{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7QXHDY6L52TXGRPA6XVCAQJ7DJ","short_pith_number":"pith:7QXHDY6L","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"},"canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","source":{"kind":"arxiv","id":"1802.04394","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04394","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04394v5","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04394","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"pith_short_12","alias_value":"7QXHDY6L52TX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7QXHDY6L52TXGRPA","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7QXHDY6L","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7QXHDY6L52TXGRPA6XVCAQJ7DJ","target":"record","payload":{"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"},"canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","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"},"source_kind":"arxiv","source_id":"1802.04394","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cGfK3VXtqgHIAkLUb2qarXMvAZh3SlhiooNXR9NOX2RRaT3EnqjELBvWM2HdDeI1nrWUB0uLjEVmWooFlSCLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:57:24.446087Z"},"content_sha256":"41fc1e364bd5e891b2c9a2b5345336d0004ed0daba42e38ca362abbf59b615ff","schema_version":"1.0","event_id":"sha256:41fc1e364bd5e891b2c9a2b5345336d0004ed0daba42e38ca362abbf59b615ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7QXHDY6L52TXGRPA6XVCAQJ7DJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zetQlvceOQ37VXbjUPzfBWUG4wn6E9EmLynklUZyyli+QOb+PDOc0opUTMWNY5U3M50UhjDGzNevLBgyYYWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:57:24.446448Z"},"content_sha256":"3b41a63ae2fbc4159197f5411ecd91e5dbfd125a69dc8aa492ff66298d8b4256","schema_version":"1.0","event_id":"sha256:3b41a63ae2fbc4159197f5411ecd91e5dbfd125a69dc8aa492ff66298d8b4256"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/bundle.json","state_url":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T00:57:24Z","links":{"resolver":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ","bundle":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/bundle.json","state":"https://pith.science/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QXHDY6L52TXGRPA6XVCAQJ7DJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7QXHDY6L52TXGRPA6XVCAQJ7DJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"91154231c2763401f797a787dee1131e7f77a2789c84ea45328db236d44966de","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T23:27:23Z","title_canon_sha256":"cb734d49f02ce24fa807c62047ef52d18969fbba89ab6da9e7b3742025fe2b37"},"schema_version":"1.0","source":{"id":"1802.04394","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04394","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04394v5","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04394","created_at":"2026-05-17T23:58:05Z"},{"alias_kind":"pith_short_12","alias_value":"7QXHDY6L52TX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7QXHDY6L52TXGRPA","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7QXHDY6L","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:3b41a63ae2fbc4159197f5411ecd91e5dbfd125a69dc8aa492ff66298d8b4256","target":"graph","created_at":"2026-05-17T23:58:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Jianfeng Gao, Jianshu Chen, Po-Sen Huang, Yelong Shen, Yuqing Guo","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T23:27:23Z","title":"M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04394","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41fc1e364bd5e891b2c9a2b5345336d0004ed0daba42e38ca362abbf59b615ff","target":"record","created_at":"2026-05-17T23:58:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"91154231c2763401f797a787dee1131e7f77a2789c84ea45328db236d44966de","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-12T23:27:23Z","title_canon_sha256":"cb734d49f02ce24fa807c62047ef52d18969fbba89ab6da9e7b3742025fe2b37"},"schema_version":"1.0","source":{"id":"1802.04394","kind":"arxiv","version":5}},"canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc2e71e3cbeea77345e0f5ea20413f1a560b54636de0630553588b1bb1fe429d","first_computed_at":"2026-05-17T23:58:05.162996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:05.162996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/bsxEMyU1IsqjwLoZqdCbS4Zd0n116fVTJSssrGswZaXTiJODaqTO9VaoPTlayjVT8SeMINWTNPslrCztvxtAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:05.163407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04394","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41fc1e364bd5e891b2c9a2b5345336d0004ed0daba42e38ca362abbf59b615ff","sha256:3b41a63ae2fbc4159197f5411ecd91e5dbfd125a69dc8aa492ff66298d8b4256"],"state_sha256":"cd49a818faf396f7fbf81483c1afcf0deded4a5af97bdc15d23605bd30baeeb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qsfzA8RCQCPIHWNbLRAwAKYCG+i+8dJKbqDKD9VJLdPV+wNuNuHqsrpCqHvQFJ3n+/4eSSJlxzaA1xzOjeh0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:57:24.448448Z","bundle_sha256":"6123b3d3ee501b6721d43d560f547c20643369b91ba0387751c36980aa15ffe4"}}