{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7EQ4A55WYX2WDIIQWRESXCK3CF","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":"3424e3056bb08a593540db6b2ae409e1e15bc0efe60cb15f51852e57b2b40aac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-13T07:46:44Z","title_canon_sha256":"ac39b16c1e5e18b6596cadf0c1a594d4d3cded6f586facfcad501657eee31f2f"},"schema_version":"1.0","source":{"id":"2405.07526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07526","created_at":"2026-07-05T08:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07526v1","created_at":"2026-07-05T08:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07526","created_at":"2026-07-05T08:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"7EQ4A55WYX2W","created_at":"2026-07-05T08:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"7EQ4A55WYX2WDIIQ","created_at":"2026-07-05T08:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"7EQ4A55W","created_at":"2026-07-05T08:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:78522e4974c3fe98375ba4da153065cb7c1d7dad7ccd17344ebd4fc095f2c36e","target":"graph","created_at":"2026-07-05T08:18:24Z","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/2405.07526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals. In this paper, we introduce MS MARCO Web Search, the first large-scale information-rich web dataset, featuring millions of real clicked query-document labels. This dataset closely mimics real-world web document and query distribution, provides rich information for various kinds of downstream tasks and encourages research in various areas, such as generic end-to-end neural indexer models, generic embedding models, and next generation information access system with large language mod","authors_text":"Andy Oakley, Anlei Dong, Bryan Tower, Carolyn Buractaon, Ce Zhang, Chenyan Xiong, Chuanjie Liu, Corby Rosset, Fan Yang, Harsha Vardhan Simhadri, Jennifer Neville, Jingwen Lu, Knut Magne Risvik, Kun Zhou, Linjun Yang, Manik Varma, Mao Yang, Mingqin Li, Nick Craswell, Nikhil Rao, Paul Bennett, Qi Chen, Rangan Majumder, Tao Shen, Wenqi Jiang, Xing Xie, Xiubo Geng, Yeyun Gong, Yujing Wang, Zengzhong Li, Zheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-13T07:46:44Z","title":"MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07526","kind":"arxiv","version":1},"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:a7395a21899537e2f576cf4e0565040a4b78252bf4bd6d4f738de5b8ca06d535","target":"record","created_at":"2026-07-05T08:18:24Z","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":"3424e3056bb08a593540db6b2ae409e1e15bc0efe60cb15f51852e57b2b40aac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-13T07:46:44Z","title_canon_sha256":"ac39b16c1e5e18b6596cadf0c1a594d4d3cded6f586facfcad501657eee31f2f"},"schema_version":"1.0","source":{"id":"2405.07526","kind":"arxiv","version":1}},"canonical_sha256":"f921c077b6c5f561a110b4492b895b115649c560317ca82b9db8433028e81020","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f921c077b6c5f561a110b4492b895b115649c560317ca82b9db8433028e81020","first_computed_at":"2026-07-05T08:18:24.230809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:24.230809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7to3yQZDN2OMt8Mmo63t82TvJkyv5jF/DnQe3eDP0gHT9t5IVajIpiCLNhEB2HnXx9vuqewQRQRsGr68jMSADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:24.231343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7395a21899537e2f576cf4e0565040a4b78252bf4bd6d4f738de5b8ca06d535","sha256:78522e4974c3fe98375ba4da153065cb7c1d7dad7ccd17344ebd4fc095f2c36e"],"state_sha256":"bfdb8d4b12153dc09dd4b1770c6aaa046fa025182f697bcb963ad318e16364e4"}