Home › Code › mask_logits

mask_logits

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

mask_logits appears in the code Syntology harvested for 27 papers, as 12 distinct code bodies found in 29 places (a place is one code body under one paper). At least one of them ran in 25 of the papers; 6 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 mask_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; 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 9 of the 12 distinct code bodies named mask_logits; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

5ran · honoured contract
0ran · violated contract
3ran · our draft was wrong
0ran · fixture could not drive it
1ran
3unverified
6fingerprinted

Licence is a property of each copy, so it is counted per place: 11 of the 29 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

27 papers shown of 27, newest first; 29 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; 2 papers have no page here and are shown by arXiv id only. 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
arXiv:2507.17402 2025-07 (from id) lijun2005/ICCV25-HLFormer/src/Models/HLFormer/model.py 1c17153fb5488283 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering 15 Apr 2025 songpipi/amdnet/Models/gmmformer/model.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding 6 Jul 2024 zxccade/SHINE/shine/text_encoder.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection 14 Apr 2024 EdenGabriel/TaskWeave/taskweave/text_encoder.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection 4 Jan 2024 mingyao1120/TR-DETR/tr_detr/model.py 60df4d5a1eee1b92 ran · honoured contract fingerprinted licence not identified · pointer only
MatterGen: a generative model for inorganic materials design 6 Dec 2023 microsoft/mattergen/mattergen/denoiser.py 03958afbc7e37a36 unverified MIT (permissive)
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos 30 Nov 2023 Pilhyeon/BAM-DETR/bam_detr/text_encoder.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval 8 Oct 2023 huangmozhi9527/GMMFormer/src/Models/gmmformer/model.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers 18 Aug 2023 tdemin16/continual-layernorm-tuning/couple/utils.py 3dd88ba90d737da4 ran Apache-2.0 (permissive)
Knowing Where to Focus: Event-aware Transformer for Video Grounding 14 Aug 2023 jinhyunj/eatr/models/text_encoder.py 1c17153fb5488283 ran · honoured contract fingerprinted MIT (permissive)
UniVTG: Towards Unified Video-Language Temporal Grounding 31 Jul 2023 showlab/univtg/model/univtg.py 60df4d5a1eee1b92 ran · honoured contract fingerprinted MIT (permissive)
MomentDiff: Generative Video Moment Retrieval from Random to Real 6 Jul 2023 imccretrieval/momentdiff/momentdiff/text_encoder.py 1c17153fb5488283 ran · honoured contract fingerprinted no licence file found · pointer only
NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory 2 Jan 2023 srama2512/NaQ/ReLER/ms_cm/model.py 60df4d5a1eee1b92 ran · honoured contract fingerprinted MIT (permissive)
Selective Query-guided Debiasing for Video Corpus Moment Retrieval 17 Oct 2022 dbstjswo505/SQuiDNet/model/squidnet.py e47b0e22eeee3414 ran · honoured contract fingerprinted MIT (permissive)
ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022 1 Jul 2022 nnnnai/ego4d_nlq_2022_1st_place_solution/ms_cm/model.py 60df4d5a1eee1b92 ran · honoured contract fingerprinted MIT (permissive)
Improving Question Answering Performance Using Knowledge Distillation and Active Learning 26 Sep 2021 identical code first harvested elsewhere 9dc49f46edd7a69d ran · our draft was wrong licence of this copy not recorded
MTVR: Multilingual Moment Retrieval in Videos 30 Jul 2021 jayleicn/mTVRetrieval/baselines/mxml/model_xml_shared.py 1a5542dee1f0295c ran · honoured contract fingerprinted no licence file found · pointer only
Video Corpus Moment Retrieval with Contrastive Learning 13 May 2021 IsaacChanghau/ReLoCLNet/method_tvr/model.py 1c17153fb5488283 ran · honoured contract fingerprinted MIT (permissive)
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA 13 May 2020 identical code first harvested elsewhere 1c17153fb5488283 ran · honoured contract fingerprinted licence of this copy not recorded
Towards Robustifying NLI Models Against Lexical Dataset Biases 10 May 2020 owenzx/LexicalDebias-ACL2020/models/hex.py 1b1fb77042d2e192 ran · our draft was wrong fingerprinted MIT (permissive)
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training 1 May 2020 linjieli222/HERO/model/modeling_utils.py 247245b1fec40c1b unverified MIT recorded; this copy not marked cleared · pointer only
Span-based Localizing Network for Natural Language Video Localization 29 Apr 2020 IsaacChanghau/VSLNet/model/layers_t7.py 60df4d5a1eee1b92 ran · honoured contract fingerprinted MIT (permissive)
Span-based Localizing Network for Natural Language Video Localization 29 Apr 2020 IsaacChanghau/VSLNet/model/ops.py e168b7ed17766ce5 unverified MIT (permissive)
Relational Graph Attention Network for Aspect-based Sentiment Analysis 26 Apr 2020 shenwzh3/RGAT-ABSA/model.py bf59110e6f5ddc08 ran · honoured contract fingerprinted MIT (permissive)
TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval 24 Jan 2020 jayleicn/TVRetrieval/baselines/crossmodal_moment_localization/model_xml.py 1c17153fb5488283 ran · honoured contract fingerprinted MIT (permissive)
TVQA+: Spatio-Temporal Grounding for Video Question Answering 25 Apr 2019 jayleicn/TVQA-PLUS/model/model_utils.py 1c17153fb5488283 ran · honoured contract fingerprinted MIT (permissive)
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension 23 Apr 2018 mirbostani/QA-KD-AL/qa/model/qanet.py 9dc49f46edd7a69d ran · our draft was wrong MIT (permissive)
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension 23 Apr 2018 andy840314/QANet-pytorch-/models.py dea46bb8718e5def ran · our draft was wrong MIT (permissive)
arXiv:aaai_29726 shesshan/CEIB/model_utils.py bf59110e6f5ddc08 ran · honoured contract fingerprinted 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 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