{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VVDM2POTNCM2TNQNYHGFLRBHOX","short_pith_number":"pith:VVDM2POT","canonical_record":{"source":{"id":"2502.02047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:27:39Z","cross_cats_sorted":[],"title_canon_sha256":"166cef760f522bf8adc5f2203ad7aa842060178c3e0a3621bc7602a4e4369c0e","abstract_canon_sha256":"6f831be344d4300caf8bc793bec896d1dd5fbe312173ef46ca1aaf5304ebd1b2"},"schema_version":"1.0"},"canonical_sha256":"ad46cd3dd36899a9b60dc1cc55c42775f1936ec15da9274db0e38b716019375c","source":{"kind":"arxiv","id":"2502.02047","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02047","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02047v1","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02047","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"VVDM2POTNCM2","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"VVDM2POTNCM2TNQN","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"VVDM2POT","created_at":"2026-07-05T10:09:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VVDM2POTNCM2TNQNYHGFLRBHOX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:27:39Z","cross_cats_sorted":[],"title_canon_sha256":"166cef760f522bf8adc5f2203ad7aa842060178c3e0a3621bc7602a4e4369c0e","abstract_canon_sha256":"6f831be344d4300caf8bc793bec896d1dd5fbe312173ef46ca1aaf5304ebd1b2"},"schema_version":"1.0"},"canonical_sha256":"ad46cd3dd36899a9b60dc1cc55c42775f1936ec15da9274db0e38b716019375c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:22.969271Z","signature_b64":"el9SsKfJ/h50/75q81HONaesbdKnyE9N6weRe+n0Cvt9bVKgV1I9v8nxPmptjGLzG9hU5CyiIOfS+y8g8AHbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad46cd3dd36899a9b60dc1cc55c42775f1936ec15da9274db0e38b716019375c","last_reissued_at":"2026-07-05T10:09:22.968861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:22.968861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02047","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":"2026-07-05T10:09:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Fcw4YA8bgSE+PZQNYIob3EPxPBMRq8qc5KmqeeDv6285+1WXOzXcYoB1PVy+otcAszfF/LpWdYbdTElrR9pBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:41.013273Z"},"content_sha256":"46941aecb2a5e337cf21e88e9e55dd8d558afdbc25675a97f24ce6e99b3521f5","schema_version":"1.0","event_id":"sha256:46941aecb2a5e337cf21e88e9e55dd8d558afdbc25675a97f24ce6e99b3521f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VVDM2POTNCM2TNQNYHGFLRBHOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Blessed Guda, Nebiyou Daniel Hailemariam, Tsegazeab Tefferi","submitted_at":"2025-02-04T06:27:39Z","abstract_excerpt":"This research presents a novel framework for translating extractive question-answering datasets into low-resource languages, as demonstrated by the creation of the AmaSQuAD dataset, a translation of SQuAD 2.0 into Amharic. The methodology addresses challenges related to misalignment between translated questions and answers, as well as the presence of multiple answer instances in the translated context. For this purpose, we used cosine similarity utilizing embeddings from a fine-tuned BERT-based model for Amharic and Longest Common Subsequence (LCS). Additionally, we fine-tune the XLM-R model o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02047","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/2502.02047/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":"2026-07-05T10:09:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXEaNyBwL1Am/vF7JNruN4JQngf+n3760Rjfrq6lYgW6YV8PV+NYtOi+LkgUCTMrrO5Qkbk/Dr5V9MYpYklMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:41.013816Z"},"content_sha256":"b40f30d4835c136e79e8c3c59c6958e22779e2bcb3c9bf78e24897e6e853dc47","schema_version":"1.0","event_id":"sha256:b40f30d4835c136e79e8c3c59c6958e22779e2bcb3c9bf78e24897e6e853dc47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/bundle.json","state_url":"https://pith.science/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/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":"2026-08-09T22:03:41Z","links":{"resolver":"https://pith.science/pith/VVDM2POTNCM2TNQNYHGFLRBHOX","bundle":"https://pith.science/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/bundle.json","state":"https://pith.science/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVDM2POTNCM2TNQNYHGFLRBHOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VVDM2POTNCM2TNQNYHGFLRBHOX","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":"6f831be344d4300caf8bc793bec896d1dd5fbe312173ef46ca1aaf5304ebd1b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:27:39Z","title_canon_sha256":"166cef760f522bf8adc5f2203ad7aa842060178c3e0a3621bc7602a4e4369c0e"},"schema_version":"1.0","source":{"id":"2502.02047","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02047","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02047v1","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02047","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"VVDM2POTNCM2","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"VVDM2POTNCM2TNQN","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"VVDM2POT","created_at":"2026-07-05T10:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:b40f30d4835c136e79e8c3c59c6958e22779e2bcb3c9bf78e24897e6e853dc47","target":"graph","created_at":"2026-07-05T10:09:22Z","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/2502.02047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research presents a novel framework for translating extractive question-answering datasets into low-resource languages, as demonstrated by the creation of the AmaSQuAD dataset, a translation of SQuAD 2.0 into Amharic. The methodology addresses challenges related to misalignment between translated questions and answers, as well as the presence of multiple answer instances in the translated context. For this purpose, we used cosine similarity utilizing embeddings from a fine-tuned BERT-based model for Amharic and Longest Common Subsequence (LCS). Additionally, we fine-tune the XLM-R model o","authors_text":"Blessed Guda, Nebiyou Daniel Hailemariam, Tsegazeab Tefferi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:27:39Z","title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02047","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":"sha256:46941aecb2a5e337cf21e88e9e55dd8d558afdbc25675a97f24ce6e99b3521f5","target":"record","created_at":"2026-07-05T10:09:22Z","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":"6f831be344d4300caf8bc793bec896d1dd5fbe312173ef46ca1aaf5304ebd1b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:27:39Z","title_canon_sha256":"166cef760f522bf8adc5f2203ad7aa842060178c3e0a3621bc7602a4e4369c0e"},"schema_version":"1.0","source":{"id":"2502.02047","kind":"arxiv","version":1}},"canonical_sha256":"ad46cd3dd36899a9b60dc1cc55c42775f1936ec15da9274db0e38b716019375c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad46cd3dd36899a9b60dc1cc55c42775f1936ec15da9274db0e38b716019375c","first_computed_at":"2026-07-05T10:09:22.968861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:22.968861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"el9SsKfJ/h50/75q81HONaesbdKnyE9N6weRe+n0Cvt9bVKgV1I9v8nxPmptjGLzG9hU5CyiIOfS+y8g8AHbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:22.969271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02047","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46941aecb2a5e337cf21e88e9e55dd8d558afdbc25675a97f24ce6e99b3521f5","sha256:b40f30d4835c136e79e8c3c59c6958e22779e2bcb3c9bf78e24897e6e853dc47"],"state_sha256":"1c6fbde2b62d6f555d37d20eb8eb34a7c801e86d6323175128ee0ffe366029df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fj+f6rhO1qoAton0ZwJbOf/sUxyMfe1BbSu4lswUYpbvazIngad275mxVycLqLTNCd+bbCQlO5ip353CnH2LAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:03:41.019940Z","bundle_sha256":"3445b6d2bfa9411f235c9bad2cd8fb0067160102b72da98bd860ff0ecba23836"}}