{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D2LFRPRGCNIY3JMNB7QHIGS3US","short_pith_number":"pith:D2LFRPRG","schema_version":"1.0","canonical_sha256":"1e9658be2613518da58d0fe0741a5ba4aea3fbd1ec9bb737add23929a9e7a770","source":{"kind":"arxiv","id":"2605.13052","version":1},"attestation_state":"computed","paper":{"title":"RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Large language models infer query-specific validity horizons to replace static time filters in web search.","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Dawei Yin, Ge Chen, Li Gao, Lixin Su, Tingyu Chen, Wenkai Zhang","submitted_at":"2026-05-13T06:20:28Z","abstract_excerpt":"In commercial web search, aligning content freshness with user intent remains challenging due to the highly varied lifespans of information. Traditional industrial approaches rely on static time-window filtering, resulting in \"one-size-fits-all\" rankings where content may be chronologically recent but semantically expired. To address the limitation, we present a novel Large Language Models (LLMs)-based Query-Aware Dynamic Content Expiration Prediction Framework deployed in Baidu search, reformulating timeliness as a dynamic validity inference task. Our framework extracts fine-grained temporal "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-13T06:20:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3a3eb5a32fd3ea38a1f33e237171581644c2f64d4486226e1f22ef12525e371d","abstract_canon_sha256":"73199040857af0483f146ca09c99ea8b040094cb3ec2c78d5f9251c4d6b48874"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.282008Z","signature_b64":"UY5JNuVZRNyOS8Cw6c8R/9qdn9hPWhNs0si+3aaGIudIOYW/tMSHy5xaAxlrXSOQwe9+zPaUkYgCM0tOxqiwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e9658be2613518da58d0fe0741a5ba4aea3fbd1ec9bb737add23929a9e7a770","last_reissued_at":"2026-05-18T03:08:59.281183Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.281183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Large language models infer query-specific validity horizons to replace static time filters in web search.","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Dawei Yin, Ge Chen, Li Gao, Lixin Su, Tingyu Chen, Wenkai Zhang","submitted_at":"2026-05-13T06:20:28Z","abstract_excerpt":"In commercial web search, aligning content freshness with user intent remains challenging due to the highly varied lifespans of information. Traditional industrial approaches rely on static time-window filtering, resulting in \"one-size-fits-all\" rankings where content may be chronologically recent but semantically expired. To address the limitation, we present a novel Large Language Models (LLMs)-based Query-Aware Dynamic Content Expiration Prediction Framework deployed in Baidu search, reformulating timeliness as a dynamic validity inference task. Our framework extracts fine-grained temporal "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific 'validity horizon' ... Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs can reliably infer query-specific semantic expiration boundaries from document text with only the described hallucination mitigation strategies, without introducing systematic errors that would negate the reported A/B gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM framework with RAG predicts query-specific validity horizons for web content expiration and shows gains in production A/B tests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large language models infer query-specific validity horizons to replace static time filters in web search.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a5ea26da7f9bc355ce66f5887604f0a79aa19f5496273f7eb4be5c5b0d7d3393"},"source":{"id":"2605.13052","kind":"arxiv","version":1},"verdict":{"id":"c434d7d5-54ee-4850-80a5-4927a9c482aa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:37:50.515418Z","strongest_claim":"Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific 'validity horizon' ... Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.","one_line_summary":"An LLM framework with RAG predicts query-specific validity horizons for web content expiration and shows gains in production A/B tests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs can reliably infer query-specific semantic expiration boundaries from document text with only the described hallucination mitigation strategies, without introducing systematic errors that would negate the reported A/B gains.","pith_extraction_headline":"Large language models infer query-specific validity horizons to replace static time filters in web search."},"references":{"count":21,"sample":[{"doi":"","year":2025,"title":"Tempretriever: Fusion-based temporal dense passage retri eval for time-sensitive questions","work_id":"4fe8c21f-c0b5-470d-b3ce-1311db644d8b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Anlei Dong, Yi Chang, Zhaohui Zheng, Gilad Mishne, Jing Bai, Ruiqiang Zhang, Karolina Buchner, Ciya Liao, and Fernando Diaz. 2010. Towards recency ranking in web search. InProceedings of the Third ACM","work_id":"34d49b61-a0ae-45c0-9ce9-aea339f1c997","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/1772690.1772725","year":2010,"title":"Anlei Dong, Ruiqiang Zhang, Pranam Kolari, Jing Bai, Fernando Diaz, Yi Chang, Zhaohui Zheng, and Hongyuan Zha. 2010. Time is of the essence: improv- ing recency ranking using Twitter data. InProceedin","work_id":"7e40f3c7-d75e-428d-8b06-36358f3c6dfb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Rujun Han, Xiang Ren, and Nanyun Peng. 2021. ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning. arXiv:2012.15283 [cs.CL] https://arxiv.org/abs/2012.15283","work_id":"05afcc3f-870d-4d08-9dce-456b9060944f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Sufficient context: A new lens on retrieval augmented generation systems.arXiv preprint arXiv:2411.06037.2024","work_id":"1e7cc03c-2824-45f8-bc29-d9c46854c552","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"5c8c3fee89bf42581aa0a579bf13be93aebf77cbdd5b8a63caf551f26816929d","internal_anchors":2},"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":"2605.13052","created_at":"2026-05-18T03:08:59.281298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13052v1","created_at":"2026-05-18T03:08:59.281298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13052","created_at":"2026-05-18T03:08:59.281298+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2LFRPRGCNIY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2LFRPRGCNIY3JMN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2LFRPRG","created_at":"2026-05-18T12:33:37.589309+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/D2LFRPRGCNIY3JMNB7QHIGS3US","json":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US.json","graph_json":"https://pith.science/api/pith-number/D2LFRPRGCNIY3JMNB7QHIGS3US/graph.json","events_json":"https://pith.science/api/pith-number/D2LFRPRGCNIY3JMNB7QHIGS3US/events.json","paper":"https://pith.science/paper/D2LFRPRG"},"agent_actions":{"view_html":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US","download_json":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US.json","view_paper":"https://pith.science/paper/D2LFRPRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13052&json=true","fetch_graph":"https://pith.science/api/pith-number/D2LFRPRGCNIY3JMNB7QHIGS3US/graph.json","fetch_events":"https://pith.science/api/pith-number/D2LFRPRGCNIY3JMNB7QHIGS3US/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US/action/storage_attestation","attest_author":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US/action/author_attestation","sign_citation":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US/action/citation_signature","submit_replication":"https://pith.science/pith/D2LFRPRGCNIY3JMNB7QHIGS3US/action/replication_record"}},"created_at":"2026-05-18T03:08:59.281298+00:00","updated_at":"2026-05-18T03:08:59.281298+00:00"}