{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JCFUWBRSBNOQG4BGZ2AKHM73QU","short_pith_number":"pith:JCFUWBRS","schema_version":"1.0","canonical_sha256":"488b4b06320b5d037026ce80a3b3fb852099eb853056e3072ccb4a465dab8680","source":{"kind":"arxiv","id":"1607.04423","version":4},"attestation_state":"computed","paper":{"title":"Attention-over-Attention Neural Networks for Reading Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Guoping Hu, Shijin Wang, Si Wei, Ting Liu, Yiming Cui, Zhipeng Chen","submitted_at":"2016-07-15T09:10:11Z","abstract_excerpt":"Cloze-style queries are representative problems in reading comprehension. Over the past few months, we have seen much progress that utilizing neural network approach to solve Cloze-style questions. In this paper, we present a novel model called attention-over-attention reader for the Cloze-style reading comprehension task. Our model aims to place another attention mechanism over the document-level attention, and induces \"attended attention\" for final predictions. Unlike the previous works, our neural network model requires less pre-defined hyper-parameters and uses an elegant architecture for "},"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":"1607.04423","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-07-15T09:10:11Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"ef40e1d75134661fc902ef619d4e7245be1078af44dcc88c16c205a874b2e508","abstract_canon_sha256":"890dc0bf965b92217735153b466b20ca14035123d428dcfb4ec24531175fc125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:33.238085Z","signature_b64":"W0+vRCO0GRQrfYzRpZnew8Jj3PEcSuR61CJCkWHnBSIjkp+wRFhoJwQxN25F3wBYiaG5uGs8eklQklkER82HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488b4b06320b5d037026ce80a3b3fb852099eb853056e3072ccb4a465dab8680","last_reissued_at":"2026-07-05T00:00:33.237587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:33.237587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-over-Attention Neural Networks for Reading Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Guoping Hu, Shijin Wang, Si Wei, Ting Liu, Yiming Cui, Zhipeng Chen","submitted_at":"2016-07-15T09:10:11Z","abstract_excerpt":"Cloze-style queries are representative problems in reading comprehension. Over the past few months, we have seen much progress that utilizing neural network approach to solve Cloze-style questions. In this paper, we present a novel model called attention-over-attention reader for the Cloze-style reading comprehension task. Our model aims to place another attention mechanism over the document-level attention, and induces \"attended attention\" for final predictions. Unlike the previous works, our neural network model requires less pre-defined hyper-parameters and uses an elegant architecture for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04423","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1607.04423/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1607.04423","created_at":"2026-07-05T00:00:33.237650+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.04423v4","created_at":"2026-07-05T00:00:33.237650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04423","created_at":"2026-07-05T00:00:33.237650+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCFUWBRSBNOQ","created_at":"2026-07-05T00:00:33.237650+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCFUWBRSBNOQG4BG","created_at":"2026-07-05T00:00:33.237650+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCFUWBRS","created_at":"2026-07-05T00:00:33.237650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.08570","citing_title":"Hindi Question Generation Using Dependency Structures","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU","json":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU.json","graph_json":"https://pith.science/api/pith-number/JCFUWBRSBNOQG4BGZ2AKHM73QU/graph.json","events_json":"https://pith.science/api/pith-number/JCFUWBRSBNOQG4BGZ2AKHM73QU/events.json","paper":"https://pith.science/paper/JCFUWBRS"},"agent_actions":{"view_html":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU","download_json":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU.json","view_paper":"https://pith.science/paper/JCFUWBRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.04423&json=true","fetch_graph":"https://pith.science/api/pith-number/JCFUWBRSBNOQG4BGZ2AKHM73QU/graph.json","fetch_events":"https://pith.science/api/pith-number/JCFUWBRSBNOQG4BGZ2AKHM73QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU/action/storage_attestation","attest_author":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU/action/author_attestation","sign_citation":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU/action/citation_signature","submit_replication":"https://pith.science/pith/JCFUWBRSBNOQG4BGZ2AKHM73QU/action/replication_record"}},"created_at":"2026-07-05T00:00:33.237650+00:00","updated_at":"2026-07-05T00:00:33.237650+00:00"}