{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CC7QO2MLWKYY3ISYBDO5MJ63E","short_pith_number":"pith:2CC7QO2M","schema_version":"1.0","canonical_sha256":"d085f83b4c5d958c6d12c046eeb13ed9350cfe3686c9dbda0afce955fc8f7354","source":{"kind":"arxiv","id":"2406.03592","version":1},"attestation_state":"computed","paper":{"title":"Measuring Retrieval Complexity in Question Answering Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alessandro Moschitti, Leonardo F. R. Ribeiro, Matteo Gabburo, Nicolaas Paul Jedema, Siddhant Garg","submitted_at":"2024-06-05T19:30:52Z","abstract_excerpt":"In this paper, we investigate which questions are challenging for retrieval-based Question Answering (QA). We (i) propose retrieval complexity (RC), a novel metric conditioned on the completeness of retrieved documents, which measures the difficulty of answering questions, and (ii) propose an unsupervised pipeline to measure RC given an arbitrary retrieval system. Our proposed pipeline measures RC more accurately than alternative estimators, including LLMs, on six challenging QA benchmarks. Further investigation reveals that RC scores strongly correlate with both QA performance and expert judg"},"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":"2406.03592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T19:30:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05791ba795998e0d43bc2705534bbf560a4bd401428b77f87099c2fcd9cc2d44","abstract_canon_sha256":"127d1410649b483a3fb01575e4efa7a8d8c6328db5ccc6a01733b3cd303062a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:13.387264Z","signature_b64":"nE6yvCftN19J0HFJs1oS45WTe0CR1mNzdvYLAB850eRJ+QbKNs2iK9VbbkqTZf1HoppNAOi73qihskCh4WmhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d085f83b4c5d958c6d12c046eeb13ed9350cfe3686c9dbda0afce955fc8f7354","last_reissued_at":"2026-07-05T08:28:13.386786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:13.386786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Retrieval Complexity in Question Answering Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alessandro Moschitti, Leonardo F. R. Ribeiro, Matteo Gabburo, Nicolaas Paul Jedema, Siddhant Garg","submitted_at":"2024-06-05T19:30:52Z","abstract_excerpt":"In this paper, we investigate which questions are challenging for retrieval-based Question Answering (QA). We (i) propose retrieval complexity (RC), a novel metric conditioned on the completeness of retrieved documents, which measures the difficulty of answering questions, and (ii) propose an unsupervised pipeline to measure RC given an arbitrary retrieval system. Our proposed pipeline measures RC more accurately than alternative estimators, including LLMs, on six challenging QA benchmarks. Further investigation reveals that RC scores strongly correlate with both QA performance and expert judg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03592","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/2406.03592/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":"2406.03592","created_at":"2026-07-05T08:28:13.386843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03592v1","created_at":"2026-07-05T08:28:13.386843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03592","created_at":"2026-07-05T08:28:13.386843+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CC7QO2MLWKY","created_at":"2026-07-05T08:28:13.386843+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CC7QO2MLWKYY3IS","created_at":"2026-07-05T08:28:13.386843+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CC7QO2M","created_at":"2026-07-05T08:28:13.386843+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/2CC7QO2MLWKYY3ISYBDO5MJ63E","json":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E.json","graph_json":"https://pith.science/api/pith-number/2CC7QO2MLWKYY3ISYBDO5MJ63E/graph.json","events_json":"https://pith.science/api/pith-number/2CC7QO2MLWKYY3ISYBDO5MJ63E/events.json","paper":"https://pith.science/paper/2CC7QO2M"},"agent_actions":{"view_html":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E","download_json":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E.json","view_paper":"https://pith.science/paper/2CC7QO2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03592&json=true","fetch_graph":"https://pith.science/api/pith-number/2CC7QO2MLWKYY3ISYBDO5MJ63E/graph.json","fetch_events":"https://pith.science/api/pith-number/2CC7QO2MLWKYY3ISYBDO5MJ63E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E/action/storage_attestation","attest_author":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E/action/author_attestation","sign_citation":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E/action/citation_signature","submit_replication":"https://pith.science/pith/2CC7QO2MLWKYY3ISYBDO5MJ63E/action/replication_record"}},"created_at":"2026-07-05T08:28:13.386843+00:00","updated_at":"2026-07-05T08:28:13.386843+00:00"}