{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K6MOYOFBMOLPT3LXOIRJCPVOA5","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":"b42cce5d2f4704e829ddab542ef2ed941427503a6e880ba3a8f27917ee603607","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:43:33Z","title_canon_sha256":"dc45fa229055fa127eb0e1a2a9dc0f73186a5aa3c6a806b9af4b1e609fd607d2"},"schema_version":"1.0","source":{"id":"2406.02061","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02061","created_at":"2026-07-05T10:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02061v5","created_at":"2026-07-05T10:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02061","created_at":"2026-07-05T10:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"K6MOYOFBMOLP","created_at":"2026-07-05T10:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"K6MOYOFBMOLPT3LX","created_at":"2026-07-05T10:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"K6MOYOFB","created_at":"2026-07-05T10:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:786e6b45ee9c68ef48785545f76f75c9c5517498c25c8aaf72e59239bb75c640","target":"graph","created_at":"2026-07-05T10:24:22Z","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/2406.02061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jenia Jitsev, Lucia Cipolina-Kun, Marianna Nezhurina, Mehdi Cherti","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:43:33Z","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02061","kind":"arxiv","version":5},"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":"sha256:9dd2d6a5da31cae01037ae75a7d3127af94eb386ea81a21f7caaf8b9419a522a","target":"record","created_at":"2026-07-05T10:24:22Z","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":"b42cce5d2f4704e829ddab542ef2ed941427503a6e880ba3a8f27917ee603607","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:43:33Z","title_canon_sha256":"dc45fa229055fa127eb0e1a2a9dc0f73186a5aa3c6a806b9af4b1e609fd607d2"},"schema_version":"1.0","source":{"id":"2406.02061","kind":"arxiv","version":5}},"canonical_sha256":"5798ec38a16396f9ed777222913eae0745bda20293fdf72fd8da91209244a945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5798ec38a16396f9ed777222913eae0745bda20293fdf72fd8da91209244a945","first_computed_at":"2026-07-05T10:24:22.455171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:22.455171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fuQkzIv+neOEwjcrn4uWMS/DltJK0EVkZTuFQwBcidBMLFCJ22Ysf/yeeLPB/xUs0GqDHzN2jfXLgYvvhPnhAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:22.456288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02061","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dd2d6a5da31cae01037ae75a7d3127af94eb386ea81a21f7caaf8b9419a522a","sha256:786e6b45ee9c68ef48785545f76f75c9c5517498c25c8aaf72e59239bb75c640"],"state_sha256":"fb7c0321efe6f4d138f206dc6c66b741a99fd996bb7271695398882ed6ad50b6"}