{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DI7BASMP2UODEWEFBQHSAYDKSI","short_pith_number":"pith:DI7BASMP","schema_version":"1.0","canonical_sha256":"1a3e10498fd51c3258850c0f20606a9237c7b7b0c623a44cd0a06f54f7b132d7","source":{"kind":"arxiv","id":"2404.15058","version":1},"attestation_state":"computed","paper":{"title":"A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Amanda McCroskery, Arianna Manzini, Arthur Douillard, Canfer Akbulut, Daniel Susser, Geoff Keeling, Harry Law, Matija Franklin, Matthew Rahtz, Michael Henry Tessler, Murray Shanahan, Nahema Marchal, Sasha Brown, Seliem El-Sayed, Shannon Vallor, Sophie Bridgers, Toby Shevlane, Tom Everitt, Zachary Kenton, Zaria Jalan","submitted_at":"2024-04-23T14:07:20Z","abstract_excerpt":"Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generative AI presents a new risk profile of persuasion due the opportunity for reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion. The current definitions of AI persuasion are unclear and related harms are insufficiently studied. Existing harm mitigation approaches priori"},"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":"2404.15058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-04-23T14:07:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f0fdd62776df4f1af0e073e18ccd37924134a8d0afd16a924fcb6e79539549d","abstract_canon_sha256":"f10e2a6b128caf39c3f0d8af8a0b0b0068c3442b133a29e23570096cf23f420c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:14.691908Z","signature_b64":"vyI9RaycaHlI7xjhCI/LyM5OD7MtevQ6cq3d3mEVrX38T1QzQXxN3grsGYMxgVVEFQCmQWm2ilbvigXWZFEDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3e10498fd51c3258850c0f20606a9237c7b7b0c623a44cd0a06f54f7b132d7","last_reissued_at":"2026-07-05T08:11:14.691444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:14.691444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Amanda McCroskery, Arianna Manzini, Arthur Douillard, Canfer Akbulut, Daniel Susser, Geoff Keeling, Harry Law, Matija Franklin, Matthew Rahtz, Michael Henry Tessler, Murray Shanahan, Nahema Marchal, Sasha Brown, Seliem El-Sayed, Shannon Vallor, Sophie Bridgers, Toby Shevlane, Tom Everitt, Zachary Kenton, Zaria Jalan","submitted_at":"2024-04-23T14:07:20Z","abstract_excerpt":"Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generative AI presents a new risk profile of persuasion due the opportunity for reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion. The current definitions of AI persuasion are unclear and related harms are insufficiently studied. Existing harm mitigation approaches priori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15058","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/2404.15058/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":"2404.15058","created_at":"2026-07-05T08:11:14.691500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15058v1","created_at":"2026-07-05T08:11:14.691500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15058","created_at":"2026-07-05T08:11:14.691500+00:00"},{"alias_kind":"pith_short_12","alias_value":"DI7BASMP2UOD","created_at":"2026-07-05T08:11:14.691500+00:00"},{"alias_kind":"pith_short_16","alias_value":"DI7BASMP2UODEWEF","created_at":"2026-07-05T08:11:14.691500+00:00"},{"alias_kind":"pith_short_8","alias_value":"DI7BASMP","created_at":"2026-07-05T08:11:14.691500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17657","citing_title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09600","citing_title":"Information Access of the Oppressed: Freirean Design for Emancipatory Information Access","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08321","citing_title":"LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09200","citing_title":"Artificial intelligence can persuade people to take political actions","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI","json":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI.json","graph_json":"https://pith.science/api/pith-number/DI7BASMP2UODEWEFBQHSAYDKSI/graph.json","events_json":"https://pith.science/api/pith-number/DI7BASMP2UODEWEFBQHSAYDKSI/events.json","paper":"https://pith.science/paper/DI7BASMP"},"agent_actions":{"view_html":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI","download_json":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI.json","view_paper":"https://pith.science/paper/DI7BASMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15058&json=true","fetch_graph":"https://pith.science/api/pith-number/DI7BASMP2UODEWEFBQHSAYDKSI/graph.json","fetch_events":"https://pith.science/api/pith-number/DI7BASMP2UODEWEFBQHSAYDKSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI/action/storage_attestation","attest_author":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI/action/author_attestation","sign_citation":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI/action/citation_signature","submit_replication":"https://pith.science/pith/DI7BASMP2UODEWEFBQHSAYDKSI/action/replication_record"}},"created_at":"2026-07-05T08:11:14.691500+00:00","updated_at":"2026-07-05T08:11:14.691500+00:00"}