{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SYXBLT2BRLZAB4URNRTG6HR6QD","short_pith_number":"pith:SYXBLT2B","schema_version":"1.0","canonical_sha256":"962e15cf418af200f2916c666f1e3e80ed5fe6b21d9728ce011c73e028c0c406","source":{"kind":"arxiv","id":"2506.06015","version":1},"attestation_state":"computed","paper":{"title":"On the Merits of LLM-Based Corpus Enrichment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gal Zur, Moshe Tennenholtz, Oren Kurland, Tommy Mordo","submitted_at":"2025-06-06T12:02:14Z","abstract_excerpt":"Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a document corpus so as to improve query-based retrieval effectiveness. The enrichment is based on modifying existing documents or generating new ones. As an empirical proof of concept, we use LLMs to generate documents relevant to a topic which are more retrievable than existing ones. In addition, we demonstrate the potential merits of using corpus enrichment for retrieval augmented generation (RAG) and answer attributi"},"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":"2506.06015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-06T12:02:14Z","cross_cats_sorted":[],"title_canon_sha256":"14aa5472d34e038539d97595084cd00d6d3bfcbbd7d0762c6931c5215994cfd6","abstract_canon_sha256":"9990e5845baceb245b9470e2a0e5b48520f7bd59a5e6f3e71f5024e29736cc53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:14.631311Z","signature_b64":"qUHApuVsrr3n59nhYHzXfgZsTbhMzg68+CD48BuN6BiTxH56J7JfJf/oyehKOQIofVKCBSCGEvCwKOvYdrbjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962e15cf418af200f2916c666f1e3e80ed5fe6b21d9728ce011c73e028c0c406","last_reissued_at":"2026-07-05T11:17:14.630779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:14.630779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Merits of LLM-Based Corpus Enrichment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gal Zur, Moshe Tennenholtz, Oren Kurland, Tommy Mordo","submitted_at":"2025-06-06T12:02:14Z","abstract_excerpt":"Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a document corpus so as to improve query-based retrieval effectiveness. The enrichment is based on modifying existing documents or generating new ones. As an empirical proof of concept, we use LLMs to generate documents relevant to a topic which are more retrievable than existing ones. In addition, we demonstrate the potential merits of using corpus enrichment for retrieval augmented generation (RAG) and answer attributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06015","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/2506.06015/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":"2506.06015","created_at":"2026-07-05T11:17:14.630850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06015v1","created_at":"2026-07-05T11:17:14.630850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06015","created_at":"2026-07-05T11:17:14.630850+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYXBLT2BRLZA","created_at":"2026-07-05T11:17:14.630850+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYXBLT2BRLZAB4UR","created_at":"2026-07-05T11:17:14.630850+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYXBLT2B","created_at":"2026-07-05T11:17:14.630850+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/SYXBLT2BRLZAB4URNRTG6HR6QD","json":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD.json","graph_json":"https://pith.science/api/pith-number/SYXBLT2BRLZAB4URNRTG6HR6QD/graph.json","events_json":"https://pith.science/api/pith-number/SYXBLT2BRLZAB4URNRTG6HR6QD/events.json","paper":"https://pith.science/paper/SYXBLT2B"},"agent_actions":{"view_html":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD","download_json":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD.json","view_paper":"https://pith.science/paper/SYXBLT2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06015&json=true","fetch_graph":"https://pith.science/api/pith-number/SYXBLT2BRLZAB4URNRTG6HR6QD/graph.json","fetch_events":"https://pith.science/api/pith-number/SYXBLT2BRLZAB4URNRTG6HR6QD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD/action/storage_attestation","attest_author":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD/action/author_attestation","sign_citation":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD/action/citation_signature","submit_replication":"https://pith.science/pith/SYXBLT2BRLZAB4URNRTG6HR6QD/action/replication_record"}},"created_at":"2026-07-05T11:17:14.630850+00:00","updated_at":"2026-07-05T11:17:14.630850+00:00"}