{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D444J7UARXO4NGKORPDJXOSPFP","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":"2d2d17586029d92508780e41d6179af1276293e1c9eebfde567ada5791cef27d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T17:41:18Z","title_canon_sha256":"517380c753e75f8492a57a55e7719328ee353b3743d1fc637bbcf6f7c8518e51"},"schema_version":"1.0","source":{"id":"2503.19877","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19877","created_at":"2026-05-20T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19877v2","created_at":"2026-05-20T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19877","created_at":"2026-05-20T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"D444J7UARXO4","created_at":"2026-05-20T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"D444J7UARXO4NGKO","created_at":"2026-05-20T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"D444J7UA","created_at":"2026-05-20T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:5d63f83bd65918cf5fa56e6d15c3e53b710e224c11f260d50658b9318d2f17b7","target":"graph","created_at":"2026-05-20T01:04:53Z","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/2503.19877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increasing LMs' \"thinking\" time through scaling test-time compute has proven an effective technique to solve challenging problems in domains such as math and code. This raises a natural question: can an LM's evaluation capability also be improved by spending more test-time compute? To answer this, we investigate employing reasoning models-LMs that natively generate long chain-of-thought reasoning-as evaluators. Specifically, we examine methods to leverage","authors_text":"Carolin Lawrence, Graham Neubig, Ian Wu, Jinu Lee, Julia Hockenmaier, Kiril Gashteovski, Mingyeong Moon, Sean Welleck, Seongyun Lee, Seungone Kim, Xiang Yue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T17:41:18Z","title":"Scaling Evaluation-time Compute with Reasoning Models as Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19877","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":"sha256:4c8e18a27c4689dfbdd63eac455b08d0313a2c63a357da152f699dca6cf1b4ac","target":"record","created_at":"2026-05-20T01:04:53Z","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":"2d2d17586029d92508780e41d6179af1276293e1c9eebfde567ada5791cef27d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T17:41:18Z","title_canon_sha256":"517380c753e75f8492a57a55e7719328ee353b3743d1fc637bbcf6f7c8518e51"},"schema_version":"1.0","source":{"id":"2503.19877","kind":"arxiv","version":2}},"canonical_sha256":"1f39c4fe808dddc6994e8bc69bba4f2bf87d9dd2ba366e11645d8d9b1b948629","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f39c4fe808dddc6994e8bc69bba4f2bf87d9dd2ba366e11645d8d9b1b948629","first_computed_at":"2026-05-20T01:04:53.264440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:04:53.264440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAydjeMwk1+URPSlY4fV4tvdWiTM54NS6VAYWuZlcme8GPfgXoI6p385Fn8xqyneQhvLXkWRtNbtPrpYrMD3DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:04:53.265219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19877","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c8e18a27c4689dfbdd63eac455b08d0313a2c63a357da152f699dca6cf1b4ac","sha256:5d63f83bd65918cf5fa56e6d15c3e53b710e224c11f260d50658b9318d2f17b7"],"state_sha256":"e37ae19347637be2f198e0884104312658e0df7cec09650e2ad0694d0a2e838b"}