{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D444J7UARXO4NGKORPDJXOSPFP","short_pith_number":"pith:D444J7UA","canonical_record":{"source":{"id":"2503.19877","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T17:41:18Z","cross_cats_sorted":[],"title_canon_sha256":"517380c753e75f8492a57a55e7719328ee353b3743d1fc637bbcf6f7c8518e51","abstract_canon_sha256":"2d2d17586029d92508780e41d6179af1276293e1c9eebfde567ada5791cef27d"},"schema_version":"1.0"},"canonical_sha256":"1f39c4fe808dddc6994e8bc69bba4f2bf87d9dd2ba366e11645d8d9b1b948629","source":{"kind":"arxiv","id":"2503.19877","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D444J7UARXO4NGKORPDJXOSPFP","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19877","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T17:41:18Z","cross_cats_sorted":[],"title_canon_sha256":"517380c753e75f8492a57a55e7719328ee353b3743d1fc637bbcf6f7c8518e51","abstract_canon_sha256":"2d2d17586029d92508780e41d6179af1276293e1c9eebfde567ada5791cef27d"},"schema_version":"1.0"},"canonical_sha256":"1f39c4fe808dddc6994e8bc69bba4f2bf87d9dd2ba366e11645d8d9b1b948629","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:53.265219Z","signature_b64":"XAydjeMwk1+URPSlY4fV4tvdWiTM54NS6VAYWuZlcme8GPfgXoI6p385Fn8xqyneQhvLXkWRtNbtPrpYrMD3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f39c4fe808dddc6994e8bc69bba4f2bf87d9dd2ba366e11645d8d9b1b948629","last_reissued_at":"2026-05-20T01:04:53.264440Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:53.264440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19877","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ur8N7B+/nDSUmm1r74L9UVr/oPW7FjYCpsluSLIGcX6WkokY9+z7CCztgIHG/NW38nI9qFlJiFd2jhFwf3VAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:05:52.048717Z"},"content_sha256":"4c8e18a27c4689dfbdd63eac455b08d0313a2c63a357da152f699dca6cf1b4ac","schema_version":"1.0","event_id":"sha256:4c8e18a27c4689dfbdd63eac455b08d0313a2c63a357da152f699dca6cf1b4ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D444J7UARXO4NGKORPDJXOSPFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Evaluation-time Compute with Reasoning Models as Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Graham Neubig, Ian Wu, Jinu Lee, Julia Hockenmaier, Kiril Gashteovski, Mingyeong Moon, Sean Welleck, Seongyun Lee, Seungone Kim, Xiang Yue","submitted_at":"2025-03-25T17:41:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19877","kind":"arxiv","version":2},"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/2503.19877/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zknz9FuKVWXPo0cwv6yTP931Ztz5+sWy4DL8u81RQrBtmsieaBckgko99PzkPQOqTMokN803sPba2i0LozBCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:05:52.049094Z"},"content_sha256":"5d63f83bd65918cf5fa56e6d15c3e53b710e224c11f260d50658b9318d2f17b7","schema_version":"1.0","event_id":"sha256:5d63f83bd65918cf5fa56e6d15c3e53b710e224c11f260d50658b9318d2f17b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D444J7UARXO4NGKORPDJXOSPFP/bundle.json","state_url":"https://pith.science/pith/D444J7UARXO4NGKORPDJXOSPFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D444J7UARXO4NGKORPDJXOSPFP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-20T12:05:52Z","links":{"resolver":"https://pith.science/pith/D444J7UARXO4NGKORPDJXOSPFP","bundle":"https://pith.science/pith/D444J7UARXO4NGKORPDJXOSPFP/bundle.json","state":"https://pith.science/pith/D444J7UARXO4NGKORPDJXOSPFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D444J7UARXO4NGKORPDJXOSPFP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNPsnETybQyyC6UXOEiuESmbT+DeoVMl1WquhGQzx7vGhpiHh1wN/6zkOWU1yTnu97NRq6zE473KLjuPyrN0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T12:05:52.051125Z","bundle_sha256":"fbfbe92b7e08144bee55b1019f43b7460a97e8abd7335e940e2017b1430b7068"}}