{"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/bias-gelu","entry":"bias_gelu","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":4,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":2,"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":"2506.00385","paper":"/paper/magicodec-simple-masked-gaussian-injected","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","date":"2025-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ereboas/MagiCodec","path":"components/ops/activations.py","file_url":"https://github.com/Ereboas/MagiCodec/blob/HEAD/components/ops/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bda6e53e10d00b2","mcp_get_code":{"code_sha256":"0bda6e53e10d00b2"}},{"arxiv_id":"2410.04798","paper":"/paper/dape-v2-process-attention-score-as-feature","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chuanyang-zheng/cape","path":"megatron/model/activations.py","file_url":"https://github.com/chuanyang-zheng/cape/blob/HEAD/megatron/model/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eb7511606bf2a37e","mcp_get_code":{"code_sha256":"eb7511606bf2a37e"}},{"arxiv_id":"2406.02528","paper":"/paper/scalable-matmul-free-language-modeling","title":"Scalable MatMul-free Language Modeling","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ridgerchu/matmulfreellm","path":"mmfreelm/modules/activations.py","file_url":"https://github.com/ridgerchu/matmulfreellm/blob/HEAD/mmfreelm/modules/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0bda6e53e10d00b2","mcp_get_code":{"code_sha256":"0bda6e53e10d00b2"}},{"arxiv_id":"2305.15032","paper":"/paper/how-to-distill-your-bert-an-empirical-study","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mainlp/How-to-distill-your-BERT","path":"task_agnostic_distillation/pretraining/modeling.py","file_url":"https://github.com/mainlp/How-to-distill-your-BERT/blob/HEAD/task_agnostic_distillation/pretraining/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f114723b758d8789","mcp_get_code":{"code_sha256":"f114723b758d8789"}},{"arxiv_id":"2205.09921","paper":"/paper/kerple-kernelized-relative-positional","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","date":"2022-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chijames/KERPLE","path":"megatron/model/activations.py","file_url":"https://github.com/chijames/KERPLE/blob/HEAD/megatron/model/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"eb7511606bf2a37e","mcp_get_code":{"code_sha256":"eb7511606bf2a37e"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifding/hetseq","path":"hetseq/bert_modeling.py","file_url":"https://github.com/yifding/hetseq/blob/HEAD/hetseq/bert_modeling.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de5ea2929d4e4106","mcp_get_code":{"code_sha256":"de5ea2929d4e4106"}},{"arxiv_id":"aaai_29781","paper":null,"title":"arXiv:aaai_29781","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jchenghu/sharebert","path":"pretraining/modeling.py","file_url":"https://github.com/jchenghu/sharebert/blob/HEAD/pretraining/modeling.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":"f114723b758d8789","mcp_get_code":{"code_sha256":"f114723b758d8789"}}]}