sigmoid_ce_loss
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
sigmoid_ce_loss appears in the code Syntology harvested for 70 papers, as 17 distinct code bodies found in 72 places (a place is one code body under one paper). Of the 70 papers, 70 with a sample that ran: 7 with a run with no instrument failure, 63 where every run was a failure of Syntology's instrument. 16 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 sigmoid_ce_loss 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 17 distinct code bodies named sigmoid_ce_loss: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 0 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:
Licence is a property of each copy, so it is counted per place: 18 of the 72 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
70 papers shown of 70, newest first; 72 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 3 papers added by Syntology; 8 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.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering added by Syntology | 2026-03 (from id) | VILA-Lab/PIXAR/model/PIXAR.py b9e60254a36a3fb8 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| UGround: Towards Unified Visual Grounding with Unrolled Transformers added by Syntology | 2025-10 (from id) | rui-qian/UGround/model/UGround.py 3face96ac23ae5bc |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| UGround: Towards Unified Visual Grounding with Unrolled Transformers added by Syntology | 2025-10 (from id) | rui-qian/UGround/model/GSVA.py 13c0bb91f8009d9c |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation added by Syntology | 2025-08 (from id) | JiahuaDong/HVPL/hvpl/modeling/vita_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation | 17 Jul 2025 | HuangShiqi128/SCORE/score/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion | 11 Jul 2025 | Enyu-Liu/DISC/maskdino/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning | 27 Jun 2025 | geshang777/FOCUS/focus/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Towards In-the-wild 3D Plane Reconstruction from a Single Image | 3 Jun 2025 | jcliu0428/ZeroPlane/ZeroPlane/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing | 23 Jan 2025 | mbzuai-oryx/geopixel/model/geopixel.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model | 5 Dec 2024 | identical code first harvested elsewhere a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation | 4 Dec 2024 | ruohaoguo/avis/avism/modeling/avism_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| A Simple Image Segmentation Framework via In-Context Examples | 7 Oct 2024 | aim-uofa/SINE/sine/model/criterion.py 7130af6c2979dba8 |
ran fingerprinted | licence not identified · pointer only |
| One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos | 29 Sep 2024 | showlab/videolisa/model/VideoLISA.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects | 23 Jul 2024 | ProvenceStar/PartGLEE/projects/PartGLEE/partglee/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| VISA: Reasoning Video Object Segmentation via Large Language Models | 16 Jul 2024 | cilinyan/VISA/model/VISA.py bf7e8883d6ce76b4 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Part2Object: Hierarchical Unsupervised 3D Instance Segmentation | 14 Jul 2024 | chengshiest/part2object/models/criterion.py c0938fc9bc7ebddd |
ran fingerprinted | MIT (permissive) |
| EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model | 28 Jun 2024 | identical code first harvested elsewhere a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Open-Vocabulary Semantic Segmentation with Image Embedding Balancing | 14 Jun 2024 | slonetime/EBSeg/ebseg/model/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Instruction-Guided Visual Masking | 30 May 2024 | 2toinf/ivm/model/IVM.py 1033e9116b1e2573 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Grounded 3D-LLM with Referent Tokens | 16 May 2024 | OpenRobotLab/Grounded_3D-LLM/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference | 9 May 2024 | lzhxmu/vtw/LISA-VTW/LISA.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation | 23 Apr 2024 | abhishekaich27/proscale-pytorch/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| LaSagnA: Language-based Segmentation Assistant for Complex Queries | 12 Apr 2024 | congvvc/lasagna/model/LaSagnA.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| CoReS: Orchestrating the Dance of Reasoning and Segmentation | 8 Apr 2024 | identical code first harvested elsewhere a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation | 4 Apr 2024 | heshuting555/DsHmp/dshmp/modeling/vita_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception | 5 Mar 2024 | jwh97nn/AnyRef/model/anyref.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| PEM: Prototype-based Efficient MaskFormer for Image Segmentation | 29 Feb 2024 | niccolocavagnero/pem/pem/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| UniVS: Unified and Universal Video Segmentation with Prompts as Queries | 28 Feb 2024 | minghanli/univs/univs/modeling/video_criterion.py 450b62615caa903a |
ran fingerprinted | no licence file found · pointer only |
| UniVS: Unified and Universal Video Segmentation with Prompts as Queries | 28 Feb 2024 | minghanli/univs/univs/modeling/video_criterion_prompt.py 46b849406325dd41 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Symbol as Points: Panoptic Symbol Spotting via Point-based Representation | 19 Jan 2024 | nicehuster/sympoint/svgnet/model/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Supervised Fine-tuning in turn Improves Visual Foundation Models | 18 Jan 2024 | tencentarc/visft/mmf/models/visft/segment_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| ODIN: A Single Model for 2D and 3D Segmentation | 4 Jan 2024 | ayushjain1144/odin/odin/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model | 28 Dec 2023 | dvlab-research/lisa/model/LISA.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces | 25 Dec 2023 | foundationvision/uniref/projects/UniRef/uniref/models/uniref_sam.py e28a878991e1e696 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| GSVA: Generalized Segmentation via Multimodal Large Language Models | 15 Dec 2023 | leaplabthu/gsva/model/losses.py 13c0bb91f8009d9c |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Collaborating Foundation Models for Domain Generalized Semantic Segmentation | 15 Dec 2023 | yasserben/clouds/clouds/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| General Object Foundation Model for Images and Videos at Scale | 14 Dec 2023 | FoundationVision/GLEE/projects/GLEE/glee/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation | 11 Dec 2023 | rkzheng99/TMT-VIS/tmt/modeling/tmt_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Open-Vocabulary Segmentation with Semantic-Assisted Calibration | 7 Dec 2023 | workforai/scan/scan/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| PixelLM: Pixel Reasoning with Large Multimodal Model | 4 Dec 2023 | maverickren/pixellm/model/PixelLM.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Mask Propagation for Efficient Video Semantic Segmentation | 29 Oct 2023 | ziplab/MPVSS/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Learning Mask-aware CLIP Representations for Zero-Shot Segmentation | 30 Sep 2023 | jiaosiyu1999/MAFT-Plus/maft/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| 3D Indoor Instance Segmentation in an Open-World | 25 Sep 2023 | aminebdj/3D-OWIS/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Detect Everything with Few Examples | 22 Sep 2023 | mlzxy/devit/detectron2/modeling/meta_arch/devit_update.py 847c0c0c48d84c9e |
ran fingerprinted | MIT (permissive) |
| MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions | 16 Aug 2023 | henghuiding/MeViS/lmpm/modeling/vita_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning | 12 Aug 2023 | aim-uofa/segprompt/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | BSD-2-Clause (permissive) |
| Symphonize 3D Semantic Scene Completion with Contextual Instance Queries | 27 Jun 2023 | hustvl/symphonies/maskdino/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation | 19 Jun 2023 | heshuting555/PADing/PADing/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Segment Any Point Cloud Sequences by Distilling Vision Foundation Models | 15 Jun 2023 | IDEA-Research/OpenSeeD/openseed/modules/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation | 12 Jun 2023 | tacju/compositor/Compositor_Mask2Former/compositor/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| DFormer: Diffusion-guided Transformer for Universal Image Segmentation | 6 Jun 2023 | cp3wan/dformer/dformer/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation | 7 May 2023 | lab206/adaptiveclick/isegm/model/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Complementary Random Masking for RGB-Thermal Semantic Segmentation | 30 Mar 2023 | UkcheolShin/CRM_RGBTSeg/models/mask2former/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| You Only Segment Once: Towards Real-Time Panoptic Segmentation | 26 Mar 2023 | Darth-Kronos/YOSO_TensorRT/projects/YOSO/yoso/loss.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| BoxSnake: Polygonal Instance Segmentation with Box Supervision | 21 Mar 2023 | Yangr116/BoxSnake/modeling/box_supervisor/box_supervisor.py 18da425e8ba54fbd |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | Apache-2.0 (permissive) |
| FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation | 15 Mar 2023 | junjiehe96/fastinst/fastinst/modeling/criterion.py a2b19dbf3e1969b9 |
ran fingerprinted | MIT (permissive) |
| Side Adapter Network for Open-Vocabulary Semantic Segmentation | 23 Feb 2023 | blumenstiel/SAN-MESS/san/model/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| OneFormer: One Transformer to Rule Universal Image Segmentation | 10 Nov 2022 | SHI-Labs/OneFormer/oneformer/modeling/criterion.py dc4a40c394479bd8 |
ran fingerprinted | MIT (permissive) |
| Mask3D: Mask Transformer for 3D Semantic Instance Segmentation | 6 Oct 2022 | jonasschult/mask3d/models/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| VITA: Video Instance Segmentation via Object Token Association | 9 Jun 2022 | sukjunhwang/vita/vita/modeling/vita_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation | 8 Mar 2022 | facebookresearch/Mask2Former/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection | 7 Mar 2022 | IDEACVR/MaskDINO/maskdino/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Mask2Former for Video Instance Segmentation | 20 Dec 2021 | nihalsid/mask2former/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Masked-attention Mask Transformer for Universal Image Segmentation | 2 Dec 2021 | DdeGeus/Mask2Former-IBS/mask2former/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| AAAI id aaai_27844 | retsuh-bqw/SRFormer-Text-Det/adet/modeling/srformer/matcher.py 641305cea54a6936 |
ran fingerprinted | Apache-2.0 (permissive) | |
| CVF open access id Zhou_LIRA_Reasoning_Reconstruction_via_Multimodal_Large_Language_Models_ICCV_2025_paper | zhen6618/LIRA/LIRA/models/LISA.py a9292f5d89194794 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) | |
| CVF open access id Zhang_Uni-3D_A_Universal_Model_for_Panoptic_3D_Scene_Reconstruction_ICCV_2023_paper | mlpc-ucsd/Uni-3D/uni_3d/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) | |
| CVF open access id Zhang_FreePoint_Unsupervised_Point_Cloud_Instance_Segmentation_CVPR_2024_paper | zzk273/FreePoint/models/criterion_freepoint.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | MIT (permissive) | |
| CVF open access id Xia_GSVA_Generalized_Segmentation_via_Multimodal_Large_Language_Models_CVPR_2024_paper | LeapLabTHU/GSVA/model/losses.py 13c0bb91f8009d9c |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) | |
| CVF open access id Qian_Reasoning_to_Attend_Try_to_Understand_How_SEG_Token_Works_CVPR_2025_paper | rui-qian/READ/model/READ.py 3face96ac23ae5bc |
ran · our draft was wrong fingerprinted | MIT (permissive) | |
| CVF open access id Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper | IDEA-Research/MaskDINO/maskdino/modeling/criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) | |
| CVF open access id Heo_A_Generalized_Framework_for_Video_Instance_Segmentation_CVPR_2023_paper | miranheo/GenVIS/genvis/modeling/genvis_criterion.py d0c61e8dba511aa3 |
ran · our draft was wrong 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