{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q5KXIZX7THVQ67ED6SC4FB7RR4","short_pith_number":"pith:Q5KXIZX7","schema_version":"1.0","canonical_sha256":"87557466ff99eb0f7c83f485c287f18f0a049250ca053600670397adf8c2becf","source":{"kind":"arxiv","id":"1908.09022","version":2},"attestation_state":"computed","paper":{"title":"Neural data-to-text generation: A comparison between pipeline and end-to-end architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris van der Lee, Emiel Krahmer, Emiel van Miltenburg, Thiago castro Ferreira","submitted_at":"2019-08-23T20:10:36Z","abstract_excerpt":"Traditionally, most data-to-text applications have been designed using a modular pipeline architecture, in which non-linguistic input data is converted into natural language through several intermediate transformations. In contrast, recent neural models for data-to-text generation have been proposed as end-to-end approaches, where the non-linguistic input is rendered in natural language with much less explicit intermediate representations in-between. This study introduces a systematic comparison between neural pipeline and end-to-end data-to-text approaches for the generation of text from RDF "},"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":"1908.09022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-23T20:10:36Z","cross_cats_sorted":[],"title_canon_sha256":"28435ad33a6dae41a3e0a2f5148691bf4c7b08b1c9b5e5bacf4e14f50c12f61d","abstract_canon_sha256":"b32964e952bf7770f8863d60595ea83dc9dd2a7d35616cdc87fad8546b522083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:25.358259Z","signature_b64":"pn1DZjjOagBmvI02NwRvwRjP0bj5ZN7gPJQ60D/ibPUWSqBKOh3x4YbPDbCQ67SBCmoo2uml+4cFVustdfAXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87557466ff99eb0f7c83f485c287f18f0a049250ca053600670397adf8c2becf","last_reissued_at":"2026-07-05T00:22:25.357749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:25.357749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural data-to-text generation: A comparison between pipeline and end-to-end architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris van der Lee, Emiel Krahmer, Emiel van Miltenburg, Thiago castro Ferreira","submitted_at":"2019-08-23T20:10:36Z","abstract_excerpt":"Traditionally, most data-to-text applications have been designed using a modular pipeline architecture, in which non-linguistic input data is converted into natural language through several intermediate transformations. In contrast, recent neural models for data-to-text generation have been proposed as end-to-end approaches, where the non-linguistic input is rendered in natural language with much less explicit intermediate representations in-between. This study introduces a systematic comparison between neural pipeline and end-to-end data-to-text approaches for the generation of text from RDF "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09022","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/1908.09022/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":"1908.09022","created_at":"2026-07-05T00:22:25.357817+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09022v2","created_at":"2026-07-05T00:22:25.357817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09022","created_at":"2026-07-05T00:22:25.357817+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5KXIZX7THVQ","created_at":"2026-07-05T00:22:25.357817+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5KXIZX7THVQ67ED","created_at":"2026-07-05T00:22:25.357817+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5KXIZX7","created_at":"2026-07-05T00:22:25.357817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19710","citing_title":"Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphs","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4","json":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4.json","graph_json":"https://pith.science/api/pith-number/Q5KXIZX7THVQ67ED6SC4FB7RR4/graph.json","events_json":"https://pith.science/api/pith-number/Q5KXIZX7THVQ67ED6SC4FB7RR4/events.json","paper":"https://pith.science/paper/Q5KXIZX7"},"agent_actions":{"view_html":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4","download_json":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4.json","view_paper":"https://pith.science/paper/Q5KXIZX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09022&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5KXIZX7THVQ67ED6SC4FB7RR4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5KXIZX7THVQ67ED6SC4FB7RR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4/action/storage_attestation","attest_author":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4/action/author_attestation","sign_citation":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4/action/citation_signature","submit_replication":"https://pith.science/pith/Q5KXIZX7THVQ67ED6SC4FB7RR4/action/replication_record"}},"created_at":"2026-07-05T00:22:25.357817+00:00","updated_at":"2026-07-05T00:22:25.357817+00:00"}