{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z7ZAMPUDHXH2W44JUCFVABSOTI","short_pith_number":"pith:Z7ZAMPUD","schema_version":"1.0","canonical_sha256":"cff2063e833dcfab7389a08b50064e9a1e79b66902643571f9efa6edb1946581","source":{"kind":"arxiv","id":"2605.18663","version":1},"attestation_state":"computed","paper":{"title":"GIM: Evaluating models via tasks that integrate multiple cognitive domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandre Rezende, Rohit Patel, Steven McClain","submitted_at":"2026-05-18T17:09:50Z","abstract_excerpt":"As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing knowledge entirely in favor of abstract reasoning (ARC-AGI). The first conflates memorization with capability; the second divorces reasoning from the practical contexts in which it matters. We take a different approach. The Grounded Integration Measure (GIM) is a benchmark of 820 original problems (615 public, 205 private) where difficulty comes from integration; individual problems require coordinating multiple cognitive operations (const"},"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":"2605.18663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T17:09:50Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0e51878ed65ffea8ce52f9ddbeb87e9bb16ffa53f88d5cb8987073df8d7c062b","abstract_canon_sha256":"ce6836f29b542bd52962abf62a7d303301d46051e739f76ccb7a619e4f3877c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:13.505311Z","signature_b64":"Z/AB2cgh1gdhvzjhqtNjvQ31FjbC078gSBvSmOP87oMYHUVF/Z+GhiPQiNcMXMRmyPDUNWA2DlWd/D1xN5e5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff2063e833dcfab7389a08b50064e9a1e79b66902643571f9efa6edb1946581","last_reissued_at":"2026-05-20T00:06:13.504596Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:13.504596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIM: Evaluating models via tasks that integrate multiple cognitive domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandre Rezende, Rohit Patel, Steven McClain","submitted_at":"2026-05-18T17:09:50Z","abstract_excerpt":"As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing knowledge entirely in favor of abstract reasoning (ARC-AGI). The first conflates memorization with capability; the second divorces reasoning from the practical contexts in which it matters. We take a different approach. The Grounded Integration Measure (GIM) is a benchmark of 820 original problems (615 public, 205 private) where difficulty comes from integration; individual problems require coordinating multiple cognitive operations (const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18663","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/2605.18663/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.147771Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6d1e06b3aeeb9bad3c640681ad2e2b5589ff660034681b77cb0f0bbc0844f979"},"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":"2605.18663","created_at":"2026-05-20T00:06:13.504711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18663v1","created_at":"2026-05-20T00:06:13.504711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18663","created_at":"2026-05-20T00:06:13.504711+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7ZAMPUDHXH2","created_at":"2026-05-20T00:06:13.504711+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7ZAMPUDHXH2W44J","created_at":"2026-05-20T00:06:13.504711+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7ZAMPUD","created_at":"2026-05-20T00:06:13.504711+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/Z7ZAMPUDHXH2W44JUCFVABSOTI","json":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI.json","graph_json":"https://pith.science/api/pith-number/Z7ZAMPUDHXH2W44JUCFVABSOTI/graph.json","events_json":"https://pith.science/api/pith-number/Z7ZAMPUDHXH2W44JUCFVABSOTI/events.json","paper":"https://pith.science/paper/Z7ZAMPUD"},"agent_actions":{"view_html":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI","download_json":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI.json","view_paper":"https://pith.science/paper/Z7ZAMPUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18663&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7ZAMPUDHXH2W44JUCFVABSOTI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7ZAMPUDHXH2W44JUCFVABSOTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI/action/storage_attestation","attest_author":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI/action/author_attestation","sign_citation":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI/action/citation_signature","submit_replication":"https://pith.science/pith/Z7ZAMPUDHXH2W44JUCFVABSOTI/action/replication_record"}},"created_at":"2026-05-20T00:06:13.504711+00:00","updated_at":"2026-05-20T00:06:13.504711+00:00"}