{"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/hard-sigmoid","entry":"hard_sigmoid","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":4,"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":4,"n_samples_fingerprinted":4,"n_places":15,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":0,"unverified":7},"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":"2603.26595","paper":"/paper/arxiv-2603-26595","title":"PQuantML: A Tool for End-to-End Hardware-Aware Model Compression","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"cern-nextgen/PQuantML","path":"src/pquant/core/keras/activations.py","file_url":"https://github.com/cern-nextgen/PQuantML/blob/HEAD/src/pquant/core/keras/activations.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":"b13bc14536964bbd","mcp_get_code":{"code_sha256":"b13bc14536964bbd"}},{"arxiv_id":"2602.03896","paper":"/paper/arxiv-2602-03896","title":"A hitchhiker's guide to Poisson gradient estimation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"hadivafaii/PoissonGradientEstimation","path":"poisson_grad_estimators/estimators.py","file_url":"https://github.com/hadivafaii/PoissonGradientEstimation/blob/HEAD/poisson_grad_estimators/estimators.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":"68db984355eefe27","mcp_get_code":{"code_sha256":"68db984355eefe27"}},{"arxiv_id":"2211.06088","paper":"/paper/repghost-a-hardware-efficient-ghost-module","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","date":"2022-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chengpengchen/repghost","path":"model/repghost.py","file_url":"https://github.com/chengpengchen/repghost/blob/HEAD/model/repghost.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9479314f0ac20b2","mcp_get_code":{"code_sha256":"f9479314f0ac20b2"}},{"arxiv_id":"2210.10090","paper":"/paper/how-to-boost-face-recognition-with-stylegan","title":"How to Boost Face Recognition with StyleGAN?","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seva100/stylegan-for-facerec","path":"backbone/GhostNet.py","file_url":"https://github.com/seva100/stylegan-for-facerec/blob/HEAD/backbone/GhostNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9479314f0ac20b2","mcp_get_code":{"code_sha256":"f9479314f0ac20b2"}},{"arxiv_id":"2209.09626","paper":"/paper/sequence-learning-using-equilibrium","title":"Sequence Learning Using Equilibrium Propagation","date":"2022-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neurocomplab-psu/eqprop-seqlearning","path":"model_utils.py","file_url":"https://github.com/neurocomplab-psu/eqprop-seqlearning/blob/HEAD/model_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40477286874877b9","mcp_get_code":{"code_sha256":"40477286874877b9"}},{"arxiv_id":"2109.03144","paper":"/paper/pp-ocrv2-bag-of-tricks-for-ultra-lightweight","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","date":"2021-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frotms/PaddleOCR2Pytorch","path":"misc/pt_table_mobilenet_v3.py","file_url":"https://github.com/frotms/PaddleOCR2Pytorch/blob/HEAD/misc/pt_table_mobilenet_v3.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":"09c8c4cd2ea079ce","mcp_get_code":{"code_sha256":"09c8c4cd2ea079ce"}},{"arxiv_id":"2107.08621","paper":"/paper/face-evolve-a-high-performance-face","title":"Face.evoLVe: A High-Performance Face Recognition Library","date":"2021-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhaoJ9014/face.evoLVe.PyTorch","path":"backbone/GhostNet.py","file_url":"https://github.com/ZhaoJ9014/face.evoLVe.PyTorch/blob/HEAD/backbone/GhostNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9479314f0ac20b2","mcp_get_code":{"code_sha256":"f9479314f0ac20b2"}},{"arxiv_id":"2004.10162","paper":"/paper/empir-ensembles-of-mixed-precision-deep-1","title":"EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks","date":"2020-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sancharisen/EMPIR","path":"cleverhans_tutorials/tutorial_models.py","file_url":"https://github.com/sancharisen/EMPIR/blob/HEAD/cleverhans_tutorials/tutorial_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"33ce7291d7174c33","mcp_get_code":{"code_sha256":"33ce7291d7174c33"}},{"arxiv_id":"2003.13880","paper":"/paper/muxconv-information-multiplexing-in","title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","date":"2020-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"human-analysis/MUXConv","path":"muxnet.py","file_url":"https://github.com/human-analysis/MUXConv/blob/HEAD/muxnet.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1d0dc1f5a5cb3014","mcp_get_code":{"code_sha256":"1d0dc1f5a5cb3014"}},{"arxiv_id":"1911.11907","paper":"/paper/ghostnet-more-features-from-cheap-operations","title":"GhostNet: More Features from Cheap Operations","date":"2019-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ozora-ogino/efficient_backbones","path":"efficient_backbones/ghostnet.py","file_url":"https://github.com/ozora-ogino/efficient_backbones/blob/HEAD/efficient_backbones/ghostnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca43d9eb44b430e5","mcp_get_code":{"code_sha256":"ca43d9eb44b430e5"}},{"arxiv_id":"1911.08717","paper":"/paper/fine-tuning-by-curriculum-learning-for-non","title":"Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation","date":"2019-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lemmonation/fcl-nat","path":"tensor2tensor/layers/common_layers.py","file_url":"https://github.com/lemmonation/fcl-nat/blob/HEAD/tensor2tensor/layers/common_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62078081af34b8ee","mcp_get_code":{"code_sha256":"62078081af34b8ee"}},{"arxiv_id":"1908.09124","paper":"/paper/seesawfacenets-sparse-and-robust-face","title":"SeesawFaceNets: sparse and robust face verification model for mobile platform","date":"2019-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pshashk/seesaw-facenet","path":"model.py","file_url":"https://github.com/pshashk/seesaw-facenet/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b5594729a056dad","mcp_get_code":{"code_sha256":"8b5594729a056dad"}},{"arxiv_id":"1905.02244","paper":"/paper/searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Randl/MobileNetV3-pytorch","path":"MobileNetV3.py","file_url":"https://github.com/Randl/MobileNetV3-pytorch/blob/HEAD/MobileNetV3.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad6446d870a72a89","mcp_get_code":{"code_sha256":"ad6446d870a72a89"}},{"arxiv_id":"1711.00449","paper":"/paper/attacking-binarized-neural-networks","title":"Attacking Binarized Neural Networks","date":"2017-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AngusG/cleverhans-attacking-bnns","path":"cleverhans_tutorials/tutorial_models.py","file_url":"https://github.com/AngusG/cleverhans-attacking-bnns/blob/HEAD/cleverhans_tutorials/tutorial_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"33ce7291d7174c33","mcp_get_code":{"code_sha256":"33ce7291d7174c33"}},{"arxiv_id":"136810034","paper":null,"title":"arXiv:136810034","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Sense-X/UniNet","path":"model_utils.py","file_url":"https://github.com/Sense-X/UniNet/blob/HEAD/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":"ad6446d870a72a89","mcp_get_code":{"code_sha256":"ad6446d870a72a89"}}]}