{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:N3ABJE6JIISSBP45TNL5WDLCZT","short_pith_number":"pith:N3ABJE6J","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"},"canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","source":{"kind":"arxiv","id":"2101.09465","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09465","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09465v2","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09465","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"N3ABJE6JIISS","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"N3ABJE6JIISSBP45","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"N3ABJE6J","created_at":"2026-07-05T03:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:N3ABJE6JIISSBP45TNL5WDLCZT","target":"record","payload":{"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"},"canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","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"},"source_kind":"arxiv","source_id":"2101.09465","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S00dbInOmgi46ghkfrog0f5rAn0Sb6XFyfSUVDdy57oUBBkC1mjiVM8wfeRhNt+/lUctJjE4fAyFCHlzJOUSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:11.063182Z"},"content_sha256":"ad40cbd558fc9ce7d11bdb1f60337c82226fdd941024b313fa0163f07937b12b","schema_version":"1.0","event_id":"sha256:ad40cbd558fc9ce7d11bdb1f60337c82226fdd941024b313fa0163f07937b12b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:N3ABJE6JIISSBP45TNL5WDLCZT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4z3NH4QdYghZpmH4OWOSHt1c+R1g8fSNKq+ntgYyZHwdjkznwi3GipQv0iGv0eWWSot4GklIiaO6FmM+y20UCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:11.063707Z"},"content_sha256":"d4617a4023cdc01c0d5d6da5dfc587ea068ed22d09f6575cd228c75ad0ffef27","schema_version":"1.0","event_id":"sha256:d4617a4023cdc01c0d5d6da5dfc587ea068ed22d09f6575cd228c75ad0ffef27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/bundle.json","state_url":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3ABJE6JIISSBP45TNL5WDLCZT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T06:32:11Z","links":{"resolver":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT","bundle":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/bundle.json","state":"https://pith.science/pith/N3ABJE6JIISSBP45TNL5WDLCZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3ABJE6JIISSBP45TNL5WDLCZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N3ABJE6JIISSBP45TNL5WDLCZT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f6250b08b40fc8efb17da471e9969450d18e59539afbcd53e6751ad14ec47021","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-23T09:43:44Z","title_canon_sha256":"566dceede33c1db776d7d1b6014693fb7350b467069fd21ca89c3fb48fdc299b"},"schema_version":"1.0","source":{"id":"2101.09465","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09465","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09465v2","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09465","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"N3ABJE6JIISS","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"N3ABJE6JIISSBP45","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"N3ABJE6J","created_at":"2026-07-05T03:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:d4617a4023cdc01c0d5d6da5dfc587ea068ed22d09f6575cd228c75ad0ffef27","target":"graph","created_at":"2026-07-05T03:29:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.09465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ao Luo, Danyang Zhang, Jiabao Ji, Kai Yu, Lu Chen, Xingyu Chen, Yuxuan Xiong, Zihan Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-23T09:43:44Z","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09465","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad40cbd558fc9ce7d11bdb1f60337c82226fdd941024b313fa0163f07937b12b","target":"record","created_at":"2026-07-05T03:29:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f6250b08b40fc8efb17da471e9969450d18e59539afbcd53e6751ad14ec47021","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-23T09:43:44Z","title_canon_sha256":"566dceede33c1db776d7d1b6014693fb7350b467069fd21ca89c3fb48fdc299b"},"schema_version":"1.0","source":{"id":"2101.09465","kind":"arxiv","version":2}},"canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec01493c9422520bf9d9b57db0d62ccd914039eb9ba698c9b50e16051f700ab","first_computed_at":"2026-07-05T03:29:47.290553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:47.290553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ElkxDfnPEa/f3MQfXphRhVAe2jDlOleGCLwnosDnWGRn8AKjQrouUJ22oo5Gjojm5l/RqEfBIox7zKcuHbDQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:47.291039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09465","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad40cbd558fc9ce7d11bdb1f60337c82226fdd941024b313fa0163f07937b12b","sha256:d4617a4023cdc01c0d5d6da5dfc587ea068ed22d09f6575cd228c75ad0ffef27"],"state_sha256":"1c2362e4906e95a61b75f3dce2f30a5ac61b04553004d7f2ce56c5bb44c49b72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4UNxhhfsvJYWF+JH9IqDWG5hy4u11pN0dRuzGgffQhIer5uAen5B4SjtCTOnBngm0zWgVSRnVyiJ0USJ0jtMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:32:11.068488Z","bundle_sha256":"0d79042a744908b046b0f5d3435cea968b79f13bd0df10556cf235f9ea45192c"}}