{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IDQLXHLDU5LUXQJBNHFEJZGTL6","short_pith_number":"pith:IDQLXHLD","schema_version":"1.0","canonical_sha256":"40e0bb9d63a7574bc12169ca44e4d35fada6f020ac02098fbe07a5a22eab07d6","source":{"kind":"arxiv","id":"2605.24661","version":1},"attestation_state":"computed","paper":{"title":"Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ali \\c{S}enol, Garima Agrawal, Huan Liu","submitted_at":"2026-05-23T17:03:42Z","abstract_excerpt":"LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers. To address this gap, this study proposes a unified multi-dimensional framework for measuring reasoning quality in LLMs from a behavioral perspective, operationalizing six theoretically grounded dimensions: Correctness (CQ), Consistency (CS), Robustness (RS), Logical Coherence (LS), Efficiency (ES), and Stability (SS). Extensive experiments on seven LLMs acr"},"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":"2605.24661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T17:03:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"422836ef21594d40cf53c5089256dc5bb598b0f2c31bb4cf023f91151269be2d","abstract_canon_sha256":"578a3d225d7b3a838b0b817b8eed0c1f761a042fb80f695286e2fec60168a91a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:51.838677Z","signature_b64":"CMqBnTOJ2kSmzJVFh9lHAAT2qdwLSObCz05OW3aQYKS/QX1C4aw37Dov5Pf+vVZaT7c+mpkmStF7sp/G/5xdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40e0bb9d63a7574bc12169ca44e4d35fada6f020ac02098fbe07a5a22eab07d6","last_reissued_at":"2026-05-26T01:03:51.837777Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:51.837777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ali \\c{S}enol, Garima Agrawal, Huan Liu","submitted_at":"2026-05-23T17:03:42Z","abstract_excerpt":"LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers. To address this gap, this study proposes a unified multi-dimensional framework for measuring reasoning quality in LLMs from a behavioral perspective, operationalizing six theoretically grounded dimensions: Correctness (CQ), Consistency (CS), Robustness (RS), Logical Coherence (LS), Efficiency (ES), and Stability (SS). Extensive experiments on seven LLMs acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24661","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/2605.24661/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":"2605.24661","created_at":"2026-05-26T01:03:51.837941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24661v1","created_at":"2026-05-26T01:03:51.837941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24661","created_at":"2026-05-26T01:03:51.837941+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDQLXHLDU5LU","created_at":"2026-05-26T01:03:51.837941+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDQLXHLDU5LUXQJB","created_at":"2026-05-26T01:03:51.837941+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDQLXHLD","created_at":"2026-05-26T01:03:51.837941+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/IDQLXHLDU5LUXQJBNHFEJZGTL6","json":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6.json","graph_json":"https://pith.science/api/pith-number/IDQLXHLDU5LUXQJBNHFEJZGTL6/graph.json","events_json":"https://pith.science/api/pith-number/IDQLXHLDU5LUXQJBNHFEJZGTL6/events.json","paper":"https://pith.science/paper/IDQLXHLD"},"agent_actions":{"view_html":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6","download_json":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6.json","view_paper":"https://pith.science/paper/IDQLXHLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24661&json=true","fetch_graph":"https://pith.science/api/pith-number/IDQLXHLDU5LUXQJBNHFEJZGTL6/graph.json","fetch_events":"https://pith.science/api/pith-number/IDQLXHLDU5LUXQJBNHFEJZGTL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6/action/storage_attestation","attest_author":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6/action/author_attestation","sign_citation":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6/action/citation_signature","submit_replication":"https://pith.science/pith/IDQLXHLDU5LUXQJBNHFEJZGTL6/action/replication_record"}},"created_at":"2026-05-26T01:03:51.837941+00:00","updated_at":"2026-05-26T01:03:51.837941+00:00"}