{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/node","entry":"Node","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":32,"n_papers_ran":20,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":33,"n_samples_ran":21,"n_samples_fingerprinted":0,"n_places":33,"n_places_pointer_only":21,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":21,"unverified":12},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.09208","paper":"/paper/arxiv-2608-09208","title":"FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"nclabteam/FedA2L","path":"strategies/DFedAvg_FedA2L.py","file_url":"https://github.com/nclabteam/FedA2L/blob/HEAD/strategies/DFedAvg_FedA2L.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8911ffbcff2bff4","mcp_get_code":{"code_sha256":"a8911ffbcff2bff4"}},{"arxiv_id":"2605.23826","paper":"/paper/arxiv-2605-23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"michalsr/ToolMerge","path":"toolmerge/merging.py","file_url":"https://github.com/michalsr/ToolMerge/blob/HEAD/toolmerge/merging.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ab481e63d3309673","mcp_get_code":{"code_sha256":"ab481e63d3309673"}},{"arxiv_id":"2605.23473","paper":"/paper/arxiv-2605-23473","title":"Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Evolutionary-Intelligence/pypop","path":"pypop7/optimizers/bo/lamcts.py","file_url":"https://github.com/Evolutionary-Intelligence/pypop/blob/HEAD/pypop7/optimizers/bo/lamcts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"2094dedb2a12c187","mcp_get_code":{"code_sha256":"2094dedb2a12c187"}},{"arxiv_id":"2605.19038","paper":"/paper/arxiv-2605-19038","title":"Guiding Neuro-Symbolic Scenario Generation with Spatio-Temporal Logic","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"lorenzobonin/strelgen","path":"strel/strel_advanced.py","file_url":"https://github.com/lorenzobonin/strelgen/blob/HEAD/strel/strel_advanced.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1dccff18a6086a6d","mcp_get_code":{"code_sha256":"1dccff18a6086a6d"}},{"arxiv_id":"2604.22937","paper":"/paper/arxiv-2604-22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"megagonlabs/AutoPyVerifier","path":"src/autopyverifier/search.py","file_url":"https://github.com/megagonlabs/AutoPyVerifier/blob/HEAD/src/autopyverifier/search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"cab1924a41908e7b","mcp_get_code":{"code_sha256":"cab1924a41908e7b"}},{"arxiv_id":"2604.12060","paper":"/paper/arxiv-2604-12060","title":"Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"nicolashuynh/deft","path":"src/trees/tree.py","file_url":"https://github.com/nicolashuynh/deft/blob/HEAD/src/trees/tree.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"acd2f0f2fd463006","mcp_get_code":{"code_sha256":"acd2f0f2fd463006"}},{"arxiv_id":"2602.09574","paper":"/paper/arxiv-2602-09574","title":"Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Sora-Miyamoto/bg-mcts","path":"treesearch/src/treesearch/algos/bg_mcts.py","file_url":"https://github.com/Sora-Miyamoto/bg-mcts/blob/HEAD/treesearch/src/treesearch/algos/bg_mcts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c75dbc1227c763cf","mcp_get_code":{"code_sha256":"c75dbc1227c763cf"}},{"arxiv_id":"2602.06974","paper":"/paper/arxiv-2602-06974","title":"FeudalNav: A Simple Framework for Visual Navigation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"visnavdev/feudalnav","path":"deterministicTrials/models.py","file_url":"https://github.com/visnavdev/feudalnav/blob/HEAD/deterministicTrials/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d48f9e86671b3bca","mcp_get_code":{"code_sha256":"d48f9e86671b3bca"}},{"arxiv_id":"2602.01485","paper":"/paper/arxiv-2602-01485","title":"Predicting and improving test-time scaling laws via reward tail-guided search","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"PotatoJnny/Scaling-Law-Guided-search","path":"Algorithm/algorithms.py","file_url":"https://github.com/PotatoJnny/Scaling-Law-Guided-search/blob/HEAD/Algorithm/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d103b68321fb85fb","mcp_get_code":{"code_sha256":"d103b68321fb85fb"}},{"arxiv_id":"2601.21912","paper":"/paper/arxiv-2601-21912","title":"ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"lilinwz/ProRAG","path":"prorag/prm/mcts.py","file_url":"https://github.com/lilinwz/ProRAG/blob/HEAD/prorag/prm/mcts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9040f1a8dcfcd15c","mcp_get_code":{"code_sha256":"9040f1a8dcfcd15c"}},{"arxiv_id":"2601.20810","paper":"/paper/arxiv-2601-20810","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"iamshahd/ProgrammingKnowledgeGraph","path":"src/core/knowledge_programming_graph.py","file_url":"https://github.com/iamshahd/ProgrammingKnowledgeGraph/blob/HEAD/src/core/knowledge_programming_graph.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5c83fc2c978e17d","mcp_get_code":{"code_sha256":"e5c83fc2c978e17d"}},{"arxiv_id":"2601.06444","paper":"/paper/arxiv-2601-06444","title":"Physics-Informed Tree Search for High-Dimensional Computational Design","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"sbanik2/PyPhysTree","path":"lgtree/MCTS.py","file_url":"https://github.com/sbanik2/PyPhysTree/blob/HEAD/lgtree/MCTS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"672a3ed16be44714","mcp_get_code":{"code_sha256":"672a3ed16be44714"}},{"arxiv_id":"2511.08595","paper":"/paper/arxiv-2511-08595","title":"Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"kimjoonghokim/SSDP","path":"inferenceKit/models/generation/cot/clustering.py","file_url":"https://github.com/kimjoonghokim/SSDP/blob/HEAD/inferenceKit/models/generation/cot/clustering.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"62de166f01bd4056","mcp_get_code":{"code_sha256":"62de166f01bd4056"}},{"arxiv_id":"2505.23566","paper":"/paper/uni-mumer-unified-multi-task-fine-tuning-of","title":"Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bflameswift/uni-mumer","path":"preprocess/unimumer_tree/latex2tree.py","file_url":"https://github.com/bflameswift/uni-mumer/blob/HEAD/preprocess/unimumer_tree/latex2tree.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"902d6fc90dfc3c3b","mcp_get_code":{"code_sha256":"902d6fc90dfc3c3b"}},{"arxiv_id":"2505.22949","paper":"/paper/directed-graph-grammars-for-sequence-based","title":"Directed Graph Grammars for Sequence-based Learning","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiningsunnyday/induction","path":"src/grammar/hrg.py","file_url":"https://github.com/shiningsunnyday/induction/blob/HEAD/src/grammar/hrg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1475f1203ba277d8","mcp_get_code":{"code_sha256":"1475f1203ba277d8"}},{"arxiv_id":"2412.11605","paper":"/paper/spar-self-play-with-tree-search-refinement-to","title":"SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/spar","path":"src/ToT/bfs.py","file_url":"https://github.com/thu-coai/spar/blob/HEAD/src/ToT/bfs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6fd053d873aad5f2","mcp_get_code":{"code_sha256":"6fd053d873aad5f2"}},{"arxiv_id":"2412.07186","paper":"/paper/monte-carlo-tree-search-based-space-transfer","title":"Monte Carlo Tree Search based Space Transfer for Black-box Optimization","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lamda-bbo/mcts-transfer","path":"mcts/MCTS.py","file_url":"https://github.com/lamda-bbo/mcts-transfer/blob/HEAD/mcts/MCTS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d1c4bc7ac1ec6710","mcp_get_code":{"code_sha256":"d1c4bc7ac1ec6710"}},{"arxiv_id":"2410.06802","paper":"/paper/seg2act-global-context-aware-action","title":"Seg2Act: Global Context-aware Action Generation for Document Logical Structuring","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cascip/seg2act","path":"seg2act/eval/ChCatExt/seg2act_eval.py","file_url":"https://github.com/cascip/seg2act/blob/HEAD/seg2act/eval/ChCatExt/seg2act_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0787b1cedd4402f","mcp_get_code":{"code_sha256":"a0787b1cedd4402f"}},{"arxiv_id":"2407.06124","paper":"/paper/structured-generations-using-hierarchical","title":"Structured Generations: Using Hierarchical Clusters to guide Diffusion Models","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JoGo175/diffuse-treevae","path":"models/model.py","file_url":"https://github.com/JoGo175/diffuse-treevae/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26b18e2db111e2c6","mcp_get_code":{"code_sha256":"26b18e2db111e2c6"}},{"arxiv_id":"2402.03131","paper":"/paper/constrained-decoding-for-cross-lingual-label","title":"Constrained Decoding for Cross-lingual Label Projection","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"duonglm38/codec","path":"constrained_decoding.py","file_url":"https://github.com/duonglm38/codec/blob/HEAD/constrained_decoding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8ce6c1a54c20e57","mcp_get_code":{"code_sha256":"e8ce6c1a54c20e57"}},{"arxiv_id":"2310.18443","paper":"/paper/towards-a-fuller-understanding-of-neurons-1","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krlgroup/clustered-compositional-explanations","path":"src/heuristic_search.py","file_url":"https://github.com/krlgroup/clustered-compositional-explanations/blob/HEAD/src/heuristic_search.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"307306f38b84eb6e","mcp_get_code":{"code_sha256":"307306f38b84eb6e"}},{"arxiv_id":"2310.14696","paper":"/paper/tree-of-clarifications-answering-ambiguous","title":"Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gankim/tree-of-clarifications","path":"toc/tree.py","file_url":"https://github.com/gankim/tree-of-clarifications/blob/HEAD/toc/tree.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f246ae3401dd6507","mcp_get_code":{"code_sha256":"f246ae3401dd6507"}},{"arxiv_id":"2310.01972","paper":"/paper/epidemic-learning-boosting-decentralized-1","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacs-epfl/decentralizepy","path":"src/decentralizepy/node/EpidemicLearning/EL_Local.py","file_url":"https://github.com/sacs-epfl/decentralizepy/blob/HEAD/src/decentralizepy/node/EpidemicLearning/EL_Local.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"331cb910e4e7bf53","mcp_get_code":{"code_sha256":"331cb910e4e7bf53"}},{"arxiv_id":"2310.01717","paper":"/paper/ensemble-distillation-for-unsupervised","title":"Ensemble Distillation for Unsupervised Constituency Parsing","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manga-uofa/ed4ucp","path":"library/ensemble.py","file_url":"https://github.com/manga-uofa/ed4ucp/blob/HEAD/library/ensemble.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d6e1aa4c953f9558","mcp_get_code":{"code_sha256":"d6e1aa4c953f9558"}},{"arxiv_id":"2306.03929","paper":"/paper/finding-counterfactually-optimal-action","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"networks-learning/counterfactual-continuous-mdp","path":"src/mimic_mdp.py","file_url":"https://github.com/networks-learning/counterfactual-continuous-mdp/blob/HEAD/src/mimic_mdp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b8907f345f3a4a9","mcp_get_code":{"code_sha256":"2b8907f345f3a4a9"}},{"arxiv_id":"2306.00751","paper":"/paper/differentiable-tree-operations-promote","title":"Differentiable Tree Operations Promote Compositional Generalization","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"psoulos/dtm","path":"models.py","file_url":"https://github.com/psoulos/dtm/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"332cd0fb6cfc0dab","mcp_get_code":{"code_sha256":"332cd0fb6cfc0dab"}},{"arxiv_id":"2304.06686","paper":"/paper/okridge-scalable-optimal-k-sparse-ridge","title":"OKRidge: Scalable Optimal k-Sparse Ridge Regression","date":"2023-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiachangliu/okridge","path":"src/okridge/tree.py","file_url":"https://github.com/jiachangliu/okridge/blob/HEAD/src/okridge/tree.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4925be329c6c8ffc","mcp_get_code":{"code_sha256":"4925be329c6c8ffc"}},{"arxiv_id":"2210.15479","paper":"/paper/low-rank-modular-reinforcement-learning-via","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","date":"2022-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"drdh/synergy-rl","path":"modular-rl/src/algs/Synergy.py","file_url":"https://github.com/drdh/synergy-rl/blob/HEAD/modular-rl/src/algs/Synergy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ef02ab5bf78a2c37","mcp_get_code":{"code_sha256":"ef02ab5bf78a2c37"}},{"arxiv_id":"2009.07365","paper":"/paper/fast-semantic-parsing-with-well-typedness","title":"Fast semantic parsing with well-typedness guarantees","date":"2020-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Oneplus/tamr","path":"amr_aligner/system/eager/state.py","file_url":"https://github.com/Oneplus/tamr/blob/HEAD/amr_aligner/system/eager/state.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a363d848e14c5c1e","mcp_get_code":{"code_sha256":"a363d848e14c5c1e"}},{"arxiv_id":"2004.00221","paper":"/paper/nbdt-neural-backed-decision-trees","title":"NBDT: Neural-Backed Decision Trees","date":"2020-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XAVILLA/nbdt","path":"nbdt/model.py","file_url":"https://github.com/XAVILLA/nbdt/blob/HEAD/nbdt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20d642b846aa125d","mcp_get_code":{"code_sha256":"20d642b846aa125d"}},{"arxiv_id":"1911.08265","paper":"/paper/mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Miatto-research-group/muzero","path":"muzero.py","file_url":"https://github.com/Miatto-research-group/muzero/blob/HEAD/muzero.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c75c7c9c180b73f","mcp_get_code":{"code_sha256":"5c75c7c9c180b73f"}},{"arxiv_id":"1911.08265","paper":"/paper/mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmiracle/muzero-starter","path":"pseudocode.py","file_url":"https://github.com/dmiracle/muzero-starter/blob/HEAD/pseudocode.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f69c690385c860bb","mcp_get_code":{"code_sha256":"f69c690385c860bb"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1jsingh/rl_navigation","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"896578e9d4f08299","mcp_get_code":{"code_sha256":"896578e9d4f08299"}}]}