{"id":44905209,"url":"https://github.com/iscc/twinspect","last_synced_at":"2026-02-17T22:28:54.584Z","repository":{"id":190377180,"uuid":"668378392","full_name":"iscc/twinspect","owner":"iscc","description":"A comprehensive benchmarking framework for evaluating near-duplicate matching and similarity search of text, audio, image, and video content based on compact binary codes.","archived":false,"fork":false,"pushed_at":"2026-01-26T15:48:18.000Z","size":6878,"stargazers_count":3,"open_issues_count":2,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-01-27T04:16:46.813Z","etag":null,"topics":["benchmark","content-identification","iscc"],"latest_commit_sha":null,"homepage":"https://eval.iscc.codes/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iscc.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-07-19T17:00:19.000Z","updated_at":"2026-01-26T15:48:03.000Z","dependencies_parsed_at":"2023-08-24T11:29:01.537Z","dependency_job_id":null,"html_url":"https://github.com/iscc/twinspect","commit_stats":null,"previous_names":["iscc/twinspect"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/iscc/twinspect","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iscc%2Ftwinspect","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iscc%2Ftwinspect/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iscc%2Ftwinspect/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iscc%2Ftwinspect/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iscc","download_url":"https://codeload.github.com/iscc/twinspect/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iscc%2Ftwinspect/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29560558,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-17T21:50:49.831Z","status":"ssl_error","status_checked_at":"2026-02-17T21:46:15.313Z","response_time":100,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["benchmark","content-identification","iscc"],"created_at":"2026-02-17T22:28:53.869Z","updated_at":"2026-02-17T22:28:54.568Z","avatar_url":"https://github.com/iscc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TwinSpect - Near-Duplicate Benchmark\n\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![Python](https://img.shields.io/badge/Python-3.11+-blue.svg)](https://www.python.org/)\n[![Documentation](https://img.shields.io/badge/docs-eval.iscc.codes-green.svg)](https://eval.iscc.codes)\n\n*A comprehensive benchmarking framework for evaluating near-duplicate matching and similarity\nsearch of text, audio, image, and video content based on compact binary codes.*\n\n## Overview\n\n**TwinSpect** was built to evaluate the\n[International Standard Content Code (ISCC)](https://iscc.codes) and inform the ISO community\nabout its capabilities and performance characteristics across different media types.\n\nThe framework provides end-to-end evaluation of information retrieval metrics for compact binary\ncode algorithms against real-world and synthetically augmented media datasets.\n\n**Live results:** https://eval.iscc.codes\n\n## Features\n\n- **Configurable benchmarks** - YAML-based configuration for algorithms, datasets, and metrics\n- **Multi-modal support** - Text, audio, image, and video content types\n- **Dataset management** - Automatic acquisition and transformation of public media collections\n- **Fast similarity search** - HNSW-based indexing for approximate nearest-neighbor queries\n- **Effectiveness metrics** - Precision, recall, F1 scores at configurable hamming thresholds\n- **Result visualization** - Auto-generated documentation with charts and tables\n- **Extensible architecture** - Plugin system for custom algorithms, datasets, and transformations\n- **Performance optimized** - Parallel processing and intelligent caching of intermediate results\n\n## Quick Start\n\n**Requirements:** [Python 3.11+](https://python.org),\n[uv](https://docs.astral.sh/uv/), and [ffmpeg](https://ffmpeg.org/) (for audio/video)\n\n```bash\n# Clone and install\ngit clone https://github.com/iscc/twinspect\ncd twinspect\nuv sync\n\n# Run the full benchmark suite\nuv run twinspect run\n```\n\n## CLI Usage\n\n```bash\n# List available components\nuv run twinspect algorithms       # Show registered algorithms\nuv run twinspect datasets         # Show available datasets\nuv run twinspect benchmarks       # Show benchmark configurations\nuv run twinspect transformations  # Show media transformations\n\n# Run benchmarks\nuv run twinspect run              # Execute all configured benchmarks\n\n# Utilities\nuv run twinspect version          # Show version\nuv run twinspect info             # Show data folder information\nuv run twinspect checksum \u003cpath\u003e  # Compute folder checksum\n```\n\n## Documentation\n\nThe benchmark results and methodology are documented at **https://eval.iscc.codes**, including:\n\n- Algorithm descriptions and configurations\n- Dataset specifications and transformations\n- Effectiveness metrics and interpretation\n- Distribution analysis charts\n\n## Development\n\n```bash\n# Install with dev dependencies\nuv sync\n\n# Run development tasks\nuv run poe all              # Run all formatting and validation tasks\nuv run poe format-code      # Format Python code with ruff\nuv run poe format-yaml      # Format YAML files\nuv run poe validate-schema  # Validate OpenAPI schema\nuv run poe generate-code    # Generate Pydantic models from schema\n\n# Preview documentation locally\nuv run mkdocs serve\n```\n\n## Project Structure\n\n```\ntwinspect/\n├── algos/          # Algorithm implementations and processing\n├── datasets/       # Dataset acquisition and management\n├── metrics/        # Effectiveness and distribution metrics\n├── render/         # Result rendering (Markdown, charts)\n├── transformations/# Media transformation functions\n├── config.yml      # Main benchmark configuration\n└── schema.yml      # OpenAPI data model specification\n```\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and release notes.\n\n## License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for\ndetails.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiscc%2Ftwinspect","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiscc%2Ftwinspect","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiscc%2Ftwinspect/lists"}