{"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/default-init","entry":"default_init","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":38,"n_papers_ran":24,"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":21,"n_samples_ran":13,"n_samples_fingerprinted":0,"n_places":40,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":0,"ran":8,"unverified":8},"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":"2609.15883","paper":"/paper/arxiv-2609-15883","title":"Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Yonsei-DILLab/OptiFlow","path":"optiflow/networks.py","file_url":"https://github.com/Yonsei-DILLab/OptiFlow/blob/HEAD/optiflow/networks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2aaa6f4e0d62bf22","mcp_get_code":{"code_sha256":"2aaa6f4e0d62bf22"}},{"arxiv_id":"2608.01205","paper":"/paper/arxiv-2608-01205","title":"ReBRAC-v2: The Return of the King","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"JongseongChae/FAC","path":"agents/rebrac.py","file_url":"https://github.com/JongseongChae/FAC/blob/HEAD/agents/rebrac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2aaa6f4e0d62bf22","mcp_get_code":{"code_sha256":"2aaa6f4e0d62bf22"}},{"arxiv_id":"2606.11087","paper":"/paper/arxiv-2606-11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"zhouzypaul/qgf","path":"utils/networks.py","file_url":"https://github.com/zhouzypaul/qgf/blob/HEAD/utils/networks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2aaa6f4e0d62bf22","mcp_get_code":{"code_sha256":"2aaa6f4e0d62bf22"}},{"arxiv_id":"2605.11125","paper":"/paper/arxiv-2605-11125","title":"Language Modeling with Hyperspherical Flows","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"s-sahoo/duo","path":"models/unet.py","file_url":"https://github.com/s-sahoo/duo/blob/HEAD/models/unet.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":"fdd6aad96accd488","mcp_get_code":{"code_sha256":"fdd6aad96accd488"}},{"arxiv_id":"2603.05066","paper":"/paper/arxiv-2603-05066","title":"Reward-Conditioned Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"naumix/BiggerRegularizedCategorical","path":"jaxrl/agent/brc_learner.py","file_url":"https://github.com/naumix/BiggerRegularizedCategorical/blob/HEAD/jaxrl/agent/brc_learner.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e1b1dbdf882411b","mcp_get_code":{"code_sha256":"7e1b1dbdf882411b"}},{"arxiv_id":"2512.04341","paper":"/paper/arxiv-2512-04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"proroklab/memoroids","path":"modules.py","file_url":"https://github.com/proroklab/memoroids/blob/HEAD/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e31de52332dff52c","mcp_get_code":{"code_sha256":"e31de52332dff52c"}},{"arxiv_id":"2506.18841","paper":"/paper/longwriter-zero-mastering-ultra-long-text","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/longwriter","path":"train/patch/modeling_chatglm.py","file_url":"https://github.com/thudm/longwriter/blob/HEAD/train/patch/modeling_chatglm.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":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2412.10193","paper":"/paper/simple-guidance-mechanisms-for-discrete","title":"Simple Guidance Mechanisms for Discrete Diffusion Models","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/discrete-diffusion-guidance","path":"models/unet.py","file_url":"https://github.com/kuleshov-group/discrete-diffusion-guidance/blob/HEAD/models/unet.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":"fdd6aad96accd488","mcp_get_code":{"code_sha256":"fdd6aad96accd488"}},{"arxiv_id":"2411.07007","paper":"/paper/non-adversarial-inverse-reinforcement","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arnavkj1995/sfm","path":"agents/sfm_sac.py","file_url":"https://github.com/arnavkj1995/sfm/blob/HEAD/agents/sfm_sac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5e2d65ae4ba9bc6","mcp_get_code":{"code_sha256":"c5e2d65ae4ba9bc6"}},{"arxiv_id":"2410.18076","paper":"/paper/leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rail-berkeley/supe","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58986e64f92121be","mcp_get_code":{"code_sha256":"58986e64f92121be"}},{"arxiv_id":"2410.03577","paper":"/paper/look-twice-before-you-answer-memory-space","title":"Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1zhou-Wang/MemVR","path":"modeling/modeling_chatglm.py","file_url":"https://github.com/1zhou-Wang/MemVR/blob/HEAD/modeling/modeling_chatglm.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":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2409.18359","paper":"/paper/generative-ai-for-fast-and-accurate","title":"Generative AI for fast and accurate statistical computation of fluids","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"camlab-ethz/gencfd","path":"GenCFD/utils/model_utils.py","file_url":"https://github.com/camlab-ethz/gencfd/blob/HEAD/GenCFD/utils/model_utils.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":"ec800de8d7a491d0","mcp_get_code":{"code_sha256":"ec800de8d7a491d0"}},{"arxiv_id":"2408.10943","paper":"/paper/sysbench-can-large-language-models-follow","title":"SysBench: Can Large Language Models Follow System Messages?","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-baichuan-mlsystemlab/sysbench","path":"attenscore/modeling_chatglm.py","file_url":"https://github.com/pku-baichuan-mlsystemlab/sysbench/blob/HEAD/attenscore/modeling_chatglm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2405.03379","paper":"/paper/reverse-forward-curriculum-learning-for","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","date":"2024-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonet2000/rfcl","path":"rfcl/models/mlp.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/models/mlp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8302176def1e542","mcp_get_code":{"code_sha256":"d8302176def1e542"}},{"arxiv_id":"2405.03379","paper":"/paper/reverse-forward-curriculum-learning-for","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","date":"2024-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonet2000/rfcl","path":"rfcl/agents/sac/networks.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/agents/sac/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32b82cb936cbd54d","mcp_get_code":{"code_sha256":"32b82cb936cbd54d"}},{"arxiv_id":"2402.11809","paper":"/paper/generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cteant/space","path":"src/models/modeling_chatglm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_chatglm.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":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2402.04467","paper":"/paper/dyslim-dynamics-stable-learning-by-invariant","title":"DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/swirl-dynamics","path":"swirl_dynamics/lib/diffusion/unets.py","file_url":"https://github.com/google-research/swirl-dynamics/blob/HEAD/swirl_dynamics/lib/diffusion/unets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5aeb858a9d4f09ef","mcp_get_code":{"code_sha256":"5aeb858a9d4f09ef"}},{"arxiv_id":"2401.18058","paper":"/paper/longalign-a-recipe-for-long-context-alignment","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","date":"2024-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/longalign","path":"modeling_chatglm.py","file_url":"https://github.com/thudm/longalign/blob/HEAD/modeling_chatglm.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":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2401.11037","paper":"/paper/equivariant-graph-neural-operator-for","title":"Equivariant Graph Neural Operator for Modeling 3D Dynamics","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minkaixu/egno","path":"model/layer_no.py","file_url":"https://github.com/minkaixu/egno/blob/HEAD/model/layer_no.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04548c6c9fff2b3f","mcp_get_code":{"code_sha256":"04548c6c9fff2b3f"}},{"arxiv_id":"2312.10431","paper":"/paper/continuous-diffusion-for-mixed-type-tabular","title":"Continuous Diffusion for Mixed-Type Tabular Data","date":"2023-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChaejeongLee/CoDi","path":"models/layers.py","file_url":"https://github.com/ChaejeongLee/CoDi/blob/HEAD/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66362066ac43ccc4","mcp_get_code":{"code_sha256":"66362066ac43ccc4"}},{"arxiv_id":"2311.18445","paper":"/paper/vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huangb23/vtimellm","path":"vtimellm/model/chatglm/modeling_chatglm.py","file_url":"https://github.com/huangb23/vtimellm/blob/HEAD/vtimellm/model/chatglm/modeling_chatglm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2310.17966","paper":"/paper/train-once-get-a-family-state-adaptive-1","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/famo2o","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29e1a06c6560973e","mcp_get_code":{"code_sha256":"29e1a06c6560973e"}},{"arxiv_id":"2310.17966","paper":"/paper/train-once-get-a-family-state-adaptive-1","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/FamO2O","path":"jax_iql/common.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_iql/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"718462716d78ea99","mcp_get_code":{"code_sha256":"718462716d78ea99"}},{"arxiv_id":"2310.12920","paper":"/paper/generative-marginalization-models","title":"Generative Marginalization Models","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrincetonLIPS/MaM","path":"mam/models/layers.py","file_url":"https://github.com/PrincetonLIPS/MaM/blob/HEAD/mam/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdd6aad96accd488","mcp_get_code":{"code_sha256":"fdd6aad96accd488"}},{"arxiv_id":"2307.13528","paper":"/paper/factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/sdak","path":"code/workers/modeling_chatglm.py","file_url":"https://github.com/freedomintelligence/sdak/blob/HEAD/code/workers/modeling_chatglm.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":"237019e36b9481d9","mcp_get_code":{"code_sha256":"237019e36b9481d9"}},{"arxiv_id":"2306.02562","paper":"/paper/video-diffusion-models-with-local-global","title":"Video Diffusion Models with Local-Global Context Guidance","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"exisas/LGC-VD","path":"model/utils.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdd6aad96accd488","mcp_get_code":{"code_sha256":"fdd6aad96accd488"}},{"arxiv_id":"2305.19693","paper":"/paper/spontaneous-symmetry-breaking-in-generative-1","title":"Spontaneous Symmetry Breaking in Generative Diffusion Models","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gabrielraya/symmetry_breaking_diffusion_models","path":"models/layers.py","file_url":"https://github.com/gabrielraya/symmetry_breaking_diffusion_models/blob/HEAD/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04548c6c9fff2b3f","mcp_get_code":{"code_sha256":"04548c6c9fff2b3f"}},{"arxiv_id":"2304.10466","paper":"/paper/efficient-deep-reinforcement-learning","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","date":"2023-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evgenii-nikishin/rl_with_resets","path":"continuous_control/networks/common.py","file_url":"https://github.com/evgenii-nikishin/rl_with_resets/blob/HEAD/continuous_control/networks/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"718462716d78ea99","mcp_get_code":{"code_sha256":"718462716d78ea99"}},{"arxiv_id":"2303.15810","paper":"/paper/offline-rl-with-no-ood-actions-in-sample","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryanxhr/IVR","path":"common.py","file_url":"https://github.com/ryanxhr/IVR/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"718462716d78ea99","mcp_get_code":{"code_sha256":"718462716d78ea99"}},{"arxiv_id":"2303.00957","paper":"/paper/preference-transformer-modeling-human","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","date":"2023-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csmile-1006/preferencetransformer","path":"common.py","file_url":"https://github.com/csmile-1006/preferencetransformer/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"718462716d78ea99","mcp_get_code":{"code_sha256":"718462716d78ea99"}},{"arxiv_id":"2302.04362","paper":"/paper/disentangling-learning-representations-with","title":"Disentangling Learning Representations with Density Estimation","date":"2023-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ericyeats/gcae-disentanglement","path":"src/architectures.py","file_url":"https://github.com/ericyeats/gcae-disentanglement/blob/HEAD/src/architectures.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1d504336b0f31fc","mcp_get_code":{"code_sha256":"e1d504336b0f31fc"}},{"arxiv_id":"2301.12842","paper":"/paper/direct-preference-based-policy-optimization-1","title":"Direct Preference-based Policy Optimization without Reward Modeling","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snu-mllab/DPPO","path":"common.py","file_url":"https://github.com/snu-mllab/DPPO/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"718462716d78ea99","mcp_get_code":{"code_sha256":"718462716d78ea99"}},{"arxiv_id":"2211.13449","paper":"/paper/fast-sampling-of-diffusion-models-via","title":"Fast Sampling of Diffusion Models via Operator Learning","date":"2022-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"devzhk/dsno-pytorch","path":"models/layers.py","file_url":"https://github.com/devzhk/dsno-pytorch/blob/HEAD/models/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04548c6c9fff2b3f","mcp_get_code":{"code_sha256":"04548c6c9fff2b3f"}},{"arxiv_id":"2206.11892","paper":"/paper/remote-sensing-change-detection-segmentation","title":"DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection","date":"2022-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wgcban/ddpm-cd","path":"model/ddpm_modules/vanilla_unet.py","file_url":"https://github.com/wgcban/ddpm-cd/blob/HEAD/model/ddpm_modules/vanilla_unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66362066ac43ccc4","mcp_get_code":{"code_sha256":"66362066ac43ccc4"}},{"arxiv_id":"2206.05564","paper":"/paper/gddim-generalized-denoising-diffusion","title":"gDDIM: Generalized denoising diffusion implicit models","date":"2022-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qsh-zh/gDDIM","path":"blur_jax/models/layers.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/models/layers.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":"f537ef3271967db2","mcp_get_code":{"code_sha256":"f537ef3271967db2"}},{"arxiv_id":"2206.01079","paper":"/paper/when-does-return-conditioned-supervised","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","date":"2022-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidbrandfonbrener/rcsl-paper","path":"jax_continuous_rl/jaxrl/networks/common.py","file_url":"https://github.com/davidbrandfonbrener/rcsl-paper/blob/HEAD/jax_continuous_rl/jaxrl/networks/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"facdc73f9b000275","mcp_get_code":{"code_sha256":"facdc73f9b000275"}},{"arxiv_id":"2205.09853","paper":"/paper/masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"voletiv/mcvd-pytorch","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90b0411e98af1284","mcp_get_code":{"code_sha256":"90b0411e98af1284"}},{"arxiv_id":"2106.03273","paper":"/paper/control-oriented-model-based-reinforcement","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evgenii-nikishin/omd","path":"mujoco/jax_rl/networks/common.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/mujoco/jax_rl/networks/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bd2d556360ac9c9","mcp_get_code":{"code_sha256":"1bd2d556360ac9c9"}},{"arxiv_id":"1812.05905","paper":"/paper/soft-actor-critic-algorithms-and-applications","title":"Soft Actor-Critic Algorithms and Applications","date":"2018-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"patrickhart/jaxdl","path":"jaxdl/nn/dnn/conv.py","file_url":"https://github.com/patrickhart/jaxdl/blob/HEAD/jaxdl/nn/dnn/conv.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e5ed014bde23917","mcp_get_code":{"code_sha256":"7e5ed014bde23917"}},{"arxiv_id":"openreview_RdkOaK4q6p","paper":null,"title":"arXiv:openreview_RdkOaK4q6p","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"2012060/DFQL","path":"utils/networks.py","file_url":"https://github.com/2012060/DFQL/blob/HEAD/utils/networks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2aaa6f4e0d62bf22","mcp_get_code":{"code_sha256":"2aaa6f4e0d62bf22"}}]}