{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VRQ3NVJMV3W7DYUXM52E2GUTQZ","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":"5e724e36df609beb1e083cca750df5aa642dceb473c87cc627ff20dd8c159f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-18T12:36:06Z","title_canon_sha256":"0358c445eefb97f7acd8eb2986318ab84c0cfa0a0b6b0f2537d8edafc9f9fa9b"},"schema_version":"1.0","source":{"id":"1710.06700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06700","created_at":"2026-05-18T00:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06700v1","created_at":"2026-05-18T00:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06700","created_at":"2026-05-18T00:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"VRQ3NVJMV3W7","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VRQ3NVJMV3W7DYUX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VRQ3NVJM","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:3cc7529ab44447d006f4385192a1f8f26ea9b8b90e23dee92e576381c4284a72","target":"graph","created_at":"2026-05-18T00:32:32Z","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 describe the complexity of building a lemmatizer for Arabic which has a rich and complex derivational morphology, and we discuss the need for a fast and accurate lammatization to enhance Arabic Information Retrieval (IR) results. We also introduce a new data set that can be used to test lemmatization accuracy, and an efficient lemmatization algorithm that outperforms state-of-the-art Arabic lemmatization in terms of accuracy and speed. We share the data set and the code for public.","authors_text":"Hamdy Mubarak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-18T12:36:06Z","title":"Build Fast and Accurate Lemmatization for Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06700","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:faa813dd622ed063b5a0aed08d2c4e7d4061461dda9690f89158c44381a8ddfe","target":"record","created_at":"2026-05-18T00:32:32Z","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":"5e724e36df609beb1e083cca750df5aa642dceb473c87cc627ff20dd8c159f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-18T12:36:06Z","title_canon_sha256":"0358c445eefb97f7acd8eb2986318ab84c0cfa0a0b6b0f2537d8edafc9f9fa9b"},"schema_version":"1.0","source":{"id":"1710.06700","kind":"arxiv","version":1}},"canonical_sha256":"ac61b6d52caeedf1e29767744d1a9386697b8c91786159beb4b9d6cd7c090e80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac61b6d52caeedf1e29767744d1a9386697b8c91786159beb4b9d6cd7c090e80","first_computed_at":"2026-05-18T00:32:32.927701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:32.927701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eb6T4+lYP5re8z7H+zkxJwjqjdoCwINpDCmKYCWJRt7fxZ3+MCMqfI89yUfMUAIdB0yzyyfasvMjcuCwF9FGBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:32.928399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.06700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faa813dd622ed063b5a0aed08d2c4e7d4061461dda9690f89158c44381a8ddfe","sha256:3cc7529ab44447d006f4385192a1f8f26ea9b8b90e23dee92e576381c4284a72"],"state_sha256":"c446988ff509376b4160b55bd86ce6b103c20e812102a1461e6aa7fae745bd23"}