{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ORCFBBVFPR5QANGUDFB24QFOGF","short_pith_number":"pith:ORCFBBVF","schema_version":"1.0","canonical_sha256":"74445086a57c7b0034d41943ae40ae317a158dca0b2763e08475f1a6c99604a6","source":{"kind":"arxiv","id":"2606.12789","version":1},"attestation_state":"computed","paper":{"title":"How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chase M. Fensore, Eugene Agichtein, Jason Fan, Joyce C. Ho, Kaustubh Dhole","submitted_at":"2026-06-11T01:14:07Z","abstract_excerpt":"Evaluating retrieval-augmented generation (RAG) systems requires benchmarks that capture diverse question characteristics, yet practitioners lack empirical guidance on which dimensions to vary and at what granularity. We present HieraRAG, a hierarchical framework for studying granularity in RAG benchmark construction, defining optimal granularity as the level that maximizes discriminative power (the standard deviation of generation quality across categories) within a given RAG configuration. As a case study, we generate 5,872 synthetic question-answer (QA) pairs from FineWeb-10BT across 3 dime"},"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":"2606.12789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T01:14:07Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"80e7a5e28f6291db62097707b92f7c9e44ae5caecaae7fd0c8d609eb2528839f","abstract_canon_sha256":"ccab09ceef5bb59adcbb9ede6798ed5831061a1c9cf10346c5a3a44027a97b80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:51.200364Z","signature_b64":"9qfbxICWYV11+NytfPQvdNBGwN+NzInK8evVkZMH8SlscjkGey/Hg3Lr/W/VFB/bfEPljcpurCfono149rdMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74445086a57c7b0034d41943ae40ae317a158dca0b2763e08475f1a6c99604a6","last_reissued_at":"2026-06-12T01:08:51.199864Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:51.199864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chase M. Fensore, Eugene Agichtein, Jason Fan, Joyce C. Ho, Kaustubh Dhole","submitted_at":"2026-06-11T01:14:07Z","abstract_excerpt":"Evaluating retrieval-augmented generation (RAG) systems requires benchmarks that capture diverse question characteristics, yet practitioners lack empirical guidance on which dimensions to vary and at what granularity. We present HieraRAG, a hierarchical framework for studying granularity in RAG benchmark construction, defining optimal granularity as the level that maximizes discriminative power (the standard deviation of generation quality across categories) within a given RAG configuration. As a case study, we generate 5,872 synthetic question-answer (QA) pairs from FineWeb-10BT across 3 dime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12789","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/2606.12789/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":"2606.12789","created_at":"2026-06-12T01:08:51.199931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12789v1","created_at":"2026-06-12T01:08:51.199931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12789","created_at":"2026-06-12T01:08:51.199931+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORCFBBVFPR5Q","created_at":"2026-06-12T01:08:51.199931+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORCFBBVFPR5QANGU","created_at":"2026-06-12T01:08:51.199931+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORCFBBVF","created_at":"2026-06-12T01:08:51.199931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF","json":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF.json","graph_json":"https://pith.science/api/pith-number/ORCFBBVFPR5QANGUDFB24QFOGF/graph.json","events_json":"https://pith.science/api/pith-number/ORCFBBVFPR5QANGUDFB24QFOGF/events.json","paper":"https://pith.science/paper/ORCFBBVF"},"agent_actions":{"view_html":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF","download_json":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF.json","view_paper":"https://pith.science/paper/ORCFBBVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12789&json=true","fetch_graph":"https://pith.science/api/pith-number/ORCFBBVFPR5QANGUDFB24QFOGF/graph.json","fetch_events":"https://pith.science/api/pith-number/ORCFBBVFPR5QANGUDFB24QFOGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF/action/storage_attestation","attest_author":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF/action/author_attestation","sign_citation":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF/action/citation_signature","submit_replication":"https://pith.science/pith/ORCFBBVFPR5QANGUDFB24QFOGF/action/replication_record"}},"created_at":"2026-06-12T01:08:51.199931+00:00","updated_at":"2026-06-12T01:08:51.199931+00:00"}