{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2QCBDX4VFEI22HO7FDUQUY4RW5","short_pith_number":"pith:2QCBDX4V","schema_version":"1.0","canonical_sha256":"d40411df952911ad1ddf28e90a6391b745a04a2aac7a357c0357fa7ec7a6176c","source":{"kind":"arxiv","id":"2010.01057","version":1},"attestation_state":"computed","paper":{"title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Hideaki Takeda, Hiroyuki Shindo, Ikuya Yamada, Yuji Matsumoto","submitted_at":"2020-10-02T15:38:03Z","abstract_excerpt":"Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware"},"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":"2010.01057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T15:38:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"608831eac91c44a8a861c19fa772c03b0ebbc1919056f829353e0dd5610c6c8b","abstract_canon_sha256":"f93e3db6b8e4168c73ca8c7e9ba99c95bb15710c0441e0eef6108adc26ce135f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:51.294788Z","signature_b64":"blgu+2n6rBP+/AqNA4fGiFy5vW4hAsc7vL+2X10poNwrzC6nGa4FZyKN/+EjLZTZjF2mcCZej6WN+cC21I3fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d40411df952911ad1ddf28e90a6391b745a04a2aac7a357c0357fa7ec7a6176c","last_reissued_at":"2026-07-05T01:39:51.294334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:51.294334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Hideaki Takeda, Hiroyuki Shindo, Ikuya Yamada, Yuji Matsumoto","submitted_at":"2020-10-02T15:38:03Z","abstract_excerpt":"Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01057","kind":"arxiv","version":1},"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/2010.01057/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":"2010.01057","created_at":"2026-07-05T01:39:51.294402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01057v1","created_at":"2026-07-05T01:39:51.294402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01057","created_at":"2026-07-05T01:39:51.294402+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QCBDX4VFEI2","created_at":"2026-07-05T01:39:51.294402+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QCBDX4VFEI22HO7","created_at":"2026-07-05T01:39:51.294402+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QCBDX4V","created_at":"2026-07-05T01:39:51.294402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02479","citing_title":"Fine-grained Multiple Supervisory Network for Multi-modal Manipulation Detecting and Grounding","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5","json":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5.json","graph_json":"https://pith.science/api/pith-number/2QCBDX4VFEI22HO7FDUQUY4RW5/graph.json","events_json":"https://pith.science/api/pith-number/2QCBDX4VFEI22HO7FDUQUY4RW5/events.json","paper":"https://pith.science/paper/2QCBDX4V"},"agent_actions":{"view_html":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5","download_json":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5.json","view_paper":"https://pith.science/paper/2QCBDX4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01057&json=true","fetch_graph":"https://pith.science/api/pith-number/2QCBDX4VFEI22HO7FDUQUY4RW5/graph.json","fetch_events":"https://pith.science/api/pith-number/2QCBDX4VFEI22HO7FDUQUY4RW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5/action/storage_attestation","attest_author":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5/action/author_attestation","sign_citation":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5/action/citation_signature","submit_replication":"https://pith.science/pith/2QCBDX4VFEI22HO7FDUQUY4RW5/action/replication_record"}},"created_at":"2026-07-05T01:39:51.294402+00:00","updated_at":"2026-07-05T01:39:51.294402+00:00"}