{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WFOGKN7DZT63H4TQPIMPFA6JHP","short_pith_number":"pith:WFOGKN7D","schema_version":"1.0","canonical_sha256":"b15c6537e3ccfdb3f2707a18f283c93bd1aeb81a003f7715ccae20a33098e310","source":{"kind":"arxiv","id":"2405.15077","version":4},"attestation_state":"computed","paper":{"title":"Eliciting Informative Text Evaluations with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.CL","authors_text":"Grant Schoenebeck, Shengwei Xu, Yichi Zhang, Yuqing Kong, Yuxuan Lu","submitted_at":"2024-05-23T21:56:12Z","abstract_excerpt":"Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models. This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media.\n  We introduce two mechanisms, the Generative Peer Predict"},"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":"2405.15077","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T21:56:12Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"913ad079da9770dfced47e05fb12f566782fe30e10a9b19811a056cb85eb2c31","abstract_canon_sha256":"da05349a00ff08a0a6dbf1f25c3e01bd13c44349b03227e004ea49aede642746"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:19.802660Z","signature_b64":"TpmULd7Ocm1jP/hupQUVhh36B+OjqsrsRvaaEyOCGZ5OcTy7N4zDAVgZgWPOEH8kCVEBgRTpPndRaB5/GlowDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b15c6537e3ccfdb3f2707a18f283c93bd1aeb81a003f7715ccae20a33098e310","last_reissued_at":"2026-07-05T09:02:19.802173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:19.802173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliciting Informative Text Evaluations with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.CL","authors_text":"Grant Schoenebeck, Shengwei Xu, Yichi Zhang, Yuqing Kong, Yuxuan Lu","submitted_at":"2024-05-23T21:56:12Z","abstract_excerpt":"Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models. This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media.\n  We introduce two mechanisms, the Generative Peer Predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15077","kind":"arxiv","version":4},"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/2405.15077/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":"2405.15077","created_at":"2026-07-05T09:02:19.802232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15077v4","created_at":"2026-07-05T09:02:19.802232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15077","created_at":"2026-07-05T09:02:19.802232+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFOGKN7DZT63","created_at":"2026-07-05T09:02:19.802232+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFOGKN7DZT63H4TQ","created_at":"2026-07-05T09:02:19.802232+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFOGKN7D","created_at":"2026-07-05T09:02:19.802232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01423","citing_title":"Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP","json":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP.json","graph_json":"https://pith.science/api/pith-number/WFOGKN7DZT63H4TQPIMPFA6JHP/graph.json","events_json":"https://pith.science/api/pith-number/WFOGKN7DZT63H4TQPIMPFA6JHP/events.json","paper":"https://pith.science/paper/WFOGKN7D"},"agent_actions":{"view_html":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP","download_json":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP.json","view_paper":"https://pith.science/paper/WFOGKN7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15077&json=true","fetch_graph":"https://pith.science/api/pith-number/WFOGKN7DZT63H4TQPIMPFA6JHP/graph.json","fetch_events":"https://pith.science/api/pith-number/WFOGKN7DZT63H4TQPIMPFA6JHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP/action/storage_attestation","attest_author":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP/action/author_attestation","sign_citation":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP/action/citation_signature","submit_replication":"https://pith.science/pith/WFOGKN7DZT63H4TQPIMPFA6JHP/action/replication_record"}},"created_at":"2026-07-05T09:02:19.802232+00:00","updated_at":"2026-07-05T09:02:19.802232+00:00"}