{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6ITC2NIOLKRDKOWJYGETFJTGVV","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":"ff17e301b4ffc9f39db33e4acad6f08ec12135dd490ed93e859d13689f37e474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T18:46:47Z","title_canon_sha256":"24b792f93236eb3073712ede427c71ab8bafd9883504680df0632e9d528131d3"},"schema_version":"1.0","source":{"id":"2512.03019","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.03019","created_at":"2026-06-03T01:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2512.03019v2","created_at":"2026-06-03T01:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03019","created_at":"2026-06-03T01:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"6ITC2NIOLKRD","created_at":"2026-06-03T01:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"6ITC2NIOLKRDKOWJ","created_at":"2026-06-03T01:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"6ITC2NIO","created_at":"2026-06-03T01:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:18c6d84585d283fd7a1d53014ac93651a52a37e5394ea11824ee449850d97f6c","target":"graph","created_at":"2026-06-03T01:05:07Z","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/2512.03019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation rules (majority vote, soft self-consistency, or instruction-based self-aggregation) are inconsistent when ties are allowed. We study inference-time compute (ITC) for evaluators that generate n independent thinking--rating samples per item, and propose a principled, distribution-calibrated aggregation scheme. Our method models three-way preferences with a Bradley-Terry-Davidson formulation on rating counts, leveraging both polarity (margin among non-ties)","authors_text":"Firas Trabelsi, Hamid Dadkhahi, Juraj Juraska, Mehdi Mirzazadeh, Parker Riley","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T18:46:47Z","title":"Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03019","kind":"arxiv","version":2},"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":"sha256:6ac7a29aa7ec68dc0516a94a70b9e0290a8c2919ecacbde9fbb12d4b71146acf","target":"record","created_at":"2026-06-03T01:05:07Z","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":"ff17e301b4ffc9f39db33e4acad6f08ec12135dd490ed93e859d13689f37e474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T18:46:47Z","title_canon_sha256":"24b792f93236eb3073712ede427c71ab8bafd9883504680df0632e9d528131d3"},"schema_version":"1.0","source":{"id":"2512.03019","kind":"arxiv","version":2}},"canonical_sha256":"f2262d350e5aa2353ac9c18932a666ad7bc1f578492671ccf3c6ac5f9606abf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2262d350e5aa2353ac9c18932a666ad7bc1f578492671ccf3c6ac5f9606abf3","first_computed_at":"2026-06-03T01:05:07.912028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:07.912028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vSvPssUBelnPJ5LoRmppxnjZgHGqCVgZQQI30uo6+YojDLM9erL3pTmEGGDw9HnBwvNyNDoJbvdcK0MmLBPVDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:07.912551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.03019","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ac7a29aa7ec68dc0516a94a70b9e0290a8c2919ecacbde9fbb12d4b71146acf","sha256:18c6d84585d283fd7a1d53014ac93651a52a37e5394ea11824ee449850d97f6c"],"state_sha256":"22865245e6207ce125dcb14172779a30f690344c2a9ce912bc0f0eb9dec0a53c"}