{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RKMBNGVWQWGMTZPNJ7MWH7KABM","short_pith_number":"pith:RKMBNGVW","canonical_record":{"source":{"id":"1611.04033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-11-12T18:41:58Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"8fd9429dbca806ddb14c7a8c999fe1968b7f64072a1a080544c325baef66bfbf","abstract_canon_sha256":"323f61e105e598ef2690a463ff6b6999aeccbcbe48c0185661fea1c50e6a9531"},"schema_version":"1.0"},"canonical_sha256":"8a98169ab6858cc9e5ed4fd963fd400b24930ad1ccc9949e6d9eb4f9c22353ae","source":{"kind":"arxiv","id":"1611.04033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04033","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04033v1","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04033","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"pith_short_12","alias_value":"RKMBNGVWQWGM","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RKMBNGVWQWGMTZPN","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RKMBNGVW","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RKMBNGVWQWGMTZPNJ7MWH7KABM","target":"record","payload":{"canonical_record":{"source":{"id":"1611.04033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-11-12T18:41:58Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"8fd9429dbca806ddb14c7a8c999fe1968b7f64072a1a080544c325baef66bfbf","abstract_canon_sha256":"323f61e105e598ef2690a463ff6b6999aeccbcbe48c0185661fea1c50e6a9531"},"schema_version":"1.0"},"canonical_sha256":"8a98169ab6858cc9e5ed4fd963fd400b24930ad1ccc9949e6d9eb4f9c22353ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:17.776559Z","signature_b64":"vkcwrpd38NfLkIR+XigwYeeVLdbMErAV0Opdm1R+a4wesWQUAkb5T8OCGMi79MjU8J7wvEFJm+3wrTe/LGPkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a98169ab6858cc9e5ed4fd963fd400b24930ad1ccc9949e6d9eb4f9c22353ae","last_reissued_at":"2026-05-18T00:59:17.776020Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:17.776020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.04033","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":"2026-05-18T00:59:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2uBYo/5Me4cOC3vEE3yCdU43VgpFlytRdifOHuR0hRgMmx89UJcnf3P58JGh86dDbRUbpK/FBBC/lCWu+u8ADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T21:29:52.081521Z"},"content_sha256":"96e69900b03ccc09205b97104f38fa27fc55c6ce61358ea6a18053901bd78c77","schema_version":"1.0","event_id":"sha256:96e69900b03ccc09205b97104f38fa27fc55c6ce61358ea6a18053901bd78c77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RKMBNGVWQWGMTZPNJ7MWH7KABM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"1.5 billion words Arabic Corpus","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"Ibrahim Abu El-khair","submitted_at":"2016-11-12T18:41:58Z","abstract_excerpt":"This study is an attempt to build a contemporary linguistic corpus for Arabic language. The corpus produced, is a text corpus includes more than five million newspaper articles. It contains over a billion and a half words in total, out of which, there is about three million unique words. The data were collected from newspaper articles in ten major news sources from eight Arabic countries, over a period of fourteen years. The corpus was encoded with two types of encoding, namely: UTF-8, and Windows CP-1256. Also it was marked with two mark-up languages, namely: SGML, and XML."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04033","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":"2026-05-18T00:59:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRT5J7AlrFXVVAS2xiyjpM5sLDnwtNspEGOJt9c3kiNXP1jRpasm7TVAs/TMkrjQWSOZ7TCJ7RcKFO0EBZciAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T21:29:52.081860Z"},"content_sha256":"bb2caa9523a27da42cb9b21cd3f30de844f7554a2719e6300398cc1eb675e82a","schema_version":"1.0","event_id":"sha256:bb2caa9523a27da42cb9b21cd3f30de844f7554a2719e6300398cc1eb675e82a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/bundle.json","state_url":"https://pith.science/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/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":"2026-07-03T21:29:52Z","links":{"resolver":"https://pith.science/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM","bundle":"https://pith.science/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/bundle.json","state":"https://pith.science/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKMBNGVWQWGMTZPNJ7MWH7KABM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RKMBNGVWQWGMTZPNJ7MWH7KABM","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":"323f61e105e598ef2690a463ff6b6999aeccbcbe48c0185661fea1c50e6a9531","cross_cats_sorted":["cs.DL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-11-12T18:41:58Z","title_canon_sha256":"8fd9429dbca806ddb14c7a8c999fe1968b7f64072a1a080544c325baef66bfbf"},"schema_version":"1.0","source":{"id":"1611.04033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04033","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04033v1","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04033","created_at":"2026-05-18T00:59:17Z"},{"alias_kind":"pith_short_12","alias_value":"RKMBNGVWQWGM","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RKMBNGVWQWGMTZPN","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RKMBNGVW","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:bb2caa9523a27da42cb9b21cd3f30de844f7554a2719e6300398cc1eb675e82a","target":"graph","created_at":"2026-05-18T00:59:17Z","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"},"paper":{"abstract_excerpt":"This study is an attempt to build a contemporary linguistic corpus for Arabic language. The corpus produced, is a text corpus includes more than five million newspaper articles. It contains over a billion and a half words in total, out of which, there is about three million unique words. The data were collected from newspaper articles in ten major news sources from eight Arabic countries, over a period of fourteen years. The corpus was encoded with two types of encoding, namely: UTF-8, and Windows CP-1256. Also it was marked with two mark-up languages, namely: SGML, and XML.","authors_text":"Ibrahim Abu El-khair","cross_cats":["cs.DL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-11-12T18:41:58Z","title":"1.5 billion words Arabic Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04033","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":"sha256:96e69900b03ccc09205b97104f38fa27fc55c6ce61358ea6a18053901bd78c77","target":"record","created_at":"2026-05-18T00:59:17Z","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":"323f61e105e598ef2690a463ff6b6999aeccbcbe48c0185661fea1c50e6a9531","cross_cats_sorted":["cs.DL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-11-12T18:41:58Z","title_canon_sha256":"8fd9429dbca806ddb14c7a8c999fe1968b7f64072a1a080544c325baef66bfbf"},"schema_version":"1.0","source":{"id":"1611.04033","kind":"arxiv","version":1}},"canonical_sha256":"8a98169ab6858cc9e5ed4fd963fd400b24930ad1ccc9949e6d9eb4f9c22353ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a98169ab6858cc9e5ed4fd963fd400b24930ad1ccc9949e6d9eb4f9c22353ae","first_computed_at":"2026-05-18T00:59:17.776020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:59:17.776020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vkcwrpd38NfLkIR+XigwYeeVLdbMErAV0Opdm1R+a4wesWQUAkb5T8OCGMi79MjU8J7wvEFJm+3wrTe/LGPkAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:59:17.776559Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.04033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96e69900b03ccc09205b97104f38fa27fc55c6ce61358ea6a18053901bd78c77","sha256:bb2caa9523a27da42cb9b21cd3f30de844f7554a2719e6300398cc1eb675e82a"],"state_sha256":"202d7c61e973fcbaa2d01e8d6e909b97c114e8e8271ce704be828e2b9875109f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T26YMPX+dmM+/XuJY92WC+t/k/TYswjcYSHfHBlSM1s9IYayUE+qcWagJHccYOwOLqVCFNi3N+hVqp4QpOSrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T21:29:52.085056Z","bundle_sha256":"459db5fce15b399b92852f25e415c8d53be4e705b557b6d8d1a49ba9961e6abc"}}