{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LGMRGDXNT76ESUB6GKB6Y5HUCN","short_pith_number":"pith:LGMRGDXN","schema_version":"1.0","canonical_sha256":"5999130eed9ffc49503e3283ec74f41348e32b0988d346a76daa450fce9c1349","source":{"kind":"arxiv","id":"1705.02798","version":6},"attestation_state":"computed","paper":{"title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Minghao Hu, Ming Zhou, Xipeng Qiu, Yuxing Peng, Zhen Huang","submitted_at":"2017-05-08T09:43:05Z","abstract_excerpt":"In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more "},"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":"1705.02798","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-08T09:43:05Z","cross_cats_sorted":[],"title_canon_sha256":"b7c0021ebbbd45b3d5ff79a06fdd93dc1a1f0dcb721b9a7f86631bff2662cd88","abstract_canon_sha256":"f5f9426c1e4bd23a41d8746758efb821649e0e35149e578bf8e17f97fae99214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.852857Z","signature_b64":"ONv7SeQ9FxKmToJRhEiIcuFCBrGrbQY2XGpA8s/ESMA5hKZt7j7R7ddn3/kYl42/hW1ZkiuVYJCLfbsPisBCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5999130eed9ffc49503e3283ec74f41348e32b0988d346a76daa450fce9c1349","last_reissued_at":"2026-05-18T00:14:06.852463Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.852463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Minghao Hu, Ming Zhou, Xipeng Qiu, Yuxing Peng, Zhen Huang","submitted_at":"2017-05-08T09:43:05Z","abstract_excerpt":"In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02798","kind":"arxiv","version":6},"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":"1705.02798","created_at":"2026-05-18T00:14:06.852525+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02798v6","created_at":"2026-05-18T00:14:06.852525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02798","created_at":"2026-05-18T00:14:06.852525+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGMRGDXNT76E","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGMRGDXNT76ESUB6","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGMRGDXN","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":229,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN","json":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN.json","graph_json":"https://pith.science/api/pith-number/LGMRGDXNT76ESUB6GKB6Y5HUCN/graph.json","events_json":"https://pith.science/api/pith-number/LGMRGDXNT76ESUB6GKB6Y5HUCN/events.json","paper":"https://pith.science/paper/LGMRGDXN"},"agent_actions":{"view_html":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN","download_json":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN.json","view_paper":"https://pith.science/paper/LGMRGDXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02798&json=true","fetch_graph":"https://pith.science/api/pith-number/LGMRGDXNT76ESUB6GKB6Y5HUCN/graph.json","fetch_events":"https://pith.science/api/pith-number/LGMRGDXNT76ESUB6GKB6Y5HUCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN/action/storage_attestation","attest_author":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN/action/author_attestation","sign_citation":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN/action/citation_signature","submit_replication":"https://pith.science/pith/LGMRGDXNT76ESUB6GKB6Y5HUCN/action/replication_record"}},"created_at":"2026-05-18T00:14:06.852525+00:00","updated_at":"2026-05-18T00:14:06.852525+00:00"}