{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5MRB2EXT2LNF2U2GOZFKGXTWT3","short_pith_number":"pith:5MRB2EXT","schema_version":"1.0","canonical_sha256":"eb221d12f3d2da5d5346764aa35e769ef692a8e7c90e4bafe286ca9aef14ef07","source":{"kind":"arxiv","id":"2605.27668","version":1},"attestation_state":"computed","paper":{"title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hui Dai, Mengye Ren, Parsa Torabian, Ryan Teehan","submitted_at":"2026-05-26T20:39:33Z","abstract_excerpt":"Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binary outcomes to output verbalized forecasts. However, while aggregated human forecasts contain rich information in both the crowd probability estimate and the degree of agreement among forecasters, how to utilize these signals remains underexplored. To address this, we propose the Beta-Bernoulli Calibrator (BBC), which converts an initial point estimate forecast from any model into a distribution over event likelihood, using supervision from both b"},"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":"2605.27668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T20:39:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0e5efc006324f7ec15500f4911f5b47455ac09f1250724f03c6791e22003a82b","abstract_canon_sha256":"05b63f29ad6120590493094654757c01eef8f7c7bcaaf0d5f7636c4c8ea23b90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:45.764856Z","signature_b64":"yjXSjxhIbjzpBygD1xSXxd2Js8RtZtmhJdFjelFkwytRJoVL70ldSn+HMDnashvsZ1mm6DKiTfzAlGt1iW+HDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb221d12f3d2da5d5346764aa35e769ef692a8e7c90e4bafe286ca9aef14ef07","last_reissued_at":"2026-05-28T01:04:45.764461Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:45.764461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hui Dai, Mengye Ren, Parsa Torabian, Ryan Teehan","submitted_at":"2026-05-26T20:39:33Z","abstract_excerpt":"Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binary outcomes to output verbalized forecasts. However, while aggregated human forecasts contain rich information in both the crowd probability estimate and the degree of agreement among forecasters, how to utilize these signals remains underexplored. To address this, we propose the Beta-Bernoulli Calibrator (BBC), which converts an initial point estimate forecast from any model into a distribution over event likelihood, using supervision from both b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27668","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/2605.27668/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":"2605.27668","created_at":"2026-05-28T01:04:45.764518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27668v1","created_at":"2026-05-28T01:04:45.764518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27668","created_at":"2026-05-28T01:04:45.764518+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MRB2EXT2LNF","created_at":"2026-05-28T01:04:45.764518+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MRB2EXT2LNF2U2G","created_at":"2026-05-28T01:04:45.764518+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MRB2EXT","created_at":"2026-05-28T01:04:45.764518+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/5MRB2EXT2LNF2U2GOZFKGXTWT3","json":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3.json","graph_json":"https://pith.science/api/pith-number/5MRB2EXT2LNF2U2GOZFKGXTWT3/graph.json","events_json":"https://pith.science/api/pith-number/5MRB2EXT2LNF2U2GOZFKGXTWT3/events.json","paper":"https://pith.science/paper/5MRB2EXT"},"agent_actions":{"view_html":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3","download_json":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3.json","view_paper":"https://pith.science/paper/5MRB2EXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27668&json=true","fetch_graph":"https://pith.science/api/pith-number/5MRB2EXT2LNF2U2GOZFKGXTWT3/graph.json","fetch_events":"https://pith.science/api/pith-number/5MRB2EXT2LNF2U2GOZFKGXTWT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3/action/storage_attestation","attest_author":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3/action/author_attestation","sign_citation":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3/action/citation_signature","submit_replication":"https://pith.science/pith/5MRB2EXT2LNF2U2GOZFKGXTWT3/action/replication_record"}},"created_at":"2026-05-28T01:04:45.764518+00:00","updated_at":"2026-05-28T01:04:45.764518+00:00"}