{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SEWTXNUNVHVEZKLEVDB2QRSG2Z","short_pith_number":"pith:SEWTXNUN","schema_version":"1.0","canonical_sha256":"912d3bb68da9ea4ca964a8c3a84646d66fea4b3451b1c06f3fcfa29436a81ec5","source":{"kind":"arxiv","id":"1511.06426","version":4},"attestation_state":"computed","paper":{"title":"Reasoning in Vector Space: An Exploratory Study of Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Li Deng, Moontae Lee, Paul Smolensky, Wen-tau Yih, Xiaodong He","submitted_at":"2015-11-19T22:30:10Z","abstract_excerpt":"Question answering tasks have shown remarkable progress with distributed vector representation. In this paper, we investigate the recently proposed Facebook bAbI tasks which consist of twenty different categories of questions that require complex reasoning. Because the previous work on bAbI are all end-to-end models, errors could come from either an imperfect understanding of semantics or in certain steps of the reasoning. For clearer analysis, we propose two vector space models inspired by Tensor Product Representation (TPR) to perform knowledge encoding and logical reasoning based on common-"},"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":"1511.06426","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-19T22:30:10Z","cross_cats_sorted":[],"title_canon_sha256":"595d752dfc0c140cdb1e74559115df770edacedd78a2983ac4fbbccde3715e05","abstract_canon_sha256":"d6a9faf173fa963ded5deba826acc0fdaa299b0dae85124b07fd46f983e28ddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:57.130585Z","signature_b64":"e5CH3NGUaUPHVLYLahQp3z/HtFFBKjcYKDHhJXTC75Ufgl4TEM6uA0ZqV8QDjzAjEanwnCvzbW2iPxma4R4kDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"912d3bb68da9ea4ca964a8c3a84646d66fea4b3451b1c06f3fcfa29436a81ec5","last_reissued_at":"2026-05-18T01:19:57.130040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:57.130040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning in Vector Space: An Exploratory Study of Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Li Deng, Moontae Lee, Paul Smolensky, Wen-tau Yih, Xiaodong He","submitted_at":"2015-11-19T22:30:10Z","abstract_excerpt":"Question answering tasks have shown remarkable progress with distributed vector representation. In this paper, we investigate the recently proposed Facebook bAbI tasks which consist of twenty different categories of questions that require complex reasoning. Because the previous work on bAbI are all end-to-end models, errors could come from either an imperfect understanding of semantics or in certain steps of the reasoning. For clearer analysis, we propose two vector space models inspired by Tensor Product Representation (TPR) to perform knowledge encoding and logical reasoning based on common-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06426","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":""},"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":"1511.06426","created_at":"2026-05-18T01:19:57.130133+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06426v4","created_at":"2026-05-18T01:19:57.130133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06426","created_at":"2026-05-18T01:19:57.130133+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEWTXNUNVHVE","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEWTXNUNVHVEZKLE","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEWTXNUN","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":266,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z","json":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z.json","graph_json":"https://pith.science/api/pith-number/SEWTXNUNVHVEZKLEVDB2QRSG2Z/graph.json","events_json":"https://pith.science/api/pith-number/SEWTXNUNVHVEZKLEVDB2QRSG2Z/events.json","paper":"https://pith.science/paper/SEWTXNUN"},"agent_actions":{"view_html":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z","download_json":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z.json","view_paper":"https://pith.science/paper/SEWTXNUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06426&json=true","fetch_graph":"https://pith.science/api/pith-number/SEWTXNUNVHVEZKLEVDB2QRSG2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/SEWTXNUNVHVEZKLEVDB2QRSG2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z/action/storage_attestation","attest_author":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z/action/author_attestation","sign_citation":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z/action/citation_signature","submit_replication":"https://pith.science/pith/SEWTXNUNVHVEZKLEVDB2QRSG2Z/action/replication_record"}},"created_at":"2026-05-18T01:19:57.130133+00:00","updated_at":"2026-05-18T01:19:57.130133+00:00"}