{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QW22EOIHOL4DV2ILK2ABQDT7KX","short_pith_number":"pith:QW22EOIH","canonical_record":{"source":{"id":"2412.17592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T14:08:45Z","cross_cats_sorted":[],"title_canon_sha256":"2d853709f196c753d5c02f86d0f2b69552330297e8a84723d8ff75db7c608149","abstract_canon_sha256":"0dce9634a6eed97b6f15b79ca2fc0a8462b508db4592166242838786bb3b0171"},"schema_version":"1.0"},"canonical_sha256":"85b5a2390772f83ae90b5680180e7f55f8b2c239e8a6eb43a18e772187991485","source":{"kind":"arxiv","id":"2412.17592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17592","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17592v2","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17592","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_12","alias_value":"QW22EOIHOL4D","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_16","alias_value":"QW22EOIHOL4DV2IL","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_8","alias_value":"QW22EOIH","created_at":"2026-07-05T10:54:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QW22EOIHOL4DV2ILK2ABQDT7KX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.17592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T14:08:45Z","cross_cats_sorted":[],"title_canon_sha256":"2d853709f196c753d5c02f86d0f2b69552330297e8a84723d8ff75db7c608149","abstract_canon_sha256":"0dce9634a6eed97b6f15b79ca2fc0a8462b508db4592166242838786bb3b0171"},"schema_version":"1.0"},"canonical_sha256":"85b5a2390772f83ae90b5680180e7f55f8b2c239e8a6eb43a18e772187991485","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:40.857420Z","signature_b64":"6ruh44J5oq09R8ijEqnZv/EeiLVpOPj11lLminr3PXPX9ojEqnYTVnPKp1moIPNN3qTpvb4PsZwyhw9hWG9XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85b5a2390772f83ae90b5680180e7f55f8b2c239e8a6eb43a18e772187991485","last_reissued_at":"2026-07-05T10:54:40.856944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:40.856944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.17592","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":"2026-07-05T10:54:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWhqZ6MEAGgl0kONgxSEKUpkEukoFfziNWIHWi96qkRkGfpcK9GRbBM54L+/1aLv69YeYnEwLPVqvj6rQyRiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:58:50.220120Z"},"content_sha256":"dda33a6651f851ed57159606da24268f698f5a9b9569940ad0b615f9d6ea2394","schema_version":"1.0","event_id":"sha256:dda33a6651f851ed57159606da24268f698f5a9b9569940ad0b615f9d6ea2394"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QW22EOIHOL4DV2ILK2ABQDT7KX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Length Issues in Document-level Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fran\\c{c}ois Yvon, Rachel Bawden, Ziqian Peng","submitted_at":"2024-12-23T14:08:45Z","abstract_excerpt":"Transformer architectures are increasingly effective at processing and generating very long chunks of texts, opening new perspectives for document-level machine translation (MT). In this work, we challenge the ability of MT systems to handle texts comprising up to several thousands of tokens. We design and implement a new approach designed to precisely measure the effect of length increments on MT outputs. Our experiments with two representative architectures unambiguously show that (a)~translation performance decreases with the length of the input text; (b)~the position of sentences within th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17592","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/2412.17592/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":"2026-07-05T10:54:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwwoTC4QWTr9tLlO6RQwI8QdOcGMUk5dH3JzRkil/kcJq7xuMchfLDHWRSpvE6I7UK75yGE6eCwk/BBfUHIhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:58:50.220706Z"},"content_sha256":"50cc86a08cc90c33554a36f559107ec9f63f5972402a92546e1664435b0df94d","schema_version":"1.0","event_id":"sha256:50cc86a08cc90c33554a36f559107ec9f63f5972402a92546e1664435b0df94d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/bundle.json","state_url":"https://pith.science/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/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":"2026-08-17T21:58:50Z","links":{"resolver":"https://pith.science/pith/QW22EOIHOL4DV2ILK2ABQDT7KX","bundle":"https://pith.science/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/bundle.json","state":"https://pith.science/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QW22EOIHOL4DV2ILK2ABQDT7KX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QW22EOIHOL4DV2ILK2ABQDT7KX","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":"0dce9634a6eed97b6f15b79ca2fc0a8462b508db4592166242838786bb3b0171","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T14:08:45Z","title_canon_sha256":"2d853709f196c753d5c02f86d0f2b69552330297e8a84723d8ff75db7c608149"},"schema_version":"1.0","source":{"id":"2412.17592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17592","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17592v2","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17592","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_12","alias_value":"QW22EOIHOL4D","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_16","alias_value":"QW22EOIHOL4DV2IL","created_at":"2026-07-05T10:54:40Z"},{"alias_kind":"pith_short_8","alias_value":"QW22EOIH","created_at":"2026-07-05T10:54:40Z"}],"graph_snapshots":[{"event_id":"sha256:50cc86a08cc90c33554a36f559107ec9f63f5972402a92546e1664435b0df94d","target":"graph","created_at":"2026-07-05T10:54:40Z","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/2412.17592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer architectures are increasingly effective at processing and generating very long chunks of texts, opening new perspectives for document-level machine translation (MT). In this work, we challenge the ability of MT systems to handle texts comprising up to several thousands of tokens. We design and implement a new approach designed to precisely measure the effect of length increments on MT outputs. Our experiments with two representative architectures unambiguously show that (a)~translation performance decreases with the length of the input text; (b)~the position of sentences within th","authors_text":"Fran\\c{c}ois Yvon, Rachel Bawden, Ziqian Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T14:08:45Z","title":"Investigating Length Issues in Document-level Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17592","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:dda33a6651f851ed57159606da24268f698f5a9b9569940ad0b615f9d6ea2394","target":"record","created_at":"2026-07-05T10:54:40Z","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":"0dce9634a6eed97b6f15b79ca2fc0a8462b508db4592166242838786bb3b0171","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T14:08:45Z","title_canon_sha256":"2d853709f196c753d5c02f86d0f2b69552330297e8a84723d8ff75db7c608149"},"schema_version":"1.0","source":{"id":"2412.17592","kind":"arxiv","version":2}},"canonical_sha256":"85b5a2390772f83ae90b5680180e7f55f8b2c239e8a6eb43a18e772187991485","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85b5a2390772f83ae90b5680180e7f55f8b2c239e8a6eb43a18e772187991485","first_computed_at":"2026-07-05T10:54:40.856944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:40.856944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ruh44J5oq09R8ijEqnZv/EeiLVpOPj11lLminr3PXPX9ojEqnYTVnPKp1moIPNN3qTpvb4PsZwyhw9hWG9XBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:40.857420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dda33a6651f851ed57159606da24268f698f5a9b9569940ad0b615f9d6ea2394","sha256:50cc86a08cc90c33554a36f559107ec9f63f5972402a92546e1664435b0df94d"],"state_sha256":"acd5adf167db635cd8fe1cd10d6985eb3dd1be25c15c2027e2c0edfca11886fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vn9o7R+keZbN1YxAS1wLedNoEMVt4Suzu/ASK99kL/eKp2Zlt5atwwlKbRvCaeedRT0aeG7rkmpmvwAfe01TDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:58:50.225912Z","bundle_sha256":"adb2e277cf8ec187cfd62d20d48180b304e1f97930fbcd560daa1720ce37b6ba"}}