{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D3AOF3LZKO63M3F7IX37ZMXWBS","short_pith_number":"pith:D3AOF3LZ","schema_version":"1.0","canonical_sha256":"1ec0e2ed7953bdb66cbf45f7fcb2f60ca0ab0975dc4541f6da8a7a23dbc6d5a1","source":{"kind":"arxiv","id":"2605.15331","version":1},"attestation_state":"computed","paper":{"title":"Learning to Persuade a Biased Receiver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A sender can learn a receiver's fixed bias in belief updating through safe exploration while achieving O(log log T) regret against a full-information oracle.","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Milind Tambe, Sadie Zhao, Yiling Chen, Yuqi Pan","submitted_at":"2026-05-14T18:54:38Z","abstract_excerpt":"We study a repeated information design setting in which the receiver, who is also the decision-maker, updates beliefs in a systematically biased way. More specifically, a distorted posterior in our model can be written as a convex combination of the prior and the Bayesian posterior, governed by a fixed but unknown parameter. Over repeated interactions, the sender chooses persuasive signaling schemes, observes only the receiver's realized actions, and seeks to minimize regret relative to a full-information oracle that knows the receiver's biased updating rule. We propose a safe exploration algo"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2026-05-14T18:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"12dfb11bd00188d03c973079b15126d34e3db6db0726ec8e04db99f0a9cf5429","abstract_canon_sha256":"7552019ea7011ef26f2b303835fbceae25b9a711598e73713188054f8d9e6359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:52.978020Z","signature_b64":"KafAp7E++QtY6VSAIUc8012dsG4lHl2HJz3s+zw3BwYNi89T3kVkIsfh7aqvE3bGgyhwqkx31PP2DbSfIzHHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ec0e2ed7953bdb66cbf45f7fcb2f60ca0ab0975dc4541f6da8a7a23dbc6d5a1","last_reissued_at":"2026-05-20T00:00:52.977414Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:52.977414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Persuade a Biased Receiver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A sender can learn a receiver's fixed bias in belief updating through safe exploration while achieving O(log log T) regret against a full-information oracle.","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Milind Tambe, Sadie Zhao, Yiling Chen, Yuqi Pan","submitted_at":"2026-05-14T18:54:38Z","abstract_excerpt":"We study a repeated information design setting in which the receiver, who is also the decision-maker, updates beliefs in a systematically biased way. More specifically, a distorted posterior in our model can be written as a convex combination of the prior and the Bayesian posterior, governed by a fixed but unknown parameter. Over repeated interactions, the sender chooses persuasive signaling schemes, observes only the receiver's realized actions, and seeks to minimize regret relative to a full-information oracle that knows the receiver's biased updating rule. We propose a safe exploration algo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For general finite state and action spaces and arbitrary bounded utilities, the safe exploration algorithm achieves O(log log T) regret relative to a full-information oracle that knows the receiver's biased updating rule, with a matching Omega(log log T) lower bound.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The receiver's bias parameter is fixed across all rounds and the only uncertainty is this single scalar; the model assumes the sender can perfectly observe the realized action after each signal but receives no other feedback.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A safe exploration algorithm learns an unknown receiver bias parameter in repeated information design and achieves O(log log T) regret with a matching lower bound.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A sender can learn a receiver's fixed bias in belief updating through safe exploration while achieving O(log log T) regret against a full-information oracle.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"731b2d951b4277acd333ff1cf1aceea3f43f1bd9e6c8e78f70948c04c91d0ee6"},"source":{"id":"2605.15331","kind":"arxiv","version":1},"verdict":{"id":"21bee8d7-6cdf-4135-8149-b5c4902e988b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:28:38.900846Z","strongest_claim":"For general finite state and action spaces and arbitrary bounded utilities, the safe exploration algorithm achieves O(log log T) regret relative to a full-information oracle that knows the receiver's biased updating rule, with a matching Omega(log log T) lower bound.","one_line_summary":"A safe exploration algorithm learns an unknown receiver bias parameter in repeated information design and achieves O(log log T) regret with a matching lower bound.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The receiver's bias parameter is fixed across all rounds and the only uncertainty is this single scalar; the model assumes the sender can perfectly observe the realized action after each signal but receives no other feedback.","pith_extraction_headline":"A sender can learn a receiver's fixed bias in belief updating through safe exploration while achieving O(log log T) regret against a full-information oracle."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15331/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.143323Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:41:05.086074Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.192500Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.761694Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b7319e66ed443559cab13c11ac845fa7c971eb49d708a59da6bcf251d5f1feb7"},"references":{"count":47,"sample":[{"doi":"","year":1995,"title":"Robert J Aumann, Michael Maschler, and Richard E Stearns.Repeated games with incomplete information. MIT press, 1995","work_id":"6bc903ff-2e6a-457e-8a2f-6d93c47aca3c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Over-and underreaction to information: Belief updating with cognitive constraints","work_id":"5a2e79c2-639d-4128-81e5-d7fb86866a27","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Markov persuasion processes: Learning to persuade from scratch.arXiv preprint arXiv:2402.03077, 2024","work_id":"dd3d2a62-8ac1-4e50-b58a-ef728312677e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A meta-analysis of the weight of advice in decision-making.Current Psychology, 42(28): 24516–24541, 2023","work_id":"a98006cc-3da2-4b76-b25b-98e9f98b50dd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1980,"title":"The base-rate fallacy in probability judgments.Acta Psychologica, 44(3): 211–233, 1980","work_id":"fba1aa0d-12f0-40c1-8f70-3676f33cd293","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":47,"snapshot_sha256":"3d9df9314f9ad1e12ee72fcf924348aac792bbde02b43e9e2c69afa0d9cc7a9c","internal_anchors":1},"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":"2605.15331","created_at":"2026-05-20T00:00:52.977508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15331v1","created_at":"2026-05-20T00:00:52.977508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15331","created_at":"2026-05-20T00:00:52.977508+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3AOF3LZKO63","created_at":"2026-05-20T00:00:52.977508+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3AOF3LZKO63M3F7","created_at":"2026-05-20T00:00:52.977508+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3AOF3LZ","created_at":"2026-05-20T00:00:52.977508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS","json":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS.json","graph_json":"https://pith.science/api/pith-number/D3AOF3LZKO63M3F7IX37ZMXWBS/graph.json","events_json":"https://pith.science/api/pith-number/D3AOF3LZKO63M3F7IX37ZMXWBS/events.json","paper":"https://pith.science/paper/D3AOF3LZ"},"agent_actions":{"view_html":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS","download_json":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS.json","view_paper":"https://pith.science/paper/D3AOF3LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15331&json=true","fetch_graph":"https://pith.science/api/pith-number/D3AOF3LZKO63M3F7IX37ZMXWBS/graph.json","fetch_events":"https://pith.science/api/pith-number/D3AOF3LZKO63M3F7IX37ZMXWBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS/action/storage_attestation","attest_author":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS/action/author_attestation","sign_citation":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS/action/citation_signature","submit_replication":"https://pith.science/pith/D3AOF3LZKO63M3F7IX37ZMXWBS/action/replication_record"}},"created_at":"2026-05-20T00:00:52.977508+00:00","updated_at":"2026-05-20T00:00:52.977508+00:00"}