{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4G74OI4MLDSNQMATWFWR4CEDSN","short_pith_number":"pith:4G74OI4M","schema_version":"1.0","canonical_sha256":"e1bfc7238c58e4d83013b16d1e08839349e4274b4193f95e04f573abe02aedc4","source":{"kind":"arxiv","id":"2305.01157","version":3},"attestation_state":"computed","paper":{"title":"Complex Logical Reasoning over Knowledge Graphs using Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LO","authors_text":"Chandan K. Reddy, Nurendra Choudhary","submitted_at":"2023-05-02T02:21:49Z","abstract_excerpt":"Reasoning over knowledge graphs (KGs) is a challenging task that requires a deep understanding of the complex relationships between entities and the underlying logic of their relations. Current approaches rely on learning geometries to embed entities in vector space for logical query operations, but they suffer from subpar performance on complex queries and dataset-specific representations. In this paper, we propose a novel decoupled approach, Language-guided Abstract Reasoning over Knowledge graphs (LARK), that formulates complex KG reasoning as a combination of contextual KG search and logic"},"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":"2305.01157","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LO","submitted_at":"2023-05-02T02:21:49Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"0c7aa783bda832eb1082ade2cdba494b6c1ef4030336f42a3b953a9ee8c1fb41","abstract_canon_sha256":"1a5d0cbb0162f4a3fcdbcffe1ad30dd825834904bbbda5c25895c88ef0ec1ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:43.453618Z","signature_b64":"ekE8/9aK8onVWbbTZhjOfM6b6fPDCjRAYLmK8D0IA7z5ownMYoWEvSvIpCFzaKxt0FoaHBmd66y/qIg+YXjNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1bfc7238c58e4d83013b16d1e08839349e4274b4193f95e04f573abe02aedc4","last_reissued_at":"2026-07-05T08:02:43.453074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:43.453074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complex Logical Reasoning over Knowledge Graphs using Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LO","authors_text":"Chandan K. Reddy, Nurendra Choudhary","submitted_at":"2023-05-02T02:21:49Z","abstract_excerpt":"Reasoning over knowledge graphs (KGs) is a challenging task that requires a deep understanding of the complex relationships between entities and the underlying logic of their relations. Current approaches rely on learning geometries to embed entities in vector space for logical query operations, but they suffer from subpar performance on complex queries and dataset-specific representations. In this paper, we propose a novel decoupled approach, Language-guided Abstract Reasoning over Knowledge graphs (LARK), that formulates complex KG reasoning as a combination of contextual KG search and logic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01157","kind":"arxiv","version":3},"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/2305.01157/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":"2305.01157","created_at":"2026-07-05T08:02:43.453153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01157v3","created_at":"2026-07-05T08:02:43.453153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01157","created_at":"2026-07-05T08:02:43.453153+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G74OI4MLDSN","created_at":"2026-07-05T08:02:43.453153+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G74OI4MLDSNQMAT","created_at":"2026-07-05T08:02:43.453153+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G74OI4M","created_at":"2026-07-05T08:02:43.453153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09195","citing_title":"Symbolic and Abstractive Reasoning with Complex Visual Queries","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02054","citing_title":"eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25985","citing_title":"Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN","json":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN.json","graph_json":"https://pith.science/api/pith-number/4G74OI4MLDSNQMATWFWR4CEDSN/graph.json","events_json":"https://pith.science/api/pith-number/4G74OI4MLDSNQMATWFWR4CEDSN/events.json","paper":"https://pith.science/paper/4G74OI4M"},"agent_actions":{"view_html":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN","download_json":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN.json","view_paper":"https://pith.science/paper/4G74OI4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01157&json=true","fetch_graph":"https://pith.science/api/pith-number/4G74OI4MLDSNQMATWFWR4CEDSN/graph.json","fetch_events":"https://pith.science/api/pith-number/4G74OI4MLDSNQMATWFWR4CEDSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN/action/storage_attestation","attest_author":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN/action/author_attestation","sign_citation":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN/action/citation_signature","submit_replication":"https://pith.science/pith/4G74OI4MLDSNQMATWFWR4CEDSN/action/replication_record"}},"created_at":"2026-07-05T08:02:43.453153+00:00","updated_at":"2026-07-05T08:02:43.453153+00:00"}