{"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/phantomwiki-on-demand-datasets-for-reasoning","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","arxiv_id":"2502.20377","date":"2025-02-27","proceeding":null,"authors":["Albert Gong","Kamilė Stankevičiūtė","Chao Wan","Anmol Kabra","Raphael Thesmar","Johann Lee","Julius Klenke","Carla P. Gomes","Kilian Q. Weinberger"],"abstract":"High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a permanent solution as they are prone to data leakage and inflated performance results. To address these challenges, we propose PhantomWiki: a pipeline to generate unique, factually consistent document corpora with diverse question-answer pairs. Unlike prior work, PhantomWiki is neither a fixed dataset, nor is it based on any existing data. Instead, a new PhantomWiki instance is generated on demand for each evaluation. We vary the question difficulty and corpus size to disentangle reasoning and retrieval capabilities respectively, and find that PhantomWiki datasets are surprisingly challenging for frontier LLMs. Thus, we contribute a scalable and data leakage-resistant framework for disentangled evaluation of reasoning, retrieval, and tool-use abilities. Our code is available at https://github.com/kilian-group/phantom-wiki.","url_abs":"https://arxiv.org/abs/2502.20377v1","url_pdf":"https://arxiv.org/pdf/2502.20377v1.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":"phantomwiki-on-demand-datasets-for-reasoning","repo_url":"https://github.com/kilian-group/phantom-wiki","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.20377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20377"}},"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":"deterministic:regex_extraction","url":"https://github.com/kilian-group/phantom-wiki","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/RUC-NLPIR/FlashRAG","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"f413f9118e5c25da","entry":"add_to_atom_assignments","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/facts/sample.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/facts/sample.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f413f9118e5c25da"}},{"code_sha256_prefix":"abb7ef6c5bbc6b74","entry":"generate_templates","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/facts/templates.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/facts/templates.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abb7ef6c5bbc6b74"}},{"code_sha256_prefix":"31a9052f33816a22","entry":"is_aggregation_question","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/facts/templates.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/facts/templates.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31a9052f33816a22"}},{"code_sha256_prefix":"88156a49c66a34b5","entry":"match_placeholder_brackets","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/utils/parsing.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/utils/parsing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88156a49c66a34b5"}},{"code_sha256_prefix":"ff149cd0b161a556","entry":"match_placeholders","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/utils/parsing.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/utils/parsing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff149cd0b161a556"}},{"code_sha256_prefix":"14d5be7e74dcc4c5","entry":"parse_prolog_predicate","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/facts/question_difficulty.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/facts/question_difficulty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14d5be7e74dcc4c5"}},{"code_sha256_prefix":"b763629ebedda1f5","entry":"remove_brackets","repo":"kilian-group/phantom-wiki","repo_kind":"official","path":"src/phantom_wiki/utils/parsing.py","file_url":"https://github.com/kilian-group/phantom-wiki/blob/HEAD/src/phantom_wiki/utils/parsing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b763629ebedda1f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}