{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YQCAPNL52FXP7VZR6FJ7UNXU5B","short_pith_number":"pith:YQCAPNL5","schema_version":"1.0","canonical_sha256":"c40407b57dd16effd731f153fa36f4e8422d4bfffc1fad4864e7b46201406613","source":{"kind":"arxiv","id":"2606.05122","version":1},"attestation_state":"computed","paper":{"title":"Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junfeng Fang, XiuYu Zhang, Yi Shan, Zhenkai Liang","submitted_at":"2026-06-03T17:27:16Z","abstract_excerpt":"Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is largely present before any targeted training: prompted few-shot, a base model already predicts an external judge's multi-attribute quality scores on open-ended responses well above chance across three benchmarks. We introduce Self-Evaluation Elicitation (SEE), a method that surfaces this latent ability through a short cycle comprising a calibration-coupled reinforcement learning phase that improves the answer and pr"},"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":"2606.05122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T17:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"d6160d00f9bfca3258d8bd5aef38fcbb5eeca0728a71b4c58ec7616170a21960","abstract_canon_sha256":"60b484058794e4ea407f5ff72619c7b1c3728cfea5986cc205db545da0cade4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:07.223208Z","signature_b64":"CL0b2gafRzQ1NAd7ZUmo8MPledHIsLGucsERhTH0OCCUEM6K/ayvJZZloKGqgKYQORnJeWZWpN45z77y7EmmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40407b57dd16effd731f153fa36f4e8422d4bfffc1fad4864e7b46201406613","last_reissued_at":"2026-06-04T01:10:07.222304Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:07.222304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junfeng Fang, XiuYu Zhang, Yi Shan, Zhenkai Liang","submitted_at":"2026-06-03T17:27:16Z","abstract_excerpt":"Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is largely present before any targeted training: prompted few-shot, a base model already predicts an external judge's multi-attribute quality scores on open-ended responses well above chance across three benchmarks. We introduce Self-Evaluation Elicitation (SEE), a method that surfaces this latent ability through a short cycle comprising a calibration-coupled reinforcement learning phase that improves the answer and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05122","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/2606.05122/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":"2606.05122","created_at":"2026-06-04T01:10:07.222453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05122v1","created_at":"2026-06-04T01:10:07.222453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05122","created_at":"2026-06-04T01:10:07.222453+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQCAPNL52FXP","created_at":"2026-06-04T01:10:07.222453+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQCAPNL52FXP7VZR","created_at":"2026-06-04T01:10:07.222453+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQCAPNL5","created_at":"2026-06-04T01:10:07.222453+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/YQCAPNL52FXP7VZR6FJ7UNXU5B","json":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B.json","graph_json":"https://pith.science/api/pith-number/YQCAPNL52FXP7VZR6FJ7UNXU5B/graph.json","events_json":"https://pith.science/api/pith-number/YQCAPNL52FXP7VZR6FJ7UNXU5B/events.json","paper":"https://pith.science/paper/YQCAPNL5"},"agent_actions":{"view_html":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B","download_json":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B.json","view_paper":"https://pith.science/paper/YQCAPNL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05122&json=true","fetch_graph":"https://pith.science/api/pith-number/YQCAPNL52FXP7VZR6FJ7UNXU5B/graph.json","fetch_events":"https://pith.science/api/pith-number/YQCAPNL52FXP7VZR6FJ7UNXU5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B/action/storage_attestation","attest_author":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B/action/author_attestation","sign_citation":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B/action/citation_signature","submit_replication":"https://pith.science/pith/YQCAPNL52FXP7VZR6FJ7UNXU5B/action/replication_record"}},"created_at":"2026-06-04T01:10:07.222453+00:00","updated_at":"2026-06-04T01:10:07.222453+00:00"}