{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FALQTRMBGMBNMTNRTKTDTETGP7","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":"d49bad80300bfd55d9de66fe9984d1b587adb27d0328055ccba3bb3e7371a599","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T12:59:04Z","title_canon_sha256":"50fc3b06429c9735d14b81937f6838b5890ad366c98332e874d39bd2d8d925bb"},"schema_version":"1.0","source":{"id":"2506.07116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07116","created_at":"2026-07-05T11:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07116v1","created_at":"2026-07-05T11:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07116","created_at":"2026-07-05T11:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"FALQTRMBGMBN","created_at":"2026-07-05T11:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"FALQTRMBGMBNMTNR","created_at":"2026-07-05T11:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"FALQTRMB","created_at":"2026-07-05T11:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:7b1423a761ec2f1aafdddd6d32cd1d32f32f3e99f558406e5d3f9b609f7463af","target":"graph","created_at":"2026-07-05T11:18:01Z","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/2506.07116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems require corpora that are both structurally clean and semantically coherent. BRIGHT is a recent and influential benchmark designed to evaluate complex multi-hop retrieval across diverse, high-reasoning domains. However, its practical effectiveness is limited by common web-crawled artifacts - such as content redundancy and semantic discontinuity - that impair retrieval accuracy and downstream reasoning. Notably, we find that such issues are concentrated in seven StackExchange-derived subdomains, while other domains (e.g., Coding and Theorem-based cont","authors_text":"Jieqiong Dong, Liyang Chen, Yiwei Wang, Yujun Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T12:59:04Z","title":"BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07116","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":"sha256:9fdf4848c3f8ac97fc65ac990c26978c9d44bf99aa39dd1c48cb713f40c02da0","target":"record","created_at":"2026-07-05T11:18:01Z","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":"d49bad80300bfd55d9de66fe9984d1b587adb27d0328055ccba3bb3e7371a599","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T12:59:04Z","title_canon_sha256":"50fc3b06429c9735d14b81937f6838b5890ad366c98332e874d39bd2d8d925bb"},"schema_version":"1.0","source":{"id":"2506.07116","kind":"arxiv","version":1}},"canonical_sha256":"281709c5813302d64db19aa63992667ffc570bdbe86b68bfd782b6d88ac2b382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"281709c5813302d64db19aa63992667ffc570bdbe86b68bfd782b6d88ac2b382","first_computed_at":"2026-07-05T11:18:01.796895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:01.796895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dhW30Gl1+NwApTGDql/urLkvwSX21Lt+YzS8AnQMQ9Cs7sKRx7pTiR1frJW1T+ZYelyooAFZH2j1Tr1If96zBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:01.797413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fdf4848c3f8ac97fc65ac990c26978c9d44bf99aa39dd1c48cb713f40c02da0","sha256:7b1423a761ec2f1aafdddd6d32cd1d32f32f3e99f558406e5d3f9b609f7463af"],"state_sha256":"0d4d10d0d60be3ad5e4c5db87979979f7533d5e04ac4c9c3e0725eaf962ce23a"}