{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XOTB67KDBCQXNPBOQDUMVTUJ2B","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":"089ff2edf48ec5cb181e8182e2798e50d5a603f975d87beeb3c0facd44360d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T01:52:59Z","title_canon_sha256":"121d4cbcff5ecf1cf3f54e8821502f46d15ed6385766f15ff1677a67d5f95fff"},"schema_version":"1.0","source":{"id":"2606.10307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10307","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10307v1","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10307","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"XOTB67KDBCQX","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"XOTB67KDBCQXNPBO","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"XOTB67KD","created_at":"2026-06-10T01:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:626a4a0d5f4ccd732cca94fb3e857a724c399603aec5df3d863723ce7ed756ca","target":"graph","created_at":"2026-06-10T01:10:10Z","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/2606.10307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended tasks without reference answers. We investigate whether intrinsic confidence signals, token-level log-probabilities from decoding, can predict reasoning quality as assessed by LLM-as-judge evaluation. Using a debate-based essay scoring framework, we compare confidence proxies against rubric-based judge scores across two ASAP essay sets. We find that early-token confidence, particularly within the first few generated tokens, is consistently the strongest predictor of reasoning quality, outperformin","authors_text":"Ali Keramati, Jacob Horne, Justin Cheok, Mark Warschauer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T01:52:59Z","title":"Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10307","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":"sha256:413d277e52262958dcca0a4f70bac6b6dac06d649a4771d1dd6568d89c9c0bcb","target":"record","created_at":"2026-06-10T01:10:10Z","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":"089ff2edf48ec5cb181e8182e2798e50d5a603f975d87beeb3c0facd44360d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T01:52:59Z","title_canon_sha256":"121d4cbcff5ecf1cf3f54e8821502f46d15ed6385766f15ff1677a67d5f95fff"},"schema_version":"1.0","source":{"id":"2606.10307","kind":"arxiv","version":1}},"canonical_sha256":"bba61f7d4308a176bc2e80e8cace89d060d256a1a24cf480ca7f70042bec12f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bba61f7d4308a176bc2e80e8cace89d060d256a1a24cf480ca7f70042bec12f6","first_computed_at":"2026-06-10T01:10:10.966743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:10.966743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FP0mvsTz1HiiKg0t4rEiQ9PtVEel1V7VbO7vtmQFED0S2MXSxpZmoOr+gaoGlPsVI2FgqIjGGhUCkl3m2F0tAw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:10.967339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:413d277e52262958dcca0a4f70bac6b6dac06d649a4771d1dd6568d89c9c0bcb","sha256:626a4a0d5f4ccd732cca94fb3e857a724c399603aec5df3d863723ce7ed756ca"],"state_sha256":"501e21b79007e8ab8fd9e8995f887436457e469953222f94a807875e80a1e91a"}