{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YL5E2VVKJKCTGMJ3GRVA32WDBB","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":"d660a5be2449f9564f5576d5ed59ab27aa21bef022be9161d2f2d0c85e5a7f43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T08:26:38Z","title_canon_sha256":"03efda04b680bd456115b96dde30eb09dac16ccf74577ad94d1defeae013fdcc"},"schema_version":"1.0","source":{"id":"2304.00483","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00483","created_at":"2026-07-05T06:59:51Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00483v2","created_at":"2026-07-05T06:59:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00483","created_at":"2026-07-05T06:59:51Z"},{"alias_kind":"pith_short_12","alias_value":"YL5E2VVKJKCT","created_at":"2026-07-05T06:59:51Z"},{"alias_kind":"pith_short_16","alias_value":"YL5E2VVKJKCTGMJ3","created_at":"2026-07-05T06:59:51Z"},{"alias_kind":"pith_short_8","alias_value":"YL5E2VVK","created_at":"2026-07-05T06:59:51Z"}],"graph_snapshots":[{"event_id":"sha256:7e4d2a7a1b21628ebd14fccb62351a55aa8bd9d61aa355b8be734eb1be2cf408","target":"graph","created_at":"2026-07-05T06:59:51Z","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/2304.00483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Duy Phung, Iva Bojic, Josef Halim, Josip Car, Mathieu Ravaut, Qi Chwen Ong, Shafiq Joty, Sreeja Tar, Verena Suharman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T08:26:38Z","title":"A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00483","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:bba6d322c462f2f476fb3c9dd00ed01322e16305d84d6aa28ef9d0837b91acd7","target":"record","created_at":"2026-07-05T06:59:51Z","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":"d660a5be2449f9564f5576d5ed59ab27aa21bef022be9161d2f2d0c85e5a7f43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T08:26:38Z","title_canon_sha256":"03efda04b680bd456115b96dde30eb09dac16ccf74577ad94d1defeae013fdcc"},"schema_version":"1.0","source":{"id":"2304.00483","kind":"arxiv","version":2}},"canonical_sha256":"c2fa4d56aa4a8533313b346a0deac308624fa15497e671c1080018e5bd0b1ce7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2fa4d56aa4a8533313b346a0deac308624fa15497e671c1080018e5bd0b1ce7","first_computed_at":"2026-07-05T06:59:51.638281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:51.638281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1c181WhNMJpsbWuxyjKoNuy/CyfVh7X5egERRIvNXSAepV+W/yI5h5CWF9ztWvVRf5kgOXYCYY9wgZ7udtRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:51.638747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00483","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bba6d322c462f2f476fb3c9dd00ed01322e16305d84d6aa28ef9d0837b91acd7","sha256:7e4d2a7a1b21628ebd14fccb62351a55aa8bd9d61aa355b8be734eb1be2cf408"],"state_sha256":"9453ef7ab1dd4994711cb678cd8d5c6e8c5b6849ea284db193abd2b063cf33fb"}