{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CE5JYSPOYQC3NJCQ2ZOTAA2OXV","short_pith_number":"pith:CE5JYSPO","schema_version":"1.0","canonical_sha256":"113a9c49eec405b6a450d65d30034ebd5fc02dd945748d84bc0605b335e21825","source":{"kind":"arxiv","id":"2501.14661","version":1},"attestation_state":"computed","paper":{"title":"Neural-Symbolic Message Passing with Dynamic Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongzhi Zhang, Junhao Zheng, Qianli Ma, Zhiping Peng","submitted_at":"2025-01-24T17:30:17Z","abstract_excerpt":"Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs) is a challenging task. Recently, a line of message-passing-based research has been proposed to solve CQA. However, they perform unsatisfactorily on negative queries and fail to address the noisy messages between variable nodes in the query graph. Moreover, they offer little interpretability and require complex query data and resource-intensive training. In this paper, we propose a Neural-Symbolic Message Passing (NSMP) framework based on pre-trained neural link predictors. By introducing symbolic reasoning and fuzzy logic, NS"},"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":"2501.14661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T17:30:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a3206d5845113af065d286bc2641501a1f475cc676db89a8beee2ae51f5b27c","abstract_canon_sha256":"2acbe748e0ef0dbfb8476ae9f6c18eae9dd6d93315d5d8df36c56935401a61dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:04.021619Z","signature_b64":"ggm/+9TDNw6G5166CYKdQF6caBPhOSl8GHEGkko84K99CHKKWJSuJ9bmwzI55GAsO3mFzLbEoL61tR2a/c4vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"113a9c49eec405b6a450d65d30034ebd5fc02dd945748d84bc0605b335e21825","last_reissued_at":"2026-07-05T10:05:04.021216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:04.021216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Symbolic Message Passing with Dynamic Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongzhi Zhang, Junhao Zheng, Qianli Ma, Zhiping Peng","submitted_at":"2025-01-24T17:30:17Z","abstract_excerpt":"Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs) is a challenging task. Recently, a line of message-passing-based research has been proposed to solve CQA. However, they perform unsatisfactorily on negative queries and fail to address the noisy messages between variable nodes in the query graph. Moreover, they offer little interpretability and require complex query data and resource-intensive training. In this paper, we propose a Neural-Symbolic Message Passing (NSMP) framework based on pre-trained neural link predictors. By introducing symbolic reasoning and fuzzy logic, NS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14661","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/2501.14661/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":"2501.14661","created_at":"2026-07-05T10:05:04.021273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14661v1","created_at":"2026-07-05T10:05:04.021273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14661","created_at":"2026-07-05T10:05:04.021273+00:00"},{"alias_kind":"pith_short_12","alias_value":"CE5JYSPOYQC3","created_at":"2026-07-05T10:05:04.021273+00:00"},{"alias_kind":"pith_short_16","alias_value":"CE5JYSPOYQC3NJCQ","created_at":"2026-07-05T10:05:04.021273+00:00"},{"alias_kind":"pith_short_8","alias_value":"CE5JYSPO","created_at":"2026-07-05T10:05:04.021273+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/CE5JYSPOYQC3NJCQ2ZOTAA2OXV","json":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV.json","graph_json":"https://pith.science/api/pith-number/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/graph.json","events_json":"https://pith.science/api/pith-number/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/events.json","paper":"https://pith.science/paper/CE5JYSPO"},"agent_actions":{"view_html":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV","download_json":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV.json","view_paper":"https://pith.science/paper/CE5JYSPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14661&json=true","fetch_graph":"https://pith.science/api/pith-number/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/graph.json","fetch_events":"https://pith.science/api/pith-number/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/action/storage_attestation","attest_author":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/action/author_attestation","sign_citation":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/action/citation_signature","submit_replication":"https://pith.science/pith/CE5JYSPOYQC3NJCQ2ZOTAA2OXV/action/replication_record"}},"created_at":"2026-07-05T10:05:04.021273+00:00","updated_at":"2026-07-05T10:05:04.021273+00:00"}