{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NY3DIPRXSGJYY4LRT7XH2FJHBI","short_pith_number":"pith:NY3DIPRX","schema_version":"1.0","canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","source":{"kind":"arxiv","id":"1808.10568","version":2},"attestation_state":"computed","paper":{"title":"Multi-Hop Knowledge Graph Reasoning with Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Richard Socher, Xi Victoria Lin","submitted_at":"2018-08-31T01:55:09Z","abstract_excerpt":"Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the "},"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":"1808.10568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-08-31T01:55:09Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"851dfe73de1707350ab6ee338b1dfbccb052f6657d9d950998b8515fcb49cc97","abstract_canon_sha256":"fb18f2b42bfeba556a40b60c2593894a0639b6ea388ac7c6987f0951e1758d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:55.698991Z","signature_b64":"2UbLwhTxkKwUmMVX+YqfCTIo+VSxEXpoYXq30muhELQE5Nz/YAjuA6ZFaYUDVS9tLhMHBUozys3EOiFDFWDIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","last_reissued_at":"2026-05-18T00:05:55.698336Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:55.698336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Hop Knowledge Graph Reasoning with Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Richard Socher, Xi Victoria Lin","submitted_at":"2018-08-31T01:55:09Z","abstract_excerpt":"Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10568","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":""},"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":"1808.10568","created_at":"2026-05-18T00:05:55.698445+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10568v2","created_at":"2026-05-18T00:05:55.698445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10568","created_at":"2026-05-18T00:05:55.698445+00:00"},{"alias_kind":"pith_short_12","alias_value":"NY3DIPRXSGJY","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NY3DIPRXSGJYY4LR","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NY3DIPRX","created_at":"2026-05-18T12:32:40.477152+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/NY3DIPRXSGJYY4LRT7XH2FJHBI","json":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI.json","graph_json":"https://pith.science/api/pith-number/NY3DIPRXSGJYY4LRT7XH2FJHBI/graph.json","events_json":"https://pith.science/api/pith-number/NY3DIPRXSGJYY4LRT7XH2FJHBI/events.json","paper":"https://pith.science/paper/NY3DIPRX"},"agent_actions":{"view_html":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI","download_json":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI.json","view_paper":"https://pith.science/paper/NY3DIPRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10568&json=true","fetch_graph":"https://pith.science/api/pith-number/NY3DIPRXSGJYY4LRT7XH2FJHBI/graph.json","fetch_events":"https://pith.science/api/pith-number/NY3DIPRXSGJYY4LRT7XH2FJHBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/action/storage_attestation","attest_author":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/action/author_attestation","sign_citation":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/action/citation_signature","submit_replication":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/action/replication_record"}},"created_at":"2026-05-18T00:05:55.698445+00:00","updated_at":"2026-05-18T00:05:55.698445+00:00"}