{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IAEGJCJRHMVTOPIT2M3SHLP3BO","short_pith_number":"pith:IAEGJCJR","canonical_record":{"source":{"id":"2503.00151","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e3f7f86db2f71bd3340576fd8607d670925299c124167c9d403207c5378fd44","abstract_canon_sha256":"6ad6ece6b84f024ccfabcca98976412ff927fd48df8cd1628c30aa218fe76857"},"schema_version":"1.0"},"canonical_sha256":"40086489313b2b373d13d33723adfb0b9b75305b506721f332ac2f59f71b64eb","source":{"kind":"arxiv","id":"2503.00151","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00151","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00151v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00151","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"IAEGJCJRHMVT","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"IAEGJCJRHMVTOPIT","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"IAEGJCJR","created_at":"2026-07-05T11:42:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IAEGJCJRHMVTOPIT2M3SHLP3BO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00151","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e3f7f86db2f71bd3340576fd8607d670925299c124167c9d403207c5378fd44","abstract_canon_sha256":"6ad6ece6b84f024ccfabcca98976412ff927fd48df8cd1628c30aa218fe76857"},"schema_version":"1.0"},"canonical_sha256":"40086489313b2b373d13d33723adfb0b9b75305b506721f332ac2f59f71b64eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:53.681274Z","signature_b64":"rN26gkZi6HWBnXhjm1e+h3s9XdWXSGozXFEJqk83Y0ivPCpXqkjDbFCE/4zAog3ZNsLRaibqOoOWWrebkhH+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40086489313b2b373d13d33723adfb0b9b75305b506721f332ac2f59f71b64eb","last_reissued_at":"2026-07-05T11:42:53.680778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:53.680778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00151","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tP34H2E7D4lNj/8NFWQpXTFMW0nau7YUubdSZiHODkfiFLM9Gu4DClVCHCJY/ahGWnCtEAwjbNzm6gIipwTKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:01:37.248994Z"},"content_sha256":"bccc5caf5c4f1a849922c298e7126055aab1aeb73857a454b4c1e0aa915c4bb4","schema_version":"1.0","event_id":"sha256:bccc5caf5c4f1a849922c298e7126055aab1aeb73857a454b4c1e0aa915c4bb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IAEGJCJRHMVTOPIT2M3SHLP3BO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdelhak Bouayad, Abdellah El Mekki, AbdelRahim A. Elmadany, Abdulfattah Mohammed Yahya, Abdulrahman S. Al-Batati, Ahmed Oumar El-Shangiti, Ahmed Sorkatti, Aisha Alraeesi, Amal Makouar, Amine Ziad Ounnoughene, Anis Koubaa, Dania Alkawi, Elgizouli Mohamed, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Hamzah A. Alsayadi, Hanin Atwany, Hiba Zayed, Houdaifa Atou, Imen Jarraya, Ismail Berrada, Issam Ait Yahia, Marwa Mohamed Ali, Mohamedou cheikh tourad, Mohammed Anwar Al-Ghrawi, Mohammed Machrouh, Muhammad Abdul-Mageed, Muhammed Saeed, Mukhtar Mohamed, Mustafa Jarrar, Noha Taha Elgindi, Omer Nacar, Rahaf Alhamouri, Reem Abdel-Salam, Rouabhia Anfel, Rwaa Assi, Safaa Taher Abdelfadil, Samar Mohamed Magdy, Sara Shatnawi, Serry Sibaee, Shady Shehata, Walid Al-Dhabyani, Yasir Ech-Chammakhy, Youssef Nafea","submitted_at":"2025-02-28T19:59:13Z","abstract_excerpt":"As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-long community-driven project covering all 22 Arab countries. The dataset includes instructions (input, response pairs) in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world, all of whom are authors of this paper, our dataset offers a broad, inclusive perspective. We use our dataset to evaluate the cultural and dialectal capa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00151","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.00151/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SN1VxiWc/MwYQSxT9k5TI1DAJpBvChccolyU7d01y6FclD5KAYERpAwXO91DgFFcbaXIXe7Sbhdj2McN21PHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:01:37.249734Z"},"content_sha256":"98f36159641614180756a8abb49e45c34ac7967edf426fc9bab711c41eb22940","schema_version":"1.0","event_id":"sha256:98f36159641614180756a8abb49e45c34ac7967edf426fc9bab711c41eb22940"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/bundle.json","state_url":"https://pith.science/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/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":"2026-07-07T13:01:37Z","links":{"resolver":"https://pith.science/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO","bundle":"https://pith.science/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/bundle.json","state":"https://pith.science/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAEGJCJRHMVTOPIT2M3SHLP3BO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IAEGJCJRHMVTOPIT2M3SHLP3BO","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":"6ad6ece6b84f024ccfabcca98976412ff927fd48df8cd1628c30aa218fe76857","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:59:13Z","title_canon_sha256":"4e3f7f86db2f71bd3340576fd8607d670925299c124167c9d403207c5378fd44"},"schema_version":"1.0","source":{"id":"2503.00151","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00151","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00151v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00151","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"IAEGJCJRHMVT","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"IAEGJCJRHMVTOPIT","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"IAEGJCJR","created_at":"2026-07-05T11:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:98f36159641614180756a8abb49e45c34ac7967edf426fc9bab711c41eb22940","target":"graph","created_at":"2026-07-05T11:42:53Z","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/2503.00151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-long community-driven project covering all 22 Arab countries. The dataset includes instructions (input, response pairs) in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world, all of whom are authors of this paper, our dataset offers a broad, inclusive perspective. We use our dataset to evaluate the cultural and dialectal capa","authors_text":"Abdelhak Bouayad, Abdellah El Mekki, AbdelRahim A. Elmadany, Abdulfattah Mohammed Yahya, Abdulrahman S. Al-Batati, Ahmed Oumar El-Shangiti, Ahmed Sorkatti, Aisha Alraeesi, Amal Makouar, Amine Ziad Ounnoughene, Anis Koubaa, Dania Alkawi, Elgizouli Mohamed, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Hamzah A. Alsayadi, Hanin Atwany, Hiba Zayed, Houdaifa Atou, Imen Jarraya, Ismail Berrada, Issam Ait Yahia, Marwa Mohamed Ali, Mohamedou cheikh tourad, Mohammed Anwar Al-Ghrawi, Mohammed Machrouh, Muhammad Abdul-Mageed, Muhammed Saeed, Mukhtar Mohamed, Mustafa Jarrar, Noha Taha Elgindi, Omer Nacar, Rahaf Alhamouri, Reem Abdel-Salam, Rouabhia Anfel, Rwaa Assi, Safaa Taher Abdelfadil, Samar Mohamed Magdy, Sara Shatnawi, Serry Sibaee, Shady Shehata, Walid Al-Dhabyani, Yasir Ech-Chammakhy, Youssef Nafea","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:59:13Z","title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00151","kind":"arxiv","version":2},"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:bccc5caf5c4f1a849922c298e7126055aab1aeb73857a454b4c1e0aa915c4bb4","target":"record","created_at":"2026-07-05T11:42:53Z","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":"6ad6ece6b84f024ccfabcca98976412ff927fd48df8cd1628c30aa218fe76857","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T19:59:13Z","title_canon_sha256":"4e3f7f86db2f71bd3340576fd8607d670925299c124167c9d403207c5378fd44"},"schema_version":"1.0","source":{"id":"2503.00151","kind":"arxiv","version":2}},"canonical_sha256":"40086489313b2b373d13d33723adfb0b9b75305b506721f332ac2f59f71b64eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40086489313b2b373d13d33723adfb0b9b75305b506721f332ac2f59f71b64eb","first_computed_at":"2026-07-05T11:42:53.680778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:53.680778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rN26gkZi6HWBnXhjm1e+h3s9XdWXSGozXFEJqk83Y0ivPCpXqkjDbFCE/4zAog3ZNsLRaibqOoOWWrebkhH+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:53.681274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00151","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bccc5caf5c4f1a849922c298e7126055aab1aeb73857a454b4c1e0aa915c4bb4","sha256:98f36159641614180756a8abb49e45c34ac7967edf426fc9bab711c41eb22940"],"state_sha256":"a7103e6404a75ab90760baf7f9ab030f33a1144ca4f7d65eff81722f6d23cbd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iaf5o7VYiFaQru8MsIWH36uUIUVEEJb9HopIetAww5myq6/B6h/j/OCrrmBiXhpCjqK1TMYjCAAV2wifhx7fCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:01:37.253525Z","bundle_sha256":"8b5da891c525ccf4a2c0a4f2e6d32a7375a3342bb46a4f827615379fa8e7dd58"}}