{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZA4TQASZLJO3ERRHT37E63QJPS","short_pith_number":"pith:ZA4TQASZ","schema_version":"1.0","canonical_sha256":"c8393802595a5db246279efe4f6e097ca1ad86c93ccb4fcb2c49595e9c07b4c6","source":{"kind":"arxiv","id":"2505.17482","version":1},"attestation_state":"computed","paper":{"title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chao Lei, Krista A. Ehinger, Nir Lipovetzky, Yanchuan Chang","submitted_at":"2025-05-23T05:21:14Z","abstract_excerpt":"Recent reasoning-oriented LLMs have demonstrated strong performance on challenging tasks such as mathematics and science examinations. However, core cognitive faculties of human intelligence, such as abstract reasoning and generalization, remain underexplored. To address this, we evaluate recent reasoning-oriented LLMs on the Abstraction and Reasoning Corpus (ARC) benchmark, which explicitly demands both faculties. We formulate ARC as a program synthesis task and propose nine candidate solvers. Experimental results show that repeated-sampling planning-aided code generation (RSPC) achieves the "},"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":"2505.17482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T05:21:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7e4c7a8c90e36bbbea1edfc3dc34a43571fb76f2efa8f774457f396f208fa6fc","abstract_canon_sha256":"322da1c46411f94f3e80f35ee3e34b2ed8776da9ccbfecfb01dfd37568c54f80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:26.727807Z","signature_b64":"g0hem6H6PfVLC4h2OUNMlxGq9RKmqjQ8KGZlzGhGr/xbSEWUG3EvkZRoC9XkJxoX+PIG3JhAS4KzEuSI4BhSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8393802595a5db246279efe4f6e097ca1ad86c93ccb4fcb2c49595e9c07b4c6","last_reissued_at":"2026-07-05T11:08:26.727417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:26.727417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chao Lei, Krista A. Ehinger, Nir Lipovetzky, Yanchuan Chang","submitted_at":"2025-05-23T05:21:14Z","abstract_excerpt":"Recent reasoning-oriented LLMs have demonstrated strong performance on challenging tasks such as mathematics and science examinations. However, core cognitive faculties of human intelligence, such as abstract reasoning and generalization, remain underexplored. To address this, we evaluate recent reasoning-oriented LLMs on the Abstraction and Reasoning Corpus (ARC) benchmark, which explicitly demands both faculties. We formulate ARC as a program synthesis task and propose nine candidate solvers. Experimental results show that repeated-sampling planning-aided code generation (RSPC) achieves the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17482","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/2505.17482/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":"2505.17482","created_at":"2026-07-05T11:08:26.727488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17482v1","created_at":"2026-07-05T11:08:26.727488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17482","created_at":"2026-07-05T11:08:26.727488+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA4TQASZLJO3","created_at":"2026-07-05T11:08:26.727488+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA4TQASZLJO3ERRH","created_at":"2026-07-05T11:08:26.727488+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA4TQASZ","created_at":"2026-07-05T11:08:26.727488+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/ZA4TQASZLJO3ERRHT37E63QJPS","json":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS.json","graph_json":"https://pith.science/api/pith-number/ZA4TQASZLJO3ERRHT37E63QJPS/graph.json","events_json":"https://pith.science/api/pith-number/ZA4TQASZLJO3ERRHT37E63QJPS/events.json","paper":"https://pith.science/paper/ZA4TQASZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS","download_json":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS.json","view_paper":"https://pith.science/paper/ZA4TQASZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17482&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA4TQASZLJO3ERRHT37E63QJPS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA4TQASZLJO3ERRHT37E63QJPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS/action/storage_attestation","attest_author":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS/action/author_attestation","sign_citation":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS/action/citation_signature","submit_replication":"https://pith.science/pith/ZA4TQASZLJO3ERRHT37E63QJPS/action/replication_record"}},"created_at":"2026-07-05T11:08:26.727488+00:00","updated_at":"2026-07-05T11:08:26.727488+00:00"}