{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WTNDWVZUPGDJ7VMCD43455KGG5","short_pith_number":"pith:WTNDWVZU","schema_version":"1.0","canonical_sha256":"b4da3b573479869fd5821f37cef546376b1ae421b2448db1760c20297e83ec99","source":{"kind":"arxiv","id":"1904.09380","version":1},"attestation_state":"computed","paper":{"title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Harsh Trivedi, Heeyoung Kwon, Niranjan Balasubramanian, Tushar Khot","submitted_at":"2019-04-20T00:30:26Z","abstract_excerpt":"Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a glob"},"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":"1904.09380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T00:30:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c4f37c774cbc9613eea2eb3fe95849d4c956c363627848b1f411ab5b400101a","abstract_canon_sha256":"e1377d9e0922ba88fcf246b8c93a5a4b8261717618e5b7ebdc430b33362eba32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:07.239591Z","signature_b64":"cSheFT0nJa9VaEbgovpKf8yPHXowIDJpVwwxfVBE5ivku91WqKySB8Gealv6iyw02jejOi/0Qe0ymoQ8CQvkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4da3b573479869fd5821f37cef546376b1ae421b2448db1760c20297e83ec99","last_reissued_at":"2026-05-17T23:48:07.239152Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:07.239152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Harsh Trivedi, Heeyoung Kwon, Niranjan Balasubramanian, Tushar Khot","submitted_at":"2019-04-20T00:30:26Z","abstract_excerpt":"Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a glob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09380","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":""},"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":"1904.09380","created_at":"2026-05-17T23:48:07.239225+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09380v1","created_at":"2026-05-17T23:48:07.239225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09380","created_at":"2026-05-17T23:48:07.239225+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTNDWVZUPGDJ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTNDWVZUPGDJ7VMC","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTNDWVZU","created_at":"2026-05-18T12:33:30.264802+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/WTNDWVZUPGDJ7VMCD43455KGG5","json":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5.json","graph_json":"https://pith.science/api/pith-number/WTNDWVZUPGDJ7VMCD43455KGG5/graph.json","events_json":"https://pith.science/api/pith-number/WTNDWVZUPGDJ7VMCD43455KGG5/events.json","paper":"https://pith.science/paper/WTNDWVZU"},"agent_actions":{"view_html":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5","download_json":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5.json","view_paper":"https://pith.science/paper/WTNDWVZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09380&json=true","fetch_graph":"https://pith.science/api/pith-number/WTNDWVZUPGDJ7VMCD43455KGG5/graph.json","fetch_events":"https://pith.science/api/pith-number/WTNDWVZUPGDJ7VMCD43455KGG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5/action/storage_attestation","attest_author":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5/action/author_attestation","sign_citation":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5/action/citation_signature","submit_replication":"https://pith.science/pith/WTNDWVZUPGDJ7VMCD43455KGG5/action/replication_record"}},"created_at":"2026-05-17T23:48:07.239225+00:00","updated_at":"2026-05-17T23:48:07.239225+00:00"}