bc9a567dbf0e3a46600091ab53eaa99703f04c7ae944acd049b1ff2cada09a","source":{"kind":"arxiv","id":"2208.14536","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14536","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14536v1","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14536","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"7C6JUVT5X4HD","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"7C6JUVT5X4HDURTA","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"7C6JUVT5","created_at":"2026-07-05T04:53:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7C6JUVT5X4HDURTAACI2WU7KVG","target":"record","payload":{"canonical_record":{"source":{"id":"2208.14536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T20:45:54Z","cross_cats_sorted":[],"title_canon_sha256":"c00ef74bfebeebf02ac92effda392f4c3e4a0877f8131019ed98d7e3a1e9a0bf","abstract_canon_sha256":"a2c9efd59bd14a5f7c877d943b3b960313a16cadbdc444bc443da49272eedcc5"},"schema_version":"1.0"},"canonical_sha256":"f8bc9a567dbf0e3a46600091ab53eaa99703f04c7ae944acd049b1ff2cada09a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:31.353678Z","signature_b64":"XTy7/5eCk2KNbCgcuFn7dZbUUuKk2zBUY4d2S59oTNJNMZi2aqimkr++D+JT9TbcyASdqhsjDLr8voTW0utEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8bc9a567dbf0e3a46600091ab53eaa99703f04c7ae944acd049b1ff2cada09a","last_reissued_at":"2026-07-05T04:53:31.353304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:31.353304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.14536","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":"2026-07-05T04:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQIuBBHiAa9RqdUqfQn82CVbp//VVR3rDzLxbQHdfCVLn0g762k1WUT4sIfbDyhAd0SZzCguIXsgFBtOSIbnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:41.004568Z"},"content_sha256":"e9623178c5976edddbf22686fc0070f6fee9bbe112935b718d354689a08b4a97","schema_version":"1.0","event_id":"sha256:e9623178c5976edddbf22686fc0070f6fee9bbe112935b718d354689a08b4a97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7C6JUVT5X4HDURTAACI2WU7KVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anjie Fang, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi, Sudipta Kar","submitted_at":"2022-08-30T20:45:54Z","abstract_excerpt":"We present MultiCoNER, a large multilingual dataset for Named Entity Recognition that covers 3 domains (Wiki sentences, questions, and search queries) across 11 languages, as well as multilingual and code-mixing subsets. This dataset is designed to represent contemporary challenges in NER, including low-context scenarios (short and uncased text), syntactically complex entities like movie titles, and long-tail entity distributions. The 26M token dataset is compiled from public resources using techniques such as heuristic-based sentence sampling, template extraction and slotting, and machine tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14536","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/2208.14536/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":"2026-07-05T04:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VY7eiapp38BmtWdJPljL7vxREwQWcGtG+gdXg+pqOv9s44oM3Eg/Ev/17nm1zAL+2nXoAw8FcGELJTbBNd7CCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:41.005187Z"},"content_sha256":"57a02243071bb7e0c3a7389510c9103be350708c40a3521cc82a0ecc42d664e3","schema_version":"1.0","event_id":"sha256:57a02243071bb7e0c3a7389510c9103be350708c40a3521cc82a0ecc42d664e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7C6JUVT5X4HDURTAACI2WU7KVG/bundle.json","state_url":"https://pith.science/pith/7C6JUVT5X4HDURTAACI2WU7KVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7C6JUVT5X4HDURTAACI2WU7KVG/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":"2026-08-08T02:54:41Z","links":{"resolver":"https://pith.science/pith/7C6JUVT5X4HDURTAACI2WU7KVG","bundle":"https://pith.science/pith/7C6JUVT5X4HDURTAACI2WU7KVG/bundle.json","state":"https://pith.science/pith/7C6JUVT5X4HDURTAACI2WU7KVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7C6JUVT5X4HDURTAACI2WU7KVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7C6JUVT5X4HDURTAACI2WU7KVG","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":"a2c9efd59bd14a5f7c877d943b3b960313a16cadbdc444bc443da49272eedcc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T20:45:54Z","title_canon_sha256":"c00ef74bfebeebf02ac92effda392f4c3e4a0877f8131019ed98d7e3a1e9a0bf"},"schema_version":"1.0","source":{"id":"2208.14536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14536","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14536v1","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14536","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"7C6JUVT5X4HD","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"7C6JUVT5X4HDURTA","created_at":"2026-07-05T04:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"7C6JUVT5","created_at":"2026-07-05T04:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:57a02243071bb7e0c3a7389510c9103be350708c40a3521cc82a0ecc42d664e3","target":"graph","created_at":"2026-07-05T04:53:31Z","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/2208.14536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MultiCoNER, a large multilingual dataset for Named Entity Recognition that covers 3 domains (Wiki sentences, questions, and search queries) across 11 languages, as well as multilingual and code-mixing subsets. This dataset is designed to represent contemporary challenges in NER, including low-context scenarios (short and uncased text), syntactically complex entities like movie titles, and long-tail entity distributions. The 26M token dataset is compiled from public resources using techniques such as heuristic-based sentence sampling, template extraction and slotting, and machine tra","authors_text":"Anjie Fang, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi, Sudipta Kar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T20:45:54Z","title":"MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14536","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:e9623178c5976edddbf22686fc0070f6fee9bbe112935b718d354689a08b4a97","target":"record","created_at":"2026-07-05T04:53:31Z","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":"a2c9efd59bd14a5f7c877d943b3b960313a16cadbdc444bc443da49272eedcc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T20:45:54Z","title_canon_sha256":"c00ef74bfebeebf02ac92effda392f4c3e4a0877f8131019ed98d7e3a1e9a0bf"},"schema_version":"1.0","source":{"id":"2208.14536","kind":"arxiv","version":1}},"canonical_sha256":"f8bc9a567dbf0e3a46600091ab53eaa99703f04c7ae944acd049b1ff2cada09a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8bc9a567dbf0e3a46600091ab53eaa99703f04c7ae944acd049b1ff2cada09a","first_computed_at":"2026-07-05T04:53:31.353304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:31.353304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XTy7/5eCk2KNbCgcuFn7dZbUUuKk2zBUY4d2S59oTNJNMZi2aqimkr++D+JT9TbcyASdqhsjDLr8voTW0utEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:31.353678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.14536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9623178c5976edddbf22686fc0070f6fee9bbe112935b718d354689a08b4a97","sha256:57a02243071bb7e0c3a7389510c9103be350708c40a3521cc82a0ecc42d664e3"],"state_sha256":"abfeb1b6b3244c8b4506c7845bbd8d033dfb1687fb2c3668e2119955d90c203e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvBJkcuPpfFHgR7j8sQ7P2NK1dDjmTCxgmo53YmQe7cAjFUCSrmepafSj/ePSRLh5R52Wt7PwAWLWPH/nYLuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:54:41.009043Z","bundle_sha256":"4a932549ed7fe3129792909a92b3a893fa1068f8c5ece42a5de5f3b66d2f722e"}}