{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7UXFCSKDUSPBVHFCX562XIZAMG","short_pith_number":"pith:7UXFCSKD","schema_version":"1.0","canonical_sha256":"fd2e514943a49e1a9ca2bf7daba320619a27c117c2ec1a487b7c75d121ad766c","source":{"kind":"arxiv","id":"2406.01860","version":1},"attestation_state":"computed","paper":{"title":"Eliciting the Priors of Large Language Models using Iterated In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian-Qiao Zhu, Thomas L. Griffiths","submitted_at":"2024-06-04T00:09:43Z","abstract_excerpt":"As Large Language Models (LLMs) are increasingly deployed in real-world settings, understanding the knowledge they implicitly use when making decisions is critical. One way to capture this knowledge is in the form of Bayesian prior distributions. We develop a prompt-based workflow for eliciting prior distributions from LLMs. Our approach is based on iterated learning, a Markov chain Monte Carlo method in which successive inferences are chained in a way that supports sampling from the prior distribution. We validated our method in settings where iterated learning has previously been used to est"},"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":"2406.01860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:09:43Z","cross_cats_sorted":[],"title_canon_sha256":"5fbcc416c32c033d3b4fbd83af779c668e87f66d6db0c18bbf2a433359aecdc3","abstract_canon_sha256":"2ee95a8ba482dd55b6bbd20a23b99b4176616d0ec122f2fe85909dce66a810f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:49.700456Z","signature_b64":"aNkFPYpI8//GKI9c32N7J3BDhNG6C6n5EZojx4LC5om7nWixJO7vuL86hvJqO3+y9/aJufi16JcSsqbGkQdYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd2e514943a49e1a9ca2bf7daba320619a27c117c2ec1a487b7c75d121ad766c","last_reissued_at":"2026-07-05T08:26:49.700033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:49.700033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliciting the Priors of Large Language Models using Iterated In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian-Qiao Zhu, Thomas L. Griffiths","submitted_at":"2024-06-04T00:09:43Z","abstract_excerpt":"As Large Language Models (LLMs) are increasingly deployed in real-world settings, understanding the knowledge they implicitly use when making decisions is critical. One way to capture this knowledge is in the form of Bayesian prior distributions. We develop a prompt-based workflow for eliciting prior distributions from LLMs. Our approach is based on iterated learning, a Markov chain Monte Carlo method in which successive inferences are chained in a way that supports sampling from the prior distribution. We validated our method in settings where iterated learning has previously been used to est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01860","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/2406.01860/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":"2406.01860","created_at":"2026-07-05T08:26:49.700088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01860v1","created_at":"2026-07-05T08:26:49.700088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01860","created_at":"2026-07-05T08:26:49.700088+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UXFCSKDUSPB","created_at":"2026-07-05T08:26:49.700088+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UXFCSKDUSPBVHFC","created_at":"2026-07-05T08:26:49.700088+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UXFCSKD","created_at":"2026-07-05T08:26:49.700088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13038","citing_title":"Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07951","citing_title":"From `May' to `Is': Certainty Distortion in Language Model Rewriting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17671","citing_title":"LILO: Bayesian Optimization with Natural Language Feedback","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12264","citing_title":"Reconstruction of Personally Identifiable Information from Supervised Finetuned Models","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG","json":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG.json","graph_json":"https://pith.science/api/pith-number/7UXFCSKDUSPBVHFCX562XIZAMG/graph.json","events_json":"https://pith.science/api/pith-number/7UXFCSKDUSPBVHFCX562XIZAMG/events.json","paper":"https://pith.science/paper/7UXFCSKD"},"agent_actions":{"view_html":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG","download_json":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG.json","view_paper":"https://pith.science/paper/7UXFCSKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01860&json=true","fetch_graph":"https://pith.science/api/pith-number/7UXFCSKDUSPBVHFCX562XIZAMG/graph.json","fetch_events":"https://pith.science/api/pith-number/7UXFCSKDUSPBVHFCX562XIZAMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG/action/storage_attestation","attest_author":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG/action/author_attestation","sign_citation":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG/action/citation_signature","submit_replication":"https://pith.science/pith/7UXFCSKDUSPBVHFCX562XIZAMG/action/replication_record"}},"created_at":"2026-07-05T08:26:49.700088+00:00","updated_at":"2026-07-05T08:26:49.700088+00:00"}