Ashish Sabharwal, Kyle Richardson, Reut Tsarfaty, Dafna Shahaf, Ronen Tamari, Oren Sultan
3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 3 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/2211.07950.json · badge: /api/ran/2211.07950.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 |
|---|---|---|
| NicolasAG/SGinPG | community Papers with Code archive |
2 ran · 3 no recorded run |
| copy not recorded | community not in the paper's declared repositories |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| AdaptiveInput | Ran ran on a synthesized input · constructed an object; no result was computed |
NicolasAG/SGinPG/src/model.py code served (permissive licence) · get_code("97cbbe490fe403ca") 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 an instance of its own class, AdaptiveInput: the run constructed the object and did not call it, so no result was computed. 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.
|
| TransformerLMLayer | Ran ran on a synthesized input · constructed an object; no result was computed |
NicolasAG/SGinPG/src/model.py code served (permissive licence) · get_code("ec9a64156f401068") 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 an instance of its own class, TransformerLMLayer: the run constructed the object and did not call it, so no result was computed. 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.
|
| gelu | Ran ran; our contract draft was wrong, not the code |
this paper's copy was not recorded; identical code first harvested from NicolasAG/SGinPG pointer only · get_code("a43d18e9c8836542") How it ranThe body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. |
| MultiheadAttention | Not yet run unverified (harvested, no recorded run) |
NicolasAG/SGinPG/src/model.py code served (permissive licence) · get_code("0b4cce6121085c3c") How it ranno invocation recorded. |
| TransformerLM | Not yet run unverified (harvested, no recorded run) |
NicolasAG/SGinPG/src/model.py code served (permissive licence) · get_code("fdbc987ebb0c5144") How it ranno invocation recorded. |
| create_sinusoidal_embeddings | Not yet run unverified (harvested, no recorded run) |
NicolasAG/SGinPG/src/model.py code served (permissive licence) · get_code("4bf26c42f90041a4") How it ranno invocation recorded. |
Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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 |
|---|---|---|---|
| create_sinusoidal_embeddings brick of this paper's assembly: helper |
2 other papers 1 dated earlier, 1 later · 1 only as an assembly brick |
1911.02116 (2019-11) Unsupervised Cross-lingual Representation Learning at Scale |
2306.11641 (2023-06) SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets |
| gelu brick of this paper's assembly: helper |
1 other paper 1 dated earlier |
2009.14786 (2020-09) Measuring Systematic Generalization in Neural Proof Generation with Transformers |
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.
Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text encoder and data marked with intermediate states (breakpoints) along with corresponding textual queries viewed as true/false propositions (i.e., the candidate beliefs of a model, consisting of information changing through time) our approach trains models in an efficient and end-to-end fashion to build intermediate representations that facilitate teaching and direct querying of beliefs at arbitrary points alongside solving other end tasks. To show the benefit of our approach, we experiment with a diverse set of NLU tasks including relational reasoning on CLUTRR and narrative understanding on bAbI. Using novel belief prediction tasks for both tasks, we show the benefit of our main breakpoint transformer, based on T5, over conventional representation learning approaches in terms of processing efficiency, prediction accuracy and prediction consistency, all with minimal to no effect on corresponding QA endtasks. To show the feasibility of incorporating our belief tracker into more complex reasoning pipelines, we also obtain SOTA performance on the three-tiered reasoning challenge for the TRIP benchmark (around 23-32% absolute improvement on Tasks 2-3). 1 * Work begun during an internship at the Allen Institute. † Equal contribution.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.07950")
get_code_for_paper("2211.07950")
have("2211.07950")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2211.07950.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2211.07950)
Connect an agent — have() is free.