{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5V4YVSBAAVP2HHWV47GCG5DFOQ","short_pith_number":"pith:5V4YVSBA","canonical_record":{"source":{"id":"2506.23340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T17:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"4a986f17e121117830c9bc1299ada82aa7d9522367f7251835383596150ee234","abstract_canon_sha256":"de644c674af61284414feb6152094a948824566d4f2e252afb3f98a1f163d0cb"},"schema_version":"1.0"},"canonical_sha256":"ed798ac820055fa39ed5e7cc23746574200094e5e3de79e78fbcaea2bb4dc1d4","source":{"kind":"arxiv","id":"2506.23340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23340","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23340v1","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23340","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"5V4YVSBAAVP2","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"5V4YVSBAAVP2HHWV","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"5V4YVSBA","created_at":"2026-07-05T11:29:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5V4YVSBAAVP2HHWV47GCG5DFOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T17:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"4a986f17e121117830c9bc1299ada82aa7d9522367f7251835383596150ee234","abstract_canon_sha256":"de644c674af61284414feb6152094a948824566d4f2e252afb3f98a1f163d0cb"},"schema_version":"1.0"},"canonical_sha256":"ed798ac820055fa39ed5e7cc23746574200094e5e3de79e78fbcaea2bb4dc1d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:20.054641Z","signature_b64":"C+FI9U5lMXP+cLE81dXfbroegz8e6baPDcoDwBvUXJT0t6ODKIGXx95dQxFkoS1WpVekFZbh1wCBUzTNTgrTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed798ac820055fa39ed5e7cc23746574200094e5e3de79e78fbcaea2bb4dc1d4","last_reissued_at":"2026-07-05T11:29:20.054137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:20.054137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23340","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":"2026-07-05T11:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddBMDbaFZ9YDZXCzht8dvH7uRDSPGTwJD+E1AfvBqbDUiMa6eCrc/3Q83NRWWYlr0wH84kY1MvzvtdwQX86bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:53:22.543312Z"},"content_sha256":"16ba39ded620f3fe8154cb441b68fea6a84381c45e5ecf06b577f537fca8a77a","schema_version":"1.0","event_id":"sha256:16ba39ded620f3fe8154cb441b68fea6a84381c45e5ecf06b577f537fca8a77a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5V4YVSBAAVP2HHWV47GCG5DFOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Haslett, Xufeng Duan, Yige Chen, Yumeng Lin, Zhenguang G. Cai","submitted_at":"2025-06-29T17:21:05Z","abstract_excerpt":"Large language models have achieved impressive progress in multilingual translation, yet they continue to face challenges with certain language pairs-particularly those with limited training data or significant linguistic divergence from English. This study systematically investigates how training data, language proximity, and language family affect information loss in multilingual translation. We evaluate two large language models, GPT-4 and Llama 2, by performing round-trip translations. Translation quality was assessed using BLEU scores and BERT similarity metrics. Our results reveal a robu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23340","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/2506.23340/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":"2026-07-05T11:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRIhaou4BVuOn1YzutKmxJMqHBwGY+mcGOfr2X9V/cYFPJ6VCIsa2ZAszfRfjVBLNxxCNoaqu9Y2zbRA2nIBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:53:22.543830Z"},"content_sha256":"38e632cc7513703386f8a2c60dbc5d28e000112fc167c7052c29afdf91a93a3f","schema_version":"1.0","event_id":"sha256:38e632cc7513703386f8a2c60dbc5d28e000112fc167c7052c29afdf91a93a3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/bundle.json","state_url":"https://pith.science/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/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":"2026-08-07T11:53:22Z","links":{"resolver":"https://pith.science/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ","bundle":"https://pith.science/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/bundle.json","state":"https://pith.science/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5V4YVSBAAVP2HHWV47GCG5DFOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5V4YVSBAAVP2HHWV47GCG5DFOQ","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":"de644c674af61284414feb6152094a948824566d4f2e252afb3f98a1f163d0cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T17:21:05Z","title_canon_sha256":"4a986f17e121117830c9bc1299ada82aa7d9522367f7251835383596150ee234"},"schema_version":"1.0","source":{"id":"2506.23340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23340","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23340v1","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23340","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"5V4YVSBAAVP2","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"5V4YVSBAAVP2HHWV","created_at":"2026-07-05T11:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"5V4YVSBA","created_at":"2026-07-05T11:29:20Z"}],"graph_snapshots":[{"event_id":"sha256:38e632cc7513703386f8a2c60dbc5d28e000112fc167c7052c29afdf91a93a3f","target":"graph","created_at":"2026-07-05T11:29:20Z","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/2506.23340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved impressive progress in multilingual translation, yet they continue to face challenges with certain language pairs-particularly those with limited training data or significant linguistic divergence from English. This study systematically investigates how training data, language proximity, and language family affect information loss in multilingual translation. We evaluate two large language models, GPT-4 and Llama 2, by performing round-trip translations. Translation quality was assessed using BLEU scores and BERT similarity metrics. Our results reveal a robu","authors_text":"David Haslett, Xufeng Duan, Yige Chen, Yumeng Lin, Zhenguang G. Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T17:21:05Z","title":"Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23340","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":"sha256:16ba39ded620f3fe8154cb441b68fea6a84381c45e5ecf06b577f537fca8a77a","target":"record","created_at":"2026-07-05T11:29:20Z","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":"de644c674af61284414feb6152094a948824566d4f2e252afb3f98a1f163d0cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T17:21:05Z","title_canon_sha256":"4a986f17e121117830c9bc1299ada82aa7d9522367f7251835383596150ee234"},"schema_version":"1.0","source":{"id":"2506.23340","kind":"arxiv","version":1}},"canonical_sha256":"ed798ac820055fa39ed5e7cc23746574200094e5e3de79e78fbcaea2bb4dc1d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed798ac820055fa39ed5e7cc23746574200094e5e3de79e78fbcaea2bb4dc1d4","first_computed_at":"2026-07-05T11:29:20.054137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:20.054137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+FI9U5lMXP+cLE81dXfbroegz8e6baPDcoDwBvUXJT0t6ODKIGXx95dQxFkoS1WpVekFZbh1wCBUzTNTgrTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:20.054641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16ba39ded620f3fe8154cb441b68fea6a84381c45e5ecf06b577f537fca8a77a","sha256:38e632cc7513703386f8a2c60dbc5d28e000112fc167c7052c29afdf91a93a3f"],"state_sha256":"7a9d410213804bf724286595e8e493c69fbee9f8b741a68f474c78ac94dced5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wz9v+yTj9AN+7I1eIewL2CZJknEMILZ/iUK46GWQBDopjNvd5uOJ5EJP0Ed+K46aTsr3LmAzs6dZzoUf7kTVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:53:22.547840Z","bundle_sha256":"0ca5f79c1ee2b253664d5d6e355432d0ea687ddef52d9f9b9ec711c6cc886544"}}