SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.07976 · 2026

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

Vladimir Braverman, Guanchu Wang, Zhaozhuo Xu, Zicheng Xu, Xiuyi Lou, Yu-Neng Chuang, Hoang Duy Le, Preprint

arXiv · PDF · Open in the Atlas

Code that ran

4 of 11 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 7 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/2607.07976.json · badge: /api/ran/2607.07976.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
xiuyilou/TACO canonical (classifier label)
classifier basis: census
4 ran · 7 no recorded run
FunctionStatusWhere it lives
generate_config_from_args Ran
ran; our contract draft was wrong, not the code
xiuyilou/TACO/verl/model_merger/base_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("8896f4e2bafe8abc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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_dynamic_pipeline_shards Ran
ran, honoured the contract we drafted
xiuyilou/TACO/verl/model_merger/megatron_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("94209884dcb2308e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

is_ipv4 Ran
ran, violated the contract we drafted
xiuyilou/TACO/verl/utils/net_utils.py
pointer only (licence: NONE) · get_code("735e93af30b15fa9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

unpad_dataproto Ran
ran; our contract draft was wrong, not the code
xiuyilou/TACO/verl/protocol.py
pointer only (licence: NONE) · get_code("83b1686d7ac03c21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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_generation_config Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/utils/model.py
pointer only (licence: NONE) · get_code("e6c72459395ae26a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

get_huggingface_actor_config Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/utils/model.py
pointer only (licence: NONE) · get_code("1b071bded6f62e73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

get_weight_loader Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("acf240079d434746")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

get_weight_saver Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("ada2d6cf9ca9ee89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

is_ipv6 Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/utils/net_utils.py
pointer only (licence: NONE) · get_code("705afe175ad8e404")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

is_valid_ipv6_address Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/utils/net_utils.py
pointer only (licence: NONE) · get_code("72b5e8089e8c68a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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.

squeeze Not yet run
unverified (harvested, no recorded run)
xiuyilou/TACO/verl/utils/model.py
pointer only (licence: NONE) · get_code("3b15e2ac7497c441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiuyilou/TACO 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 11 the same month, 11 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.

FunctionAlso present inEarliest-datedOthers named
unpad_dataproto 89 other papers
79 dated earlier, 2 the same month, 5 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
squeeze 82 other papers
73 dated earlier, 1 the same month, 5 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 79 more not named here
get_generation_config 63 other papers
55 dated earlier, 1 the same month, 5 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
and 60 more not named here
get_weight_loader 58 other papers
49 dated earlier, 2 the same month, 5 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2505.14362 (2025-05)
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
2505.20046 (2025-05)
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
and 55 more not named here
generate_config_from_args 57 other papers
44 dated earlier, 4 the same month, 6 later, 3 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 54 more not named here
get_dynamic_pipeline_shards 52 other papers
39 dated earlier, 3 the same month, 8 later, 2 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 49 more not named here
is_ipv4 41 other papers
33 dated earlier, 1 the same month, 5 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2506.08672 (2025-06)
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
2506.12935 (2025-06)
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
and 38 more not named here
is_ipv6 41 other papers
33 dated earlier, 1 the same month, 5 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2506.08672 (2025-06)
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
2506.12935 (2025-06)
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
and 38 more not named here
get_huggingface_actor_config 28 other papers
21 dated earlier, 1 the same month, 5 later, 1 undated
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2601.02648 (2026-01)
Prioritized Replay for RL Post-training
2602.02518 (2026-02)
GRAPHDANCER: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
and 25 more not named here
get_weight_saver 17 other papers
11 dated earlier, 1 the same month, 5 later
2601.02648 (2026-01)
Prioritized Replay for RL Post-training
2602.04879 (2026-02)
Rethinking the Trust Region in LLM Reinforcement Learning
2602.10609 (2026-02)
Online Causal Kalman Filtering for Stable and Effective Policy Optimization
and 14 more not named here
is_valid_ipv6_address 15 other papers
9 dated earlier, 1 the same month, 5 later
2506.03887 (2025-06)
Pre 3 : Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation
2602.04879 (2026-02)
Rethinking the Trust Region in LLM Reinforcement Learning
2602.10609 (2026-02)
Online Causal Kalman Filtering for Stable and Effective Policy Optimization
and 12 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

Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rely on uniform credit assignment, broadcasting the same advantage to all tokens regardless of their differences. We identify a critical failure mode of this design, which we refer to as Positive-Credit Contamination: lowprobability tail tokens that are contextually erroneous receive identical positive credit to plausible ones within the same trajectory, resulting in the indiscriminate reinforcement of flawed reasoning behavior. To mitigate this issue, we propose Tail-Aware Credit calibratiOn (TACO), a method that calibrates uniform credit assignment to suppress undesirable positive updates. TACO first computes a tail-risk score that incorporates the local generation context to assess each token's risk of falling into the unreliable tail, distinguishing unexpected rarity from uncertaintydriven exploration. TACO then uses this score to tune positive credit for risky tokens without removing their gradients entirely, so that recurring useful rare patterns can accumulate reinforcement while incidental noise is progressively dampened. Experimental results across three LLMs and eight benchmarks show that TACO consistently outperforms GRPO-style baselines. Notably, TACO improves training stability, supporting sustained performance gains in long-horizon RL. The source code is available at: https://github.com/xiuyilou/TACO.

For agents

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

get_harvested_code_for_paper("2607.07976")
get_code_for_paper("2607.07976")
have("2607.07976")

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

curl https://syntology.ai/api/ran/2607.07976.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.07976.svg)](https://syntology.ai/paper/2607.07976)

Connect an agent — have() is free.