{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TUWWX7WQLL7JHTDCSZVDOD5AH6","short_pith_number":"pith:TUWWX7WQ","schema_version":"1.0","canonical_sha256":"9d2d6bfed05afe93cc62966a370fa03f9a716e19b162410538a54089bc44afc2","source":{"kind":"arxiv","id":"2102.13247","version":1},"attestation_state":"computed","paper":{"title":"DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Ravula, Bhargav Kanagal, Fei Sha, Ilya Eckstein, Juraj Gottweis, Ruining He, Sudeep Gandhe, Yury Zemlyanskiy","submitted_at":"2021-02-26T01:00:12Z","abstract_excerpt":"This paper explores learning rich self-supervised entity representations from large amounts of the associated text. Once pre-trained, these models become applicable to multiple entity-centric tasks such as ranked retrieval, knowledge base completion, question answering, and more. Unlike other methods that harvest self-supervision signals based merely on a local context within a sentence, we radically expand the notion of context to include any available text related to an entity. This enables a new class of powerful, high-capacity representations that can ultimately distill much of the useful "},"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":"2102.13247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-26T01:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"6eb207418beddf0bc10782b8146a59bc4c2ffe89bbfdfac62fbc5ef200a48392","abstract_canon_sha256":"921780e571a6c6b67dc15d7d36199c08cbdac071bc1753d9ee49578b381c8ef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:35.485205Z","signature_b64":"NOeQbQ1yE8Ssysqzd4LDgYD6XekEw12+ScVh0uI6DtDuA7038mPZxKO8EnfptRoTjXL0HEUT9U8RwbWKsg/3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d2d6bfed05afe93cc62966a370fa03f9a716e19b162410538a54089bc44afc2","last_reissued_at":"2026-07-05T02:18:35.484769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:35.484769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Ravula, Bhargav Kanagal, Fei Sha, Ilya Eckstein, Juraj Gottweis, Ruining He, Sudeep Gandhe, Yury Zemlyanskiy","submitted_at":"2021-02-26T01:00:12Z","abstract_excerpt":"This paper explores learning rich self-supervised entity representations from large amounts of the associated text. Once pre-trained, these models become applicable to multiple entity-centric tasks such as ranked retrieval, knowledge base completion, question answering, and more. Unlike other methods that harvest self-supervision signals based merely on a local context within a sentence, we radically expand the notion of context to include any available text related to an entity. This enables a new class of powerful, high-capacity representations that can ultimately distill much of the useful "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13247","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/2102.13247/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":"2102.13247","created_at":"2026-07-05T02:18:35.484830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.13247v1","created_at":"2026-07-05T02:18:35.484830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13247","created_at":"2026-07-05T02:18:35.484830+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUWWX7WQLL7J","created_at":"2026-07-05T02:18:35.484830+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUWWX7WQLL7JHTDC","created_at":"2026-07-05T02:18:35.484830+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUWWX7WQ","created_at":"2026-07-05T02:18:35.484830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6","json":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6.json","graph_json":"https://pith.science/api/pith-number/TUWWX7WQLL7JHTDCSZVDOD5AH6/graph.json","events_json":"https://pith.science/api/pith-number/TUWWX7WQLL7JHTDCSZVDOD5AH6/events.json","paper":"https://pith.science/paper/TUWWX7WQ"},"agent_actions":{"view_html":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6","download_json":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6.json","view_paper":"https://pith.science/paper/TUWWX7WQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.13247&json=true","fetch_graph":"https://pith.science/api/pith-number/TUWWX7WQLL7JHTDCSZVDOD5AH6/graph.json","fetch_events":"https://pith.science/api/pith-number/TUWWX7WQLL7JHTDCSZVDOD5AH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6/action/storage_attestation","attest_author":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6/action/author_attestation","sign_citation":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6/action/citation_signature","submit_replication":"https://pith.science/pith/TUWWX7WQLL7JHTDCSZVDOD5AH6/action/replication_record"}},"created_at":"2026-07-05T02:18:35.484830+00:00","updated_at":"2026-07-05T02:18:35.484830+00:00"}