{"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/is-numeric","entry":"is_numeric","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":28,"n_papers_ran":23,"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":9,"n_samples_ran":7,"n_samples_fingerprinted":4,"n_places":28,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":2},"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":"2608.02332","paper":"/paper/arxiv-2608-02332","title":"Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"aviralkumar2907/CQL","path":"d4rl/rlkit/pythonplusplus.py","file_url":"https://github.com/aviralkumar2907/CQL/blob/HEAD/d4rl/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2607.09371","paper":"/paper/arxiv-2607-09371","title":"Spectrally Deconfounded Gradient Boosting","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"fabsig/GPBoost","path":"python-package/gpboost/basic.py","file_url":"https://github.com/fabsig/GPBoost/blob/HEAD/python-package/gpboost/basic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2076b13e5ea7eb87","mcp_get_code":{"code_sha256":"2076b13e5ea7eb87"}},{"arxiv_id":"2602.05786","paper":"/paper/arxiv-2602-05786","title":"Selecting Hyperparameters for Tree-Boosting","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"fl0risk/HPOTreeBoosting","path":"utils.py","file_url":"https://github.com/fl0risk/HPOTreeBoosting/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2076b13e5ea7eb87","mcp_get_code":{"code_sha256":"2076b13e5ea7eb87"}},{"arxiv_id":"2508.15868","paper":"/paper/arxiv-2508-15868","title":"CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"WNQzhu/CARFT","path":"code/mwp_ReFT/src/utils.py","file_url":"https://github.com/WNQzhu/CARFT/blob/HEAD/code/mwp_ReFT/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3b86a3bceec86cd","mcp_get_code":{"code_sha256":"c3b86a3bceec86cd"}},{"arxiv_id":"2507.08387","paper":null,"title":"arXiv:2507.08387","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"shlee94/Off2OnRL","path":"rlkit/rlkit/pythonplusplus.py","file_url":"https://github.com/shlee94/Off2OnRL/blob/HEAD/rlkit/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2410.05757","paper":"/paper/temperature-optimization-for-bayesian-deep","title":"Temperature Optimization for Bayesian Deep Learning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weiyaw/tempered-posteriors","path":"training.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/training.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d4d5d0d375201d6","mcp_get_code":{"code_sha256":"0d4d5d0d375201d6"}},{"arxiv_id":"2406.00132","paper":"/paper/quanta-efficient-high-rank-fine-tuning-of","title":"QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"quanta-fine-tuning/quanta","path":"run/utils/metrics.py","file_url":"https://github.com/quanta-fine-tuning/quanta/blob/HEAD/run/utils/metrics.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":"9dfc4c4547d0b93e","mcp_get_code":{"code_sha256":"9dfc4c4547d0b93e"}},{"arxiv_id":"2404.03592","paper":"/paper/reft-representation-finetuning-for-language","title":"ReFT: Representation Finetuning for Language Models","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lqtrung1998/mwp_reft","path":"src/utils.py","file_url":"https://github.com/lqtrung1998/mwp_reft/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c3b86a3bceec86cd","mcp_get_code":{"code_sha256":"c3b86a3bceec86cd"}},{"arxiv_id":"2402.17786","paper":"/paper/stepwise-self-consistent-mathematical","title":"Stepwise Self-Consistent Mathematical Reasoning with Large Language Models","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhao-zilong/ssc-cot","path":"KG.py","file_url":"https://github.com/zhao-zilong/ssc-cot/blob/HEAD/KG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"abb2b7f03cf38f35","mcp_get_code":{"code_sha256":"abb2b7f03cf38f35"}},{"arxiv_id":"2402.05808","paper":"/paper/training-large-language-models-for-reasoning","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woooodyy/llm-reverse-curriculum-rl","path":"R3_math/src/utils.py","file_url":"https://github.com/woooodyy/llm-reverse-curriculum-rl/blob/HEAD/R3_math/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3b86a3bceec86cd","mcp_get_code":{"code_sha256":"c3b86a3bceec86cd"}},{"arxiv_id":"2401.08967","paper":"/paper/reft-reasoning-with-reinforced-fine-tuning","title":"ReFT: Reasoning with Reinforced Fine-Tuning","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lqtrung1998/mwp_ReFT","path":"src/utils.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c3b86a3bceec86cd","mcp_get_code":{"code_sha256":"c3b86a3bceec86cd"}},{"arxiv_id":"2312.08153","paper":"/paper/r-diffusion-a-diffusion-based-density","title":"$ρ$-Diffusion: A diffusion-based density estimation framework for computational physics","date":"2023-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intel/rho-diffusion","path":"rho_diffusion/hypothesis_utils.py","file_url":"https://github.com/intel/rho-diffusion/blob/HEAD/rho_diffusion/hypothesis_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6bc2ba621397fee0","mcp_get_code":{"code_sha256":"6bc2ba621397fee0"}},{"arxiv_id":"2311.05067","paper":"/paper/accelerating-exploration-with-unlabeled-prior-1","title":"Accelerating Exploration with Unlabeled Prior Data","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"avisingh599/cog","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/avisingh599/cog/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2310.15147","paper":"/paper/s3eval-a-synthetic-scalable-systematic","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lfy79001/s3eval","path":"eval/claude.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/eval/claude.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2ca80fb7cf12de69","mcp_get_code":{"code_sha256":"2ca80fb7cf12de69"}},{"arxiv_id":"2307.05891","paper":"/paper/pid-inspired-inductive-biases-for-deep-1","title":"PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks","date":"2023-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IanChar/GPIDE","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/IanChar/GPIDE/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2305.19746","paper":"/paper/adaptive-and-explainable-deployment-of","title":"Adaptive and Explainable Deployment of Navigation Skills via Hierarchical Deep Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2023-05","title_source":"archive","repo":"leekwoon/hrl-nav","path":"src/rlkit/pythonplusplus.py","file_url":"https://github.com/leekwoon/hrl-nav/blob/HEAD/src/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2212.13936","paper":"/paper/on-pathologies-in-kl-regularized-1","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","date":"2022-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conglu1997/nppac","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/conglu1997/nppac/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2201.06239","paper":"/paper/mt-gbm-a-multi-task-gradient-boosting-machine-1","title":"MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Trees","date":"2022-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antmachineintelligence/mtgbmcode","path":"python-package/lightgbmmt/basic.py","file_url":"https://github.com/antmachineintelligence/mtgbmcode/blob/HEAD/python-package/lightgbmmt/basic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"2076b13e5ea7eb87","mcp_get_code":{"code_sha256":"2076b13e5ea7eb87"}},{"arxiv_id":"2110.03655","paper":"/paper/augmenting-reinforcement-learning-with","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","date":"2021-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UT-Austin-RPL/maple","path":"maple/pythonplusplus.py","file_url":"https://github.com/UT-Austin-RPL/maple/blob/HEAD/maple/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2104.09122","paper":"/paper/probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","date":"2021-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JieRen98/rlkit-pmoe","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2010.08252","paper":"/paper/hyperparameter-auto-tuning-in-self-supervised","title":"Hyperparameter Auto-tuning in Self-Supervised Robotic Learning","date":"2020-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"birlrobotics/rlkit_autotune","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/birlrobotics/rlkit_autotune/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2006.13916","paper":"/paper/off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shreyasc-13/off_domain_rlkit","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/shreyasc-13/off_domain_rlkit/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"2006.04779","paper":"/paper/conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ikostrikov/cql-results","path":"d4rl/rlkit/pythonplusplus.py","file_url":"https://github.com/ikostrikov/cql-results/blob/HEAD/d4rl/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"1912.11032","paper":"/paper/towards-practical-multi-object-manipulation","title":"Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning","date":"2019-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richardrl/rlkit-relational","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/richardrl/rlkit-relational/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"1911.08453","paper":"/paper/planning-with-goal-conditioned-policies-1","title":"Planning with Goal-Conditioned Policies","date":"2019-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snasiriany/leap","path":"railrl/pythonplusplus.py","file_url":"https://github.com/snasiriany/leap/blob/HEAD/railrl/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"1910.12827","paper":"/paper/entity-abstraction-in-visual-model-based","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","date":"2019-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jcoreyes/OP3","path":"op3/pythonplusplus.py","file_url":"https://github.com/jcoreyes/OP3/blob/HEAD/op3/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"1910.11670","paper":"/paper/contextual-imagined-goals-for-self-supervised","title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","date":"2019-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anair13/rlkit","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/anair13/rlkit/blob/HEAD/rlkit/pythonplusplus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4138766e854db009","mcp_get_code":{"code_sha256":"4138766e854db009"}},{"arxiv_id":"1012.2599","paper":"/paper/a-tutorial-on-bayesian-optimization-of","title":"A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning","date":"2010-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bayesian-optimization/bayesianoptimization","path":"bayes_opt/parameter.py","file_url":"https://github.com/bayesian-optimization/bayesianoptimization/blob/HEAD/bayes_opt/parameter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a2732ed857b86a4f","mcp_get_code":{"code_sha256":"a2732ed857b86a4f"}}]}