{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y652OHKLRI6OU2ZW22BLVTB5VO","short_pith_number":"pith:Y652OHKL","canonical_record":{"source":{"id":"2403.06354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:04:36Z","cross_cats_sorted":[],"title_canon_sha256":"fbbc8018d9a2420c87eb5fde0aa015678e0cea587723bb2468ae7eddb236b749","abstract_canon_sha256":"4d1e06f69dd8f679ecbc8854ccc1ba4ffe97e85c123cbd4b272c88d4e87bea4b"},"schema_version":"1.0"},"canonical_sha256":"c7bba71d4b8a3cea6b36d682bacc3dab9e58bc1dfff000140123b5d7b1495b9d","source":{"kind":"arxiv","id":"2403.06354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06354","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06354v1","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06354","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"Y652OHKLRI6O","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"Y652OHKLRI6OU2ZW","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"Y652OHKL","created_at":"2026-07-05T07:54:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y652OHKLRI6OU2ZW22BLVTB5VO","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:04:36Z","cross_cats_sorted":[],"title_canon_sha256":"fbbc8018d9a2420c87eb5fde0aa015678e0cea587723bb2468ae7eddb236b749","abstract_canon_sha256":"4d1e06f69dd8f679ecbc8854ccc1ba4ffe97e85c123cbd4b272c88d4e87bea4b"},"schema_version":"1.0"},"canonical_sha256":"c7bba71d4b8a3cea6b36d682bacc3dab9e58bc1dfff000140123b5d7b1495b9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:22.379461Z","signature_b64":"3ZetNDn7suNiD9bkKgBmeZID0VrTqUYuaK8LixlBiEc8yVheSTrPasElUKF5HNOFRpxvOoeecEgxQQX4LSYfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7bba71d4b8a3cea6b36d682bacc3dab9e58bc1dfff000140123b5d7b1495b9d","last_reissued_at":"2026-07-05T07:54:22.378984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:22.378984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06354","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":"2026-07-05T07:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dngr71gKPqHLqyejcJWtDF7+ZI3SKHn047uAaaQJ6c461S9FwE13X9xxv0y/WPdlnAjh5o8/+9kcMv5+3CTvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:41:17.888653Z"},"content_sha256":"34767201ee30b16fdfc1c9d89fff4c55e6df5d184a1f19618a23083bc2f33345","schema_version":"1.0","event_id":"sha256:34767201ee30b16fdfc1c9d89fff4c55e6df5d184a1f19618a23083bc2f33345"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y652OHKLRI6OU2ZW22BLVTB5VO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Michael Andersland","submitted_at":"2024-03-11T01:04:36Z","abstract_excerpt":"Large Language Models (LLMs) like GPT-4 and LLaMA have shown incredible proficiency at natural language processing tasks and have even begun to excel at tasks across other modalities such as vision and audio. Despite their success, LLMs often struggle to perform well on low-resource languages because there is so little training data available. This shortcoming is especially prevalent with open source models. In this work, we explore training LLaMA-2 to speak Amharic, a language which is spoken by over 50 million people world wide, but has orders of magnitude less data available than languages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06354","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/2403.06354/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":"2026-07-05T07:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qn1W/jjkFsrMVvwpupCvfZzgcbuHpahypsAujVj0m982ozTt+WArY4odFFlE4aCTCBygO/Ghb/S0pJqE16MxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:41:17.889159Z"},"content_sha256":"6c54018ebfc1c8d73ebdac3aef31d744946e190aea82c39c2968fff32750e01c","schema_version":"1.0","event_id":"sha256:6c54018ebfc1c8d73ebdac3aef31d744946e190aea82c39c2968fff32750e01c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/bundle.json","state_url":"https://pith.science/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/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":"2026-08-09T03:41:17Z","links":{"resolver":"https://pith.science/pith/Y652OHKLRI6OU2ZW22BLVTB5VO","bundle":"https://pith.science/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/bundle.json","state":"https://pith.science/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y652OHKLRI6OU2ZW22BLVTB5VO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y652OHKLRI6OU2ZW22BLVTB5VO","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":"4d1e06f69dd8f679ecbc8854ccc1ba4ffe97e85c123cbd4b272c88d4e87bea4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:04:36Z","title_canon_sha256":"fbbc8018d9a2420c87eb5fde0aa015678e0cea587723bb2468ae7eddb236b749"},"schema_version":"1.0","source":{"id":"2403.06354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06354","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06354v1","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06354","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"Y652OHKLRI6O","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"Y652OHKLRI6OU2ZW","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"Y652OHKL","created_at":"2026-07-05T07:54:22Z"}],"graph_snapshots":[{"event_id":"sha256:6c54018ebfc1c8d73ebdac3aef31d744946e190aea82c39c2968fff32750e01c","target":"graph","created_at":"2026-07-05T07:54:22Z","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/2403.06354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) like GPT-4 and LLaMA have shown incredible proficiency at natural language processing tasks and have even begun to excel at tasks across other modalities such as vision and audio. Despite their success, LLMs often struggle to perform well on low-resource languages because there is so little training data available. This shortcoming is especially prevalent with open source models. In this work, we explore training LLaMA-2 to speak Amharic, a language which is spoken by over 50 million people world wide, but has orders of magnitude less data available than languages ","authors_text":"Michael Andersland","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:04:36Z","title":"Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06354","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":"sha256:34767201ee30b16fdfc1c9d89fff4c55e6df5d184a1f19618a23083bc2f33345","target":"record","created_at":"2026-07-05T07:54:22Z","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":"4d1e06f69dd8f679ecbc8854ccc1ba4ffe97e85c123cbd4b272c88d4e87bea4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:04:36Z","title_canon_sha256":"fbbc8018d9a2420c87eb5fde0aa015678e0cea587723bb2468ae7eddb236b749"},"schema_version":"1.0","source":{"id":"2403.06354","kind":"arxiv","version":1}},"canonical_sha256":"c7bba71d4b8a3cea6b36d682bacc3dab9e58bc1dfff000140123b5d7b1495b9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7bba71d4b8a3cea6b36d682bacc3dab9e58bc1dfff000140123b5d7b1495b9d","first_computed_at":"2026-07-05T07:54:22.378984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:22.378984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZetNDn7suNiD9bkKgBmeZID0VrTqUYuaK8LixlBiEc8yVheSTrPasElUKF5HNOFRpxvOoeecEgxQQX4LSYfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:22.379461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34767201ee30b16fdfc1c9d89fff4c55e6df5d184a1f19618a23083bc2f33345","sha256:6c54018ebfc1c8d73ebdac3aef31d744946e190aea82c39c2968fff32750e01c"],"state_sha256":"89b59fedb8f9d8bb37d5b6f23c403fb13445f6e4db3235356295c2e6372839ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VwwVuNerIykADo2dySWaYrw8UWKfyICCfYZ3IgyoSxiVOqTymIpV9ybfgILOZ0uPC2f7Dm3uqbHhtM0KWRcwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:41:17.893940Z","bundle_sha256":"c5c2fe228850af52c8c42fe18a0abc0133e4d73d55574bea8124ebe8c952ae16"}}