{"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/distillation","entry":"distillation","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":7,"n_papers_ran":5,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":3,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"2009.08325","paper":"/paper/noisy-concurrent-training-for-efficient","title":"Noisy Concurrent Training for Efficient Learning under Label Noise","date":"2020-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NeurAI-Lab/NCT","path":"utilities/losses.py","file_url":"https://github.com/NeurAI-Lab/NCT/blob/HEAD/utilities/losses.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f8ea28418068366","mcp_get_code":{"code_sha256":"2f8ea28418068366"}},{"arxiv_id":"2005.09394","paper":"/paper/enhancing-monotonic-multihead-attention-for","title":"Enhancing Monotonic Multihead Attention for Streaming ASR","date":"2020-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hirofumi0810/neural_sp","path":"neural_sp/models/criterion.py","file_url":"https://github.com/hirofumi0810/neural_sp/blob/HEAD/neural_sp/models/criterion.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":"8cef8c0370530397","mcp_get_code":{"code_sha256":"8cef8c0370530397"}},{"arxiv_id":"2001.02905","paper":"/paper/fast-adaptation-to-super-resolution-networks","title":"Fast Adaptation to Super-Resolution Networks via Meta-Learning","date":"2020-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parkseobin/MLSR","path":"IDN_definition.py","file_url":"https://github.com/parkseobin/MLSR/blob/HEAD/IDN_definition.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5335593d33fc9a1","mcp_get_code":{"code_sha256":"a5335593d33fc9a1"}},{"arxiv_id":"1906.04113","paper":"/paper/blockswap-fisher-guided-block-substitution","title":"BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget","date":"2019-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BayesWatch/pytorch-blockswap","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-blockswap/blob/HEAD/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f6484efda3ef4ceb","mcp_get_code":{"code_sha256":"f6484efda3ef4ceb"}},{"arxiv_id":"1905.13409","paper":"/paper/bypassing-backdoor-detection-algorithms-in","title":"Bypassing Backdoor Detection Algorithms in Deep Learning","date":"2019-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"5c6b89d763f0a8f3","mcp_get_code":{"code_sha256":"5c6b89d763f0a8f3"}},{"arxiv_id":"1711.02613","paper":"/paper/moonshine-distilling-with-cheap-convolutions","title":"Moonshine: Distilling with Cheap Convolutions","date":"2017-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BayesWatch/pytorch-moonshine","path":"funcs.py","file_url":"https://github.com/BayesWatch/pytorch-moonshine/blob/HEAD/funcs.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f6484efda3ef4ceb","mcp_get_code":{"code_sha256":"f6484efda3ef4ceb"}},{"arxiv_id":"1708.06733","paper":"/paper/badnets-identifying-vulnerabilities-in-the","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","date":"2017-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aisafety-hkust/backdoor_safety_tuning","path":"fine_tune/qra.py","file_url":"https://github.com/aisafety-hkust/backdoor_safety_tuning/blob/HEAD/fine_tune/qra.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5c6b89d763f0a8f3","mcp_get_code":{"code_sha256":"5c6b89d763f0a8f3"}}]}