Home › Code › compute_bleu

compute_bleu

Syntologyentry name in harvested coderead from the graph 2026-09-24

compute_bleu appears in the code Syntology harvested for 30 papers, as 18 distinct code bodies found in 30 places (a place is one code body under one paper). At least one of them ran in 14 of the papers; 2 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named compute_bleu do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 6 of the 18 distinct code bodies named compute_bleu; 12 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

3ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
3ran
12unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 5 of the 30 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

30 papers shown of 30, newest first; 30 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology; 5 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation added by Syntology 2026-06 (from id) fensorechase/rag-diverse-benchmarks-synthetic-qa/rag_system/generate/complete_analysis.py 52f277ebffee2f1f ran · honoured contract fingerprinted Apache-2.0 (permissive)
Reflective Translation for Low-Resource Machine Translation via Structured Self-Reflection added by Syntology 2026-01 (from id) Nickcheng123/reflective-translation-mt/src/reflective_translation/pipeline.py 5ce1568daa37b696 ran · honoured contract fingerprinted MIT (permissive)
Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems 29 Sep 2024 elviswxy/rag_fairness/flashrag/evaluator/_bleu.py 2dd8e40379d7bbb9 ran no licence file found · pointer only
Diabetica: Adapting Large Language Model to Enhance Multiple Medical Tasks in Diabetes Care and Management 20 Sep 2024 waltonfuture/Diabetica/evaluation/fill-in-the-blank_eval.py fc8f0da4acefd1b7 unverified MIT (permissive)
RDRec: Rationale Distillation for LLM-based Recommendation 17 May 2024 WangXFng/RDRec/utils/bleu.py 49289a7f94c227bd ran no licence file found · pointer only
ScreenAgent: A Vision Language Model-driven Computer Control Agent 9 Feb 2024 niuzaisheng/ScreenAgent/client/bleu.py 49289a7f94c227bd ran no licence file found · pointer only
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models 30 Jan 2024 kwanwaichung/mt-eval/utils/bleu.py 2dd8e40379d7bbb9 ran MIT (permissive)
PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models 28 Jan 2024 seekingdream/ppm/diversity.py b059913a28aa8d55 unverified Apache-2.0 (permissive)
An Analysis and Mitigation of the Reversal Curse 13 Nov 2023 trestad/mitigating-reversal-curse/generate.py f0d20ebd827390d6 ran no licence file found · pointer only
LLMRec: Benchmarking Large Language Models on Recommendation Task 23 Aug 2023 williamliujl/llmrec/utils/evaluate/bleu.py 49289a7f94c227bd ran Apache-2.0 (permissive)
Execution-based Evaluation for Data Science Code Generation Models 17 Nov 2022 jun-jie-huang/exeds/codegpt/bleu.py 2dd8e40379d7bbb9 ran MIT (permissive)
XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence 16 Jun 2022 reddy-lab-code-research/xlcost/code/translation/code/bleu.py 49289a7f94c227bd ran Apache-2.0 (permissive)
StructCoder: Structure-Aware Transformer for Code Generation 10 Jun 2022 reddy-lab-code-research/structcoder/bleu.py 49289a7f94c227bd ran MIT (permissive)
EnvEdit: Environment Editing for Vision-and-Language Navigation 29 Mar 2022 jialuli-luka/envedit/r2r_src/bleu.py 7b5b4685db18fbca unverified MIT (permissive)
CodeQA: A Question Answering Dataset for Source Code Comprehension 17 Sep 2021 jadecxliu/codeqa/codeBERT/code/eval/bleu/google_bleu.py 225b0921f040310c unverified MIT (permissive)
Neighbor-view Enhanced Model for Vision and Language Navigation 15 Jul 2021 MarSaKi/NvEM/r2r_src/bleu.py 7b5b4685db18fbca unverified MIT (permissive)
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding 15 Oct 2020 VegB/Diagnose_VLN/rxr/model/CLIP-ViL-VLN/r2r_src/bleu.py 7b5b4685db18fbca unverified MIT (permissive)
On the Computational Power of Transformers and its Implications in Sequence Modeling 16 Jun 2020 satwik77/Transformer-Computation-Analysis/Transformer/src/utils/bleu.py ae3b0a421287c5c9 unverified MIT (permissive)
Copy that! Editing Sequences by Copying Spans 8 Jun 2020 microsoft/aaai21-copy-that/model/testencdec.py 912f05720e2aef3a unverified MIT (permissive)
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search 20 Sep 2019 nchen909/codeattention/evaluator/bleu.py 49289a7f94c227bd ran MIT (permissive)
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering 13 Sep 2019 ZhangShiyue/QGforQA/LIB/EVAL/bleu.py 9212e9aaf973fc1a unverified MIT (permissive)
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout 8 Apr 2019 airsplay/R2R-EnvDrop/r2r_src/bleu.py 7b5b4685db18fbca unverified MIT (permissive)
Text Infilling 1 Jan 2019 VegB/Text_Infilling/text_infilling/bleu_tool.py dda226c5d7902119 unverified Apache-2.0 (permissive)
A Study of Reinforcement Learning for Neural Machine Translation 27 Aug 2018 apeterswu/RL4NMT/tensor2tensor/utils/bleu_hook.py 0479f465eb03e39f ran · honoured contract no licence file found · pointer only
MojiTalk: Generating Emotional Responses at Scale 11 Nov 2017 Claude-Zhou/MojiTalk/bleu.py 2c08a727cace5066 unverified MIT (permissive)
arXiv:aaai_6453 siat-nlp/TransDG/src/utils/bleu.py c2167c0487876139 unverified MIT (permissive)
arXiv:2025.acl-long.1142 GenIRAG/PER-PSE/flashrag/evaluator/_bleu.py 2dd8e40379d7bbb9 ran MIT (permissive)
arXiv:2024.findings-naacl.46 knalin55/LEEETs-Dial/evaluation_utils.py 9fc45e6d9ca90f15 unverified MIT (permissive)
arXiv:2022.findings-naacl.160 malllabiisc/SGCP/src/bleu.py ae3b0a421287c5c9 unverified Apache-2.0 (permissive)
arXiv:2020.findings-emnlp.289 h4ste/mtft_zsl/fslks/eval/bleu.py f23551c5f115973e unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections