{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WMGGVN4C2NA7JRSVEESUWFXQZZ","short_pith_number":"pith:WMGGVN4C","canonical_record":{"source":{"id":"2606.17213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T18:51:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6b10b206ecb665d2019e592bc8cc70bc0a44b35161d9e865edaf40c54a5e924a","abstract_canon_sha256":"1f88951e93d55b809ca43e1809d3f22f240152422ce1b414f33d4c6ba04aa400"},"schema_version":"1.0"},"canonical_sha256":"b30c6ab782d341f4c65521254b16f0ce473719a43698472ee610be914180aca5","source":{"kind":"arxiv","id":"2606.17213","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17213","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17213v1","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17213","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"WMGGVN4C2NA7","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"WMGGVN4C2NA7JRSV","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"WMGGVN4C","created_at":"2026-06-19T16:10:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WMGGVN4C2NA7JRSVEESUWFXQZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.17213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T18:51:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6b10b206ecb665d2019e592bc8cc70bc0a44b35161d9e865edaf40c54a5e924a","abstract_canon_sha256":"1f88951e93d55b809ca43e1809d3f22f240152422ce1b414f33d4c6ba04aa400"},"schema_version":"1.0"},"canonical_sha256":"b30c6ab782d341f4c65521254b16f0ce473719a43698472ee610be914180aca5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:06.146736Z","signature_b64":"WVGQFWH+zh4Q9HPxzAI9tse6i6vbPMcQcreeE4YukL4XSNPpKzv7AbP5Nwtm5tWCb5Q5mLggPNiF5faTCFB/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b30c6ab782d341f4c65521254b16f0ce473719a43698472ee610be914180aca5","last_reissued_at":"2026-06-19T16:10:06.146292Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:06.146292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.17213","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":"2026-06-19T16:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"veDfhbllKCS+uJbGtYFN/CmiRF1sC3x1QG7V36mt7OUOrtT+rQdlzKLSCDgmDOJAUdbhxLDIzSMFyABrGoRECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:52:35.381087Z"},"content_sha256":"b1008fab39c95e2c184f9446322ed187ddd7a4aae71f19e6986c6a89f04c9bac","schema_version":"1.0","event_id":"sha256:b1008fab39c95e2c184f9446322ed187ddd7a4aae71f19e6986c6a89f04c9bac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WMGGVN4C2NA7JRSVEESUWFXQZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Andrea M. Bejar, Debesh Jha, Gorkem Durak, Halil Ertugrul Aktas, Quoc-Huy Trinh, Ulas Bagci, Vanshali Sharma","submitted_at":"2026-06-15T18:51:31Z","abstract_excerpt":"Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrated strong adaptability to natural images. However, extending their use to the medical domain, particularly for volumetric (3D) images, is challenging due to high computational complexity, volumetric dependencies and the semantic gap between visual features and clinical terminology. Naively fine-tuning LLMs on limited medical data often leads to overfitting and clinical hallucination, where linguistic fluency is prioritized over clinical factuality. In this study, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17213","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/2606.17213/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":"2026-06-19T16:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bq7z7Tyqij1dwWyBivL7/uJKhFvclS3YosPjc1Y0Grqf3Jpt4PK5VMFAlOVK4j7Vc94PMujAQJppdj72708LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:52:35.381481Z"},"content_sha256":"3181ae0d928f7cb90ade3feeddb0af2be2dde866410310326af92eabaf650b7d","schema_version":"1.0","event_id":"sha256:3181ae0d928f7cb90ade3feeddb0af2be2dde866410310326af92eabaf650b7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/bundle.json","state_url":"https://pith.science/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/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":"2026-07-03T11:52:35Z","links":{"resolver":"https://pith.science/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ","bundle":"https://pith.science/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/bundle.json","state":"https://pith.science/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMGGVN4C2NA7JRSVEESUWFXQZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WMGGVN4C2NA7JRSVEESUWFXQZZ","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":"1f88951e93d55b809ca43e1809d3f22f240152422ce1b414f33d4c6ba04aa400","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T18:51:31Z","title_canon_sha256":"6b10b206ecb665d2019e592bc8cc70bc0a44b35161d9e865edaf40c54a5e924a"},"schema_version":"1.0","source":{"id":"2606.17213","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17213","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17213v1","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17213","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"WMGGVN4C2NA7","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"WMGGVN4C2NA7JRSV","created_at":"2026-06-19T16:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"WMGGVN4C","created_at":"2026-06-19T16:10:06Z"}],"graph_snapshots":[{"event_id":"sha256:3181ae0d928f7cb90ade3feeddb0af2be2dde866410310326af92eabaf650b7d","target":"graph","created_at":"2026-06-19T16:10:06Z","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/2606.17213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrated strong adaptability to natural images. However, extending their use to the medical domain, particularly for volumetric (3D) images, is challenging due to high computational complexity, volumetric dependencies and the semantic gap between visual features and clinical terminology. Naively fine-tuning LLMs on limited medical data often leads to overfitting and clinical hallucination, where linguistic fluency is prioritized over clinical factuality. In this study, we ","authors_text":"Andrea M. Bejar, Debesh Jha, Gorkem Durak, Halil Ertugrul Aktas, Quoc-Huy Trinh, Ulas Bagci, Vanshali Sharma","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T18:51:31Z","title":"Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17213","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:b1008fab39c95e2c184f9446322ed187ddd7a4aae71f19e6986c6a89f04c9bac","target":"record","created_at":"2026-06-19T16:10:06Z","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":"1f88951e93d55b809ca43e1809d3f22f240152422ce1b414f33d4c6ba04aa400","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T18:51:31Z","title_canon_sha256":"6b10b206ecb665d2019e592bc8cc70bc0a44b35161d9e865edaf40c54a5e924a"},"schema_version":"1.0","source":{"id":"2606.17213","kind":"arxiv","version":1}},"canonical_sha256":"b30c6ab782d341f4c65521254b16f0ce473719a43698472ee610be914180aca5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b30c6ab782d341f4c65521254b16f0ce473719a43698472ee610be914180aca5","first_computed_at":"2026-06-19T16:10:06.146292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:06.146292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVGQFWH+zh4Q9HPxzAI9tse6i6vbPMcQcreeE4YukL4XSNPpKzv7AbP5Nwtm5tWCb5Q5mLggPNiF5faTCFB/BQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:06.146736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17213","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1008fab39c95e2c184f9446322ed187ddd7a4aae71f19e6986c6a89f04c9bac","sha256:3181ae0d928f7cb90ade3feeddb0af2be2dde866410310326af92eabaf650b7d"],"state_sha256":"6aa2317e128c0a8bf2d0a6d49a9d6f262120f30009df66ed96a87be2483adffe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fw85n2ps7uH9koTpp18TgzP9EZqGYFPwUIkXxbMjpYdIstnBSgRts9aw9Ubhezns73GpiVKEaH7lCJwZjCQyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T11:52:35.383529Z","bundle_sha256":"4ea60146b7b56a65b71b0c55437d6cedc547dfdcdee1bf479d1c488c5b8ce574"}}