{"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","entry":"unpad_input","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":12,"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":2,"n_samples_fingerprinted":1,"n_places":12,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"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":"2605.15422","paper":"/paper/arxiv-2605-15422","title":"DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"amazon-science/dualkv-flash-attn-for-rl","path":"flash-attention/flash_attn/bert_padding.py","file_url":"https://github.com/amazon-science/dualkv-flash-attn-for-rl/blob/HEAD/flash-attention/flash_attn/bert_padding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d84093c20a0ed8fd","mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"arxiv_id":"2604.23798","paper":"/paper/arxiv-2604-23798","title":"ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Dao-AILab/flash-attention","path":"flash_attn/bert_padding.py","file_url":"https://github.com/Dao-AILab/flash-attention/blob/HEAD/flash_attn/bert_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":"d84093c20a0ed8fd","mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"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":"ee341a843ab02d5f","mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}},{"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/padding.py","file_url":"https://github.com/Ereboas/MagiCodec/blob/HEAD/components/ops/padding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4ca9ddf6b6d4cad","mcp_get_code":{"code_sha256":"b4ca9ddf6b6d4cad"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee341a843ab02d5f","mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}},{"arxiv_id":"2502.19613","paper":"/paper/self-rewarding-correction-for-mathematical","title":"Self-rewarding correction for mathematical reasoning","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentica-project/verl-pipeline","path":"verl/models/bert_padding.py","file_url":"https://github.com/agentica-project/verl-pipeline/blob/HEAD/verl/models/bert_padding.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":"d84093c20a0ed8fd","mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"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":"ee341a843ab02d5f","mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}},{"arxiv_id":"2407.08608","paper":"/paper/flashattention-3-fast-and-accurate-attention","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dao-ailab/flash-attention","path":"flash_attn/bert_padding.py","file_url":"https://github.com/dao-ailab/flash-attention/blob/HEAD/flash_attn/bert_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":"d84093c20a0ed8fd","mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ee341a843ab02d5f","mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"ee341a843ab02d5f","mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}},{"arxiv_id":"2309.06180","paper":"/paper/2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ROCm/flash-attention","path":"flash_attn/bert_padding.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/bert_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":"d84093c20a0ed8fd","mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"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":"e819e759304fc70a","mcp_get_code":{"code_sha256":"e819e759304fc70a"}}]}