{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AZV5GUFA4PDUIYFEWILTXX3AAW","short_pith_number":"pith:AZV5GUFA","canonical_record":{"source":{"id":"2406.10459","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T01:02:48Z","cross_cats_sorted":[],"title_canon_sha256":"7a4f20eeca62e9f0140687ab6b9a21f3c5ff9423efb2c889b4707373c3a10f2d","abstract_canon_sha256":"8a400c89025c5aed171f63df29b0eb33b5c51d584ce4258d242374c07e2be970"},"schema_version":"1.0"},"canonical_sha256":"066bd350a0e3c74460a4b2173bdf6005ab20ad15f19ffc983b62615cec27e323","source":{"kind":"arxiv","id":"2406.10459","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10459","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10459v3","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10459","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"AZV5GUFA4PDU","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"AZV5GUFA4PDUIYFE","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"AZV5GUFA","created_at":"2026-07-05T10:42:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AZV5GUFA4PDUIYFEWILTXX3AAW","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10459","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T01:02:48Z","cross_cats_sorted":[],"title_canon_sha256":"7a4f20eeca62e9f0140687ab6b9a21f3c5ff9423efb2c889b4707373c3a10f2d","abstract_canon_sha256":"8a400c89025c5aed171f63df29b0eb33b5c51d584ce4258d242374c07e2be970"},"schema_version":"1.0"},"canonical_sha256":"066bd350a0e3c74460a4b2173bdf6005ab20ad15f19ffc983b62615cec27e323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:11.716634Z","signature_b64":"VZxiGTJrM36nlW+OoNBfF/5zH1F9dnbYh1edW0uaIhXW62LnMAJT+jo8Zo/D0FwHs+Y4Bsrf6hbr8is6T3oMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"066bd350a0e3c74460a4b2173bdf6005ab20ad15f19ffc983b62615cec27e323","last_reissued_at":"2026-07-05T10:42:11.715993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:11.715993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10459","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGqqLkMuhuVlo1qkiQXUZ43u3/gZHaWnwP6uIdC2vPcctyp24+8tEFh5fIDR4ZeKbujBfHbCwJK59tEd2Ox7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:27.318076Z"},"content_sha256":"386d030267d33ae823294068d9a224b33aa34d60da0c8b76926c43056c354d97","schema_version":"1.0","event_id":"sha256:386d030267d33ae823294068d9a224b33aa34d60da0c8b76926c43056c354d97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AZV5GUFA4PDUIYFEWILTXX3AAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CancerLLM: A Large Language Model in Cancer Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Blaes, Hongfang Liu, Hua Xu, Jeremy Yeung, Jiatan Huang, Mingchen Li, Rui Zhang, Steven Johnson","submitted_at":"2024-06-15T01:02:48Z","abstract_excerpt":"Medical Large Language Models (LLMs) have demonstrated impressive performance on a wide variety of medical NLP tasks; however, there still lacks a LLM specifically designed for phenotyping identification and diagnosis in cancer domain. Moreover, these LLMs typically have several billions of parameters, making them computationally expensive for healthcare systems. Thus, in this study, we propose CancerLLM, a model with 7 billion parameters and a Mistral-style architecture, pre-trained on nearly 2.7M clinical notes and over 515K pathology reports covering 17 cancer types, followed by fine-tuning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10459","kind":"arxiv","version":3},"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/2406.10459/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":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIX/z+1TOaQTConl04F+euehWB8qeUIfyfaUXPh4+8deXfSs/npAcy57KKWpwb6BSyqrrjLWj+i9M+32lIODAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:27.318469Z"},"content_sha256":"b6734f2b372266f7a388112f43585b67e60ead7f403ef0547ad1a24d4ea33e43","schema_version":"1.0","event_id":"sha256:b6734f2b372266f7a388112f43585b67e60ead7f403ef0547ad1a24d4ea33e43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/bundle.json","state_url":"https://pith.science/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/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":"2026-07-06T18:08:27Z","links":{"resolver":"https://pith.science/pith/AZV5GUFA4PDUIYFEWILTXX3AAW","bundle":"https://pith.science/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/bundle.json","state":"https://pith.science/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZV5GUFA4PDUIYFEWILTXX3AAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZV5GUFA4PDUIYFEWILTXX3AAW","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":"8a400c89025c5aed171f63df29b0eb33b5c51d584ce4258d242374c07e2be970","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T01:02:48Z","title_canon_sha256":"7a4f20eeca62e9f0140687ab6b9a21f3c5ff9423efb2c889b4707373c3a10f2d"},"schema_version":"1.0","source":{"id":"2406.10459","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10459","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10459v3","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10459","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"AZV5GUFA4PDU","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"AZV5GUFA4PDUIYFE","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"AZV5GUFA","created_at":"2026-07-05T10:42:11Z"}],"graph_snapshots":[{"event_id":"sha256:b6734f2b372266f7a388112f43585b67e60ead7f403ef0547ad1a24d4ea33e43","target":"graph","created_at":"2026-07-05T10:42:11Z","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/2406.10459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Medical Large Language Models (LLMs) have demonstrated impressive performance on a wide variety of medical NLP tasks; however, there still lacks a LLM specifically designed for phenotyping identification and diagnosis in cancer domain. Moreover, these LLMs typically have several billions of parameters, making them computationally expensive for healthcare systems. Thus, in this study, we propose CancerLLM, a model with 7 billion parameters and a Mistral-style architecture, pre-trained on nearly 2.7M clinical notes and over 515K pathology reports covering 17 cancer types, followed by fine-tuning","authors_text":"Anne Blaes, Hongfang Liu, Hua Xu, Jeremy Yeung, Jiatan Huang, Mingchen Li, Rui Zhang, Steven Johnson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T01:02:48Z","title":"CancerLLM: A Large Language Model in Cancer Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10459","kind":"arxiv","version":3},"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":"sha256:386d030267d33ae823294068d9a224b33aa34d60da0c8b76926c43056c354d97","target":"record","created_at":"2026-07-05T10:42:11Z","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":"8a400c89025c5aed171f63df29b0eb33b5c51d584ce4258d242374c07e2be970","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T01:02:48Z","title_canon_sha256":"7a4f20eeca62e9f0140687ab6b9a21f3c5ff9423efb2c889b4707373c3a10f2d"},"schema_version":"1.0","source":{"id":"2406.10459","kind":"arxiv","version":3}},"canonical_sha256":"066bd350a0e3c74460a4b2173bdf6005ab20ad15f19ffc983b62615cec27e323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"066bd350a0e3c74460a4b2173bdf6005ab20ad15f19ffc983b62615cec27e323","first_computed_at":"2026-07-05T10:42:11.715993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:11.715993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VZxiGTJrM36nlW+OoNBfF/5zH1F9dnbYh1edW0uaIhXW62LnMAJT+jo8Zo/D0FwHs+Y4Bsrf6hbr8is6T3oMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:11.716634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10459","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:386d030267d33ae823294068d9a224b33aa34d60da0c8b76926c43056c354d97","sha256:b6734f2b372266f7a388112f43585b67e60ead7f403ef0547ad1a24d4ea33e43"],"state_sha256":"ae2ddbc1edc9891ac8bb3dad4d465e3e93be5ac6f9213c34c3f885fe845c0ead"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqHrj2OywmZKup6niEbjp7d4JoxHAYHVCyZGFLzxBvmWSXKkLOwKvnYlozfowr8KR9sqXi3NLROWFq7Nsd/ABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:08:27.320454Z","bundle_sha256":"79f37ab7eb160ee254bf06a044cf1f5aeefbf598f2a21f07c35e8d923f1650b4"}}