{"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-for-concatenated-sequences","entry":"unpad_input_for_concatenated_sequences","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":5,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"62394c842aafb022","mcp_get_code":{"code_sha256":"62394c842aafb022"}},{"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":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62394c842aafb022","mcp_get_code":{"code_sha256":"62394c842aafb022"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"62394c842aafb022","mcp_get_code":{"code_sha256":"62394c842aafb022"}},{"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":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62394c842aafb022","mcp_get_code":{"code_sha256":"62394c842aafb022"}},{"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":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"62394c842aafb022","mcp_get_code":{"code_sha256":"62394c842aafb022"}}]}