{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XY2WEDRFRGE24R6T5XAJGSGXYN","short_pith_number":"pith:XY2WEDRF","schema_version":"1.0","canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","source":{"kind":"arxiv","id":"2301.09685","version":2},"attestation_state":"computed","paper":{"title":"Noisy Parallel Data Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Ruoyu Xie","submitted_at":"2023-01-23T19:26:34Z","abstract_excerpt":"An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of resources required to train and evaluate models, most modern language technologies are either nonexistent or unreliable to process endangered, local, and non-standardized languages. Optical character recognition (OCR) is often used to convert endangered language documents into machine-readable data. However, such OCR output is typically noisy, and most word alignme"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.09685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T19:26:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2dca5c7b16e57467ce2298529d973c20a210ccf04cd20b4b793ce92c60fd1c0c","abstract_canon_sha256":"b5e708aff9acbc300688195f6f6bb7a365382969d63fde51291d59dd8093ef51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:33.980681Z","signature_b64":"f5ooeSTwMR7+URsDZ5lVlEw3qeBHHXK7hPQZRPAYfrd6Xw8wFdrKJOu8JN+NJKmMaAMLk5SDGHKi23JdEQRnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","last_reissued_at":"2026-07-05T05:40:33.980241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:33.980241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noisy Parallel Data Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Ruoyu Xie","submitted_at":"2023-01-23T19:26:34Z","abstract_excerpt":"An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of resources required to train and evaluate models, most modern language technologies are either nonexistent or unreliable to process endangered, local, and non-standardized languages. Optical character recognition (OCR) is often used to convert endangered language documents into machine-readable data. However, such OCR output is typically noisy, and most word alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09685","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/2301.09685/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.09685","created_at":"2026-07-05T05:40:33.980298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09685v2","created_at":"2026-07-05T05:40:33.980298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09685","created_at":"2026-07-05T05:40:33.980298+00:00"},{"alias_kind":"pith_short_12","alias_value":"XY2WEDRFRGE2","created_at":"2026-07-05T05:40:33.980298+00:00"},{"alias_kind":"pith_short_16","alias_value":"XY2WEDRFRGE24R6T","created_at":"2026-07-05T05:40:33.980298+00:00"},{"alias_kind":"pith_short_8","alias_value":"XY2WEDRF","created_at":"2026-07-05T05:40:33.980298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN","json":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN.json","graph_json":"https://pith.science/api/pith-number/XY2WEDRFRGE24R6T5XAJGSGXYN/graph.json","events_json":"https://pith.science/api/pith-number/XY2WEDRFRGE24R6T5XAJGSGXYN/events.json","paper":"https://pith.science/paper/XY2WEDRF"},"agent_actions":{"view_html":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN","download_json":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN.json","view_paper":"https://pith.science/paper/XY2WEDRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09685&json=true","fetch_graph":"https://pith.science/api/pith-number/XY2WEDRFRGE24R6T5XAJGSGXYN/graph.json","fetch_events":"https://pith.science/api/pith-number/XY2WEDRFRGE24R6T5XAJGSGXYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/action/storage_attestation","attest_author":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/action/author_attestation","sign_citation":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/action/citation_signature","submit_replication":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/action/replication_record"}},"created_at":"2026-07-05T05:40:33.980298+00:00","updated_at":"2026-07-05T05:40:33.980298+00:00"}