{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:36LCQUJ73DES365WET65UX2E3E","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":"5b6ca712ef1bb41a2063079852f6a4e827b7369feb22cb2d6d65e3e64cb81938","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T16:37:54Z","title_canon_sha256":"8db0a7d33efef4ffaad8e834c577be1873e9ac4f4b0b9f24ac7ead9d788918c1"},"schema_version":"1.0","source":{"id":"2403.17848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17848","created_at":"2026-07-05T08:00:56Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17848v1","created_at":"2026-07-05T08:00:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17848","created_at":"2026-07-05T08:00:56Z"},{"alias_kind":"pith_short_12","alias_value":"36LCQUJ73DES","created_at":"2026-07-05T08:00:56Z"},{"alias_kind":"pith_short_16","alias_value":"36LCQUJ73DES365W","created_at":"2026-07-05T08:00:56Z"},{"alias_kind":"pith_short_8","alias_value":"36LCQUJ7","created_at":"2026-07-05T08:00:56Z"}],"graph_snapshots":[{"event_id":"sha256:f728ea4b410c6b7b9c76595c04a5d69ccfdd520358b9b21f4a7e385cb7df2566","target":"graph","created_at":"2026-07-05T08:00:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.17848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we address the significant gap in Arabic natural language processing (NLP) resources by introducing ArabicaQA, the first large-scale dataset for machine reading comprehension and open-domain question answering in Arabic. This comprehensive dataset, consisting of 89,095 answerable and 3,701 unanswerable questions created by crowdworkers to look similar to answerable ones, along with additional labels of open-domain questions marks a crucial advancement in Arabic NLP resources. We also present AraDPR, the first dense passage retrieval model trained on the Arabic Wikipedia corpus, ","authors_text":"Abdelrahman Abdallah, Adam Jatowt, Mahmoud Abdalla, Mahmoud Kasem, Mohamed Elkasaby, Mohamed Mahmoud, Yasser Elbendary","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T16:37:54Z","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17848","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:dd16e0207297770bab15410c91704eb94fdc8b42ee391f078e5f35e2ebb54594","target":"record","created_at":"2026-07-05T08:00:56Z","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":"5b6ca712ef1bb41a2063079852f6a4e827b7369feb22cb2d6d65e3e64cb81938","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T16:37:54Z","title_canon_sha256":"8db0a7d33efef4ffaad8e834c577be1873e9ac4f4b0b9f24ac7ead9d788918c1"},"schema_version":"1.0","source":{"id":"2403.17848","kind":"arxiv","version":1}},"canonical_sha256":"df9628513fd8c92dfbb624fdda5f44d9143c8b2f88f924ff63214a564758bcf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df9628513fd8c92dfbb624fdda5f44d9143c8b2f88f924ff63214a564758bcf9","first_computed_at":"2026-07-05T08:00:56.158030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:56.158030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eMXOmT46fblnhUU7hcgr0v+Wx+389x78p4gBHGEKjiHvEGBCvM1O2IJ6zYBUoBr6ux/Hlm9fzm/g+mzhQzSXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:56.158512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd16e0207297770bab15410c91704eb94fdc8b42ee391f078e5f35e2ebb54594","sha256:f728ea4b410c6b7b9c76595c04a5d69ccfdd520358b9b21f4a7e385cb7df2566"],"state_sha256":"0d85cb59b2771e6e649f5f20b45e70ecf3c45a5679d3c6619e39a40a54927f01"}