{"adoption": {"forks": 25, "observed_at": "2026-08-28T04:03:13.117374+00:00", "stars": 1011}, "canonical_url": "https://ross.abutalabs.com/products/bird-interact", "card": {"archived": false, "artifact_type": "dataset", "description": "[ICLR 2026 Oral] BIRD-INTERACT: Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.", "domain": ["databases", "large-language-models", "artificial-intelligence"], "enriched": true, "function": ["benchmarking", "llm-inference", "agent-framework", "database", "nlp"], "health_score": 65, "homepage": "https://bird-interact.github.io/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["bird-bench/BIRD-Interact"], "name": "bird-bench/BIRD-Interact", "platform": ["python", "cli"], "pushed_at": "2026-03-29T07:54:22+00:00", "repo": "bird-bench/BIRD-Interact", "stars": 1011, "tags": ["text-to-sql", "benchmark", "interactive-evaluation", "user-simulator", "llm-evaluation", "sql", "ai-agents", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["evaluate LLMs on interactive text-to-sql tasks", "benchmark agentic database assistants", "test conversational SQL generation with clarifying questions", "measure model performance on CRUD and BI database tasks", "compare reasoning models on multi-turn database interaction", "research dynamic evaluation for text-to-sql"], "what_it_is": "BIRD-INTERACT is an interactive Text-to-SQL benchmark that evaluates LLMs through dynamic multi-turn interactions with a simulated user, a hierarchical knowledge base, and database documentation. It provides 600 annotated tasks spanning BI and CRUD operations in passive conversational and active agentic modes, each guarded by executable test cases.", "when_to_avoid": ["you need a simple static text-to-SQL dataset without interaction", "you need a lightweight single-turn SQL generation benchmark", "your focus is non-SQL code generation evaluation"], "when_to_choose": ["you need a rigorous, executable-test-guarded benchmark for interactive Text-to-SQL", "you want to evaluate agents that must ask clarifying questions or act proactively", "you are benchmarking production-ready database assistant capabilities"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bird-interact", "repo": "bird-bench/BIRD-Interact", "role": "main", "score": 52}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:13.117374+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:11:49.541259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "369758f88880c00d4fe8af0d9d074b9290a73e62d45580c87f88fbcbfb392822", "fetched_at": "2026-08-28T04:03:13.117374+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-Interact"}, {"content_hash": "4250d1f7a2d20306bc6d5b2a5223c379fbe90cc5a4c874eeed25195f2fb7572f", "fetched_at": "2026-08-29T13:11:38.750692+00:00", "kind": "homepage", "missing": false, "url": "https://bird-interact.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 74, "longevity": 33, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 469, "days_push": 157, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 52, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}