12 of 14 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; 1 honoured the contract we drafted, 1 violated it and 9 have no contract verdict; 1 failure of our instrument; 2 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/2004.09144.json · badge: /api/ran/2004.09144.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 |
|---|---|---|
| mesnico/TERN | canonical (classifier label) classifier basis: census |
12 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| dcg_score | Ran ran on a synthesized input |
mesnico/TERN/evaluate_utils/dcg.py code served (permissive licence) · get_code("f6b4594fd6677dbe") 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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was 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.
|
| dot_sim | Ran ran on a synthesized input |
mesnico/TERN/models/loss.py code served (permissive licence) · get_code("6a49bab714ec6122") 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 Tensor, ndim 2, dtype family float, shape (2, 3) 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.
|
| encode_data | Ran ran on a synthesized input |
mesnico/TERN/evaluation.py code served (permissive licence) · get_code("0919fda55c323689") 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 tuple, ndim 3, 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.
|
| find_nhead | Ran ran on a synthesized input |
mesnico/TERN/models/visual.py code served (permissive licence) · get_code("6e963f0bd8b4ec0f") 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 int, ndim 0, dtype family int, 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.
|
| generate_square_subsequent_mask | Ran ran, violated the contract we drafted |
mesnico/TERN/models/utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from chend-vl/instructocr, is pointer only (licence: NONE) · get_code("894b253f35765276") 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 chend-vl/instructocr, 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_paths | Ran ran on a synthesized input |
mesnico/TERN/data.py code served (permissive licence) · get_code("ae1d8e2720a00989") 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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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.
|
| get_transform | Ran ran on a synthesized input |
mesnico/TERN/data.py code served (permissive licence) · get_code("e7518699cbc1bd68") 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 Compose. 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.
|
| l2norm | Ran ran; our contract draft was wrong, not the code |
mesnico/TERN/models/utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from Maryeon/asen, is pointer only (licence: NONE) · get_code("f92e514b398e75d8") 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 Maryeon/asen, 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. |
| my_collate | Ran ran on a synthesized input |
mesnico/TERN/evaluate_utils/compute_relevance.py code served (permissive licence) · get_code("d9047caaedf4aadb") 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. 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.
|
| my_lcs | Ran ran, honoured the contract we drafted |
mesnico/TERN/evaluate_utils/rouge.py code served (permissive licence) · get_code("8e177567218199c4") 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 int, ndim 0, dtype family int, 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.
|
| order_sim | Ran ran on a synthesized input |
mesnico/TERN/models/loss.py code served (permissive licence) · get_code("da16023b8239c604") 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 Tensor, ndim 2, dtype family float, shape (2, 3) 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.
|
| ranking_precision_score | Ran ran on a synthesized input |
mesnico/TERN/evaluate_utils/dcg.py code served (permissive licence) · get_code("8183b31354ef5eef") 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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was 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.
|
| EncoderText | Not yet run unverified (harvested, no recorded run) |
mesnico/TERN/models/text.py code served (permissive licence) · get_code("ef1f72eefcd0fcda") How it ranno invocation recorded. |
| average_precision_score | Not yet run unverified (harvested, no recorded run) |
mesnico/TERN/evaluate_utils/dcg.py code served (permissive licence) · get_code("c9ccc8160ca8229a") How it ranno invocation recorded. |
Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 11 later) and 3 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 |
|---|---|---|---|
| generate_square_subsequent_mask | 8 other papers 8 later · 1 only as an assembly brick |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
2107.03377 (2021-07) Long Short-Term Transformer for Online Action Detection 2109.10852 (2021-09) Pix2seq: A Language Modeling Framework for Object Detection and 5 more not named here |
| my_lcs | 7 other papers 3 dated earlier, 4 later |
1503.01817 (2015-03) YFCC100M: The New Data in Multimedia Research |
1608.00272 (2016-08) Modeling Context in Referring Expressions 1802.06842 (2018-02) Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types and 4 more not named here |
| order_sim | 7 other papers 1 dated earlier, 6 later |
1809.06181 (2018-09) Dual Encoding for Zero-Example Video Retrieval |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders 2104.00650 (2021-04) Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval and 4 more not named here |
| l2norm | 6 other papers 3 dated earlier, 3 later |
1707.05612 (2017-07) VSE++: Improving Visual-Semantic Embeddings with Hard Negatives |
1809.06181 (2018-09) Dual Encoding for Zero-Example Video Retrieval 2002.02814 (2020-02) Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network and 3 more not named here |
| dot_sim | 3 other papers 3 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
2203.09138 (2022-03) MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering 2306.08789 (2023-06) Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training |
| find_nhead | 2 other papers 2 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
2306.08789 (2023-06) Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training |
| get_transform | 2 other papers 2 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
2306.08789 (2023-06) Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training |
| my_collate | 2 other papers 2 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
2306.08789 (2023-06) Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training |
| average_precision_score | 1 other paper 1 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
|
| dcg_score | 1 other paper 1 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
|
| ranking_precision_score | 1 other paper 1 later |
2008.05231 (2020-08) Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders |
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.
Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual and textual features needed for later indexing steps in large-scale retrieval systems. In this regard, we introduce the Transformer Encoder Reasoning Network (TERN), an architecture built upon one of the modern relationship-aware self-attentive architectures, the Transformer Encoder (TE). This architecture is able to separately reason on the two different modalities and to enforce a final common abstract concept space by sharing the weights of the deeper transformer layers. Thanks to this design, the implemented network is able to produce compact and very rich visual and textual features available for the successive indexing step. Experiments are conducted on the MS-COCO dataset, and we evaluate the results using a discounted cumulative gain metric with relevance computed exploiting caption similarities, in order to assess possibly non-exact but relevant search results. We demonstrate that on this metric we are able to achieve state-of-the-art results in the image retrieval task. Our code is freely available at https://github.com/mesnico/TERN.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.09144")
get_code_for_paper("2004.09144")
have("2004.09144")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2004.09144.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2004.09144)
Connect an agent — have() is free.