{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EG66GJLUFHMRVSAMVGBUD23YWY","short_pith_number":"pith:EG66GJLU","schema_version":"1.0","canonical_sha256":"21bde3257429d91ac80ca98341eb78b639df23fb7687721a3b134b22824f5c69","source":{"kind":"arxiv","id":"1705.03802","version":1},"attestation_state":"computed","paper":{"title":"Analysing Data-To-Text Generation Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claire Gardent, Laura Perez-Beltrachini","submitted_at":"2017-05-10T14:42:54Z","abstract_excerpt":"Recently, several data-sets associating data to text have been created to train data-to-text surface realisers. It is unclear however to what extent the surface realisation task exercised by these data-sets is linguistically challenging. Do these data-sets provide enough variety to encourage the development of generic, high-quality data-to-text surface realisers ? In this paper, we argue that these data-sets have important drawbacks. We back up our claim using statistics, metrics and manual evaluation. We conclude by eliciting a set of criteria for the creation of a data-to-text benchmark whic"},"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":"1705.03802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T14:42:54Z","cross_cats_sorted":[],"title_canon_sha256":"5b6cf3e28baad7b924d83ad031ee3cbdc6b258586334ae5ec03c6636c0c63fb1","abstract_canon_sha256":"2fa8108cb2dd86d8e6ccfdb05233a9d8abdadbfa93aa555c25e74216eee9c2ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:43.010696Z","signature_b64":"jdhtIPpxsB8OwFYNPeDxGMJTtGjtx3yBUFGnvpMzXS6o9LqZ4vJjBbKkq4cZ+rb5h2BxK+aoi/oeCMSXvsAUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21bde3257429d91ac80ca98341eb78b639df23fb7687721a3b134b22824f5c69","last_reissued_at":"2026-05-18T00:44:43.010253Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:43.010253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysing Data-To-Text Generation Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claire Gardent, Laura Perez-Beltrachini","submitted_at":"2017-05-10T14:42:54Z","abstract_excerpt":"Recently, several data-sets associating data to text have been created to train data-to-text surface realisers. It is unclear however to what extent the surface realisation task exercised by these data-sets is linguistically challenging. Do these data-sets provide enough variety to encourage the development of generic, high-quality data-to-text surface realisers ? In this paper, we argue that these data-sets have important drawbacks. We back up our claim using statistics, metrics and manual evaluation. We conclude by eliciting a set of criteria for the creation of a data-to-text benchmark whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03802","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":"1705.03802","created_at":"2026-05-18T00:44:43.010309+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.03802v1","created_at":"2026-05-18T00:44:43.010309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03802","created_at":"2026-05-18T00:44:43.010309+00:00"},{"alias_kind":"pith_short_12","alias_value":"EG66GJLUFHMR","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EG66GJLUFHMRVSAM","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EG66GJLU","created_at":"2026-05-18T12:31:12.930513+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/EG66GJLUFHMRVSAMVGBUD23YWY","json":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY.json","graph_json":"https://pith.science/api/pith-number/EG66GJLUFHMRVSAMVGBUD23YWY/graph.json","events_json":"https://pith.science/api/pith-number/EG66GJLUFHMRVSAMVGBUD23YWY/events.json","paper":"https://pith.science/paper/EG66GJLU"},"agent_actions":{"view_html":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY","download_json":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY.json","view_paper":"https://pith.science/paper/EG66GJLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.03802&json=true","fetch_graph":"https://pith.science/api/pith-number/EG66GJLUFHMRVSAMVGBUD23YWY/graph.json","fetch_events":"https://pith.science/api/pith-number/EG66GJLUFHMRVSAMVGBUD23YWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY/action/storage_attestation","attest_author":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY/action/author_attestation","sign_citation":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY/action/citation_signature","submit_replication":"https://pith.science/pith/EG66GJLUFHMRVSAMVGBUD23YWY/action/replication_record"}},"created_at":"2026-05-18T00:44:43.010309+00:00","updated_at":"2026-05-18T00:44:43.010309+00:00"}