{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HZ3VNFBXJCYOMODSPYNPHL7LNH","short_pith_number":"pith:HZ3VNFBX","schema_version":"1.0","canonical_sha256":"3e7756943748b0e638727e1af3afeb69e2a36cd76910b872cd438224130dadbe","source":{"kind":"arxiv","id":"1707.06690","version":3},"attestation_state":"computed","paper":{"title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Thien Hoang, Wenhan Xiong, William Yang Wang","submitted_at":"2017-07-20T19:39:23Z","abstract_excerpt":"We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based al"},"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":"1707.06690","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-20T19:39:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dd988be5238f401aaa3fe9c07f1262de09ccb1ad115da6ea98aa02e894ef05d","abstract_canon_sha256":"687d456a88cbf78750d76f5073b413263e1d20632681488aac54ef032dbe8846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:18.785953Z","signature_b64":"9hNeFbhPZmxhWxqeq7aQO/uUhSrdZYL6/g/dbvaB+Nxqik8dv0MtNkPpGgoYDOCS6yIL7loV4frvSAOWPS1kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e7756943748b0e638727e1af3afeb69e2a36cd76910b872cd438224130dadbe","last_reissued_at":"2026-05-18T00:11:18.785248Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:18.785248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Thien Hoang, Wenhan Xiong, William Yang Wang","submitted_at":"2017-07-20T19:39:23Z","abstract_excerpt":"We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06690","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":""},"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":"1707.06690","created_at":"2026-05-18T00:11:18.785367+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06690v3","created_at":"2026-05-18T00:11:18.785367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06690","created_at":"2026-05-18T00:11:18.785367+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZ3VNFBXJCYO","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZ3VNFBXJCYOMODS","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZ3VNFBX","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07422","citing_title":"InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH","json":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH.json","graph_json":"https://pith.science/api/pith-number/HZ3VNFBXJCYOMODSPYNPHL7LNH/graph.json","events_json":"https://pith.science/api/pith-number/HZ3VNFBXJCYOMODSPYNPHL7LNH/events.json","paper":"https://pith.science/paper/HZ3VNFBX"},"agent_actions":{"view_html":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH","download_json":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH.json","view_paper":"https://pith.science/paper/HZ3VNFBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06690&json=true","fetch_graph":"https://pith.science/api/pith-number/HZ3VNFBXJCYOMODSPYNPHL7LNH/graph.json","fetch_events":"https://pith.science/api/pith-number/HZ3VNFBXJCYOMODSPYNPHL7LNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH/action/storage_attestation","attest_author":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH/action/author_attestation","sign_citation":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH/action/citation_signature","submit_replication":"https://pith.science/pith/HZ3VNFBXJCYOMODSPYNPHL7LNH/action/replication_record"}},"created_at":"2026-05-18T00:11:18.785367+00:00","updated_at":"2026-05-18T00:11:18.785367+00:00"}