{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2AWSG5SZ453265TKE6XA3BIPP4","short_pith_number":"pith:2AWSG5SZ","schema_version":"1.0","canonical_sha256":"d02d237659e777af766a27ae0d850f7f09296bf97b5bc3c5996779326013e9d9","source":{"kind":"arxiv","id":"2505.17162","version":1},"attestation_state":"computed","paper":{"title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jiehan Cheng, Zhicheng Dou","submitted_at":"2025-05-22T15:13:33Z","abstract_excerpt":"We propose DailyQA, an automatically updated dynamic dataset that updates questions weekly and contains answers to questions on any given date. DailyQA utilizes daily updates from Wikipedia revision logs to implement a fully automated pipeline of data filtering, query generation synthesis, quality checking, answer extraction, and query classification. The benchmark requires large language models (LLMs) to process and answer questions involving fast-changing factual data and covering multiple domains. We evaluate several open-source and closed-source LLMs using different RAG pipelines with web "},"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":"2505.17162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T15:13:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d50af399839602455be688ab0430226f5dc59a508e3f292a9cc6c826ee03abd5","abstract_canon_sha256":"4970318729e8193527fc10ee118d3c6ed6137e8c7788d22613f59f0ba9e86061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:48.146617Z","signature_b64":"wDNqoUrRsyGqSbHcZUUkcTk5Ce2O9o9pCEEwWP5Cn5HnHtAA0MzTU8bFExRwpHCxDBWw1g2gRbXDlzG9c3tBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02d237659e777af766a27ae0d850f7f09296bf97b5bc3c5996779326013e9d9","last_reissued_at":"2026-07-05T11:07:48.146118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:48.146118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jiehan Cheng, Zhicheng Dou","submitted_at":"2025-05-22T15:13:33Z","abstract_excerpt":"We propose DailyQA, an automatically updated dynamic dataset that updates questions weekly and contains answers to questions on any given date. DailyQA utilizes daily updates from Wikipedia revision logs to implement a fully automated pipeline of data filtering, query generation synthesis, quality checking, answer extraction, and query classification. The benchmark requires large language models (LLMs) to process and answer questions involving fast-changing factual data and covering multiple domains. We evaluate several open-source and closed-source LLMs using different RAG pipelines with web "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17162","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/2505.17162/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":"2505.17162","created_at":"2026-07-05T11:07:48.146177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17162v1","created_at":"2026-07-05T11:07:48.146177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17162","created_at":"2026-07-05T11:07:48.146177+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AWSG5SZ4532","created_at":"2026-07-05T11:07:48.146177+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AWSG5SZ453265TK","created_at":"2026-07-05T11:07:48.146177+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AWSG5SZ","created_at":"2026-07-05T11:07:48.146177+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/2AWSG5SZ453265TKE6XA3BIPP4","json":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4.json","graph_json":"https://pith.science/api/pith-number/2AWSG5SZ453265TKE6XA3BIPP4/graph.json","events_json":"https://pith.science/api/pith-number/2AWSG5SZ453265TKE6XA3BIPP4/events.json","paper":"https://pith.science/paper/2AWSG5SZ"},"agent_actions":{"view_html":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4","download_json":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4.json","view_paper":"https://pith.science/paper/2AWSG5SZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17162&json=true","fetch_graph":"https://pith.science/api/pith-number/2AWSG5SZ453265TKE6XA3BIPP4/graph.json","fetch_events":"https://pith.science/api/pith-number/2AWSG5SZ453265TKE6XA3BIPP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4/action/storage_attestation","attest_author":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4/action/author_attestation","sign_citation":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4/action/citation_signature","submit_replication":"https://pith.science/pith/2AWSG5SZ453265TKE6XA3BIPP4/action/replication_record"}},"created_at":"2026-07-05T11:07:48.146177+00:00","updated_at":"2026-07-05T11:07:48.146177+00:00"}