{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SYXBLT2BRLZAB4URNRTG6HR6QD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9990e5845baceb245b9470e2a0e5b48520f7bd59a5e6f3e71f5024e29736cc53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-06T12:02:14Z","title_canon_sha256":"14aa5472d34e038539d97595084cd00d6d3bfcbbd7d0762c6931c5215994cfd6"},"schema_version":"1.0","source":{"id":"2506.06015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06015","created_at":"2026-07-05T11:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06015v1","created_at":"2026-07-05T11:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06015","created_at":"2026-07-05T11:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"SYXBLT2BRLZA","created_at":"2026-07-05T11:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"SYXBLT2BRLZAB4UR","created_at":"2026-07-05T11:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"SYXBLT2B","created_at":"2026-07-05T11:17:14Z"}],"graph_snapshots":[{"event_id":"sha256:7153636f93ca542bc2654a181c2f044d02475e32a7b94a6e65ed50b6ea958f12","target":"graph","created_at":"2026-07-05T11:17:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gal Zur, Moshe Tennenholtz, Oren Kurland, Tommy Mordo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-06T12:02:14Z","title":"On the Merits of LLM-Based Corpus Enrichment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06015","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b286c0ab9b2bfc95b09fe633092b09239e68a1b577551bc3a7189129b7ec2d9","target":"record","created_at":"2026-07-05T11:17:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9990e5845baceb245b9470e2a0e5b48520f7bd59a5e6f3e71f5024e29736cc53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-06T12:02:14Z","title_canon_sha256":"14aa5472d34e038539d97595084cd00d6d3bfcbbd7d0762c6931c5215994cfd6"},"schema_version":"1.0","source":{"id":"2506.06015","kind":"arxiv","version":1}},"canonical_sha256":"962e15cf418af200f2916c666f1e3e80ed5fe6b21d9728ce011c73e028c0c406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"962e15cf418af200f2916c666f1e3e80ed5fe6b21d9728ce011c73e028c0c406","first_computed_at":"2026-07-05T11:17:14.630779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:14.630779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qUHApuVsrr3n59nhYHzXfgZsTbhMzg68+CD48BuN6BiTxH56J7JfJf/oyehKOQIofVKCBSCGEvCwKOvYdrbjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:14.631311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b286c0ab9b2bfc95b09fe633092b09239e68a1b577551bc3a7189129b7ec2d9","sha256:7153636f93ca542bc2654a181c2f044d02475e32a7b94a6e65ed50b6ea958f12"],"state_sha256":"7af1391e4f2f83a35ea432617f4ea69b800d3346278e049aadd4b91ece233c26"}