{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7DG33EB6ZI45RNZ6XT42JTTWOX","short_pith_number":"pith:7DG33EB6","canonical_record":{"source":{"id":"2409.16563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T02:29:44Z","cross_cats_sorted":[],"title_canon_sha256":"1902fbc4c07d0021175de4c99352a2f842a5d1cc4e71e0143bbd45f6d9cb99e6","abstract_canon_sha256":"b102bc156ce0f9bd87e9822913d58c87f861eba402663e9214328d505ef3b70f"},"schema_version":"1.0"},"canonical_sha256":"f8cdbd903eca39d8b73ebcf9a4ce7675f4b9fcba8f9122ed662c15f5e2938f56","source":{"kind":"arxiv","id":"2409.16563","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16563","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16563v1","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16563","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"7DG33EB6ZI45","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"7DG33EB6ZI45RNZ6","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"7DG33EB6","created_at":"2026-07-05T09:11:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7DG33EB6ZI45RNZ6XT42JTTWOX","target":"record","payload":{"canonical_record":{"source":{"id":"2409.16563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T02:29:44Z","cross_cats_sorted":[],"title_canon_sha256":"1902fbc4c07d0021175de4c99352a2f842a5d1cc4e71e0143bbd45f6d9cb99e6","abstract_canon_sha256":"b102bc156ce0f9bd87e9822913d58c87f861eba402663e9214328d505ef3b70f"},"schema_version":"1.0"},"canonical_sha256":"f8cdbd903eca39d8b73ebcf9a4ce7675f4b9fcba8f9122ed662c15f5e2938f56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:35.834153Z","signature_b64":"ycqLAdqKQtnDlgD2S9mGwtEpSDcp9AWPLCats/ilaCVK7G0BwLpR3pWrVI9A5lO5kffdxduKL0pO54EbgLgZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8cdbd903eca39d8b73ebcf9a4ce7675f4b9fcba8f9122ed662c15f5e2938f56","last_reissued_at":"2026-07-05T09:11:35.833679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:35.833679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.16563","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":"2026-07-05T09:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9mBPqTlNGGEqkq8/05sPMZjxecM676pnYVKdbh7nd4T8BNIisEUJLFQPGXMTCKUkm2cvELbNkrc0bptCo4vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:30.023488Z"},"content_sha256":"01b14ae6339f6839a9bfec1fd15948f78b530263ac5c248af2a3be152fee3a2f","schema_version":"1.0","event_id":"sha256:01b14ae6339f6839a9bfec1fd15948f78b530263ac5c248af2a3be152fee3a2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7DG33EB6ZI45RNZ6XT42JTTWOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Flanders, George Shih, Hanley Ong, Xindi Wang, Yifan Peng, Yiliang Zhou, Yishu Wei","submitted_at":"2024-09-25T02:29:44Z","abstract_excerpt":"Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4- o), L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16563","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/2409.16563/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":"2026-07-05T09:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPm1cfOpS4xlxAvPcQIoUagN7AZcTuB1dxZ7CNWuSwEvmkTf2px9Ie+TzN3sUH1dx1TkqhDiVRfzbNueVahWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:30.023996Z"},"content_sha256":"6148443c04593f1f75e73be85f5b54b920d781db4917cf96ceadccd787e879ba","schema_version":"1.0","event_id":"sha256:6148443c04593f1f75e73be85f5b54b920d781db4917cf96ceadccd787e879ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/bundle.json","state_url":"https://pith.science/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/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":"2026-08-07T22:41:30Z","links":{"resolver":"https://pith.science/pith/7DG33EB6ZI45RNZ6XT42JTTWOX","bundle":"https://pith.science/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/bundle.json","state":"https://pith.science/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DG33EB6ZI45RNZ6XT42JTTWOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7DG33EB6ZI45RNZ6XT42JTTWOX","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":"b102bc156ce0f9bd87e9822913d58c87f861eba402663e9214328d505ef3b70f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T02:29:44Z","title_canon_sha256":"1902fbc4c07d0021175de4c99352a2f842a5d1cc4e71e0143bbd45f6d9cb99e6"},"schema_version":"1.0","source":{"id":"2409.16563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16563","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16563v1","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16563","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"7DG33EB6ZI45","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"7DG33EB6ZI45RNZ6","created_at":"2026-07-05T09:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"7DG33EB6","created_at":"2026-07-05T09:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:6148443c04593f1f75e73be85f5b54b920d781db4917cf96ceadccd787e879ba","target":"graph","created_at":"2026-07-05T09:11:35Z","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/2409.16563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4- o), L","authors_text":"Adam Flanders, George Shih, Hanley Ong, Xindi Wang, Yifan Peng, Yiliang Zhou, Yishu Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T02:29:44Z","title":"Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16563","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":"sha256:01b14ae6339f6839a9bfec1fd15948f78b530263ac5c248af2a3be152fee3a2f","target":"record","created_at":"2026-07-05T09:11:35Z","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":"b102bc156ce0f9bd87e9822913d58c87f861eba402663e9214328d505ef3b70f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T02:29:44Z","title_canon_sha256":"1902fbc4c07d0021175de4c99352a2f842a5d1cc4e71e0143bbd45f6d9cb99e6"},"schema_version":"1.0","source":{"id":"2409.16563","kind":"arxiv","version":1}},"canonical_sha256":"f8cdbd903eca39d8b73ebcf9a4ce7675f4b9fcba8f9122ed662c15f5e2938f56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8cdbd903eca39d8b73ebcf9a4ce7675f4b9fcba8f9122ed662c15f5e2938f56","first_computed_at":"2026-07-05T09:11:35.833679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:35.833679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ycqLAdqKQtnDlgD2S9mGwtEpSDcp9AWPLCats/ilaCVK7G0BwLpR3pWrVI9A5lO5kffdxduKL0pO54EbgLgZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:35.834153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01b14ae6339f6839a9bfec1fd15948f78b530263ac5c248af2a3be152fee3a2f","sha256:6148443c04593f1f75e73be85f5b54b920d781db4917cf96ceadccd787e879ba"],"state_sha256":"7f24eb2f61fdaa272f8028d6f152209728ea204f71415fbe8d77310300c79c25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzMYKHFgdsAC+xPBiluo2u6ifC+/mZpLrjNuWE95ghPqEJn7xdHRNZzaNJURrM5xahXiqHGMVrPkpLU5C9HdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:41:30.027652Z","bundle_sha256":"36d96ad80ed046253aeb466edda74724971b774587029653aeb188a7175068ca"}}