{"adoption": {"forks": 533, "observed_at": "2026-08-28T04:06:01.628170+00:00", "stars": 1979}, "canonical_url": "https://ross.abutalabs.com/products/deepdive", "card": {"archived": false, "artifact_type": "application", "description": "DeepDive", "domain": ["data-science", "databases", "big-data"], "enriched": true, "function": ["machine-learning", "nlp", "database", "etl", "data-science"], "health_score": 20, "homepage": "deepdive.stanford.edu", "language": "Shell", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["HazyResearch/deepdive"], "name": "HazyResearch/deepdive", "platform": ["cli"], "pushed_at": "2022-06-09T05:49:44+00:00", "repo": "HazyResearch/deepdive", "stars": 1979, "tags": ["information-extraction", "knowledge-base-construction", "distant-supervision", "probabilistic-inference", "stanford", "dark-data", "natural-language-processing", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["build a knowledge base from scientific papers", "extract entities and relations from text documents", "populate a database from unstructured text", "train relation extractors without labeled data", "run probabilistic inference over extracted facts", "perform information extraction over dark data"], "what_it_is": "DeepDive is a Stanford-developed system for extracting structured data from unstructured sources and building knowledge bases using distant supervision and probabilistic inference. It lets users declare extraction and inference rules over databases rather than writing feature engineering code.", "when_to_avoid": ["you need actively maintained software with new features or guaranteed support", "you want a modern weak-supervision pipeline - consider the Snorkel project instead", "you need a lightweight library rather than a full system with database dependencies"], "when_to_choose": ["you need to construct structured knowledge bases from large unstructured corpora", "you want distant-supervision-based extraction without hand-labeling training data", "you work with domain-specific text like scientific or legal documents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deepdive", "repo": "HazyResearch/deepdive", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:01.628170+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:04:40.992206+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e346826cd46ee49603bf6728065b9a58ce2801d787629cf95e29e1852ac8ffdd", "fetched_at": "2026-08-28T04:06:01.628170+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/deepdive"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4550, "days_push": 1546, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}