{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GXQODCBQ33H7BPRZZ7OCQAPX5R","short_pith_number":"pith:GXQODCBQ","canonical_record":{"source":{"id":"2210.10692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","cross_cats_sorted":[],"title_canon_sha256":"ef28d1e7b8f415adeed2bef071d5fae430beb6bf33646eaa472011ce9a942526","abstract_canon_sha256":"6f689eddf706c502f3974c22d920371e82ae6cc2381e3b32fd42a33bffd07eb3"},"schema_version":"1.0"},"canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","source":{"kind":"arxiv","id":"2210.10692","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10692","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10692v2","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10692","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"GXQODCBQ33H7","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"GXQODCBQ33H7BPRZ","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"GXQODCBQ","created_at":"2026-07-05T05:08:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GXQODCBQ33H7BPRZZ7OCQAPX5R","target":"record","payload":{"canonical_record":{"source":{"id":"2210.10692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","cross_cats_sorted":[],"title_canon_sha256":"ef28d1e7b8f415adeed2bef071d5fae430beb6bf33646eaa472011ce9a942526","abstract_canon_sha256":"6f689eddf706c502f3974c22d920371e82ae6cc2381e3b32fd42a33bffd07eb3"},"schema_version":"1.0"},"canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:31.958828Z","signature_b64":"0qq/rtYxyiTYio5a3fbFjuzQGc/5lnEgZaQabG9C/4EIKJWdqgF3fghJXoqCOp4Qr7sP0zV+ENYTydLZtvZ+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","last_reissued_at":"2026-07-05T05:08:31.958486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:31.958486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.10692","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":"2026-07-05T05:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eexzjjDMYAgmSIo8kdwK47YlyB7zDsElwp7VHb9PliFSnepdX50q2TrZjdWtEAKEizGy9R2g1Y+ZrKyapnl7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:49.718063Z"},"content_sha256":"085442244c81f3605245486a7bcc65bbd0e5c9fcd1f9844256763d220dee3879","schema_version":"1.0","event_id":"sha256:085442244c81f3605245486a7bcc65bbd0e5c9fcd1f9844256763d220dee3879"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GXQODCBQ33H7BPRZZ7OCQAPX5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Emezue, Everlyn Asiko, Idris Abdulmumin, Jesujoba O. Alabi, Michael Beukman, Mofetoluwa Adeyemi, Oreen Yousuf, Sahib Singh, Shamsuddeen Hassan Muhammad, Tajuddeen Rabiu Gwadabe, Tosin Adewumi","submitted_at":"2022-10-19T16:12:27Z","abstract_excerpt":"We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine transla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10692","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/2210.10692/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":"2026-07-05T05:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JOOWaZ4Fv6hQQcB4nbLLT8q3Tgotar/9lnXnawWNEHlTXzteaMbYWVs3kKU+T8uvFTC7SljcwOsRKn2SEyCuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:49.718442Z"},"content_sha256":"59ccb97eb16b0538be63ded0c5743376b4f79256087944cdb388cf4ab3d42f55","schema_version":"1.0","event_id":"sha256:59ccb97eb16b0538be63ded0c5743376b4f79256087944cdb388cf4ab3d42f55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/bundle.json","state_url":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/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":"2026-07-07T09:03:49Z","links":{"resolver":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R","bundle":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/bundle.json","state":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GXQODCBQ33H7BPRZZ7OCQAPX5R","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":"6f689eddf706c502f3974c22d920371e82ae6cc2381e3b32fd42a33bffd07eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","title_canon_sha256":"ef28d1e7b8f415adeed2bef071d5fae430beb6bf33646eaa472011ce9a942526"},"schema_version":"1.0","source":{"id":"2210.10692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10692","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10692v2","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10692","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"GXQODCBQ33H7","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"GXQODCBQ33H7BPRZ","created_at":"2026-07-05T05:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"GXQODCBQ","created_at":"2026-07-05T05:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:59ccb97eb16b0538be63ded0c5743376b4f79256087944cdb388cf4ab3d42f55","target":"graph","created_at":"2026-07-05T05:08:31Z","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/2210.10692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine transla","authors_text":"Chris Emezue, Everlyn Asiko, Idris Abdulmumin, Jesujoba O. Alabi, Michael Beukman, Mofetoluwa Adeyemi, Oreen Yousuf, Sahib Singh, Shamsuddeen Hassan Muhammad, Tajuddeen Rabiu Gwadabe, Tosin Adewumi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10692","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":"sha256:085442244c81f3605245486a7bcc65bbd0e5c9fcd1f9844256763d220dee3879","target":"record","created_at":"2026-07-05T05:08:31Z","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":"6f689eddf706c502f3974c22d920371e82ae6cc2381e3b32fd42a33bffd07eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","title_canon_sha256":"ef28d1e7b8f415adeed2bef071d5fae430beb6bf33646eaa472011ce9a942526"},"schema_version":"1.0","source":{"id":"2210.10692","kind":"arxiv","version":2}},"canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","first_computed_at":"2026-07-05T05:08:31.958486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:31.958486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0qq/rtYxyiTYio5a3fbFjuzQGc/5lnEgZaQabG9C/4EIKJWdqgF3fghJXoqCOp4Qr7sP0zV+ENYTydLZtvZ+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:31.958828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.10692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085442244c81f3605245486a7bcc65bbd0e5c9fcd1f9844256763d220dee3879","sha256:59ccb97eb16b0538be63ded0c5743376b4f79256087944cdb388cf4ab3d42f55"],"state_sha256":"484aefc4e509c578ce2df4fe7092d2d10bd5e7c7e334838a81a33b4422b466dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftkUJWSo99Ny4CHE3tI7/c7pEVqwdONebdklR/xvBSz/swkfrD5xK34PmkGnN9SkZc1Sym7NpilPR3I+fXSvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:03:49.720379Z","bundle_sha256":"7f7d5edd33bf8864e0b81994f37835a1fe2c70d57f0a38a2ad571d4cc1f4fade"}}