{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K6MOYOFBMOLPT3LXOIRJCPVOA5","short_pith_number":"pith:K6MOYOFB","schema_version":"1.0","canonical_sha256":"5798ec38a16396f9ed777222913eae0745bda20293fdf72fd8da91209244a945","source":{"kind":"arxiv","id":"2406.02061","version":5},"attestation_state":"computed","paper":{"title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jenia Jitsev, Lucia Cipolina-Kun, Marianna Nezhurina, Mehdi Cherti","submitted_at":"2024-06-04T07:43:33Z","abstract_excerpt":"Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws, and therefore transfer robustly across various conditions in few- or zero-shot manner. Such claims rely on standardized benchmarks that suppose to measure generalization and reasoning, where state-of-the-art (SOTA) models score high. We demonstrate here a dramatic breakdown of generalization and basic reasoning of all SOTA models claiming strong function, including large scale advanced models like GPT-4 or Claude 3 Opus, using a simple, short common sense "},"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":"2406.02061","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:43:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dc45fa229055fa127eb0e1a2a9dc0f73186a5aa3c6a806b9af4b1e609fd607d2","abstract_canon_sha256":"b42cce5d2f4704e829ddab542ef2ed941427503a6e880ba3a8f27917ee603607"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:22.456288Z","signature_b64":"fuQkzIv+neOEwjcrn4uWMS/DltJK0EVkZTuFQwBcidBMLFCJ22Ysf/yeeLPB/xUs0GqDHzN2jfXLgYvvhPnhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5798ec38a16396f9ed777222913eae0745bda20293fdf72fd8da91209244a945","last_reissued_at":"2026-07-05T10:24:22.455171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:22.455171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jenia Jitsev, Lucia Cipolina-Kun, Marianna Nezhurina, Mehdi Cherti","submitted_at":"2024-06-04T07:43:33Z","abstract_excerpt":"Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws, and therefore transfer robustly across various conditions in few- or zero-shot manner. Such claims rely on standardized benchmarks that suppose to measure generalization and reasoning, where state-of-the-art (SOTA) models score high. We demonstrate here a dramatic breakdown of generalization and basic reasoning of all SOTA models claiming strong function, including large scale advanced models like GPT-4 or Claude 3 Opus, using a simple, short common sense "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02061","kind":"arxiv","version":5},"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/2406.02061/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":"2406.02061","created_at":"2026-07-05T10:24:22.455377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02061v5","created_at":"2026-07-05T10:24:22.455377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02061","created_at":"2026-07-05T10:24:22.455377+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6MOYOFBMOLP","created_at":"2026-07-05T10:24:22.455377+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6MOYOFBMOLPT3LX","created_at":"2026-07-05T10:24:22.455377+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6MOYOFB","created_at":"2026-07-05T10:24:22.455377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12731","citing_title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08571","citing_title":"Robust Reasoning Benchmark","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18852","citing_title":"Mechanistic Interpretability Needs Philosophy","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06941","citing_title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05229","citing_title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08571","citing_title":"Robust Reasoning Benchmark","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09678","citing_title":"Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06882","citing_title":"How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05631","citing_title":"Beyond Behavior: Why AI Evaluation Needs a Cognitive Revolution","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15618","citing_title":"Majority Voting for Code Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5","json":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5.json","graph_json":"https://pith.science/api/pith-number/K6MOYOFBMOLPT3LXOIRJCPVOA5/graph.json","events_json":"https://pith.science/api/pith-number/K6MOYOFBMOLPT3LXOIRJCPVOA5/events.json","paper":"https://pith.science/paper/K6MOYOFB"},"agent_actions":{"view_html":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5","download_json":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5.json","view_paper":"https://pith.science/paper/K6MOYOFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02061&json=true","fetch_graph":"https://pith.science/api/pith-number/K6MOYOFBMOLPT3LXOIRJCPVOA5/graph.json","fetch_events":"https://pith.science/api/pith-number/K6MOYOFBMOLPT3LXOIRJCPVOA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5/action/storage_attestation","attest_author":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5/action/author_attestation","sign_citation":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5/action/citation_signature","submit_replication":"https://pith.science/pith/K6MOYOFBMOLPT3LXOIRJCPVOA5/action/replication_record"}},"created_at":"2026-07-05T10:24:22.455377+00:00","updated_at":"2026-07-05T10:24:22.455377+00:00"}