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-2026-2961 version: 1 kind: certified reason: Certified into the record timestamp: 2026-11-16T06:02:20.544479Z status: published lens: g_space sector: science headline: New Large Language Models Outperform Older Models and Hallucinate Less in Operative Note Data Extraction dek: Background: Recent improvements in large language models (LLMs) may provide a scalable solution for registry data curation. However, trust in model outputs remains limited by hallucinations, wherein models invent information. Given the rapid pace of LLM development, the purpose of this study was to compare the accuracy and hallucination rates of a "newer" and an "older" and previously evaluated LLM in extracting total hip arthroplasty (THA) operative variables. Methods: Surgical approach, fixation technique, and… gain_title: In a study of 1,000 total hip arthroplasty operative notes, a 2026 language model extracted surgical approach, fixation and bearing surface at 98%, 98% and 93% accuracy versus 96%, 96% and 89% for a 2024 model, and hallucinated far less. problem_title: (none) trace_subject: (none) gain_reading: In a study of 1,000 total hip arthroplasty operative notes, a 2026 language model extracted surgical approach, fixation and bearing surface at 98%, 98% and 93% accuracy versus 96%, 96% and 89% for a 2024 model, and hallucinated far less. gain_evidence: surgical approach (98 versus 96%), fixation technique (98 versus 96%), and bearing surface (93 versus 89%) | 49, 20, and 49% for the older model problem_reading: (none) problem_evidence: (none) quick_read: Researchers compared two locally hosted large language models on pulling three data points from 1,000 primary total hip arthroplasty operative notes written by 47 surgeons. The model released in 2026 beat the 2024 model on every task: surgical approach 98% versus 96%, fixation technique 98% versus 96% and bearing surface 93% versus 89%. The bigger gap was in hallucinations, where models invent information. In 100 manually reviewed output reasonings per model, the newer model hallucinated 5%, 3% and 11% of the time for approach, fixation and bearing surface, against 49%, 20% and 49% for the older model. The work matters for registry data curation, where trust in model output is limited by invented content. The authors conclude the models are getting better at following directions, but remaining hallucinations still limit how far the output can be trusted. limitation: The authors say hallucinations persisted in the newer model, at 5%, 3% and 11% across the three tasks, which limits trustworthiness of its output. tag: Evidence-backed gain key_points: Surgical approach, fixation technique and bearing surface were manually abstracted from 1,000 primary total hip arthroplasty operative notes by 47 surgeons. | Prompts were developed on 25% of the notes and tested on the remaining 75%. | Accuracy for the newer model was 98%, 98% and 93%, versus 96%, 96% and 89% for the older model. | Hallucination rates were 5%, 3% and 11% for the newer model versus 49%, 20% and 49% for the older one. | The best-performing prompts for the newer model were simpler than those for the older model. | Hallucinations were assessed manually on 100 sample output reasonings from each model. rundown: The team abstracted three variables by hand from 1,000 operative notes from 47 surgeons. They used 25% of the notes to iteratively develop prompts for two locally hosted models, one released in 2024 and one in 2026, then tested the pipeline on the other 75%. The newer model scored higher on all three tasks, with the largest gain on bearing surface (93% versus 89%). For each task its best prompt was simpler than the best prompt for the older model. For hallucinations, reviewers manually assessed 100 sample reasonings from each model. The newer model's rates were significantly lower across all domains, for example 11% versus 49% for bearing surface. The authors say lower rates persist, which limits trustworthiness. sources: - peer_reviewed | The Journal of Arthroplasty | https://doi.org/10.1016/j.arth.2026.11.047 | 2026-11-12 prev: 0000000000000000000000000000000000000000000000000000000000000000
- SHA-256 hash
- 545ae74af89573bf8f48a14466f4ade9499ac84da1f57b46878e014457b20840
- Previous version’s hash
- 0000000000000000000000000000000000000000000000000000000000000000
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2961 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