Home › Code › extract_code

extract_code

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

extract_code appears in the code Syntology harvested for 24 papers, as 27 distinct code bodies found in 28 places (a place is one code body under one paper). Of the 24 papers, 21 with a sample that ran: 6 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument. 21 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 extract_code 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 27 distinct code bodies named extract_code: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 17 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
17ran · our draft was wrong
0ran; the contract check could not run
7ran
3unverified
21fingerprinted

Licence is a property of each copy, so it is counted per place: 10 of the 28 places are pointer only (Syntology does not serve that copy's text); at 1 of them this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

24 papers shown of 24, newest first; 28 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 9 papers added by Syntology. 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. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models added by Syntology 2026-07 (from id) ming053l/C4-dLLM/c4/codegen_grade.py 1660493478fd2823 ran · our draft was wrong fingerprinted MIT (permissive)
Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes added by Syntology 2026-07 (from id) ZhouYuxuanYX/Fast-HSD/fast_hsd/benchmarks/_mbppplus_scoring.py 6802b1b27591fad2 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources added by Syntology 2026-06 (from id) Hsiang-1/MiniOpt/rl/opt_reward.py dd14950a6b76ffbc ran · our draft was wrong fingerprinted no licence file found · pointer only
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models added by Syntology 2026-05 (from id) GaryBall/GDSD/gdsd/rewards.py 0f07a2dc4671890b ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions added by Syntology 2026-05 (from id) masamodelkin/llm-robustness-code-execution/src/evals/PAL.py 1b2e245d59818293 ran · our draft was wrong fingerprinted MIT (permissive)
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers added by Syntology 2026-05 (from id) IDEALLab/neural-solver-synthesis/evaluation/sds/universal_solver_search.py 5a3b15c8fcdee09d ran · our draft was wrong fingerprinted no licence file found · pointer only
Strategy-Aware Optimization Modeling with Reasoning LLMs added by Syntology 2026-05 (from id) rachhhhing/SAGE/eval/execute.py dc0fc511d2aa9942 ran · our draft was wrong fingerprinted no licence file found · pointer only
HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy added by Syntology 2026-04 (from id) XMUDeepLIT/HCRE/auto-tree/utils.py 495dba1ca2e724dc ran · our draft was wrong fingerprinted no licence file found · pointer only
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning added by Syntology 2026-04 (from id) ericjiang18/Agent-Q-Mix/agent_baseline/utils/code_extract.py e7afca0a2b453f4c ran · our draft was wrong fingerprinted no licence file found · pointer only
Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization 27 May 2025 yiding-s/MoH/moh.py 02ffbc411e44afd8 unverified MIT (permissive)
Absolute Zero: Reinforced Self-play Reasoning with Zero Data 6 May 2025 LeapLabTHU/Absolute-Zero-Reasoner/absolute_zero_reasoner/rewards/code_reward.py dd14950a6b76ffbc ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Absolute Zero: Reinforced Self-play Reasoning with Zero Data 6 May 2025 LeapLabTHU/Absolute-Zero-Reasoner/absolute_zero_reasoner/rewards/custom_evaluate.py 72c1465a54867eee ran fingerprinted MIT (permissive)
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing 10 Mar 2025 yiqingxyq/RepoST/utils.py 71210ee33ca4b9bb ran MIT (permissive)
Scalable Best-of-N Selection for Large Language Models via Self-Certainty 25 Feb 2025 backprop07/Self-Certainty/src/livecode_self_certainty_from_list.py 8a7e4da9680173bb ran · our draft was wrong fingerprinted no licence file found · pointer only
Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models 29 Sep 2024 bupt-gamma/graphteam/multi-agents-4-graph-analysis/GraphTeam/camel/agents.py 77d746c4da984457 ran fingerprinted MIT (permissive)
OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale 29 Jul 2024 teshnizi/optimus/Reflexion.py 3400042ef10a04a1 ran · our draft was wrong fingerprinted MIT (permissive)
OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale 29 Jul 2024 teshnizi/optimus/execute_code.py 1b35aeee4688c891 ran · our draft was wrong fingerprinted MIT (permissive)
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct 8 Jul 2024 wyt2000/InverseCoder/src/InstGen/sample_vllm.py 4ba4d218cc21b7c3 ran · our draft was wrong fingerprinted no licence file found · pointer only
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct 8 Jul 2024 wyt2000/InverseCoder/src/InstGen/sample_vllm_parallel.py 2e57c27d5464d633 ran · our draft was wrong fingerprinted no licence file found · pointer only
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools 18 Jun 2024 thudm/chatglm/composite_demo/demo_tool.py e4671affec558222 unverified Apache-2.0 (permissive)
AnalogCoder: Analog Circuit Design via Training-Free Code Generation 23 May 2024 laiyao1/AnalogCoder/gpt_run.py 3248e0669f8d0053 ran · our draft was wrong fingerprinted MIT (permissive)
Aligning the Objective of LLM-based Program Repair 13 Apr 2024 cuhk-shenzhen-se/d4c/utils/patch_apply.py d11e7e729a9dd4ea ran · our draft was wrong fingerprinted MIT (permissive)
Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents 8 Mar 2024 tapilot-crossing/tapilot_code/postprocessing/combine_code_gen_AIR.py c805463b7efcc6de ran MIT (permissive)
Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents 8 Mar 2024 tapilot-crossing/tapilot_code/postprocessing/combine_code_gen_base.py 0d2c5937f51ac5ab ran fingerprinted MIT (permissive)
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation 4 Mar 2024 shirley-wu/daco/code/utils.py 723183a95fe27709 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation 3 Oct 2023 microsoft/stop/helpers.py dc62532cec8323f5 unverified MIT (permissive)
GenSim: Generating Robotic Simulation Tasks via Large Language Models 2 Oct 2023 liruiw/gensim/gensim/utils.py 5f7af117975e9a6e ran fingerprinted MIT (permissive)
Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference 8 Mar 2023 kevin666aa/flaml/flaml/autogen/code_utils.py 0a954340369b7456 ran MIT recorded; this copy not marked cleared · pointer only

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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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