{"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/ema-2","entry":"ema","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":15,"n_papers_ran":8,"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":11,"n_samples_ran":5,"n_samples_fingerprinted":5,"n_places":15,"n_places_pointer_only":3,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":6},"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":"2605.08840","paper":"/paper/arxiv-2605-08840","title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"an-yongqi/rest-kv","path":"restkv/llama_model.py","file_url":"https://github.com/an-yongqi/rest-kv/blob/HEAD/restkv/llama_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88375ce705173d0e","mcp_get_code":{"code_sha256":"88375ce705173d0e"}},{"arxiv_id":"2605.04507","paper":"/paper/arxiv-2605-04507","title":"Distilling Bayesian Belief States into Language Models for Auditable Negotiation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"kaneis1/CaSiNo_negotiation-agent","path":"src/casino_belief/evaluation/metrics.py","file_url":"https://github.com/kaneis1/CaSiNo_negotiation-agent/blob/HEAD/src/casino_belief/evaluation/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"093bd02fd4d1be7c","mcp_get_code":{"code_sha256":"093bd02fd4d1be7c"}},{"arxiv_id":"2311.01489","paper":"/paper/invariant-causal-imitation-learning-for-1","title":"Invariant Causal Imitation Learning for Generalizable Policies","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ioanabica/invariant-causal-imitation-learning","path":"network/mine_network.py","file_url":"https://github.com/ioanabica/invariant-causal-imitation-learning/blob/HEAD/network/mine_network.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1073d8f05df7b5a","mcp_get_code":{"code_sha256":"a1073d8f05df7b5a"}},{"arxiv_id":"2310.16828","paper":"/paper/td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicklashansen/tdmpc","path":"src/algorithm/tdmpc.py","file_url":"https://github.com/nicklashansen/tdmpc/blob/HEAD/src/algorithm/tdmpc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e39520f04bf0598d","mcp_get_code":{"code_sha256":"e39520f04bf0598d"}},{"arxiv_id":"2211.09760","paper":"/paper/velo-training-versatile-learned-optimizers-by","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/learned_optimization","path":"learned_optimization/notebook_utils.py","file_url":"https://github.com/google/learned_optimization/blob/HEAD/learned_optimization/notebook_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":"e6c862d84c69f94c","mcp_get_code":{"code_sha256":"e6c862d84c69f94c"}},{"arxiv_id":"2108.12630","paper":"/paper/groupformer-group-activity-recognition-with","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","date":"2021-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xueyee/GroupFormer","path":"group/models/cluster_transformer.py","file_url":"https://github.com/xueyee/GroupFormer/blob/HEAD/group/models/cluster_transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f70774c0916069a5","mcp_get_code":{"code_sha256":"f70774c0916069a5"}},{"arxiv_id":"2105.14850","paper":"/paper/cascaded-head-colliding-attention","title":"Cascaded Head-colliding Attention","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pytorch/fairseq","path":"fairseq/modules/kmeans_attention.py","file_url":"https://github.com/pytorch/fairseq/blob/HEAD/fairseq/modules/kmeans_attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62b973828672478f","mcp_get_code":{"code_sha256":"62b973828672478f"}},{"arxiv_id":"2010.14860","paper":"/paper/the-evidence-lower-bound-of-variational","title":"The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies","date":"2020-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"learning-with-entropies/elbo-entropies-aistats23","path":"utils.py","file_url":"https://github.com/learning-with-entropies/elbo-entropies-aistats23/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"419e916c07567d5b","mcp_get_code":{"code_sha256":"419e916c07567d5b"}},{"arxiv_id":"2009.04416","paper":"/paper/phasic-policy-gradient","title":"Phasic Policy Gradient","date":"2020-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/phasic-policy-gradient","path":"phasic_policy_gradient/graph_util.py","file_url":"https://github.com/openai/phasic-policy-gradient/blob/HEAD/phasic_policy_gradient/graph_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a362c435a091c0f4","mcp_get_code":{"code_sha256":"a362c435a091c0f4"}},{"arxiv_id":"1912.01588","paper":"/paper/leveraging-procedural-generation-to-benchmark","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/train-procgen","path":"train_procgen/graph_util.py","file_url":"https://github.com/openai/train-procgen/blob/HEAD/train_procgen/graph_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a362c435a091c0f4","mcp_get_code":{"code_sha256":"a362c435a091c0f4"}},{"arxiv_id":"1801.04062","paper":"/paper/mine-mutual-information-neural-estimation","title":"MINE: Mutual Information Neural Estimation","date":"2018-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a1073d8f05df7b5a","mcp_get_code":{"code_sha256":"a1073d8f05df7b5a"}},{"arxiv_id":"1703.04200","paper":"/paper/continual-learning-through-synaptic","title":"Continual Learning Through Synaptic Intelligence","date":"2017-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganguli-lab/pathint","path":"pathint/utils.py","file_url":"https://github.com/ganguli-lab/pathint/blob/HEAD/pathint/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8908090914518af0","mcp_get_code":{"code_sha256":"8908090914518af0"}},{"arxiv_id":"1703.00810","paper":"/paper/opening-the-black-box-of-deep-neural-networks","title":"Opening the Black Box of Deep Neural Networks via Information","date":"2017-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a1073d8f05df7b5a","mcp_get_code":{"code_sha256":"a1073d8f05df7b5a"}},{"arxiv_id":"1610.02242","paper":"/paper/temporal-ensembling-for-semi-supervised","title":"Temporal Ensembling for Semi-Supervised Learning","date":"2016-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"notha99y/mean_teacher_domain_adapt","path":"src/model.py","file_url":"https://github.com/notha99y/mean_teacher_domain_adapt/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88874fb38feaf13a","mcp_get_code":{"code_sha256":"88874fb38feaf13a"}},{"arxiv_id":"1606.03657","paper":"/paper/infogan-interpretable-representation-learning","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","date":"2016-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gtegner/mine-pytorch","path":"mine/models/mine.py","file_url":"https://github.com/gtegner/mine-pytorch/blob/HEAD/mine/models/mine.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1073d8f05df7b5a","mcp_get_code":{"code_sha256":"a1073d8f05df7b5a"}}]}