{"adoption": {"forks": 353, "observed_at": "2026-08-28T04:03:17.533994+00:00", "stars": 1028}, "canonical_url": "https://ross.abutalabs.com/products/mallet", "card": {"archived": false, "artifact_type": "library", "description": "MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.", "domain": ["machine-learning", "text-editors"], "enriched": true, "function": ["machine-learning", "nlp", "parser", "serialization"], "health_score": 98, "homepage": "https://mimno.github.io/Mallet/", "language": "Java", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["mimno/Mallet"], "name": "mimno/Mallet", "platform": ["jvm", "cross-platform", "cli"], "pushed_at": "2026-08-04T20:21:57+00:00", "repo": "mimno/Mallet", "stars": 1028, "tags": ["topic-modeling", "lda", "document-classification", "conditional-random-fields", "named-entity-recognition", "text-clustering", "java", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["train topic models like LDA on large text corpora", "classify documents into categories", "extract named entities from text with CRFs", "cluster unlabeled documents", "convert raw text into feature vectors for machine learning", "run sequence tagging on token streams"], "what_it_is": "MALLET (MAchine Learning for LanguagE Toolkit) is a Java-based package for statistical natural language processing, including document classification, clustering, sequence tagging, and topic modeling. It provides efficient implementations of algorithms such as Naive Bayes, Maximum Entropy, CRFs, and LDA, along with text-processing pipelines and numerical optimization routines.", "when_to_avoid": ["you need modern deep-learning or transformer-based NLP models", "your stack is Python-first and you prefer libraries like scikit-learn, Gensim, or spaCy", "you need GPU acceleration for large-scale training"], "when_to_choose": ["you need mature, sampling-based topic modeling (LDA, Pachinko Allocation, Hierarchical LDA) in Java", "you want classic NLP classification and sequence tagging algorithms on the JVM", "you need efficient text-to-feature pipelines with tokenization and stopword handling"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mallet", "repo": "mimno/Mallet", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.533994+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:47.904575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9d377cafd2852d466b06fa8d21cefe6ebf03dd5d0467ffcb1d210dc22243a1e1", "fetched_at": "2026-08-28T04:03:17.533994+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mimno/Mallet"}, {"content_hash": "32c4faedb004382e3bb2a4eec4f4faa979ee8673d266b41048da8630380bd42c", "fetched_at": "2026-08-29T13:07:41.408619+00:00", "kind": "homepage", "missing": false, "url": "https://mimno.github.io/Mallet/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 64}, "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": 4536, "days_push": 29, "days_rel": 29, "gap_med": 208, "n_releases_24m": 2}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}