{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQBJQO4ZFHT5VKVAV7M24TXA7V","short_pith_number":"pith:JQBJQO4Z","schema_version":"1.0","canonical_sha256":"4c02983b9929e7daaaa0afd9ae4ee0fd5989f5f41d0918dde0fe6f73052196eb","source":{"kind":"arxiv","id":"2405.05905","version":5},"attestation_state":"computed","paper":{"title":"Truthful Aggregation of LLMs with an Application to Online Advertising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Ermis Soumalias, Michael J. Curry, Sven Seuken","submitted_at":"2024-05-09T17:01:31Z","abstract_excerpt":"The next frontier of online advertising is revenue generation from LLM-generated content. We consider a setting where advertisers aim to influence the responses of an LLM to align with their interests, while platforms seek to maximize advertiser value and ensure user satisfaction. The challenge is that advertisers' preferences generally conflict with those of the user, and advertisers may misreport their preferences. To address this, we introduce MOSAIC, an auction mechanism that ensures that truthful reporting is a dominant strategy for advertisers and that aligns the utility of each advertis"},"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":"2405.05905","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-09T17:01:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be7593c25e15c5570396fb19444adb6869c3eeee1cf7d8076fab2941705b1f1b","abstract_canon_sha256":"2263adf4ecc12bc9f1946516019001b12f8e8555a8f9bb4fa9cf2b0e68337b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:00.086370Z","signature_b64":"XqetuCHd1748ViWWWRKxwQdV6VwctkwWyI0HT7Mp77OKdRxdQZ9ZygLALvoZNiv0gaEWFCknpF9m3wiarNSRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c02983b9929e7daaaa0afd9ae4ee0fd5989f5f41d0918dde0fe6f73052196eb","last_reissued_at":"2026-07-05T10:13:00.085825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:00.085825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Truthful Aggregation of LLMs with an Application to Online Advertising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Ermis Soumalias, Michael J. Curry, Sven Seuken","submitted_at":"2024-05-09T17:01:31Z","abstract_excerpt":"The next frontier of online advertising is revenue generation from LLM-generated content. We consider a setting where advertisers aim to influence the responses of an LLM to align with their interests, while platforms seek to maximize advertiser value and ensure user satisfaction. The challenge is that advertisers' preferences generally conflict with those of the user, and advertisers may misreport their preferences. To address this, we introduce MOSAIC, an auction mechanism that ensures that truthful reporting is a dominant strategy for advertisers and that aligns the utility of each advertis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05905","kind":"arxiv","version":5},"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/2405.05905/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":"2405.05905","created_at":"2026-07-05T10:13:00.085888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05905v5","created_at":"2026-07-05T10:13:00.085888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05905","created_at":"2026-07-05T10:13:00.085888+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQBJQO4ZFHT5","created_at":"2026-07-05T10:13:00.085888+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQBJQO4ZFHT5VKVA","created_at":"2026-07-05T10:13:00.085888+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQBJQO4Z","created_at":"2026-07-05T10:13:00.085888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24052","citing_title":"Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18673","citing_title":"Generative AI Advertising as a Problem of Trustworthy Commercial Intervention","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16474","citing_title":"LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04925","citing_title":"Detecting RAG Advertisements Across Advertising Styles","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10964","citing_title":"Mechanism Design for Quality-Preserving LLM Advertising","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09918","citing_title":"NaiAD: Initiate Data-Driven Research for LLM Advertising","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10440","citing_title":"TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V","json":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V.json","graph_json":"https://pith.science/api/pith-number/JQBJQO4ZFHT5VKVAV7M24TXA7V/graph.json","events_json":"https://pith.science/api/pith-number/JQBJQO4ZFHT5VKVAV7M24TXA7V/events.json","paper":"https://pith.science/paper/JQBJQO4Z"},"agent_actions":{"view_html":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V","download_json":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V.json","view_paper":"https://pith.science/paper/JQBJQO4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05905&json=true","fetch_graph":"https://pith.science/api/pith-number/JQBJQO4ZFHT5VKVAV7M24TXA7V/graph.json","fetch_events":"https://pith.science/api/pith-number/JQBJQO4ZFHT5VKVAV7M24TXA7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V/action/storage_attestation","attest_author":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V/action/author_attestation","sign_citation":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V/action/citation_signature","submit_replication":"https://pith.science/pith/JQBJQO4ZFHT5VKVAV7M24TXA7V/action/replication_record"}},"created_at":"2026-07-05T10:13:00.085888+00:00","updated_at":"2026-07-05T10:13:00.085888+00:00"}