{"adoption": {"forks": 303, "observed_at": "2026-08-28T04:03:31.903973+00:00", "stars": 1085}, "canonical_url": "https://ross.abutalabs.com/products/sif", "card": {"archived": false, "artifact_type": "library", "description": "sentence embedding by Smooth Inverse Frequency weighting scheme", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["PrincetonML/SIF"], "name": "PrincetonML/SIF", "platform": ["python"], "pushed_at": "2019-07-23T19:22:37+00:00", "repo": "PrincetonML/SIF", "stars": 1085, "tags": ["sentence-embeddings", "smooth-inverse-frequency", "textual-similarity", "research-code", "word-embeddings", "natural-language-processing", "research"], "topics": [], "urls": [], "use_cases": ["compute sentence embeddings with SIF weighting", "evaluate textual similarity between sentences", "reproduce results from the SIF paper", "build a simple baseline for sentence representation tasks", "train models on sentence similarity and entailment tasks"], "what_it_is": "A Python research library implementing the Smooth Inverse Frequency (SIF) weighting scheme for computing sentence embeddings, from the ICLR 2017 paper 'A Simple but Tough-to-Beat Baseline for Sentence Embeddings'. It includes scripts for generating embeddings, evaluating textual similarity, and training on supervised tasks.", "when_to_avoid": ["you need modern transformer-based sentence embeddings like Sentence-BERT", "you want a production-ready, actively maintained library", "you need support for recent deep learning frameworks instead of Theano/Lasagne"], "when_to_choose": ["you need a simple, strong baseline for sentence embeddings", "you want to reproduce or build on the SIF research", "you're working with GloVe word embeddings and need sentence-level vectors"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/sif", "repo": "PrincetonML/SIF", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.903973+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:49:41.661319+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1547248ec4ce30a1f3b6c5cf03453f5db014041d20ed869d790a4bb8fc615dea", "fetched_at": "2026-08-28T04:03:31.903973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrincetonML/SIF"}], "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": 3582, "days_push": 2598, "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}}