{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF55JDRT6R6EMU7NQXH34656JS","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":"d8adaf38d73949b927a36c539c7b5e962cf320b6d9d387f413bbf6f7db31b6f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T14:28:25Z","title_canon_sha256":"5740df0d96ee9be6afadf30b03e5bdd3e32ed016a06c6cb057f79626161230e1"},"schema_version":"1.0","source":{"id":"2406.08255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08255","created_at":"2026-07-05T08:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08255v1","created_at":"2026-07-05T08:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08255","created_at":"2026-07-05T08:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"EF55JDRT6R6E","created_at":"2026-07-05T08:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"EF55JDRT6R6EMU7N","created_at":"2026-07-05T08:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"EF55JDRT","created_at":"2026-07-05T08:30:57Z"}],"graph_snapshots":[{"event_id":"sha256:bb1215730f77d7a3e71f8c3a7c0099822fbf972b3412ed9d076024189b02f775","target":"graph","created_at":"2026-07-05T08:30:57Z","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/2406.08255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with their precise reading order. These systems also tend to disregard additional visual cues such as the document layout, deeming it irrelevant. However, real-world documents often possess intricate text layouts that defy these assumptions. Extracting information from Optical Character Recognition (OCR) or heuristic rules can result in errors, and the layout (e.g","authors_text":"Benjamin Hsu, Huayang Li, Maria Nadejde, Raghavendra Pappagari, Ron Litman, Xiaoyu Liu, Xing Niu, Yair Kittenplon, Yoshinari Fujinuma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T14:28:25Z","title":"M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08255","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:da33e93b16dd5b01b5a6d07d187a9cb83b19512fb3ecdfb18b63d438d8e95967","target":"record","created_at":"2026-07-05T08:30:57Z","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":"d8adaf38d73949b927a36c539c7b5e962cf320b6d9d387f413bbf6f7db31b6f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T14:28:25Z","title_canon_sha256":"5740df0d96ee9be6afadf30b03e5bdd3e32ed016a06c6cb057f79626161230e1"},"schema_version":"1.0","source":{"id":"2406.08255","kind":"arxiv","version":1}},"canonical_sha256":"217bd48e33f47c4653ed85cfbe7bbe4ca896958db2d80f0a3fc0467d526dcf1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217bd48e33f47c4653ed85cfbe7bbe4ca896958db2d80f0a3fc0467d526dcf1c","first_computed_at":"2026-07-05T08:30:57.256814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:57.256814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qeVTgg8g3vbDso+n3lHftvOixo2+aHZomkp25hnwrLJ9dl1X9Kb/90rFvh1z3voqgAQ6UD4i8eRqPit6Iq/dDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:57.257353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da33e93b16dd5b01b5a6d07d187a9cb83b19512fb3ecdfb18b63d438d8e95967","sha256:bb1215730f77d7a3e71f8c3a7c0099822fbf972b3412ed9d076024189b02f775"],"state_sha256":"2bb937477cf896b8a377e0b4b1a76db85db7c37ec2eb91ebbd7cc711b52522e3"}