Home › Code › top_k_logits

top_k_logits

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

top_k_logits appears in the code Syntology harvested for 36 papers, as 14 distinct code bodies found in 38 places (a place is one code body under one paper). Of the 36 papers, 32 with a sample that ran: 4 with a run with no instrument failure, 28 where every run was a failure of Syntology's instrument. 11 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 top_k_logits 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 14 distinct code bodies named top_k_logits: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
7ran; the contract check could not run
4ran
2unverified
11fingerprinted

Licence is a property of each copy, so it is counted per place: 21 of the 38 places are pointer only (Syntology does not serve that copy's text); at 5 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

36 papers shown of 36, newest first; 38 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; 3 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. 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.

PaperDateFileStatus SyntologyLicence
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference added by Syntology 2026-08 (from id) burcgokden/lm-evaluation-harness-with-PLDR-LLM/lm_eval/models/pldrllm.py d45ec14e4fa4dd35 unverified MIT (permissive)
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation added by Syntology 2026-06 (from id) PunchlineAAAA/DICE/dream/generation_utils.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models added by Syntology 2026-06 (from id) PKU-ML/TrustLDM/generate_functions/generate_dream.py afeb1c0675c8b6a9 ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted CC-BY-SA-4.0 (copyleft) · pointer only
MotionHiFlow: Text-to-Motion via Hierarchical Flow Matching added by Syntology 2026-04 (from id) ai-lh/MotionHiFlow/src/evaluators/t2m_eval_modules.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted no licence file found · pointer only
R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction added by Syntology 2026-04 (from id) GATECH-EIC/R2-dLLM/dream/model/generation_utils.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference added by Syntology 2026-04 (from id) X-Xia0828/DepCap/dream/model/generation_utils.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs added by Syntology 2026-02 (from id) lizhuo-luo/DAWN/dream/model/generation_utils.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only
AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models? added by Syntology 2026-02 (from id) AMAP-ML/AR-MAP/dLLM-RL-main/generate.py 5ed7c8c8efe5160d ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only
Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding added by Syntology 2026-01 (from id) xiaoshideta/Streaming-dLLM/OpenPangu/inference/generation_utils_streaming.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
Selecting Language Models for Social Science: Start Small, Start Open, and Validate Preprint XX(X):1-22 ©The Author(s) 2026 added by Syntology 2026-01 (from id) openai/gpt-2/src/sample.py d45ec14e4fa4dd35 unverified no licence file found · pointer only
Position: Foundation Agents as the Paradigm Shift for Decision Making 27 May 2024 microsoft/smart/src/models/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted no licence file found · pointer only
Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention 4 Apr 2024 applied-machine-learning-lab/dt4ier/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted no licence file found · pointer only
Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces 29 Mar 2024 toshihiro-ota/decision-mamba/atari/mingpt/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection 17 Feb 2024 mbzuai-nlp/m4gt-bench/src/GLTR/backend/api.py 7be611d6e7fba121 unverified no licence file found · pointer only
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction 6 Feb 2024 ygjin11/r2-play/tool/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted no licence file found · pointer only
MoMask: Generative Masked Modeling of 3D Human Motions 29 Nov 2023 EricGuo5513/momask-codes/models/t2m_eval_modules.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT 11 Oct 2023 deanhazineh/emergent-world-representations-othello/EWOthello/othello_world/mingpt/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Emergent Linear Representations in World Models of Self-Supervised Sequence Models 2 Sep 2023 ajyl/mech_int_othellogpt/mingpt/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training 16 Jul 2023 yunyikristy/DualMind/src/models/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted no licence file found · pointer only
Recurrent Action Transformer with Memory 15 Jun 2023 airi-institute/rate/Atari/train_rate_atari.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task 24 Oct 2022 likenneth/othello_world/mingpt/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts 4 Jul 2022 identical code first harvested elsewhere 0f0021cdea13e4da ran · our draft was wrong fingerprinted licence of this copy not recorded
CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers 28 Apr 2022 thudm/cogview2/coglm_strategy.py 5825bfe57509ed97 ran fingerprinted Apache-2.0 (permissive)
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning 12 Oct 2021 elicassion/StARformer/atari_and_dmc/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
CCVS: Context-aware Controllable Video Synthesis 16 Jul 2021 16lemoing/ccvs/models/skip_vid_generator/models/mingpt.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
SymbolicGPT: A Generative Transformer Model for Symbolic Regression 27 Jun 2021 mojivalipour/symbolicgpt/utils.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation 14 Jun 2021 shawnlimn/scalegrad/custom/sequence_generator.py 298689919da2c5b0 ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive)
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation 14 Jun 2021 shawnlimn/ScaleGrad/custom/sequence_generator.py ace3f464bf5b4c7a ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only
Offline Reinforcement Learning as One Big Sequence Modeling Problem 3 Jun 2021 JannerM/trajectory-transformer/trajectory/search/sampling.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
Offline Reinforcement Learning as One Big Sequence Modeling Problem 3 Jun 2021 howuhh/faster-trajectory-transformer/trajectory/utils/common.py c7cbcd467cc49a53 ran fingerprinted MIT (permissive)
Geometry-Free View Synthesis: Transformers and no 3D Priors 15 Apr 2021 CompVis/geometry-free-view-synthesis/geofree/modules/transformer/mingpt.py 0f0021cdea13e4da ran · our draft was wrong fingerprinted MIT (permissive)
The Adapter-Bot: All-In-One Controllable Conversational Model 28 Aug 2020 HLTCHKUST/adapterbot/interact_adapter.py 612fc65430e63524 ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order 24 Apr 2020 huawei-noah/Pretrained-Language-Model/PMLM/interactive_conditional_samples_sincos_acrostic.py eaa09f3e52dcedfd ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
Neural Text Generation with Unlikelihood Training 12 Aug 2019 facebookresearch/unlikelihood_training/custom/sequence_generator.py ace3f464bf5b4c7a ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only
GLTR: Statistical Detection and Visualization of Generated Text 10 Jun 2019 tgao1337/detecting-fake-text/backend/api.py 7be611d6e7fba121 unverified Apache-2.0 (permissive) here; the stored copy is pointer only
OpenReview id openreview_QrC8OgQyOI viiika/Prism/Dream/Dream_Prism/src/diffllm/gen_utils.py d78ba22cffe4710b ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
ACL Anthology id 2023.findings-acl.805 iesl/Softmax-CPR/src/LM/utils_testing.py a5301805a0a78cfb ran fingerprinted Apache-2.0 (permissive)
ACL Anthology id 2023.findings-acl.765 qtli/EIB/code/BottleSum/bottleSelf_summarize.py 3c40291da6e3944c ran fingerprinted 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 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 under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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