{"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/init","entry":"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":55,"n_papers_ran":38,"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":27,"n_samples_ran":9,"n_samples_fingerprinted":0,"n_places":58,"n_places_pointer_only":17,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":4,"unverified":18},"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":"2607.19181","paper":"/paper/arxiv-2607-19181","title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"aixiuxiuxiu/Legal-MT-SFT-RL","path":"dist.py","file_url":"https://github.com/aixiuxiuxiu/Legal-MT-SFT-RL/blob/HEAD/dist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"968bb0ff4e9f3f20","mcp_get_code":{"code_sha256":"968bb0ff4e9f3f20"}},{"arxiv_id":"2604.13472","paper":"/paper/arxiv-2604-13472","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"PKU-MARL/Multi-Agent-Transformer","path":"mat/algorithms/mat/algorithm/ma_transformer.py","file_url":"https://github.com/PKU-MARL/Multi-Agent-Transformer/blob/HEAD/mat/algorithms/mat/algorithm/ma_transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c00885ffa5fe61e7","mcp_get_code":{"code_sha256":"c00885ffa5fe61e7"}},{"arxiv_id":"2604.03523","paper":"/paper/arxiv-2604-03523","title":"Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"NACLab/neurorobot-preference-regret-learning","path":"lib/agent/active.py","file_url":"https://github.com/NACLab/neurorobot-preference-regret-learning/blob/HEAD/lib/agent/active.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2946157301d5cc74","mcp_get_code":{"code_sha256":"2946157301d5cc74"}},{"arxiv_id":"2603.24366","paper":"/paper/arxiv-2603-24366","title":"CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"marmotlab/CoordLight","path":"Models/CoordLightModel.py","file_url":"https://github.com/marmotlab/CoordLight/blob/HEAD/Models/CoordLightModel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c31c51db289b4c16","mcp_get_code":{"code_sha256":"c31c51db289b4c16"}},{"arxiv_id":"2509.25550","paper":"/paper/arxiv-2509-25550","title":"Unifying Agent Interaction and World Information for Multi-agent Coordination","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"zoeyuchao/mappo","path":"onpolicy/algorithms/utils/util.py","file_url":"https://github.com/zoeyuchao/mappo/blob/HEAD/onpolicy/algorithms/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2508.06214","paper":"/paper/arxiv-2508-06214","title":"Reparameterization Proximal Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"SonSang/gippo","path":"src/gippo/network.py","file_url":"https://github.com/SonSang/gippo/blob/HEAD/src/gippo/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0cd749d322eccb6","mcp_get_code":{"code_sha256":"d0cd749d322eccb6"}},{"arxiv_id":"2506.19997","paper":"/paper/traced-transition-aware-regret-approximation","title":"TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design","date":"2025-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cho-Geonwoo/TRACED","path":"models/recurrent_walker_models.py","file_url":"https://github.com/Cho-Geonwoo/TRACED/blob/HEAD/models/recurrent_walker_models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2506.19997","paper":"/paper/traced-transition-aware-regret-approximation","title":"TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design","date":"2025-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cho-Geonwoo/TRACED","path":"models/common.py","file_url":"https://github.com/Cho-Geonwoo/TRACED/blob/HEAD/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f8db408bc65dbb3a","mcp_get_code":{"code_sha256":"f8db408bc65dbb3a"}},{"arxiv_id":"2411.11364","paper":"/paper/continual-task-learning-through-adaptive","title":"Continual Task Learning through Adaptive Policy Self-Composition","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charleshsc/CompoFormer","path":"dt/decision_transformer_grow.py","file_url":"https://github.com/charleshsc/CompoFormer/blob/HEAD/dt/decision_transformer_grow.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c00885ffa5fe61e7","mcp_get_code":{"code_sha256":"c00885ffa5fe61e7"}},{"arxiv_id":"2411.04466","paper":"/paper/enabling-adaptive-agent-training-in-open","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robbycostales/diva","path":"diva/components/policy/networks.py","file_url":"https://github.com/robbycostales/diva/blob/HEAD/diva/components/policy/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e211798265a006a","mcp_get_code":{"code_sha256":"3e211798265a006a"}},{"arxiv_id":"2410.22564","paper":"/paper/vertical-federated-learning-with-missing","title":"Vertical Federated Learning with Missing Features During Training and Inference","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Valdeira/LASER-VFL","path":"models/mimic_model_utils.py","file_url":"https://github.com/Valdeira/LASER-VFL/blob/HEAD/models/mimic_model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4531a69fbf2a306","mcp_get_code":{"code_sha256":"d4531a69fbf2a306"}},{"arxiv_id":"2409.19660","paper":"/paper/all-in-one-image-coding-for-joint-human","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"njuvision/mpa","path":"examples/train_stage1_wo_gan.py","file_url":"https://github.com/njuvision/mpa/blob/HEAD/examples/train_stage1_wo_gan.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6656404be8df535e","mcp_get_code":{"code_sha256":"6656404be8df535e"}},{"arxiv_id":"2409.19660","paper":"/paper/all-in-one-image-coding-for-joint-human","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"njuvision/mpa","path":"examples/eval_cls_real_bpp.py","file_url":"https://github.com/njuvision/mpa/blob/HEAD/examples/eval_cls_real_bpp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ffb7e6e59725022b","mcp_get_code":{"code_sha256":"ffb7e6e59725022b"}},{"arxiv_id":"2409.05344","paper":"/paper/gopt-generalizable-online-3d-bin-packing-via","title":"GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"xiong5heng/gopt","path":"model.py","file_url":"https://github.com/xiong5heng/gopt/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2405.16273","paper":"/paper/m-3-gpt-an-advanced-multimodal-multitask","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luomingshuang/M3GPT","path":"m3gpt/core/fp16/amp.py","file_url":"https://github.com/luomingshuang/M3GPT/blob/HEAD/m3gpt/core/fp16/amp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb8a2600afc1de95","mcp_get_code":{"code_sha256":"eb8a2600afc1de95"}},{"arxiv_id":"2404.17521","paper":"/paper/ag2manip-learning-novel-manipulation-skills","title":"Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xiaoyao-Li/Ag2Manip","path":"algos/utils/util.py","file_url":"https://github.com/Xiaoyao-Li/Ag2Manip/blob/HEAD/algos/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2403.15098","paper":"/paper/unitraj-a-unified-framework-for-scalable","title":"UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-epfl/UniTraj","path":"unitraj/models/autobot/autobot.py","file_url":"https://github.com/vita-epfl/UniTraj/blob/HEAD/unitraj/models/autobot/autobot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d7a51202f8456490","mcp_get_code":{"code_sha256":"d7a51202f8456490"}},{"arxiv_id":"2402.02097","paper":"/paper/settling-decentralized-multi-agent","title":"Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2312.08710","paper":"/paper/gradient-informed-proximal-policy-1","title":"Gradient Informed Proximal Policy Optimization","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sonsang/gippo","path":"src/gippo/network.py","file_url":"https://github.com/sonsang/gippo/blob/HEAD/src/gippo/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0cd749d322eccb6","mcp_get_code":{"code_sha256":"d0cd749d322eccb6"}},{"arxiv_id":"2312.03126","paper":"/paper/learning-curricula-in-open-ended-worlds","title":"Learning Curricula in Open-Ended Worlds","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/dcd","path":"models/common.py","file_url":"https://github.com/facebookresearch/dcd/blob/HEAD/models/common.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2312.01697","paper":"/paper/hulk-a-universal-knowledge-translator-for","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/hulk","path":"core/fp16/amp.py","file_url":"https://github.com/opengvlab/hulk/blob/HEAD/core/fp16/amp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb8a2600afc1de95","mcp_get_code":{"code_sha256":"eb8a2600afc1de95"}},{"arxiv_id":"2311.15112","paper":"/paper/everybody-needs-a-little-help-explaining","title":"Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts","date":"2023-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jonasjuerss/help","path":"custom_logger.py","file_url":"https://github.com/jonasjuerss/help/blob/HEAD/custom_logger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5265ccd1e6a4830b","mcp_get_code":{"code_sha256":"5265ccd1e6a4830b"}},{"arxiv_id":"2311.14670","paper":"/paper/differentiable-and-accelerated-spherical","title":"Differentiable and accelerated spherical harmonic and Wigner transforms","date":"2023-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"astro-informatics/s2fft","path":"s2fft/recursions/trapani.py","file_url":"https://github.com/astro-informatics/s2fft/blob/HEAD/s2fft/recursions/trapani.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94b976a8c3413231","mcp_get_code":{"code_sha256":"94b976a8c3413231"}},{"arxiv_id":"2308.04836","paper":"/paper/intrinsic-motivation-via-surprise-memory","title":"Beyond Surprise: Improving Exploration Through Surprise Novelty","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thaihungle/sm","path":"dist.py","file_url":"https://github.com/thaihungle/sm/blob/HEAD/dist.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2307.00337","paper":"/paper/recursive-algorithmic-reasoning","title":"Recursive Algorithmic Reasoning","date":"2023-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DJayalath/gnn-call-stack","path":"gnn_call_stack/utils.py","file_url":"https://github.com/DJayalath/gnn-call-stack/blob/HEAD/gnn_call_stack/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":"ec6c1cbb5fa6ffa6","mcp_get_code":{"code_sha256":"ec6c1cbb5fa6ffa6"}},{"arxiv_id":"2305.00350","paper":"/paper/pouf-prompt-oriented-unsupervised-fine-tuning","title":"POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models","date":"2023-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"korawat-tanwisuth/pouf","path":"pouf_mlm/src/label_search.py","file_url":"https://github.com/korawat-tanwisuth/pouf/blob/HEAD/pouf_mlm/src/label_search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5fabcb6bbd28aa2f","mcp_get_code":{"code_sha256":"5fabcb6bbd28aa2f"}},{"arxiv_id":"2303.02936","paper":"/paper/unihcp-a-unified-model-for-human-centric","title":"UniHCP: A Unified Model for Human-Centric Perceptions","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/UniHCP","path":"core/fp16/amp.py","file_url":"https://github.com/OpenGVLab/UniHCP/blob/HEAD/core/fp16/amp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb8a2600afc1de95","mcp_get_code":{"code_sha256":"eb8a2600afc1de95"}},{"arxiv_id":"2302.06205","paper":"/paper/order-matters-agent-by-agent-policy","title":"Order Matters: Agent-by-agent Policy Optimization","date":"2023-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xihuai18/A2PO-ICLR2023","path":"onpolicy/algorithms/utils/util.py","file_url":"https://github.com/xihuai18/A2PO-ICLR2023/blob/HEAD/onpolicy/algorithms/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2211.14238","paper":"/paper/wild-time-a-benchmark-of-in-the-wild","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","date":"2022-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huaxiuyao/wild-time","path":"wildtime/baseline_trainer.py","file_url":"https://github.com/huaxiuyao/wild-time/blob/HEAD/wildtime/baseline_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"beca3cd43469c27a","mcp_get_code":{"code_sha256":"beca3cd43469c27a"}},{"arxiv_id":"2210.03104","paper":"/paper/distributionally-adaptive-meta-reinforcement","title":"Distributionally Adaptive Meta Reinforcement Learning","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ikostrikov/pytorch-a2c-ppo-acktr-gail","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/blob/HEAD/a2c_ppo_acktr/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2207.05631","paper":"/paper/dgpo-discovering-multiple-strategies-with","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenRL-Lab/DGPO","path":"onpolicy/algorithms/utils/util.py","file_url":"https://github.com/OpenRL-Lab/DGPO/blob/HEAD/onpolicy/algorithms/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2206.09314","paper":"/paper/robust-imitation-learning-against-variations","title":"Robust Imitation Learning against Variations in Environment Dynamics","date":"2022-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JongseongChae/RIME","path":"algorithm/utils.py","file_url":"https://github.com/JongseongChae/RIME/blob/HEAD/algorithm/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2205.11184","paper":"/paper/an-evaluation-study-of-intrinsic-motivation","title":"An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments","date":"2022-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aklein1995/intrinsic_motivation_techniques_study","path":"model.py","file_url":"https://github.com/aklein1995/intrinsic_motivation_techniques_study/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2204.13841","paper":"/paper/an-extensive-data-processing-pipeline-for","title":"An Extensive Data Processing Pipeline for MIMIC-IV","date":"2022-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"healthylaife/mimic-iv-data-pipeline","path":"model/model_utils.py","file_url":"https://github.com/healthylaife/mimic-iv-data-pipeline/blob/HEAD/model/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7cedea7a54f72fb3","mcp_get_code":{"code_sha256":"7cedea7a54f72fb3"}},{"arxiv_id":"2203.03800","paper":"/paper/unknown-aware-object-detection-learning-what","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deeplearning-wisc/stud","path":"datasets/bdd100k2coco.py","file_url":"https://github.com/deeplearning-wisc/stud/blob/HEAD/datasets/bdd100k2coco.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5113c7c282ca0da7","mcp_get_code":{"code_sha256":"5113c7c282ca0da7"}},{"arxiv_id":"2109.11251","paper":"/paper/trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mehdinasiri/mirror-descent-in-marl","path":"algorithms/utils/util.py","file_url":"https://github.com/mehdinasiri/mirror-descent-in-marl/blob/HEAD/algorithms/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2107.07394","paper":"/paper/explore-and-control-with-adversarial-surprise","title":"Explore and Control with Adversarial Surprise","date":"2021-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ArnaudFickinger/adversarial-surprise","path":"model.py","file_url":"https://github.com/ArnaudFickinger/adversarial-surprise/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2107.00339","paper":"/paper/policy-transfer-across-visual-and-dynamics","title":"Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding","date":"2021-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clvrai/idapt","path":"training/networks/distributions.py","file_url":"https://github.com/clvrai/idapt/blob/HEAD/training/networks/distributions.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2106.14334","paper":"/paper/noisy-mappo-noisy-advantage-values-for","title":"Policy Regularization via Noisy Advantage Values for Cooperative Multi-agent Actor-Critic methods","date":null,"month_inferred_from_arxiv_id":"2021-06","title_source":"archive","repo":"hijkzzz/noisy-mappo","path":"onpolicy/algorithms/utils/util.py","file_url":"https://github.com/hijkzzz/noisy-mappo/blob/HEAD/onpolicy/algorithms/utils/util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2106.08746","paper":"/paper/real-time-attacks-against-deep-reinforcement","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","date":"2021-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssg-research/ad3-action-distribution-divergence-detector","path":"src/agents/models.py","file_url":"https://github.com/ssg-research/ad3-action-distribution-divergence-detector/blob/HEAD/src/agents/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2104.07495","paper":"/paper/self-supervised-exploration-via-latent","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/lbs-exploration","path":"exploration/utils.py","file_url":"https://github.com/mazpie/lbs-exploration/blob/HEAD/exploration/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2103.14274","paper":"/paper/character-controllers-using-motion-vaes","title":"Character Controllers Using Motion VAEs","date":"2021-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"electronicarts/character-motion-vaes","path":"common/controller.py","file_url":"https://github.com/electronicarts/character-motion-vaes/blob/HEAD/common/controller.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2104.00563","paper":"/paper/latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roggirg/AutoBots","path":"models/autobot_joint.py","file_url":"https://github.com/roggirg/AutoBots/blob/HEAD/models/autobot_joint.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2104.00563","paper":"/paper/latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roggirg/AutoBots","path":"models/autobot_ego.py","file_url":"https://github.com/roggirg/AutoBots/blob/HEAD/models/autobot_ego.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":"d7a51202f8456490","mcp_get_code":{"code_sha256":"d7a51202f8456490"}},{"arxiv_id":"2010.01878","paper":"/paper/lazimpa-lazy-and-impatient-neural-agents","title":"\"LazImpa\": Lazy and Impatient neural agents learn to communicate efficiently","date":"2020-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MathieuRita/Lazimpa","path":"egg/core/util.py","file_url":"https://github.com/MathieuRita/Lazimpa/blob/HEAD/egg/core/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c2081da5221dfd6","mcp_get_code":{"code_sha256":"3c2081da5221dfd6"}},{"arxiv_id":"2009.01439","paper":"/paper/dexterous-robotic-grasping-with-object","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","date":"2020-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"priyankamandikal/graff","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/priyankamandikal/graff/blob/HEAD/a2c_ppo_acktr/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2007.05270","paper":"/paper/learning-to-plan-with-uncertain-topological","title":"Learning to plan with uncertain topological maps","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edbeeching/learning_to_plan","path":"layers.py","file_url":"https://github.com/edbeeching/learning_to_plan/blob/HEAD/layers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2006.12862","paper":"/paper/automatic-data-augmentation-for","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","date":"2020-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rraileanu/auto-drac","path":"ucb_rl2_meta/utils.py","file_url":"https://github.com/rraileanu/auto-drac/blob/HEAD/ucb_rl2_meta/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"2006.09447","paper":"/paper/opponent-modelling-with-local-information","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/LIAM","path":"double_speaker_listener/utils.py","file_url":"https://github.com/uoe-agents/LIAM/blob/HEAD/double_speaker_listener/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"1907.09470","paper":"/paper/characterizing-attacks-on-deep-reinforcement","title":"Characterizing Attacks on Deep Reinforcement Learning","date":"2019-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssg-research/flare","path":"src/agents/models.py","file_url":"https://github.com/ssg-research/flare/blob/HEAD/src/agents/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"1906.09712","paper":"/paper/sequential-estimation-of-quantiles-with","title":"Sequential estimation of quantiles with applications to A/B-testing and best-arm identification","date":"2019-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WLM1ke/poptimizer","path":"poptimizer/adapters/logger.py","file_url":"https://github.com/WLM1ke/poptimizer/blob/HEAD/poptimizer/adapters/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Unlicense","inline_ok":true,"code_sha256_prefix":"eff60c9fec6ef025","mcp_get_code":{"code_sha256":"eff60c9fec6ef025"}},{"arxiv_id":"1906.09323","paper":"/paper/reinforcement-learning-with-convex","title":"Reinforcement Learning with Convex Constraints","date":"2019-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xkianteb/ApproPO","path":"ApproPO/nets.py","file_url":"https://github.com/xkianteb/ApproPO/blob/HEAD/ApproPO/nets.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"1905.04640","paper":"/paper/mega-reward-achieving-human-level-play","title":"Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards","date":"2019-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuhangSong/Mega-Reward","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/YuhangSong/Mega-Reward/blob/HEAD/a2c_ppo_acktr/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9de355e93051e4ad","mcp_get_code":{"code_sha256":"9de355e93051e4ad"}},{"arxiv_id":"1812.09755","paper":"/paper/learning-when-to-communicate-at-scale-in","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","date":"2018-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IC3Net/IC3Net","path":"data.py","file_url":"https://github.com/IC3Net/IC3Net/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8cab58f1257e1400","mcp_get_code":{"code_sha256":"8cab58f1257e1400"}},{"arxiv_id":"1709.04057","paper":"/paper/parallelizing-linear-recurrent-neural-nets","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","date":"2017-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"proger/accelerated-scan","path":"tests/bench.py","file_url":"https://github.com/proger/accelerated-scan/blob/HEAD/tests/bench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6ac2ecfb8cd3b4a0","mcp_get_code":{"code_sha256":"6ac2ecfb8cd3b4a0"}},{"arxiv_id":"1705.05363","paper":"/paper/curiosity-driven-exploration-by-self","title":"Curiosity-driven Exploration by Self-supervised Prediction","date":"2017-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rpatrik96/AttA2C","path":"src/model.py","file_url":"https://github.com/rpatrik96/AttA2C/blob/HEAD/src/model.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":"87da60c05cf5addb","mcp_get_code":{"code_sha256":"87da60c05cf5addb"}},{"arxiv_id":"1612.07695","paper":"/paper/multinet-real-time-joint-semantic-reasoning","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","date":"2016-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MarvinTeichmann/KittiBox","path":"submodules/utils/googlenet_load.py","file_url":"https://github.com/MarvinTeichmann/KittiBox/blob/HEAD/submodules/utils/googlenet_load.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0380022ecb697fdf","mcp_get_code":{"code_sha256":"0380022ecb697fdf"}},{"arxiv_id":"1608.04667","paper":"/paper/medical-image-denoising-using-convolutional","title":"Medical image denoising using convolutional denoising autoencoders","date":"2016-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adam-mah/Medical-Image-Denoising","path":"bm3d.py","file_url":"https://github.com/adam-mah/Medical-Image-Denoising/blob/HEAD/bm3d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d86875c444f7728a","mcp_get_code":{"code_sha256":"d86875c444f7728a"}}]}