{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3IW3UBXEJ6KBXQD3GF3AR3ONII","short_pith_number":"pith:3IW3UBXE","canonical_record":{"source":{"id":"1903.02784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T09:22:35Z","cross_cats_sorted":[],"title_canon_sha256":"9fafb8ecc390c9b2785ec9b6e4b81c3850ad6586232256f13b4439c135529220","abstract_canon_sha256":"881b45666421c996c8b35bef799ca7196e50bd95289699e45a413d43bcf71992"},"schema_version":"1.0"},"canonical_sha256":"da2dba06e44f941bc07b317608edcd4204b60305bcf9e8fc99e9842d2a56825e","source":{"kind":"arxiv","id":"1903.02784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02784","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02784v1","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02784","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"3IW3UBXEJ6KB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3IW3UBXEJ6KBXQD3","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3IW3UBXE","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3IW3UBXEJ6KBXQD3GF3AR3ONII","target":"record","payload":{"canonical_record":{"source":{"id":"1903.02784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T09:22:35Z","cross_cats_sorted":[],"title_canon_sha256":"9fafb8ecc390c9b2785ec9b6e4b81c3850ad6586232256f13b4439c135529220","abstract_canon_sha256":"881b45666421c996c8b35bef799ca7196e50bd95289699e45a413d43bcf71992"},"schema_version":"1.0"},"canonical_sha256":"da2dba06e44f941bc07b317608edcd4204b60305bcf9e8fc99e9842d2a56825e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:51.119170Z","signature_b64":"YQ5A7/9BtbkweebvzVCy8NQQPuWaX5o0DB6tPbTS7co/DbK911MHPn4fjntIHQizcVAEecBXzS5jKgK0vlnUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2dba06e44f941bc07b317608edcd4204b60305bcf9e8fc99e9842d2a56825e","last_reissued_at":"2026-05-17T23:51:51.118337Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:51.118337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.02784","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":"2026-05-17T23:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5MiD4AilEYx7gNcHQ0UvpAqntwzh7jlSa1/8gE6idHUfURBtu1EFzt0J3+ZH36r1L2APUrvU1670gO6ZVshtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:29:41.073736Z"},"content_sha256":"ce1c86404f4c65d41d4baac1fc58133a219a1deacb0ed77da7a55c1582469bfe","schema_version":"1.0","event_id":"sha256:ce1c86404f4c65d41d4baac1fc58133a219a1deacb0ed77da7a55c1582469bfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3IW3UBXEJ6KBXQD3GF3AR3ONII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arabic natural language processing: An overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Billel Gueni, Damien Nouvel, Faical Azouaou, Houda Sa\\^adane, Imane Guellil","submitted_at":"2019-03-07T09:22:35Z","abstract_excerpt":"Arabic is recognised as the 4th most used language of the Internet. Arabic has three main varieties: (1) classical Arabic (CA), (2) Modern Standard Arabic (MSA), (3) Arabic Dialect (AD). MSA and AD could be written either in Arabic or in Roman script (Arabizi), which corresponds to Arabic written with Latin letters, numerals and punctuation. Due to the complexity of this language and the number of corresponding challenges for NLP, many surveys have been conducted, in order to synthesise the work done on Arabic. However these surveys principally focus on two varieties of Arabic (MSA and AD, wri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02784","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":"2026-05-17T23:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+iAnwAwmF6vHStDo/m4mp+ZKd0EKGF7C7D2TQQtcazPaeq+XG1zszAdoHcOJFoRy6dramFwBvdiV0bRI3trDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:29:41.074081Z"},"content_sha256":"0dd5eb1fc0552f95ed6686146d248a69f1ae9914c3d8330f7de9cc065914f305","schema_version":"1.0","event_id":"sha256:0dd5eb1fc0552f95ed6686146d248a69f1ae9914c3d8330f7de9cc065914f305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/bundle.json","state_url":"https://pith.science/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/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":"2026-06-25T05:29:41Z","links":{"resolver":"https://pith.science/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII","bundle":"https://pith.science/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/bundle.json","state":"https://pith.science/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IW3UBXEJ6KBXQD3GF3AR3ONII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3IW3UBXEJ6KBXQD3GF3AR3ONII","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":"881b45666421c996c8b35bef799ca7196e50bd95289699e45a413d43bcf71992","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T09:22:35Z","title_canon_sha256":"9fafb8ecc390c9b2785ec9b6e4b81c3850ad6586232256f13b4439c135529220"},"schema_version":"1.0","source":{"id":"1903.02784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02784","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02784v1","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02784","created_at":"2026-05-17T23:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"3IW3UBXEJ6KB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3IW3UBXEJ6KBXQD3","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3IW3UBXE","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:0dd5eb1fc0552f95ed6686146d248a69f1ae9914c3d8330f7de9cc065914f305","target":"graph","created_at":"2026-05-17T23:51:51Z","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":"Arabic is recognised as the 4th most used language of the Internet. Arabic has three main varieties: (1) classical Arabic (CA), (2) Modern Standard Arabic (MSA), (3) Arabic Dialect (AD). MSA and AD could be written either in Arabic or in Roman script (Arabizi), which corresponds to Arabic written with Latin letters, numerals and punctuation. Due to the complexity of this language and the number of corresponding challenges for NLP, many surveys have been conducted, in order to synthesise the work done on Arabic. However these surveys principally focus on two varieties of Arabic (MSA and AD, wri","authors_text":"Billel Gueni, Damien Nouvel, Faical Azouaou, Houda Sa\\^adane, Imane Guellil","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T09:22:35Z","title":"Arabic natural language processing: An overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02784","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:ce1c86404f4c65d41d4baac1fc58133a219a1deacb0ed77da7a55c1582469bfe","target":"record","created_at":"2026-05-17T23:51:51Z","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":"881b45666421c996c8b35bef799ca7196e50bd95289699e45a413d43bcf71992","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T09:22:35Z","title_canon_sha256":"9fafb8ecc390c9b2785ec9b6e4b81c3850ad6586232256f13b4439c135529220"},"schema_version":"1.0","source":{"id":"1903.02784","kind":"arxiv","version":1}},"canonical_sha256":"da2dba06e44f941bc07b317608edcd4204b60305bcf9e8fc99e9842d2a56825e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2dba06e44f941bc07b317608edcd4204b60305bcf9e8fc99e9842d2a56825e","first_computed_at":"2026-05-17T23:51:51.118337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:51.118337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQ5A7/9BtbkweebvzVCy8NQQPuWaX5o0DB6tPbTS7co/DbK911MHPn4fjntIHQizcVAEecBXzS5jKgK0vlnUCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:51.119170Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.02784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce1c86404f4c65d41d4baac1fc58133a219a1deacb0ed77da7a55c1582469bfe","sha256:0dd5eb1fc0552f95ed6686146d248a69f1ae9914c3d8330f7de9cc065914f305"],"state_sha256":"87e04b955b0e283ed608e6c9193982b11e54aec18bc7667a4c7cd09b940a38ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hr5HMFNpwUsxxh++d8GuQ97bNAb/4JVLpX6x3k1wC2ciIgU8lddXzr7lcWu8uq7KvtKHvqMWVawsfoK+6DmdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T05:29:41.076054Z","bundle_sha256":"f394c2bdc35f9fd3976b76d0884ecdb68d297e276a984246637b2d954fd1f061"}}