{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YOKVRAJG3KG3W4IUJF3LCMWPFD","short_pith_number":"pith:YOKVRAJG","schema_version":"1.0","canonical_sha256":"c395588126da8dbb71144976b132cf28cc410f1b3b6afa9073e231ca5a6b76a3","source":{"kind":"arxiv","id":"1707.08052","version":1},"attestation_state":"computed","paper":{"title":"Challenges in Data-to-Document Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Sam Wiseman, Stuart M. Shieber","submitted_at":"2017-07-25T15:42:25Z","abstract_excerpt":"Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records. In this work, we suggest a slightly more difficult data-to-text generation task, and investigate how effective current approaches are on this task. In particular, we introduce a new, large-scale corpus of data records paired with descriptive documents, propose a series of extractive evaluation methods for analyzing performance, and obtain baseline results using current neural generation methods. Experiments show that these models produce f"},"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":"1707.08052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-25T15:42:25Z","cross_cats_sorted":[],"title_canon_sha256":"19041d9c169c82fff5944dcaad6c526efe050733863fdc3612db7589c49fbe18","abstract_canon_sha256":"eb1e948320c81a1fe649bea996f4d8e1a9e3396080c7cc6622f9d8d687f48491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:29.566389Z","signature_b64":"qFuNGLIjQnX7scIwikz62xp80QxIJ2RMKvntoZzuASF23ejfGeiOIqsv0lPGlllDEeQTzT54H9FP4TiIZpFPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c395588126da8dbb71144976b132cf28cc410f1b3b6afa9073e231ca5a6b76a3","last_reissued_at":"2026-05-18T00:39:29.565755Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:29.565755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges in Data-to-Document Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Sam Wiseman, Stuart M. Shieber","submitted_at":"2017-07-25T15:42:25Z","abstract_excerpt":"Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records. In this work, we suggest a slightly more difficult data-to-text generation task, and investigate how effective current approaches are on this task. In particular, we introduce a new, large-scale corpus of data records paired with descriptive documents, propose a series of extractive evaluation methods for analyzing performance, and obtain baseline results using current neural generation methods. Experiments show that these models produce f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08052","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":""},"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":"1707.08052","created_at":"2026-05-18T00:39:29.565847+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.08052v1","created_at":"2026-05-18T00:39:29.565847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08052","created_at":"2026-05-18T00:39:29.565847+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOKVRAJG3KG3","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOKVRAJG3KG3W4IU","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOKVRAJG","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18939","citing_title":"TabEmb: Joint Semantic-Structure Embedding for Table Annotation","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD","json":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD.json","graph_json":"https://pith.science/api/pith-number/YOKVRAJG3KG3W4IUJF3LCMWPFD/graph.json","events_json":"https://pith.science/api/pith-number/YOKVRAJG3KG3W4IUJF3LCMWPFD/events.json","paper":"https://pith.science/paper/YOKVRAJG"},"agent_actions":{"view_html":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD","download_json":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD.json","view_paper":"https://pith.science/paper/YOKVRAJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.08052&json=true","fetch_graph":"https://pith.science/api/pith-number/YOKVRAJG3KG3W4IUJF3LCMWPFD/graph.json","fetch_events":"https://pith.science/api/pith-number/YOKVRAJG3KG3W4IUJF3LCMWPFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD/action/storage_attestation","attest_author":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD/action/author_attestation","sign_citation":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD/action/citation_signature","submit_replication":"https://pith.science/pith/YOKVRAJG3KG3W4IUJF3LCMWPFD/action/replication_record"}},"created_at":"2026-05-18T00:39:29.565847+00:00","updated_at":"2026-05-18T00:39:29.565847+00:00"}