{"adoption": {"forks": 263, "observed_at": "2026-08-28T04:03:51.265990+00:00", "stars": 1170}, "canonical_url": "https://ross.abutalabs.com/products/simhash", "card": {"archived": false, "artifact_type": "library", "description": "中文文档simhash值计算", "domain": ["developer-tools"], "enriched": true, "function": ["nlp", "search-engine", "developer-tools"], "health_score": 89, "homepage": null, "language": "C++", "license": null, "license_family": "other", "maturity": "stable", "member_repos": ["yanyiwu/simhash"], "name": "yanyiwu/simhash", "platform": ["cpp"], "pushed_at": "2026-07-20T07:02:25+00:00", "repo": "yanyiwu/simhash", "stars": 1170, "tags": ["simhash", "chinese-text", "text-deduplication", "fingerprinting", "hamming-distance", "header-only", "cppjieba", "natural-language-processing", "search", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["compute simhash fingerprints for Chinese documents", "detect near-duplicate Chinese web pages or articles", "compare text similarity via Hamming distance", "deduplicate large corpora of Chinese text", "serve simhash calculations over HTTP"], "what_it_is": "A C++ header-only library that computes Simhash fingerprints for Chinese documents, using CppJieba for tokenization and keyword extraction. It supports Hamming-distance-based similarity comparison and includes an optional HTTP server for serving Simhash values.", "when_to_avoid": ["you need Simhash for non-Chinese languages without adapting the tokenizer", "you need a managed-language (Python/Java) library rather than C++", "you require semantic similarity rather than lexical near-duplicate detection"], "when_to_choose": ["you need fast, near-duplicate detection specifically for Chinese text", "you want a lightweight header-only C++ library with no linking overhead", "you need an embeddable fingerprinting algorithm with tunable keyword counts"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/simhash", "repo": "yanyiwu/simhash", "role": "main", "score": 65}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:51.265990+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:28:39.377037+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6fc5940830daffc40a8c261c6f6dc5f7adcaad1af517b2cf78fa8cf0b3473b", "fetched_at": "2026-08-28T04:03:51.265990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yanyiwu/simhash"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4643, "days_push": 44, "days_rel": 453, "gap_med": null, "n_releases_24m": 1}, "score": 65, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}