Vitaly Shmatikov, Hannaneh Hajishirzi, Sewon Min, Junjie Yin, John Morris
5 of 6 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; 0 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; 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/2602.19020.json · badge: /api/ran/2602.19020.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 |
|---|---|---|
| oseyosey/MIA-RL | canonical (classifier label) classifier basis: census |
5 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| convert_pandas_to_native | Ran ran; our contract draft was wrong, not the code |
oseyosey/MIA-RL/adra/utils/plot/inspect_mia_data.py code served (permissive licence) · get_code("ae762b8aa066fee7") 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 dict. 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.
|
| extract_aurocs | Ran ran; our contract draft was wrong, not the code |
oseyosey/MIA-RL/adra/utils/extract_mia_aurocs.py code served (permissive licence) · get_code("6c2da8114920433e") 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 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.
|
| extract_mia_weights | Ran ran; our contract draft was wrong, not the code |
oseyosey/MIA-RL/adra/utils/plot/inspect_mia_data.py code served (permissive licence) · get_code("0234fa19d1b37973") 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. 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.
|
| format_results | Ran ran; our contract draft was wrong, not the code |
oseyosey/MIA-RL/adra/utils/format_mia_aurocs.py code served (permissive licence) · get_code("493d2de212395f45") 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 str. 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.
|
| load_aurocs | Ran ran; our contract draft was wrong, not the code |
oseyosey/MIA-RL/adra/utils/format_mia_aurocs.py code served (permissive licence) · get_code("7f9efa2d98d20202") 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 dict. 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.
|
| load_parquet_data | Not yet run unverified (harvested, no recorded run) |
oseyosey/MIA-RL/adra/utils/plot/inspect_mia_data.py code served (permissive licence) · get_code("e875b779bc4b40a7") 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, 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 6 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.
Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce Active Data Reconstruction Attack (ADRA), a family of MIA that actively induces a model to reconstruct a given text through training. We hypothesize that training data are more reconstructible than non-members, and the difference in their reconstructibility can be exploited for membership inference. Motivated by findings that reinforcement learning (RL) sharpens behaviors already encoded in weights, we leverage on-policy RL to actively elicit data reconstruction by finetuning a policy initialized from the target model. To effectively use RL for MIA, we design reconstruction metrics and contrastive rewards. The resulting algorithms, ADRA and its adaptive variant ADRA+, improve both reconstruction and detection given a pool of candidate data. Experiments show that our methods consistently outperform existing MIAs in detecting pre-training, posttraining, and distillation data, with an average improvement of 10.7% over the previous runner-up. In particular, ADRA+ improves over Min-K%++ by 18.8% on BookMIA for pre-training detection and by 7.6% on AIME for post-training detection.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.19020")
get_code_for_paper("2602.19020")
have("2602.19020")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.19020.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.19020)
Connect an agent — have() is free.