{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EDBWG6AS7KW7OOP3AB7KYNR2Z2","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":"dabe5b8d554fdf22ef0937025be761755729845a61855cd1c610ed91daa70bcd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T20:07:18Z","title_canon_sha256":"ab785911a433e17dba7b2a12a71c81cf1d2b7d2b8602c5411088491e2b7a8d48"},"schema_version":"1.0","source":{"id":"2501.11721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11721","created_at":"2026-07-05T10:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11721v2","created_at":"2026-07-05T10:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11721","created_at":"2026-07-05T10:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"EDBWG6AS7KW7","created_at":"2026-07-05T10:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"EDBWG6AS7KW7OOP3","created_at":"2026-07-05T10:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"EDBWG6AS","created_at":"2026-07-05T10:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:c7e7b974617da1c51c21435838c8b8ccaee5f8812f30e52a024cfaee834ca9fa","target":"graph","created_at":"2026-07-05T10:27:23Z","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/2501.11721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable proficiency in generating detailed and coherent explanations of complex concepts. However, the extent to which these models truly comprehend the concepts they articulate remains unclear. To assess the level of comprehension of a model relative to the content it generates, we implemented a self-evaluation pipeline where models: (i) given a topic generate an excerpt with information about the topic, (ii) given an excerpt generate question-answer pairs, and finally (iii) given a question generate an answer. We refer to this self-evaluation","authors_text":"Joao Monteiro, Saeid Asgari Taghanaki","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T20:07:18Z","title":"Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11721","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:f09954bc2c9185ebe6fca003a6a051f004a625001b60a008f39ef24a33186616","target":"record","created_at":"2026-07-05T10:27:23Z","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":"dabe5b8d554fdf22ef0937025be761755729845a61855cd1c610ed91daa70bcd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T20:07:18Z","title_canon_sha256":"ab785911a433e17dba7b2a12a71c81cf1d2b7d2b8602c5411088491e2b7a8d48"},"schema_version":"1.0","source":{"id":"2501.11721","kind":"arxiv","version":2}},"canonical_sha256":"20c3637812faadf739fb007eac363aceb971efc296a8fb4f54f466795687bb78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20c3637812faadf739fb007eac363aceb971efc296a8fb4f54f466795687bb78","first_computed_at":"2026-07-05T10:27:23.698085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:23.698085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1WbWS+3t8LhJM43dpcCw+yf8QOYmK67PzkJMNhkNTgxj14MyFaeWPqfzDAwQ6WW234ZiPHxB+kVScZjYtTCODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:23.699273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f09954bc2c9185ebe6fca003a6a051f004a625001b60a008f39ef24a33186616","sha256:c7e7b974617da1c51c21435838c8b8ccaee5f8812f30e52a024cfaee834ca9fa"],"state_sha256":"de4b6fa6f5dcadfebb0355aa56f6a1f388889c7594ac33ee05564da0b002fa75"}