{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJD5EJUYMEA2C4NUSG4LHLHLFD","short_pith_number":"pith:HJD5EJUY","schema_version":"1.0","canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","source":{"kind":"arxiv","id":"2405.06093","version":2},"attestation_state":"computed","paper":{"title":"Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhawesh Kumar, Eric Yang, Jonathan Amar, Nan Li, Yugang Jia","submitted_at":"2024-05-09T20:45:58Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated their efficacy across a broad spectrum of tasks in healthcare applications. However, often LLMs need to be fine-tuned on task-specific expert annotated data to achieve optimal performance, which can be expensive and time consuming. In this study, we fine-tune PaLM-2 with parameter efficient fine-tuning (PEFT) using noisy labels obtained from gemini-pro 1.0 for the detection of Schedule-of-Event (SoE) tables, which specify care plan in clinical trial protocols. We introduce a filtering mechanism to select high-confidence labels for this table class"},"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":"2405.06093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-09T20:45:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"885084b35722289f541d9ea39731b81f93e8275ad8752e25b2e2070691489d71","abstract_canon_sha256":"d8804397f2f5fd6e7b380f565aea20b7e28de6eb7e0a01ed957f45fc4e541601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:51.904178Z","signature_b64":"Xbtc0b+KX7UuCIPcZFdDKTiTJI51o84jBlZKMPIzV+IdYudRBKlI3b2onKVgxuLZDs2hkCPoivqDeIYqJ9yRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","last_reissued_at":"2026-07-05T08:51:51.903706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:51.903706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhawesh Kumar, Eric Yang, Jonathan Amar, Nan Li, Yugang Jia","submitted_at":"2024-05-09T20:45:58Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated their efficacy across a broad spectrum of tasks in healthcare applications. However, often LLMs need to be fine-tuned on task-specific expert annotated data to achieve optimal performance, which can be expensive and time consuming. In this study, we fine-tune PaLM-2 with parameter efficient fine-tuning (PEFT) using noisy labels obtained from gemini-pro 1.0 for the detection of Schedule-of-Event (SoE) tables, which specify care plan in clinical trial protocols. We introduce a filtering mechanism to select high-confidence labels for this table class"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06093","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/2405.06093/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":"2405.06093","created_at":"2026-07-05T08:51:51.903769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06093v2","created_at":"2026-07-05T08:51:51.903769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06093","created_at":"2026-07-05T08:51:51.903769+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJD5EJUYMEA2","created_at":"2026-07-05T08:51:51.903769+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJD5EJUYMEA2C4NU","created_at":"2026-07-05T08:51:51.903769+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJD5EJUY","created_at":"2026-07-05T08:51:51.903769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12468","citing_title":"Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD","json":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD.json","graph_json":"https://pith.science/api/pith-number/HJD5EJUYMEA2C4NUSG4LHLHLFD/graph.json","events_json":"https://pith.science/api/pith-number/HJD5EJUYMEA2C4NUSG4LHLHLFD/events.json","paper":"https://pith.science/paper/HJD5EJUY"},"agent_actions":{"view_html":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD","download_json":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD.json","view_paper":"https://pith.science/paper/HJD5EJUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06093&json=true","fetch_graph":"https://pith.science/api/pith-number/HJD5EJUYMEA2C4NUSG4LHLHLFD/graph.json","fetch_events":"https://pith.science/api/pith-number/HJD5EJUYMEA2C4NUSG4LHLHLFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/action/storage_attestation","attest_author":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/action/author_attestation","sign_citation":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/action/citation_signature","submit_replication":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/action/replication_record"}},"created_at":"2026-07-05T08:51:51.903769+00:00","updated_at":"2026-07-05T08:51:51.903769+00:00"}