SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.03042 · 2026

BaseCal: Unsupervised Confidence Calibration via Base Model Signals

Xin Chen, Xueqi Cheng, Fei Sun, Jingang Wang, Du Su, Hexiang Tan, Wanli Yang, Rui Tang, Yuanzhuo Wang, Junwei Zhang

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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, 2 violated it and 0 have no contract verdict; 10 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2601.03042.json · badge: /api/ran/2601.03042.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.

RepositoryRoleRan
Tan-Hexiang/BaseCal canonical (classifier label)
classifier basis: census
12 ran · 3 no recorded run
FunctionStatusWhere it lives
basic_process Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/gen_metric/post_process.py
pointer only (licence: NONE) · get_code("77da2f9c09197fbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_mapper Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/basecal.py
pointer only (licence: NONE) · get_code("88cb386ce6a2f122")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

em Ran
ran, violated the contract we drafted
Tan-Hexiang/BaseCal/gen_metric/em.py
pointer only (licence: NONE) · get_code("b38e9fba40933c59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exact_match_score Ran
ran, violated the contract we drafted
Tan-Hexiang/BaseCal/gen_metric/em.py
pointer only (licence: NONE) · get_code("8aa9ea4da99420bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_with_id Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/src/utils.py
pointer only (licence: NONE) · get_code("6a964c15ecd8ec04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_hds_with_cache Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/basecal.py
pointer only (licence: NONE) · get_code("9247ef0c3ccc7441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_loss_fn Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/basecal.py
pointer only (licence: NONE) · get_code("c93832b7f136eb16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

init_logger Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/src/utils.py
pointer only (licence: NONE) · get_code("3b6e57e4e5953ce8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_answer Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/gen_metric/em.py
pointer only (licence: NONE) · get_code("9891ffc5ad4f4684")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

plot_calibration Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Tan-Hexiang/BaseCal/src/plot.py
pointer only (licence: NONE) · get_code("81e1472badb1ace2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

post_process Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/gen_metric/post_process.py
pointer only (licence: NONE) · get_code("569ffcd1c346d06c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_for_base_model Ran
ran; our contract draft was wrong, not the code
Tan-Hexiang/BaseCal/gen_metric/post_process.py
pointer only (licence: NONE) · get_code("eeef9404f039d487")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt Not yet run
unverified (harvested, no recorded run)
Tan-Hexiang/BaseCal/src/prompts.py
pointer only (licence: NONE) · get_code("db9655767f69c29f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

create_prompt Not yet run
unverified (harvested, no recorded run)
Tan-Hexiang/BaseCal/src/prompts_wo_prefix_answer.py
pointer only (licence: NONE) · get_code("d16a3b512854596e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

vllm_correctness Not yet run
unverified (harvested, no recorded run)
Tan-Hexiang/BaseCal/gen_metric/lm_correctness.py
pointer only (licence: NONE) · get_code("f3b360c8e9dfdbf5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Tan-Hexiang/BaseCal when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 0 later) and 12 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.

FunctionAlso present inEarliest-datedOthers named
exact_match_score 56 other papers
55 dated earlier, 1 the same month
1508.06615 (2015-08)
Character-Aware Neural Language Models
1606.05250 (2016-06)
SQuAD: 100,000+ Questions for Machine Comprehension of Text
1608.07905 (2016-08)
Machine Comprehension Using Match-LSTM and Answer Pointer
and 53 more not named here
normalize_answer 9 other papers
8 dated earlier, 1 the same month
2305.12421 (2023-05)
Evaluating Open-QA Evaluation
2308.11730 (2023-08)
Knowledge Graph Prompting for Multi-Document Question Answering
2310.14393 (2023-10)
Merging Generated and Retrieved Knowledge for Open-Domain QA
and 6 more not named here

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed posttrained LLMs (PoLLMs) typically compromise this trust with severe overconfidence. In contrast, we observe that their corresponding base LLMs often remain well-calibrated. This naturally motivates us to calibrate PoLLM confidence using the base LLM as a reference. This work proposes two ways to achieve this. A straightforward solution, BaseCal-ReEval, evaluates PoLLM's responses by feeding them into the base LLM to get average probabilities as confidence. While effective, this approach introduces additional inference overhead. To address this, we propose BaseCal-Proj, which trains a lightweight projection to map the finallayer hidden states of PoLLMs back to those of their base LLMs. These projected states are then processed by the base LLM's output layer to derive base-calibrated confidence for PoLLM's responses. Notably, BaseCal is an unsupervised, plug-and-play solution that operates without human labels or LLM modifications. Experiments across five datasets and three LLM families demonstrate the effectiveness of BaseCal, reducing Expected Calibration Error (ECE) by an average of 42.90% compared to the best unsupervised baselines 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.03042")
get_code_for_paper("2601.03042")
have("2601.03042")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2601.03042.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2601.03042.svg)](https://syntology.ai/paper/2601.03042)

Connect an agent — have() is free.