Home › Code › generate_completions

generate_completions

Syntologyentry name in harvested coderead from the graph 2026-09-24

generate_completions appears in the code Syntology harvested for 38 papers, as 15 distinct code bodies found in 39 places (a place is one code body under one paper). At least one of them ran in 23 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named generate_completions do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 7 of the 15 distinct code bodies named generate_completions; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
7ran
8unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 39 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

38 papers shown of 38, newest first; 39 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 10 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output added by Syntology 2026-06 (from id) fanqiwan/FuseAI/FuseO1-Preview/math_evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
LLM Self-Recognition: Steering and Retrieving Activation Signatures added by Syntology 2026-06 (from id) Thibaud-Ardoin/LLM-Self-Recognition/self_recognition/LLM_SelfRecognition_via_Activations-public/text_generation.py 4eab1454f559e5e8 unverified MIT (permissive)
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR added by Syntology 2026-04 (from id) QwenLM/Qwen2.5-Math/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning added by Syntology 2026-04 (from id) 00Dreamer00/ATTC/model_utils.py 1525d8bc0fc8d5a0 ran MIT (permissive)
Learning to Hint for Reinforcement Learning added by Syntology 2026-04 (from id) Andree-9/HiLL/eval/qwen_evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL added by Syntology 2026-03 (from id) amazon-science/adaptive-layerwise-perturbation/multi-turn/eval/qwen_evaluation/model_utils.py 1525d8bc0fc8d5a0 ran Apache-2.0 (permissive)
On Representation Redundancy in Large-Scale Instruction Tuning Data Selection added by Syntology 2026-02 (from id) tdano1/CRDS/main/eval/eval_utils.py 352416cd121404a7 unverified Apache-2.0 (permissive)
On Representation Redundancy in Large-Scale Instruction Tuning Data Selection added by Syntology 2026-02 (from id) tdano1/CRDS/main/eval/utils.py cdbcc01805fac313 unverified Apache-2.0 (permissive)
Self-Hinting Language Models Enhance Reinforcement Learning added by Syntology 2026-02 (from id) BaohaoLiao/SAGE/eval/qwen_evaluation/model_utils.py 1525d8bc0fc8d5a0 ran Apache-2.0 (permissive)
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety added by Syntology 2026-02 (from id) BattleWen/MAGIC/eval/safety-eval-fork/src/generation_utils.py 0910689e7f72b55a unverified Apache-2.0 (permissive)
All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training added by Syntology 2026-01 (from id) chi2liu/ABC-GRPO/eval_math/model_utils.py 1525d8bc0fc8d5a0 ran Apache-2.0 (permissive)
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation 17 Jul 2025 foreverlasting1202/QuestA/AReaL/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling 25 Jun 2025 gair-nlp/octothinker/eval/eval/utils.py 73f280086b2714ce unverified Apache-2.0 (permissive)
Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting 26 May 2025 evanwu1125/litecot/eval/Qwen2.5-Math/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran MIT (permissive)
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning 12 May 2025 HKUSTDial/LEAD/src/eval/utils.py cdbcc01805fac313 unverified MIT (permissive)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example 29 Apr 2025 ypwang61/one-shot-rlvr/Qwen2.5-Eval/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran Apache-2.0 (permissive)
Process Reward Models That Think 23 Apr 2025 mukhal/thinkprm/search-and-learn/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran MIT (permissive)
DataDecide: How to Predict Best Pretraining Data with Small Experiments 15 Apr 2025 gair-nlp/prox/eval/utils.py 656a50d525064a31 unverified Apache-2.0 (permissive)
Concise Reasoning via Reinforcement Learning 7 Apr 2025 ai-wand/concise-reasoning/eval/model_utils.py 1525d8bc0fc8d5a0 ran MIT (permissive)
S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning 18 Feb 2025 nineabyss/s2r/sample/model_utils.py 1525d8bc0fc8d5a0 ran MIT (permissive)
TokenSkip: Controllable Chain-of-Thought Compression in LLMs 17 Feb 2025 hemingkx/TokenSkip/eval/utils.py 14ec4b04b4360475 unverified Apache-2.0 (permissive)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition 10 Feb 2025 GuanghaoYe/Emergence-of-Thinking/evaluation/model_utils.py 25f1381fe69df071 unverified Apache-2.0 (permissive)
Weighted-Reward Preference Optimization for Implicit Model Fusion 4 Dec 2024 fanqiwan/fuseai/FuseO1-Preview/math_evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
Constraint Back-translation Improves Complex Instruction Following of Large Language Models 31 Oct 2024 thu-keg/crab/eval/utils.py cdbcc01805fac313 unverified no licence file found · pointer only
Compute-Constrained Data Selection 21 Oct 2024 oseyosey/CCDS/ccds/evaluation/eval/utils.py 352416cd121404a7 unverified Apache-2.0 (permissive)
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models 10 Oct 2024 kbsdjames/omni-math-rule/evaluation/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization 14 Aug 2024 YJiangcm/BMC/eval/math/eval/model_utils.py 1525d8bc0fc8d5a0 ran Apache-2.0 (permissive)
Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing 11 Jul 2024 lucywang720/model-surgery/eval/utils.py 0064be5c9154d721 ran no licence file found · pointer only
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs 26 Jun 2024 dvlab-research/step-dpo/evaluation/eval/utils.py df28d2ed3962986b ran no licence file found · pointer only
Finding Safety Neurons in Large Language Models 20 Jun 2024 THU-KEG/SafetyNeuron/src/eval/utils.py 4b7fca0051f25274 ran MIT (permissive)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models 23 May 2024 rucaibox/jiuzhang3.0/eval/model_utils.py 1525d8bc0fc8d5a0 ran no licence file found · pointer only
ADELIE: Aligning Large Language Models on Information Extraction 8 May 2024 THU-KEG/ADELIE/train4llama/eval/utils.py cdbcc01805fac313 unverified no licence file found · pointer only
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection 26 Feb 2024 Blue-Raincoat/SelectIT/eval/eval/utils.py cdbcc01805fac313 unverified no licence file found · pointer only
Scaling Sparse Fine-Tuning to Large Language Models 29 Jan 2024 ducdauge/sft-llm/eval/utils.py 62004a6900e0e332 ran MIT (permissive)
Airavata: Introducing Hindi Instruction-tuned LLM 26 Jan 2024 ai4bharat/indicinstruct/eval/utils.py 352416cd121404a7 unverified Apache-2.0 (permissive)
Knowledge Verification to Nip Hallucination in the Bud 19 Jan 2024 fanqiwan/KCA/examination/utils.py 352416cd121404a7 unverified Apache-2.0 (permissive)
Tuning Language Models by Proxy 16 Jan 2024 alisawuffles/proxy-tuning/eval/utils.py b304416cbba64cb7 ran no licence file found · pointer only
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models 12 Oct 2023 kaistAI/Prometheus/train/utils.py 352416cd121404a7 unverified no licence file found · pointer only
Lemur: Harmonizing Natural Language and Code for Language Agents 10 Oct 2023 OpenLemur/Lemur/xchat/eval/utils.py 3eeddf88871321ab ran Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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