{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q4IKQFD4KJJVUN6VIW3U4HSVN5","short_pith_number":"pith:Q4IKQFD4","schema_version":"1.0","canonical_sha256":"8710a8147c52535a37d545b74e1e556f5e294f8ac43a281caec2cee4f0feea44","source":{"kind":"arxiv","id":"2606.29947","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"(2) Stanford University, (3) Independent Researcher), Fang Qin (2), Manish Shah (3), Yicheng Wang (3) ((1) University of Maine at Presque Isle, Zhe Dong (1)","submitted_at":"2026-06-29T08:23:40Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes. We test this assumption with a five-domain benchmark that explicitly separates reranking quality from retrieval coverage. In a positive-controlled regime where the gold item is guaranteed present, calibrated LLM rerankers fail to consistently outperform strong collaborative and content baselines under natural traffic, and within-family scaling from Qwen3-8B to Qwen3-32B narrows but does not close the gap on most "},"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":"2606.29947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-29T08:23:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6e8bd3b55fe69a5d3b02c62fa227100ff68fccc8d1fd038a1495fb02c052b6f","abstract_canon_sha256":"7549d15b85fa28033b26a67aa9d67322fc4697908182f217f321f88f99b5c795"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:42.202699Z","signature_b64":"+X8vr6+AxV62ycrG7nsh4vW5Ifp+/Y3oysIEjxMo0C2kmOkMEeeEh0TMoBnq+zbjsYu9KILFL6YaiWBynhnRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8710a8147c52535a37d545b74e1e556f5e294f8ac43a281caec2cee4f0feea44","last_reissued_at":"2026-06-30T02:17:42.202177Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:42.202177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"(2) Stanford University, (3) Independent Researcher), Fang Qin (2), Manish Shah (3), Yicheng Wang (3) ((1) University of Maine at Presque Isle, Zhe Dong (1)","submitted_at":"2026-06-29T08:23:40Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes. We test this assumption with a five-domain benchmark that explicitly separates reranking quality from retrieval coverage. In a positive-controlled regime where the gold item is guaranteed present, calibrated LLM rerankers fail to consistently outperform strong collaborative and content baselines under natural traffic, and within-family scaling from Qwen3-8B to Qwen3-32B narrows but does not close the gap on most "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29947","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/2606.29947/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":"2606.29947","created_at":"2026-06-30T02:17:42.202255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29947v1","created_at":"2026-06-30T02:17:42.202255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29947","created_at":"2026-06-30T02:17:42.202255+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4IKQFD4KJJV","created_at":"2026-06-30T02:17:42.202255+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4IKQFD4KJJVUN6V","created_at":"2026-06-30T02:17:42.202255+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4IKQFD4","created_at":"2026-06-30T02:17:42.202255+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/Q4IKQFD4KJJVUN6VIW3U4HSVN5","json":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5.json","graph_json":"https://pith.science/api/pith-number/Q4IKQFD4KJJVUN6VIW3U4HSVN5/graph.json","events_json":"https://pith.science/api/pith-number/Q4IKQFD4KJJVUN6VIW3U4HSVN5/events.json","paper":"https://pith.science/paper/Q4IKQFD4"},"agent_actions":{"view_html":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5","download_json":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5.json","view_paper":"https://pith.science/paper/Q4IKQFD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29947&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4IKQFD4KJJVUN6VIW3U4HSVN5/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4IKQFD4KJJVUN6VIW3U4HSVN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5/action/storage_attestation","attest_author":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5/action/author_attestation","sign_citation":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5/action/citation_signature","submit_replication":"https://pith.science/pith/Q4IKQFD4KJJVUN6VIW3U4HSVN5/action/replication_record"}},"created_at":"2026-06-30T02:17:42.202255+00:00","updated_at":"2026-06-30T02:17:42.202255+00:00"}