{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4T7RETT5KA45EDOQXPKQM2LMEV","short_pith_number":"pith:4T7RETT5","schema_version":"1.0","canonical_sha256":"e4ff124e7d5039d20dd0bbd506696c255370a18fc0fb74cb5551227e088f0e3e","source":{"kind":"arxiv","id":"2603.05290","version":2},"attestation_state":"computed","paper":{"title":"X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jin Song Dong, Tianxi Gao, Yufan Cai, Yusi Yuan","submitted_at":"2026-03-05T15:34:22Z","abstract_excerpt":"Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood. Existing evaluations largely emphasize task-level accuracy, often conflating pattern matching with reasoning capability. We present X-RAY, an explainable reasoning analysis system that maps the LLM reasoning capability using calibrated, formally verified probes. We model reasoning capability as a function of extractable \\textit{structure}, operationalized through formal properties such as constraint interaction, reasoning depth, and solution-space geometry. X-Ray generates probes "},"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":"2603.05290","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-05T15:34:22Z","cross_cats_sorted":[],"title_canon_sha256":"8861a20498869c44a10bbbc88dfd058e5b4a0a5d9d553fc43c3503c210ed9d76","abstract_canon_sha256":"ddc4f3e87be7c7c83643324693d8cb75782f28feb011d3171ca7de695236c1ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:49.547330Z","signature_b64":"+/y49KoVaPVL2rz240Nk31gunyHHCUzm8mJpWHMlEdhBsywir92WLLtBTVy7CoU+Dtaoo7pCETX2TzmIe012Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ff124e7d5039d20dd0bbd506696c255370a18fc0fb74cb5551227e088f0e3e","last_reissued_at":"2026-06-03T01:05:49.546839Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:49.546839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jin Song Dong, Tianxi Gao, Yufan Cai, Yusi Yuan","submitted_at":"2026-03-05T15:34:22Z","abstract_excerpt":"Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood. Existing evaluations largely emphasize task-level accuracy, often conflating pattern matching with reasoning capability. We present X-RAY, an explainable reasoning analysis system that maps the LLM reasoning capability using calibrated, formally verified probes. We model reasoning capability as a function of extractable \\textit{structure}, operationalized through formal properties such as constraint interaction, reasoning depth, and solution-space geometry. X-Ray generates probes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05290","kind":"arxiv","version":2},"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/2603.05290/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":"2603.05290","created_at":"2026-06-03T01:05:49.546895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.05290v2","created_at":"2026-06-03T01:05:49.546895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05290","created_at":"2026-06-03T01:05:49.546895+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T7RETT5KA45","created_at":"2026-06-03T01:05:49.546895+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T7RETT5KA45EDOQ","created_at":"2026-06-03T01:05:49.546895+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T7RETT5","created_at":"2026-06-03T01:05:49.546895+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/4T7RETT5KA45EDOQXPKQM2LMEV","json":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV.json","graph_json":"https://pith.science/api/pith-number/4T7RETT5KA45EDOQXPKQM2LMEV/graph.json","events_json":"https://pith.science/api/pith-number/4T7RETT5KA45EDOQXPKQM2LMEV/events.json","paper":"https://pith.science/paper/4T7RETT5"},"agent_actions":{"view_html":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV","download_json":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV.json","view_paper":"https://pith.science/paper/4T7RETT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.05290&json=true","fetch_graph":"https://pith.science/api/pith-number/4T7RETT5KA45EDOQXPKQM2LMEV/graph.json","fetch_events":"https://pith.science/api/pith-number/4T7RETT5KA45EDOQXPKQM2LMEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV/action/storage_attestation","attest_author":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV/action/author_attestation","sign_citation":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV/action/citation_signature","submit_replication":"https://pith.science/pith/4T7RETT5KA45EDOQXPKQM2LMEV/action/replication_record"}},"created_at":"2026-06-03T01:05:49.546895+00:00","updated_at":"2026-06-03T01:05:49.546895+00:00"}