{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PMKDAYN3HJ6BXTO42NU7TDVZFI","short_pith_number":"pith:PMKDAYN3","schema_version":"1.0","canonical_sha256":"7b143061bb3a7c1bcddcd369f98eb92a370b68f9505d15bd9e8cb5ca901eb384","source":{"kind":"arxiv","id":"2202.10610","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Base Question Answering by Case-based Reasoning over Subgraphs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameya Godbole, Andrew McCallum, Ankita Naik, Elliot Tower, Hannaneh Hajishirzi, Manzil Zaheer, Rajarshi Das, Robin Jia","submitted_at":"2022-02-22T01:34:35Z","abstract_excerpt":"Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type reoccur for various entities in their respective subgraph neighborhoods. Leveraging this structural similarity between local neighborhoods of different subgraphs, we introduce a semiparametric model (CBR-SUBG) with (i) a nonparametric component that for each query, dynamically retrieves other similar $k$-nearest neighbor (KNN) training queries along with quer"},"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":"2202.10610","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-22T01:34:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cd61a123166c166bb9cc4a95b161362b0b66f7dbc1dba28eced3f19910436595","abstract_canon_sha256":"0815a9af00d31b42ed5f368ecbf93ca4a512f8b39d8ebf79bf1f9972e967d668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:56.712178Z","signature_b64":"Sfsb+8g9dkte8HqdSp357U+tOcO/vlvz+AzyB25wMIBEVkofNi2Px14FE2Fn5Hm28SbA/GMsdqQqOS3He7KaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b143061bb3a7c1bcddcd369f98eb92a370b68f9505d15bd9e8cb5ca901eb384","last_reissued_at":"2026-07-05T04:32:56.711695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:56.711695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Base Question Answering by Case-based Reasoning over Subgraphs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameya Godbole, Andrew McCallum, Ankita Naik, Elliot Tower, Hannaneh Hajishirzi, Manzil Zaheer, Rajarshi Das, Robin Jia","submitted_at":"2022-02-22T01:34:35Z","abstract_excerpt":"Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type reoccur for various entities in their respective subgraph neighborhoods. Leveraging this structural similarity between local neighborhoods of different subgraphs, we introduce a semiparametric model (CBR-SUBG) with (i) a nonparametric component that for each query, dynamically retrieves other similar $k$-nearest neighbor (KNN) training queries along with quer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10610","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/2202.10610/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":"2202.10610","created_at":"2026-07-05T04:32:56.711753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.10610v2","created_at":"2026-07-05T04:32:56.711753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10610","created_at":"2026-07-05T04:32:56.711753+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMKDAYN3HJ6B","created_at":"2026-07-05T04:32:56.711753+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMKDAYN3HJ6BXTO4","created_at":"2026-07-05T04:32:56.711753+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMKDAYN3","created_at":"2026-07-05T04:32:56.711753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18468","citing_title":"Short-Duration Gamma-ray Burst and Afterglow Rates in the Rubin and Roman Era","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI","json":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI.json","graph_json":"https://pith.science/api/pith-number/PMKDAYN3HJ6BXTO42NU7TDVZFI/graph.json","events_json":"https://pith.science/api/pith-number/PMKDAYN3HJ6BXTO42NU7TDVZFI/events.json","paper":"https://pith.science/paper/PMKDAYN3"},"agent_actions":{"view_html":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI","download_json":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI.json","view_paper":"https://pith.science/paper/PMKDAYN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.10610&json=true","fetch_graph":"https://pith.science/api/pith-number/PMKDAYN3HJ6BXTO42NU7TDVZFI/graph.json","fetch_events":"https://pith.science/api/pith-number/PMKDAYN3HJ6BXTO42NU7TDVZFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI/action/storage_attestation","attest_author":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI/action/author_attestation","sign_citation":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI/action/citation_signature","submit_replication":"https://pith.science/pith/PMKDAYN3HJ6BXTO42NU7TDVZFI/action/replication_record"}},"created_at":"2026-07-05T04:32:56.711753+00:00","updated_at":"2026-07-05T04:32:56.711753+00:00"}