{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FALQTRMBGMBNMTNRTKTDTETGP7","short_pith_number":"pith:FALQTRMB","schema_version":"1.0","canonical_sha256":"281709c5813302d64db19aa63992667ffc570bdbe86b68bfd782b6d88ac2b382","source":{"kind":"arxiv","id":"2506.07116","version":1},"attestation_state":"computed","paper":{"title":"BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jieqiong Dong, Liyang Chen, Yiwei Wang, Yujun Cai","submitted_at":"2025-06-08T12:59:04Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T12:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"50fc3b06429c9735d14b81937f6838b5890ad366c98332e874d39bd2d8d925bb","abstract_canon_sha256":"d49bad80300bfd55d9de66fe9984d1b587adb27d0328055ccba3bb3e7371a599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:01.797413Z","signature_b64":"dhW30Gl1+NwApTGDql/urLkvwSX21Lt+YzS8AnQMQ9Cs7sKRx7pTiR1frJW1T+ZYelyooAFZH2j1Tr1If96zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281709c5813302d64db19aa63992667ffc570bdbe86b68bfd782b6d88ac2b382","last_reissued_at":"2026-07-05T11:18:01.796895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:01.796895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jieqiong Dong, Liyang Chen, Yiwei Wang, Yujun Cai","submitted_at":"2025-06-08T12:59:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07116","kind":"arxiv","version":1},"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/2506.07116/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07116","created_at":"2026-07-05T11:18:01.796953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07116v1","created_at":"2026-07-05T11:18:01.796953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07116","created_at":"2026-07-05T11:18:01.796953+00:00"},{"alias_kind":"pith_short_12","alias_value":"FALQTRMBGMBN","created_at":"2026-07-05T11:18:01.796953+00:00"},{"alias_kind":"pith_short_16","alias_value":"FALQTRMBGMBNMTNR","created_at":"2026-07-05T11:18:01.796953+00:00"},{"alias_kind":"pith_short_8","alias_value":"FALQTRMB","created_at":"2026-07-05T11:18:01.796953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7","json":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7.json","graph_json":"https://pith.science/api/pith-number/FALQTRMBGMBNMTNRTKTDTETGP7/graph.json","events_json":"https://pith.science/api/pith-number/FALQTRMBGMBNMTNRTKTDTETGP7/events.json","paper":"https://pith.science/paper/FALQTRMB"},"agent_actions":{"view_html":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7","download_json":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7.json","view_paper":"https://pith.science/paper/FALQTRMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07116&json=true","fetch_graph":"https://pith.science/api/pith-number/FALQTRMBGMBNMTNRTKTDTETGP7/graph.json","fetch_events":"https://pith.science/api/pith-number/FALQTRMBGMBNMTNRTKTDTETGP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7/action/storage_attestation","attest_author":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7/action/author_attestation","sign_citation":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7/action/citation_signature","submit_replication":"https://pith.science/pith/FALQTRMBGMBNMTNRTKTDTETGP7/action/replication_record"}},"created_at":"2026-07-05T11:18:01.796953+00:00","updated_at":"2026-07-05T11:18:01.796953+00:00"}