{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5LYGAKK4WVHP2VRWXYHVIQNQWZ","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":"93a5385a9573cc7473d36d24103fd323074dd7f8d63d4737fca0d271f3725a14","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T16:32:17Z","title_canon_sha256":"0e8692e7baeb96f4f654728b201be3600a34bae356a39a91a9facde03d116466"},"schema_version":"1.0","source":{"id":"2305.18354","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18354","created_at":"2026-07-05T07:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18354v2","created_at":"2026-07-05T07:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18354","created_at":"2026-07-05T07:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"5LYGAKK4WVHP","created_at":"2026-07-05T07:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"5LYGAKK4WVHP2VRW","created_at":"2026-07-05T07:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"5LYGAKK4","created_at":"2026-07-05T07:45:14Z"}],"graph_snapshots":[{"event_id":"sha256:36a91fa552dba4a2cb147ed7e672b4e2810bcb5841aa2968f07c3df7cc25a033","target":"graph","created_at":"2026-07-05T07:45:14Z","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/2305.18354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can a Large Language Model (LLM) solve simple abstract reasoning problems? We explore this broad question through a systematic analysis of GPT on the Abstraction and Reasoning Corpus (ARC), a representative benchmark of abstract reasoning ability from limited examples in which solutions require some \"core knowledge\" of concepts such as objects, goal states, counting, and basic geometry. GPT-4 solves only 13/50 of the most straightforward ARC tasks when using textual encodings for their two-dimensional input-output grids. Our failure analysis reveals that GPT-4's capacity to identify objects an","authors_text":"Elias B. Khalil, Pashootan Vaezipoor, Scott Sanner, Wenhao Li, Yudong Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T16:32:17Z","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18354","kind":"arxiv","version":2},"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":"sha256:845a328c81ca294db24045d629337d1fb2b260ebce4433e84ca8c4323c90cb30","target":"record","created_at":"2026-07-05T07:45:14Z","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":"93a5385a9573cc7473d36d24103fd323074dd7f8d63d4737fca0d271f3725a14","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T16:32:17Z","title_canon_sha256":"0e8692e7baeb96f4f654728b201be3600a34bae356a39a91a9facde03d116466"},"schema_version":"1.0","source":{"id":"2305.18354","kind":"arxiv","version":2}},"canonical_sha256":"eaf060295cb54efd5636be0f5441b0b6491c36f4c01b7632628354b426e71009","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaf060295cb54efd5636be0f5441b0b6491c36f4c01b7632628354b426e71009","first_computed_at":"2026-07-05T07:45:14.015869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:14.015869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"at8WPqBiIwts9VSOpAxdVjBAwziAa1xTH4EKvGhKxALOu0SH9chbTpBpZh2i73Sjz0cM0/Z7luaFTWSpBxCZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:14.017072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18354","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:845a328c81ca294db24045d629337d1fb2b260ebce4433e84ca8c4323c90cb30","sha256:36a91fa552dba4a2cb147ed7e672b4e2810bcb5841aa2968f07c3df7cc25a033"],"state_sha256":"61c8b0031065ea77806c0fd1c46d0fb64975838f7acced1a3f3ce173f38dd461"}