{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KNESQDTL7SPI5BYVTP2DYTRZ6W","short_pith_number":"pith:KNESQDTL","schema_version":"1.0","canonical_sha256":"5349280e6bfc9e8e87159bf43c4e39f59dc5d5a0b6f909421679d72df9a3d746","source":{"kind":"arxiv","id":"2004.14224","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Guodong Long, Pengcheng He, Tao Shen, Weizhu Chen, Yi Mao","submitted_at":"2020-04-29T14:22:42Z","abstract_excerpt":"In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme that exploits relational knowledge underlying the text. This is fulfilled by using a linked knowledge graph to select informative entities and then masking their mentions. In addition we use knowledge graphs to obtain distractors for the masked entities, and propose a novel distractor-suppressed ranking obj"},"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":"2004.14224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T14:22:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d62a4c8e3455a6f00384bb034faa95f8e5ed0ee7549bdba1eaf6db8c8e6092bc","abstract_canon_sha256":"8b06dfde6eec5f13223775a0ef7d9c4b895c9b9a2a6a21a628636f1e2554f13f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:18.372970Z","signature_b64":"q9uNEYYQfPcqzvi8sr/toZbTp7BqwtJBpqKF39fm4HvB+przxX6Pc0/CeMvjMcQi7EODo2768DDZHU1DszRqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5349280e6bfc9e8e87159bf43c4e39f59dc5d5a0b6f909421679d72df9a3d746","last_reissued_at":"2026-07-05T00:59:18.372473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:18.372473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Guodong Long, Pengcheng He, Tao Shen, Weizhu Chen, Yi Mao","submitted_at":"2020-04-29T14:22:42Z","abstract_excerpt":"In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme that exploits relational knowledge underlying the text. This is fulfilled by using a linked knowledge graph to select informative entities and then masking their mentions. In addition we use knowledge graphs to obtain distractors for the masked entities, and propose a novel distractor-suppressed ranking obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14224","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/2004.14224/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":"2004.14224","created_at":"2026-07-05T00:59:18.372524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14224v1","created_at":"2026-07-05T00:59:18.372524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14224","created_at":"2026-07-05T00:59:18.372524+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNESQDTL7SPI","created_at":"2026-07-05T00:59:18.372524+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNESQDTL7SPI5BYV","created_at":"2026-07-05T00:59:18.372524+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNESQDTL","created_at":"2026-07-05T00:59:18.372524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2006.03654","citing_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W","json":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W.json","graph_json":"https://pith.science/api/pith-number/KNESQDTL7SPI5BYVTP2DYTRZ6W/graph.json","events_json":"https://pith.science/api/pith-number/KNESQDTL7SPI5BYVTP2DYTRZ6W/events.json","paper":"https://pith.science/paper/KNESQDTL"},"agent_actions":{"view_html":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W","download_json":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W.json","view_paper":"https://pith.science/paper/KNESQDTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14224&json=true","fetch_graph":"https://pith.science/api/pith-number/KNESQDTL7SPI5BYVTP2DYTRZ6W/graph.json","fetch_events":"https://pith.science/api/pith-number/KNESQDTL7SPI5BYVTP2DYTRZ6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W/action/storage_attestation","attest_author":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W/action/author_attestation","sign_citation":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W/action/citation_signature","submit_replication":"https://pith.science/pith/KNESQDTL7SPI5BYVTP2DYTRZ6W/action/replication_record"}},"created_at":"2026-07-05T00:59:18.372524+00:00","updated_at":"2026-07-05T00:59:18.372524+00:00"}