{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CKXHTBMPKWIQ3Y6VKJYWVT3CPZ","short_pith_number":"pith:CKXHTBMP","canonical_record":{"source":{"id":"2104.08597","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-17T16:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"4b27afde2fcfd3633850ad201f025c21c8ec94bfb8180d45950d8d42867ae001","abstract_canon_sha256":"365bcc0a3ceb5caee55074aad957922ff8136c2a576211fecf5bef144d32814f"},"schema_version":"1.0"},"canonical_sha256":"12ae79858f55910de3d552716acf627e5fcdee25bb9119ef765afbbdca4c8c7a","source":{"kind":"arxiv","id":"2104.08597","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08597","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08597v2","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08597","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"CKXHTBMPKWIQ","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_16","alias_value":"CKXHTBMPKWIQ3Y6V","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_8","alias_value":"CKXHTBMP","created_at":"2026-07-05T03:13:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CKXHTBMPKWIQ3Y6VKJYWVT3CPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08597","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-17T16:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"4b27afde2fcfd3633850ad201f025c21c8ec94bfb8180d45950d8d42867ae001","abstract_canon_sha256":"365bcc0a3ceb5caee55074aad957922ff8136c2a576211fecf5bef144d32814f"},"schema_version":"1.0"},"canonical_sha256":"12ae79858f55910de3d552716acf627e5fcdee25bb9119ef765afbbdca4c8c7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:03.070115Z","signature_b64":"qSu18pgdSoHCossyzaUI5/YBNeHhDoSggL/fiRDD+ciBTCLqcflk0+LwHB2xMJQRGcu/LYJRhNVYKk3pXiXsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ae79858f55910de3d552716acf627e5fcdee25bb9119ef765afbbdca4c8c7a","last_reissued_at":"2026-07-05T03:13:03.069702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:03.069702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08597","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RInD1w+7AQ3ZZJsO24ulJjxOwzZnG1oZi2Vr7Gq68ZxY42ciWHbpiyFWJKLfuHSvDkQbYxUvv9YPvniL6xMgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:06:49.648947Z"},"content_sha256":"d2bfa715bd95a3653d569144bc465796ab8aa79f6f8e89e6f32556006365ef7e","schema_version":"1.0","event_id":"sha256:d2bfa715bd95a3653d569144bc465796ab8aa79f6f8e89e6f32556006365ef7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CKXHTBMPKWIQ3Y6VKJYWVT3CPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adithya Renduchintala, Ahmed El-Kishky, Francisco Guzm\\'an, James Cross, Philipp Koehn","submitted_at":"2021-04-17T16:58:05Z","abstract_excerpt":"Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification. While knowledge bases contain a large number of entities in high-resource languages such as English and French, corresponding entities for lower-resource languages are often missing. To address this, we propose Lexical-Semantic-Phonetic Align (LSP-Align), a technique to automatically mine cross-lingual entity lexica from mined web data. We demonstrate LSP-Align outperforms baselines at extracting cross-lingual entity pairs and mine 164 million entity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08597","kind":"arxiv","version":2},"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/2104.08597/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":"2026-07-05T03:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OTaFpPzS20MJCB8NW1axEgCSmxIfawDQTFzCxXjiTUWXkTTYGX5X05RzkE7dQkR98XDExdo7pAUscbFb8hd9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:06:49.649326Z"},"content_sha256":"8737a5bcac34b519dffc7c857be38e00fde9e681bc9487e76e02ee1248877dea","schema_version":"1.0","event_id":"sha256:8737a5bcac34b519dffc7c857be38e00fde9e681bc9487e76e02ee1248877dea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/bundle.json","state_url":"https://pith.science/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/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":"2026-07-06T18:06:49Z","links":{"resolver":"https://pith.science/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ","bundle":"https://pith.science/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/bundle.json","state":"https://pith.science/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKXHTBMPKWIQ3Y6VKJYWVT3CPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CKXHTBMPKWIQ3Y6VKJYWVT3CPZ","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":"365bcc0a3ceb5caee55074aad957922ff8136c2a576211fecf5bef144d32814f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-17T16:58:05Z","title_canon_sha256":"4b27afde2fcfd3633850ad201f025c21c8ec94bfb8180d45950d8d42867ae001"},"schema_version":"1.0","source":{"id":"2104.08597","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08597","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08597v2","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08597","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"CKXHTBMPKWIQ","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_16","alias_value":"CKXHTBMPKWIQ3Y6V","created_at":"2026-07-05T03:13:03Z"},{"alias_kind":"pith_short_8","alias_value":"CKXHTBMP","created_at":"2026-07-05T03:13:03Z"}],"graph_snapshots":[{"event_id":"sha256:8737a5bcac34b519dffc7c857be38e00fde9e681bc9487e76e02ee1248877dea","target":"graph","created_at":"2026-07-05T03:13:03Z","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/2104.08597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification. While knowledge bases contain a large number of entities in high-resource languages such as English and French, corresponding entities for lower-resource languages are often missing. To address this, we propose Lexical-Semantic-Phonetic Align (LSP-Align), a technique to automatically mine cross-lingual entity lexica from mined web data. We demonstrate LSP-Align outperforms baselines at extracting cross-lingual entity pairs and mine 164 million entity","authors_text":"Adithya Renduchintala, Ahmed El-Kishky, Francisco Guzm\\'an, James Cross, Philipp Koehn","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-17T16:58:05Z","title":"XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08597","kind":"arxiv","version":2},"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:d2bfa715bd95a3653d569144bc465796ab8aa79f6f8e89e6f32556006365ef7e","target":"record","created_at":"2026-07-05T03:13:03Z","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":"365bcc0a3ceb5caee55074aad957922ff8136c2a576211fecf5bef144d32814f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-17T16:58:05Z","title_canon_sha256":"4b27afde2fcfd3633850ad201f025c21c8ec94bfb8180d45950d8d42867ae001"},"schema_version":"1.0","source":{"id":"2104.08597","kind":"arxiv","version":2}},"canonical_sha256":"12ae79858f55910de3d552716acf627e5fcdee25bb9119ef765afbbdca4c8c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ae79858f55910de3d552716acf627e5fcdee25bb9119ef765afbbdca4c8c7a","first_computed_at":"2026-07-05T03:13:03.069702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:03.069702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qSu18pgdSoHCossyzaUI5/YBNeHhDoSggL/fiRDD+ciBTCLqcflk0+LwHB2xMJQRGcu/LYJRhNVYKk3pXiXsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:03.070115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08597","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2bfa715bd95a3653d569144bc465796ab8aa79f6f8e89e6f32556006365ef7e","sha256:8737a5bcac34b519dffc7c857be38e00fde9e681bc9487e76e02ee1248877dea"],"state_sha256":"e7d27e38cd461cc0c11d5dc1500218846dd016354b3c0621a2ace2fd746721c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ov0XVm7IsnPggSr+1EF+ks1a+hgSdYeCqQc50dwJiSv5iu56Dn4hxiv6W5OiU3Pz9BAF/AfdUkJQKriW70+CCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:06:49.652013Z","bundle_sha256":"0cf6be7608ec6db62e6b3d4696a618f328d171e918069b90a71662d0cc8b2f63"}}