With an AI assistant, the test, the example and the docs may all come from the process that wrote the feature. Two ways to check.

The GitHub Annotation Toolkit is a Figma asset library packed with components to help you organize your design canvas, diagram UI anatomy, and annotate accessibility details for web and mobile exp...

If you have ever needed thousands of detailed image captions for a dataset, tagging pipeline or accessibility workflow, Caption-Pro is a name to note. Published by prithivMLmods on Modelers.cn,…

Untargeted liquid chromatography-mass spectrometry (LC-MS) metabolomics generates thousands of features, but incomplete metabolite annotation and reliance on predefined pathways limit their biological interpretation. Here we present FeatureMAP, an LC-MS feature-centric computational framework that integrates multi-evidence metabolite annotation, network-guided refinement, metabolic module discovery, and structured large language model-based functional interpretation. Across ten public datasets, FeatureMAP improved MS1-based metabolite candidate prioritization while reducing annotation redundancy. In semi-synthetic benchmarks, FeatureMAP recovered coordinated metabolic perturbations, achieving 92% recovery of a simulated perturbation, and distinguished concurrent metabolic processes. Controlled benchmarks further evaluated functional interpretation under competing metabolite-level signals. Based on FeatureMAP, we additionally developed PhenoMAP, a phenotype-aware knowledge graph comprising 12,929 dysregulated metabolic modules from 501 human metabolomics studies spanning 326 phenotypes. Module-level comparisons revealed reproducible metabolic similarities across independent studies and biologically supported relationships among phenotypes. Application to Alzheimer's disease cerebrospinal fluid and cellular datasets identified convergent membrane-lipid alterations and implicated galactose-linked glycosphingolipid remodeling. Together, FeatureMAP and PhenoMAP enable network-grounded interpretation of incompletely annotated LC-MS metabolomics data and systematic investigation of metabolic dysregulation across biological conditions.

Thank you, this is practical and I’m adopting two of the points. Confidence score: the second rater will give a 1–3 confidence score with each label. Since the first human rater in Test 2 gave binary labels only, the primary agreement comparison stays binary; the confidence scores will set the order of case review in Pass 2 and show whether disagreements cluster on low-confidence scenes. Reasoning traces: the second rater will write a one-sentence justification before each label, so that conceptual disagreements (a different reading of the definition) can be told apart from perceptual ones. I’ll note as a limitation that writing a justification may itself shift some labels. The definition stays unchanged for Pass 1. On finding a rater: if you know a specific Turkish NLP or literary studies group that has done annotation work like this, I’d be grateful for a name. And if anyone reading this thread reads Turkish fiction and would consider labelling 100 short scenes for one feature, please get in touch through the dataset page.

UCL Discovery is UCL's open access repository, showcasing and providing access to UCL research outputs from all UCL disciplines.