{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YAOEUSJJSM6SXJ4OWN3HRWEQ24","short_pith_number":"pith:YAOEUSJJ","canonical_record":{"source":{"id":"2507.03580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T13:49:14Z","cross_cats_sorted":[],"title_canon_sha256":"4c81141aab98a1bee25edaebbbe41e9a5f9099c161c00fc94879418783cce7e4","abstract_canon_sha256":"e520a730deba7e424d2eeb345a1648e8ad403d35a91db139d3d4ab5d22d6eb18"},"schema_version":"1.0"},"canonical_sha256":"c01c4a4929933d2ba78eb37678d890d72cee2fd5b951e55b50a7a0bc56a71630","source":{"kind":"arxiv","id":"2507.03580","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03580","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03580v2","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03580","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"YAOEUSJJSM6S","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"YAOEUSJJSM6SXJ4O","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"YAOEUSJJ","created_at":"2026-07-05T11:38:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YAOEUSJJSM6SXJ4OWN3HRWEQ24","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T13:49:14Z","cross_cats_sorted":[],"title_canon_sha256":"4c81141aab98a1bee25edaebbbe41e9a5f9099c161c00fc94879418783cce7e4","abstract_canon_sha256":"e520a730deba7e424d2eeb345a1648e8ad403d35a91db139d3d4ab5d22d6eb18"},"schema_version":"1.0"},"canonical_sha256":"c01c4a4929933d2ba78eb37678d890d72cee2fd5b951e55b50a7a0bc56a71630","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:31.054490Z","signature_b64":"4CrknPoHo5eyUpYtfMqARvYQYgX/boLtkNHOz+n2jJyvWadBahDHKNqkmfcVg24OzzfdVeGRbJPz8RuxsXvWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01c4a4929933d2ba78eb37678d890d72cee2fd5b951e55b50a7a0bc56a71630","last_reissued_at":"2026-07-05T11:38:31.054014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:31.054014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03580","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":"2026-07-05T11:38:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FrsVZA1GBRPooqX1MGofNaXuVZWgdqXJhiQeB6X6sGzM+NL3P9tcE31jeW+Ek78yUBAWW1Inkfgc4W4HuTgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:29:15.836099Z"},"content_sha256":"3d674515e3832caba39cd69e5ee05c1b8ebb89478537cce121a60132595aa760","schema_version":"1.0","event_id":"sha256:3d674515e3832caba39cd69e5ee05c1b8ebb89478537cce121a60132595aa760"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YAOEUSJJSM6SXJ4OWN3HRWEQ24","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Johannes Eschbach-Dymanus, Matthias Huck, Miriam Exel, Nathaniel Berger, Stefan Riezler","submitted_at":"2025-07-04T13:49:14Z","abstract_excerpt":"In real world translation scenarios, terminology is rarely one-to-one. Instead, multiple valid translations may appear in a terminology dictionary, but correctness of a translation depends on corporate style guides and context. This can be challenging for neural machine translation (NMT) systems. Luckily, in a corporate context, many examples of human post-edits of valid but incorrect terminology exist. The goal of this work is to learn how to disambiguate our terminology based on these corrections. Our approach is based on preference optimization, using the term post-edit as the knowledge to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03580","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/2507.03580/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":"2026-07-05T11:38:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EwfSDUoa8aqAx4b61MSDzl3Qvg8kHrc7PMA8paWr9fW2EX2o2qmiTse5SzxhZzIN2EgDCHWo9TSjCPTjqbD7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:29:15.836674Z"},"content_sha256":"ab05bef3fabbc8b7642fa76c8cf64bdce498267f29d9a336d53e7c353afaaeba","schema_version":"1.0","event_id":"sha256:ab05bef3fabbc8b7642fa76c8cf64bdce498267f29d9a336d53e7c353afaaeba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/bundle.json","state_url":"https://pith.science/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/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":"2026-08-18T09:29:15Z","links":{"resolver":"https://pith.science/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24","bundle":"https://pith.science/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/bundle.json","state":"https://pith.science/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAOEUSJJSM6SXJ4OWN3HRWEQ24/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YAOEUSJJSM6SXJ4OWN3HRWEQ24","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":"e520a730deba7e424d2eeb345a1648e8ad403d35a91db139d3d4ab5d22d6eb18","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T13:49:14Z","title_canon_sha256":"4c81141aab98a1bee25edaebbbe41e9a5f9099c161c00fc94879418783cce7e4"},"schema_version":"1.0","source":{"id":"2507.03580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03580","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03580v2","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03580","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"YAOEUSJJSM6S","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"YAOEUSJJSM6SXJ4O","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"YAOEUSJJ","created_at":"2026-07-05T11:38:31Z"}],"graph_snapshots":[{"event_id":"sha256:ab05bef3fabbc8b7642fa76c8cf64bdce498267f29d9a336d53e7c353afaaeba","target":"graph","created_at":"2026-07-05T11:38:31Z","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/2507.03580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real world translation scenarios, terminology is rarely one-to-one. Instead, multiple valid translations may appear in a terminology dictionary, but correctness of a translation depends on corporate style guides and context. This can be challenging for neural machine translation (NMT) systems. Luckily, in a corporate context, many examples of human post-edits of valid but incorrect terminology exist. The goal of this work is to learn how to disambiguate our terminology based on these corrections. Our approach is based on preference optimization, using the term post-edit as the knowledge to ","authors_text":"Johannes Eschbach-Dymanus, Matthias Huck, Miriam Exel, Nathaniel Berger, Stefan Riezler","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T13:49:14Z","title":"Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03580","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":"sha256:3d674515e3832caba39cd69e5ee05c1b8ebb89478537cce121a60132595aa760","target":"record","created_at":"2026-07-05T11:38:31Z","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":"e520a730deba7e424d2eeb345a1648e8ad403d35a91db139d3d4ab5d22d6eb18","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T13:49:14Z","title_canon_sha256":"4c81141aab98a1bee25edaebbbe41e9a5f9099c161c00fc94879418783cce7e4"},"schema_version":"1.0","source":{"id":"2507.03580","kind":"arxiv","version":2}},"canonical_sha256":"c01c4a4929933d2ba78eb37678d890d72cee2fd5b951e55b50a7a0bc56a71630","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c01c4a4929933d2ba78eb37678d890d72cee2fd5b951e55b50a7a0bc56a71630","first_computed_at":"2026-07-05T11:38:31.054014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:31.054014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4CrknPoHo5eyUpYtfMqARvYQYgX/boLtkNHOz+n2jJyvWadBahDHKNqkmfcVg24OzzfdVeGRbJPz8RuxsXvWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:31.054490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d674515e3832caba39cd69e5ee05c1b8ebb89478537cce121a60132595aa760","sha256:ab05bef3fabbc8b7642fa76c8cf64bdce498267f29d9a336d53e7c353afaaeba"],"state_sha256":"f2d5822095181aa9b888a161c1b75200a264e23274ac022a1d122a90475e83e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMDcn14tyS0FgSwNHnjWBu3kj3d7J9tWmpN/3Xe7/wMgTlPzU12jINUCCyhUzEJWhJpCkJLK4zRb399PQfBDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:29:15.843185Z","bundle_sha256":"1f4ac1005116f41ecf9900532f3d8c389e4803f935f0b169b53462943d3dfacf"}}