{"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/unpad-input-only","entry":"unpad_input_only","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":2,"n_places":7,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2601.05776","paper":"/paper/arxiv-2601-05776","title":"One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AnswerDotAI/ModernBERT","path":"src/bert_padding.py","file_url":"https://github.com/AnswerDotAI/ModernBERT/blob/HEAD/src/bert_padding.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":"e7df9e4a71a03583","mcp_get_code":{"code_sha256":"e7df9e4a71a03583"}},{"arxiv_id":"2505.00598","paper":"/paper/fast-and-low-cost-genomic-foundation-models","title":"Fast and Low-Cost Genomic Foundation Models via Outlier Removal","date":"2025-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MAGICS-LAB/GERM","path":"DNABERT2/bert_padding.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/DNABERT2/bert_padding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a41fa8c40b551ec1","mcp_get_code":{"code_sha256":"a41fa8c40b551ec1"}},{"arxiv_id":"2407.09941","paper":"/paper/hydra-bidirectional-state-space-models","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","date":"2024-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goombalab/hydra","path":"hydra/bert/src/bert_padding.py","file_url":"https://github.com/goombalab/hydra/blob/HEAD/hydra/bert/src/bert_padding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7df9e4a71a03583","mcp_get_code":{"code_sha256":"e7df9e4a71a03583"}},{"arxiv_id":"2402.08777","paper":"/paper/dnabert-s-learning-species-aware-dna","title":"DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magics-lab/dnabert_s","path":"evaluate/model_codes/bert_padding.py","file_url":"https://github.com/magics-lab/dnabert_s/blob/HEAD/evaluate/model_codes/bert_padding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a41fa8c40b551ec1","mcp_get_code":{"code_sha256":"a41fa8c40b551ec1"}},{"arxiv_id":"2311.12570","paper":"/paper/bend-benchmarking-dna-language-models-on","title":"BEND: Benchmarking DNA Language Models on biologically meaningful tasks","date":"2023-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frederikkemarin/BEND","path":"bend/models/dnabert2_padding.py","file_url":"https://github.com/frederikkemarin/BEND/blob/HEAD/bend/models/dnabert2_padding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"a41fa8c40b551ec1","mcp_get_code":{"code_sha256":"a41fa8c40b551ec1"}},{"arxiv_id":"2306.15006","paper":"/paper/dnabert-2-efficient-foundation-model-and","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","date":"2023-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frederikkemarin/bend","path":"bend/utils/embedders.py","file_url":"https://github.com/frederikkemarin/bend/blob/HEAD/bend/utils/embedders.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9c99ec96528c0f00","mcp_get_code":{"code_sha256":"9c99ec96528c0f00"}},{"arxiv_id":"2108.12409","paper":"/paper/train-short-test-long-attention-with-linear","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","date":"2021-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"answerdotai/modernbert","path":"src/bert_layers/attention.py","file_url":"https://github.com/answerdotai/modernbert/blob/HEAD/src/bert_layers/attention.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4e534e11984c06b5","mcp_get_code":{"code_sha256":"4e534e11984c06b5"}}]}