Home › Code › get_system_prompt

get_system_prompt

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

get_system_prompt appears in the code Syntology harvested for 15 papers, as 16 distinct code bodies found in 16 places (a place is one code body under one paper). At least one of them ran in 8 of the papers; 4 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 get_system_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 9 of the 16 distinct code bodies named get_system_prompt; 7 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
0ran · fixture could not drive it
8ran
7unverified
4fingerprinted

Licence is a property of each copy, so it is counted per place: 9 of the 16 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

15 papers shown of 15, newest first; 16 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 11 papers added by Syntology; 1 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
ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs added by Syntology 2026-09 (from id) megagonlabs/absol-bn/core/prompts.py 1fd3e1daf983bd2c unverified licence not identified · pointer only
When Does Continual Learning Require Learning added by Syntology 2026-07 (from id) anneharrington/studying-cl/cl/tasks.py 7cfd22b79a701a78 unverified MIT (permissive)
Evidence-Supported Credit Risk Report Generation Using News-Centric Financial Knowledge Graph added by Syntology 2026-07 (from id) ichise-laboratory/FINKG-news/FinKG-News-Framework/2.1-run_event_detection.py bacadcaa2c825138 ran Apache-2.0 (permissive)
LegalCiteBench: Evaluating Citation Reliability in Legal Language Models added by Syntology 2026-05 (from id) Sijia711/LegalCiteBench/legal-citation-benchmark-clean/eval/eval_model.py a99a765f3eb79781 ran fingerprinted MIT (permissive)
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search added by Syntology 2026-05 (from id) hbhalpha/InterLV-Search-Bench/agentic_search/prompts.py fe322f624cf17ea6 ran fingerprinted no licence file found · pointer only
Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen added by Syntology 2026-04 (from id) synthiumjp/koriat/inference_engine_koriat.py 3e2f19601a37f1ae ran fingerprinted MIT (permissive)
RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning added by Syntology 2026-03 (from id) rlisml/RxnNano/src/config/prompts.py 6d32fa4e45923284 unverified MIT (permissive)
IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering added by Syntology 2026-02 (from id) weaviate/query-agent-benchmarking/query_agent_benchmarking/internal/config/qa_system_prompt_registry.py ac61116f90ca6017 unverified BSD-3-Clause (permissive)
Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding added by Syntology 2026-01 (from id) scheshmi/CrossStyle-MMR/train/grpo.py 87d9f8c9b2eb76a4 unverified no licence file found · pointer only
ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting added by Syntology 2026-01 (from id) LuminosityX/ThinkTank-ME/POLECAT-FOR-ME/3_country_dataset/multiexpert/get_real_data.py bb6a58cc807f647f ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only
NO RELIABLE EVIDENCE OF SELF-REPORTED SENTIENCE IN LARGE LANGUAGE MODELS added by Syntology 2026-01 (from id) casparwarwick/sentient_machines_public/01_cluster_pipeline/generate_chat_datasets_exercise.py 219d347ff1180ea6 unverified no licence file found · pointer only
LLMs generate structurally realistic social networks but overestimate political homophily 29 Aug 2024 snap-stanford/llm-social-network/generate_networks.py 0d15a8a4a2812268 ran no licence file found · pointer only
ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems 5 Aug 2024 zhudotexe/redel/redel/kanis.py 3b48984314572989 ran licence not identified · pointer only
ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning 11 Feb 2024 YihongT/ITINERA/model/utils/all_en_prompts.py 87a664f64490967a ran GPL-3.0 (copyleft) · pointer only
ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning 11 Feb 2024 YihongT/ITINERA/model/utils/all_prompts.py 6e22cfdfe430f70a ran GPL-3.0 (copyleft) · pointer only
arXiv:2024.findings-emnlp.514 VityaVitalich/MeritOpt/pipeline_src/dataset/dataset.py ec3414697fadb07b 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