{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UN5PSIOXZ4ZU67WLDW37TFJTBB","short_pith_number":"pith:UN5PSIOX","canonical_record":{"source":{"id":"2404.17342","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:46:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8661a98b97720a4a9233d223b538e96946c1d11c64a5ed207aa9d4d1bfc5dbf","abstract_canon_sha256":"4e760b9e0a3ddbc8279f59001f805318991f8c2219c67bbd913390ffe80f1853"},"schema_version":"1.0"},"canonical_sha256":"a37af921d7cf334f7ecb1db7f995330857a36f8a575493292568c81b4d11a616","source":{"kind":"arxiv","id":"2404.17342","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17342","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17342v2","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17342","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"UN5PSIOXZ4ZU","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"UN5PSIOXZ4ZU67WL","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"UN5PSIOX","created_at":"2026-07-05T10:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UN5PSIOXZ4ZU67WLDW37TFJTBB","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17342","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:46:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8661a98b97720a4a9233d223b538e96946c1d11c64a5ed207aa9d4d1bfc5dbf","abstract_canon_sha256":"4e760b9e0a3ddbc8279f59001f805318991f8c2219c67bbd913390ffe80f1853"},"schema_version":"1.0"},"canonical_sha256":"a37af921d7cf334f7ecb1db7f995330857a36f8a575493292568c81b4d11a616","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:38.603829Z","signature_b64":"OmIS1pZYqIxTCT/MjqokSH4TvQiqu609KrIa+lIn4/8Gf4sGAeC9TT2J3EuHYdN32i7ge2MKgokDf0lzbI0mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a37af921d7cf334f7ecb1db7f995330857a36f8a575493292568c81b4d11a616","last_reissued_at":"2026-07-05T10:04:38.603270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:38.603270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17342","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":"2026-07-05T10:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2+29SCkVLee4b/DFiAa2tSxahMcTaMANbZ7yLv9Eu4nOe+deMzcq5gj4AgKRA5Me+5mTzFc1POHISfS0t3iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:18:49.689497Z"},"content_sha256":"b12942ed96f864c03e9698a5275f32c14ffaa3dba95449c90e55d4b6ab741076","schema_version":"1.0","event_id":"sha256:b12942ed96f864c03e9698a5275f32c14ffaa3dba95449c90e55d4b6ab741076"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UN5PSIOXZ4ZU67WLDW37TFJTBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Multiple-Choice to Extractive QA: A Case Study for English and Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Chenyang Lyu, Kirill Chirkunov, Malik H. Altakrori, Mohamed Nasr, Nizar Habash, Preslav Nakov, Radu Florian, Rocktim Jyoti Das, Salim Roukos, Samar Mohamed Magdy, Shantanu Godbole, Teresa Lynn, Younes Samih","submitted_at":"2024-04-26T11:46:05Z","abstract_excerpt":"The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task whose importance cannot be underestimated, but which is time-consuming and costly. Thus, any dataset for resource-poor languages is precious, in particular when it is task-specific. Here, we explore the feasibility of repurposing an existing multilingual dataset for a new NLP task: we repurpose a subset of the BELEBELE dataset (Bandarkar et al., 2023), which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17342","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/2404.17342/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":"2026-07-05T10:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aUIj+X8ov3Fl4Pfn+WJNF2a72Assf6JED1pjSoV19WyBAwH45T7nIbK5Ri7haHUrGHS6cLEFs7AB8leOwtEpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:18:49.690033Z"},"content_sha256":"986c67927b07cb9b21fd1e67c6f3992c8298bb494d907380af62deb9c4815719","schema_version":"1.0","event_id":"sha256:986c67927b07cb9b21fd1e67c6f3992c8298bb494d907380af62deb9c4815719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/bundle.json","state_url":"https://pith.science/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/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":"2026-08-17T19:18:49Z","links":{"resolver":"https://pith.science/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB","bundle":"https://pith.science/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/bundle.json","state":"https://pith.science/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UN5PSIOXZ4ZU67WLDW37TFJTBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UN5PSIOXZ4ZU67WLDW37TFJTBB","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":"4e760b9e0a3ddbc8279f59001f805318991f8c2219c67bbd913390ffe80f1853","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:46:05Z","title_canon_sha256":"b8661a98b97720a4a9233d223b538e96946c1d11c64a5ed207aa9d4d1bfc5dbf"},"schema_version":"1.0","source":{"id":"2404.17342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17342","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17342v2","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17342","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"UN5PSIOXZ4ZU","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"UN5PSIOXZ4ZU67WL","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"UN5PSIOX","created_at":"2026-07-05T10:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:986c67927b07cb9b21fd1e67c6f3992c8298bb494d907380af62deb9c4815719","target":"graph","created_at":"2026-07-05T10:04:38Z","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/2404.17342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task whose importance cannot be underestimated, but which is time-consuming and costly. Thus, any dataset for resource-poor languages is precious, in particular when it is task-specific. Here, we explore the feasibility of repurposing an existing multilingual dataset for a new NLP task: we repurpose a subset of the BELEBELE dataset (Bandarkar et al., 2023), which","authors_text":"Alham Fikri Aji, Chenyang Lyu, Kirill Chirkunov, Malik H. Altakrori, Mohamed Nasr, Nizar Habash, Preslav Nakov, Radu Florian, Rocktim Jyoti Das, Salim Roukos, Samar Mohamed Magdy, Shantanu Godbole, Teresa Lynn, Younes Samih","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:46:05Z","title":"From Multiple-Choice to Extractive QA: A Case Study for English and Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17342","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:b12942ed96f864c03e9698a5275f32c14ffaa3dba95449c90e55d4b6ab741076","target":"record","created_at":"2026-07-05T10:04:38Z","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":"4e760b9e0a3ddbc8279f59001f805318991f8c2219c67bbd913390ffe80f1853","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:46:05Z","title_canon_sha256":"b8661a98b97720a4a9233d223b538e96946c1d11c64a5ed207aa9d4d1bfc5dbf"},"schema_version":"1.0","source":{"id":"2404.17342","kind":"arxiv","version":2}},"canonical_sha256":"a37af921d7cf334f7ecb1db7f995330857a36f8a575493292568c81b4d11a616","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37af921d7cf334f7ecb1db7f995330857a36f8a575493292568c81b4d11a616","first_computed_at":"2026-07-05T10:04:38.603270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:38.603270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OmIS1pZYqIxTCT/MjqokSH4TvQiqu609KrIa+lIn4/8Gf4sGAeC9TT2J3EuHYdN32i7ge2MKgokDf0lzbI0mBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:38.603829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b12942ed96f864c03e9698a5275f32c14ffaa3dba95449c90e55d4b6ab741076","sha256:986c67927b07cb9b21fd1e67c6f3992c8298bb494d907380af62deb9c4815719"],"state_sha256":"f311496c16592c0f698292fa2894a4a6e0b49b6e14cb33bf0bd773e0dc4d4996"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yER7yDB6WRG0q+eRrN6bZIBgjssX4BsHRkI8buWymFh1IfxPkc0uClDTMXgXcXzjBd6Qrde0/lw3P7QWHvRqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:18:49.695978Z","bundle_sha256":"439c774a20f0511623991fcafe95c3ba4cacbb317009263f4e7292229e77e202"}}