{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NY3DIPRXSGJYY4LRT7XH2FJHBI","short_pith_number":"pith:NY3DIPRX","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"},"canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","source":{"kind":"arxiv","id":"1808.10568","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10568","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10568v2","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10568","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"NY3DIPRXSGJY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NY3DIPRXSGJYY4LR","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NY3DIPRX","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NY3DIPRXSGJYY4LRT7XH2FJHBI","target":"record","payload":{"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"},"canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","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"},"source_kind":"arxiv","source_id":"1808.10568","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFAKI+9T9buS2oe+iGNtYJnbA8pV4Jg2VmI8E8LttyBrA+t2S7B5cgLuL1phLpykAIKUI1AY3QQfNfW6fep7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:22:53.643137Z"},"content_sha256":"2c73ff43dcccd1e03b3992c0880075a3131649f31ce1352b3fd3bc14c780d395","schema_version":"1.0","event_id":"sha256:2c73ff43dcccd1e03b3992c0880075a3131649f31ce1352b3fd3bc14c780d395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NY3DIPRXSGJYY4LRT7XH2FJHBI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/MhPXqVA1x1vYb2Iy0jHEWnPk7T+oj/hmA7HBydAmsjH3n1nKuntfEla2ba4KV5CG9VjoceGmEZWlEvi5pdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:22:53.643515Z"},"content_sha256":"555e2e28a67e9c52e7ed34ba39fe7e3dc6e86748b8d7780de1d4342a6961208e","schema_version":"1.0","event_id":"sha256:555e2e28a67e9c52e7ed34ba39fe7e3dc6e86748b8d7780de1d4342a6961208e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/bundle.json","state_url":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/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":"2026-05-27T19:22:53Z","links":{"resolver":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI","bundle":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/bundle.json","state":"https://pith.science/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NY3DIPRXSGJYY4LRT7XH2FJHBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NY3DIPRXSGJYY4LRT7XH2FJHBI","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":"fb18f2b42bfeba556a40b60c2593894a0639b6ea388ac7c6987f0951e1758d17","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-08-31T01:55:09Z","title_canon_sha256":"851dfe73de1707350ab6ee338b1dfbccb052f6657d9d950998b8515fcb49cc97"},"schema_version":"1.0","source":{"id":"1808.10568","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10568","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10568v2","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10568","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"NY3DIPRXSGJY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NY3DIPRXSGJYY4LR","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NY3DIPRX","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:555e2e28a67e9c52e7ed34ba39fe7e3dc6e86748b8d7780de1d4342a6961208e","target":"graph","created_at":"2026-05-18T00:05:55Z","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":"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 ","authors_text":"Caiming Xiong, Richard Socher, Xi Victoria Lin","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-08-31T01:55:09Z","title":"Multi-Hop Knowledge Graph Reasoning with Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10568","kind":"arxiv","version":2},"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":"sha256:2c73ff43dcccd1e03b3992c0880075a3131649f31ce1352b3fd3bc14c780d395","target":"record","created_at":"2026-05-18T00:05:55Z","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":"fb18f2b42bfeba556a40b60c2593894a0639b6ea388ac7c6987f0951e1758d17","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-08-31T01:55:09Z","title_canon_sha256":"851dfe73de1707350ab6ee338b1dfbccb052f6657d9d950998b8515fcb49cc97"},"schema_version":"1.0","source":{"id":"1808.10568","kind":"arxiv","version":2}},"canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e36343e3791938c71719fee7d15270a2689bb4f8417be6b71ffd31b5e379553","first_computed_at":"2026-05-18T00:05:55.698336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:55.698336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2UbLwhTxkKwUmMVX+YqfCTIo+VSxEXpoYXq30muhELQE5Nz/YAjuA6ZFaYUDVS9tLhMHBUozys3EOiFDFWDIAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:55.698991Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10568","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c73ff43dcccd1e03b3992c0880075a3131649f31ce1352b3fd3bc14c780d395","sha256:555e2e28a67e9c52e7ed34ba39fe7e3dc6e86748b8d7780de1d4342a6961208e"],"state_sha256":"691bc5d06e9b7ed83c4e8e9b3310a4c1b9773fe48537441c1dbce11ede4c705c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5NJckmOigo4fzKYw5FrIwLFRNbtDDno5Hu5nLpfyRzDmK7i7st531Sbpr3t5pfkL3R0rnAnnpBsJMpBhBSYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:22:53.646359Z","bundle_sha256":"208b1de1139fe382b56f020985c8075cb5675e9ea04077d96214a12d671a8761"}}