{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X7YNMBSJEH3EO7HHZUUPPEHFGZ","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":"1e42ce814f23ba65eb3ac6b417ecc62d562e9db2e8ff478db1e5091fc369236b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-29T00:49:40Z","title_canon_sha256":"c2562b10a2d1243f21ce4ea12c2393fcc694f4b1f79dc234915c3a2d0922b03d"},"schema_version":"1.0","source":{"id":"2211.15848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15848","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15848v2","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15848","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"X7YNMBSJEH3E","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"X7YNMBSJEH3EO7HH","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"X7YNMBSJ","created_at":"2026-07-05T05:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:10d19f30ba3c472392554aff4db78aed3a3df62e070621e33c3aaab537577652","target":"graph","created_at":"2026-07-05T05:21:45Z","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/2211.15848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ClueWeb22, the newest iteration of the ClueWeb line of datasets, provides 10 billion web pages affiliated with rich information. Its design was influenced by the need for a high quality, large scale web corpus to support a range of academic and industry research, for example, in information systems, retrieval-augmented AI systems, and model pretraining. Compared with earlier ClueWeb corpora, the ClueWeb22 corpus is larger, more varied, of higher-quality, and aligned with the document distributions in commercial web search. Besides raw HTML, ClueWeb22 includes rich information about the web pag","authors_text":"Arnold Overwijk, Cameron VandenBerg, Chenyan Xiong, Jamie Callan, Xiao Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-29T00:49:40Z","title":"ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15848","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":"sha256:9bb07846d6b245d1e170fddaa611f71d6d79937950eaf591c0b38cde01e00b5c","target":"record","created_at":"2026-07-05T05:21:45Z","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":"1e42ce814f23ba65eb3ac6b417ecc62d562e9db2e8ff478db1e5091fc369236b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-29T00:49:40Z","title_canon_sha256":"c2562b10a2d1243f21ce4ea12c2393fcc694f4b1f79dc234915c3a2d0922b03d"},"schema_version":"1.0","source":{"id":"2211.15848","kind":"arxiv","version":2}},"canonical_sha256":"bff0d6064921f6477ce7cd28f790e5366a1ca6d7e36933f25b5fab25fef884b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bff0d6064921f6477ce7cd28f790e5366a1ca6d7e36933f25b5fab25fef884b6","first_computed_at":"2026-07-05T05:21:45.395945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:45.395945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eZe5ByBPlWgq2zCGxfJ/JiVGHOwed47Vx7yRBhSdO9357z7kcTWFfSIP9dobCoMHFsRPjTINBGTHGk857FG9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:45.396372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bb07846d6b245d1e170fddaa611f71d6d79937950eaf591c0b38cde01e00b5c","sha256:10d19f30ba3c472392554aff4db78aed3a3df62e070621e33c3aaab537577652"],"state_sha256":"4db1cad7e55bdef5fb9c3c67fde7cf087bbc76588545e141f0e00e446c1c9b3c"}