Home › Code › construct_prompt

construct_prompt

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

construct_prompt appears in the code Syntology harvested for 24 papers, as 22 distinct code bodies found in 26 places (a place is one code body under one paper). At least one of them ran in 11 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 construct_prompt 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 8 of the 22 distinct code bodies named construct_prompt; 14 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
5ran · our draft was wrong
0ran · fixture could not drive it
3ran
14unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 10 of the 26 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

24 papers shown of 24, newest first; 26 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 4 papers added by Syntology; 2 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
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits added by Syntology 2026-08 (from id) ellyoana/sn-guided-diffusion/utils.py af81b308c704f33f unverified no licence file found · pointer only
LJ-Bench: Ontology-Based Benchmark for U.S. Crime added by Syntology 2026-03 (from id) AndreaTseng/LJ-Bench/src/format_prompt.py 645c86835778befe ran · our draft was wrong fingerprinted no licence file found · pointer only
Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs added by Syntology 2026-01 (from id) myracheng/accommodation/evaluation_scripts/cancereval.py c0260539abdf7bc3 unverified no licence file found · pointer only
Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs added by Syntology 2026-01 (from id) myracheng/accommodation/evaluation_scripts/cancernfpeval.py 232b2b752503f49b unverified no licence file found · pointer only
Teaching Language Models to Reason with Tools added by Syntology 2025-10 (from id) ChengpengLi1003/CoRT/infer/utils.py ecdacf069c9d10db unverified no licence file found · pointer only
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs 19 May 2025 case-lab-umd/llm-auditing-coin/6_discussion/LLM_predict.py 2843e3f35ce11d01 unverified MIT (permissive)
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs 19 May 2025 case-lab-umd/llm-auditing-coin/6_discussion/LLM_reconstruct.py 577fc0eeba8dfc18 unverified MIT (permissive)
UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios 30 Aug 2024 opendatalab/urbench/lmms_eval/tasks/urbench/utils.py 5096e10842a99b97 ran licence not identified · pointer only
Long Context Transfer from Language to Vision 24 Jun 2024 identical code first harvested elsewhere 2e94fa2078ca5f7c ran · our draft was wrong licence of this copy not recorded
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models 21 Jun 2024 BAAI-DCAI/Bunny/bunny/eval/model_vqa_cmmmu.py 2fd1673b298c086c ran Apache-2.0 (permissive)
GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation 17 Jun 2024 lanyu0303/geogpt4v_project/pipeline/gen_instruction_mp.py 8a9188d48800ce95 ran · our draft was wrong MIT (permissive)
Universal In-Context Approximation By Prompting Fully Recurrent Models 3 Jun 2024 aleksandarpetrov/lsrl/lsrl/utils.py 6c84f0afac911592 unverified Apache-2.0 (permissive)
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts 9 May 2024 shi-labs/cumo/cumo/eval/model_vqa_mathvista.py ed80aaedae521e4f unverified Apache-2.0 (permissive)
Rectifying Demonstration Shortcut in In-Context Learning 14 Mar 2024 lainshower/in-context-calibration/utils.py e37bbdf75acd586c ran · our draft was wrong no licence file found · pointer only
Efficient Multimodal Learning from Data-centric Perspective 18 Feb 2024 baai-dcai/bunny/bunny/eval/model_vqa_cmmmu.py 2fd1673b298c086c ran Apache-2.0 (permissive)
Evading Data Contamination Detection for Language Models is (too) Easy 5 Feb 2024 eth-sri/malicious-contamination/src/contamination/llm_decontaminator.py 255132d5b9dc4ec5 ran fingerprinted Apache-2.0 (permissive)
A Study on the Calibration of In-context Learning 7 Dec 2023 hlzhang109/icl-calibration/run_classification_cot.py ef2f02ab0c2e6b74 unverified MIT (permissive)
Ring Attention with Blockwise Transformers for Near-Infinite Context 3 Oct 2023 jzhang38/EasyContext/eval_needle.py 2e94fa2078ca5f7c ran · our draft was wrong Apache-2.0 (permissive)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving 29 Sep 2023 microsoft/tora/src/utils/utils.py ecdacf069c9d10db unverified MIT (permissive)
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models 25 Sep 2023 identical code first harvested elsewhere 2e94fa2078ca5f7c ran · our draft was wrong licence of this copy not recorded
WizardCoder: Empowering Code Large Language Models with Evol-Instruct 14 Jun 2023 kyle-lyu/data-efficient-finetuning/utils/dataset.py fb57aad9f9c18c48 ran · our draft was wrong no licence file found · pointer only
GPT-4 Technical Report 15 Mar 2023 AUCOHL/RTL-Repo/src/utils.py 522809481fa31587 unverified Apache-2.0 (permissive)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings 19 Dec 2022 HKUNLP/instructor-embedding/evaluation/prompt_retrieval/main_geo.py 012e0e03723d52ec unverified Apache-2.0 (permissive)
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks 16 Apr 2022 naver-ai/rethinking-proxy-reward/evaluation.py 308ab826d7562425 unverified Apache-2.0 (permissive)
arXiv:2025.findings-emnlp.103 yha9806/VULCA-EMNLP2025/src/evaluate.py 6da92e6b14d39573 unverified MIT (permissive)
arXiv:2025.findings-acl.491 biodatlab/ec-raft/evaluate.py bbd9e3b2b65460ef unverified Apache-2.0 (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