{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7QXHDY6L52TXGRPA6XVCAQJ7DJ","short_pith_number":"pith:7QXHDY6L","schema_version":"1.0","canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","source":{"kind":"arxiv","id":"1802.04394","version":5},"attestation_state":"computed","paper":{"title":"M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jianfeng Gao, Jianshu Chen, Po-Sen Huang, Yelong Shen, Yuqing Guo","submitted_at":"2018-02-12T23:27:23Z","abstract_excerpt":"Learning to walk over a graph towards a target node for a given query and a source node is an important problem in applications such as knowledge base completion (KBC). It can be formulated as a reinforcement learning (RL) problem with a known state transition model. To overcome the challenge of sparse rewards, we develop a graph-walking agent called M-Walk, which consists of a deep recurrent neural network (RNN) and Monte Carlo Tree Search (MCTS). The RNN encodes the state (i.e., history of the walked path) and maps it separately to a policy and Q-values. In order to effectively train the age"},"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":"1802.04394","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T23:27:23Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cb734d49f02ce24fa807c62047ef52d18969fbba89ab6da9e7b3742025fe2b37","abstract_canon_sha256":"91154231c2763401f797a787dee1131e7f77a2789c84ea45328db236d44966de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:05.163407Z","signature_b64":"/bsxEMyU1IsqjwLoZqdCbS4Zd0n116fVTJSssrGswZaXTiJODaqTO9VaoPTlayjVT8SeMINWTNPslrCztvxtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","last_reissued_at":"2026-05-17T23:58:05.162996Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:05.162996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jianfeng Gao, Jianshu Chen, Po-Sen Huang, Yelong Shen, Yuqing Guo","submitted_at":"2018-02-12T23:27:23Z","abstract_excerpt":"Learning to walk over a graph towards a target node for a given query and a source node is an important problem in applications such as knowledge base completion (KBC). It can be formulated as a reinforcement learning (RL) problem with a known state transition model. To overcome the challenge of sparse rewards, we develop a graph-walking agent called M-Walk, which consists of a deep recurrent neural network (RNN) and Monte Carlo Tree Search (MCTS). The RNN encodes the state (i.e., history of the walked path) and maps it separately to a policy and Q-values. In order to effectively train the age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04394","kind":"arxiv","version":5},"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":"1802.04394","created_at":"2026-05-17T23:58:05.163059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04394v5","created_at":"2026-05-17T23:58:05.163059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04394","created_at":"2026-05-17T23:58:05.163059+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QXHDY6L52TX","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QXHDY6L52TXGRPA","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QXHDY6L","created_at":"2026-05-18T12:32:11.075285+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/7QXHDY6L52TXGRPA6XVCAQJ7DJ","json":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ.json","graph_json":"https://pith.science/api/pith-number/7QXHDY6L52TXGRPA6XVCAQJ7DJ/graph.json","events_json":"https://pith.science/api/pith-number/7QXHDY6L52TXGRPA6XVCAQJ7DJ/events.json","paper":"https://pith.science/paper/7QXHDY6L"},"agent_actions":{"view_html":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ","download_json":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ.json","view_paper":"https://pith.science/paper/7QXHDY6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04394&json=true","fetch_graph":"https://pith.science/api/pith-number/7QXHDY6L52TXGRPA6XVCAQJ7DJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7QXHDY6L52TXGRPA6XVCAQJ7DJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/action/storage_attestation","attest_author":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/action/author_attestation","sign_citation":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/action/citation_signature","submit_replication":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/action/replication_record"}},"created_at":"2026-05-17T23:58:05.163059+00:00","updated_at":"2026-05-17T23:58:05.163059+00:00"}