5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2311.04155.json · badge: /api/ran/2311.04155.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| thu-coai/bpo | canonical (classifier label) classifier basis: census |
5 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| build_template_default | Ran ran; our contract draft was wrong, not the code |
thu-coai/bpo/src/training/data_processer.py code served (permissive licence) · get_code("53444f4af7b67958") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| build_template_llama | Ran ran; our contract draft was wrong, not the code |
thu-coai/bpo/src/training/data_processer.py code served (permissive licence) · get_code("12f81c87374a4ab2") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| build_template_tiger | Ran ran; our contract draft was wrong, not the code |
thu-coai/bpo/src/training/data_processer.py code served (permissive licence) · get_code("b8b3a308395df443") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| postprocess | Ran ran; our contract draft was wrong, not the code |
thu-coai/bpo/src/training/data_utils.py code served (permissive licence) · get_code("b629ae49b12e3de3") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| preprocess | Ran ran; our contract draft was wrong, not the code |
thu-coai/bpo/src/training/data_utils.py code served (permissive licence) · get_code("ce3e76d93e76d129") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| chat_gpt | Not yet run unverified (harvested, no recorded run) |
thu-coai/bpo/src/data_construction/chatgpt_infer.py code served (permissive licence) · get_code("c6e5695547deaf80") How it ranno invocation recorded. |
| chat_gpt | Not yet run unverified (harvested, no recorded run) |
thu-coai/bpo/src/evaluation/gpt4_score.py code served (permissive licence) · get_code("1350e6afade56462") How it ranno invocation recorded. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| build_template_default | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| build_template_llama | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| build_template_tiger | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| chat_gpt | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| chat_gpt | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| postprocess | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
|
| preprocess | 1 other paper 1 later |
2024.acl-long.176 (2024 (year only)) Black-Box Prompt Optimization: Aligning Large Language Models without Model Training |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make LLMs better follow user instructions, existing alignment methods primarily focus on further training them. However, the extra training of LLMs is usually expensive in terms of GPU computing; even worse, some LLMs are not accessible for user-demanded training, such as GPTs. In this work, we take a different perspective -- Black-Box Prompt Optimization (BPO) -- to perform alignments. The idea is to optimize user prompts to suit LLMs' input understanding, so as to best realize users' intents without updating LLMs' parameters. BPO leverages human preferences to optimize prompts, thus making it superior to LLM (e.g., ChatGPT) as a prompt engineer. Moreover, BPO is model-agnostic, and the empirical results demonstrate that the BPO-aligned ChatGPT yields a 22% increase in the win rate against its original version and 10% for GPT-4. Notably, the BPO-aligned LLMs can outperform the same models aligned by PPO and DPO, and it also brings additional performance gains when combining BPO with PPO or DPO. Code and datasets are released at https://github.com/thu-coai/BPO.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.04155")
get_code_for_paper("2311.04155")
have("2311.04155")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2311.04155.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2311.04155)
Connect an agent — have() is free.