{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HORBMMMM4VT6OIEGMWRAENB763","short_pith_number":"pith:HORBMMMM","schema_version":"1.0","canonical_sha256":"3ba216318ce567e7208665a202343ff6e3b123aa56aa06a43d92e8ade56ce1ce","source":{"kind":"arxiv","id":"2307.04412","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Biomedical Text Summarization and Question-Answering: On the Utility of Domain-Specific Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dima Galat, Marian-Andrei Rizoiu","submitted_at":"2023-07-10T08:32:45Z","abstract_excerpt":"Biomedical summarization requires large datasets to train for text generation. We show that while transfer learning offers a viable option for addressing this challenge, an in-domain pre-training does not always offer advantages in a BioASQ summarization task. We identify a suitable model architecture and use it to show a benefit of a general-domain pre-training followed by a task-specific fine-tuning in the context of a BioASQ summarization task, leading to a novel three-step fine-tuning approach that works with only a thousand in-domain examples. Our results indicate that a Large Language Mo"},"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":"2307.04412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-10T08:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"e64a6de3c7c659fb50731941261ada86d463183a6849e6b8bb8e4f2b61bf59c7","abstract_canon_sha256":"d114c8ab17029b27346e5be342d9707749fbd33f9653323472bb1b66fcde38e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:12.846965Z","signature_b64":"tAdp2TVUWBHPTva/5CXoC25b1zGNJ4iNBbsijQeWE0L+A8aS5wnS1yykUTHwXK98YubovUuMYC7ehycQNc4LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba216318ce567e7208665a202343ff6e3b123aa56aa06a43d92e8ade56ce1ce","last_reissued_at":"2026-07-05T06:29:12.846519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:12.846519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Biomedical Text Summarization and Question-Answering: On the Utility of Domain-Specific Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dima Galat, Marian-Andrei Rizoiu","submitted_at":"2023-07-10T08:32:45Z","abstract_excerpt":"Biomedical summarization requires large datasets to train for text generation. We show that while transfer learning offers a viable option for addressing this challenge, an in-domain pre-training does not always offer advantages in a BioASQ summarization task. We identify a suitable model architecture and use it to show a benefit of a general-domain pre-training followed by a task-specific fine-tuning in the context of a BioASQ summarization task, leading to a novel three-step fine-tuning approach that works with only a thousand in-domain examples. Our results indicate that a Large Language Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04412","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/2307.04412/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":"2307.04412","created_at":"2026-07-05T06:29:12.846580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04412v1","created_at":"2026-07-05T06:29:12.846580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04412","created_at":"2026-07-05T06:29:12.846580+00:00"},{"alias_kind":"pith_short_12","alias_value":"HORBMMMM4VT6","created_at":"2026-07-05T06:29:12.846580+00:00"},{"alias_kind":"pith_short_16","alias_value":"HORBMMMM4VT6OIEG","created_at":"2026-07-05T06:29:12.846580+00:00"},{"alias_kind":"pith_short_8","alias_value":"HORBMMMM","created_at":"2026-07-05T06:29:12.846580+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/HORBMMMM4VT6OIEGMWRAENB763","json":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763.json","graph_json":"https://pith.science/api/pith-number/HORBMMMM4VT6OIEGMWRAENB763/graph.json","events_json":"https://pith.science/api/pith-number/HORBMMMM4VT6OIEGMWRAENB763/events.json","paper":"https://pith.science/paper/HORBMMMM"},"agent_actions":{"view_html":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763","download_json":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763.json","view_paper":"https://pith.science/paper/HORBMMMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04412&json=true","fetch_graph":"https://pith.science/api/pith-number/HORBMMMM4VT6OIEGMWRAENB763/graph.json","fetch_events":"https://pith.science/api/pith-number/HORBMMMM4VT6OIEGMWRAENB763/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763/action/storage_attestation","attest_author":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763/action/author_attestation","sign_citation":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763/action/citation_signature","submit_replication":"https://pith.science/pith/HORBMMMM4VT6OIEGMWRAENB763/action/replication_record"}},"created_at":"2026-07-05T06:29:12.846580+00:00","updated_at":"2026-07-05T06:29:12.846580+00:00"}