{"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/stereotyping-and-bias-in-the-flickr30k","title":"Stereotyping and Bias in the Flickr30K Dataset","arxiv_id":"1605.06083","date":"2016-05-19","proceeding":null,"authors":["Emiel van Miltenburg"],"abstract":"An untested assumption behind the crowdsourced descriptions of the images in\nthe Flickr30K dataset (Young et al., 2014) is that they \"focus only on the\ninformation that can be obtained from the image alone\" (Hodosh et al., 2013, p.\n859). This paper presents some evidence against this assumption, and provides a\nlist of biases and unwarranted inferences that can be found in the Flickr30K\ndataset. Finally, it considers methods to find examples of these, and discusses\nhow we should deal with stereotype-driven descriptions in future applications.","url_abs":"http://arxiv.org/abs/1605.06083v1","url_pdf":"http://arxiv.org/pdf/1605.06083v1.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":"stereotyping-and-bias-in-the-flickr30k","repo_url":"https://github.com/evanmiltenburg/Flickr30K-Image-Viewer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stereotyping-and-bias-in-the-flickr30k","repo_url":"https://github.com/evanmiltenburg/Flickr30k-clusters","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.06083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.06083"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/evanmiltenburg/Flickr30K-Image-Viewer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/evanmiltenburg/Flickr30k-clusters","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":2}},"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":"a112709fc73f0fa3","entry":"get_desc_and_link_counters","repo":"evanmiltenburg/Flickr30k-clusters","repo_kind":"official","path":"cluster_descriptions.py","file_url":"https://github.com/evanmiltenburg/Flickr30k-clusters/blob/HEAD/cluster_descriptions.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a112709fc73f0fa3"}},{"code_sha256_prefix":"cee74358a1a8f6c0","entry":"image_url","repo":"evanmiltenburg/Flickr30K-Image-Viewer","repo_kind":"official","path":"annotate_selection.py","file_url":"https://github.com/evanmiltenburg/Flickr30K-Image-Viewer/blob/HEAD/annotate_selection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cee74358a1a8f6c0"}},{"code_sha256_prefix":"ec9c88e2643bb6b9","entry":"url_to_id","repo":"evanmiltenburg/Flickr30K-Image-Viewer","repo_kind":"official","path":"annotate_selection.py","file_url":"https://github.com/evanmiltenburg/Flickr30K-Image-Viewer/blob/HEAD/annotate_selection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec9c88e2643bb6b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}