{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3VMURTCVC7RULVN45UBBVDG4TK","short_pith_number":"pith:3VMURTCV","schema_version":"1.0","canonical_sha256":"dd5948cc5517e345d5bced021a8cdc9ab855c8945cd449508be791172e1062e8","source":{"kind":"arxiv","id":"2111.15366","version":1},"attestation_state":"computed","paper":{"title":"AI and the Everything in the Whole Wide World Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alex Hanna, Amandalynne Paullada, Emily Denton, Emily M. Bender, Inioluwa Deborah Raji","submitted_at":"2021-11-26T19:39:34Z","abstract_excerpt":"There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and generalizable AI systems. State-of-the-art performance on these benchmarks is widely understood as indicative of progress towards these long-term goals. In this position paper, we explore the limits of such benchmarks in order to reveal the construct validity issues in their framing as the functionally \"general\" broad meas"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.15366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-26T19:39:34Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"012ba4f2e2078f1062a85f693f02b19e99adf63fccc2aa810145c3281e428352","abstract_canon_sha256":"5af46a8fcf38785ec266babe31d98ce2ece11d55a685605f4a7987444bbcf1f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:25.447525Z","signature_b64":"KBgEEIPGIq6gxIFOY9iPnh/XdgFBwpZvmwXShqs5FFGW+bVnQogc9uVuPw2t6/zb2y49g+MP085MDt18DfK3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd5948cc5517e345d5bced021a8cdc9ab855c8945cd449508be791172e1062e8","last_reissued_at":"2026-07-05T03:36:25.446051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:25.446051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI and the Everything in the Whole Wide World Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alex Hanna, Amandalynne Paullada, Emily Denton, Emily M. Bender, Inioluwa Deborah Raji","submitted_at":"2021-11-26T19:39:34Z","abstract_excerpt":"There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and generalizable AI systems. State-of-the-art performance on these benchmarks is widely understood as indicative of progress towards these long-term goals. In this position paper, we explore the limits of such benchmarks in order to reveal the construct validity issues in their framing as the functionally \"general\" broad meas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15366","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.15366/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.15366","created_at":"2026-07-05T03:36:25.446115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15366v1","created_at":"2026-07-05T03:36:25.446115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15366","created_at":"2026-07-05T03:36:25.446115+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VMURTCVC7RU","created_at":"2026-07-05T03:36:25.446115+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VMURTCVC7RULVN4","created_at":"2026-07-05T03:36:25.446115+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VMURTCV","created_at":"2026-07-05T03:36:25.446115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19704","citing_title":"Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01254","citing_title":"The Benchmark Ceiling: Human Judgment, Evaluation Scarcity, and the Political Economy of AI Capability Measurement","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18158","citing_title":"The Measurement Gap in the Automation of EU Law: Benchmarking Doctrinal Legal Reasoning under the EU AI Act","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18532","citing_title":"AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08044","citing_title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28524","citing_title":"Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25492","citing_title":"SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02258","citing_title":"Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22612","citing_title":"Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20520","citing_title":"Open-World Evaluations for Measuring Frontier AI Capabilities","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18660","citing_title":"Evaluating Multi-turn Human-AI Interaction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15297","citing_title":"VERA-MH Concept Paper","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14782","citing_title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09896","citing_title":"The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13988","citing_title":"Neural Fields for NV-Center Inverse Sensing","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14167","citing_title":"The Evaluation Trap: Benchmark Design as Theoretical Commitment","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14164","citing_title":"Unsteady Metrics and Benchmarking Cultures of AI Model Builders","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10403","citing_title":"PaLM 2 Technical Report","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10834","citing_title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2204.02311","citing_title":"PaLM: Scaling Language Modeling with Pathways","ref_index":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK","json":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK.json","graph_json":"https://pith.science/api/pith-number/3VMURTCVC7RULVN45UBBVDG4TK/graph.json","events_json":"https://pith.science/api/pith-number/3VMURTCVC7RULVN45UBBVDG4TK/events.json","paper":"https://pith.science/paper/3VMURTCV"},"agent_actions":{"view_html":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK","download_json":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK.json","view_paper":"https://pith.science/paper/3VMURTCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15366&json=true","fetch_graph":"https://pith.science/api/pith-number/3VMURTCVC7RULVN45UBBVDG4TK/graph.json","fetch_events":"https://pith.science/api/pith-number/3VMURTCVC7RULVN45UBBVDG4TK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK/action/storage_attestation","attest_author":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK/action/author_attestation","sign_citation":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK/action/citation_signature","submit_replication":"https://pith.science/pith/3VMURTCVC7RULVN45UBBVDG4TK/action/replication_record"}},"created_at":"2026-07-05T03:36:25.446115+00:00","updated_at":"2026-07-05T03:36:25.446115+00:00"}