{"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/attention-mask-func","entry":"attention_mask_func","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":8,"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":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2411.04168","paper":"/paper/dimsum-diffusion-mamba-a-scalable-and-unified","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinairesearch/dimsum","path":"dimsum/bias_gelu.py","file_url":"https://github.com/vinairesearch/dimsum/blob/HEAD/dimsum/bias_gelu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d3b0933503154c4d","mcp_get_code":{"code_sha256":"d3b0933503154c4d"}},{"arxiv_id":"2410.11289","paper":"/paper/subspace-optimization-for-large-language","title":"Subspace Optimization for Large Language Models with Convergence Guarantees","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkumelon/Golore","path":"peft_pretraining/modeling_pythia.py","file_url":"https://github.com/pkumelon/Golore/blob/HEAD/peft_pretraining/modeling_pythia.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"4397f33726a2999e","mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"arxiv_id":"2409.01193","paper":"/paper/clibe-detecting-dynamic-backdoors-in","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raytsang123/clibe","path":"generative_backdoors/detection/modeling_gpt_neox.py","file_url":"https://github.com/raytsang123/clibe/blob/HEAD/generative_backdoors/detection/modeling_gpt_neox.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":"4397f33726a2999e","mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"arxiv_id":"2403.19928","paper":"/paper/dijiang-efficient-large-language-models","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchuantian/dijiang","path":"modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4397f33726a2999e","mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"arxiv_id":"2311.13230","paper":"/paper/enhancing-uncertainty-based-hallucination","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","date":"2023-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zthang/focus","path":"models/modeling_gpt_neox.py","file_url":"https://github.com/zthang/focus/blob/HEAD/models/modeling_gpt_neox.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4397f33726a2999e","mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"arxiv_id":"2307.05695","paper":"/paper/stack-more-layers-differently-high-rank","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","date":"2023-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guitaricet/peft_pretraining","path":"peft_pretraining/modeling_pythia.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/modeling_pythia.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":"4397f33726a2999e","mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"arxiv_id":"2203.01670","paper":"/paper/a-simple-hash-based-early-exiting-approach-1","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","date":"2022-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"txsun1997/hashee","path":"models/modeling_elasticbert_approx_hashee.py","file_url":"https://github.com/txsun1997/hashee/blob/HEAD/models/modeling_elasticbert_approx_hashee.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce106170b591f393","mcp_get_code":{"code_sha256":"ce106170b591f393"}},{"arxiv_id":"aaai_33874","paper":null,"title":"arXiv:aaai_33874","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"txsun1997/Black-Box-Tuning","path":"models/deep_modeling_cpt.py","file_url":"https://github.com/txsun1997/Black-Box-Tuning/blob/HEAD/models/deep_modeling_cpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce106170b591f393","mcp_get_code":{"code_sha256":"ce106170b591f393"}}]}