8 of 9 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 1 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/2312.06173.json · badge: /api/ran/2312.06173.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 |
|---|---|---|
| tanganke/subspace_fusion | canonical (classifier label) classifier basis: census |
8 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_block_wise_weights_by_block_size | Ran ran; our contract draft was wrong, not the code |
tanganke/subspace_fusion/src/block_wise_fusion.py pointer only (licence: NONE) · get_code("31c0be98853385be") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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_block_wise_weights_by_partitions | Ran ran, honoured the contract we drafted |
tanganke/subspace_fusion/src/block_wise_fusion.py pointer only (licence: NONE) · get_code("835005bb4d36b7aa") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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_layer_wise_weights | Ran ran, honoured the contract we drafted |
tanganke/subspace_fusion/src/layer_wise_fusion.py pointer only (licence: NONE) · get_code("65c48146354a3100") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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_task_wise_weights | Ran ran, honoured the contract we drafted |
tanganke/subspace_fusion/src/task_wise_fusion.py pointer only (licence: NONE) · get_code("95fa453992ae3b46") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. |
| gumbel_softmax_sample | Ran ran; our contract draft was wrong, not the code |
tanganke/subspace_fusion/src/gumbel.py pointer only (licence: NONE) · get_code("4f0159d8d299aec4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. |
| make_functional | Ran ran; our contract draft was wrong, not the code |
tanganke/subspace_fusion/src/adamerging.py pointer only (licence: NONE) · get_code("64e4ae217b73cdfa") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. |
| sample_gumbel | Ran ran; our contract draft was wrong, not the code |
tanganke/subspace_fusion/src/gumbel.py pointer only (licence: NONE) · get_code("00e884bd2fc5d361") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. |
| softmax_entropy | Ran ran; our contract draft was wrong, not the code |
tanganke/subspace_fusion/src/adamerging.py pointer only (licence: NONE) · get_code("d3c4cec689591885") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. |
| gumbel_softmax | Not yet run unverified (harvested, no recorded run) |
tanganke/subspace_fusion/src/gumbel.py pointer only (licence: NONE) · get_code("4862418d811e8034") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, tanganke/subspace_fusion 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. No invocation recorded. |
Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.
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.
Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks. Recent research, exemplified by task arithmetic, highlights that this multi-task model can be derived through arithmetic operations on task vectors. Nevertheless, current merging techniques frequently resolve potential conflicts among parameters from task-specific models by evaluating individual attributes, such as the parameters' magnitude or sign, overlooking their collective impact on the overall functionality of the model. In this work, we propose the CONtinuous relaxation of disCRETE (Concrete) subspace learning method to identify a common low-dimensional subspace and utilize its shared information to track the interference problem without sacrificing much performance. Specifically, we model the problem as a bi-level optimization problem and introduce a meta-learning framework to find the Concrete subspace mask through gradient-based techniques. At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model. We conduct extensive experiments on both vision domain and language domain, and the results demonstrate the effectiveness of our method. The code is available at https://github.com/tanganke/subspace_fusion
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.06173")
get_code_for_paper("2312.06173")
have("2312.06173")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2312.06173.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2312.06173)
Connect an agent — have() is free.