{"adoption": {"forks": 221, "observed_at": "2026-08-28T04:03:20.015663+00:00", "stars": 1039}, "canonical_url": "https://ross.abutalabs.com/products/1e0ng-simhash", "card": {"archived": false, "artifact_type": "library", "description": "A Python Implementation of Simhash Algorithm", "domain": [], "enriched": true, "function": ["nlp", "search-engine", "parser"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["1e0ng/simhash"], "name": "1e0ng/simhash", "platform": ["python"], "pushed_at": "2022-03-24T19:22:32+00:00", "repo": "1e0ng/simhash", "stars": 1039, "tags": ["simhash", "locality-sensitive-hashing", "near-duplicate-detection", "text-similarity", "hashing", "natural-language-processing", "algorithms", "search"], "topics": [], "urls": [], "use_cases": ["detect near-duplicate documents in a corpus", "deduplicate web pages or news articles", "compute similarity between text strings", "find duplicate content at scale with hashing", "cluster similar text documents", "identify plagiarism or copied content"], "what_it_is": "A Python implementation of the Simhash algorithm for near-duplicate detection and similarity estimation of text. It provides a small, focused library for computing Simhash fingerprints and comparing their Hamming distance.", "when_to_avoid": ["you need full semantic similarity rather than lexical near-duplicates", "you need actively maintained features or support", "you need embeddings-based similarity for short texts"], "when_to_choose": ["you need fast, lightweight near-duplicate detection in Python", "you want a minimal, dependency-free Simhash implementation", "you are processing large text collections where exact matching is insufficient"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/1e0ng-simhash", "repo": "1e0ng/simhash", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:20.015663+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:03:32.919255+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2807b9827f1b023c70aa0186bc2c93ef62b4e7499e88d80d4dd2a9fb2aeaa7ae", "fetched_at": "2026-08-28T04:03:20.015663+00:00", "kind": "readme", "missing": false, "url": "https://github.com/1e0ng/simhash"}, {"content_hash": "6b59c3292c9b4b42b7e4b140b49ad07155ce771d20fc486d0343339955be8ff3", "fetched_at": "2026-08-29T13:04:37.700448+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/simhash/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4736, "days_push": 1623, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}