Papers › CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs

19 May 2025arXiv:2505.13778archive 2025-07-28

Guoheng Sun, Ziyao Wang, Bowei Tian, Meng Liu, Zheyu Shen, Shwai He, Yexiao He, Wanghao Ye, Yiting Wang, Ang Li

As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement learning. These reasoning-enhanced models outperform standard LLMs on complex tasks and now underpin many commercial LLM APIs. However, to protect proprietary behavior and reduce verbosity, providers typically conceal the reasoning traces while returning only the final answer. This opacity introduces a critical transparency gap: users are billed for invisible reasoning tokens, which often account for the majority of the cost, yet have no means to verify their authenticity. This opens the door to token count inflation, where providers may overreport token usage or inject synthetic, low-effort tokens to inflate charges. To address this issue, we propose CoIn, a verification framework that audits both the quantity and semantic validity of hidden tokens. CoIn constructs a verifiable hash tree from token embedding fingerprints to check token counts, and uses embedding-based relevance matching to detect fabricated reasoning content. Experiments demonstrate that CoIn, when deployed as a trusted third-party auditor, can effectively detect token count inflation with a success rate reaching up to 94.7%, showing the strong ability to restore billing transparency in opaque LLM services. The dataset and code are available at https://github.com/CASE-Lab-UMD/LLM-Auditing-CoIn.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 15 ran (15 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

case-lab-umd/llm-auditing-coin officialmentioned in paperpytorchMITSyntology: 18 samples, 15 ran (0 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

15ran
3unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from case-lab-umd/llm-auditing-coin. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its 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.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at 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 cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

case-lab-umd/llm-auditing-coin official repository 18 samples, 15 ran (0 instrument-failed) · 3 unverified
circle_loss 3_Block2Answer/train/loss_func.py ran MIT (permissive) · 191c319131abd458 · report fixture: signature logits:Tensor/1/float, labels:Tensor/1/int, margin:float/0/float, gamma:int/0/int · returned Tensor · level recorded 2026-09-25
construct_flat_merkle_tree 2_hash_tree/main_eval.py ran MIT (permissive) · f002064d6028a788 · report fixture: signature leaves:list/1/str · returned list · level recorded 2026-09-25
construct_prompt in 24 papers 6_discussion/LLM_predict.py ran MIT (permissive) · 2843e3f35ce11d01 · report fixture: signature item:dict/0/? · returned str · level recorded 2026-09-25
construct_prompt in 24 papers 6_discussion/LLM_reconstruct.py ran MIT (permissive) · 577fc0eeba8dfc18 · report fixture: signature item:dict/0/? · returned str · level recorded 2026-09-25
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
3_Block2Answer/train/loss_func.py ran MIT (permissive) · 37e51a6ba577d8d9 · report fixture: signature emb_a:Tensor/2/float, emb_b:Tensor/2/float, labels:Tensor/1/float, margin:float/0/float · returned Tensor · level recorded 2026-09-25
extract_think_and_solution_V2 0_preprocess/train_eval.py ran MIT (permissive) · 0bdd5673fd4522a4 · report fixture: signature text:str/0/str · returned tuple · level recorded 2026-09-25
extract_think_sections 0_preprocess/train_eval.py ran MIT (permissive) · ecfef8a7e8d9d7da · report fixture: signature text:str/0/str · returned tuple · level recorded 2026-09-25
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
3_Block2Answer/train/loss_func.py ran MIT (permissive) · d00ea9e4c5542ee7 · report fixture: signature logits:Tensor/2/float, targets:Tensor/2/float, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-25
get_matching_head 5_CoIn_pipline/heads.py ran MIT (permissive) · 755711dbf05419ed · report fixture: signature head_type:str/0/str, embedding_dim:int/0/int · returned MatchingHeadBase · level recorded 2026-09-25
hash_data 2_hash_tree/main_eval.py ran fingerprinted MIT (permissive) · 081cd788e89c4c62 · report fixture: signature data:str/0/str · returned str · level recorded 2026-09-25
hash_data 2_hash_tree/verify.py ran fingerprinted MIT (permissive) · e706f25280079c8b · report fixture: signature data:str/0/str · returned str · level recorded 2026-09-25
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
6_discussion/LLM_predict.py ran MIT (permissive) · d586143500c563f6 · report fixture: signature item:dict/0/? · returned dict · level recorded 2026-09-25
record_result 6_discussion/LLM_predict.py ran MIT (permissive) · f76ceb3944d49dd6 · report fixture: signature item:dict/0/?, result:str/0/str · returned dict · level recorded 2026-09-25
run_validation_on_preprocessed_rule_based 5_CoIn_pipline/main_rule_based_efficient_acc.py ran MIT (permissive) · 05c3140dd19ecd13 · report fixture: signature preprocessed_sample_data:dict/0/?, probing_ratio:float/0/float, verification_threshold:float/0/float · returned bool · level recorded 2026-09-25
verify_merkle_proof 2_hash_tree/verify.py ran MIT (permissive) · 03c01d5adb6beae2 · report fixture: signature index:int/0/int, leaf_value:str/0/str, proof:list/1/str, root:str/0/str, total_leaves:int/0/int · returned bool · level recorded 2026-09-25
generate_merkle_proof 2_hash_tree/verify.py unverified MIT (permissive) · b07a313f5559ca17 · report
run_validation_on_preprocessed 5_CoIn_pipline/main_learned_verify_efficient_acc.py unverified MIT (permissive) · a23ed0eaf28abbcc · report
run_validation_on_preprocessed 5_CoIn_pipline/main_learned_verify_efficient_other_metric.py unverified MIT (permissive) · 3d239420db2c90e4 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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