{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5H6F5FECVFAY4PWLMHA36Z3TRM","short_pith_number":"pith:5H6F5FEC","schema_version":"1.0","canonical_sha256":"e9fc5e9482a9418e3ecb61c1bf67738b1a6311efd53919973ff25c45a7ca1abf","source":{"kind":"arxiv","id":"2607.24999","version":1},"attestation_state":"computed","paper":{"title":"CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dengzhe Hou, Fangzhou Lin, Kazunori D Yamada, Lingyu Jiang","submitted_at":"2026-07-27T18:56:13Z","abstract_excerpt":"LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a procedurally generated 13-paradigm benchmark built around a multimethod framework for determining when cognitive-task scores warrant dimensional labels across five theory-motivated groupings. Across 55 open-weight models, nearly all paradigm correlations are positive and a common axis explains about half the variance. The within-grouping advantage is sm"},"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":"2607.24999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T18:56:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96953c8b78093ec487763dafa593a072942d714de9303fb8aff9976c58477a4c","abstract_canon_sha256":"1219927f827f787c06478ac555cfbbea8d293c9030c14f1b93561815ce1531e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:57.174801Z","signature_b64":"EWM3ROtaYbL6N/0wXWEtXpSZn8xPMCYOVgDtVqHZjW13n8Oj0MaCAYgOXZYwFeQFAdh1hKK+v8eH0bUmfDi5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9fc5e9482a9418e3ecb61c1bf67738b1a6311efd53919973ff25c45a7ca1abf","last_reissued_at":"2026-07-29T00:24:57.173952Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:57.173952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dengzhe Hou, Fangzhou Lin, Kazunori D Yamada, Lingyu Jiang","submitted_at":"2026-07-27T18:56:13Z","abstract_excerpt":"LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a procedurally generated 13-paradigm benchmark built around a multimethod framework for determining when cognitive-task scores warrant dimensional labels across five theory-motivated groupings. Across 55 open-weight models, nearly all paradigm correlations are positive and a common axis explains about half the variance. The within-grouping advantage is sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24999","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/2607.24999/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":"2607.24999","created_at":"2026-07-29T00:24:57.174388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24999v1","created_at":"2026-07-29T00:24:57.174388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24999","created_at":"2026-07-29T00:24:57.174388+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H6F5FECVFAY","created_at":"2026-07-29T00:24:57.174388+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H6F5FECVFAY4PWL","created_at":"2026-07-29T00:24:57.174388+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H6F5FEC","created_at":"2026-07-29T00:24:57.174388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM","json":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM.json","graph_json":"https://pith.science/api/pith-number/5H6F5FECVFAY4PWLMHA36Z3TRM/graph.json","events_json":"https://pith.science/api/pith-number/5H6F5FECVFAY4PWLMHA36Z3TRM/events.json","paper":"https://pith.science/paper/5H6F5FEC"},"agent_actions":{"view_html":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM","download_json":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM.json","view_paper":"https://pith.science/paper/5H6F5FEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24999&json=true","fetch_graph":"https://pith.science/api/pith-number/5H6F5FECVFAY4PWLMHA36Z3TRM/graph.json","fetch_events":"https://pith.science/api/pith-number/5H6F5FECVFAY4PWLMHA36Z3TRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM/action/storage_attestation","attest_author":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM/action/author_attestation","sign_citation":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM/action/citation_signature","submit_replication":"https://pith.science/pith/5H6F5FECVFAY4PWLMHA36Z3TRM/action/replication_record"}},"created_at":"2026-07-29T00:24:57.174388+00:00","updated_at":"2026-07-29T00:24:57.174388+00:00"}