{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SYNB3AX5X4XFPDF62B5IEHJUDS","short_pith_number":"pith:SYNB3AX5","canonical_record":{"source":{"id":"2503.04369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"601f2d5cc5c61c657d44bb4ea51f935afdf13b1f2d51c983d5599ccaea4ebeab","abstract_canon_sha256":"c04371a2d0b9492bd7c333c1286aa7bc3eb58852519fd851a068a1fdd21626a9"},"schema_version":"1.0"},"canonical_sha256":"961a1d82fdbf2e578cbed07a821d341ca81d6302a7f1667ee5285e89ff57d5f6","source":{"kind":"arxiv","id":"2503.04369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04369","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04369v1","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04369","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"SYNB3AX5X4XF","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"SYNB3AX5X4XFPDF6","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"SYNB3AX5","created_at":"2026-07-05T10:25:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SYNB3AX5X4XFPDF62B5IEHJUDS","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"601f2d5cc5c61c657d44bb4ea51f935afdf13b1f2d51c983d5599ccaea4ebeab","abstract_canon_sha256":"c04371a2d0b9492bd7c333c1286aa7bc3eb58852519fd851a068a1fdd21626a9"},"schema_version":"1.0"},"canonical_sha256":"961a1d82fdbf2e578cbed07a821d341ca81d6302a7f1667ee5285e89ff57d5f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:37.297381Z","signature_b64":"JdoihUgRDOhDaKKupD+KGvX0+c0EXRpXCZz5gOAPxCezh3JvOVQ8UHNw/Y6rHCiHiWFI1qVBNlFEIvqMAaw9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961a1d82fdbf2e578cbed07a821d341ca81d6302a7f1667ee5285e89ff57d5f6","last_reissued_at":"2026-07-05T10:25:37.296700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:37.296700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04369","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":"2026-07-05T10:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLW7wI1y2RQoiraKaQ0wsEBclbmKBHfZ3Zdgb63Z1GaGASXaJO3bzDIVyYOMtxAmEY1OXQsq63DZ4FW2lSK0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:51:42.803374Z"},"content_sha256":"5bc2483467b23e01960cfa5abbbc5e9030d514d79ab8ccf94c92e7f939b3b5d1","schema_version":"1.0","event_id":"sha256:5bc2483467b23e01960cfa5abbbc5e9030d514d79ab8ccf94c92e7f939b3b5d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SYNB3AX5X4XFPDF62B5IEHJUDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lost in Literalism: How Supervised Training Shapes Translationese in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huajian Zhang, Leyang Cui, Ronghao Zhang, Tong Xiao, Yafu Li, Yongjing Yin, Yue Zhang, Zhilin Wang","submitted_at":"2025-03-06T12:14:45Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge in LLM-based translation systems. Despite their pre-training on vast corpora of natural utterances, LLMs exhibit translationese errors and generate unexpected unnatural translations, stemming from biases introduced during supervised fine-tuning (SFT). In this work, we systematically evaluate the prevalence of translationese in LLM-ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04369","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/2503.04369/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":"2026-07-05T10:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MkqBdlIQctB3CwnXBdB+IM9frJNIiaahWt7Y1ABcG/jLwArEVvCPCboJ1gYBCr5wPypC++RY5y+vB8kSgIUqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:51:42.804262Z"},"content_sha256":"69bf27fbae4fd052d9884996d62e23178abea75d9fad1dbd18865ac41f97e7be","schema_version":"1.0","event_id":"sha256:69bf27fbae4fd052d9884996d62e23178abea75d9fad1dbd18865ac41f97e7be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/bundle.json","state_url":"https://pith.science/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/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":"2026-08-12T06:51:42Z","links":{"resolver":"https://pith.science/pith/SYNB3AX5X4XFPDF62B5IEHJUDS","bundle":"https://pith.science/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/bundle.json","state":"https://pith.science/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYNB3AX5X4XFPDF62B5IEHJUDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SYNB3AX5X4XFPDF62B5IEHJUDS","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":"c04371a2d0b9492bd7c333c1286aa7bc3eb58852519fd851a068a1fdd21626a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:14:45Z","title_canon_sha256":"601f2d5cc5c61c657d44bb4ea51f935afdf13b1f2d51c983d5599ccaea4ebeab"},"schema_version":"1.0","source":{"id":"2503.04369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04369","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04369v1","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04369","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"SYNB3AX5X4XF","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"SYNB3AX5X4XFPDF6","created_at":"2026-07-05T10:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"SYNB3AX5","created_at":"2026-07-05T10:25:37Z"}],"graph_snapshots":[{"event_id":"sha256:69bf27fbae4fd052d9884996d62e23178abea75d9fad1dbd18865ac41f97e7be","target":"graph","created_at":"2026-07-05T10:25:37Z","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/2503.04369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge in LLM-based translation systems. Despite their pre-training on vast corpora of natural utterances, LLMs exhibit translationese errors and generate unexpected unnatural translations, stemming from biases introduced during supervised fine-tuning (SFT). In this work, we systematically evaluate the prevalence of translationese in LLM-ge","authors_text":"Huajian Zhang, Leyang Cui, Ronghao Zhang, Tong Xiao, Yafu Li, Yongjing Yin, Yue Zhang, Zhilin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:14:45Z","title":"Lost in Literalism: How Supervised Training Shapes Translationese in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04369","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":"sha256:5bc2483467b23e01960cfa5abbbc5e9030d514d79ab8ccf94c92e7f939b3b5d1","target":"record","created_at":"2026-07-05T10:25:37Z","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":"c04371a2d0b9492bd7c333c1286aa7bc3eb58852519fd851a068a1fdd21626a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:14:45Z","title_canon_sha256":"601f2d5cc5c61c657d44bb4ea51f935afdf13b1f2d51c983d5599ccaea4ebeab"},"schema_version":"1.0","source":{"id":"2503.04369","kind":"arxiv","version":1}},"canonical_sha256":"961a1d82fdbf2e578cbed07a821d341ca81d6302a7f1667ee5285e89ff57d5f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"961a1d82fdbf2e578cbed07a821d341ca81d6302a7f1667ee5285e89ff57d5f6","first_computed_at":"2026-07-05T10:25:37.296700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:37.296700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JdoihUgRDOhDaKKupD+KGvX0+c0EXRpXCZz5gOAPxCezh3JvOVQ8UHNw/Y6rHCiHiWFI1qVBNlFEIvqMAaw9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:37.297381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bc2483467b23e01960cfa5abbbc5e9030d514d79ab8ccf94c92e7f939b3b5d1","sha256:69bf27fbae4fd052d9884996d62e23178abea75d9fad1dbd18865ac41f97e7be"],"state_sha256":"f2ca7f126c3c3360e52d87976e1e8f3cbd9f59d6f81497890f91a6a39c048073"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+44bN77k+339OdBCVg9Z+Rs9EbNf6ZfFQL1iNU7EbytFFJQ+kKhHITssXgLZ0uFmTqS1QTkoHg7iFJiUzv6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:51:42.810713Z","bundle_sha256":"2a65a24359f017a11f5a022c5a653fa53803cebc7291fddebce133dd873331f8"}}