{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HJD5EJUYMEA2C4NUSG4LHLHLFD","short_pith_number":"pith:HJD5EJUY","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"},"canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","source":{"kind":"arxiv","id":"2405.06093","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06093","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06093v2","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06093","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"HJD5EJUYMEA2","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"HJD5EJUYMEA2C4NU","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"HJD5EJUY","created_at":"2026-07-05T08:51:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HJD5EJUYMEA2C4NUSG4LHLHLFD","target":"record","payload":{"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"},"canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","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"},"source_kind":"arxiv","source_id":"2405.06093","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKqfrTYRpOVBdax4crUtHj8yithQ13fIB6TFh8iqXApR6eFvL2oSYdqSBUYCe+Q31gP2zTapqF6hN1j5xa8SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:09:44.235438Z"},"content_sha256":"0bcfa0a4e479c0074a893be90f6d7cc87243644429e5c3466f32a41161cf8f20","schema_version":"1.0","event_id":"sha256:0bcfa0a4e479c0074a893be90f6d7cc87243644429e5c3466f32a41161cf8f20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HJD5EJUYMEA2C4NUSG4LHLHLFD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b+oMpoAD9+mlmTWwPT8IGUuLJW3xH1bVKNieFMScOygvFytrYoBHAFGJ5CI5RoDtmXplzLVWRPBDAUTUaFBtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:09:44.235973Z"},"content_sha256":"ae5d1a1d9e597b3ea1ce79f766586c6bac2b4e5102b3d92cfb11b122f7f50590","schema_version":"1.0","event_id":"sha256:ae5d1a1d9e597b3ea1ce79f766586c6bac2b4e5102b3d92cfb11b122f7f50590"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/bundle.json","state_url":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/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":"2026-08-06T08:09:44Z","links":{"resolver":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD","bundle":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/bundle.json","state":"https://pith.science/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJD5EJUYMEA2C4NUSG4LHLHLFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJD5EJUYMEA2C4NUSG4LHLHLFD","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":"d8804397f2f5fd6e7b380f565aea20b7e28de6eb7e0a01ed957f45fc4e541601","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-09T20:45:58Z","title_canon_sha256":"885084b35722289f541d9ea39731b81f93e8275ad8752e25b2e2070691489d71"},"schema_version":"1.0","source":{"id":"2405.06093","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06093","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06093v2","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06093","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"HJD5EJUYMEA2","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"HJD5EJUYMEA2C4NU","created_at":"2026-07-05T08:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"HJD5EJUY","created_at":"2026-07-05T08:51:51Z"}],"graph_snapshots":[{"event_id":"sha256:ae5d1a1d9e597b3ea1ce79f766586c6bac2b4e5102b3d92cfb11b122f7f50590","target":"graph","created_at":"2026-07-05T08:51:51Z","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/2405.06093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bhawesh Kumar, Eric Yang, Jonathan Amar, Nan Li, Yugang Jia","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-09T20:45:58Z","title":"Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06093","kind":"arxiv","version":2},"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":"sha256:0bcfa0a4e479c0074a893be90f6d7cc87243644429e5c3466f32a41161cf8f20","target":"record","created_at":"2026-07-05T08:51:51Z","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":"d8804397f2f5fd6e7b380f565aea20b7e28de6eb7e0a01ed957f45fc4e541601","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-09T20:45:58Z","title_canon_sha256":"885084b35722289f541d9ea39731b81f93e8275ad8752e25b2e2070691489d71"},"schema_version":"1.0","source":{"id":"2405.06093","kind":"arxiv","version":2}},"canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a47d226986101a171b491b8b3aceb28dcb8a5aba0474cc6d08b320340109390","first_computed_at":"2026-07-05T08:51:51.903706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:51.903706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xbtc0b+KX7UuCIPcZFdDKTiTJI51o84jBlZKMPIzV+IdYudRBKlI3b2onKVgxuLZDs2hkCPoivqDeIYqJ9yRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:51.904178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.06093","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bcfa0a4e479c0074a893be90f6d7cc87243644429e5c3466f32a41161cf8f20","sha256:ae5d1a1d9e597b3ea1ce79f766586c6bac2b4e5102b3d92cfb11b122f7f50590"],"state_sha256":"c76e6e81c516db4eb14b72bcb3deaef3e0f96064c661c290d0963204b8b9a4c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CueyA04iGOCX9zpH6b4umN0bROiDRiHXVwtXPJjI7A9P2mfBSpCsdzryvRVfDDIry6KcYuS1lixjRNT82OZ+AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:09:44.240005Z","bundle_sha256":"c02c5ebb2f08ac7cd0c09f9e566f3a9541f095d073adbfa482c849c265964175"}}