Peter Hase, Harry Xie, Mohit Bansal
1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures 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/2106.00786.json · badge: /api/ran/2106.00786.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 |
|---|---|---|
| peterbhase/explanationsearch | canonical (classifier label) classifier basis: classifier_2025 |
0 ran · 3 no recorded run |
| peterbhase/ExplanationSearch | marked official in Papers with Code Papers with Code archive |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| PLSExplainer | Ran ran on a synthesized input · constructed an object; no result was computed |
peterbhase/ExplanationSearch/explanation_methods_and_eval/src/models/parallel_local_search.py code served (permissive licence) · get_code("297c47761a4ab839") 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, PLSExplainer: 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.
|
| compute_counterfactual | Not yet run unverified (harvested, no recorded run) |
peterbhase/explanationsearch/OOD_analysis/compute_counterfactual.py code served (permissive licence) · get_code("b5f573fe9b7a4f5e") How it ranno invocation recorded. |
| get_masked_inputs | Not yet run unverified (harvested, no recorded run) |
peterbhase/explanationsearch/OOD_analysis/compute_counterfactual.py code served (permissive licence) · get_code("f26e2899dfb5e361") How it ranno invocation recorded. |
| random_mask | Not yet run unverified (harvested, no recorded run) |
peterbhase/explanationsearch/OOD_analysis/compute_counterfactual.py code served (permissive licence) · get_code("4f898c3ab836a9b9") How it ranno invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back. |
Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.
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.
Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. For example, in the standard Sufficiency metric, only the top-k most important tokens are kept. In this paper, we study several under-explored dimensions of FI explanations, providing conceptual and empirical improvements for this form of explanation. First, we advance a new argument for why it can be problematic to remove features from an input when creating or evaluating explanations: the fact that these counterfactual inputs are out-of-distribution (OOD) to models implies that the resulting explanations are socially misaligned. The crux of the problem is that the model prior and random weight initialization influence the explanations (and explanation metrics) in unintended ways. To resolve this issue, we propose a simple alteration to the model training process, which results in more socially aligned explanations and metrics. Second, we compare among five approaches for removing features from model inputs. We find that some methods produce more OOD counterfactuals than others, and we make recommendations for selecting a feature-replacement function. Finally, we introduce four search-based methods for identifying FI explanations and compare them to strong baselines, including LIME, Anchors, and Integrated Gradients. Through experiments with six diverse text classification datasets, we find that the only method that consistently outperforms random search is a Parallel Local Search (PLS) that we introduce. Improvements over the second best method are as large as 5.4 points for Sufficiency and 17 points for Comprehensiveness. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.00786")
get_code_for_paper("2106.00786")
have("2106.00786")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.00786.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.00786)
Connect an agent — have() is free.