{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCM6UHQH23AYZPAGDK2KOEWUUU","short_pith_number":"pith:YCM6UHQH","schema_version":"1.0","canonical_sha256":"c099ea1e07d6c18cbc061ab4a712d4a5307d8d5b6f132908ec6f6d2a3325de26","source":{"kind":"arxiv","id":"2511.07910","version":2},"attestation_state":"computed","paper":{"title":"Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huajun Chen, Lei Liang, Songze Li, Wen Zhang, Xiaoke Guo, Zhaoyan Gong, Zhengke Gui, Zhiqiang Liu, Zhongpu Bo","submitted_at":"2025-11-11T07:08:27Z","abstract_excerpt":"Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-consistent responses. However, the representational differences between unstructured and structured knowledge make LLMs inherently struggle to maintain logic consistency, leading to \\textit{Logic Drift} challenges in structured knowledge reasoning tasks such as Knowledge Graph Question Answering (KGQA). Existing methods address this limitation by designing complex workflows emb"},"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":"2511.07910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-11T07:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"24567c703f362b717d3314a921875dde24826aed5e2f57b6fd71079af82555fd","abstract_canon_sha256":"bc4fab2f84ad8f5fce7dc392ac87ceb3573a45ef3dcc4d053d1b80ba1e350c8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:38.330313Z","signature_b64":"1Kop/b2DhvFAQOB4/htbdoL/acq5ucU5G47TTF/5fe9dguN5R2bTgSZr50uKvp9LGo+5t73Cq66At/TpKpYBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c099ea1e07d6c18cbc061ab4a712d4a5307d8d5b6f132908ec6f6d2a3325de26","last_reissued_at":"2026-06-02T01:03:38.329754Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:38.329754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huajun Chen, Lei Liang, Songze Li, Wen Zhang, Xiaoke Guo, Zhaoyan Gong, Zhengke Gui, Zhiqiang Liu, Zhongpu Bo","submitted_at":"2025-11-11T07:08:27Z","abstract_excerpt":"Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-consistent responses. However, the representational differences between unstructured and structured knowledge make LLMs inherently struggle to maintain logic consistency, leading to \\textit{Logic Drift} challenges in structured knowledge reasoning tasks such as Knowledge Graph Question Answering (KGQA). Existing methods address this limitation by designing complex workflows emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07910","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/2511.07910/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":"2511.07910","created_at":"2026-06-02T01:03:38.329816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07910v2","created_at":"2026-06-02T01:03:38.329816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07910","created_at":"2026-06-02T01:03:38.329816+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCM6UHQH23AY","created_at":"2026-06-02T01:03:38.329816+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCM6UHQH23AYZPAG","created_at":"2026-06-02T01:03:38.329816+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCM6UHQH","created_at":"2026-06-02T01:03:38.329816+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/YCM6UHQH23AYZPAGDK2KOEWUUU","json":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU.json","graph_json":"https://pith.science/api/pith-number/YCM6UHQH23AYZPAGDK2KOEWUUU/graph.json","events_json":"https://pith.science/api/pith-number/YCM6UHQH23AYZPAGDK2KOEWUUU/events.json","paper":"https://pith.science/paper/YCM6UHQH"},"agent_actions":{"view_html":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU","download_json":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU.json","view_paper":"https://pith.science/paper/YCM6UHQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07910&json=true","fetch_graph":"https://pith.science/api/pith-number/YCM6UHQH23AYZPAGDK2KOEWUUU/graph.json","fetch_events":"https://pith.science/api/pith-number/YCM6UHQH23AYZPAGDK2KOEWUUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU/action/storage_attestation","attest_author":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU/action/author_attestation","sign_citation":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU/action/citation_signature","submit_replication":"https://pith.science/pith/YCM6UHQH23AYZPAGDK2KOEWUUU/action/replication_record"}},"created_at":"2026-06-02T01:03:38.329816+00:00","updated_at":"2026-06-02T01:03:38.329816+00:00"}