{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:T6N643E355TMZMJZGARJR4Q4UU","short_pith_number":"pith:T6N643E3","canonical_record":{"source":{"id":"1905.09438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T02:32:34Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"054933206df2263c9f109daa2b1b049e7c2c9b4add268511b02f06ef42c786b2","abstract_canon_sha256":"21b24392521ff63c21247e7a21ebd6e124073bba48e58ed26ca8bf7af0b101cb"},"schema_version":"1.0"},"canonical_sha256":"9f9bee6c9bef66ccb139302298f21ca50378926b5566f7f06dc06d78cb502b32","source":{"kind":"arxiv","id":"1905.09438","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09438","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09438v1","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09438","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"pith_short_12","alias_value":"T6N643E355TM","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"T6N643E355TMZMJZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"T6N643E3","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:T6N643E355TMZMJZGARJR4Q4UU","target":"record","payload":{"canonical_record":{"source":{"id":"1905.09438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T02:32:34Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"054933206df2263c9f109daa2b1b049e7c2c9b4add268511b02f06ef42c786b2","abstract_canon_sha256":"21b24392521ff63c21247e7a21ebd6e124073bba48e58ed26ca8bf7af0b101cb"},"schema_version":"1.0"},"canonical_sha256":"9f9bee6c9bef66ccb139302298f21ca50378926b5566f7f06dc06d78cb502b32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:17.038113Z","signature_b64":"Q6DANp9Ge3QLIc5xV3D6GlOGFr8AvfySJHekwxudBYzaRtRrTRg7G7WVRTPBkTYOFFc3mM7xBZqcNJLtO2gFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9bee6c9bef66ccb139302298f21ca50378926b5566f7f06dc06d78cb502b32","last_reissued_at":"2026-05-17T23:45:17.037522Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:17.037522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.09438","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32AUYorw72771KFHBpHDlDJ/tpsCnRdenPNlzE02Xno3qJR51jVH80FAKTLuz6xXnqaU33UHWKMr5kTQ0Gc0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:42:09.998541Z"},"content_sha256":"92160e385a58c2eca9039199b147326d50f8dec412da56aba48f88976fa150eb","schema_version":"1.0","event_id":"sha256:92160e385a58c2eca9039199b147326d50f8dec412da56aba48f88976fa150eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:T6N643E355TMZMJZGARJR4Q4UU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Alan Blair, Alex Long, Joel Mason, Wei Wang","submitted_at":"2019-05-23T02:32:34Z","abstract_excerpt":"Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning remains particularly challenging. To address MH-QA specifically, we propose a Deep Reinforcement Learning based method capable of learning sequential reasoning across large collections of documents so as to pass a query-aware, fixed-size context subset to existing models for answer extraction. Our method is comprised of two stages: a linker, which decomposes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09438","kind":"arxiv","version":1},"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":"2026-05-17T23:45:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wzwFqTnesbgkrdIYp/8YQPPt4s5m54dCRv4BcxiIgrguxUxBs6PX4gOcUCpBmuqO2g0AFmFuwz5RePhOUHzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:42:09.998966Z"},"content_sha256":"d06228045e645c55a840de6986973a9e522861cb7120cf19233dedd77d4f9c05","schema_version":"1.0","event_id":"sha256:d06228045e645c55a840de6986973a9e522861cb7120cf19233dedd77d4f9c05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6N643E355TMZMJZGARJR4Q4UU/bundle.json","state_url":"https://pith.science/pith/T6N643E355TMZMJZGARJR4Q4UU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6N643E355TMZMJZGARJR4Q4UU/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":"2026-06-09T09:42:09Z","links":{"resolver":"https://pith.science/pith/T6N643E355TMZMJZGARJR4Q4UU","bundle":"https://pith.science/pith/T6N643E355TMZMJZGARJR4Q4UU/bundle.json","state":"https://pith.science/pith/T6N643E355TMZMJZGARJR4Q4UU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6N643E355TMZMJZGARJR4Q4UU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:T6N643E355TMZMJZGARJR4Q4UU","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":"21b24392521ff63c21247e7a21ebd6e124073bba48e58ed26ca8bf7af0b101cb","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T02:32:34Z","title_canon_sha256":"054933206df2263c9f109daa2b1b049e7c2c9b4add268511b02f06ef42c786b2"},"schema_version":"1.0","source":{"id":"1905.09438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09438","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09438v1","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09438","created_at":"2026-05-17T23:45:17Z"},{"alias_kind":"pith_short_12","alias_value":"T6N643E355TM","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"T6N643E355TMZMJZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"T6N643E3","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:d06228045e645c55a840de6986973a9e522861cb7120cf19233dedd77d4f9c05","target":"graph","created_at":"2026-05-17T23:45:17Z","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":"Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning remains particularly challenging. To address MH-QA specifically, we propose a Deep Reinforcement Learning based method capable of learning sequential reasoning across large collections of documents so as to pass a query-aware, fixed-size context subset to existing models for answer extraction. Our method is comprised of two stages: a linker, which decomposes t","authors_text":"Alan Blair, Alex Long, Joel Mason, Wei Wang","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T02:32:34Z","title":"Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09438","kind":"arxiv","version":1},"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":"sha256:92160e385a58c2eca9039199b147326d50f8dec412da56aba48f88976fa150eb","target":"record","created_at":"2026-05-17T23:45:17Z","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":"21b24392521ff63c21247e7a21ebd6e124073bba48e58ed26ca8bf7af0b101cb","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T02:32:34Z","title_canon_sha256":"054933206df2263c9f109daa2b1b049e7c2c9b4add268511b02f06ef42c786b2"},"schema_version":"1.0","source":{"id":"1905.09438","kind":"arxiv","version":1}},"canonical_sha256":"9f9bee6c9bef66ccb139302298f21ca50378926b5566f7f06dc06d78cb502b32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f9bee6c9bef66ccb139302298f21ca50378926b5566f7f06dc06d78cb502b32","first_computed_at":"2026-05-17T23:45:17.037522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:17.037522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q6DANp9Ge3QLIc5xV3D6GlOGFr8AvfySJHekwxudBYzaRtRrTRg7G7WVRTPBkTYOFFc3mM7xBZqcNJLtO2gFCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:17.038113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92160e385a58c2eca9039199b147326d50f8dec412da56aba48f88976fa150eb","sha256:d06228045e645c55a840de6986973a9e522861cb7120cf19233dedd77d4f9c05"],"state_sha256":"56500c735500053964cca360c326214510b0659f6de2502937b87b077db810f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tU535YaWFhCaHwYnqdOGfNldrGr8KAZMWvhoNJciqAoAWAy/7Bi+cqDLMC6qMViCGxZZWFKdgOiyPW8ffB39BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:42:10.001007Z","bundle_sha256":"0b6837046c2cdf44a9549df9c7d59c55154a04ee3e3e1d3270a4bebf5550120d"}}