{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:US4JBFUHRV72OJZPCCVNCJAEA7","short_pith_number":"pith:US4JBFUH","schema_version":"1.0","canonical_sha256":"a4b89096878d7fa7272f10aad1240407e2f1b5c2b693f7d7122baa95a4d2b8ff","source":{"kind":"arxiv","id":"1909.07598","version":1},"attestation_state":"computed","paper":{"title":"Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Singhal, Ameya Godbole, Andrew McCallum, Dilip Kavarthapu, Hamed Zamani, Manzil Zaheer, Mo Yu, Rajarshi Das, Tian Gao, Xiaoxiao Guo, Zhiyu Gong","submitted_at":"2019-09-17T05:23:50Z","abstract_excerpt":"Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \\emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `\\emph{hop}' to other relevant evidence. In a setting, with more than \\textbf{5 million} Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without "},"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":"1909.07598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-17T05:23:50Z","cross_cats_sorted":[],"title_canon_sha256":"c820001ee7565bfe17d3f722de4a3a198d807947ef7f92af385c1b94a1e6d7f5","abstract_canon_sha256":"1be3cf6b73d0b2110f858338cfc77a88437cf078a3f324e205088ba5e02bd6cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:15.807386Z","signature_b64":"C4V4noy1FS6WGqzNgEwZkJYKcpMXsw2/9Ok1K1p7PzwlUvYolcUlMhi8CtDaCJyVCLXfQu5S+2V+rBObht9ECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4b89096878d7fa7272f10aad1240407e2f1b5c2b693f7d7122baa95a4d2b8ff","last_reissued_at":"2026-07-05T00:05:15.806984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:15.806984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Singhal, Ameya Godbole, Andrew McCallum, Dilip Kavarthapu, Hamed Zamani, Manzil Zaheer, Mo Yu, Rajarshi Das, Tian Gao, Xiaoxiao Guo, Zhiyu Gong","submitted_at":"2019-09-17T05:23:50Z","abstract_excerpt":"Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \\emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `\\emph{hop}' to other relevant evidence. In a setting, with more than \\textbf{5 million} Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07598","kind":"arxiv","version":1},"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/1909.07598/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":"1909.07598","created_at":"2026-07-05T00:05:15.807041+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07598v1","created_at":"2026-07-05T00:05:15.807041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07598","created_at":"2026-07-05T00:05:15.807041+00:00"},{"alias_kind":"pith_short_12","alias_value":"US4JBFUHRV72","created_at":"2026-07-05T00:05:15.807041+00:00"},{"alias_kind":"pith_short_16","alias_value":"US4JBFUHRV72OJZP","created_at":"2026-07-05T00:05:15.807041+00:00"},{"alias_kind":"pith_short_8","alias_value":"US4JBFUH","created_at":"2026-07-05T00:05:15.807041+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/US4JBFUHRV72OJZPCCVNCJAEA7","json":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7.json","graph_json":"https://pith.science/api/pith-number/US4JBFUHRV72OJZPCCVNCJAEA7/graph.json","events_json":"https://pith.science/api/pith-number/US4JBFUHRV72OJZPCCVNCJAEA7/events.json","paper":"https://pith.science/paper/US4JBFUH"},"agent_actions":{"view_html":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7","download_json":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7.json","view_paper":"https://pith.science/paper/US4JBFUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07598&json=true","fetch_graph":"https://pith.science/api/pith-number/US4JBFUHRV72OJZPCCVNCJAEA7/graph.json","fetch_events":"https://pith.science/api/pith-number/US4JBFUHRV72OJZPCCVNCJAEA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7/action/storage_attestation","attest_author":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7/action/author_attestation","sign_citation":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7/action/citation_signature","submit_replication":"https://pith.science/pith/US4JBFUHRV72OJZPCCVNCJAEA7/action/replication_record"}},"created_at":"2026-07-05T00:05:15.807041+00:00","updated_at":"2026-07-05T00:05:15.807041+00:00"}