{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OBIY5GXQPUW5ICJJPSA3I7MSWU","short_pith_number":"pith:OBIY5GXQ","schema_version":"1.0","canonical_sha256":"70518e9af07d2dd409297c81b47d92b508910cd0b19385a81944510be8771607","source":{"kind":"arxiv","id":"2406.09459","version":2},"attestation_state":"computed","paper":{"title":"Ad Auctions for LLMs via Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.GT","authors_text":"Keivan Rezaei, MohammadTaghi Hajiaghayi, S\\'ebastien Lahaie, Suho Shin","submitted_at":"2024-06-12T22:05:51Z","abstract_excerpt":"In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to compet"},"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":"2406.09459","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-06-12T22:05:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"f03073f6ace1358bb13c1b12356d7f7f9d7ffdb3bd13134387a57e50e41e1e09","abstract_canon_sha256":"03156eae44453ded67608e93362c0a9da7478bd52647f94bc9d931142c3c55ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:44.936936Z","signature_b64":"TErRIGVPkQOxpXi554oU0sIlnXuvrqB48XVhrhy9KzmAhdeSmgYthrw8CNT6mhUCgLHzizpAg2HiGW4zp9EjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70518e9af07d2dd409297c81b47d92b508910cd0b19385a81944510be8771607","last_reissued_at":"2026-07-05T11:20:44.936438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:44.936438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ad Auctions for LLMs via Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.GT","authors_text":"Keivan Rezaei, MohammadTaghi Hajiaghayi, S\\'ebastien Lahaie, Suho Shin","submitted_at":"2024-06-12T22:05:51Z","abstract_excerpt":"In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to compet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09459","kind":"arxiv","version":2},"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/2406.09459/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":"2406.09459","created_at":"2026-07-05T11:20:44.936503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09459v2","created_at":"2026-07-05T11:20:44.936503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09459","created_at":"2026-07-05T11:20:44.936503+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBIY5GXQPUW5","created_at":"2026-07-05T11:20:44.936503+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBIY5GXQPUW5ICJJ","created_at":"2026-07-05T11:20:44.936503+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBIY5GXQ","created_at":"2026-07-05T11:20:44.936503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.04925","citing_title":"Detecting RAG Advertisements Across Advertising Styles","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08326","citing_title":"LLM Advertisement based on Neuron Auctions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU","json":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU.json","graph_json":"https://pith.science/api/pith-number/OBIY5GXQPUW5ICJJPSA3I7MSWU/graph.json","events_json":"https://pith.science/api/pith-number/OBIY5GXQPUW5ICJJPSA3I7MSWU/events.json","paper":"https://pith.science/paper/OBIY5GXQ"},"agent_actions":{"view_html":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU","download_json":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU.json","view_paper":"https://pith.science/paper/OBIY5GXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09459&json=true","fetch_graph":"https://pith.science/api/pith-number/OBIY5GXQPUW5ICJJPSA3I7MSWU/graph.json","fetch_events":"https://pith.science/api/pith-number/OBIY5GXQPUW5ICJJPSA3I7MSWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU/action/storage_attestation","attest_author":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU/action/author_attestation","sign_citation":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU/action/citation_signature","submit_replication":"https://pith.science/pith/OBIY5GXQPUW5ICJJPSA3I7MSWU/action/replication_record"}},"created_at":"2026-07-05T11:20:44.936503+00:00","updated_at":"2026-07-05T11:20:44.936503+00:00"}