{"adoption": {"forks": 163, "observed_at": "2026-08-28T04:06:52.767715+00:00", "stars": 2448}, "canonical_url": "https://ross.abutalabs.com/products/logic-rl", "card": {"archived": false, "artifact_type": "library", "description": "Reproduce R1 Zero on Logic Puzzle", "domain": ["large-language-models", "reinforcement-learning", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["llm-training", "reinforcement-learning", "machine-learning", "benchmarking"], "health_score": 27, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Unakar/Logic-RL"], "name": "Unakar/Logic-RL", "platform": ["python"], "pushed_at": "2025-03-20T06:24:26+00:00", "repo": "Unakar/Logic-RL", "stars": 2448, "tags": ["grpo", "verl", "vllm", "rule-based-reward", "logic-puzzles", "reasoning", "r1-zero", "research-code", "gpu", "linux", "docker"], "topics": [], "urls": [], "use_cases": ["train an LLM to reason with rule-based reinforcement learning", "reproduce R1 Zero emergent reasoning behavior", "run GRPO training on logic puzzle datasets", "benchmark small models on multi-person logic puzzles", "generate and preprocess knight-and-knave puzzle data"], "what_it_is": "Logic-RL is a research framework that reproduces R1-Zero-style LLM reasoning via rule-based reinforcement learning (GRPO) on logic puzzles, built on verl and vLLM. It includes data preprocessing, reward modeling, and training scripts for 4×A100 setups.", "when_to_avoid": ["you need a production LLM serving or inference system", "you lack GPU cluster resources for RL training", "you want a general-purpose RL library rather than a research reproduction"], "when_to_choose": ["you want to replicate or extend rule-based RL for LLM reasoning research", "you have multi-GPU (A100) resources and want a working verl/vLLM training pipeline", "you need a reproducible baseline for reasoning benchmarks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/logic-rl", "repo": "Unakar/Logic-RL", "role": "main", "score": 26}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.767715+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:30:27.527660+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab777ba05d7bb3ea2dec530c7e6ef8b46d3a302135b9e838ea31883c413d12a8", "fetched_at": "2026-08-28T04:06:52.767715+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unakar/Logic-RL"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 12, "longevity": 41, "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": 577, "days_push": 531, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 26, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}