{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WR7AAS3KD7KAJ45QMSZ6N6FACF","short_pith_number":"pith:WR7AAS3K","schema_version":"1.0","canonical_sha256":"b47e004b6a1fd404f3b064b3e6f8a0115c35f5d3e1dc629b5f90208c1dde42f4","source":{"kind":"arxiv","id":"1607.06275","version":2},"attestation_state":"computed","paper":{"title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Peng Li, Wei Li, Wei Xu, Xuguang Wang, Ying Cao, Zhengyan He","submitted_at":"2016-07-21T11:40:50Z","abstract_excerpt":"While question answering (QA) with neural network, i.e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system. To alleviate this problem, we propose a large scale human annotated real-world QA dataset WebQA with more than 42k questions and 556k evidences. As existing neural QA methods resolve QA either as sequence generation or classification/ranking problem, they face challenges of expensive softmax computation, unseen answers handling or separate candidate answer generation co"},"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":"1607.06275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T11:40:50Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"7b1d95b4ec2aa519e08fe0a63485ffeb684a8111162a1459fb04878cb9309865","abstract_canon_sha256":"e646692593e95c71dd41b9c67896e585e76a45942c37cda41e3c1274ab0f5f65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:28.441217Z","signature_b64":"b7tu9FhCWMP9rCfwOJNlqM0zrObFAcpqN324MK7ZgRnm4b9j1BDSHsyee5rv+TxcUnl4gaSYG/9k/iA+WzjbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47e004b6a1fd404f3b064b3e6f8a0115c35f5d3e1dc629b5f90208c1dde42f4","last_reissued_at":"2026-05-18T01:06:28.440649Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:28.440649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Peng Li, Wei Li, Wei Xu, Xuguang Wang, Ying Cao, Zhengyan He","submitted_at":"2016-07-21T11:40:50Z","abstract_excerpt":"While question answering (QA) with neural network, i.e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system. To alleviate this problem, we propose a large scale human annotated real-world QA dataset WebQA with more than 42k questions and 556k evidences. As existing neural QA methods resolve QA either as sequence generation or classification/ranking problem, they face challenges of expensive softmax computation, unseen answers handling or separate candidate answer generation co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.06275","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1607.06275","created_at":"2026-05-18T01:06:28.440753+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.06275v2","created_at":"2026-05-18T01:06:28.440753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.06275","created_at":"2026-05-18T01:06:28.440753+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR7AAS3KD7KA","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR7AAS3KD7KAJ45Q","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR7AAS3K","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1705.03551","citing_title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF","json":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF.json","graph_json":"https://pith.science/api/pith-number/WR7AAS3KD7KAJ45QMSZ6N6FACF/graph.json","events_json":"https://pith.science/api/pith-number/WR7AAS3KD7KAJ45QMSZ6N6FACF/events.json","paper":"https://pith.science/paper/WR7AAS3K"},"agent_actions":{"view_html":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF","download_json":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF.json","view_paper":"https://pith.science/paper/WR7AAS3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.06275&json=true","fetch_graph":"https://pith.science/api/pith-number/WR7AAS3KD7KAJ45QMSZ6N6FACF/graph.json","fetch_events":"https://pith.science/api/pith-number/WR7AAS3KD7KAJ45QMSZ6N6FACF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF/action/storage_attestation","attest_author":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF/action/author_attestation","sign_citation":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF/action/citation_signature","submit_replication":"https://pith.science/pith/WR7AAS3KD7KAJ45QMSZ6N6FACF/action/replication_record"}},"created_at":"2026-05-18T01:06:28.440753+00:00","updated_at":"2026-05-18T01:06:28.440753+00:00"}