{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KLYOSW5QGWFOTDECRXEY76GLZE","short_pith_number":"pith:KLYOSW5Q","canonical_record":{"source":{"id":"2408.04775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T22:18:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"164f337c016789d3fb9a9e5cfc1d8ea7424847606ad53e745a55000fbd516726","abstract_canon_sha256":"7909d343c6917faa073688a8850cf9030cecf0eb3fc3e7cbe738d0f4f9bfc868"},"schema_version":"1.0"},"canonical_sha256":"52f0e95bb0358ae98c828dc98ff8cbc9265515427456db35ca5b36849b252856","source":{"kind":"arxiv","id":"2408.04775","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04775","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04775v1","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04775","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"KLYOSW5QGWFO","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"KLYOSW5QGWFOTDEC","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"KLYOSW5Q","created_at":"2026-07-05T08:53:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KLYOSW5QGWFOTDECRXEY76GLZE","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T22:18:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"164f337c016789d3fb9a9e5cfc1d8ea7424847606ad53e745a55000fbd516726","abstract_canon_sha256":"7909d343c6917faa073688a8850cf9030cecf0eb3fc3e7cbe738d0f4f9bfc868"},"schema_version":"1.0"},"canonical_sha256":"52f0e95bb0358ae98c828dc98ff8cbc9265515427456db35ca5b36849b252856","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:43.926946Z","signature_b64":"/ne4WEYd0yPdXnJc+k6Mc09R/D/qbLEczcaZSfkiulDMOdZ0xw9qKU2qOcveQFIDfscQnXBhy98f8tc7SdOdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f0e95bb0358ae98c828dc98ff8cbc9265515427456db35ca5b36849b252856","last_reissued_at":"2026-07-05T08:53:43.926409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:43.926409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04775","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":"2026-07-05T08:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAPtROROO5xZfgQgw29KJhEgDQGxyiptgrtPXPGz4OaWSLXb/jDpWXN1bvvUNHgX/OraDvOUpD/EpsL70uisCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:38:21.890828Z"},"content_sha256":"e1fcdfc75d44951d02e7f8733a12b6c80ed34b16043cb48bb70d7f151f5043a3","schema_version":"1.0","event_id":"sha256:e1fcdfc75d44951d02e7f8733a12b6c80ed34b16043cb48bb70d7f151f5043a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KLYOSW5QGWFOTDECRXEY76GLZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ahmed I. Ghanem, Benjamin Movsas, Bing Luo, Hassan Bagher-Ebadian, Indrin J. Chetty, Kundan Thind, Kyle Verdecchia, Mohamed Elshaikh, Mohammad M. Ghassemi, Reza Khanmohammadi, Ryan Hall, Tuka Alhanai","submitted_at":"2024-08-08T22:18:01Z","abstract_excerpt":"Large Language Models (LLMs) offer significant potential for clinical symptom extraction, but their deployment in healthcare settings is constrained by privacy concerns, computational limitations, and operational costs. This study investigates the optimization of compact LLMs for cancer toxicity symptom extraction using a novel iterative refinement approach. We employ a student-teacher architecture, utilizing Zephyr-7b-beta and Phi3-mini-128 as student models and GPT-4o as the teacher, to dynamically select between prompt refinement, Retrieval-Augmented Generation (RAG), and fine-tuning strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04775","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/2408.04775/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":"2026-07-05T08:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8Yzp5MMWcfYnmu6zFNauu8mE+R7Z2v1/sbC6T/hpH8yUphnprQATAgIOUUje/XWEJhnc0K0uLK3al05UONoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:38:21.891513Z"},"content_sha256":"f3acd6aa347af7ba41f4971a342583d66cdc92adfdb3a078b9e017ff7e67e9f3","schema_version":"1.0","event_id":"sha256:f3acd6aa347af7ba41f4971a342583d66cdc92adfdb3a078b9e017ff7e67e9f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLYOSW5QGWFOTDECRXEY76GLZE/bundle.json","state_url":"https://pith.science/pith/KLYOSW5QGWFOTDECRXEY76GLZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLYOSW5QGWFOTDECRXEY76GLZE/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":"2026-07-12T14:38:21Z","links":{"resolver":"https://pith.science/pith/KLYOSW5QGWFOTDECRXEY76GLZE","bundle":"https://pith.science/pith/KLYOSW5QGWFOTDECRXEY76GLZE/bundle.json","state":"https://pith.science/pith/KLYOSW5QGWFOTDECRXEY76GLZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLYOSW5QGWFOTDECRXEY76GLZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KLYOSW5QGWFOTDECRXEY76GLZE","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":"7909d343c6917faa073688a8850cf9030cecf0eb3fc3e7cbe738d0f4f9bfc868","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T22:18:01Z","title_canon_sha256":"164f337c016789d3fb9a9e5cfc1d8ea7424847606ad53e745a55000fbd516726"},"schema_version":"1.0","source":{"id":"2408.04775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04775","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04775v1","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04775","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"KLYOSW5QGWFO","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"KLYOSW5QGWFOTDEC","created_at":"2026-07-05T08:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"KLYOSW5Q","created_at":"2026-07-05T08:53:43Z"}],"graph_snapshots":[{"event_id":"sha256:f3acd6aa347af7ba41f4971a342583d66cdc92adfdb3a078b9e017ff7e67e9f3","target":"graph","created_at":"2026-07-05T08:53:43Z","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/2408.04775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) offer significant potential for clinical symptom extraction, but their deployment in healthcare settings is constrained by privacy concerns, computational limitations, and operational costs. This study investigates the optimization of compact LLMs for cancer toxicity symptom extraction using a novel iterative refinement approach. We employ a student-teacher architecture, utilizing Zephyr-7b-beta and Phi3-mini-128 as student models and GPT-4o as the teacher, to dynamically select between prompt refinement, Retrieval-Augmented Generation (RAG), and fine-tuning strate","authors_text":"Ahmed I. Ghanem, Benjamin Movsas, Bing Luo, Hassan Bagher-Ebadian, Indrin J. Chetty, Kundan Thind, Kyle Verdecchia, Mohamed Elshaikh, Mohammad M. Ghassemi, Reza Khanmohammadi, Ryan Hall, Tuka Alhanai","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T22:18:01Z","title":"Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04775","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:e1fcdfc75d44951d02e7f8733a12b6c80ed34b16043cb48bb70d7f151f5043a3","target":"record","created_at":"2026-07-05T08:53:43Z","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":"7909d343c6917faa073688a8850cf9030cecf0eb3fc3e7cbe738d0f4f9bfc868","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T22:18:01Z","title_canon_sha256":"164f337c016789d3fb9a9e5cfc1d8ea7424847606ad53e745a55000fbd516726"},"schema_version":"1.0","source":{"id":"2408.04775","kind":"arxiv","version":1}},"canonical_sha256":"52f0e95bb0358ae98c828dc98ff8cbc9265515427456db35ca5b36849b252856","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52f0e95bb0358ae98c828dc98ff8cbc9265515427456db35ca5b36849b252856","first_computed_at":"2026-07-05T08:53:43.926409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:43.926409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ne4WEYd0yPdXnJc+k6Mc09R/D/qbLEczcaZSfkiulDMOdZ0xw9qKU2qOcveQFIDfscQnXBhy98f8tc7SdOdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:43.926946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1fcdfc75d44951d02e7f8733a12b6c80ed34b16043cb48bb70d7f151f5043a3","sha256:f3acd6aa347af7ba41f4971a342583d66cdc92adfdb3a078b9e017ff7e67e9f3"],"state_sha256":"755767e13fa845c52701f01d991d48c77c2d37d8d5c76386b21b20ec30a14d3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QC8NMGsb8o8tbrXAuHZ1uHUoSziXXpuGJcbR0XcN1cWfbZISJWe2UyKDXHT47Yb+uOisrpwfQCKqRfFqyGACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T14:38:21.896439Z","bundle_sha256":"ae0ef7eb7937ec4a6bfe25b56d70581b9d840ce8fb3a817b45e444eb785cf3e7"}}