{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:55LSX7YTQWSRQL4TKOQVQA5GTT","short_pith_number":"pith:55LSX7YT","schema_version":"1.0","canonical_sha256":"ef572bff1385a5182f9353a15803a69cde7e6815ab448b9af1bd1e05a39ff440","source":{"kind":"arxiv","id":"1911.10470","version":2},"attestation_state":"computed","paper":{"title":"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akari Asai, Caiming Xiong, Hannaneh Hajishirzi, Kazuma Hashimoto, Richard Socher","submitted_at":"2019-11-24T08:27:42Z","abstract_excerpt":"Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. Our retriever model trains a recurrent neural network that learns to sequentially retrieve evidence paragraphs in the reasoning path by conditioning on the previously retrieved documents. Our reader model ranks the reasoning"},"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":"1911.10470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-24T08:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"966caeb5961c387cdced7037a39a3f237c2f5e721ac35d75ebdfa7cafc68f593","abstract_canon_sha256":"350b434c6a89f63b69877e197cae3c4c84241dddb9b174b694f8a4b77b6479f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:45.826010Z","signature_b64":"Oeq9KKpzOfsBOXjRFrfTqYfkYaCD1WbHrw38eqwUkhAGznD0orpR88grGl8okvwC389ahzt12nV9nlq7qsnyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef572bff1385a5182f9353a15803a69cde7e6815ab448b9af1bd1e05a39ff440","last_reissued_at":"2026-07-05T00:40:45.825492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:45.825492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akari Asai, Caiming Xiong, Hannaneh Hajishirzi, Kazuma Hashimoto, Richard Socher","submitted_at":"2019-11-24T08:27:42Z","abstract_excerpt":"Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. Our retriever model trains a recurrent neural network that learns to sequentially retrieve evidence paragraphs in the reasoning path by conditioning on the previously retrieved documents. Our reader model ranks the reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10470","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/1911.10470/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":"1911.10470","created_at":"2026-07-05T00:40:45.825550+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.10470v2","created_at":"2026-07-05T00:40:45.825550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10470","created_at":"2026-07-05T00:40:45.825550+00:00"},{"alias_kind":"pith_short_12","alias_value":"55LSX7YTQWSR","created_at":"2026-07-05T00:40:45.825550+00:00"},{"alias_kind":"pith_short_16","alias_value":"55LSX7YTQWSRQL4T","created_at":"2026-07-05T00:40:45.825550+00:00"},{"alias_kind":"pith_short_8","alias_value":"55LSX7YT","created_at":"2026-07-05T00:40:45.825550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2002.08909","citing_title":"REALM: Retrieval-Augmented Language Model Pre-Training","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03344","citing_title":"RAG over Thinking Traces Can Improve Reasoning Tasks","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT","json":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT.json","graph_json":"https://pith.science/api/pith-number/55LSX7YTQWSRQL4TKOQVQA5GTT/graph.json","events_json":"https://pith.science/api/pith-number/55LSX7YTQWSRQL4TKOQVQA5GTT/events.json","paper":"https://pith.science/paper/55LSX7YT"},"agent_actions":{"view_html":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT","download_json":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT.json","view_paper":"https://pith.science/paper/55LSX7YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.10470&json=true","fetch_graph":"https://pith.science/api/pith-number/55LSX7YTQWSRQL4TKOQVQA5GTT/graph.json","fetch_events":"https://pith.science/api/pith-number/55LSX7YTQWSRQL4TKOQVQA5GTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT/action/storage_attestation","attest_author":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT/action/author_attestation","sign_citation":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT/action/citation_signature","submit_replication":"https://pith.science/pith/55LSX7YTQWSRQL4TKOQVQA5GTT/action/replication_record"}},"created_at":"2026-07-05T00:40:45.825550+00:00","updated_at":"2026-07-05T00:40:45.825550+00:00"}