{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y2ADU5HSHIJGBPXW7LUC3UBKNC","short_pith_number":"pith:Y2ADU5HS","canonical_record":{"source":{"id":"2311.12179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T20:48:25Z","cross_cats_sorted":[],"title_canon_sha256":"63c6570538af44eeaba518fcde0ecbafe4a27dfdca91f0efe68b9859c611bf7b","abstract_canon_sha256":"d31434b34781ddc8798a2867ec55243227af88d4d53bca7098f6c124d418273f"},"schema_version":"1.0"},"canonical_sha256":"c6803a74f23a1260bef6fae82dd02a68aecf17d5fd93b3696de6501c8615b7b2","source":{"kind":"arxiv","id":"2311.12179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12179","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12179v1","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12179","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y2ADU5HSHIJG","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y2ADU5HSHIJGBPXW","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y2ADU5HS","created_at":"2026-07-05T07:15:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y2ADU5HSHIJGBPXW7LUC3UBKNC","target":"record","payload":{"canonical_record":{"source":{"id":"2311.12179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T20:48:25Z","cross_cats_sorted":[],"title_canon_sha256":"63c6570538af44eeaba518fcde0ecbafe4a27dfdca91f0efe68b9859c611bf7b","abstract_canon_sha256":"d31434b34781ddc8798a2867ec55243227af88d4d53bca7098f6c124d418273f"},"schema_version":"1.0"},"canonical_sha256":"c6803a74f23a1260bef6fae82dd02a68aecf17d5fd93b3696de6501c8615b7b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:01.736624Z","signature_b64":"PseZAYyijV1Ylu0CBGFq1yMqt79yj3tX3/JbnQrO33IV851516JZsZI+LFQjJjD/cBhwe7CQuwEuhwkHYn5iBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6803a74f23a1260bef6fae82dd02a68aecf17d5fd93b3696de6501c8615b7b2","last_reissued_at":"2026-07-05T07:15:01.736215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:01.736215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.12179","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SxK1JllHH3DLDwLvkXEAtDesH3KKdXbj8t1hUUQlkwlKxXgzHJjc6ipSjvRzTQ2nLRyxI5TEPC4OL5mv+4KCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:11:05.937006Z"},"content_sha256":"4079da1678ab1a567e5994f16cb68d264700b4d28ff5a04083f8d6d676b55427","schema_version":"1.0","event_id":"sha256:4079da1678ab1a567e5994f16cb68d264700b4d28ff5a04083f8d6d676b55427"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y2ADU5HSHIJGBPXW7LUC3UBKNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Auwal Abubakar Khalid, Babangida Sani, Bala Mairiga Abduljalil, Ibrahim Said Ahmad, Idris Abdulmumin, Lukman Jibril Aliyu, Sani Ahmad Hassan, Shamsuddeen Hassan Muhammad","submitted_at":"2023-11-20T20:48:25Z","abstract_excerpt":"The importance of qualitative parallel data in machine translation has long been determined but it has always been very difficult to obtain such in sufficient quantity for the majority of world languages, mainly because of the associated cost and also the lack of accessibility to these languages. Despite the potential for obtaining parallel datasets from online articles using automatic approaches, forensic investigations have found a lot of quality-related issues such as misalignment, and wrong language codes. In this work, we present a simple but qualitative parallel sentence aligner that car"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12179","kind":"arxiv","version":1},"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/2311.12179/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":"2026-07-05T07:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJmLoFrKsINgAIHJ/9SUR547kIsxZRzmqPqNNtg+fOu0cXbFEbEjqp7hATLHsbM7lAIeEVBASaSIdy9gWFg1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:11:05.937848Z"},"content_sha256":"455314cabcca2b0f403a26f31ea5b5debf4048da184c16514929e4bed2b06973","schema_version":"1.0","event_id":"sha256:455314cabcca2b0f403a26f31ea5b5debf4048da184c16514929e4bed2b06973"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/bundle.json","state_url":"https://pith.science/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/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":"2026-08-10T08:11:05Z","links":{"resolver":"https://pith.science/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC","bundle":"https://pith.science/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/bundle.json","state":"https://pith.science/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2ADU5HSHIJGBPXW7LUC3UBKNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y2ADU5HSHIJGBPXW7LUC3UBKNC","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":"d31434b34781ddc8798a2867ec55243227af88d4d53bca7098f6c124d418273f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T20:48:25Z","title_canon_sha256":"63c6570538af44eeaba518fcde0ecbafe4a27dfdca91f0efe68b9859c611bf7b"},"schema_version":"1.0","source":{"id":"2311.12179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12179","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12179v1","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12179","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y2ADU5HSHIJG","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y2ADU5HSHIJGBPXW","created_at":"2026-07-05T07:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y2ADU5HS","created_at":"2026-07-05T07:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:455314cabcca2b0f403a26f31ea5b5debf4048da184c16514929e4bed2b06973","target":"graph","created_at":"2026-07-05T07:15:01Z","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/2311.12179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The importance of qualitative parallel data in machine translation has long been determined but it has always been very difficult to obtain such in sufficient quantity for the majority of world languages, mainly because of the associated cost and also the lack of accessibility to these languages. Despite the potential for obtaining parallel datasets from online articles using automatic approaches, forensic investigations have found a lot of quality-related issues such as misalignment, and wrong language codes. In this work, we present a simple but qualitative parallel sentence aligner that car","authors_text":"Auwal Abubakar Khalid, Babangida Sani, Bala Mairiga Abduljalil, Ibrahim Said Ahmad, Idris Abdulmumin, Lukman Jibril Aliyu, Sani Ahmad Hassan, Shamsuddeen Hassan Muhammad","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T20:48:25Z","title":"Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12179","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":"sha256:4079da1678ab1a567e5994f16cb68d264700b4d28ff5a04083f8d6d676b55427","target":"record","created_at":"2026-07-05T07:15:01Z","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":"d31434b34781ddc8798a2867ec55243227af88d4d53bca7098f6c124d418273f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T20:48:25Z","title_canon_sha256":"63c6570538af44eeaba518fcde0ecbafe4a27dfdca91f0efe68b9859c611bf7b"},"schema_version":"1.0","source":{"id":"2311.12179","kind":"arxiv","version":1}},"canonical_sha256":"c6803a74f23a1260bef6fae82dd02a68aecf17d5fd93b3696de6501c8615b7b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6803a74f23a1260bef6fae82dd02a68aecf17d5fd93b3696de6501c8615b7b2","first_computed_at":"2026-07-05T07:15:01.736215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:01.736215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PseZAYyijV1Ylu0CBGFq1yMqt79yj3tX3/JbnQrO33IV851516JZsZI+LFQjJjD/cBhwe7CQuwEuhwkHYn5iBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:01.736624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4079da1678ab1a567e5994f16cb68d264700b4d28ff5a04083f8d6d676b55427","sha256:455314cabcca2b0f403a26f31ea5b5debf4048da184c16514929e4bed2b06973"],"state_sha256":"b28bd9278a5d963de8a8818efbbb575e0e9c5864610fa3005acf3da72e625458"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfoTsFri/ezvRe2Il9vrxwQ//wolDFN9B4hvjbM9Oy5dQgxwjoJi59CpxzWodf2IR62u5VDfWUsERBKPT1VxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:11:05.944676Z","bundle_sha256":"30982d3804ee4eb172fbf85f483bc628e912993148ba79c87a29d084ba0eb819"}}