{"adoption": {"forks": 157, "observed_at": "2026-08-28T04:05:35.412170+00:00", "stars": 1780}, "canonical_url": "https://ross.abutalabs.com/products/npc_gzip", "card": {"archived": false, "artifact_type": "library", "description": "Code for Paper: “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "machine-learning", "compression", "cli"], "health_score": 22, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["bazingagin/npc_gzip"], "name": "bazingagin/npc_gzip", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2023-08-07T04:43:48+00:00", "repo": "bazingagin/npc_gzip", "stars": 1780, "tags": ["text-classification", "gzip-classifier", "knn", "low-resource-nlp", "research-code", "acl2023", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["classify text without training a model", "low-resource text classification for languages with little data", "run gzip-based kNN classification experiments", "benchmark compression-based classifiers on AG News or DBpedia", "classify a custom labeled dataset with compressors", "reproduce ACL 2023 paper results"], "what_it_is": "A Python library and research codebase implementing the parameter-free 'kNN-gzip' text classification method from the ACL 2023 paper, which classifies text using compression-based distances (gzip, lzma, bz2) instead of trained models. It is installable via pip and includes CLI scripts for running experiments on standard datasets or custom data.", "when_to_avoid": ["you need state-of-the-art accuracy on large datasets", "you need fast low-latency inference at scale", "you want embeddings or fine-tuning with transformers", "your text is very long, since compression distances scale poorly"], "when_to_choose": ["you need a parameter-free, training-free text classifier", "you have very few labeled examples per class", "you want to reproduce or extend the kNN-gzip paper", "you want a simple baseline that avoids GPU/model training"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/npc_gzip", "repo": "bazingagin/npc_gzip", "role": "main", "score": 20}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:35.412170+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:24:35.176005+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21cb148abfaf29d979a2527f047cfa19e83d6c22c6ec71faee3765d0d6c3f017", "fetched_at": "2026-08-28T04:05:35.412170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bazingagin/npc_gzip"}, {"content_hash": "6d9f7dc24464610c11669e8f88b7aec63f8b22422650ef8500ce3d85769f79b9", "fetched_at": "2026-08-29T11:03:07.740682+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/npc_gzip/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 85, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1196, "days_push": 1122, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 20, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}