Jaehyung Kim, Minjae Kang
2 of 3 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, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 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/2603.06745.json · badge: /api/ran/2603.06745.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 |
|---|---|---|
| mjk0618/directer | community Papers with Code archive |
2 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| _parse_token_indices | Ran ran, honoured the contract we drafted |
mjk0618/directer/src/generator.py pointer only (licence: NONE) · get_code("121c9cadb1f55fce") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, mjk0618/directer 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. |
| scale_kv_cache | Ran ran; our contract draft was wrong, not the code |
mjk0618/directer/src/generator.py pointer only (licence: NONE) · get_code("48a479092d5a872f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, mjk0618/directer 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. |
| DirecterGenerator | Not yet run unverified (harvested, no recorded run) |
mjk0618/directer/src/generator.py pointer only (licence: NONE) · get_code("860eff61c35da510") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, mjk0618/directer 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. |
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.
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 , despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of oversteering, where excessive emphasis on the instruction degrades task accuracy and overall text quality. To address this, we introduce DIRECTER (Dynamic rejection steering), a novel steering method that dynamically modulates steering strength by scaling the KV cache without extra dataset. DIRECTER couples steering with a plausibilityguided decoding loop, which adaptively adjusts steering strength at each step by the steered output distribution to the original. If the steered output is deemed implausible, steering strength is progressively weakened. This strength modulation is guided by a lightweight, one-time attention sensitivity analysis that ranks layers by their influence on model representations. Extensive evaluations show that DIRECTER significantly enhances instruction-following capabilities across diverse benchmarks, improving accuracy by up to 6.5% over baselines without the common trade-offs in generation quality or task fidelity. The proposed dynamic, plausibility-guided control during activation steering further demonstrates its potential as a general mechanism for mitigating oversteering that is compatible with existing baselines.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2603.06745")
get_code_for_paper("2603.06745")
have("2603.06745")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2603.06745.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2603.06745)
Connect an agent — have() is free.