{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N3ABJE6JIISSBP45TNL5WDLCZT","short_pith_number":"pith:N3ABJE6J","schema_version":"1.0","canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","source":{"kind":"arxiv","id":"2101.09465","version":2},"attestation_state":"computed","paper":{"title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ao Luo, Danyang Zhang, Jiabao Ji, Kai Yu, Lu Chen, Xingyu Chen, Yuxuan Xiong, Zihan Zhao","submitted_at":"2021-01-23T09:43:44Z","abstract_excerpt":"Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce the task of structural reading comprehension (SRC) on web. Given a web page and a question about it, the task is to find the answer from the web page. This task requires a system not only to understand the semantics of texts but also the structure of the web page. Moreover, we proposed WebSRC, a novel Web-based Structural Reading Comprehension dataset. WebSRC consists of 400K question-answer pairs, which are collecte"},"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":"2101.09465","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-23T09:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"566dceede33c1db776d7d1b6014693fb7350b467069fd21ca89c3fb48fdc299b","abstract_canon_sha256":"f6250b08b40fc8efb17da471e9969450d18e59539afbcd53e6751ad14ec47021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:47.291039Z","signature_b64":"ElkxDfnPEa/f3MQfXphRhVAe2jDlOleGCLwnosDnWGRn8AKjQrouUJ22oo5Gjojm5l/RqEfBIox7zKcuHbDQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","last_reissued_at":"2026-07-05T03:29:47.290553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:47.290553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ao Luo, Danyang Zhang, Jiabao Ji, Kai Yu, Lu Chen, Xingyu Chen, Yuxuan Xiong, Zihan Zhao","submitted_at":"2021-01-23T09:43:44Z","abstract_excerpt":"Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce the task of structural reading comprehension (SRC) on web. Given a web page and a question about it, the task is to find the answer from the web page. This task requires a system not only to understand the semantics of texts but also the structure of the web page. Moreover, we proposed WebSRC, a novel Web-based Structural Reading Comprehension dataset. WebSRC consists of 400K question-answer pairs, which are collecte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09465","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/2101.09465/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":"2101.09465","created_at":"2026-07-05T03:29:47.290615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09465v2","created_at":"2026-07-05T03:29:47.290615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09465","created_at":"2026-07-05T03:29:47.290615+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3ABJE6JIISS","created_at":"2026-07-05T03:29:47.290615+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3ABJE6JIISSBP45","created_at":"2026-07-05T03:29:47.290615+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3ABJE6J","created_at":"2026-07-05T03:29:47.290615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24602","citing_title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT","json":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT.json","graph_json":"https://pith.science/api/pith-number/N3ABJE6JIISSBP45TNL5WDLCZT/graph.json","events_json":"https://pith.science/api/pith-number/N3ABJE6JIISSBP45TNL5WDLCZT/events.json","paper":"https://pith.science/paper/N3ABJE6J"},"agent_actions":{"view_html":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT","download_json":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT.json","view_paper":"https://pith.science/paper/N3ABJE6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09465&json=true","fetch_graph":"https://pith.science/api/pith-number/N3ABJE6JIISSBP45TNL5WDLCZT/graph.json","fetch_events":"https://pith.science/api/pith-number/N3ABJE6JIISSBP45TNL5WDLCZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/action/storage_attestation","attest_author":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/action/author_attestation","sign_citation":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/action/citation_signature","submit_replication":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/action/replication_record"}},"created_at":"2026-07-05T03:29:47.290615+00:00","updated_at":"2026-07-05T03:29:47.290615+00:00"}