{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LC56V2FHBUTX2NPLRNXHFU7YUW","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":"ccf2c0906d9bd109dfc6ac90c0e09a9dab280382635ec30a6af7918806021249","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-28T21:10:28Z","title_canon_sha256":"cc93c39ee55dcdd51311a5d15885028d47ed954a3faf6c2a23011267f108a06e"},"schema_version":"1.0","source":{"id":"1612.08989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08989","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08989v1","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08989","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"LC56V2FHBUTX","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LC56V2FHBUTX2NPL","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LC56V2FH","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:943097c7b5f2271b39f4004ba956282b88f0f361c8f9659e03b59dc0a556a255","target":"graph","created_at":"2026-05-18T00:53:46Z","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 a widely-spoken language with a rich and long history spanning more than fourteen centuries. Yet existing Arabic corpora largely focus on the modern period or lack sufficient diachronic information. We develop a large-scale, historical corpus of Arabic of about 1 billion words from diverse periods of time. We clean this corpus, process it with a morphological analyzer, and enhance it by detecting parallel passages and automatically dating undated texts. We demonstrate its utility with selected case-studies in which we show its application to the digital humanities.","authors_text":"Alexander Magidow, Avi Shmidman, Maxim Romanov, Moshe Koppel, Yonatan Belinkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-28T21:10:28Z","title":"Shamela: A Large-Scale Historical Arabic Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08989","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":"sha256:3fce87e7e43c8e5292e40eeaa9fb43d4726abad6f30d9d122f9f18544be0676c","target":"record","created_at":"2026-05-18T00:53:46Z","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":"ccf2c0906d9bd109dfc6ac90c0e09a9dab280382635ec30a6af7918806021249","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-28T21:10:28Z","title_canon_sha256":"cc93c39ee55dcdd51311a5d15885028d47ed954a3faf6c2a23011267f108a06e"},"schema_version":"1.0","source":{"id":"1612.08989","kind":"arxiv","version":1}},"canonical_sha256":"58bbeae8a70d277d35eb8b6e72d3f8a5b8a2f067cde4b359d5c5a0a8c691f2c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58bbeae8a70d277d35eb8b6e72d3f8a5b8a2f067cde4b359d5c5a0a8c691f2c6","first_computed_at":"2026-05-18T00:53:46.704781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:46.704781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uz9HDVXTJSwf6ZhKLTRBXHuEWGJ6aii+GOJ7iqAwbTSN7ejUrOS9oRmLx6R9MnT5oXOh49ktaC1sJtMjBINxCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:46.705177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.08989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fce87e7e43c8e5292e40eeaa9fb43d4726abad6f30d9d122f9f18544be0676c","sha256:943097c7b5f2271b39f4004ba956282b88f0f361c8f9659e03b59dc0a556a255"],"state_sha256":"e1ece2a3464b3be0f6e8a642fba5ba3495b25193942f7280875148e32386720b"}