{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JTPRBO6BJ6HNL3PWZNU2SJ2NTG","short_pith_number":"pith:JTPRBO6B","schema_version":"1.0","canonical_sha256":"4cdf10bbc14f8ed5edf6cb69a9274d999a02b3c5ccea741419872cd28b4488f8","source":{"kind":"arxiv","id":"2004.14579","version":2},"attestation_state":"computed","paper":{"title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanwen Zha, Sairam Sundaresan, Wenhu Chen, William Yang Wang, Xiyou Zhou, Yunkai Zhang, Zhiyu Chen","submitted_at":"2020-04-30T04:06:06Z","abstract_excerpt":"Previous works on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an NLG system to describe interesting facts from logical inferences across records. If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations. In this work, we formulate logical level NLG as generation from logical forms in order to obtain controllable, high-fidelity, and faithful generations. We"},"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":"2004.14579","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T04:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"34d2ef969aba8aab933c545d9a751c0c7c403f3f52cedf3a696974debb50a4c1","abstract_canon_sha256":"58e1d447ccd553a1eefe9bf1b7e175834ae9a6d72b111a1d0d32dc894f145b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:42.087616Z","signature_b64":"JjQvFE1BD40BuEXrZjmJzJ5B+SYRVI/YYJpGaWAErJa+AAlTXY4UA0hMQl0HJzGxPP0nHVVVgnSfHGUh57s+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cdf10bbc14f8ed5edf6cb69a9274d999a02b3c5ccea741419872cd28b4488f8","last_reissued_at":"2026-07-05T01:37:42.087169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:42.087169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanwen Zha, Sairam Sundaresan, Wenhu Chen, William Yang Wang, Xiyou Zhou, Yunkai Zhang, Zhiyu Chen","submitted_at":"2020-04-30T04:06:06Z","abstract_excerpt":"Previous works on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an NLG system to describe interesting facts from logical inferences across records. If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations. In this work, we formulate logical level NLG as generation from logical forms in order to obtain controllable, high-fidelity, and faithful generations. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14579","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/2004.14579/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":"2004.14579","created_at":"2026-07-05T01:37:42.087225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14579v2","created_at":"2026-07-05T01:37:42.087225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14579","created_at":"2026-07-05T01:37:42.087225+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTPRBO6BJ6HN","created_at":"2026-07-05T01:37:42.087225+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTPRBO6BJ6HNL3PW","created_at":"2026-07-05T01:37:42.087225+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTPRBO6B","created_at":"2026-07-05T01:37:42.087225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10971","citing_title":"Rule2Text: A Framework for Generating and Evaluating Natural Language Explanations of Knowledge Graph Rules","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG","json":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG.json","graph_json":"https://pith.science/api/pith-number/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/graph.json","events_json":"https://pith.science/api/pith-number/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/events.json","paper":"https://pith.science/paper/JTPRBO6B"},"agent_actions":{"view_html":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG","download_json":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG.json","view_paper":"https://pith.science/paper/JTPRBO6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14579&json=true","fetch_graph":"https://pith.science/api/pith-number/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/graph.json","fetch_events":"https://pith.science/api/pith-number/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/action/storage_attestation","attest_author":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/action/author_attestation","sign_citation":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/action/citation_signature","submit_replication":"https://pith.science/pith/JTPRBO6BJ6HNL3PWZNU2SJ2NTG/action/replication_record"}},"created_at":"2026-07-05T01:37:42.087225+00:00","updated_at":"2026-07-05T01:37:42.087225+00:00"}