{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K2WVAVFYHETJRPFX2EZP5AZ6DQ","short_pith_number":"pith:K2WVAVFY","canonical_record":{"source":{"id":"2402.17733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"060fa128e18ac5f0436c69f6f36b942695c4ba0eba7f32f7e11ef8cc6602e644","abstract_canon_sha256":"41e2b25ccc8daa73a29f80c2f9a220bbf6353060ffc625b7095cc4413be5c693"},"schema_version":"1.0"},"canonical_sha256":"56ad5054b8392698bcb7d132fe833e1c38c0d42ee9ca3e0ef935792af4ac307c","source":{"kind":"arxiv","id":"2402.17733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17733","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17733v1","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17733","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"K2WVAVFYHETJ","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"K2WVAVFYHETJRPFX","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"K2WVAVFY","created_at":"2026-07-05T07:49:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K2WVAVFYHETJRPFX2EZP5AZ6DQ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"060fa128e18ac5f0436c69f6f36b942695c4ba0eba7f32f7e11ef8cc6602e644","abstract_canon_sha256":"41e2b25ccc8daa73a29f80c2f9a220bbf6353060ffc625b7095cc4413be5c693"},"schema_version":"1.0"},"canonical_sha256":"56ad5054b8392698bcb7d132fe833e1c38c0d42ee9ca3e0ef935792af4ac307c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:56.871191Z","signature_b64":"7Zp7/JYC/K80+P4ttBpqlrcBUUo8vEV8+VXbV5LYSaHaSMXLOc/3bivJLfEzvUKzKSn2JEtf1ebzv3MM8K+QDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ad5054b8392698bcb7d132fe833e1c38c0d42ee9ca3e0ef935792af4ac307c","last_reissued_at":"2026-07-05T07:49:56.870703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:56.870703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17733","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":"2026-07-05T07:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWsVX8XyX49fQWpGIfJciXsVk/hTvCApAhYmvGc4byC6h42PTfwTO75hZuV7eVt1a+psaA+5JPHFti2DjF+OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:06.460046Z"},"content_sha256":"162d2cef50635ebe9bffd1a14cdcdb681ce624aee346027005c0361d9a4604a1","schema_version":"1.0","event_id":"sha256:162d2cef50635ebe9bffd1a14cdcdb681ce624aee346027005c0361d9a4604a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K2WVAVFYHETJRPFX2EZP5AZ6DQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amin Farajian, Andr\\'e F.T. Martins, Ben Peters, Duarte M. Alves, Jo\\~ao Alves, Jos\\'e G.C. de Souza, Jos\\'e Pombal, Nuno M. Guerreiro, Patrick Fernandes, Pedro H. Martins, Pierre Colombo, Ricardo Rei, Sweta Agrawal","submitted_at":"2024-02-27T18:09:36Z","abstract_excerpt":"While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose a recipe for tailoring LLMs to multiple tasks present in translation workflows. We perform continued pretraining on a multilingual mixture of monolingual and parallel data, creating TowerBase, followed by finetuning on instructions relevant for translation processes, creating TowerInstruct. Our final model surpasses open alternatives on several tasks relevan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17733","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/2402.17733/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":"2026-07-05T07:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZmD2S4L7bwCBW59istsLVT4pWx94GpvN+f8VGCjsxYbKzir/P3M4KViUnSef4oGp4tBK+jnXyS1vVvvPf8pBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:06.460943Z"},"content_sha256":"dd2e7ce083dbe5f9762d13f97a38359200b62d8431917345bf5400522162dc83","schema_version":"1.0","event_id":"sha256:dd2e7ce083dbe5f9762d13f97a38359200b62d8431917345bf5400522162dc83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/bundle.json","state_url":"https://pith.science/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/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":"2026-08-08T13:15:06Z","links":{"resolver":"https://pith.science/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ","bundle":"https://pith.science/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/bundle.json","state":"https://pith.science/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2WVAVFYHETJRPFX2EZP5AZ6DQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K2WVAVFYHETJRPFX2EZP5AZ6DQ","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":"41e2b25ccc8daa73a29f80c2f9a220bbf6353060ffc625b7095cc4413be5c693","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:09:36Z","title_canon_sha256":"060fa128e18ac5f0436c69f6f36b942695c4ba0eba7f32f7e11ef8cc6602e644"},"schema_version":"1.0","source":{"id":"2402.17733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17733","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17733v1","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17733","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"K2WVAVFYHETJ","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"K2WVAVFYHETJRPFX","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"K2WVAVFY","created_at":"2026-07-05T07:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:dd2e7ce083dbe5f9762d13f97a38359200b62d8431917345bf5400522162dc83","target":"graph","created_at":"2026-07-05T07:49:56Z","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/2402.17733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose a recipe for tailoring LLMs to multiple tasks present in translation workflows. We perform continued pretraining on a multilingual mixture of monolingual and parallel data, creating TowerBase, followed by finetuning on instructions relevant for translation processes, creating TowerInstruct. Our final model surpasses open alternatives on several tasks relevan","authors_text":"Amin Farajian, Andr\\'e F.T. Martins, Ben Peters, Duarte M. Alves, Jo\\~ao Alves, Jos\\'e G.C. de Souza, Jos\\'e Pombal, Nuno M. Guerreiro, Patrick Fernandes, Pedro H. Martins, Pierre Colombo, Ricardo Rei, Sweta Agrawal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:09:36Z","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17733","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":"sha256:162d2cef50635ebe9bffd1a14cdcdb681ce624aee346027005c0361d9a4604a1","target":"record","created_at":"2026-07-05T07:49:56Z","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":"41e2b25ccc8daa73a29f80c2f9a220bbf6353060ffc625b7095cc4413be5c693","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:09:36Z","title_canon_sha256":"060fa128e18ac5f0436c69f6f36b942695c4ba0eba7f32f7e11ef8cc6602e644"},"schema_version":"1.0","source":{"id":"2402.17733","kind":"arxiv","version":1}},"canonical_sha256":"56ad5054b8392698bcb7d132fe833e1c38c0d42ee9ca3e0ef935792af4ac307c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56ad5054b8392698bcb7d132fe833e1c38c0d42ee9ca3e0ef935792af4ac307c","first_computed_at":"2026-07-05T07:49:56.870703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:56.870703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Zp7/JYC/K80+P4ttBpqlrcBUUo8vEV8+VXbV5LYSaHaSMXLOc/3bivJLfEzvUKzKSn2JEtf1ebzv3MM8K+QDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:56.871191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:162d2cef50635ebe9bffd1a14cdcdb681ce624aee346027005c0361d9a4604a1","sha256:dd2e7ce083dbe5f9762d13f97a38359200b62d8431917345bf5400522162dc83"],"state_sha256":"13e2016c79f3f60eeb0fb795d64981bb995a0f5d8ab4aa5a3305274b64aec988"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LNJw2JRdQD3HKsHXe8KxSMuLQwxppOqmcwWptAD8Pd3J+2BKg18HbjK4eSRVan4khRZvVplO0evRRgS9c6jBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:06.471207Z","bundle_sha256":"d680b0d25b953519b21f856b225c7b6b385e16daeaea1e728ae2e54835326b97"}}