SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11729 · ICML · 2024

Prospector Heads: Generalized Feature Attribution for Large Models & Data

Christopher Ré, James Zou, Amir-Hossein Karimi, Alexander Derry, Russ Altman, Arjun Desai, Neel Guha, Gautam Machiraju, Parag Mallick

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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 0 have no contract verdict; 5 failures of our instrument; 4 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/2402.11729.json · badge: /api/ran/2402.11729.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.

RepositoryRoleRan
gmachiraju/k2 canonical (classifier label)
classifier basis: classifier_2025
6 ran · 4 no recorded run
FunctionStatusWhere it lives
construct_sprite Ran
ran; our contract draft was wrong, not the code
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("2fbbd3736d73afc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

convert_graph2arr Ran
ran; our contract draft was wrong, not the code
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("c21dcb7a74fed6c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

deserialize Ran
ran; our contract draft was wrong, not the code
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("4151128d19e2a9ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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_prospect_range Ran
ran, honoured the contract we drafted
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("be2dc6ef9bc23fe5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

set_graph_emb Ran
ran; our contract draft was wrong, not the code
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("bcb28698ac4fb0d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

visualize_cell_graph Ran
ran; our contract draft was wrong, not the code
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("c3ba13f40abe6ee1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

K2Model Not yet run
unverified (harvested, no recorded run)
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("bd9d46ed18fef7e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

dotdict Not yet run
unverified (harvested, no recorded run)
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("d147647e3fdc860d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

visualize_quantizedZ Not yet run
unverified (harvested, no recorded run)
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("714dab283815345e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

visualize_sprite Not yet run
unverified (harvested, no recorded run)
gmachiraju/k2/src/k2.py
pointer only (licence: NONE) · get_code("2fd8ef05fa8aa404")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gmachiraju/k2 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
dotdict
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
2001.00248 (2020-01)
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
2006.05467 (2020-06)
Pruning neural networks without any data by iteratively conserving synaptic flow

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanationbased attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.11729")
get_code_for_paper("2402.11729")
have("2402.11729")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.11729.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.11729.svg)](https://syntology.ai/paper/2402.11729)

Connect an agent — have() is free.