{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6CFTE7GHQBJWUBGEHVJWAHKGUH","short_pith_number":"pith:6CFTE7GH","canonical_record":{"source":{"id":"2407.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T13:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"ffd0d39a5eb32a1638347b3fec5bc11c43eba45aefb987e1cf892aa59c2ed6af","abstract_canon_sha256":"ee39d5e049d007f319f3f03e8f80f8b47d8907c8238a00fc00ab9a6be79cfad2"},"schema_version":"1.0"},"canonical_sha256":"f08b327cc780536a04c43d53601d46a1f5a2f7b4191f08207acb4067dec7f5a9","source":{"kind":"arxiv","id":"2407.00436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00436","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00436v2","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00436","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"6CFTE7GHQBJW","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"6CFTE7GHQBJWUBGE","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"6CFTE7GH","created_at":"2026-07-05T10:11:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6CFTE7GHQBJWUBGEHVJWAHKGUH","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T13:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"ffd0d39a5eb32a1638347b3fec5bc11c43eba45aefb987e1cf892aa59c2ed6af","abstract_canon_sha256":"ee39d5e049d007f319f3f03e8f80f8b47d8907c8238a00fc00ab9a6be79cfad2"},"schema_version":"1.0"},"canonical_sha256":"f08b327cc780536a04c43d53601d46a1f5a2f7b4191f08207acb4067dec7f5a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:21.370563Z","signature_b64":"g5NoC8SlZOZbzN5L51sSE/SKZ041hlwi5VoV76ccC10cCIUK8agUgGVHPUR+XVllYyOTWZEx+YLHRkDMJxHZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08b327cc780536a04c43d53601d46a1f5a2f7b4191f08207acb4067dec7f5a9","last_reissued_at":"2026-07-05T10:11:21.370058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:21.370058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2Lh+LpRhrd3MTOHK6Qrb7ospfMf53bj/+t2lZ6IC8XPyQjtZ+GHJn0fRw5xSWSTmz2soYovorP9wHD5jNI0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:50:27.622947Z"},"content_sha256":"e49ac3fcb19253246dd5e72d977131324069d790eb493250c5a26efecb11c35b","schema_version":"1.0","event_id":"sha256:e49ac3fcb19253246dd5e72d977131324069d790eb493250c5a26efecb11c35b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6CFTE7GHQBJWUBGEHVJWAHKGUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Hinrich Sch\\\"utze, Peiqin Lin","submitted_at":"2024-06-29T13:12:39Z","abstract_excerpt":"Recent studies have highlighted the potential of exploiting parallel corpora to enhance multilingual large language models, improving performance in both bilingual tasks, e.g., machine translation, and general-purpose tasks, e.g., text classification. Building upon these findings, our comprehensive study aims to identify the most effective strategies for leveraging parallel corpora. We investigate the impact of parallel corpora quality and quantity, training objectives, and model size on the performance of multilingual large language models enhanced with parallel corpora across diverse languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00436","kind":"arxiv","version":2},"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/2407.00436/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":"2026-07-05T10:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8ULeHYz70wZKafG1eZofwDu+81nsSNdwa8CaCWUOEsYVsjNh/em2Yo1nrYeIU/WJdWYymAnn4ybOpzJZcXnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:50:27.623492Z"},"content_sha256":"f8f4e5bb530db3dc6477cd22319e7c9475fda1e685950aa5efe5c007183f7dc6","schema_version":"1.0","event_id":"sha256:f8f4e5bb530db3dc6477cd22319e7c9475fda1e685950aa5efe5c007183f7dc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/bundle.json","state_url":"https://pith.science/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/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":"2026-08-08T08:50:27Z","links":{"resolver":"https://pith.science/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH","bundle":"https://pith.science/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/bundle.json","state":"https://pith.science/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CFTE7GHQBJWUBGEHVJWAHKGUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CFTE7GHQBJWUBGEHVJWAHKGUH","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":"ee39d5e049d007f319f3f03e8f80f8b47d8907c8238a00fc00ab9a6be79cfad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T13:12:39Z","title_canon_sha256":"ffd0d39a5eb32a1638347b3fec5bc11c43eba45aefb987e1cf892aa59c2ed6af"},"schema_version":"1.0","source":{"id":"2407.00436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00436","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00436v2","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00436","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"6CFTE7GHQBJW","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"6CFTE7GHQBJWUBGE","created_at":"2026-07-05T10:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"6CFTE7GH","created_at":"2026-07-05T10:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:f8f4e5bb530db3dc6477cd22319e7c9475fda1e685950aa5efe5c007183f7dc6","target":"graph","created_at":"2026-07-05T10:11:21Z","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/2407.00436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have highlighted the potential of exploiting parallel corpora to enhance multilingual large language models, improving performance in both bilingual tasks, e.g., machine translation, and general-purpose tasks, e.g., text classification. Building upon these findings, our comprehensive study aims to identify the most effective strategies for leveraging parallel corpora. We investigate the impact of parallel corpora quality and quantity, training objectives, and model size on the performance of multilingual large language models enhanced with parallel corpora across diverse languag","authors_text":"Andr\\'e F. T. Martins, Hinrich Sch\\\"utze, Peiqin Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T13:12:39Z","title":"A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00436","kind":"arxiv","version":2},"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:e49ac3fcb19253246dd5e72d977131324069d790eb493250c5a26efecb11c35b","target":"record","created_at":"2026-07-05T10:11:21Z","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":"ee39d5e049d007f319f3f03e8f80f8b47d8907c8238a00fc00ab9a6be79cfad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T13:12:39Z","title_canon_sha256":"ffd0d39a5eb32a1638347b3fec5bc11c43eba45aefb987e1cf892aa59c2ed6af"},"schema_version":"1.0","source":{"id":"2407.00436","kind":"arxiv","version":2}},"canonical_sha256":"f08b327cc780536a04c43d53601d46a1f5a2f7b4191f08207acb4067dec7f5a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f08b327cc780536a04c43d53601d46a1f5a2f7b4191f08207acb4067dec7f5a9","first_computed_at":"2026-07-05T10:11:21.370058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:21.370058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g5NoC8SlZOZbzN5L51sSE/SKZ041hlwi5VoV76ccC10cCIUK8agUgGVHPUR+XVllYyOTWZEx+YLHRkDMJxHZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:21.370563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e49ac3fcb19253246dd5e72d977131324069d790eb493250c5a26efecb11c35b","sha256:f8f4e5bb530db3dc6477cd22319e7c9475fda1e685950aa5efe5c007183f7dc6"],"state_sha256":"6e2ee5e835fdc91b20c4bf7836921ef924277e60c49ffc81a1457b010b4b2fbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nqZ8KGuU5dZ2F3WPXDjnsxIss44Zpsf5CcKDZ4p6wXgYgUHPXUTlNycLdabYuVLDuQ5iuPBCx2sGR52KxsuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:50:27.628615Z","bundle_sha256":"ead2664f224ab5e3134886383a5f9bb394be159a985e53d2c68bb4d12e747bbb"}}