{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BAWXTKKEVIGKKLKXLOCOHBNA25","short_pith_number":"pith:BAWXTKKE","schema_version":"1.0","canonical_sha256":"082d79a944aa0ca52d575b84e385a0d77464aa8d1d496cb42f765591e2cea5c4","source":{"kind":"arxiv","id":"2004.07202","version":2},"attestation_state":"computed","paper":{"title":"Entities as Experts: Sparse Memory Access with Entity Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Livio Baldini Soares, Nicholas FitzGerald, Thibault F\\'evry, Tom Kwiatkowski","submitted_at":"2020-04-15T17:00:05Z","abstract_excerpt":"We focus on the problem of capturing declarative knowledge about entities in the learned parameters of a language model. We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EAE's entity representations are learned directly from text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions such as \"Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?\", outperfor"},"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":"2004.07202","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-15T17:00:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8fccf35741f381bd08bb711df2df41e63a3e28674bed9cf7d8744ccb93ee8345","abstract_canon_sha256":"3d6fbf4d411cf16d53d935e6bdfb6edf8300e336a7e4ad9a1ae92224cec10834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:56.481528Z","signature_b64":"Lsqv7hSTkLDopnkf5ni6VQHF+s9Ek3ZWX4X3jQityThpXo1zewHPWrdzuU0VPTlDOzai5yzlUVi+JPl7E4eOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"082d79a944aa0ca52d575b84e385a0d77464aa8d1d496cb42f765591e2cea5c4","last_reissued_at":"2026-07-05T01:40:56.480982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:56.480982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entities as Experts: Sparse Memory Access with Entity Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Livio Baldini Soares, Nicholas FitzGerald, Thibault F\\'evry, Tom Kwiatkowski","submitted_at":"2020-04-15T17:00:05Z","abstract_excerpt":"We focus on the problem of capturing declarative knowledge about entities in the learned parameters of a language model. We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EAE's entity representations are learned directly from text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions such as \"Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?\", outperfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.07202","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/2004.07202/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":"2004.07202","created_at":"2026-07-05T01:40:56.481039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.07202v2","created_at":"2026-07-05T01:40:56.481039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.07202","created_at":"2026-07-05T01:40:56.481039+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAWXTKKEVIGK","created_at":"2026-07-05T01:40:56.481039+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAWXTKKEVIGKKLKX","created_at":"2026-07-05T01:40:56.481039+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAWXTKKE","created_at":"2026-07-05T01:40:56.481039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":56,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2112.09118","citing_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08519","citing_title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2005.11401","citing_title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25","json":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25.json","graph_json":"https://pith.science/api/pith-number/BAWXTKKEVIGKKLKXLOCOHBNA25/graph.json","events_json":"https://pith.science/api/pith-number/BAWXTKKEVIGKKLKXLOCOHBNA25/events.json","paper":"https://pith.science/paper/BAWXTKKE"},"agent_actions":{"view_html":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25","download_json":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25.json","view_paper":"https://pith.science/paper/BAWXTKKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.07202&json=true","fetch_graph":"https://pith.science/api/pith-number/BAWXTKKEVIGKKLKXLOCOHBNA25/graph.json","fetch_events":"https://pith.science/api/pith-number/BAWXTKKEVIGKKLKXLOCOHBNA25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25/action/storage_attestation","attest_author":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25/action/author_attestation","sign_citation":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25/action/citation_signature","submit_replication":"https://pith.science/pith/BAWXTKKEVIGKKLKXLOCOHBNA25/action/replication_record"}},"created_at":"2026-07-05T01:40:56.481039+00:00","updated_at":"2026-07-05T01:40:56.481039+00:00"}