{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OLMIE34HWO5TOJNNFFFCHTFSKH","short_pith_number":"pith:OLMIE34H","schema_version":"1.0","canonical_sha256":"72d8826f87b3bb3725ad294a23ccb251f5ff54ccc356231f002f32a3939fd387","source":{"kind":"arxiv","id":"2505.23833","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qingchuan Ma, Rongrong Ji, Xiawu Zheng, Yuhang Wu","submitted_at":"2025-05-28T09:02:45Z","abstract_excerpt":"In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs). To achieve this, we first develop a mathematic framework that defines abstract reasoning as the ability to: (i) extract essential patterns independent of surface representations, and (ii) apply consistent rules to these abstract patterns. Based on this framework, we introduce two novel complementary metrics: \\(\\scoreGamma\\) measures basic reasoning accuracy, while \\(\\scoreDelta\\) quantifies a model's reliance on specific symbols"},"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":"2505.23833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T09:02:45Z","cross_cats_sorted":[],"title_canon_sha256":"3b03944a13d5ce857ecfd6b894665a608d1020ca51313e2a6f00ffced8a3cca1","abstract_canon_sha256":"d26d396ead9eb24433cab9ee577551b381de5dac794e6849fd5a49593ee457a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:36.233611Z","signature_b64":"+BP0n5nMzUwirnNH5hUcf/Q4poeREj/Ju1aH/m57do/T4DSH8UIm7K+qrDICaTWzyRl8wf8loU6QrnApvWSRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d8826f87b3bb3725ad294a23ccb251f5ff54ccc356231f002f32a3939fd387","last_reissued_at":"2026-07-05T11:12:36.233085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:36.233085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qingchuan Ma, Rongrong Ji, Xiawu Zheng, Yuhang Wu","submitted_at":"2025-05-28T09:02:45Z","abstract_excerpt":"In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs). To achieve this, we first develop a mathematic framework that defines abstract reasoning as the ability to: (i) extract essential patterns independent of surface representations, and (ii) apply consistent rules to these abstract patterns. Based on this framework, we introduce two novel complementary metrics: \\(\\scoreGamma\\) measures basic reasoning accuracy, while \\(\\scoreDelta\\) quantifies a model's reliance on specific symbols"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23833","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/2505.23833/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":"2505.23833","created_at":"2026-07-05T11:12:36.233144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23833v1","created_at":"2026-07-05T11:12:36.233144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23833","created_at":"2026-07-05T11:12:36.233144+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLMIE34HWO5T","created_at":"2026-07-05T11:12:36.233144+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLMIE34HWO5TOJNN","created_at":"2026-07-05T11:12:36.233144+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLMIE34H","created_at":"2026-07-05T11:12:36.233144+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/OLMIE34HWO5TOJNNFFFCHTFSKH","json":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH.json","graph_json":"https://pith.science/api/pith-number/OLMIE34HWO5TOJNNFFFCHTFSKH/graph.json","events_json":"https://pith.science/api/pith-number/OLMIE34HWO5TOJNNFFFCHTFSKH/events.json","paper":"https://pith.science/paper/OLMIE34H"},"agent_actions":{"view_html":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH","download_json":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH.json","view_paper":"https://pith.science/paper/OLMIE34H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23833&json=true","fetch_graph":"https://pith.science/api/pith-number/OLMIE34HWO5TOJNNFFFCHTFSKH/graph.json","fetch_events":"https://pith.science/api/pith-number/OLMIE34HWO5TOJNNFFFCHTFSKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH/action/storage_attestation","attest_author":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH/action/author_attestation","sign_citation":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH/action/citation_signature","submit_replication":"https://pith.science/pith/OLMIE34HWO5TOJNNFFFCHTFSKH/action/replication_record"}},"created_at":"2026-07-05T11:12:36.233144+00:00","updated_at":"2026-07-05T11:12:36.233144+00:00"}