{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UZYOKS27VHRB35WDUZKK55ASZ4","short_pith_number":"pith:UZYOKS27","schema_version":"1.0","canonical_sha256":"a670e54b5fa9e21df6c3a654aef412cf35a04cae90c43518a5fd96abd6ee79ed","source":{"kind":"arxiv","id":"1911.03814","version":3},"attestation_state":"computed","paper":{"title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio Petroni, Ledell Wu, Luke Zettlemoyer, Martin Josifoski, Sebastian Riedel","submitted_at":"2019-11-10T01:01:45Z","abstract_excerpt":"This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off. We present a two-stage zero-shot linking algorithm, where each entity is defined only by a short textual description. The first stage does retrieval in a dense space defined by a bi-encoder that independently embeds the mention context and the entity descriptions. Each candidate is then re-ranked with a cross-encoder, that concatenates the mention and entity text. Experiments demonstrate that this approach is state of t"},"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":"1911.03814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T01:01:45Z","cross_cats_sorted":[],"title_canon_sha256":"307e2636c121184be1326aeaffa25d6ca1d614e3f53521aaaec613faacb25eb0","abstract_canon_sha256":"6c717ea2e8a060cd1fe90e68219e25f5b6ed27565148856ee3b382ac645b08f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:33.919070Z","signature_b64":"NIHTdk4N3o28o/KQZk7UzmGSz2JSDFrIrPDqvAMYhH+CVkSmCjBiDEbU3IbVkoxTup27iYbI3x0uKWvTxvECAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a670e54b5fa9e21df6c3a654aef412cf35a04cae90c43518a5fd96abd6ee79ed","last_reissued_at":"2026-07-05T01:38:33.918674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:33.918674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio Petroni, Ledell Wu, Luke Zettlemoyer, Martin Josifoski, Sebastian Riedel","submitted_at":"2019-11-10T01:01:45Z","abstract_excerpt":"This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off. We present a two-stage zero-shot linking algorithm, where each entity is defined only by a short textual description. The first stage does retrieval in a dense space defined by a bi-encoder that independently embeds the mention context and the entity descriptions. Each candidate is then re-ranked with a cross-encoder, that concatenates the mention and entity text. Experiments demonstrate that this approach is state of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03814","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/1911.03814/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":"1911.03814","created_at":"2026-07-05T01:38:33.918731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03814v3","created_at":"2026-07-05T01:38:33.918731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03814","created_at":"2026-07-05T01:38:33.918731+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZYOKS27VHRB","created_at":"2026-07-05T01:38:33.918731+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZYOKS27VHRB35WD","created_at":"2026-07-05T01:38:33.918731+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZYOKS27","created_at":"2026-07-05T01:38:33.918731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26956","citing_title":"LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2010.03496","citing_title":"Inductive Entity Representations from Text via Link Prediction","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05967","citing_title":"Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4","json":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4.json","graph_json":"https://pith.science/api/pith-number/UZYOKS27VHRB35WDUZKK55ASZ4/graph.json","events_json":"https://pith.science/api/pith-number/UZYOKS27VHRB35WDUZKK55ASZ4/events.json","paper":"https://pith.science/paper/UZYOKS27"},"agent_actions":{"view_html":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4","download_json":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4.json","view_paper":"https://pith.science/paper/UZYOKS27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03814&json=true","fetch_graph":"https://pith.science/api/pith-number/UZYOKS27VHRB35WDUZKK55ASZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/UZYOKS27VHRB35WDUZKK55ASZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4/action/storage_attestation","attest_author":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4/action/author_attestation","sign_citation":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4/action/citation_signature","submit_replication":"https://pith.science/pith/UZYOKS27VHRB35WDUZKK55ASZ4/action/replication_record"}},"created_at":"2026-07-05T01:38:33.918731+00:00","updated_at":"2026-07-05T01:38:33.918731+00:00"}