{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XY2WEDRFRGE24R6T5XAJGSGXYN","short_pith_number":"pith:XY2WEDRF","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"},"canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","source":{"kind":"arxiv","id":"2301.09685","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09685","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09685v2","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09685","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"XY2WEDRFRGE2","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"XY2WEDRFRGE24R6T","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"XY2WEDRF","created_at":"2026-07-05T05:40:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XY2WEDRFRGE24R6T5XAJGSGXYN","target":"record","payload":{"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"},"canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","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"},"source_kind":"arxiv","source_id":"2301.09685","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":"2026-07-05T05:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qQXzRHp/fJPmRMTB3MWxRDryfSxvKcpDtyrRk/nBeDyY6m0CYhuBr/PIuf1Znup3IWsfPcQMXN0uSYrbHKYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:22:47.605652Z"},"content_sha256":"68390d5ff0502fb2426bf8c1181b3ced2b688f42dadcf11a81d03c47a1afcd17","schema_version":"1.0","event_id":"sha256:68390d5ff0502fb2426bf8c1181b3ced2b688f42dadcf11a81d03c47a1afcd17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XY2WEDRFRGE24R6T5XAJGSGXYN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mp2FVBWCEqTTxlbxOkOyn5lvTwuTKonOhdUH1H3kjs4HxoOR0kxPv73VpNaHF5fw/guw8wyUbEx98GAl6ylPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:22:47.606016Z"},"content_sha256":"8a232eb3deed4736a200491d9f0b8dfc141bfbbea31dc9f8ca4bbacf721006ab","schema_version":"1.0","event_id":"sha256:8a232eb3deed4736a200491d9f0b8dfc141bfbbea31dc9f8ca4bbacf721006ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/bundle.json","state_url":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/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":"2026-08-22T12:22:47Z","links":{"resolver":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN","bundle":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/bundle.json","state":"https://pith.science/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XY2WEDRFRGE24R6T5XAJGSGXYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XY2WEDRFRGE24R6T5XAJGSGXYN","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":"b5e708aff9acbc300688195f6f6bb7a365382969d63fde51291d59dd8093ef51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T19:26:34Z","title_canon_sha256":"2dca5c7b16e57467ce2298529d973c20a210ccf04cd20b4b793ce92c60fd1c0c"},"schema_version":"1.0","source":{"id":"2301.09685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09685","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09685v2","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09685","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"XY2WEDRFRGE2","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"XY2WEDRFRGE24R6T","created_at":"2026-07-05T05:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"XY2WEDRF","created_at":"2026-07-05T05:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:8a232eb3deed4736a200491d9f0b8dfc141bfbbea31dc9f8ca4bbacf721006ab","target":"graph","created_at":"2026-07-05T05:40:33Z","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/2301.09685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antonios Anastasopoulos, Ruoyu Xie","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T19:26:34Z","title":"Noisy Parallel Data Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09685","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":"sha256:68390d5ff0502fb2426bf8c1181b3ced2b688f42dadcf11a81d03c47a1afcd17","target":"record","created_at":"2026-07-05T05:40:33Z","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":"b5e708aff9acbc300688195f6f6bb7a365382969d63fde51291d59dd8093ef51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T19:26:34Z","title_canon_sha256":"2dca5c7b16e57467ce2298529d973c20a210ccf04cd20b4b793ce92c60fd1c0c"},"schema_version":"1.0","source":{"id":"2301.09685","kind":"arxiv","version":2}},"canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be35620e258989ae47d3edc09348d7c375dc77eacbd1162de3af4f28f5c55c43","first_computed_at":"2026-07-05T05:40:33.980241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:33.980241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f5ooeSTwMR7+URsDZ5lVlEw3qeBHHXK7hPQZRPAYfrd6Xw8wFdrKJOu8JN+NJKmMaAMLk5SDGHKi23JdEQRnDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:33.980681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68390d5ff0502fb2426bf8c1181b3ced2b688f42dadcf11a81d03c47a1afcd17","sha256:8a232eb3deed4736a200491d9f0b8dfc141bfbbea31dc9f8ca4bbacf721006ab"],"state_sha256":"22b93e581257a383834977b57cc93381ca76e0b3fe948b39ab909e87d3c44631"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63A6bFheDn6luqjhjBbfSWXMCjFCMZaexQoZrfIOk2ZiU/zii3JU6ZflDExMfrUhjzUJ/gNLEtPL93K4r1M2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:22:47.609728Z","bundle_sha256":"535cfe1295b14dcef981a6871175c882fe693d52486c6cbdaf4e93b20e924fdc"}}