{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5WFIMLJ5LRDDPQCN4656N4JLIJ","short_pith_number":"pith:5WFIMLJ5","schema_version":"1.0","canonical_sha256":"ed8a862d3d5c4637c04de7bbe6f12b4279d53f3806ddf690628bcfd2163d364c","source":{"kind":"arxiv","id":"2507.00509","version":1},"attestation_state":"computed","paper":{"title":"TeamCMU at Touch\\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gbemileke Onilude, Jai Singh, Jo\\~ao Coelho, To Eun Kim","submitted_at":"2025-07-01T07:24:29Z","abstract_excerpt":"As conversational search engines increasingly adopt generation-based paradigms powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), the integration of advertisements into generated responses presents both commercial opportunities and challenges for user experience. Unlike traditional search, where advertisements are clearly delineated, generative systems blur the boundary between informational content and promotional material, raising concerns around transparency and trust. In this work, we propose a modular pipeline for advertisement management in RAG-based conver"},"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":"2507.00509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T07:24:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c4d43b4c72dffbcaa00ff624a473f0c7faafd6ddf07245eabce91cdec1a7dfa","abstract_canon_sha256":"07e90ee6ce8aacb239f11e72e008949502300b53c98dd3447a52c43628892207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:10.063344Z","signature_b64":"R3f3d3h7OgG4PJjiRMMQxb9CVZtZSz/pnB2pidd7KGqK/KAsvEpcMT7c/k9tnLS2Qn82eUNgQZVY4PDsHPf/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8a862d3d5c4637c04de7bbe6f12b4279d53f3806ddf690628bcfd2163d364c","last_reissued_at":"2026-07-05T11:30:10.062862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:10.062862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TeamCMU at Touch\\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gbemileke Onilude, Jai Singh, Jo\\~ao Coelho, To Eun Kim","submitted_at":"2025-07-01T07:24:29Z","abstract_excerpt":"As conversational search engines increasingly adopt generation-based paradigms powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), the integration of advertisements into generated responses presents both commercial opportunities and challenges for user experience. Unlike traditional search, where advertisements are clearly delineated, generative systems blur the boundary between informational content and promotional material, raising concerns around transparency and trust. In this work, we propose a modular pipeline for advertisement management in RAG-based conver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00509","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/2507.00509/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":"2507.00509","created_at":"2026-07-05T11:30:10.062920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00509v1","created_at":"2026-07-05T11:30:10.062920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00509","created_at":"2026-07-05T11:30:10.062920+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WFIMLJ5LRDD","created_at":"2026-07-05T11:30:10.062920+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WFIMLJ5LRDDPQCN","created_at":"2026-07-05T11:30:10.062920+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WFIMLJ5","created_at":"2026-07-05T11:30:10.062920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27511","citing_title":"When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18673","citing_title":"Generative AI Advertising as a Problem of Trustworthy Commercial Intervention","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ","json":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ.json","graph_json":"https://pith.science/api/pith-number/5WFIMLJ5LRDDPQCN4656N4JLIJ/graph.json","events_json":"https://pith.science/api/pith-number/5WFIMLJ5LRDDPQCN4656N4JLIJ/events.json","paper":"https://pith.science/paper/5WFIMLJ5"},"agent_actions":{"view_html":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ","download_json":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ.json","view_paper":"https://pith.science/paper/5WFIMLJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00509&json=true","fetch_graph":"https://pith.science/api/pith-number/5WFIMLJ5LRDDPQCN4656N4JLIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5WFIMLJ5LRDDPQCN4656N4JLIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ/action/storage_attestation","attest_author":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ/action/author_attestation","sign_citation":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ/action/citation_signature","submit_replication":"https://pith.science/pith/5WFIMLJ5LRDDPQCN4656N4JLIJ/action/replication_record"}},"created_at":"2026-07-05T11:30:10.062920+00:00","updated_at":"2026-07-05T11:30:10.062920+00:00"}