{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4WSLLAIHNVJQDFYOEPFLFCSWLG","short_pith_number":"pith:4WSLLAIH","schema_version":"1.0","canonical_sha256":"e5a4b581076d5301970e23cab28a5659b74f1b00e4248ffb69bcc251bdb386ac","source":{"kind":"arxiv","id":"2109.08535","version":3},"attestation_state":"computed","paper":{"title":"Simple Entity-Centric Questions Challenge Dense Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Christopher Sciavolino, Danqi Chen, Jinhyuk Lee, Zexuan Zhong","submitted_at":"2021-09-17T13:19:03Z","abstract_excerpt":"Open-domain question answering has exploded in popularity recently due to the success of dense retrieval models, which have surpassed sparse models using only a few supervised training examples. However, in this paper, we demonstrate current dense models are not yet the holy grail of retrieval. We first construct EntityQuestions, a set of simple, entity-rich questions based on facts from Wikidata (e.g., \"Where was Arve Furset born?\"), and observe that dense retrievers drastically underperform sparse methods. We investigate this issue and uncover that dense retrievers can only generalize to com"},"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":"2109.08535","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T13:19:03Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"07ffd3a19abf7fe579df7e19a7c8c028d2006fefb4ba2e920015e2a17a8b0dce","abstract_canon_sha256":"130ef519974dfe45197dd92f77ebfb8b7b417eb0d55eaa6746d3fad2845ab751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:53.931996Z","signature_b64":"aGpXbMTTfI0vtq9PPV6ayApUNpbS4D5/IMKGQJkmQuGd4iYAkSj1ascFmsipN/y1HKlp9cm8vEmfmoKPAPp+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5a4b581076d5301970e23cab28a5659b74f1b00e4248ffb69bcc251bdb386ac","last_reissued_at":"2026-07-05T03:58:53.931515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:53.931515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Entity-Centric Questions Challenge Dense Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Christopher Sciavolino, Danqi Chen, Jinhyuk Lee, Zexuan Zhong","submitted_at":"2021-09-17T13:19:03Z","abstract_excerpt":"Open-domain question answering has exploded in popularity recently due to the success of dense retrieval models, which have surpassed sparse models using only a few supervised training examples. However, in this paper, we demonstrate current dense models are not yet the holy grail of retrieval. We first construct EntityQuestions, a set of simple, entity-rich questions based on facts from Wikidata (e.g., \"Where was Arve Furset born?\"), and observe that dense retrievers drastically underperform sparse methods. We investigate this issue and uncover that dense retrievers can only generalize to com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08535","kind":"arxiv","version":3},"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/2109.08535/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":"2109.08535","created_at":"2026-07-05T03:58:53.931573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08535v3","created_at":"2026-07-05T03:58:53.931573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08535","created_at":"2026-07-05T03:58:53.931573+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WSLLAIHNVJQ","created_at":"2026-07-05T03:58:53.931573+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WSLLAIHNVJQDFYO","created_at":"2026-07-05T03:58:53.931573+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WSLLAIH","created_at":"2026-07-05T03:58:53.931573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG","json":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG.json","graph_json":"https://pith.science/api/pith-number/4WSLLAIHNVJQDFYOEPFLFCSWLG/graph.json","events_json":"https://pith.science/api/pith-number/4WSLLAIHNVJQDFYOEPFLFCSWLG/events.json","paper":"https://pith.science/paper/4WSLLAIH"},"agent_actions":{"view_html":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG","download_json":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG.json","view_paper":"https://pith.science/paper/4WSLLAIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08535&json=true","fetch_graph":"https://pith.science/api/pith-number/4WSLLAIHNVJQDFYOEPFLFCSWLG/graph.json","fetch_events":"https://pith.science/api/pith-number/4WSLLAIHNVJQDFYOEPFLFCSWLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG/action/storage_attestation","attest_author":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG/action/author_attestation","sign_citation":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG/action/citation_signature","submit_replication":"https://pith.science/pith/4WSLLAIHNVJQDFYOEPFLFCSWLG/action/replication_record"}},"created_at":"2026-07-05T03:58:53.931573+00:00","updated_at":"2026-07-05T03:58:53.931573+00:00"}