{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JJSERAWMBZ4L46XOQ5LPDGMFMP","short_pith_number":"pith:JJSERAWM","canonical_record":{"source":{"id":"2205.12514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"97e57416ffc01088ff65a2c88518a0d06dc7e3e712699aca650a3a225295b039","abstract_canon_sha256":"950137b0843f42f5c906b1832a3d1ed36f5eb4df73ff443b9a2958a9d9dcab4f"},"schema_version":"1.0"},"canonical_sha256":"4a644882cc0e78be7aee8756f1998563c131887a6c7ed61315d7b27a0aedd111","source":{"kind":"arxiv","id":"2205.12514","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12514","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12514v2","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12514","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_12","alias_value":"JJSERAWMBZ4L","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_16","alias_value":"JJSERAWMBZ4L46XO","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_8","alias_value":"JJSERAWM","created_at":"2026-07-05T05:14:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JJSERAWMBZ4L46XOQ5LPDGMFMP","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"97e57416ffc01088ff65a2c88518a0d06dc7e3e712699aca650a3a225295b039","abstract_canon_sha256":"950137b0843f42f5c906b1832a3d1ed36f5eb4df73ff443b9a2958a9d9dcab4f"},"schema_version":"1.0"},"canonical_sha256":"4a644882cc0e78be7aee8756f1998563c131887a6c7ed61315d7b27a0aedd111","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:46.376976Z","signature_b64":"6RrCa6SUXfKj+cBWRk/59rMMPXKGXiwu8PisYfIZ1f9jvAlHmqvvfkIdUjvZ0bHDyVPX8kYu6rZLT4nnB0MNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a644882cc0e78be7aee8756f1998563c131887a6c7ed61315d7b27a0aedd111","last_reissued_at":"2026-07-05T05:14:46.376572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:46.376572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12514","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":"2026-07-05T05:14:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X7b4RH4wYF4EYaxBo4WRs1pLRjxlV8Ge/soU0kZQWDjQlLlZNnRqUkETuDQRsfKnVW44byZyDDfGgjgqe4/9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:03:37.501021Z"},"content_sha256":"0e0f34c732d1c46a1f0317d8c5615597bd04c8a4707612adc25435daadfdd348","schema_version":"1.0","event_id":"sha256:0e0f34c732d1c46a1f0317d8c5615597bd04c8a4707612adc25435daadfdd348"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JJSERAWMBZ4L46XOQ5LPDGMFMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine Translation Robustness to Natural Asemantic Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Bremerman, Jonathan May, Xiang Ren","submitted_at":"2022-05-25T06:06:06Z","abstract_excerpt":"Current Machine Translation (MT) models still struggle with more challenging input, such as noisy data and tail-end words and phrases. Several works have addressed this robustness issue by identifying specific categories of noise and variation then tuning models to perform better on them. An important yet under-studied category involves minor variations in nuance (non-typos) that preserve meaning w.r.t. the target language. We introduce and formalize this category as Natural Asemantic Variation (NAV) and investigate it in the context of MT robustness. We find that existing MT models fail when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12514","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/2205.12514/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":"2026-07-05T05:14:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypfxHvWgyC6FagBJeLnOQaBBs3QyCaq171QQB8dWu643vbelHSMeM64F3YOvZcOLm7JrNRDSP9+ueTCSZd2/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:03:37.501572Z"},"content_sha256":"dc9a155d8ec2c8cf8f7fbc8fec549120451ea8342d2540f3726e507d55dd10e4","schema_version":"1.0","event_id":"sha256:dc9a155d8ec2c8cf8f7fbc8fec549120451ea8342d2540f3726e507d55dd10e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/bundle.json","state_url":"https://pith.science/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/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":"2026-08-05T12:03:37Z","links":{"resolver":"https://pith.science/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP","bundle":"https://pith.science/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/bundle.json","state":"https://pith.science/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJSERAWMBZ4L46XOQ5LPDGMFMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JJSERAWMBZ4L46XOQ5LPDGMFMP","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":"950137b0843f42f5c906b1832a3d1ed36f5eb4df73ff443b9a2958a9d9dcab4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:06:06Z","title_canon_sha256":"97e57416ffc01088ff65a2c88518a0d06dc7e3e712699aca650a3a225295b039"},"schema_version":"1.0","source":{"id":"2205.12514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12514","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12514v2","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12514","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_12","alias_value":"JJSERAWMBZ4L","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_16","alias_value":"JJSERAWMBZ4L46XO","created_at":"2026-07-05T05:14:46Z"},{"alias_kind":"pith_short_8","alias_value":"JJSERAWM","created_at":"2026-07-05T05:14:46Z"}],"graph_snapshots":[{"event_id":"sha256:dc9a155d8ec2c8cf8f7fbc8fec549120451ea8342d2540f3726e507d55dd10e4","target":"graph","created_at":"2026-07-05T05:14:46Z","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/2205.12514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Machine Translation (MT) models still struggle with more challenging input, such as noisy data and tail-end words and phrases. Several works have addressed this robustness issue by identifying specific categories of noise and variation then tuning models to perform better on them. An important yet under-studied category involves minor variations in nuance (non-typos) that preserve meaning w.r.t. the target language. We introduce and formalize this category as Natural Asemantic Variation (NAV) and investigate it in the context of MT robustness. We find that existing MT models fail when ","authors_text":"Jacob Bremerman, Jonathan May, Xiang Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:06:06Z","title":"Machine Translation Robustness to Natural Asemantic Variation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12514","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":"sha256:0e0f34c732d1c46a1f0317d8c5615597bd04c8a4707612adc25435daadfdd348","target":"record","created_at":"2026-07-05T05:14:46Z","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":"950137b0843f42f5c906b1832a3d1ed36f5eb4df73ff443b9a2958a9d9dcab4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:06:06Z","title_canon_sha256":"97e57416ffc01088ff65a2c88518a0d06dc7e3e712699aca650a3a225295b039"},"schema_version":"1.0","source":{"id":"2205.12514","kind":"arxiv","version":2}},"canonical_sha256":"4a644882cc0e78be7aee8756f1998563c131887a6c7ed61315d7b27a0aedd111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a644882cc0e78be7aee8756f1998563c131887a6c7ed61315d7b27a0aedd111","first_computed_at":"2026-07-05T05:14:46.376572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:46.376572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RrCa6SUXfKj+cBWRk/59rMMPXKGXiwu8PisYfIZ1f9jvAlHmqvvfkIdUjvZ0bHDyVPX8kYu6rZLT4nnB0MNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:46.376976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e0f34c732d1c46a1f0317d8c5615597bd04c8a4707612adc25435daadfdd348","sha256:dc9a155d8ec2c8cf8f7fbc8fec549120451ea8342d2540f3726e507d55dd10e4"],"state_sha256":"453433ec9223fb56e78548f8a26603cca4603a0ce73cecce462c09a2720baf06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxEmi/gnNv1hPLIILXe1Eq33vShEvFnQ1+KBPWcz1RzrCM7/fetcjA2Mx1LYXPcC2zan0bXmCuiVuNn0IYRZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:03:37.505524Z","bundle_sha256":"d90815b9a35a5f1ad1f026752c002b69dfbc92688c1ac2d9899d3dab5c01ce2a"}}