{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YL5E2VVKJKCTGMJ3GRVA32WDBB","short_pith_number":"pith:YL5E2VVK","schema_version":"1.0","canonical_sha256":"c2fa4d56aa4a8533313b346a0deac308624fa15497e671c1080018e5bd0b1ce7","source":{"kind":"arxiv","id":"2304.00483","version":2},"attestation_state":"computed","paper":{"title":"A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duy Phung, Iva Bojic, Josef Halim, Josip Car, Mathieu Ravaut, Qi Chwen Ong, Shafiq Joty, Sreeja Tar, Verena Suharman","submitted_at":"2023-04-02T08:26:38Z","abstract_excerpt":"Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Models (LLMs) training, as well as for domain-specific models, which are usually small in size as it is costly to engage a large number of domain experts for their creation. Thus, it is vital to ensure high-quality domain-specific training data. In this paper, we propose a framework for enhancing the data quality of original datasets. We applied the proposed fra"},"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":"2304.00483","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T08:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"03efda04b680bd456115b96dde30eb09dac16ccf74577ad94d1defeae013fdcc","abstract_canon_sha256":"d660a5be2449f9564f5576d5ed59ab27aa21bef022be9161d2f2d0c85e5a7f43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:51.638747Z","signature_b64":"o1c181WhNMJpsbWuxyjKoNuy/CyfVh7X5egERRIvNXSAepV+W/yI5h5CWF9ztWvVRf5kgOXYCYY9wgZ7udtRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2fa4d56aa4a8533313b346a0deac308624fa15497e671c1080018e5bd0b1ce7","last_reissued_at":"2026-07-05T06:59:51.638281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:51.638281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duy Phung, Iva Bojic, Josef Halim, Josip Car, Mathieu Ravaut, Qi Chwen Ong, Shafiq Joty, Sreeja Tar, Verena Suharman","submitted_at":"2023-04-02T08:26:38Z","abstract_excerpt":"Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Models (LLMs) training, as well as for domain-specific models, which are usually small in size as it is costly to engage a large number of domain experts for their creation. Thus, it is vital to ensure high-quality domain-specific training data. In this paper, we propose a framework for enhancing the data quality of original datasets. We applied the proposed fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00483","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/2304.00483/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":"2304.00483","created_at":"2026-07-05T06:59:51.638341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00483v2","created_at":"2026-07-05T06:59:51.638341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00483","created_at":"2026-07-05T06:59:51.638341+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL5E2VVKJKCT","created_at":"2026-07-05T06:59:51.638341+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL5E2VVKJKCTGMJ3","created_at":"2026-07-05T06:59:51.638341+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL5E2VVK","created_at":"2026-07-05T06:59:51.638341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB","json":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB.json","graph_json":"https://pith.science/api/pith-number/YL5E2VVKJKCTGMJ3GRVA32WDBB/graph.json","events_json":"https://pith.science/api/pith-number/YL5E2VVKJKCTGMJ3GRVA32WDBB/events.json","paper":"https://pith.science/paper/YL5E2VVK"},"agent_actions":{"view_html":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB","download_json":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB.json","view_paper":"https://pith.science/paper/YL5E2VVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00483&json=true","fetch_graph":"https://pith.science/api/pith-number/YL5E2VVKJKCTGMJ3GRVA32WDBB/graph.json","fetch_events":"https://pith.science/api/pith-number/YL5E2VVKJKCTGMJ3GRVA32WDBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB/action/storage_attestation","attest_author":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB/action/author_attestation","sign_citation":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB/action/citation_signature","submit_replication":"https://pith.science/pith/YL5E2VVKJKCTGMJ3GRVA32WDBB/action/replication_record"}},"created_at":"2026-07-05T06:59:51.638341+00:00","updated_at":"2026-07-05T06:59:51.638341+00:00"}