{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BDBQ3C4R3QIVSLBNS2HEWSGY4N","short_pith_number":"pith:BDBQ3C4R","schema_version":"1.0","canonical_sha256":"08c30d8b91dc11592c2d968e4b48d8e34ed029efe88f1ef5cd7b23c35924a1ab","source":{"kind":"arxiv","id":"2008.09084","version":2},"attestation_state":"computed","paper":{"title":"Do Syntax Trees Help Pre-trained Transformers Extract Information?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Devendra Singh Sachan, Peng Qi, William Hamilton, Yuhao Zhang","submitted_at":"2020-08-20T17:17:38Z","abstract_excerpt":"Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency tree information into pre-trained transformer models (e.g., BERT) remains unclear, especially given recent studies highlighting how these models implicitly encode syntax. In this work, we systematically study the utility of incorporating dependency trees into pre-trained transformers on three representative information extraction tasks: semantic role labeling (SRL), named entity recognition, and relation extraction.\n"},"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":"2008.09084","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T17:17:38Z","cross_cats_sorted":[],"title_canon_sha256":"609a78d6d023018ce82e5dbde69eec2fa7be683b6ad425a9925050b0aa3c9313","abstract_canon_sha256":"ad084b02db608786faae199fe4c74a2d95345e758ad010abb0afade3267c2579"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:06.653392Z","signature_b64":"MlMiBls4Z2EObEIAoaLfnv8LBXgi638l+Dpt0WD0lMjhas8Db8YEaZJtpnQiSZgi3kzQ/43HsMM1AicElNXzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c30d8b91dc11592c2d968e4b48d8e34ed029efe88f1ef5cd7b23c35924a1ab","last_reissued_at":"2026-07-05T02:10:06.652873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:06.652873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Syntax Trees Help Pre-trained Transformers Extract Information?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Devendra Singh Sachan, Peng Qi, William Hamilton, Yuhao Zhang","submitted_at":"2020-08-20T17:17:38Z","abstract_excerpt":"Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency tree information into pre-trained transformer models (e.g., BERT) remains unclear, especially given recent studies highlighting how these models implicitly encode syntax. In this work, we systematically study the utility of incorporating dependency trees into pre-trained transformers on three representative information extraction tasks: semantic role labeling (SRL), named entity recognition, and relation extraction.\n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09084","kind":"arxiv","version":2},"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/2008.09084/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":"2008.09084","created_at":"2026-07-05T02:10:06.652947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.09084v2","created_at":"2026-07-05T02:10:06.652947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09084","created_at":"2026-07-05T02:10:06.652947+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDBQ3C4R3QIV","created_at":"2026-07-05T02:10:06.652947+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDBQ3C4R3QIVSLBN","created_at":"2026-07-05T02:10:06.652947+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDBQ3C4R","created_at":"2026-07-05T02:10:06.652947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09925","citing_title":"Extracting Cause-Effect Pairs from a Sentence with a Dependency-Aware Transformer Model","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N","json":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N.json","graph_json":"https://pith.science/api/pith-number/BDBQ3C4R3QIVSLBNS2HEWSGY4N/graph.json","events_json":"https://pith.science/api/pith-number/BDBQ3C4R3QIVSLBNS2HEWSGY4N/events.json","paper":"https://pith.science/paper/BDBQ3C4R"},"agent_actions":{"view_html":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N","download_json":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N.json","view_paper":"https://pith.science/paper/BDBQ3C4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.09084&json=true","fetch_graph":"https://pith.science/api/pith-number/BDBQ3C4R3QIVSLBNS2HEWSGY4N/graph.json","fetch_events":"https://pith.science/api/pith-number/BDBQ3C4R3QIVSLBNS2HEWSGY4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N/action/storage_attestation","attest_author":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N/action/author_attestation","sign_citation":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N/action/citation_signature","submit_replication":"https://pith.science/pith/BDBQ3C4R3QIVSLBNS2HEWSGY4N/action/replication_record"}},"created_at":"2026-07-05T02:10:06.652947+00:00","updated_at":"2026-07-05T02:10:06.652947+00:00"}