{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:K25FN3EPZFVWY77MGUWC5CIXLQ","short_pith_number":"pith:K25FN3EP","schema_version":"1.0","canonical_sha256":"56ba56ec8fc96b6c7fec352c2e89175c17b23e40fce9cc357add2e4e72a3285b","source":{"kind":"arxiv","id":"2010.04029","version":2},"attestation_state":"computed","paper":{"title":"RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jian Tang, Junkun Chen, Louis-Pascal Xhonneux, Meng Qu, Yoshua Bengio","submitted_at":"2020-10-08T14:47:02Z","abstract_excerpt":"This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simul"},"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":"2010.04029","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-08T14:47:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96f6002ddebe88cb126a59863211f014947a0ba484de323e780a63f6f08ff739","abstract_canon_sha256":"d82a19ebf5d83a93ed0d7614195fa7f1c2131fda4772038b7b68bbadcaa57713"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:22.820253Z","signature_b64":"Eb+FW2DhofzbWrkKI+9PC9BpOLvOtpKTw1d0o3Tp7zVVLfjcEV/i+16C3hIFovwlB07LaIVloirP4fnV2XgXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ba56ec8fc96b6c7fec352c2e89175c17b23e40fce9cc357add2e4e72a3285b","last_reissued_at":"2026-07-05T02:58:22.819873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:22.819873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jian Tang, Junkun Chen, Louis-Pascal Xhonneux, Meng Qu, Yoshua Bengio","submitted_at":"2020-10-08T14:47:02Z","abstract_excerpt":"This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04029","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/2010.04029/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":"2010.04029","created_at":"2026-07-05T02:58:22.819920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04029v2","created_at":"2026-07-05T02:58:22.819920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04029","created_at":"2026-07-05T02:58:22.819920+00:00"},{"alias_kind":"pith_short_12","alias_value":"K25FN3EPZFVW","created_at":"2026-07-05T02:58:22.819920+00:00"},{"alias_kind":"pith_short_16","alias_value":"K25FN3EPZFVWY77M","created_at":"2026-07-05T02:58:22.819920+00:00"},{"alias_kind":"pith_short_8","alias_value":"K25FN3EP","created_at":"2026-07-05T02:58:22.819920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.13663","citing_title":"Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19644","citing_title":"Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies","ref_index":21,"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":190,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ","json":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ.json","graph_json":"https://pith.science/api/pith-number/K25FN3EPZFVWY77MGUWC5CIXLQ/graph.json","events_json":"https://pith.science/api/pith-number/K25FN3EPZFVWY77MGUWC5CIXLQ/events.json","paper":"https://pith.science/paper/K25FN3EP"},"agent_actions":{"view_html":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ","download_json":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ.json","view_paper":"https://pith.science/paper/K25FN3EP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04029&json=true","fetch_graph":"https://pith.science/api/pith-number/K25FN3EPZFVWY77MGUWC5CIXLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/K25FN3EPZFVWY77MGUWC5CIXLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ/action/storage_attestation","attest_author":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ/action/author_attestation","sign_citation":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ/action/citation_signature","submit_replication":"https://pith.science/pith/K25FN3EPZFVWY77MGUWC5CIXLQ/action/replication_record"}},"created_at":"2026-07-05T02:58:22.819920+00:00","updated_at":"2026-07-05T02:58:22.819920+00:00"}