{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7CAX2QXP6TFRDQIQJX3TUNVTHN","short_pith_number":"pith:7CAX2QXP","canonical_record":{"source":{"id":"1707.02459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T16:17:04Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e042d8ced380b3fba5ae918691941db01e60b8a3945c79763e123aae5ea5fa5d","abstract_canon_sha256":"80464219bcc63b902cc0124631e0ea615a579ad2c16457fd5f63476c9ac31d6f"},"schema_version":"1.0"},"canonical_sha256":"f8817d42eff4cb11c1104df73a36b33b625bcf24f6e4bb9508818874cbc9b075","source":{"kind":"arxiv","id":"1707.02459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02459","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02459v1","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02459","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"7CAX2QXP6TFR","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"7CAX2QXP6TFRDQIQ","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"7CAX2QXP","created_at":"2026-07-05T00:16:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7CAX2QXP6TFRDQIQJX3TUNVTHN","target":"record","payload":{"canonical_record":{"source":{"id":"1707.02459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T16:17:04Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e042d8ced380b3fba5ae918691941db01e60b8a3945c79763e123aae5ea5fa5d","abstract_canon_sha256":"80464219bcc63b902cc0124631e0ea615a579ad2c16457fd5f63476c9ac31d6f"},"schema_version":"1.0"},"canonical_sha256":"f8817d42eff4cb11c1104df73a36b33b625bcf24f6e4bb9508818874cbc9b075","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:17.911231Z","signature_b64":"KEImB3NX+Gc/ocuH0zLtBp19CJY53ZZa8RWJo44ujRn2qtTAHXY0Ps4zf2eIT/ekuZ6C7dqHxLr8o6QaJTF7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8817d42eff4cb11c1104df73a36b33b625bcf24f6e4bb9508818874cbc9b075","last_reissued_at":"2026-07-05T00:16:17.910880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:17.910880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.02459","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":"2026-07-05T00:16:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfXNHvxKBFwkRBdeWyRq5ho3IszuZfbij0HbQ32KbTZvGP7mz/gR6WbB09rfBz4F2wgllEPhGbMjiXOY6ZKOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:40:03.985107Z"},"content_sha256":"cc1166d5ecc91c3e19774cb5d5faf4deca1d465425684ab1d530651692721755","schema_version":"1.0","event_id":"sha256:cc1166d5ecc91c3e19774cb5d5faf4deca1d465425684ab1d530651692721755"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7CAX2QXP6TFRDQIQJX3TUNVTHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jian Ni, Radu Florian","submitted_at":"2017-07-08T16:17:04Z","abstract_excerpt":"The state-of-the-art named entity recognition (NER) systems are statistical machine learning models that have strong generalization capability (i.e., can recognize unseen entities that do not appear in training data) based on lexical and contextual information. However, such a model could still make mistakes if its features favor a wrong entity type. In this paper, we utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to our approach is the construction of high-accuracy, high-coverage multilingual Wikipedia entity type mappings. These mappings are built fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02459","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/1707.02459/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":"2026-07-05T00:16:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3v2cf86hvZsJuLc3JNBTTzSnZXJfYadjC+PIgQKWVWwLouLpgiS9x0rumnMPizij5qLpXIgVkwDXNPn7ILWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:40:03.985629Z"},"content_sha256":"5a93a1aedcd97ca847b4e406618dd0aa664d95caf973a8a47ea20d03189d13c2","schema_version":"1.0","event_id":"sha256:5a93a1aedcd97ca847b4e406618dd0aa664d95caf973a8a47ea20d03189d13c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/bundle.json","state_url":"https://pith.science/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/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":"2026-08-15T09:40:03Z","links":{"resolver":"https://pith.science/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN","bundle":"https://pith.science/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/bundle.json","state":"https://pith.science/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CAX2QXP6TFRDQIQJX3TUNVTHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7CAX2QXP6TFRDQIQJX3TUNVTHN","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":"80464219bcc63b902cc0124631e0ea615a579ad2c16457fd5f63476c9ac31d6f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T16:17:04Z","title_canon_sha256":"e042d8ced380b3fba5ae918691941db01e60b8a3945c79763e123aae5ea5fa5d"},"schema_version":"1.0","source":{"id":"1707.02459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02459","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02459v1","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02459","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"7CAX2QXP6TFR","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"7CAX2QXP6TFRDQIQ","created_at":"2026-07-05T00:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"7CAX2QXP","created_at":"2026-07-05T00:16:17Z"}],"graph_snapshots":[{"event_id":"sha256:5a93a1aedcd97ca847b4e406618dd0aa664d95caf973a8a47ea20d03189d13c2","target":"graph","created_at":"2026-07-05T00:16:17Z","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/1707.02459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The state-of-the-art named entity recognition (NER) systems are statistical machine learning models that have strong generalization capability (i.e., can recognize unseen entities that do not appear in training data) based on lexical and contextual information. However, such a model could still make mistakes if its features favor a wrong entity type. In this paper, we utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to our approach is the construction of high-accuracy, high-coverage multilingual Wikipedia entity type mappings. These mappings are built fr","authors_text":"Jian Ni, Radu Florian","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T16:17:04Z","title":"Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02459","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:cc1166d5ecc91c3e19774cb5d5faf4deca1d465425684ab1d530651692721755","target":"record","created_at":"2026-07-05T00:16:17Z","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":"80464219bcc63b902cc0124631e0ea615a579ad2c16457fd5f63476c9ac31d6f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T16:17:04Z","title_canon_sha256":"e042d8ced380b3fba5ae918691941db01e60b8a3945c79763e123aae5ea5fa5d"},"schema_version":"1.0","source":{"id":"1707.02459","kind":"arxiv","version":1}},"canonical_sha256":"f8817d42eff4cb11c1104df73a36b33b625bcf24f6e4bb9508818874cbc9b075","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8817d42eff4cb11c1104df73a36b33b625bcf24f6e4bb9508818874cbc9b075","first_computed_at":"2026-07-05T00:16:17.910880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:17.910880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KEImB3NX+Gc/ocuH0zLtBp19CJY53ZZa8RWJo44ujRn2qtTAHXY0Ps4zf2eIT/ekuZ6C7dqHxLr8o6QaJTF7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:17.911231Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.02459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc1166d5ecc91c3e19774cb5d5faf4deca1d465425684ab1d530651692721755","sha256:5a93a1aedcd97ca847b4e406618dd0aa664d95caf973a8a47ea20d03189d13c2"],"state_sha256":"2283142410faa4fed53a271e5cae7fc5d12d8d8454359a8c29daa3f6fff15916"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EF7vK/AvxDPvwc1OhDoJ9bIPA+OKju3UyWgX/FR9ANScst65I1OfOBWtLnxY9eCZ2maF3Dyc27F96XxBIic7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:40:03.990741Z","bundle_sha256":"eb7bbffe5f5220a9a1eba58d52f73e6b6c8275bf151470aa4bfeceed9709c90a"}}