{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L57KJVMGFERUHUQ6ZLRZL35JLO","short_pith_number":"pith:L57KJVMG","canonical_record":{"source":{"id":"2406.06455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T16:44:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55ee6e8077ec80618b510d36dc9e4a169825220eb4a389053bddd79e0b2e85b2","abstract_canon_sha256":"46b640d95cd7c7a12173ae874ea173463702d226c9e165796e3760b4b2bb7496"},"schema_version":"1.0"},"canonical_sha256":"5f7ea4d586292343d21ecae395efa95ba6762e41ab78ec3d09f7c92c25a4e095","source":{"kind":"arxiv","id":"2406.06455","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06455","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06455v2","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06455","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"L57KJVMGFERU","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"L57KJVMGFERUHUQ6","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"L57KJVMG","created_at":"2026-07-05T08:31:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L57KJVMGFERUHUQ6ZLRZL35JLO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T16:44:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55ee6e8077ec80618b510d36dc9e4a169825220eb4a389053bddd79e0b2e85b2","abstract_canon_sha256":"46b640d95cd7c7a12173ae874ea173463702d226c9e165796e3760b4b2bb7496"},"schema_version":"1.0"},"canonical_sha256":"5f7ea4d586292343d21ecae395efa95ba6762e41ab78ec3d09f7c92c25a4e095","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:52.572651Z","signature_b64":"qpzoTug8kKOkWk6Q1N0NqHgduQvBJ4Nw0f/WkuA++qYIcJEwsoFM/WMRoUEgjE6kJ5cM0ElbSiq/+Ex/7akDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f7ea4d586292343d21ecae395efa95ba6762e41ab78ec3d09f7c92c25a4e095","last_reissued_at":"2026-07-05T08:31:52.572126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:52.572126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06455","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":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwJNtfuWM6bpuIzn4bA3EVjq0T9uEuNG9hUpEtFtcphAz5gDn88HjmMPu3OTx5M5Jx7rnrvsBef7g8EUuCtrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:44:14.437823Z"},"content_sha256":"0f72a8c3b720026edc174b305b49328365392c030e3259b56a97b0738c17de7b","schema_version":"1.0","event_id":"sha256:0f72a8c3b720026edc174b305b49328365392c030e3259b56a97b0738c17de7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L57KJVMGFERUHUQ6ZLRZL35JLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large Language Model Pipeline for Breast Cancer Oncology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dennis Trujillo, Tristen Pool","submitted_at":"2024-06-10T16:44:48Z","abstract_excerpt":"Large language models (LLMs) have demonstrated potential in the innovation of many disciplines. However, how they can best be developed for oncology remains underdeveloped. State-of-the-art OpenAI models were fine-tuned on a clinical dataset and clinical guidelines text corpus for two important cancer treatment factors, adjuvant radiation therapy and chemotherapy, using a novel Langchain prompt engineering pipeline. A high accuracy (0.85+) was achieved in the classification of adjuvant radiation therapy and chemotherapy for breast cancer patients. Furthermore, a confidence interval was formed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06455","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/2406.06455/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":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U59+M2CU0UFmexazWtffK5apRguBLyByoaPQRi6qJFe/6aWvx2M8g1im3GrJcido6cNzLTqNlp5cZPumhHbGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:44:14.438214Z"},"content_sha256":"1407c99455e1ec21604325a1f43052587b121f4273822b4517bf21e3901ff195","schema_version":"1.0","event_id":"sha256:1407c99455e1ec21604325a1f43052587b121f4273822b4517bf21e3901ff195"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/bundle.json","state_url":"https://pith.science/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/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":"2026-08-22T15:44:14Z","links":{"resolver":"https://pith.science/pith/L57KJVMGFERUHUQ6ZLRZL35JLO","bundle":"https://pith.science/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/bundle.json","state":"https://pith.science/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L57KJVMGFERUHUQ6ZLRZL35JLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L57KJVMGFERUHUQ6ZLRZL35JLO","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":"46b640d95cd7c7a12173ae874ea173463702d226c9e165796e3760b4b2bb7496","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T16:44:48Z","title_canon_sha256":"55ee6e8077ec80618b510d36dc9e4a169825220eb4a389053bddd79e0b2e85b2"},"schema_version":"1.0","source":{"id":"2406.06455","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06455","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06455v2","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06455","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"L57KJVMGFERU","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"L57KJVMGFERUHUQ6","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"L57KJVMG","created_at":"2026-07-05T08:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:1407c99455e1ec21604325a1f43052587b121f4273822b4517bf21e3901ff195","target":"graph","created_at":"2026-07-05T08:31:52Z","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/2406.06455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated potential in the innovation of many disciplines. However, how they can best be developed for oncology remains underdeveloped. State-of-the-art OpenAI models were fine-tuned on a clinical dataset and clinical guidelines text corpus for two important cancer treatment factors, adjuvant radiation therapy and chemotherapy, using a novel Langchain prompt engineering pipeline. A high accuracy (0.85+) was achieved in the classification of adjuvant radiation therapy and chemotherapy for breast cancer patients. Furthermore, a confidence interval was formed ","authors_text":"Dennis Trujillo, Tristen Pool","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T16:44:48Z","title":"A Large Language Model Pipeline for Breast Cancer Oncology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06455","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":"sha256:0f72a8c3b720026edc174b305b49328365392c030e3259b56a97b0738c17de7b","target":"record","created_at":"2026-07-05T08:31:52Z","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":"46b640d95cd7c7a12173ae874ea173463702d226c9e165796e3760b4b2bb7496","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T16:44:48Z","title_canon_sha256":"55ee6e8077ec80618b510d36dc9e4a169825220eb4a389053bddd79e0b2e85b2"},"schema_version":"1.0","source":{"id":"2406.06455","kind":"arxiv","version":2}},"canonical_sha256":"5f7ea4d586292343d21ecae395efa95ba6762e41ab78ec3d09f7c92c25a4e095","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f7ea4d586292343d21ecae395efa95ba6762e41ab78ec3d09f7c92c25a4e095","first_computed_at":"2026-07-05T08:31:52.572126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:52.572126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpzoTug8kKOkWk6Q1N0NqHgduQvBJ4Nw0f/WkuA++qYIcJEwsoFM/WMRoUEgjE6kJ5cM0ElbSiq/+Ex/7akDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:52.572651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06455","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f72a8c3b720026edc174b305b49328365392c030e3259b56a97b0738c17de7b","sha256:1407c99455e1ec21604325a1f43052587b121f4273822b4517bf21e3901ff195"],"state_sha256":"237e58c60f6b3e5fa58e2d94a70671151d2e39f0fa701c9f585f8d660faa9361"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EeJqeKagbtWf+bGNjX+aQduRVWR1sVGgms8OluWivho12zSJ7rk9NSj2hNf0cvQUe6olQl0eMJwLO0dyv1hGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:44:14.441083Z","bundle_sha256":"e610877351f4ec8d3fc94efe0a8022d86e2d519260ccfbcab2b173f558bb047d"}}