{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6EVRZHAMEVEES3L2Y2253642DD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dab4d0fbbc61c18faf5d1f8ac67dfc1e60b02537c53383fd96165013e5f58c37","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T15:23:27Z","title_canon_sha256":"eabe97af9248e97f0f9e9d7b9eab9c2e563c0fc4893161fde63f15a03fb75c8d"},"schema_version":"1.0","source":{"id":"2605.25133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25133","created_at":"2026-05-26T02:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25133v1","created_at":"2026-05-26T02:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25133","created_at":"2026-05-26T02:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"6EVRZHAMEVEE","created_at":"2026-05-26T02:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"6EVRZHAMEVEES3L2","created_at":"2026-05-26T02:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"6EVRZHAM","created_at":"2026-05-26T02:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:20d312c4c52bfb9b56f06c54db584fad0eac6d21a9f59fdd8481291c871c55ad","target":"graph","created_at":"2026-05-26T02:04:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.25133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in interactive proof theory, as a mechanism for selective prediction: the protocol produces both an answer and a structured confidence verdict, allowing a system to report high-confidence answers while abstaining on uncertain cases. In each dialogue, a prover defends a candidate answer through checkable sub-claims while a verifier issues targeted challenges and returns \\textsc{Accept}, \\textsc{Challenge}, or \\textsc{Reje","authors_text":"Baotong Zhang, Dean Foster, Jo\\~ao Sedoc","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T15:23:27Z","title":"Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25133","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ce6ae11c6ea19398eb3dc1499fac629333b315f68eb1a4b1e845fa5097b6c19","target":"record","created_at":"2026-05-26T02:04:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dab4d0fbbc61c18faf5d1f8ac67dfc1e60b02537c53383fd96165013e5f58c37","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T15:23:27Z","title_canon_sha256":"eabe97af9248e97f0f9e9d7b9eab9c2e563c0fc4893161fde63f15a03fb75c8d"},"schema_version":"1.0","source":{"id":"2605.25133","kind":"arxiv","version":1}},"canonical_sha256":"f12b1c9c0c2548496d7ac6b5ddfb9a18d56ba9e3102f7ea2fdcd51ee5b7e2525","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12b1c9c0c2548496d7ac6b5ddfb9a18d56ba9e3102f7ea2fdcd51ee5b7e2525","first_computed_at":"2026-05-26T02:04:19.597697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:19.597697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M4JnUk6HRvkqdYRmYkyqMU16yU+SrUy0/f+UV8fR4aKhVsqv7ud9Ww7ywsMwAttnoPmZhg5Mm0VMtf5Qtuq8CQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:19.598416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce6ae11c6ea19398eb3dc1499fac629333b315f68eb1a4b1e845fa5097b6c19","sha256:20d312c4c52bfb9b56f06c54db584fad0eac6d21a9f59fdd8481291c871c55ad"],"state_sha256":"64d8904eff516819d75cd71051bac4a66e1bc66c381dabffef3574a598773ba8"}