Ansong Ni, Pradeep Dasigi, Matt Gardner
3 of 3 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, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2103.12235.json · badge: /api/ran/2103.12235.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 |
|---|---|---|
| niansong1996/retrieval_marginalization | canonical (classifier label) classifier basis: census |
3 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| swish | Ran ran; our contract draft was wrong, not the code |
niansong1996/retrieval_marginalization/rranm_modules/neural_modules/numnet_utils.py code served (permissive licence) · get_code("0f786c407fb1ee4c") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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.
|
| gelu | Ran ran, honoured the contract we drafted |
niansong1996/retrieval_marginalization/rranm_modules/neural_modules/numnet_utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from rlqja1107/melt, is pointer only (licence: NONE) · get_code("56a9ab06b860b180") 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 rlqja1107/melt, 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_tryout_combinations | Ran ran on a synthesized input |
niansong1996/retrieval_marginalization/rranm_modules/neural_modules/joint_qa.py code served (permissive licence) · get_code("8f1849dbdeffc499") 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 2, dtype family int; 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.
|
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 1 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 |
|---|---|---|---|
| swish | 206 other papers 58 dated earlier, 4 the same month, 141 later, 3 same year, order not determinable · 44 only as an assembly brick |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1805.12114 (2018-05) Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models 1809.01357 (2018-09) Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference and 203 more not named here |
| gelu | 198 other papers 69 dated earlier, 2 the same month, 123 later, 4 same year, order not determinable · 32 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 1901.10125 (2019-01) Glyce: Glyph-vectors for Chinese Character Representations and 195 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.
Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled supporting evidence. However, when retrieving from large text corpora such as Wikipedia, the correct answer can often be obtained from multiple evidence candidates. Moreover, not all such candidates are labeled as positive during annotation, rendering the training signal weak and noisy. This problem is exacerbated when the questions are unanswerable or when the answers are Boolean, since the model cannot rely on lexical overlap to make a connection between the answer and supporting evidence. We develop a new parameterization of set-valued retrieval that handles unanswerable queries, and we show that marginalizing over this set during training allows a model to mitigate false negatives in supporting evidence annotations. We test our method on two multi-document QA datasets, IIRC and HotpotQA. On IIRC, we show that joint modeling with marginalization improves model performance by 5.5 F1 points and achieves a new state-of-the-art performance of 50.5 F1. We also show that retrieval marginalization results in 4.1 QA F1 improvement over a non-marginalized baseline on HotpotQA in the fullwiki setting. 1 * Majority of the work done as an intern at AI2.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.12235")
get_code_for_paper("2103.12235")
have("2103.12235")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.12235.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.12235)
Connect an agent — have() is free.