{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YQBTNIMZ6CBWEVNNGSQ4P2UYB2","short_pith_number":"pith:YQBTNIMZ","schema_version":"1.0","canonical_sha256":"c40336a199f0836255ad34a1c7ea980e83a5f26fb741b086131375e5a5d1f2c5","source":{"kind":"arxiv","id":"2606.17312","version":1},"attestation_state":"computed","paper":{"title":"Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baishali Chaudhury, Hyunji Hayley Park, Jae Oh Woo, Mengdie Flora Wang, Rahul Ghosh, Sungmin Hong","submitted_at":"2026-06-15T21:39:47Z","abstract_excerpt":"Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning. Existing methods assess reliability primarily through output dispersion -- measuring how much sampled answers differ -- but this discards a complementary signal: whether the model can consistently rank competing reasoning candidates. We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings over sampled reasoni"},"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":"2606.17312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-15T21:39:47Z","cross_cats_sorted":[],"title_canon_sha256":"215b06441516fa865d095c9d4e397df1efaed4db010c319eec50a87bbe8229c9","abstract_canon_sha256":"d9b348e21ba251f22cd5b4e1aa08cb14ae3d54410646cd9f7c61e46a56fb94a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:08.754983Z","signature_b64":"zSVBcaIiBlH6R7h97f/7cwlVvZs0zsgtl2OD8ByoYD/gnuCpWNL29GUj1KhhPXRVhgIjD4ibPC28h7EkUx4eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40336a199f0836255ad34a1c7ea980e83a5f26fb741b086131375e5a5d1f2c5","last_reissued_at":"2026-06-19T16:10:08.754646Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:08.754646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baishali Chaudhury, Hyunji Hayley Park, Jae Oh Woo, Mengdie Flora Wang, Rahul Ghosh, Sungmin Hong","submitted_at":"2026-06-15T21:39:47Z","abstract_excerpt":"Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning. Existing methods assess reliability primarily through output dispersion -- measuring how much sampled answers differ -- but this discards a complementary signal: whether the model can consistently rank competing reasoning candidates. We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings over sampled reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17312","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/2606.17312/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":"2606.17312","created_at":"2026-06-19T16:10:08.754702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17312v1","created_at":"2026-06-19T16:10:08.754702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17312","created_at":"2026-06-19T16:10:08.754702+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQBTNIMZ6CBW","created_at":"2026-06-19T16:10:08.754702+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQBTNIMZ6CBWEVNN","created_at":"2026-06-19T16:10:08.754702+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQBTNIMZ","created_at":"2026-06-19T16:10:08.754702+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/YQBTNIMZ6CBWEVNNGSQ4P2UYB2","json":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2.json","graph_json":"https://pith.science/api/pith-number/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/graph.json","events_json":"https://pith.science/api/pith-number/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/events.json","paper":"https://pith.science/paper/YQBTNIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2","download_json":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2.json","view_paper":"https://pith.science/paper/YQBTNIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17312&json=true","fetch_graph":"https://pith.science/api/pith-number/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/graph.json","fetch_events":"https://pith.science/api/pith-number/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/action/storage_attestation","attest_author":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/action/author_attestation","sign_citation":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/action/citation_signature","submit_replication":"https://pith.science/pith/YQBTNIMZ6CBWEVNNGSQ4P2UYB2/action/replication_record"}},"created_at":"2026-06-19T16:10:08.754702+00:00","updated_at":"2026-06-19T16:10:08.754702+00:00"}