{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SZWQMJHBO2L5NXWHKZFY7PUQRN","short_pith_number":"pith:SZWQMJHB","schema_version":"1.0","canonical_sha256":"966d0624e17697d6dec7564b8fbe908b79f8403baa29071007392ef43ecf267a","source":{"kind":"arxiv","id":"2404.01012","version":3},"attestation_state":"computed","paper":{"title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Arian Askari, Chuan Meng, Maarten de Rijke, Mohammad Aliannejadi, Negar Arabzadeh","submitted_at":"2024-04-01T09:33:05Z","abstract_excerpt":"Query performance prediction (QPP) aims to estimate the retrieval quality of a search system for a query without human relevance judgments. Previous QPP methods typically return a single scalar value and do not require the predicted values to approximate a specific information retrieval (IR) evaluation measure, leading to certain drawbacks: (i) a single scalar is insufficient to accurately represent different IR evaluation measures, especially when metrics do not highly correlate, and (ii) a single scalar limits the interpretability of QPP methods because solely using a scalar is insufficient "},"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":"2404.01012","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-04-01T09:33:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"4acedc0245322c109c320ed823ea611d865c6a557d7e135754bbad0987fff092","abstract_canon_sha256":"5b5db4fc108ba8914fabcc4819e16c37222bad8c892652de1f68ccee080470fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:57.011120Z","signature_b64":"WRiyU9BJ5h/7T6rm3x9jZdlUlXaqnIJ+Onzddjd2iq7HIrzmrgjZvTEGzFW1hxIt2S9bYN7U8lM6MgmWVooGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966d0624e17697d6dec7564b8fbe908b79f8403baa29071007392ef43ecf267a","last_reissued_at":"2026-07-05T11:08:57.010681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:57.010681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Arian Askari, Chuan Meng, Maarten de Rijke, Mohammad Aliannejadi, Negar Arabzadeh","submitted_at":"2024-04-01T09:33:05Z","abstract_excerpt":"Query performance prediction (QPP) aims to estimate the retrieval quality of a search system for a query without human relevance judgments. Previous QPP methods typically return a single scalar value and do not require the predicted values to approximate a specific information retrieval (IR) evaluation measure, leading to certain drawbacks: (i) a single scalar is insufficient to accurately represent different IR evaluation measures, especially when metrics do not highly correlate, and (ii) a single scalar limits the interpretability of QPP methods because solely using a scalar is insufficient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01012","kind":"arxiv","version":3},"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/2404.01012/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":"2404.01012","created_at":"2026-07-05T11:08:57.010738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01012v3","created_at":"2026-07-05T11:08:57.010738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01012","created_at":"2026-07-05T11:08:57.010738+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZWQMJHBO2L5","created_at":"2026-07-05T11:08:57.010738+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZWQMJHBO2L5NXWH","created_at":"2026-07-05T11:08:57.010738+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZWQMJHB","created_at":"2026-07-05T11:08:57.010738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25249","citing_title":"Adaptive Re-Ranking","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27244","citing_title":"RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN","json":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN.json","graph_json":"https://pith.science/api/pith-number/SZWQMJHBO2L5NXWHKZFY7PUQRN/graph.json","events_json":"https://pith.science/api/pith-number/SZWQMJHBO2L5NXWHKZFY7PUQRN/events.json","paper":"https://pith.science/paper/SZWQMJHB"},"agent_actions":{"view_html":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN","download_json":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN.json","view_paper":"https://pith.science/paper/SZWQMJHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01012&json=true","fetch_graph":"https://pith.science/api/pith-number/SZWQMJHBO2L5NXWHKZFY7PUQRN/graph.json","fetch_events":"https://pith.science/api/pith-number/SZWQMJHBO2L5NXWHKZFY7PUQRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN/action/storage_attestation","attest_author":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN/action/author_attestation","sign_citation":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN/action/citation_signature","submit_replication":"https://pith.science/pith/SZWQMJHBO2L5NXWHKZFY7PUQRN/action/replication_record"}},"created_at":"2026-07-05T11:08:57.010738+00:00","updated_at":"2026-07-05T11:08:57.010738+00:00"}