{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q34QY5BD5NHFFRP43WP2N24GRI","short_pith_number":"pith:Q34QY5BD","schema_version":"1.0","canonical_sha256":"86f90c7423eb4e52c5fcdd9fa6eb868a1f84a5887be07ceae326c6a0602a170d","source":{"kind":"arxiv","id":"2402.12869","version":2},"attestation_state":"computed","paper":{"title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dehai Min, Guilin Qi, Jiaoyan Chen, Nan Hu, Nijun Li, Nuo Lin, Qianren Wang, Rihui Jin, Yongrui Chen, Yu Li, Yun Li","submitted_at":"2024-02-20T10:00:58Z","abstract_excerpt":"Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affe"},"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":"2402.12869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T10:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"80a9c20285ffd8d813cdf96999ec0f4ad67889f8e55c7292c255eb0854c17b2f","abstract_canon_sha256":"9e06b450764a0832413f842257c9da403f2976db753a027c2c3046fad7c4b481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:56.301005Z","signature_b64":"OBmnDEnEGzcbwtB/mspAT7SeDJInz32JvnfJon+P3CodRp44m1y5cizm1ocxHxxL6TjT//xDDymOY8Rn1dBXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f90c7423eb4e52c5fcdd9fa6eb868a1f84a5887be07ceae326c6a0602a170d","last_reissued_at":"2026-07-05T08:05:56.300530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:56.300530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dehai Min, Guilin Qi, Jiaoyan Chen, Nan Hu, Nijun Li, Nuo Lin, Qianren Wang, Rihui Jin, Yongrui Chen, Yu Li, Yun Li","submitted_at":"2024-02-20T10:00:58Z","abstract_excerpt":"Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12869","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/2402.12869/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":"2402.12869","created_at":"2026-07-05T08:05:56.300600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12869v2","created_at":"2026-07-05T08:05:56.300600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12869","created_at":"2026-07-05T08:05:56.300600+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q34QY5BD5NHF","created_at":"2026-07-05T08:05:56.300600+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q34QY5BD5NHFFRP4","created_at":"2026-07-05T08:05:56.300600+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q34QY5BD","created_at":"2026-07-05T08:05:56.300600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":294,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI","json":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI.json","graph_json":"https://pith.science/api/pith-number/Q34QY5BD5NHFFRP43WP2N24GRI/graph.json","events_json":"https://pith.science/api/pith-number/Q34QY5BD5NHFFRP43WP2N24GRI/events.json","paper":"https://pith.science/paper/Q34QY5BD"},"agent_actions":{"view_html":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI","download_json":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI.json","view_paper":"https://pith.science/paper/Q34QY5BD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12869&json=true","fetch_graph":"https://pith.science/api/pith-number/Q34QY5BD5NHFFRP43WP2N24GRI/graph.json","fetch_events":"https://pith.science/api/pith-number/Q34QY5BD5NHFFRP43WP2N24GRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI/action/storage_attestation","attest_author":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI/action/author_attestation","sign_citation":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI/action/citation_signature","submit_replication":"https://pith.science/pith/Q34QY5BD5NHFFRP43WP2N24GRI/action/replication_record"}},"created_at":"2026-07-05T08:05:56.300600+00:00","updated_at":"2026-07-05T08:05:56.300600+00:00"}