{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DPBKEQ7C6PQX35D7WVQO7E5O2A","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":"2b2536b7862bdeb25d1b733cffb152aecc4bc92f3a5e355c21336a35c2e0da69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:51:13Z","title_canon_sha256":"9f75e253db3fc4f95fbb0a2940e9bfd1409156a88ae8f2c97cc751d9a3adca0d"},"schema_version":"1.0","source":{"id":"2412.09569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09569","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09569v2","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09569","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_12","alias_value":"DPBKEQ7C6PQX","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_16","alias_value":"DPBKEQ7C6PQX35D7","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_8","alias_value":"DPBKEQ7C","created_at":"2026-07-05T11:19:01Z"}],"graph_snapshots":[{"event_id":"sha256:9643434cf792af7debf367554b60315bdabc51031f24cd3ce5a345f872b60d74","target":"graph","created_at":"2026-07-05T11:19:01Z","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/2412.09569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the rapid progress of generative AI, there is a pressing need to systematically compare and choose between the numerous models and configurations available. The scale and versatility of such evaluations make the use of LLM-based judges a compelling solution for this challenge. Crucially, this approach requires first to validate the quality of the LLM judge itself. Previous work has focused on instance-based assessment of LLM judges, where a judge is evaluated over a set of responses, or response pairs, while being agnostic to their source systems. We argue that this setting overlooks cri","authors_text":"Ariel Gera, Asaf Yehudai, Lilach Eden, Odellia Boni, Roy Bar-Haim, Yotam Perlitz","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:51:13Z","title":"JuStRank: Benchmarking LLM Judges for System Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09569","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":"sha256:21cd7f50e7047a1c79490d4c8afcd7da92014182bc0ad8a05a5b666d36c9ce06","target":"record","created_at":"2026-07-05T11:19:01Z","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":"2b2536b7862bdeb25d1b733cffb152aecc4bc92f3a5e355c21336a35c2e0da69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:51:13Z","title_canon_sha256":"9f75e253db3fc4f95fbb0a2940e9bfd1409156a88ae8f2c97cc751d9a3adca0d"},"schema_version":"1.0","source":{"id":"2412.09569","kind":"arxiv","version":2}},"canonical_sha256":"1bc2a243e2f3e17df47fb560ef93aed02e05d33e8c6a6dad2f7619f66fb0d36d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bc2a243e2f3e17df47fb560ef93aed02e05d33e8c6a6dad2f7619f66fb0d36d","first_computed_at":"2026-07-05T11:19:01.917101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:01.917101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nI8L3crxXjwkmKKAWXPMs9T3hVDpcydtoDrlPIDMwjIq+nDn9TOb9EpbA665cqboNXItqwV3ab8BlRxgBSerAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:01.917922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21cd7f50e7047a1c79490d4c8afcd7da92014182bc0ad8a05a5b666d36c9ce06","sha256:9643434cf792af7debf367554b60315bdabc51031f24cd3ce5a345f872b60d74"],"state_sha256":"09be37d6845729e919fb7e9e666595f3ef779dc419a3473a48eff868cbadd0ad"}