15 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 8 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2211.09623.json · badge: /api/ran/2211.09623.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| leaplabthu/cross-modal-adapter | canonical (classifier label) classifier basis not recorded on the link |
15 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| all_gather | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/comm.py code served (permissive licence) · get_code("d741eb912b24880a") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| cached_path | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/modules/file_utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("349d780dd4a89a37") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sejong-rcv/TAME, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| check_attr | Ran ran, violated the contract we drafted |
leaplabthu/cross-modal-adapter/modules/modeling_jointvt_upshare_adapter.py code served (permissive licence) · get_code("47c2715feba5fd6b") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| compute_metrics | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/metrics.py code served (permissive licence) · get_code("f45b80d057798fed") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| filename_to_url | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/modules/file_utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("db0ac56aaf6e35e6") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sejong-rcv/TAME, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| get_cosine_schedule_with_warmup | Ran ran on a synthesized input |
leaplabthu/cross-modal-adapter/modules/optimization_xpool.py code served (permissive licence) · get_code("28936c41e64792bd") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned LambdaLR. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_linear_schedule_with_warmup | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/modules/optimization_xpool.py code served (permissive licence) · get_code("afba2c06a42074fe") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned LambdaLR. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| reduce_dict | Ran ran, violated the contract we drafted |
leaplabthu/cross-modal-adapter/comm.py code served (permissive licence) · get_code("2a3280757ce5a198") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| tensor_text_to_video_metrics | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
leaplabthu/cross-modal-adapter/metrics.py code served (permissive licence) · get_code("66bf2e9b33bd27dd") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| tensor_video_to_text_sim | Ran ran, honoured the contract we drafted |
leaplabthu/cross-modal-adapter/metrics.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("b6f9f3930836fe3f") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sejong-rcv/TAME, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| update_attr | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/modules/modeling_jointvt_upshare_adapter.py code served (permissive licence) · get_code("d34a2226d2cf142e") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned TargetConfig. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| url_to_filename | Ran ran; our contract draft was wrong, not the code |
leaplabthu/cross-modal-adapter/modules/file_utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from lonePatient/ERNIE-text-classification-pytorch, is pointer only (licence: NONE) · get_code("af64ec220e8bcdbc") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lonePatient/ERNIE-text-classification-pytorch, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| warmup_constant | Ran ran, honoured the contract we drafted |
leaplabthu/cross-modal-adapter/modules/optimization.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("59e4e730a9dc5dc6") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sejong-rcv/TAME, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| warmup_cosine | Ran ran, honoured the contract we drafted |
leaplabthu/cross-modal-adapter/modules/optimization.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("20b3d25ba1b796e5") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sejong-rcv/TAME, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| warmup_linear | Ran ran, honoured the contract we drafted |
leaplabthu/cross-modal-adapter/modules/optimization.py code served (permissive licence) · get_code("e0960afdb0d64aa7") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 15 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 0 the same month, 14 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| warmup_constant | 28 other papers 19 dated earlier, 8 later, 1 same year, order not determinable |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1903.09588 (2019-03) Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence 1906.01698 (2019-06) Open Sesame: Getting Inside BERT's Linguistic Knowledge and 25 more not named here |
| get_linear_schedule_with_warmup | 21 other papers 5 dated earlier, 16 later |
2004.10964 (2020-04) Don't Stop Pretraining: Adapt Language Models to Domains and Tasks |
2011.07430 (2020-11) Audio-Visual Event Recognition through the lens of Adversary 2109.04912 (2021-09) ReasonBERT: Pre-trained to Reason with Distant Supervision and 18 more not named here |
| url_to_filename | 20 other papers 10 dated earlier, 10 later · 3 only as an assembly brick |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 1906.01698 (2019-06) Open Sesame: Getting Inside BERT's Linguistic Knowledge and 17 more not named here |
| cached_path | 17 other papers 8 dated earlier, 9 later · 3 only as an assembly brick |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 1906.01698 (2019-06) Open Sesame: Getting Inside BERT's Linguistic Knowledge and 14 more not named here |
| reduce_dict | 15 other papers 5 dated earlier, 9 later, 1 same year, order not determinable |
2003.04030 (2020-03) Learning Delicate Local Representations for Multi-Person Pose Estimation |
2004.01946 (2020-04) Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild 2108.02833 (2021-08) Elaborative Rehearsal for Zero-shot Action Recognition and 12 more not named here |
| warmup_linear | 14 other papers 7 dated earlier, 7 later |
1908.09355 (2019-08) Patient Knowledge Distillation for BERT Model Compression |
1909.00126 (2019-09) A Logic-Driven Framework for Consistency of Neural Models 2021.emnlp-main.518 (2021 (year only)) NDH-FULL: Learning and Evaluating Navigational Agents on Full-Length Dialogue and 11 more not named here |
| filename_to_url | 13 other papers 5 dated earlier, 8 later |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1906.01698 (2019-06) Open Sesame: Getting Inside BERT's Linguistic Knowledge 1909.11059 (2019-09) Unified Vision-Language Pre-Training for Image Captioning and VQA and 10 more not named here |
| check_attr | 9 other papers 2 dated earlier, 7 later |
2104.08860 (2021-04) CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval |
2204.02874 (2022-04) EclipSE: Efficient Long-range Video Retrieval using Sight and Sound 2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? and 6 more not named here |
| update_attr | 9 other papers 2 dated earlier, 7 later |
2104.08860 (2021-04) CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval |
2204.02874 (2022-04) EclipSE: Efficient Long-range Video Retrieval using Sight and Sound 2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? and 6 more not named here |
| warmup_cosine | 8 other papers 2 dated earlier, 6 later |
2110.00855 (2021-10) SurvTRACE: Transformers for Survival Analysis with Competing Events |
2203.07111 (2022-03) Disentangled Representation Learning for Text-Video Retrieval 2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? and 5 more not named here |
| all_gather | 7 other papers 4 dated earlier, 3 later |
2004.01946 (2020-04) Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild |
2007.10985 (2020-07) PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding 2104.10011 (2021-04) Perceptual Loss for Robust Unsupervised Homography Estimation and 4 more not named here |
| tensor_video_to_text_sim | 7 other papers 1 dated earlier, 6 later |
2204.02874 (2022-04) EclipSE: Efficient Long-range Video Retrieval using Sight and Sound |
2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? 2308.11551 (2023-08) Multi-event Video-Text Retrieval and 4 more not named here |
| tensor_text_to_video_metrics | 6 other papers 1 dated earlier, 5 later |
2204.02874 (2022-04) EclipSE: Efficient Long-range Video Retrieval using Sight and Sound |
2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? 2308.11551 (2023-08) Multi-event Video-Text Retrieval and 3 more not named here |
| get_cosine_schedule_with_warmup | 5 other papers 5 dated earlier |
2007.06028 (2020-07) TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech |
2010.14150 (2020-10) FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention 2105.01051 (2021-05) SUPERB: Speech processing Universal PERformance Benchmark and 2 more not named here |
| compute_metrics | 4 other papers 4 later |
2301.00184 (2023-01) Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? |
2309.10091 (2023-09) Unified Coarse-to-Fine Alignment for Video-Text Retrieval 2309.17093 (2023-09) Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval and 1 more not named here |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval tasks. However, as pre-trained models are scaling up, fully fine-tuning them on donwstream retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient transfer learning. Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers. However, there are two notable differences. First, our method is designed for the multi-modal domain. Secondly, it allows encoder-level implicit cross-modal interactions between vision and language encoders. Although surprisingly simple, our approach has three notable benefits: (1) reduces the vast majority of fine-tuned parameters, (2) saves training time, and (3) allows all the pre-trained parameters to be fixed, enabling the pre-trained model to be shared across datasets. Extensive experiments demonstrate that, without bells and whistles, our approach outperforms adapter-based methods on image-text retrieval datasets (MSCOCO, Flickr30K) and video-text retrieval datasets (MSR-VTT, DiDeMo, and ActivityNet).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.09623")
get_code_for_paper("2211.09623")
have("2211.09623")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2211.09623.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2211.09623)
Connect an agent — have() is free.