{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:O2RWDRRSUVIPVUBBGEA2BFCQLA","short_pith_number":"pith:O2RWDRRS","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"},"canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","source":{"kind":"arxiv","id":"2109.01518","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01518","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01518v1","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01518","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"O2RWDRRSUVIP","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"O2RWDRRSUVIPVUBB","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"O2RWDRRS","created_at":"2026-07-05T03:11:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:O2RWDRRSUVIPVUBBGEA2BFCQLA","target":"record","payload":{"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"},"canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","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"},"source_kind":"arxiv","source_id":"2109.01518","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6Y2eSVwsHrKjCWZtB+dcFwr0DFOteJbdP2nPeuqwiBpNvBsbF1hIJDdhqXQNdKi1ptH2DqXIpSY50fRdI3WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:02:14.386187Z"},"content_sha256":"003b14843a22a6ad44d5f6ff283c5aa9bc7c2f41baab550d98a3eb3ccdc56a8f","schema_version":"1.0","event_id":"sha256:003b14843a22a6ad44d5f6ff283c5aa9bc7c2f41baab550d98a3eb3ccdc56a8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:O2RWDRRSUVIPVUBBGEA2BFCQLA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C93EK839L3F2Pd4ZNDLFq6N1pXUy645Ke54ow7qOHiiNQIsNX60wo2up3L38In+X3Aw9LNcPIkEBTCpYRupoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:02:14.386568Z"},"content_sha256":"c2c6065ef4d9fa3ad6cdf5eb604ce69c8d998d646d6ef17101bdea8933657014","schema_version":"1.0","event_id":"sha256:c2c6065ef4d9fa3ad6cdf5eb604ce69c8d998d646d6ef17101bdea8933657014"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/bundle.json","state_url":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T09:02:14Z","links":{"resolver":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA","bundle":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/bundle.json","state":"https://pith.science/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2RWDRRSUVIPVUBBGEA2BFCQLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:O2RWDRRSUVIPVUBBGEA2BFCQLA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fa8aca4f51cb22f036b3aa68bb1001b510c96157f593e45c8a07f010aa14863b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-03T13:42:30Z","title_canon_sha256":"b8a2be6fb0745945ee985dc4371616dc23223e02f62d25c5b91b78b487c57ae5"},"schema_version":"1.0","source":{"id":"2109.01518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01518","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01518v1","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01518","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"O2RWDRRSUVIP","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"O2RWDRRSUVIPVUBB","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"O2RWDRRS","created_at":"2026-07-05T03:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:c2c6065ef4d9fa3ad6cdf5eb604ce69c8d998d646d6ef17101bdea8933657014","target":"graph","created_at":"2026-07-05T03:11:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.01518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Angelo Ziletti, Nicholas Drago, Ruslan Yermakov","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-03T13:42:30Z","title":"Biomedical Data-to-Text Generation via Fine-Tuning Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01518","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:003b14843a22a6ad44d5f6ff283c5aa9bc7c2f41baab550d98a3eb3ccdc56a8f","target":"record","created_at":"2026-07-05T03:11:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fa8aca4f51cb22f036b3aa68bb1001b510c96157f593e45c8a07f010aa14863b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-03T13:42:30Z","title_canon_sha256":"b8a2be6fb0745945ee985dc4371616dc23223e02f62d25c5b91b78b487c57ae5"},"schema_version":"1.0","source":{"id":"2109.01518","kind":"arxiv","version":1}},"canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76a361c632a550fad0213101a09450581cc058032d45a49875ab7c66b2cb6b39","first_computed_at":"2026-07-05T03:11:19.237601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:19.237601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHlBPh1w52q1HO8awDa8gZ9/At3TpWsuqf+g5Bpu31c0kkjCXkJkL/gyULnVWCa2opJ1IGu2rDIAo1jnT/bwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:19.237943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:003b14843a22a6ad44d5f6ff283c5aa9bc7c2f41baab550d98a3eb3ccdc56a8f","sha256:c2c6065ef4d9fa3ad6cdf5eb604ce69c8d998d646d6ef17101bdea8933657014"],"state_sha256":"cac58e325a0b73377924847fcf7067b752952acd47dfb8e06af1a443d3e0d84f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzlHTCgE1m9Fd+i/Av5xUhpn5AvEbBkg9vMvm0nwML8+lB3BhKMAkID8+is8Z6rWd28Vh9VGmEFxB8tPrcuyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:02:14.388591Z","bundle_sha256":"04c4e3e456d7cf5450d8c35e8f0be0c18e6a8f628150badd01fe0d7cb73467db"}}