{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KQPRZPC25EFBM7S4FBEXXX7YCF","short_pith_number":"pith:KQPRZPC2","schema_version":"1.0","canonical_sha256":"541f1cbc5ae90a167e5c28497bdff8115082ab2b8dcf26ab333755a7066db494","source":{"kind":"arxiv","id":"2303.03290","version":2},"attestation_state":"computed","paper":{"title":"AmQA: Amharic Question Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Ricardo Usbeck, Tilahun Abedissa, Yaregal Assabie","submitted_at":"2023-03-06T17:06:50Z","abstract_excerpt":"Question Answering (QA) returns concise answers or answer lists from natural language text given a context document. Many resources go into curating QA datasets to advance robust models' development. There is a surge of QA datasets for languages like English, however, this is not true for Amharic. Amharic, the official language of Ethiopia, is the second most spoken Semitic language in the world. There is no published or publicly available Amharic QA dataset. Hence, to foster the research in Amharic QA, we present the first Amharic QA (AmQA) dataset. We crowdsourced 2628 question-answer pairs "},"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":"2303.03290","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-06T17:06:50Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d1c1fb8ac85b88f66352bf633149115d0efc2b0173ff638ee1cb9aae21c27f5e","abstract_canon_sha256":"f9220b91a0d17b83850d20b2dddbf8c683f54163c557effde38fc44b5474fd5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:21.784510Z","signature_b64":"vEhSC6gfDLmBlFPDEX+UkrXvJccTk1/sC5evAWzizaxxVtfutIoDFFswZBD3HkXRRSOlA+1zQKoSIfSZoBorBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"541f1cbc5ae90a167e5c28497bdff8115082ab2b8dcf26ab333755a7066db494","last_reissued_at":"2026-07-05T07:13:21.784024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:21.784024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AmQA: Amharic Question Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Ricardo Usbeck, Tilahun Abedissa, Yaregal Assabie","submitted_at":"2023-03-06T17:06:50Z","abstract_excerpt":"Question Answering (QA) returns concise answers or answer lists from natural language text given a context document. Many resources go into curating QA datasets to advance robust models' development. There is a surge of QA datasets for languages like English, however, this is not true for Amharic. Amharic, the official language of Ethiopia, is the second most spoken Semitic language in the world. There is no published or publicly available Amharic QA dataset. Hence, to foster the research in Amharic QA, we present the first Amharic QA (AmQA) dataset. We crowdsourced 2628 question-answer pairs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03290","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/2303.03290/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":"2303.03290","created_at":"2026-07-05T07:13:21.784080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03290v2","created_at":"2026-07-05T07:13:21.784080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03290","created_at":"2026-07-05T07:13:21.784080+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQPRZPC25EFB","created_at":"2026-07-05T07:13:21.784080+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQPRZPC25EFBM7S4","created_at":"2026-07-05T07:13:21.784080+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQPRZPC2","created_at":"2026-07-05T07:13:21.784080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24556","citing_title":"The Multilingual Curse at the Retrieval Layer: Evidence from Amharic","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF","json":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF.json","graph_json":"https://pith.science/api/pith-number/KQPRZPC25EFBM7S4FBEXXX7YCF/graph.json","events_json":"https://pith.science/api/pith-number/KQPRZPC25EFBM7S4FBEXXX7YCF/events.json","paper":"https://pith.science/paper/KQPRZPC2"},"agent_actions":{"view_html":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF","download_json":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF.json","view_paper":"https://pith.science/paper/KQPRZPC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03290&json=true","fetch_graph":"https://pith.science/api/pith-number/KQPRZPC25EFBM7S4FBEXXX7YCF/graph.json","fetch_events":"https://pith.science/api/pith-number/KQPRZPC25EFBM7S4FBEXXX7YCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF/action/storage_attestation","attest_author":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF/action/author_attestation","sign_citation":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF/action/citation_signature","submit_replication":"https://pith.science/pith/KQPRZPC25EFBM7S4FBEXXX7YCF/action/replication_record"}},"created_at":"2026-07-05T07:13:21.784080+00:00","updated_at":"2026-07-05T07:13:21.784080+00:00"}