{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/average-gradients","entry":"average_gradients","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":20,"n_papers_ran":14,"n_papers_ran_no_instrument_failure":14,"n_papers_ran_instrument_only":0,"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":18,"n_samples_ran":12,"n_samples_constructed":0,"n_samples_ran_checked":12,"n_samples_instrument":0,"n_samples_unverified":6,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":0,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":12,"unverified":6},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2205.00705","arxiv_id_is_arxiv":true,"paper":"/paper/3d-object-detection-with-a-self-supervised","title":"3D Object Detection with a Self-supervised Lidar Scene Flow Backbone","date":"2022-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeijingShi/Point-GNN","path":"util/tf_util.py","file_url":"https://github.com/WeijingShi/Point-GNN/blob/HEAD/util/tf_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a0172c48afaa4a94","code_sha256_prefix":"a0172c48afaa4a94","mcp_get_code":{"code_sha256":"a0172c48afaa4a94"}},{"arxiv_id":"2105.01051","arxiv_id_is_arxiv":true,"paper":"/paper/superb-speech-processing-universal","title":"SUPERB: Speech processing Universal PERformance Benchmark","date":"2021-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usc-sail/fed-ser-leakage","path":"mitigation/update.py","file_url":"https://github.com/usc-sail/fed-ser-leakage/blob/HEAD/mitigation/update.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e5cb81a78546f033","code_sha256_prefix":"e5cb81a78546f033","mcp_get_code":{"code_sha256":"e5cb81a78546f033"}},{"arxiv_id":"2007.02622","arxiv_id_is_arxiv":true,"paper":"/paper/nappo-modular-and-scalable-reinforcement","title":"Integrating Distributed Architectures in Highly Modular RL Libraries","date":"2020-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PyTorchRL/pytorchrl","path":"pytorchrl/scheme/utils.py","file_url":"https://github.com/PyTorchRL/pytorchrl/blob/HEAD/pytorchrl/scheme/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9c88cb72fa692623","code_sha256_prefix":"9c88cb72fa692623","mcp_get_code":{"code_sha256":"9c88cb72fa692623"}},{"arxiv_id":"2003.03030","arxiv_id_is_arxiv":true,"paper":"/paper/clean-label-backdoor-attacks-on-video","title":"Clean-Label Backdoor Attacks on Video Recognition Models","date":"2020-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShihaoZhaoZSH/Video-Backdoor-Attack","path":"utils.py","file_url":"https://github.com/ShihaoZhaoZSH/Video-Backdoor-Attack/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8553e59eb6f6feab","code_sha256_prefix":"8553e59eb6f6feab","mcp_get_code":{"code_sha256":"8553e59eb6f6feab"}},{"arxiv_id":"1904.10014","arxiv_id_is_arxiv":true,"paper":"/paper/linked-dynamic-graph-cnn-learning-on-point","title":"Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features","date":"2019-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KuangenZhang/ldgcnn","path":"part_seg/train_multi_gpu.py","file_url":"https://github.com/KuangenZhang/ldgcnn/blob/HEAD/part_seg/train_multi_gpu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34732848a23a9c10","code_sha256_prefix":"34732848a23a9c10","mcp_get_code":{"code_sha256":"34732848a23a9c10"}},{"arxiv_id":"1902.09212","arxiv_id_is_arxiv":true,"paper":"/paper/deep-high-resolution-representation-learning","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","date":"2019-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mks0601/PoseFix_RELEASE","path":"lib/tfflat/net_utils.py","file_url":"https://github.com/mks0601/PoseFix_RELEASE/blob/HEAD/lib/tfflat/net_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"94ffb5d47eee6270","code_sha256_prefix":"94ffb5d47eee6270","mcp_get_code":{"code_sha256":"94ffb5d47eee6270"}},{"arxiv_id":"1809.01465","arxiv_id_is_arxiv":true,"paper":"/paper/deep-bilevel-learning","title":"Deep Bilevel Learning","date":"2018-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjenni/DeepBilevel","path":"utils.py","file_url":"https://github.com/sjenni/DeepBilevel/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c9376dbf970ce49f","code_sha256_prefix":"c9376dbf970ce49f","mcp_get_code":{"code_sha256":"c9376dbf970ce49f"}},{"arxiv_id":"1808.08583","arxiv_id_is_arxiv":true,"paper":"/paper/semi-autoregressive-neural-machine","title":"Semi-Autoregressive Neural Machine Translation","date":"2018-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chqiwang/sa-nmt","path":"utils.py","file_url":"https://github.com/chqiwang/sa-nmt/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3ad1487952836d07","code_sha256_prefix":"3ad1487952836d07","mcp_get_code":{"code_sha256":"3ad1487952836d07"}},{"arxiv_id":"1808.00157","arxiv_id_is_arxiv":true,"paper":"/paper/instance-level-human-parsing-via-part","title":"Instance-level Human Parsing via Part Grouping Network","date":"2018-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Engineering-Course/CIHP_PGN","path":"train_pgn.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/train_pgn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c598804162457140","code_sha256_prefix":"c598804162457140","mcp_get_code":{"code_sha256":"c598804162457140"}},{"arxiv_id":"1807.09190","arxiv_id_is_arxiv":true,"paper":"/paper/premvos-proposal-generation-refinement-and","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","date":"2018-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AyaLotfy/PReMVOS-trial","path":"code/ReID_net/Util.py","file_url":"https://github.com/AyaLotfy/PReMVOS-trial/blob/HEAD/code/ReID_net/Util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d82c26b8b96a063f","code_sha256_prefix":"d82c26b8b96a063f","mcp_get_code":{"code_sha256":"d82c26b8b96a063f"}},{"arxiv_id":"1806.04326","arxiv_id_is_arxiv":true,"paper":"/paper/differentiable-compositional-kernel-learning","title":"Differentiable Compositional Kernel Learning for Gaussian Processes","date":"2018-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thjashin/spectral-stein-grad","path":"utils/multi_gpu.py","file_url":"https://github.com/thjashin/spectral-stein-grad/blob/HEAD/utils/multi_gpu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"19a2e9b1682d85e8","code_sha256_prefix":"19a2e9b1682d85e8","mcp_get_code":{"code_sha256":"19a2e9b1682d85e8"}},{"arxiv_id":"1805.01954","arxiv_id_is_arxiv":true,"paper":"/paper/behavioral-cloning-from-observation","title":"Behavioral Cloning from Observation","date":"2018-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"greerviau/GlorifiedCruiseControl","path":"SCNN_lanenet/train_lanenet.py","file_url":"https://github.com/greerviau/GlorifiedCruiseControl/blob/HEAD/SCNN_lanenet/train_lanenet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10e8814dfd1ac64c","code_sha256_prefix":"10e8814dfd1ac64c","mcp_get_code":{"code_sha256":"10e8814dfd1ac64c"}},{"arxiv_id":"1803.11527","arxiv_id_is_arxiv":true,"paper":"/paper/spidercnn-deep-learning-on-point-sets-with","title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","date":"2018-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyf513/SpiderCNN","path":"train_xyz.py","file_url":"https://github.com/xyf513/SpiderCNN/blob/HEAD/train_xyz.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0e0c2135e80629bb","code_sha256_prefix":"0e0c2135e80629bb","mcp_get_code":{"code_sha256":"0e0c2135e80629bb"}},{"arxiv_id":"1803.03764","arxiv_id_is_arxiv":true,"paper":"/paper/variance-networks-when-expectation-does-not","title":"Variance Networks: When Expectation Does Not Meet Your Expectations","date":"2018-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"da-molchanov/variance-networks","path":"variance-networks-tf/nets/utils.py","file_url":"https://github.com/da-molchanov/variance-networks/blob/HEAD/variance-networks-tf/nets/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8553e59eb6f6feab","code_sha256_prefix":"8553e59eb6f6feab","mcp_get_code":{"code_sha256":"8553e59eb6f6feab"}},{"arxiv_id":"1802.05365","arxiv_id_is_arxiv":true,"paper":"/paper/deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/bilm-tf","path":"bilm/training.py","file_url":"https://github.com/allenai/bilm-tf/blob/HEAD/bilm/training.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"821ed0b50fc8c75a","code_sha256_prefix":"821ed0b50fc8c75a","mcp_get_code":{"code_sha256":"821ed0b50fc8c75a"}},{"arxiv_id":"1710.09829","arxiv_id_is_arxiv":true,"paper":"/paper/dynamic-routing-between-capsules","title":"Dynamic Routing Between Capsules","date":"2017-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naturomics/CapsNet-Tensorflow","path":"dist_version/distributed_train.py","file_url":"https://github.com/naturomics/CapsNet-Tensorflow/blob/HEAD/dist_version/distributed_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"25474dc6ec455a0d","code_sha256_prefix":"25474dc6ec455a0d","mcp_get_code":{"code_sha256":"25474dc6ec455a0d"}},{"arxiv_id":"1706.02275","arxiv_id_is_arxiv":true,"paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yutongamber/MADDPG","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a3e542c9d6910a27","code_sha256_prefix":"a3e542c9d6910a27","mcp_get_code":{"code_sha256":"a3e542c9d6910a27"}},{"arxiv_id":"1703.04887","arxiv_id_is_arxiv":true,"paper":"/paper/improving-neural-machine-translation-with","title":"Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets","date":"2017-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhenYangIACAS/NMT_GAN","path":"model.py","file_url":"https://github.com/ZhenYangIACAS/NMT_GAN/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8a792606b6037ff1","code_sha256_prefix":"8a792606b6037ff1","mcp_get_code":{"code_sha256":"8a792606b6037ff1"}},{"arxiv_id":"1612.08810","arxiv_id_is_arxiv":true,"paper":"/paper/the-predictron-end-to-end-learning-and","title":"The Predictron: End-To-End Learning and Planning","date":"2016-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongwen/predictron","path":"train_multigpu.py","file_url":"https://github.com/zhongwen/predictron/blob/HEAD/train_multigpu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a7a9c8edfe63551c","code_sha256_prefix":"a7a9c8edfe63551c","mcp_get_code":{"code_sha256":"a7a9c8edfe63551c"}},{"arxiv_id":"1511.06422","arxiv_id_is_arxiv":true,"paper":"/paper/all-you-need-is-a-good-init","title":"All you need is a good init","date":"2015-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JonasWechsler/DeepLearningLab5","path":"cifar10/cifar10_multi_gpu_train.py","file_url":"https://github.com/JonasWechsler/DeepLearningLab5/blob/HEAD/cifar10/cifar10_multi_gpu_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"25474dc6ec455a0d","code_sha256_prefix":"25474dc6ec455a0d","mcp_get_code":{"code_sha256":"25474dc6ec455a0d"}}],"record_sha256":"9f0528f3f08b3ba008c11f85a47f119a48b627612b484344f345ac7937072f60","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}