{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2BB7ROQKZ3ZQP45ZVMRWIQJWK6","short_pith_number":"pith:2BB7ROQK","schema_version":"1.0","canonical_sha256":"d043f8ba0acef307f3b9ab23644136579654e813b3ecb77cff991e3eb512315a","source":{"kind":"arxiv","id":"2401.01183","version":1},"attestation_state":"computed","paper":{"title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binhua Li, Can Ma, Fei Huang, Guanghu Yuan, Liang Li, Min Yang, Ruiying Geng, Shao Yuan, Shujie Li, Wanwei He, Yongbin Li","submitted_at":"2024-01-02T12:23:49Z","abstract_excerpt":"Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performances. However, previous pre-training methods either oversimplified structured data into a sequence without considering input structures or designed training objectives tailored for a specific data structure (e.g., table or knowledge graph). In this paper, we unify different types of structured data (i.e., table, key-value data, knowledge graph) into the graph format and cast different data-to-te"},"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":"2401.01183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T12:23:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e85bbc6b7dc9a91abcc196d60285063003c3cb29ea14a78bda48fb46c1a41d5e","abstract_canon_sha256":"961c474a9b978f46728a5924fd4b4127a10f052015ee99aa0bafa960228b6936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:35.094143Z","signature_b64":"d1wuDe1rVbOOI4sIjby+/Wjo8ur9S9dmTH3S8tyMGgeR7KRMzcB3/V89rYIqINSv2Zvi93QPsH5ybfm6i30cBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d043f8ba0acef307f3b9ab23644136579654e813b3ecb77cff991e3eb512315a","last_reissued_at":"2026-07-05T07:29:35.093768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:35.093768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binhua Li, Can Ma, Fei Huang, Guanghu Yuan, Liang Li, Min Yang, Ruiying Geng, Shao Yuan, Shujie Li, Wanwei He, Yongbin Li","submitted_at":"2024-01-02T12:23:49Z","abstract_excerpt":"Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performances. However, previous pre-training methods either oversimplified structured data into a sequence without considering input structures or designed training objectives tailored for a specific data structure (e.g., table or knowledge graph). In this paper, we unify different types of structured data (i.e., table, key-value data, knowledge graph) into the graph format and cast different data-to-te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01183","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/2401.01183/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":"2401.01183","created_at":"2026-07-05T07:29:35.093818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01183v1","created_at":"2026-07-05T07:29:35.093818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01183","created_at":"2026-07-05T07:29:35.093818+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BB7ROQKZ3ZQ","created_at":"2026-07-05T07:29:35.093818+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BB7ROQKZ3ZQP45Z","created_at":"2026-07-05T07:29:35.093818+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BB7ROQK","created_at":"2026-07-05T07:29:35.093818+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/2BB7ROQKZ3ZQP45ZVMRWIQJWK6","json":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6.json","graph_json":"https://pith.science/api/pith-number/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/graph.json","events_json":"https://pith.science/api/pith-number/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/events.json","paper":"https://pith.science/paper/2BB7ROQK"},"agent_actions":{"view_html":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6","download_json":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6.json","view_paper":"https://pith.science/paper/2BB7ROQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01183&json=true","fetch_graph":"https://pith.science/api/pith-number/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/graph.json","fetch_events":"https://pith.science/api/pith-number/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/action/storage_attestation","attest_author":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/action/author_attestation","sign_citation":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/action/citation_signature","submit_replication":"https://pith.science/pith/2BB7ROQKZ3ZQP45ZVMRWIQJWK6/action/replication_record"}},"created_at":"2026-07-05T07:29:35.093818+00:00","updated_at":"2026-07-05T07:29:35.093818+00:00"}