{"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/normalize-l2","entry":"normalize_l2","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":6,"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":4,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":1},"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":"2503.01822","paper":"/paper/projecting-assumptions-the-duality-between","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","date":"2025-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KempnerInstitute/Overcomplete","path":"overcomplete/sae/jump_sae.py","file_url":"https://github.com/KempnerInstitute/Overcomplete/blob/HEAD/overcomplete/sae/jump_sae.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":"efac2c02b2c4b989","mcp_get_code":{"code_sha256":"efac2c02b2c4b989"}},{"arxiv_id":"2105.00956","paper":"/paper/unignn-a-unified-framework-for-graph-and","title":"UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks","date":"2021-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OneForward/UniGNN","path":"model/UniGNN.py","file_url":"https://github.com/OneForward/UniGNN/blob/HEAD/model/UniGNN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"688dca370c1d9b47","mcp_get_code":{"code_sha256":"688dca370c1d9b47"}},{"arxiv_id":"1912.12510","paper":"/paper/detecting-out-of-distribution-examples-with","title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","date":"2019-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"b16e920816efe253","mcp_get_code":{"code_sha256":"b16e920816efe253"}},{"arxiv_id":"1908.08016","paper":"/paper/190808016","title":"Testing Robustness Against Unforeseen Adversaries","date":"2019-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"centerforaisafety/adversarial-corruptions","path":"attacks/attacks.py","file_url":"https://github.com/centerforaisafety/adversarial-corruptions/blob/HEAD/attacks/attacks.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1e43d48e3be5a73","mcp_get_code":{"code_sha256":"c1e43d48e3be5a73"}},{"arxiv_id":"1906.12340","paper":"/paper/using-self-supervised-learning-can-improve","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","date":"2019-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/ss-ood","path":"adversarial/attacks.py","file_url":"https://github.com/hendrycks/ss-ood/blob/HEAD/adversarial/attacks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b16e920816efe253","mcp_get_code":{"code_sha256":"b16e920816efe253"}},{"arxiv_id":"1901.09960","paper":"/paper/using-pre-training-can-improve-model","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","date":"2019-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/pre-training","path":"robustness/adversarial/attacks.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/adversarial/attacks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b16e920816efe253","mcp_get_code":{"code_sha256":"b16e920816efe253"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joelsimonoff/gram-adversary-detection","path":"new-work/model-training/utils/attacks.py","file_url":"https://github.com/joelsimonoff/gram-adversary-detection/blob/HEAD/new-work/model-training/utils/attacks.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":"b16e920816efe253","mcp_get_code":{"code_sha256":"b16e920816efe253"}}]}