{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TRUGLNEYCVTCWBGR5NFDZCCGZC","short_pith_number":"pith:TRUGLNEY","schema_version":"1.0","canonical_sha256":"9c6865b49815662b04d1eb4a3c8846c8a88940d2d5b183bd1745e0fc9bbe1c1c","source":{"kind":"arxiv","id":"2604.10825","version":2},"attestation_state":"computed","paper":{"title":"CheeseBench: Evaluating Large Language Models on Rodent Behavioral Neuroscience Paradigms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zacharie Bugaud","submitted_at":"2026-04-12T21:37:26Z","abstract_excerpt":"We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maze, operant chamber, shuttle box, conditioned place preference, and delayed non-match to sample), spanning six cognitive dimensions. Each task is grounded in peer-reviewed rodent protocols with approximate animal baselines. The agent receives a unified system prompt with no task-specific instructions and must discover goals purely from ASCII text observations and reward signals, much like a rodent "},"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":"2604.10825","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-12T21:37:26Z","cross_cats_sorted":[],"title_canon_sha256":"8f76097af32e619e69f6c0dad621447ae762ed1b9987f839b3732ab83cd5a33d","abstract_canon_sha256":"35e2ab0f93727970a58e0e2eca64eecb02bbba26445ccaf8c784cae24d4deca6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:11.384760Z","signature_b64":"zfVKHfnlzVQEhFiFPvLVuZWCNRm6kTGxYpX14bYI5/UuokyN5+eD9GTjmkJBXt/YBI/4F3LelI4ViC/puvTbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c6865b49815662b04d1eb4a3c8846c8a88940d2d5b183bd1745e0fc9bbe1c1c","last_reissued_at":"2026-05-20T00:02:11.383748Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:11.383748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CheeseBench: Evaluating Large Language Models on Rodent Behavioral Neuroscience Paradigms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zacharie Bugaud","submitted_at":"2026-04-12T21:37:26Z","abstract_excerpt":"We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maze, operant chamber, shuttle box, conditioned place preference, and delayed non-match to sample), spanning six cognitive dimensions. Each task is grounded in peer-reviewed rodent protocols with approximate animal baselines. The agent receives a unified system prompt with no task-specific instructions and must discover goals purely from ASCII text observations and reward signals, much like a rodent "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The ASCII text renderings of the tasks accurately capture the core cognitive and perceptual demands of the original rodent behavioral paradigms without introducing artifacts that alter difficulty.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs reach 52.6% average success on text-based rodent neuroscience tasks, above random agents at 32.1% but below approximate rodent baselines at 78.9%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cf72cf3f28c4c7f6aebf5c99fa4759044dabc47f5a1727f61d4425940cedc3d7"},"source":{"id":"2604.10825","kind":"arxiv","version":2},"verdict":{"id":"cca5bbe6-e395-4aa8-ad0e-a20bbc9712bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:17:28.384818Z","strongest_claim":"Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.","one_line_summary":"LLMs reach 52.6% average success on text-based rodent neuroscience tasks, above random agents at 32.1% but below approximate rodent baselines at 78.9%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The ASCII text renderings of the tasks accurately capture the core cognitive and perceptual demands of the original rodent behavioral paradigms without introducing artifacts that alter difficulty.","pith_extraction_headline":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10825/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":"2604.10825","created_at":"2026-05-20T00:02:11.383920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.10825v2","created_at":"2026-05-20T00:02:11.383920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10825","created_at":"2026-05-20T00:02:11.383920+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRUGLNEYCVTC","created_at":"2026-05-20T00:02:11.383920+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRUGLNEYCVTCWBGR","created_at":"2026-05-20T00:02:11.383920+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRUGLNEY","created_at":"2026-05-20T00:02:11.383920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.01847","citing_title":"NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01847","citing_title":"NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC","json":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC.json","graph_json":"https://pith.science/api/pith-number/TRUGLNEYCVTCWBGR5NFDZCCGZC/graph.json","events_json":"https://pith.science/api/pith-number/TRUGLNEYCVTCWBGR5NFDZCCGZC/events.json","paper":"https://pith.science/paper/TRUGLNEY"},"agent_actions":{"view_html":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC","download_json":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC.json","view_paper":"https://pith.science/paper/TRUGLNEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.10825&json=true","fetch_graph":"https://pith.science/api/pith-number/TRUGLNEYCVTCWBGR5NFDZCCGZC/graph.json","fetch_events":"https://pith.science/api/pith-number/TRUGLNEYCVTCWBGR5NFDZCCGZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC/action/storage_attestation","attest_author":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC/action/author_attestation","sign_citation":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC/action/citation_signature","submit_replication":"https://pith.science/pith/TRUGLNEYCVTCWBGR5NFDZCCGZC/action/replication_record"}},"created_at":"2026-05-20T00:02:11.383920+00:00","updated_at":"2026-05-20T00:02:11.383920+00:00"}