{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RKJXV6YPJBYSJYC7FHMNEBYLSZ","short_pith_number":"pith:RKJXV6YP","schema_version":"1.0","canonical_sha256":"8a937afb0f487124e05f29d8d2070b96755b3865c17ecc09e1de6dc93f7fddf7","source":{"kind":"arxiv","id":"2405.01649","version":4},"attestation_state":"computed","paper":{"title":"Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Guojia Wan, Liang Ding, Tianle Xia, Yibing Zhan","submitted_at":"2024-05-02T18:12:08Z","abstract_excerpt":"Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary fi"},"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":"2405.01649","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T18:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"b04efcc2eacc217f166eec77cff791e6bfce3586f0701871582c8f034d47f0ae","abstract_canon_sha256":"3145df28b63a6c0ee8135c0c457d2f88a7784c0224bb0920da22454699c34f36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:59.444550Z","signature_b64":"No4lWcVwlbIE3f5hBsswndMFVvP6nH1lbow1S9QPu5HtnDAkf9Sg3FyPu/v2HedzC1oygnzsSsLv3GqgUZ01Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a937afb0f487124e05f29d8d2070b96755b3865c17ecc09e1de6dc93f7fddf7","last_reissued_at":"2026-07-05T10:21:59.444028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:59.444028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Guojia Wan, Liang Ding, Tianle Xia, Yibing Zhan","submitted_at":"2024-05-02T18:12:08Z","abstract_excerpt":"Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01649","kind":"arxiv","version":4},"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/2405.01649/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":"2405.01649","created_at":"2026-07-05T10:21:59.444095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01649v4","created_at":"2026-07-05T10:21:59.444095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01649","created_at":"2026-07-05T10:21:59.444095+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKJXV6YPJBYS","created_at":"2026-07-05T10:21:59.444095+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKJXV6YPJBYSJYC7","created_at":"2026-07-05T10:21:59.444095+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKJXV6YP","created_at":"2026-07-05T10:21:59.444095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01129","citing_title":"Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ","json":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ.json","graph_json":"https://pith.science/api/pith-number/RKJXV6YPJBYSJYC7FHMNEBYLSZ/graph.json","events_json":"https://pith.science/api/pith-number/RKJXV6YPJBYSJYC7FHMNEBYLSZ/events.json","paper":"https://pith.science/paper/RKJXV6YP"},"agent_actions":{"view_html":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ","download_json":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ.json","view_paper":"https://pith.science/paper/RKJXV6YP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01649&json=true","fetch_graph":"https://pith.science/api/pith-number/RKJXV6YPJBYSJYC7FHMNEBYLSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RKJXV6YPJBYSJYC7FHMNEBYLSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ/action/storage_attestation","attest_author":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ/action/author_attestation","sign_citation":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ/action/citation_signature","submit_replication":"https://pith.science/pith/RKJXV6YPJBYSJYC7FHMNEBYLSZ/action/replication_record"}},"created_at":"2026-07-05T10:21:59.444095+00:00","updated_at":"2026-07-05T10:21:59.444095+00:00"}