SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.13223 · NeurIPS · 2021

Identifying and Benchmarking Natural Out-of-Context Prediction Problems

Richard Zemel, David Madras

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
dmadras/nooch canonical 10 of 12
FunctionStatusWhere it lives
auc Ran dmadras/nooch/src/nooch.py
code served (permissive licence) · get_code("fc57d2f52876c2cc")
create_cocostuff_category_maps Ran dmadras/nooch/src/attr_functions.py
code served (permissive licence) · get_code("260bbff2b621dfd5")
define_labels Ran dmadras/nooch/src/attr_functions.py
code served (permissive licence) · get_code("89fca942f26988da")
device Ran dmadras/nooch/src/utils/utils.py
code served (permissive licence) · get_code("2ae3d74510d82d77")
evaluate Ran dmadras/nooch/src/nooch.py
code served (permissive licence) · get_code("773a53ce9d82db41")
gong Ran dmadras/nooch/src/utils/utils.py
code served (permissive licence) · get_code("75cb70ed73e3ccbd")
init_model Ran dmadras/nooch/src/utils/utils.py
code served (permissive licence) · get_code("8369e57e3ee67024")
load_cocostuff_category_maps Ran dmadras/nooch/src/attr_functions.py
code served (permissive licence) · get_code("cfb4459c28de8af3")
merge_cocostuff_jsons Ran dmadras/nooch/src/utils/cocostuff_loading_utils.py
code served (permissive licence) · get_code("ce22cca93ae61f2c")
nll Ran dmadras/nooch/src/nooch.py
code served (permissive licence) · get_code("b246bd5672f4ff91")
load_cocostuff Not yet run dmadras/nooch/src/utils/cocostuff_loading_utils.py
code served (permissive licence) · get_code("48e5e80e1ebe503a")
prepare_cocostuff_minibatching Not yet run dmadras/nooch/src/utils/cocostuff_loading_utils.py
code served (permissive licence) · get_code("07c4b71349f1cafd")

Repositories linked to this paper

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

Abstract

Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of making reliable predictions on uncommon or unusual inputs or subgroups of the training distribution. To this end, a number of benchmarks for measuring OOC performance have recently been introduced. In this work, we introduce a framework unifying the literature on OOC performance measurement, and demonstrate how rich auxiliary information can be leveraged to identify candidate sets of OOC examples in existing datasets. We present NOOCH: a suite of naturallyoccurring "challenge sets", and show how varying notions of context can be used to probe specific OOC failure modes. Experimentally, we explore the tradeoffs between various learning approaches on these challenge sets and demonstrate how the choices made in designing OOC benchmarks can yield varying conclusions.

For agents

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

get_harvested_code_for_paper("2110.13223")
get_code_for_paper("2110.13223")
have("2110.13223")

Connect an agent — have() is free.