{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:57WWHJAJAFOGJKK2ZJ4KEOOSL4","short_pith_number":"pith:57WWHJAJ","canonical_record":{"source":{"id":"2506.05057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:02:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34886669e5cea2b9b402a02ab01a276d9fac892a3a0b23ef29d42eab52ae6002","abstract_canon_sha256":"c657ce031a1072511fc6de78694e0170e8b3ae5597a39e29ff09431d3f7f4616"},"schema_version":"1.0"},"canonical_sha256":"efed63a409015c64a95aca78a239d25f1717520f6c79f45508b7723dcecaeb59","source":{"kind":"arxiv","id":"2506.05057","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05057","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05057v1","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05057","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"57WWHJAJAFOG","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"57WWHJAJAFOGJKK2","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"57WWHJAJ","created_at":"2026-07-05T11:16:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:57WWHJAJAFOGJKK2ZJ4KEOOSL4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:02:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34886669e5cea2b9b402a02ab01a276d9fac892a3a0b23ef29d42eab52ae6002","abstract_canon_sha256":"c657ce031a1072511fc6de78694e0170e8b3ae5597a39e29ff09431d3f7f4616"},"schema_version":"1.0"},"canonical_sha256":"efed63a409015c64a95aca78a239d25f1717520f6c79f45508b7723dcecaeb59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.617139Z","signature_b64":"fsR+Z9rbvXKsBdJVA/815LPDqIMXgpkzqUuUstgcLcPunBvPNKGHRNsBVPArii6A4hSyODr+Zk6TQ/1Sj/+TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efed63a409015c64a95aca78a239d25f1717520f6c79f45508b7723dcecaeb59","last_reissued_at":"2026-07-05T11:16:41.616599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.616599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05057","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":"2026-07-05T11:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYg+rGQfXdsvxsGb8Pdgzv9XCpLCgdz8+U7hDerj6eoflCHiX4WrO2OQylD0yzG3wkCaIwXBOa0dYMkUZZMDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:35:55.209424Z"},"content_sha256":"5d45bddb9fb756209fa02cdacbe96307319d5222a5b378597b32a10d47d4ab1a","schema_version":"1.0","event_id":"sha256:5d45bddb9fb756209fa02cdacbe96307319d5222a5b378597b32a10d47d4ab1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:57WWHJAJAFOGJKK2ZJ4KEOOSL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TALL -- A Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amos Azaria, Moshe Ofer, Orel Zamler","submitted_at":"2025-06-05T14:02:12Z","abstract_excerpt":"Large Language Models (LLMs) excel in high-resource languages but struggle with low-resource languages due to limited training data. This paper presents TALL (Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages), which integrates an LLM with two bilingual translation models. TALL transforms low-resource inputs into high-resource representations, leveraging the LLM's capabilities while preserving linguistic features through dimension alignment layers and custom transformers. Our experiments on Hebrew demonstrate significant improvements over several baselines, includi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05057","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/2506.05057/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":"2026-07-05T11:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUvi4RBMwWxOMi4OKr56vw001vhW0oxN63o+2aDRmVBZwCkZPJQkjJBA5TLLEz0BGnR+oZyo38p5w/ImOZOiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:35:55.210000Z"},"content_sha256":"520b570096db7857588be08a851cdd5fe1db93dc15b284e23435894e38b12e51","schema_version":"1.0","event_id":"sha256:520b570096db7857588be08a851cdd5fe1db93dc15b284e23435894e38b12e51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/bundle.json","state_url":"https://pith.science/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/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":"2026-08-07T23:35:55Z","links":{"resolver":"https://pith.science/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4","bundle":"https://pith.science/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/bundle.json","state":"https://pith.science/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57WWHJAJAFOGJKK2ZJ4KEOOSL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:57WWHJAJAFOGJKK2ZJ4KEOOSL4","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":"c657ce031a1072511fc6de78694e0170e8b3ae5597a39e29ff09431d3f7f4616","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:02:12Z","title_canon_sha256":"34886669e5cea2b9b402a02ab01a276d9fac892a3a0b23ef29d42eab52ae6002"},"schema_version":"1.0","source":{"id":"2506.05057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05057","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05057v1","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05057","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"57WWHJAJAFOG","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"57WWHJAJAFOGJKK2","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"57WWHJAJ","created_at":"2026-07-05T11:16:41Z"}],"graph_snapshots":[{"event_id":"sha256:520b570096db7857588be08a851cdd5fe1db93dc15b284e23435894e38b12e51","target":"graph","created_at":"2026-07-05T11:16:41Z","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/2506.05057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel in high-resource languages but struggle with low-resource languages due to limited training data. This paper presents TALL (Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages), which integrates an LLM with two bilingual translation models. TALL transforms low-resource inputs into high-resource representations, leveraging the LLM's capabilities while preserving linguistic features through dimension alignment layers and custom transformers. Our experiments on Hebrew demonstrate significant improvements over several baselines, includi","authors_text":"Amos Azaria, Moshe Ofer, Orel Zamler","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:02:12Z","title":"TALL -- A Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05057","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":"sha256:5d45bddb9fb756209fa02cdacbe96307319d5222a5b378597b32a10d47d4ab1a","target":"record","created_at":"2026-07-05T11:16:41Z","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":"c657ce031a1072511fc6de78694e0170e8b3ae5597a39e29ff09431d3f7f4616","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:02:12Z","title_canon_sha256":"34886669e5cea2b9b402a02ab01a276d9fac892a3a0b23ef29d42eab52ae6002"},"schema_version":"1.0","source":{"id":"2506.05057","kind":"arxiv","version":1}},"canonical_sha256":"efed63a409015c64a95aca78a239d25f1717520f6c79f45508b7723dcecaeb59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efed63a409015c64a95aca78a239d25f1717520f6c79f45508b7723dcecaeb59","first_computed_at":"2026-07-05T11:16:41.616599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:41.616599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fsR+Z9rbvXKsBdJVA/815LPDqIMXgpkzqUuUstgcLcPunBvPNKGHRNsBVPArii6A4hSyODr+Zk6TQ/1Sj/+TCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:41.617139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d45bddb9fb756209fa02cdacbe96307319d5222a5b378597b32a10d47d4ab1a","sha256:520b570096db7857588be08a851cdd5fe1db93dc15b284e23435894e38b12e51"],"state_sha256":"5df989b16c52bb951436f791769964049bd181886ab8f1f7870535a0fa5dd23a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNeZNlI3ip1n75i32XT0xiaTquYAzJRFo+XPuIwWejcVHnrd00l2EXyct2cjjMGy1JIL0aFNRi8oU3wmwHX/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:35:55.213788Z","bundle_sha256":"265d0025ddec1afe91a8b851eb0c47aa583a7c2e8c1b30f1c4c7b86e956837ea"}}