{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RE4PAEWTQPJRHNHPGEMPPEDBM5","short_pith_number":"pith:RE4PAEWT","canonical_record":{"source":{"id":"2407.15390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T05:35:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df0694bc83a62424d221d325a49550101064115ea37981e2ccade7821d944396","abstract_canon_sha256":"9a78d44dfbe6bbd23bb62582cb7719b585b719d5fc224aad96de02e56cfb0795"},"schema_version":"1.0"},"canonical_sha256":"8938f012d383d313b4ef3118f79061674ca9468b0fcb17841e440088b20a2375","source":{"kind":"arxiv","id":"2407.15390","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15390","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15390v1","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15390","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"RE4PAEWTQPJR","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_16","alias_value":"RE4PAEWTQPJRHNHP","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_8","alias_value":"RE4PAEWT","created_at":"2026-07-05T08:46:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RE4PAEWTQPJRHNHPGEMPPEDBM5","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T05:35:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df0694bc83a62424d221d325a49550101064115ea37981e2ccade7821d944396","abstract_canon_sha256":"9a78d44dfbe6bbd23bb62582cb7719b585b719d5fc224aad96de02e56cfb0795"},"schema_version":"1.0"},"canonical_sha256":"8938f012d383d313b4ef3118f79061674ca9468b0fcb17841e440088b20a2375","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:43.120121Z","signature_b64":"rHVwqdjvJ7QyACf2wyc2p2Gxpfo8pjR6LDxzQqJowroir1P6CsYND5/BDcXKAUHEZKvVlYSy4qvpjoMi7PyaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8938f012d383d313b4ef3118f79061674ca9468b0fcb17841e440088b20a2375","last_reissued_at":"2026-07-05T08:46:43.119685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:43.119685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15390","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UM++WauS/UVB4tZBmo9Tk88MToyFEU4wiyGB5vrGM59g5gRH3QH2b8ZCa0p/MBAEqfQ3IQ1R0gkva0ZyQxk3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T07:59:03.593471Z"},"content_sha256":"302864c831618c28fc2aeea4ee5ae1315c1d53c9068ab90927af94a098a8528d","schema_version":"1.0","event_id":"sha256:302864c831618c28fc2aeea4ee5ae1315c1d53c9068ab90927af94a098a8528d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RE4PAEWTQPJRHNHPGEMPPEDBM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALLaM: Large Language Models for Arabic and English","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdalghani Abujabal, Abdulmohsen Al-Thubaity, Ahmed Abdelali, Ali Alammari, Areeb Alowisheq, Faisal A. Mirza, Ghadah Alabduljabbar, Haidar Khan, Hassan A. Alahmed, Hisham A. Alyahya, Jeril Kuriakose, Majed Alrubaian, Maryam Al Mansour, M Saiful Bari, Nora Al-Twairesh, Norah A. Alzahrani, Nouf M. Alotaibi, Raghad Alkhathran, Raneem Alnajim, Salman Alsubaihi, Shaykhah Z. Alsubaie, Sultan Alrashed, Yazeed Alnumay, Yousef Almushayqih, Zaki Alawami","submitted_at":"2024-07-22T05:35:17Z","abstract_excerpt":"We present ALLaM: Arabic Large Language Model, a series of large language models to support the ecosystem of Arabic Language Technologies (ALT). ALLaM is carefully trained considering the values of language alignment and knowledge transfer at scale. Our autoregressive decoder-only architecture models demonstrate how second-language acquisition via vocabulary expansion and pretraining on a mixture of Arabic and English text can steer a model towards a new language (Arabic) without any catastrophic forgetting in the original language (English). Furthermore, we highlight the effectiveness of usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15390","kind":"arxiv","version":1},"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/2407.15390/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":"2026-07-05T08:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0oWP8B7bFcMK3cf/2N38ZlSPPKN8wNmP38MApVpqYzo0bkvKlueER3UqKdX+oX3S20o/Et7/bRlfvyoVDsMZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T07:59:03.593853Z"},"content_sha256":"d35daffe73476c139ae18ce238afbb2781d39a787f0462d307a5b6d4ece0b2af","schema_version":"1.0","event_id":"sha256:d35daffe73476c139ae18ce238afbb2781d39a787f0462d307a5b6d4ece0b2af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/bundle.json","state_url":"https://pith.science/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/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":"2026-07-24T07:59:03Z","links":{"resolver":"https://pith.science/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5","bundle":"https://pith.science/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/bundle.json","state":"https://pith.science/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RE4PAEWTQPJRHNHPGEMPPEDBM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RE4PAEWTQPJRHNHPGEMPPEDBM5","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":"9a78d44dfbe6bbd23bb62582cb7719b585b719d5fc224aad96de02e56cfb0795","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T05:35:17Z","title_canon_sha256":"df0694bc83a62424d221d325a49550101064115ea37981e2ccade7821d944396"},"schema_version":"1.0","source":{"id":"2407.15390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15390","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15390v1","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15390","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"RE4PAEWTQPJR","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_16","alias_value":"RE4PAEWTQPJRHNHP","created_at":"2026-07-05T08:46:43Z"},{"alias_kind":"pith_short_8","alias_value":"RE4PAEWT","created_at":"2026-07-05T08:46:43Z"}],"graph_snapshots":[{"event_id":"sha256:d35daffe73476c139ae18ce238afbb2781d39a787f0462d307a5b6d4ece0b2af","target":"graph","created_at":"2026-07-05T08:46:43Z","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/2407.15390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ALLaM: Arabic Large Language Model, a series of large language models to support the ecosystem of Arabic Language Technologies (ALT). ALLaM is carefully trained considering the values of language alignment and knowledge transfer at scale. Our autoregressive decoder-only architecture models demonstrate how second-language acquisition via vocabulary expansion and pretraining on a mixture of Arabic and English text can steer a model towards a new language (Arabic) without any catastrophic forgetting in the original language (English). Furthermore, we highlight the effectiveness of usin","authors_text":"Abdalghani Abujabal, Abdulmohsen Al-Thubaity, Ahmed Abdelali, Ali Alammari, Areeb Alowisheq, Faisal A. Mirza, Ghadah Alabduljabbar, Haidar Khan, Hassan A. Alahmed, Hisham A. Alyahya, Jeril Kuriakose, Majed Alrubaian, Maryam Al Mansour, M Saiful Bari, Nora Al-Twairesh, Norah A. Alzahrani, Nouf M. Alotaibi, Raghad Alkhathran, Raneem Alnajim, Salman Alsubaihi, Shaykhah Z. Alsubaie, Sultan Alrashed, Yazeed Alnumay, Yousef Almushayqih, Zaki Alawami","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T05:35:17Z","title":"ALLaM: Large Language Models for Arabic and English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15390","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":"sha256:302864c831618c28fc2aeea4ee5ae1315c1d53c9068ab90927af94a098a8528d","target":"record","created_at":"2026-07-05T08:46:43Z","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":"9a78d44dfbe6bbd23bb62582cb7719b585b719d5fc224aad96de02e56cfb0795","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T05:35:17Z","title_canon_sha256":"df0694bc83a62424d221d325a49550101064115ea37981e2ccade7821d944396"},"schema_version":"1.0","source":{"id":"2407.15390","kind":"arxiv","version":1}},"canonical_sha256":"8938f012d383d313b4ef3118f79061674ca9468b0fcb17841e440088b20a2375","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8938f012d383d313b4ef3118f79061674ca9468b0fcb17841e440088b20a2375","first_computed_at":"2026-07-05T08:46:43.119685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:43.119685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHVwqdjvJ7QyACf2wyc2p2Gxpfo8pjR6LDxzQqJowroir1P6CsYND5/BDcXKAUHEZKvVlYSy4qvpjoMi7PyaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:43.120121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:302864c831618c28fc2aeea4ee5ae1315c1d53c9068ab90927af94a098a8528d","sha256:d35daffe73476c139ae18ce238afbb2781d39a787f0462d307a5b6d4ece0b2af"],"state_sha256":"7fe2311d448f96810f29346222963c94ddcf508098e1cbea94790a6c1ef5ed88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pwd74w/1AsKRrQg3sJdJq6k1ac15yGjcg9PF2V4FPcwmQXgEXnQRHe1Iij3jLFTXlF1HkIQHnn9uGMaQ1NG3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T07:59:03.596030Z","bundle_sha256":"dcdcda7fe61af537c671f174681a6bd2f23cdae86c8d039eaa6f2c46d69c5115"}}