{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CO5QXQ46SB6BW6FX4XJA2DW2O6","short_pith_number":"pith:CO5QXQ46","schema_version":"1.0","canonical_sha256":"13bb0bc39e907c1b78b7e5d20d0eda77b9d0e24b9a20a4a068dbe95a18213c4b","source":{"kind":"arxiv","id":"2005.02557","version":2},"attestation_state":"computed","paper":{"title":"Crossing Variational Autoencoders for Answer Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Lingfei Wu, Meng Jiang, Qingkai Zeng, Shu Tao, Wenhao Yu, Yu Deng","submitted_at":"2020-05-06T01:59:13Z","abstract_excerpt":"Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semant"},"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":"2005.02557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-06T01:59:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f46d75600b0ab37f621abf607c5bba26817c0a9271bdff5ba75d861ea84a6f82","abstract_canon_sha256":"1aa07e884f9523adaf09d82b6424b2150c86f90a29daa50daabaaacf580fcd31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:14.970415Z","signature_b64":"zYmp2+tb0PN5Ao/wkEf1iMpJDanYSQdHZ/L9gmRk/Ry+WZjNlwD/EQZj1sX4BvMZh7e4x3dJ7FUEEjvjc2qkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13bb0bc39e907c1b78b7e5d20d0eda77b9d0e24b9a20a4a068dbe95a18213c4b","last_reissued_at":"2026-07-05T01:16:14.969863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:14.969863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crossing Variational Autoencoders for Answer Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Lingfei Wu, Meng Jiang, Qingkai Zeng, Shu Tao, Wenhao Yu, Yu Deng","submitted_at":"2020-05-06T01:59:13Z","abstract_excerpt":"Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02557","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.02557/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":"2005.02557","created_at":"2026-07-05T01:16:14.969925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.02557v2","created_at":"2026-07-05T01:16:14.969925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02557","created_at":"2026-07-05T01:16:14.969925+00:00"},{"alias_kind":"pith_short_12","alias_value":"CO5QXQ46SB6B","created_at":"2026-07-05T01:16:14.969925+00:00"},{"alias_kind":"pith_short_16","alias_value":"CO5QXQ46SB6BW6FX","created_at":"2026-07-05T01:16:14.969925+00:00"},{"alias_kind":"pith_short_8","alias_value":"CO5QXQ46","created_at":"2026-07-05T01:16:14.969925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6","json":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6.json","graph_json":"https://pith.science/api/pith-number/CO5QXQ46SB6BW6FX4XJA2DW2O6/graph.json","events_json":"https://pith.science/api/pith-number/CO5QXQ46SB6BW6FX4XJA2DW2O6/events.json","paper":"https://pith.science/paper/CO5QXQ46"},"agent_actions":{"view_html":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6","download_json":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6.json","view_paper":"https://pith.science/paper/CO5QXQ46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.02557&json=true","fetch_graph":"https://pith.science/api/pith-number/CO5QXQ46SB6BW6FX4XJA2DW2O6/graph.json","fetch_events":"https://pith.science/api/pith-number/CO5QXQ46SB6BW6FX4XJA2DW2O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6/action/storage_attestation","attest_author":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6/action/author_attestation","sign_citation":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6/action/citation_signature","submit_replication":"https://pith.science/pith/CO5QXQ46SB6BW6FX4XJA2DW2O6/action/replication_record"}},"created_at":"2026-07-05T01:16:14.969925+00:00","updated_at":"2026-07-05T01:16:14.969925+00:00"}