{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WRIICYIUVPKUKEBABTNOFEZM4I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c8c96d7d0d4efa2cf3b8ac619dfc90a42405df15cb450a8344dc8abfbb34c0b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T20:21:36Z","title_canon_sha256":"3cf85272acb206a6369a8d2a3d5559e7e2cc5ec5b446bbe1c08abae6ee56fa1e"},"schema_version":"1.0","source":{"id":"2502.20502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20502","created_at":"2026-07-05T10:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20502v1","created_at":"2026-07-05T10:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20502","created_at":"2026-07-05T10:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"WRIICYIUVPKU","created_at":"2026-07-05T10:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"WRIICYIUVPKUKEBA","created_at":"2026-07-05T10:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"WRIICYIU","created_at":"2026-07-05T10:21:34Z"}],"graph_snapshots":[{"event_id":"sha256:2d75296aa3e09e30b7cc273fc95f1f93731eed23ffdee05c6ec0840e67ab7516","target":"graph","created_at":"2026-07-05T10:21:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.20502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent benchmark studies have claimed that AI has approached or even surpassed human-level performances on various cognitive tasks. However, this position paper argues that current AI evaluation paradigms are insufficient for assessing human-like cognitive capabilities. We identify a set of key shortcomings: a lack of human-validated labels, inadequate representation of human response variability and uncertainty, and reliance on simplified and ecologically-invalid tasks. We support our claims by conducting a human evaluation study on ten existing AI benchmarks, suggesting significant biases an","authors_text":"Adrian Weller, Ilia Sucholutsky, Joshua B. Tenenbaum, Katherine M. Collins, Lance Ying, Lionel Wong, Ryan Liu, Thomas L. Griffiths, Tianmin Shu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T20:21:36Z","title":"On Benchmarking Human-Like Intelligence in Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20502","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2fd1f3fd206bdd2971c122cf92b2252b9ef3f9d53944a542a746ab9f1473ddcb","target":"record","created_at":"2026-07-05T10:21:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c8c96d7d0d4efa2cf3b8ac619dfc90a42405df15cb450a8344dc8abfbb34c0b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T20:21:36Z","title_canon_sha256":"3cf85272acb206a6369a8d2a3d5559e7e2cc5ec5b446bbe1c08abae6ee56fa1e"},"schema_version":"1.0","source":{"id":"2502.20502","kind":"arxiv","version":1}},"canonical_sha256":"b450816114abd54510200cdae2932ce206e5790d7d4e3941fdf96bd8dc606645","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b450816114abd54510200cdae2932ce206e5790d7d4e3941fdf96bd8dc606645","first_computed_at":"2026-07-05T10:21:34.139842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:34.139842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kl7tNKuw+M4zO+4PcXYfuja0dyDbpLFYh8j3zQVgUnGk5oco3Anrcq/8U1uR3+VEmsrtmjFTvu91+qqgiTcnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:34.140400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fd1f3fd206bdd2971c122cf92b2252b9ef3f9d53944a542a746ab9f1473ddcb","sha256:2d75296aa3e09e30b7cc273fc95f1f93731eed23ffdee05c6ec0840e67ab7516"],"state_sha256":"5907be213eb6fdb488c0b716d6c75c23ad53cc3ef26bbb011605d1474647b1bf"}