{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PMJHBTUUYBGOGTTV3LMX4C2ONB","short_pith_number":"pith:PMJHBTUU","schema_version":"1.0","canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","source":{"kind":"arxiv","id":"1907.03110","version":1},"attestation_state":"computed","paper":{"title":"ANETAC: Arabic Named Entity Transliteration and Classification Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ahmed Guessoum, Farid Meziane, Mohamed Seghir Hadj Ameur","submitted_at":"2019-07-06T10:37:18Z","abstract_excerpt":"In this paper, we make freely accessible ANETAC our English-Arabic named entity transliteration and classification dataset that we built from freely available parallel translation corpora. The dataset contains 79,924 instances, each instance is a triplet (e, a, c), where e is the English named entity, a is its Arabic transliteration and c is its class that can be either a Person, a Location, or an Organization. The ANETAC dataset is mainly aimed for the researchers that are working on Arabic named entity transliteration, but it can also be used for named entity classification purposes."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.03110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-06T10:37:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"69c91c5b01416597a48a4ceb5e2f0d8c1aea02fefa987e2d63d24d379f3dee8b","abstract_canon_sha256":"4d80a603bafc0c0e1f7044d6f0c38bbfe007c53b763180797750f62653dbbde4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:16.866077Z","signature_b64":"F0pNtu84vak/toBkrsYuk4ceOVD3Yt9dRhV3+LJHdgdpOHhUWZdDZUMdbu+iYB7u4DhClQdeWUd0mHFlw4nsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","last_reissued_at":"2026-05-17T23:41:16.865605Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:16.865605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ANETAC: Arabic Named Entity Transliteration and Classification Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ahmed Guessoum, Farid Meziane, Mohamed Seghir Hadj Ameur","submitted_at":"2019-07-06T10:37:18Z","abstract_excerpt":"In this paper, we make freely accessible ANETAC our English-Arabic named entity transliteration and classification dataset that we built from freely available parallel translation corpora. The dataset contains 79,924 instances, each instance is a triplet (e, a, c), where e is the English named entity, a is its Arabic transliteration and c is its class that can be either a Person, a Location, or an Organization. The ANETAC dataset is mainly aimed for the researchers that are working on Arabic named entity transliteration, but it can also be used for named entity classification purposes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03110","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.03110","created_at":"2026-05-17T23:41:16.865678+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03110v1","created_at":"2026-05-17T23:41:16.865678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03110","created_at":"2026-05-17T23:41:16.865678+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMJHBTUUYBGO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMJHBTUUYBGOGTTV","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMJHBTUU","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB","json":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB.json","graph_json":"https://pith.science/api/pith-number/PMJHBTUUYBGOGTTV3LMX4C2ONB/graph.json","events_json":"https://pith.science/api/pith-number/PMJHBTUUYBGOGTTV3LMX4C2ONB/events.json","paper":"https://pith.science/paper/PMJHBTUU"},"agent_actions":{"view_html":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB","download_json":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB.json","view_paper":"https://pith.science/paper/PMJHBTUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03110&json=true","fetch_graph":"https://pith.science/api/pith-number/PMJHBTUUYBGOGTTV3LMX4C2ONB/graph.json","fetch_events":"https://pith.science/api/pith-number/PMJHBTUUYBGOGTTV3LMX4C2ONB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/action/storage_attestation","attest_author":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/action/author_attestation","sign_citation":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/action/citation_signature","submit_replication":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/action/replication_record"}},"created_at":"2026-05-17T23:41:16.865678+00:00","updated_at":"2026-05-17T23:41:16.865678+00:00"}