{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PMJHBTUUYBGOGTTV3LMX4C2ONB","short_pith_number":"pith:PMJHBTUU","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"},"canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","source":{"kind":"arxiv","id":"1907.03110","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03110","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03110v1","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03110","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"PMJHBTUUYBGO","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PMJHBTUUYBGOGTTV","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PMJHBTUU","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PMJHBTUUYBGOGTTV3LMX4C2ONB","target":"record","payload":{"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"},"canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","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"},"source_kind":"arxiv","source_id":"1907.03110","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":"2026-05-17T23:41:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pj7XKXenMxXPZ1MuFXhnQUBWGAuJzkEdlznztze6esF3mXCec7YRChG0nE3xWq9o3usIyq1Cca3XCV2bunCaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:31:02.005034Z"},"content_sha256":"eb35df00c42fa817787f3d9e62f3b9430f768e6cf4541d8d199ba407150cee1b","schema_version":"1.0","event_id":"sha256:eb35df00c42fa817787f3d9e62f3b9430f768e6cf4541d8d199ba407150cee1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PMJHBTUUYBGOGTTV3LMX4C2ONB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/V4k21GfKgpGJ/xbL+uSdKd8274kXlWwAdfHqI3mjzNEta97GaeQbFxjbdlGlUVeKM6enYahnpsiX71ClPfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:31:02.005741Z"},"content_sha256":"f0696a94874ff9cb18835d35c037674f133b534c7c58e1e3adf66bdea2faf2e7","schema_version":"1.0","event_id":"sha256:f0696a94874ff9cb18835d35c037674f133b534c7c58e1e3adf66bdea2faf2e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/bundle.json","state_url":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/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":"2026-05-25T22:31:02Z","links":{"resolver":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB","bundle":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/bundle.json","state":"https://pith.science/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PMJHBTUUYBGOGTTV3LMX4C2ONB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PMJHBTUUYBGOGTTV3LMX4C2ONB","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":"4d80a603bafc0c0e1f7044d6f0c38bbfe007c53b763180797750f62653dbbde4","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-06T10:37:18Z","title_canon_sha256":"69c91c5b01416597a48a4ceb5e2f0d8c1aea02fefa987e2d63d24d379f3dee8b"},"schema_version":"1.0","source":{"id":"1907.03110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03110","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03110v1","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03110","created_at":"2026-05-17T23:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"PMJHBTUUYBGO","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PMJHBTUUYBGOGTTV","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PMJHBTUU","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:f0696a94874ff9cb18835d35c037674f133b534c7c58e1e3adf66bdea2faf2e7","target":"graph","created_at":"2026-05-17T23:41:16Z","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":"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.","authors_text":"Ahmed Guessoum, Farid Meziane, Mohamed Seghir Hadj Ameur","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-06T10:37:18Z","title":"ANETAC: Arabic Named Entity Transliteration and Classification Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03110","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:eb35df00c42fa817787f3d9e62f3b9430f768e6cf4541d8d199ba407150cee1b","target":"record","created_at":"2026-05-17T23:41:16Z","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":"4d80a603bafc0c0e1f7044d6f0c38bbfe007c53b763180797750f62653dbbde4","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-06T10:37:18Z","title_canon_sha256":"69c91c5b01416597a48a4ceb5e2f0d8c1aea02fefa987e2d63d24d379f3dee8b"},"schema_version":"1.0","source":{"id":"1907.03110","kind":"arxiv","version":1}},"canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b1270ce94c04ce34e75dad97e0b4e685c9a79176e098ceb29e7112826022585","first_computed_at":"2026-05-17T23:41:16.865605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:16.865605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F0pNtu84vak/toBkrsYuk4ceOVD3Yt9dRhV3+LJHdgdpOHhUWZdDZUMdbu+iYB7u4DhClQdeWUd0mHFlw4nsDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:16.866077Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.03110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb35df00c42fa817787f3d9e62f3b9430f768e6cf4541d8d199ba407150cee1b","sha256:f0696a94874ff9cb18835d35c037674f133b534c7c58e1e3adf66bdea2faf2e7"],"state_sha256":"51b256bdd89c9ebebb4a38387872fb1776cf37b4491afe6643f12c95c943106f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5LICN7Tpt81CyMV15MVoYuv4rAjBWuhtuRhIhgT5LcQzQ9Q6ZMtcW1w8woloz8c9ilh+UzgRHfXcUgNUCHrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:31:02.009296Z","bundle_sha256":"15c5c009c7d29f0d0e2acd070aa5f714297844ba48116fff9ec9ed163ddf6e69"}}