{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X325OLDCC4KQ77WRCHD6FAP2TX","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":"22fdcbd5e46437a59fabbccf3a88e3a86ecf52846fc563f7fb95bb8d811761f1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-01T00:04:58Z","title_canon_sha256":"f44356a6177219717eff40749d81b248e9031028b1d97bc7f9c3fdef26c255a1"},"schema_version":"1.0","source":{"id":"2506.06339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06339","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06339v1","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06339","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"X325OLDCC4KQ","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"X325OLDCC4KQ77WR","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"X325OLDC","created_at":"2026-07-05T11:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:fee7092759fbef469de76bceca0db81027795e661142dc91f1ca346160c5bccd","target":"graph","created_at":"2026-07-05T11:17:48Z","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/2506.06339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for combining the precision of retrieval systems with the fluency of large language models. While several studies have investigated RAG pipelines for high-resource languages, the optimization of RAG components for Arabic remains underexplored. This study presents a comprehensive empirical evaluation of state-of-the-art RAG components-including chunking strategies, embedding models, rerankers, and language models-across a diverse set of Arabic datasets. Using the RAGAS framework, we systematically compare performance ac","authors_text":"Ahmad Shabana, Ahmed Alhusayni, Ibrahim Aldailami, Israa Hamdine, Jumana Alsubhi, Mohammad D. Alahmadi, Suhayb Khayyat, Yazeed Iskandar","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-01T00:04:58Z","title":"Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06339","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:e535464fcf3d9326af0e5b0836161802475ec85cc126b071fa258b7ed5e84db0","target":"record","created_at":"2026-07-05T11:17:48Z","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":"22fdcbd5e46437a59fabbccf3a88e3a86ecf52846fc563f7fb95bb8d811761f1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-01T00:04:58Z","title_canon_sha256":"f44356a6177219717eff40749d81b248e9031028b1d97bc7f9c3fdef26c255a1"},"schema_version":"1.0","source":{"id":"2506.06339","kind":"arxiv","version":1}},"canonical_sha256":"bef5d72c6217150ffed111c7e281fa9dd66fb0546cbbbf04519d9a32422dfaf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef5d72c6217150ffed111c7e281fa9dd66fb0546cbbbf04519d9a32422dfaf9","first_computed_at":"2026-07-05T11:17:48.351865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:48.351865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2uw7s5bDxnz0BsHahXXOkMcRrXldNZemlpYCNjSgoEZ/EPJu4IGaHRf/UStrkRiezc9iFJHtCDwJvU4Mo0BNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:48.352383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e535464fcf3d9326af0e5b0836161802475ec85cc126b071fa258b7ed5e84db0","sha256:fee7092759fbef469de76bceca0db81027795e661142dc91f1ca346160c5bccd"],"state_sha256":"278838ef63573e03356fa1d74b4e8327e527535fb76509fe0ac50b1afefa751a"}