{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LYKD3BVEKXITP7PEHBZ4W7EXNL","short_pith_number":"pith:LYKD3BVE","canonical_record":{"source":{"id":"2505.17082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:38:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e966723f68ee7a32d8795ba00e46e5c12292b52d25d7137f035f2d572579b79d","abstract_canon_sha256":"e5b2dc78675bd6781f9b5c3abd71191a482aa9575ce62e317285fc39d522316a"},"schema_version":"1.0"},"canonical_sha256":"5e143d86a455d137fde43873cb7c976afbfd9e3bf27bd743a5877c9abbc3a47c","source":{"kind":"arxiv","id":"2505.17082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17082","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17082v1","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17082","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"LYKD3BVEKXIT","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"LYKD3BVEKXITP7PE","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"LYKD3BVE","created_at":"2026-07-05T11:07:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LYKD3BVEKXITP7PEHBZ4W7EXNL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:38:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e966723f68ee7a32d8795ba00e46e5c12292b52d25d7137f035f2d572579b79d","abstract_canon_sha256":"e5b2dc78675bd6781f9b5c3abd71191a482aa9575ce62e317285fc39d522316a"},"schema_version":"1.0"},"canonical_sha256":"5e143d86a455d137fde43873cb7c976afbfd9e3bf27bd743a5877c9abbc3a47c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:46.839360Z","signature_b64":"WPXdVnKR03ayCEW0MbdyXZ43RLziwzBbvFo7tdKx7Q86aGkgjlKVxFg8fow4oEOIv9gGddWDb6IBD4ZG/EggDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e143d86a455d137fde43873cb7c976afbfd9e3bf27bd743a5877c9abbc3a47c","last_reissued_at":"2026-07-05T11:07:46.838884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:46.838884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17082","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":"2026-07-05T11:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D/+1dm79yBx3n09UGoBVMCr66SIUoOJrDDE4w1mQXXM87Mpbs1n8vjAcuCu02hRi37PTllG7tLsA4dpzyPEwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:52.255252Z"},"content_sha256":"7675362247d9b803ef5f24998367487c588a444460005e6112e5daf49b39b461","schema_version":"1.0","event_id":"sha256:7675362247d9b803ef5f24998367487c588a444460005e6112e5daf49b39b461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LYKD3BVEKXITP7PEHBZ4W7EXNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abderrahman Skiredj, Ferdaous Azhari, Houdaifa Atou, Ismail Berrada, Nouamane Tazi","submitted_at":"2025-05-20T12:38:42Z","abstract_excerpt":"Open-source large language models (LLMs) still marginalise Moroccan Arabic (Darija), forcing practitioners either to bolt on heavyweight Arabic adapters or to sacrifice the very reasoning skills that make LLMs useful. We show that a rigorously quality-over-quantity alignment strategy can surface fluent Darija while safeguarding the backbone s cross-lingual reasoning at a sliver of the usual compute. We translate three compact instruction suites LIMA 1 K, DEITA 6 K and TULU 50 K into Darija, preserve 20 of the English originals, and add mathematics, coding and scientific prompts. A LoRA-tuned G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17082","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/2505.17082/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":"2026-07-05T11:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bxbz/36dWjhuVm5KT5U5gWRa9EhakJyWmgfrcH/w+6+7S282O21lqMDkxhu2IwslDwJzN8sVDkiDLcSoyrPRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:52.255859Z"},"content_sha256":"07bd3ff23a063689b219471dd55a6815bfe3253cbb3e17906992c75a2126bde6","schema_version":"1.0","event_id":"sha256:07bd3ff23a063689b219471dd55a6815bfe3253cbb3e17906992c75a2126bde6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/bundle.json","state_url":"https://pith.science/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/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":"2026-08-08T20:55:52Z","links":{"resolver":"https://pith.science/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL","bundle":"https://pith.science/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/bundle.json","state":"https://pith.science/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYKD3BVEKXITP7PEHBZ4W7EXNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYKD3BVEKXITP7PEHBZ4W7EXNL","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":"e5b2dc78675bd6781f9b5c3abd71191a482aa9575ce62e317285fc39d522316a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:38:42Z","title_canon_sha256":"e966723f68ee7a32d8795ba00e46e5c12292b52d25d7137f035f2d572579b79d"},"schema_version":"1.0","source":{"id":"2505.17082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17082","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17082v1","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17082","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"LYKD3BVEKXIT","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"LYKD3BVEKXITP7PE","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"LYKD3BVE","created_at":"2026-07-05T11:07:46Z"}],"graph_snapshots":[{"event_id":"sha256:07bd3ff23a063689b219471dd55a6815bfe3253cbb3e17906992c75a2126bde6","target":"graph","created_at":"2026-07-05T11:07:46Z","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/2505.17082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-source large language models (LLMs) still marginalise Moroccan Arabic (Darija), forcing practitioners either to bolt on heavyweight Arabic adapters or to sacrifice the very reasoning skills that make LLMs useful. We show that a rigorously quality-over-quantity alignment strategy can surface fluent Darija while safeguarding the backbone s cross-lingual reasoning at a sliver of the usual compute. We translate three compact instruction suites LIMA 1 K, DEITA 6 K and TULU 50 K into Darija, preserve 20 of the English originals, and add mathematics, coding and scientific prompts. A LoRA-tuned G","authors_text":"Abderrahman Skiredj, Ferdaous Azhari, Houdaifa Atou, Ismail Berrada, Nouamane Tazi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:38:42Z","title":"GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17082","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":"sha256:7675362247d9b803ef5f24998367487c588a444460005e6112e5daf49b39b461","target":"record","created_at":"2026-07-05T11:07:46Z","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":"e5b2dc78675bd6781f9b5c3abd71191a482aa9575ce62e317285fc39d522316a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:38:42Z","title_canon_sha256":"e966723f68ee7a32d8795ba00e46e5c12292b52d25d7137f035f2d572579b79d"},"schema_version":"1.0","source":{"id":"2505.17082","kind":"arxiv","version":1}},"canonical_sha256":"5e143d86a455d137fde43873cb7c976afbfd9e3bf27bd743a5877c9abbc3a47c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e143d86a455d137fde43873cb7c976afbfd9e3bf27bd743a5877c9abbc3a47c","first_computed_at":"2026-07-05T11:07:46.838884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:46.838884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WPXdVnKR03ayCEW0MbdyXZ43RLziwzBbvFo7tdKx7Q86aGkgjlKVxFg8fow4oEOIv9gGddWDb6IBD4ZG/EggDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:46.839360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7675362247d9b803ef5f24998367487c588a444460005e6112e5daf49b39b461","sha256:07bd3ff23a063689b219471dd55a6815bfe3253cbb3e17906992c75a2126bde6"],"state_sha256":"38219f42dd319f5fc3f19aee2a2144f21a2f4f32a166345dd145c8b6fe959eec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HS/0Y7uKD6SJkwsTTq9aCsZyMOf6Gl6b2t//9LN4a5WmC+nlsQJhmrEb6ak5y/ZKrnoqFJBCVeLsSz1CBD8XCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:55:52.260657Z","bundle_sha256":"4e801c49d3b402119ff090ae423cf0b995d13d6b44615c0f7401f58e08890649"}}