{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-baiyuetribe--paper2gui","slug":"baiyuetribe--paper2gui","name":"paper2gui","type":"webapp","url":"https://xiaobaituai.com","page_url":"https://unfragile.ai/baiyuetribe--paper2gui","categories":["research-search"],"tags":["animegan2","codeformer-gui","dain","dain-gui","gfpgan","huoshan-tts","microsoft-tts","ncnn","ncnn-model","noveria","realcugan-gui","realcugan-pro","realesrganv2-gu","rife-gui","stable-diffusion","waifu2x-gui"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-baiyuetribe--paper2gui__cap_0","uri":"capability://image.visual.gpu.accelerated.image.super.resolution.with.ncnn.framework","name":"gpu-accelerated image super-resolution with ncnn framework","description":"Implements real-time image upscaling using NCNN's optimized inference engine with Vulkan GPU acceleration, supporting multiple super-resolution models (RealESRGAN, RealCugan, Waifu2x, RealSR) with automatic hardware detection and fallback to CPU processing. The architecture leverages NCNN's quantized model format for reduced memory footprint while maintaining inference speed through direct GPU memory management and batch processing pipelines.","intents":["I need to upscale low-resolution images to 2x-4x resolution without quality loss for batch processing","I want to enhance anime/artwork images specifically while preserving artistic style details","I need to run image super-resolution locally without cloud API dependencies or latency","I want to process images on consumer GPUs with minimal VRAM requirements"],"best_for":["Desktop users processing images locally without internet dependency","Content creators working with anime, manga, or artwork requiring style-aware upscaling","Developers building offline image enhancement pipelines","Users with limited GPU memory (2GB-8GB VRAM) requiring efficient inference"],"limitations":["Windows primary support; Mac/Linux compatibility varies by model","Vulkan GPU acceleration requires compatible GPU drivers; CPU fallback adds 5-10x latency","Maximum practical image dimensions ~4K due to VRAM constraints on consumer GPUs","Model selection must be pre-chosen; no automatic model selection based on image content","Batch processing limited by available GPU memory; single-image processing is primary use case"],"requires":["Windows 7+ or Mac/Linux with Vulkan-capable GPU","GPU with minimum 2GB VRAM for real-time processing","NCNN framework pre-compiled binaries included in distribution","Vulkan drivers installed and functional on target system"],"input_types":["image/jpeg","image/png","image/bmp","image/webp"],"output_types":["image/png (lossless output)","image/jpeg (optional lossy output)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_1","uri":"capability://image.visual.real.time.video.frame.interpolation.with.temporal.coherence","name":"real-time video frame interpolation with temporal coherence","description":"Synthesizes intermediate video frames between existing frames using deep learning models (RIFE, DAIN) integrated through NCNN inference, maintaining temporal consistency and reducing motion artifacts through optical flow estimation and frame blending. The Go backend processes video streams with configurable frame multiplication factors (2x, 4x, 8x) while managing memory buffers to prevent frame accumulation and maintain real-time performance on consumer hardware.","intents":["I want to convert 24fps video to 60fps for smoother playback without motion blur","I need to slow down video while maintaining smooth motion for slow-motion effects","I want to reduce judder in low-frame-rate video content","I need to process video locally without uploading to cloud services"],"best_for":["Video editors and content creators needing frame interpolation without expensive plugins","Users with 60Hz+ displays wanting to watch 24fps content smoothly","Developers building offline video processing pipelines","Gamers and streamers wanting to increase perceived smoothness"],"limitations":["Windows primary platform; Mac/Linux support limited","Processing speed depends on video resolution and GPU; 1080p60 requires high-end GPU","Interpolation quality degrades with fast motion or scene cuts; may introduce ghosting artifacts","Memory usage scales with video resolution; 4K processing requires 8GB+ VRAM","No real-time preview during processing; batch processing only"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 4GB VRAM for 1080p processing; 8GB+ for 4K","Video file in H.264/H.265 format (MP4, MKV containers)","NCNN framework binaries included in distribution"],"input_types":["video/mp4","video/x-matroska","video/quicktime"],"output_types":["video/mp4 (H.264 encoded)","video/x-matroska (optional)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_10","uri":"capability://automation.workflow.memory.optimized.batch.processing.with.streaming.i.o","name":"memory-optimized batch processing with streaming i/o","description":"Implements efficient batch processing pipeline using Go's concurrent processing with configurable worker pools and streaming I/O to avoid loading entire datasets into memory, achieving 26-30% speedup through reduced disk I/O and optimized memory management. The system uses ring buffers for frame/image queuing, lazy model loading, and automatic memory cleanup between batches to maintain consistent performance across long-running processing jobs.","intents":["I want to process hundreds of images without running out of memory","I need to batch-process video files with consistent performance","I want to optimize processing speed for large-scale image/video workflows","I need to process data larger than available system RAM"],"best_for":["Users processing large image/video collections (100+ files)","Content creators with batch processing workflows","Developers building production image processing pipelines","Teams processing data on resource-constrained systems"],"limitations":["Batch processing requires pre-configuration of worker count and queue sizes","Memory optimization adds complexity; debugging memory issues requires profiling","Streaming I/O introduces latency for small batches (overhead not amortized)","Ring buffer implementation may cause frame drops under extreme load","No adaptive worker scaling; manual tuning required for different hardware"],"requires":["Go 1.16+ for concurrent processing features","Sufficient disk I/O bandwidth for streaming (SSD recommended)","Configurable worker pool size based on CPU core count","Monitoring tools for memory usage profiling"],"input_types":["image-files","video-files","file-lists"],"output_types":["processed-images","processed-videos","batch-results-summary"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_11","uri":"capability://automation.workflow.cross.platform.desktop.application.packaging.and.distribution","name":"cross-platform desktop application packaging and distribution","description":"Packages AI tools as standalone executables for Windows, Mac, and Linux using Wails framework with platform-specific build configurations, enabling distribution without requiring users to install Python, Go, or any frameworks. The build system includes model weight embedding, dependency bundling, and code signing for Windows/Mac, producing single-file executables that run immediately after download without installation or configuration.","intents":["I want to distribute AI tools to non-technical users without installation complexity","I need to create standalone executables that work on any Windows/Mac/Linux system","I want to package AI models with applications for offline distribution","I need to ensure users can run tools immediately after download"],"best_for":["Open-source developers distributing AI tools to general users","Teams deploying AI applications to end-users","Creators building consumer-facing AI tools","Organizations requiring offline-capable applications"],"limitations":["Executable size 100-500MB depending on included models (large download)","Mac/Linux support varies by model; not all tools available on all platforms","Code signing and notarization required for Mac distribution (additional complexity)","Windows Defender may flag unsigned executables as suspicious","Updates require re-downloading entire executable; no incremental updates"],"requires":["Wails framework installed and configured","Go 1.16+ for backend compilation","Node.js 14+ for frontend bundling","Platform-specific build tools (MSVC for Windows, Xcode for Mac)","Model weights in NCNN format included in distribution"],"input_types":["source-code","model-weights","configuration-files"],"output_types":["executable-windows","executable-macos","executable-linux"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_12","uri":"capability://tool.use.integration.aggregated.multi.tool.interface.with.unified.settings.management","name":"aggregated multi-tool interface with unified settings management","description":"Provides 'Little White Rabbit AI' aggregated application combining 50+ AI tools in single interface with unified settings, model management, and processing queue. The architecture uses a plugin-like system where individual tools register capabilities with the main application, sharing common infrastructure for GPU management, model caching, and batch processing while maintaining tool-specific UI customization through Naive-UI component composition.","intents":["I want to access multiple AI tools from single application without switching between windows","I need unified model management and GPU resource allocation across tools","I want consistent settings and preferences across all AI processing tools","I need to chain multiple AI operations (e.g., upscale then restore faces)"],"best_for":["Power users working with multiple AI tools regularly","Content creators needing diverse AI capabilities in one interface","Developers building AI tool suites","Teams standardizing on single application for all AI processing"],"limitations":["Aggregated application larger than individual tools (500MB+ executable)","Complex UI with 50+ tools may be overwhelming for casual users","Tool chaining requires manual output/input management between steps","Shared GPU resource management may cause contention under heavy load","Updates to single tool require re-downloading entire aggregated application"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 4GB VRAM for comfortable multi-tool usage","Sufficient disk space for aggregated executable (500MB+)","NCNN framework binaries included in distribution"],"input_types":["images","videos","text","audio"],"output_types":["processed-images","processed-videos","generated-audio","batch-results"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_2","uri":"capability://image.visual.semantic.image.background.removal.with.matting.networks","name":"semantic image background removal with matting networks","description":"Removes image backgrounds using deep matting networks (RVM, MODNet, MobileNetV2) executed through NCNN inference, producing alpha channel masks that preserve fine details like hair and transparency. The system applies post-processing filters to refine edge boundaries and supports batch processing with configurable output formats (PNG with alpha, composite backgrounds).","intents":["I need to remove backgrounds from product photos for e-commerce listings","I want to extract subjects from photos while preserving fine details like hair","I need to batch-process hundreds of images for background removal","I want to replace backgrounds with custom images or colors"],"best_for":["E-commerce businesses processing product photography","Content creators and designers needing quick background removal","Photo editors wanting automated matting without manual selection","Batch processing workflows requiring consistent background removal"],"limitations":["Windows primary support; Mac/Linux compatibility limited","Performance degrades with complex backgrounds or transparent subjects","Fine hair/fur details may require manual refinement for professional results","Requires minimum 2GB VRAM for real-time processing","No interactive refinement tools; output is final after processing"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 2GB VRAM for standard image processing","Image file in JPEG, PNG, or BMP format","NCNN framework binaries included in distribution"],"input_types":["image/jpeg","image/png","image/bmp"],"output_types":["image/png (with alpha channel)","image/jpeg (with composite background)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_3","uri":"capability://image.visual.multi.model.face.restoration.and.enhancement","name":"multi-model face restoration and enhancement","description":"Restores and enhances facial details in images using GFPGAN model integrated through NCNN, applying blind face restoration to upscale low-resolution faces, remove artifacts, and enhance facial features. The pipeline includes face detection preprocessing, model inference with configurable enhancement strength, and post-processing to blend restored faces back into original images while maintaining natural appearance.","intents":["I want to enhance facial details in old or low-quality photos","I need to remove compression artifacts and noise from face regions","I want to upscale faces in images while preserving overall image quality","I need to batch-process portraits for consistent enhancement"],"best_for":["Photo restoration specialists working with old or damaged photographs","Content creators enhancing portrait quality for social media","Developers building automated photo enhancement pipelines","Users restoring family photos or historical images"],"limitations":["Windows primary platform; Mac/Linux support limited","Face detection preprocessing required; fails on non-frontal or partially visible faces","Enhancement strength is global; no per-face customization in batch mode","Requires 2GB+ VRAM for real-time processing","May introduce artifacts if enhancement strength set too high"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 2GB VRAM for standard image processing","Image file in JPEG, PNG, or BMP format","NCNN framework binaries included in distribution"],"input_types":["image/jpeg","image/png","image/bmp"],"output_types":["image/png (lossless output)","image/jpeg (optional lossy output)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_4","uri":"capability://text.generation.language.text.to.speech.synthesis.with.multiple.provider.backends","name":"text-to-speech synthesis with multiple provider backends","description":"Converts text input to natural-sounding speech using multiple TTS backends (Microsoft TTS, Huoshan TTS, Aliyun TTS) with configurable voice selection, speech rate, and pitch parameters. The Go backend abstracts provider-specific APIs and handles audio encoding/decoding, supporting both local synthesis (Microsoft TTS) and cloud-based synthesis (Huoshan, Aliyun) with fallback mechanisms and caching of generated audio.","intents":["I want to generate natural-sounding speech from text without installing TTS engines","I need to create audio content with different voice options and speaking styles","I want to batch-convert documents or scripts to audio files","I need TTS with Chinese language support for content creation"],"best_for":["Content creators producing audio content from text","Accessibility specialists creating audio versions of documents","Developers building voice-enabled applications","Users creating multilingual audio content (especially Chinese)"],"limitations":["Cloud-based providers (Huoshan, Aliyun) require API keys and internet connectivity","Microsoft TTS limited to Windows platform; requires Windows TTS engine installation","API rate limits apply to cloud providers; batch processing may be throttled","Audio quality varies by provider; no unified quality guarantee","Latency for cloud providers depends on network and provider load"],"requires":["Windows 7+ for Microsoft TTS; Mac/Linux for cloud providers","Internet connection for Huoshan TTS and Aliyun TTS","API keys for Huoshan TTS and Aliyun TTS (free tier available)","Windows TTS engine installed for Microsoft TTS option"],"input_types":["text/plain","text/utf-8"],"output_types":["audio/wav","audio/mp3"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_5","uri":"capability://image.visual.anime.style.image.generation.and.style.transfer","name":"anime-style image generation and style transfer","description":"Transforms photographs into anime/cartoon artwork using AnimeGAN2 model integrated through NCNN inference, applying artistic style transfer while preserving content structure. The system uses NCNN's quantized model format for efficient GPU processing and includes preprocessing to normalize input images and post-processing to enhance color vibrancy and line definition.","intents":["I want to convert photos into anime-style artwork for creative projects","I need to batch-process images with consistent anime style application","I want to create anime avatars from portrait photos","I need to apply artistic style transfer without manual editing"],"best_for":["Anime and manga enthusiasts creating fan art","Content creators producing stylized social media content","Developers building creative image processing applications","Users creating avatar images from photos"],"limitations":["Windows primary platform; Mac/Linux support limited","Style transfer quality depends on input image content and lighting","No fine-grained control over style intensity; output is binary (applied or not)","Requires 2GB+ VRAM for real-time processing","May produce artifacts on complex backgrounds or multiple subjects"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 2GB VRAM for standard image processing","Image file in JPEG, PNG, or BMP format","NCNN framework binaries included in distribution"],"input_types":["image/jpeg","image/png","image/bmp"],"output_types":["image/png (lossless output)","image/jpeg (optional lossy output)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_6","uri":"capability://image.visual.real.time.object.detection.with.yolo.models","name":"real-time object detection with yolo models","description":"Detects and localizes objects in images using YOLO family models (YOLOv5, YOLOv6, YOLOX) integrated through NCNN inference, producing bounding box coordinates, class labels, and confidence scores. The system includes configurable confidence thresholds, non-maximum suppression for duplicate detection filtering, and visualization overlays showing detected objects with labels and bounding boxes.","intents":["I want to detect specific object types in images for inventory or quality control","I need to process images to identify and count objects automatically","I want to build object detection pipelines without training custom models","I need to batch-process images for object detection with consistent parameters"],"best_for":["Quality control and manufacturing inspection specialists","Developers building computer vision applications","Researchers prototyping object detection pipelines","Users automating image analysis workflows"],"limitations":["Windows primary platform; Mac/Linux support limited","Detection accuracy depends on model choice and object types in training data","Confidence threshold tuning required for different use cases; no automatic optimization","Requires 2GB+ VRAM for real-time processing","No model fine-tuning or transfer learning capabilities; pre-trained models only"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 2GB VRAM for standard image processing","Image file in JPEG, PNG, or BMP format","NCNN framework binaries included in distribution"],"input_types":["image/jpeg","image/png","image/bmp"],"output_types":["image/png (with detection overlays)","application/json (detection results with coordinates)"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_7","uri":"capability://image.visual.stable.diffusion.text.to.image.generation.with.local.inference","name":"stable diffusion text-to-image generation with local inference","description":"Generates images from text prompts using Stable Diffusion model integrated through NCNN inference, supporting configurable sampling steps, guidance scale, and seed parameters for reproducible generation. The Go backend manages model loading, memory allocation, and inference scheduling while the Wails frontend provides prompt input, parameter adjustment, and image preview with generation progress tracking.","intents":["I want to generate images from text descriptions without cloud API dependencies","I need to create multiple image variations from the same prompt with different seeds","I want to adjust generation parameters (steps, guidance) for quality/speed tradeoff","I need to batch-generate images with consistent parameters"],"best_for":["Artists and designers exploring creative concepts through AI generation","Content creators producing visual assets for projects","Developers building image generation applications","Users wanting local, privacy-preserving image generation"],"limitations":["Windows primary platform; Mac/Linux support limited","Requires 6GB+ VRAM for real-time generation; 8GB+ recommended for quality","Generation time 30-60 seconds per image on consumer GPUs (varies by step count)","NCNN quantization may reduce image quality vs full-precision PyTorch inference","No model fine-tuning or LoRA support; base Stable Diffusion model only"],"requires":["Windows 7+ with GPU supporting Vulkan","Minimum 6GB VRAM; 8GB+ recommended for quality generation","Stable Diffusion model weights (included in distribution or downloaded on first run)","NCNN framework binaries included in distribution"],"input_types":["text/plain (text prompts)"],"output_types":["image/png (generated images)"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_8","uri":"capability://tool.use.integration.modular.gui.framework.with.wails.and.naive.ui.integration","name":"modular gui framework with wails and naive-ui integration","description":"Provides a unified desktop application framework using Wails (Go-based desktop framework) with Naive-UI Vue 3 component library, enabling rapid development of AI tool GUIs with consistent styling and responsive layouts. The architecture separates Go backend logic from Vue frontend presentation, allowing independent scaling of processing capabilities and UI complexity while maintaining cross-platform compatibility through Wails' native window management.","intents":["I want to build desktop AI applications without learning Electron or Qt","I need consistent UI components across multiple AI tools in a suite","I want to create responsive, modern interfaces for AI processing tools","I need to package Go-based AI processing with a professional GUI"],"best_for":["Go developers building desktop AI applications","Teams developing multiple AI tools requiring consistent UI","Developers wanting lightweight desktop frameworks vs Electron","Builders creating cross-platform AI tool suites"],"limitations":["Wails framework adds ~50-100MB to application size vs native applications","Vue 3 frontend adds complexity for developers unfamiliar with JavaScript/TypeScript","Limited native OS integration compared to platform-specific frameworks","Debugging frontend-backend communication requires familiarity with IPC patterns","Performance overhead from Go-JavaScript bridge for frequent updates"],"requires":["Go 1.16+ for backend development","Node.js 14+ for frontend development","Wails CLI installed (go install github.com/wailsapp/wails/v2/cmd/wails@latest)","Naive-UI npm package (npm install naive-ui)"],"input_types":["user-interface-events","file-system-paths","configuration-parameters"],"output_types":["rendered-html-ui","application-windows","file-system-operations"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-baiyuetribe--paper2gui__cap_9","uri":"capability://tool.use.integration.ncnn.based.model.inference.with.vulkan.gpu.acceleration","name":"ncnn-based model inference with vulkan gpu acceleration","description":"Provides unified inference engine using NCNN framework with Vulkan GPU acceleration for executing quantized AI models across all Paper2GUI tools, abstracting hardware-specific optimizations and providing fallback CPU execution. The system manages model loading, memory allocation, and inference scheduling through Go bindings to NCNN C++ library, enabling efficient batch processing and real-time inference on consumer GPUs with minimal VRAM requirements.","intents":["I want to run AI models locally without Python/PyTorch/TensorFlow dependencies","I need efficient inference on consumer GPUs with limited VRAM","I want to create standalone executables that don't require framework installation","I need to support multiple AI models with unified inference infrastructure"],"best_for":["Developers building standalone AI applications","Teams deploying AI tools to end-users without technical expertise","Builders creating lightweight desktop applications","Organizations requiring offline AI processing without cloud dependencies"],"limitations":["NCNN quantization (INT8) may reduce model accuracy vs full-precision inference","Limited model format support; requires conversion from PyTorch/TensorFlow to NCNN format","Vulkan GPU acceleration requires compatible GPU drivers; CPU fallback is slow","No dynamic model loading; models must be pre-compiled into application","Debugging quantization artifacts requires deep understanding of NCNN internals"],"requires":["NCNN framework source code or pre-compiled binaries","Vulkan SDK installed for GPU acceleration support","GPU with Vulkan support (most modern GPUs from 2015+)","Model weights in NCNN format (conversion tools required for PyTorch/TensorFlow models)"],"input_types":["image-tensors","video-frames","text-embeddings"],"output_types":["inference-results","feature-maps","classification-scores"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":39,"verified":false,"data_access_risk":"high","permissions":["Windows 7+ or Mac/Linux with Vulkan-capable GPU","GPU with minimum 2GB VRAM for real-time processing","NCNN framework pre-compiled binaries included in distribution","Vulkan drivers installed and functional on target system","Windows 7+ with GPU supporting Vulkan","Minimum 4GB VRAM for 1080p processing; 8GB+ for 4K","Video file in H.264/H.265 format (MP4, MKV containers)","NCNN framework binaries included in distribution","Go 1.16+ for concurrent processing features","Sufficient disk I/O bandwidth for streaming (SSD recommended)"],"failure_modes":["Windows primary support; Mac/Linux compatibility varies by model","Vulkan GPU acceleration requires compatible GPU drivers; CPU fallback adds 5-10x latency","Maximum practical image dimensions ~4K due to VRAM constraints on consumer GPUs","Model selection must be pre-chosen; no automatic model selection based on image content","Batch processing limited by available GPU memory; single-image processing is primary use case","Windows primary platform; Mac/Linux support limited","Processing speed depends on video resolution and GPU; 1080p60 requires high-end GPU","Interpolation quality degrades with fast motion or scene cuts; may introduce ghosting artifacts","Memory usage scales with video resolution; 4K processing requires 8GB+ VRAM","No real-time preview during processing; batch processing only","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.35228739440457424,"quality":0.5,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.549Z","last_scraped_at":"2026-05-03T13:58:42.318Z","last_commit":"2024-09-20T05:57:52Z"},"community":{"stars":10725,"forks":884,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=baiyuetribe--paper2gui","compare_url":"https://unfragile.ai/compare?artifact=baiyuetribe--paper2gui"}},"signature":"jKeOW73lFF+wBoTpijPnFaxLlmq3DaiVZ6SdnYTMDUPAdH5SYqJQmmb3OWHBtuYE/TUh2LL2BTSuCKoi6c9nAg==","signedAt":"2026-06-21T08:50:34.961Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/baiyuetribe--paper2gui","artifact":"https://unfragile.ai/baiyuetribe--paper2gui","verify":"https://unfragile.ai/api/v1/verify?slug=baiyuetribe--paper2gui","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}