{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RSAGZ66BI2YVVOXCBRF3UUYW4Y","short_pith_number":"pith:RSAGZ66B","schema_version":"1.0","canonical_sha256":"8c806cfbc146b15abae20c4bba5316e60787818ca4a766c5150f4d7ae01fd513","source":{"kind":"arxiv","id":"2103.05639","version":1},"attestation_state":"computed","paper":{"title":"An Amharic News Text classification Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Israel Abebe Azime, Nebil Mohammed","submitted_at":"2021-03-10T16:36:39Z","abstract_excerpt":"In NLP, text classification is one of the primary problems we try to solve and its uses in language analyses are indisputable. The lack of labeled training data made it harder to do these tasks in low resource languages like Amharic. The task of collecting, labeling, annotating, and making valuable this kind of data will encourage junior researchers, schools, and machine learning practitioners to implement existing classification models in their language. In this short paper, we aim to introduce the Amharic text classification dataset that consists of more than 50k news articles that were cate"},"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":"2103.05639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-10T16:36:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3804ed31c4269ba9337b9be782aeb065c6a8517f891a744e81016655e222dc3e","abstract_canon_sha256":"6874d67266b3bf3ce0f2fd343f92cd8a6fe75d691b5b155faa4776eac2939c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:56.619648Z","signature_b64":"HdCbqKrsI70Xo6rtPS0h6w6yy6dvp9xHdghUaD4KS3NnJXXW78YeC7CdJY59JhhWdp/AOB08BYsoM2B5MCDAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c806cfbc146b15abae20c4bba5316e60787818ca4a766c5150f4d7ae01fd513","last_reissued_at":"2026-07-05T02:21:56.619143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:56.619143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Amharic News Text classification Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Israel Abebe Azime, Nebil Mohammed","submitted_at":"2021-03-10T16:36:39Z","abstract_excerpt":"In NLP, text classification is one of the primary problems we try to solve and its uses in language analyses are indisputable. The lack of labeled training data made it harder to do these tasks in low resource languages like Amharic. The task of collecting, labeling, annotating, and making valuable this kind of data will encourage junior researchers, schools, and machine learning practitioners to implement existing classification models in their language. In this short paper, we aim to introduce the Amharic text classification dataset that consists of more than 50k news articles that were cate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05639","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/2103.05639/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":"2103.05639","created_at":"2026-07-05T02:21:56.619209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05639v1","created_at":"2026-07-05T02:21:56.619209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05639","created_at":"2026-07-05T02:21:56.619209+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSAGZ66BI2YV","created_at":"2026-07-05T02:21:56.619209+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSAGZ66BI2YVVOXC","created_at":"2026-07-05T02:21:56.619209+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSAGZ66B","created_at":"2026-07-05T02:21:56.619209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19356","citing_title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y","json":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y.json","graph_json":"https://pith.science/api/pith-number/RSAGZ66BI2YVVOXCBRF3UUYW4Y/graph.json","events_json":"https://pith.science/api/pith-number/RSAGZ66BI2YVVOXCBRF3UUYW4Y/events.json","paper":"https://pith.science/paper/RSAGZ66B"},"agent_actions":{"view_html":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y","download_json":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y.json","view_paper":"https://pith.science/paper/RSAGZ66B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05639&json=true","fetch_graph":"https://pith.science/api/pith-number/RSAGZ66BI2YVVOXCBRF3UUYW4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/RSAGZ66BI2YVVOXCBRF3UUYW4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y/action/storage_attestation","attest_author":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y/action/author_attestation","sign_citation":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y/action/citation_signature","submit_replication":"https://pith.science/pith/RSAGZ66BI2YVVOXCBRF3UUYW4Y/action/replication_record"}},"created_at":"2026-07-05T02:21:56.619209+00:00","updated_at":"2026-07-05T02:21:56.619209+00:00"}