{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X7YNMBSJEH3EO7HHZUUPPEHFGZ","short_pith_number":"pith:X7YNMBSJ","canonical_record":{"source":{"id":"2211.15848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-29T00:49:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c2562b10a2d1243f21ce4ea12c2393fcc694f4b1f79dc234915c3a2d0922b03d","abstract_canon_sha256":"1e42ce814f23ba65eb3ac6b417ecc62d562e9db2e8ff478db1e5091fc369236b"},"schema_version":"1.0"},"canonical_sha256":"bff0d6064921f6477ce7cd28f790e5366a1ca6d7e36933f25b5fab25fef884b6","source":{"kind":"arxiv","id":"2211.15848","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X7YNMBSJEH3EO7HHZUUPPEHFGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2211.15848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-29T00:49:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c2562b10a2d1243f21ce4ea12c2393fcc694f4b1f79dc234915c3a2d0922b03d","abstract_canon_sha256":"1e42ce814f23ba65eb3ac6b417ecc62d562e9db2e8ff478db1e5091fc369236b"},"schema_version":"1.0"},"canonical_sha256":"bff0d6064921f6477ce7cd28f790e5366a1ca6d7e36933f25b5fab25fef884b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:45.396372Z","signature_b64":"eZe5ByBPlWgq2zCGxfJ/JiVGHOwed47Vx7yRBhSdO9357z7kcTWFfSIP9dobCoMHFsRPjTINBGTHGk857FG9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bff0d6064921f6477ce7cd28f790e5366a1ca6d7e36933f25b5fab25fef884b6","last_reissued_at":"2026-07-05T05:21:45.395945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:45.395945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.15848","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":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+Q1Gim9AEzTDwiyPu4Pxf69fcTTEyGJ79nRwvjhG3fsKczmNB8dSIWLJdiUkpRvSM9hQtBrSRyldbebDfyjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:25.118917Z"},"content_sha256":"9bb07846d6b245d1e170fddaa611f71d6d79937950eaf591c0b38cde01e00b5c","schema_version":"1.0","event_id":"sha256:9bb07846d6b245d1e170fddaa611f71d6d79937950eaf591c0b38cde01e00b5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X7YNMBSJEH3EO7HHZUUPPEHFGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Arnold Overwijk, Cameron VandenBerg, Chenyan Xiong, Jamie Callan, Xiao Liu","submitted_at":"2022-11-29T00:49:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15848","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/2211.15848/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":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dq4KC1gEVd4TjZCpnB4UufdYIpj7dtf1I4nd5SCDYpagCr7Jrk0ys76CxV6rpX6czdt5zxQXU0Cb2Bg8uJ/uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:25.119424Z"},"content_sha256":"10d19f30ba3c472392554aff4db78aed3a3df62e070621e33c3aaab537577652","schema_version":"1.0","event_id":"sha256:10d19f30ba3c472392554aff4db78aed3a3df62e070621e33c3aaab537577652"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/bundle.json","state_url":"https://pith.science/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/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":"2026-08-06T05:00:25Z","links":{"resolver":"https://pith.science/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ","bundle":"https://pith.science/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/bundle.json","state":"https://pith.science/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7YNMBSJEH3EO7HHZUUPPEHFGZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HRX04Pk5dPf/3OX9nkIhIK5SQ2ZcW/g6scO5fN8zIy6ajMZY73jF+cCG2zXZ+vdfBGE7s8kTqA8F1uIiH2D0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:00:25.123038Z","bundle_sha256":"cecbdd719d775df01439341a82b4f0e548cf765c121e13168c7de5d7cea7907a"}}