Certified into the record
The exact text we saved
This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.
TRUVACE RECORD VERSION record: TRV-2026-2992 version: 1 kind: certified reason: Certified into the record timestamp: 2026-11-17T12:02:11.893248Z status: published lens: p_space sector: health headline: Comparative evaluation of GPT 5.2 Pro and Gemini 3 Pro large multimodal models for retinal optical coherence tomography interpretation dek: Purpose: Large multimodal models (LMMs) capable of interpreting medical images are increasingly accessible to patients, yet their reliability for retinal optical coherence tomography (OCT) interpretation remains uncertain. This study evaluated the performance of two state-of-the-art LMMs in detecting OCT features and generating diagnostic interpretations. Methods: In this cross-sectional study, 330 publicly available retinal OCT B-scans spanning 12 diagnostic categories, including normal scans and common retinal… gain_title: (none) problem_title: In a cross-sectional study of 330 retinal OCT scans, GPT 5.2 Pro reached 32.1% diagnostic accuracy and Gemini 3 Pro 58.8%, and GPT 5.2 Pro failed to correctly identify any normal scan. trace_subject: (none) gain_reading: (none) gain_evidence: (none) problem_reading: In a cross-sectional study of 330 retinal OCT scans, GPT 5.2 Pro reached 32.1% diagnostic accuracy and Gemini 3 Pro 58.8%, and GPT 5.2 Pro failed to correctly identify any normal scan. problem_evidence: higher diagnostic accuracy (58.8% vs. 32.1%) | GPT 5.2 Pro, which failed to correctly identify any normal images | Normal OCT scans were frequently misclassified as pathological quick_read: A cross-sectional study tested two commercial multimodal AI models, GPT 5.2 Pro and Gemini 3 Pro, on 330 publicly available retinal optical coherence tomography scans covering 12 diagnostic categories. Gemini 3 Pro got 58.8% of diagnoses right, against 32.1% for GPT 5.2 Pro. Both models handled obvious abnormalities better than subtle structural features, and both often labelled normal scans as diseased. GPT 5.2 Pro did not correctly identify a single normal image. The researchers also observed recurring model-specific biases and hallucinated diagnoses. The authors say these models are increasingly available to patients, so misreadings outside supervised clinical settings are a risk. They call for careful validation and clear usage boundaries before such tools are built into patient-facing workflows. limitation: The study used publicly available scans and zero-shot prompting of two models, so results may not reflect other models or clinical use; the authors say careful validation is still needed. tag: Evidence-backed problem key_points: The study analysed 330 public retinal OCT B-scans across 12 diagnostic categories, including normal scans and common retinal diseases. | Both models were tested with zero-shot inference, meaning no task-specific training or examples. | Feature detection covered nine predefined OCT features; Gemini 3 Pro scored a macro-averaged F1 of 0.558 versus 0.472 for GPT 5.2 Pro. | Diagnostic accuracy, judged against expert-adjudicated reference standards, was 58.8% for Gemini 3 Pro and 32.1% for GPT 5.2 Pro. | Both models showed limited sensitivity for subtle structural features but did better on visually salient abnormalities. | Normal scans were often misclassified as pathological, and GPT 5.2 Pro identified none of them correctly. | The researchers observed recurrent model-specific diagnostic biases and hallucinated diagnoses. rundown: The researchers used 330 publicly available retinal OCT B-scans spanning 12 diagnostic categories, including normal scans and common retinal diseases. Two commercially available models, GPT 5.2 Pro and Gemini 3 Pro, were run with zero-shot inference. The models were assessed on two tasks: detecting nine predefined OCT features, scored with per-feature metrics and macro-averaged F1, and producing free-text diagnostic interpretations, scored against expert-adjudicated reference standards. Gemini 3 Pro outperformed GPT 5.2 Pro on both tasks, with an F1 of 0.558 versus 0.472 and diagnostic accuracy of 58.8% versus 32.1%. Both did better on visually salient abnormalities than subtle ones. Overcalling of pathology was common, and GPT 5.2 Pro failed to correctly identify any normal images. The authors conclude that the models can extract clinically relevant information from OCT scans but that diagnostic reliability remains limited. They warn of misinterpretation outside supervised clinical settings and say careful validation and clear usage boundaries are needed. sources: - peer_reviewed | Graefe's Archive for Clinical and Experimental Ophthalmology | https://doi.org/10.1007/s00417-026-07604-7 | 2026-11-16 prev: 0000000000000000000000000000000000000000000000000000000000000000
- SHA-256 hash
- b002266629f11de39fdd737e7a032c41bca1713db8c9b5d3f62e6156123a8f2c
- Previous version’s hash
- 0000000000000000000000000000000000000000000000000000000000000000
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2992 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace