{"adoption": {"forks": 270, "observed_at": "2026-08-28T04:06:27.647052+00:00", "stars": 2222}, "canonical_url": "https://ross.abutalabs.com/products/retain-pdf", "card": {"archived": false, "artifact_type": "application", "description": "在保留版面、公式与结构的前提下进行 PDF 翻译，适用于科研与技术文档", "domain": ["pdf", "files", "education"], "enriched": true, "function": ["ocr", "pdf", "nlp", "machine-learning", "image-processing"], "health_score": 96, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["wxyhgk/retain-pdf"], "name": "wxyhgk/retain-pdf", "platform": ["windows", "self-hosted", "cross-platform"], "pushed_at": "2026-07-22T10:16:11+00:00", "repo": "wxyhgk/retain-pdf", "stars": 2222, "tags": ["pdf-translation", "layout-preserving", "scanned-pdfs", "scientific-papers", "typst", "document-ai", "translation", "natural-language-processing", "localization", "macos", "linux", "docker"], "topics": ["document-ai", "document-processing", "ocr", "pdf", "scientific-papers", "translation", "typst", "layout-preserving"], "urls": [], "use_cases": ["translate scientific papers while keeping the original layout", "translate scanned or image-based PDFs", "preserve inline math formulas when translating PDFs", "batch translate technical documentation with custom translation rules", "self-host a PDF translation service for a team via Docker", "compress translated PDFs and control font sizes"], "what_it_is": "RetainPDF is an open-source PDF translation tool that preserves layout, formulas, and document structure, with special support for scanned/image-based PDFs and complex inline formulas. It ships as desktop apps for Windows/macOS/Linux and a Docker-deployable web service with OCR, translation, and typesetting modules.", "when_to_avoid": ["you only need plain text extraction or translation without layout", "you need a lightweight CLI-only tool", "you require a fully offline solution without any model/API dependencies"], "when_to_choose": ["you need layout-preserving translation of scanned PDFs or complex formulas", "you want a self-hosted or API-driven PDF translation pipeline", "you translate scientific or technical documents regularly"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/retain-pdf", "repo": "wxyhgk/retain-pdf", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:27.647052+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:45:46.498975+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c9fe0604dfc561dfe8810789da62b9c45093f35d1bda17a07a2889549f02b604", "fetched_at": "2026-08-28T04:06:27.647052+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wxyhgk/retain-pdf"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 11, "rhythm": 94}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 157, "days_push": 42, "days_rel": 42, "gap_med": 0.0, "n_releases_24m": 43}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}