{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/identifying-and-benchmarking-natural-out-of","title":"Identifying and Benchmarking Natural Out-of-Context Prediction Problems","arxiv_id":"2110.13223","date":"2021-10-25","proceeding":"NeurIPS 2021 12","authors":["David Madras","Richard Zemel"],"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 naturally-occurring \"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.","url_abs":"https://arxiv.org/abs/2110.13223v1","url_pdf":"https://arxiv.org/pdf/2110.13223v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"identifying-and-benchmarking-natural-out-of","repo_url":"https://github.com/dmadras/nooch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.13223","atlas_url":"https://app.syntology.ai/?focus=2110.13223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13223"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/dmadras/nooch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nightrome/cocostuff","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fc57d2f52876c2cc","entry":"auc","repo":"dmadras/nooch","repo_kind":"official","path":"src/nooch.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/nooch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fc57d2f52876c2cc"}},{"code_sha256_prefix":"260bbff2b621dfd5","entry":"create_cocostuff_category_maps","repo":"dmadras/nooch","repo_kind":"official","path":"src/attr_functions.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/attr_functions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"260bbff2b621dfd5"}},{"code_sha256_prefix":"89fca942f26988da","entry":"define_labels","repo":"dmadras/nooch","repo_kind":"official","path":"src/attr_functions.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/attr_functions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"89fca942f26988da"}},{"code_sha256_prefix":"2ae3d74510d82d77","entry":"device","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2ae3d74510d82d77"}},{"code_sha256_prefix":"773a53ce9d82db41","entry":"evaluate","repo":"dmadras/nooch","repo_kind":"official","path":"src/nooch.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/nooch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"773a53ce9d82db41"}},{"code_sha256_prefix":"75cb70ed73e3ccbd","entry":"gong","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"75cb70ed73e3ccbd"}},{"code_sha256_prefix":"8369e57e3ee67024","entry":"init_model","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8369e57e3ee67024"}},{"code_sha256_prefix":"cfb4459c28de8af3","entry":"load_cocostuff_category_maps","repo":"dmadras/nooch","repo_kind":"official","path":"src/attr_functions.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/attr_functions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cfb4459c28de8af3"}},{"code_sha256_prefix":"ce22cca93ae61f2c","entry":"merge_cocostuff_jsons","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/cocostuff_loading_utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/cocostuff_loading_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ce22cca93ae61f2c"}},{"code_sha256_prefix":"b246bd5672f4ff91","entry":"nll","repo":"dmadras/nooch","repo_kind":"official","path":"src/nooch.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/nooch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b246bd5672f4ff91"}},{"code_sha256_prefix":"48e5e80e1ebe503a","entry":"load_cocostuff","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/cocostuff_loading_utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/cocostuff_loading_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"48e5e80e1ebe503a"}},{"code_sha256_prefix":"07c4b71349f1cafd","entry":"prepare_cocostuff_minibatching","repo":"dmadras/nooch","repo_kind":"official","path":"src/utils/cocostuff_loading_utils.py","file_url":"https://github.com/dmadras/nooch/blob/HEAD/src/utils/cocostuff_loading_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"07c4b71349f1cafd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}