{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CZEB3NGEDRRE4NOJCOYGN2HMLY","short_pith_number":"pith:CZEB3NGE","schema_version":"1.0","canonical_sha256":"16481db4c41c624e35c913b066e8ec5e14e0835ff56989a45ab27f402fde870c","source":{"kind":"arxiv","id":"2507.22927","version":1},"attestation_state":"computed","paper":{"title":"PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Yang, Duolin Sun, Jian Wang, Jie Feng, Jinjie Gu, Lei Liu, Peng Wei, Yihan Jiao, Yue Shen, Zhehao Tan","submitted_at":"2025-07-23T16:14:08Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination of a given query and retrieved documents is crucial. However, most benchmarks focus on overall RAG system performance, rarely assessing LLM-specific capabilities. Current benchmarks emphasize broad aspects such as noise robustness, but lack a systematic and granular evaluation framework on document utilization. To this end, we introduce \\textit{Placeholder-RAG-Benchmark}, a multi-level fine-grained benchmark, emphas"},"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":"2507.22927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T16:14:08Z","cross_cats_sorted":[],"title_canon_sha256":"116bcf9b5d71668e38565b4ef42faf9b481833e0429587467b5a8fc1018e154d","abstract_canon_sha256":"d6afb1973eb253b58bca43ddd37ace48e22d5dd31f327b469b19d7ec6b3acff7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:02.068991Z","signature_b64":"RnKyze8XM59YIHdFJrZ8IapEqeFXNjxGjKSJBSZVLXDmNHWHOc3GypjTNRqvZR0HbLWgrvE2gMSrN7gKNhzPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16481db4c41c624e35c913b066e8ec5e14e0835ff56989a45ab27f402fde870c","last_reissued_at":"2026-07-05T11:46:02.068436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:02.068436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Yang, Duolin Sun, Jian Wang, Jie Feng, Jinjie Gu, Lei Liu, Peng Wei, Yihan Jiao, Yue Shen, Zhehao Tan","submitted_at":"2025-07-23T16:14:08Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination of a given query and retrieved documents is crucial. However, most benchmarks focus on overall RAG system performance, rarely assessing LLM-specific capabilities. Current benchmarks emphasize broad aspects such as noise robustness, but lack a systematic and granular evaluation framework on document utilization. To this end, we introduce \\textit{Placeholder-RAG-Benchmark}, a multi-level fine-grained benchmark, emphas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22927","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/2507.22927/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":"2507.22927","created_at":"2026-07-05T11:46:02.068499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22927v1","created_at":"2026-07-05T11:46:02.068499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22927","created_at":"2026-07-05T11:46:02.068499+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZEB3NGEDRRE","created_at":"2026-07-05T11:46:02.068499+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZEB3NGEDRRE4NOJ","created_at":"2026-07-05T11:46:02.068499+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZEB3NGE","created_at":"2026-07-05T11:46:02.068499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY","json":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY.json","graph_json":"https://pith.science/api/pith-number/CZEB3NGEDRRE4NOJCOYGN2HMLY/graph.json","events_json":"https://pith.science/api/pith-number/CZEB3NGEDRRE4NOJCOYGN2HMLY/events.json","paper":"https://pith.science/paper/CZEB3NGE"},"agent_actions":{"view_html":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY","download_json":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY.json","view_paper":"https://pith.science/paper/CZEB3NGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22927&json=true","fetch_graph":"https://pith.science/api/pith-number/CZEB3NGEDRRE4NOJCOYGN2HMLY/graph.json","fetch_events":"https://pith.science/api/pith-number/CZEB3NGEDRRE4NOJCOYGN2HMLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY/action/storage_attestation","attest_author":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY/action/author_attestation","sign_citation":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY/action/citation_signature","submit_replication":"https://pith.science/pith/CZEB3NGEDRRE4NOJCOYGN2HMLY/action/replication_record"}},"created_at":"2026-07-05T11:46:02.068499+00:00","updated_at":"2026-07-05T11:46:02.068499+00:00"}