Home › Code › batch_to_device

batch_to_device

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.

batch_to_device appears in the code Syntology harvested for 18 papers, as 14 distinct code bodies found in 18 places (a place is one code body under one paper). Of the 18 papers, 17 with a sample that ran: 3 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument. 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 batch_to_device 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 batch_to_device: 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 1 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
10ran · our draft was wrong
0ran; the contract check could not run
3ran
1unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 4 of the 18 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 “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

18 papers shown of 18, newest first; 18 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 1 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. 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
VIRTUE: Visual-Interactive Text-Image Universal Embedder added by Syntology 2025-10 (from id) sony/virtue/codes/src/utils.py 5210e1b5ee25838a ran · our draft was wrong Apache-2.0 (permissive)
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining 16 May 2025 raghavlite/b3/eval_mmeb.py 5210e1b5ee25838a ran · our draft was wrong Apache-2.0 (permissive)
Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search 18 Feb 2025 identical code first harvested elsewhere 74b280cb6a91117e ran · our draft was wrong licence of this copy not recorded
Boltzmann priors for Implicit Transfer Operators 2024-10 (from id) olsson-group/bopito/bopito/utils/utils.py 14f0e23d9b147a4c ran · our draft was wrong MIT (permissive)
Scaling Laws For Dense Retrieval 27 Mar 2024 jingtaozhan/drscale/modeling.py 784e8a98f055bde0 ran · our draft was wrong MIT (permissive)
Repetition Improves Language Model Embeddings 23 Feb 2024 identical code first harvested elsewhere 74b280cb6a91117e ran · our draft was wrong licence of this copy not recorded
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models 20 Feb 2024 YangLing0818/RealCompo/inference_layout.py 6e5276dc429a7d87 unverified no licence file found · pointer only
Answer is All You Need: Instruction-following Text Embedding via Answering the Question 15 Feb 2024 zhang-yu-wei/inbedder/lm_encoders_hf/causallm_encoder_hf.py 90710324cdd36fd8 ran · our draft was wrong MIT (permissive)
Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL 11 Feb 2024 rlatjddbs/SSD/dc/dc.py 61a25fc7fbbca3a7 ran · our draft was wrong no licence file found · pointer only
InstanceDiffusion: Instance-level Control for Image Generation 5 Feb 2024 frank-xwang/InstanceDiffusion/dataset/jsondataset.py 6a31c83c41f11b71 ran · our draft was wrong Apache-2.0 (permissive)
Improving Text Embeddings with Large Language Models 31 Dec 2023 mcgill-nlp/llm2vec/llm2vec/llm2vec.py 74b280cb6a91117e ran · our draft was wrong MIT (permissive)
Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans 30 Oct 2023 leekwoon/rgg/scripts/train_gap_predictor.py cf94ba8f107993a3 ran · our draft was wrong MIT (permissive)
LightGlue: Local Feature Matching at Light Speed 23 Jun 2023 cvg/lightglue/lightglue/utils.py 80f11116ef08b1e5 ran Apache-2.0 (permissive)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings 19 Dec 2022 xlang-ai/instructor-embedding/InstructorEmbedding/instructor.py f567def389222696 ran · our draft was wrong Apache-2.0 (permissive)
Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest 13 Sep 2022 jmhessel/caption_contest_corpus/clip/train_clip.py a727742f777acc6a ran · our draft was wrong MIT (permissive)
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval 12 Oct 2021 jingtaozhan/JPQ/jpq/model.py 784e8a98f055bde0 ran · our draft was wrong MIT (permissive)
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs 28 May 2020 seanie12/Info-HCVAE/vae/utils.py 7cef89edf29127bc ran Apache-2.0 (permissive)
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models 29 Nov 2018 molecularsets/moses/moses/utils.py 5915368a2b2e451a ran MIT (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