{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LTBFC6LEZ5NK7QWDBLQIMQGBTY","short_pith_number":"pith:LTBFC6LE","schema_version":"1.0","canonical_sha256":"5cc2517964cf5aafc2c30ae08640c19e2e6dbc7151c9eb250e75a36a1cd9f54c","source":{"kind":"arxiv","id":"2005.00512","version":1},"attestation_state":"computed","paper":{"title":"SciREX: A Challenge Dataset for Document-Level Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Iz Beltagy, Madeleine van Zuylen, Sarthak Jain","submitted_at":"2020-05-01T17:30:10Z","abstract_excerpt":"Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to create a large-scale information extraction (IE) dataset at the document level since it requires an understanding of the whole document to annotate entities and their document-level relationships that usually span beyond sentences or even sections. In this paper, we introduce SciREX, a document level IE dataset that encompasses multiple IE tasks, including salient entity identification and document l"},"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":"2005.00512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T17:30:10Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"dcbcb15480e7990e60fac63751364ad34d47f15c86c33f4aa41e3ed61d4fe779","abstract_canon_sha256":"9ecd74a7ee7e13a32e5eb212e94b7a20984ec774d3e19ff4b4fb50b5f9c5b4e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:41.576524Z","signature_b64":"Sgl3iamOrIlKF/vogSmEIwlj/hNmhFUy887P0klilVT+cycNT4Im4mD6Ws//t22Zxskr5mGPxyBSd34Hla5sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cc2517964cf5aafc2c30ae08640c19e2e6dbc7151c9eb250e75a36a1cd9f54c","last_reissued_at":"2026-07-05T00:59:41.576082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:41.576082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciREX: A Challenge Dataset for Document-Level Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Iz Beltagy, Madeleine van Zuylen, Sarthak Jain","submitted_at":"2020-05-01T17:30:10Z","abstract_excerpt":"Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to create a large-scale information extraction (IE) dataset at the document level since it requires an understanding of the whole document to annotate entities and their document-level relationships that usually span beyond sentences or even sections. In this paper, we introduce SciREX, a document level IE dataset that encompasses multiple IE tasks, including salient entity identification and document l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00512","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/2005.00512/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":"2005.00512","created_at":"2026-07-05T00:59:41.576146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00512v1","created_at":"2026-07-05T00:59:41.576146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00512","created_at":"2026-07-05T00:59:41.576146+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTBFC6LEZ5NK","created_at":"2026-07-05T00:59:41.576146+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTBFC6LEZ5NK7QWD","created_at":"2026-07-05T00:59:41.576146+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTBFC6LE","created_at":"2026-07-05T00:59:41.576146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16618","citing_title":"StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY","json":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY.json","graph_json":"https://pith.science/api/pith-number/LTBFC6LEZ5NK7QWDBLQIMQGBTY/graph.json","events_json":"https://pith.science/api/pith-number/LTBFC6LEZ5NK7QWDBLQIMQGBTY/events.json","paper":"https://pith.science/paper/LTBFC6LE"},"agent_actions":{"view_html":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY","download_json":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY.json","view_paper":"https://pith.science/paper/LTBFC6LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00512&json=true","fetch_graph":"https://pith.science/api/pith-number/LTBFC6LEZ5NK7QWDBLQIMQGBTY/graph.json","fetch_events":"https://pith.science/api/pith-number/LTBFC6LEZ5NK7QWDBLQIMQGBTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY/action/storage_attestation","attest_author":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY/action/author_attestation","sign_citation":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY/action/citation_signature","submit_replication":"https://pith.science/pith/LTBFC6LEZ5NK7QWDBLQIMQGBTY/action/replication_record"}},"created_at":"2026-07-05T00:59:41.576146+00:00","updated_at":"2026-07-05T00:59:41.576146+00:00"}