{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O2RWDRRSUVIPVUBBGEA2BFCQLA","short_pith_number":"pith:O2RWDRRS","schema_version":"1.0","canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","source":{"kind":"arxiv","id":"2109.01518","version":1},"attestation_state":"computed","paper":{"title":"Biomedical Data-to-Text Generation via Fine-Tuning Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Angelo Ziletti, Nicholas Drago, Ruslan Yermakov","submitted_at":"2021-09-03T13:42:30Z","abstract_excerpt":"Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines. We show that fine-tuned transformers are able to generate realistic, multisentence text from data in the biomedical domain, yet have important limitations. We also release a new dataset (BioLeaflets) for benchmarking D2T generation models in the biomedical domain."},"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":"2109.01518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-03T13:42:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b8a2be6fb0745945ee985dc4371616dc23223e02f62d25c5b91b78b487c57ae5","abstract_canon_sha256":"fa8aca4f51cb22f036b3aa68bb1001b510c96157f593e45c8a07f010aa14863b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:19.237943Z","signature_b64":"pHlBPh1w52q1HO8awDa8gZ9/At3TpWsuqf+g5Bpu31c0kkjCXkJkL/gyULnVWCa2opJ1IGu2rDIAo1jnT/bwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","last_reissued_at":"2026-07-05T03:11:19.237601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:19.237601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Biomedical Data-to-Text Generation via Fine-Tuning Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Angelo Ziletti, Nicholas Drago, Ruslan Yermakov","submitted_at":"2021-09-03T13:42:30Z","abstract_excerpt":"Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines. We show that fine-tuned transformers are able to generate realistic, multisentence text from data in the biomedical domain, yet have important limitations. We also release a new dataset (BioLeaflets) for benchmarking D2T generation models in the biomedical domain."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01518","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/2109.01518/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":"2109.01518","created_at":"2026-07-05T03:11:19.237664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01518v1","created_at":"2026-07-05T03:11:19.237664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01518","created_at":"2026-07-05T03:11:19.237664+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2RWDRRSUVIP","created_at":"2026-07-05T03:11:19.237664+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2RWDRRSUVIPVUBB","created_at":"2026-07-05T03:11:19.237664+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2RWDRRS","created_at":"2026-07-05T03:11:19.237664+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/O2RWDRRSUVIPVUBBGEA2BFCQLA","json":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA.json","graph_json":"https://pith.science/api/pith-number/O2RWDRRSUVIPVUBBGEA2BFCQLA/graph.json","events_json":"https://pith.science/api/pith-number/O2RWDRRSUVIPVUBBGEA2BFCQLA/events.json","paper":"https://pith.science/paper/O2RWDRRS"},"agent_actions":{"view_html":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA","download_json":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA.json","view_paper":"https://pith.science/paper/O2RWDRRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01518&json=true","fetch_graph":"https://pith.science/api/pith-number/O2RWDRRSUVIPVUBBGEA2BFCQLA/graph.json","fetch_events":"https://pith.science/api/pith-number/O2RWDRRSUVIPVUBBGEA2BFCQLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/action/storage_attestation","attest_author":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/action/author_attestation","sign_citation":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/action/citation_signature","submit_replication":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/action/replication_record"}},"created_at":"2026-07-05T03:11:19.237664+00:00","updated_at":"2026-07-05T03:11:19.237664+00:00"}