{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RDB4AD6LKHPKFO7SROUVQDSSOZ","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":"f8d82def872af3e4492cae652544bacc2ce20c8dfec7bc7636212683c6a80559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T15:31:33Z","title_canon_sha256":"b7e87b89db12e4fa0f24c6b3d2093c8e09d2a1c97e3cc730e326af4cb468ced9"},"schema_version":"1.0","source":{"id":"2607.12885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12885","created_at":"2026-07-15T01:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12885v1","created_at":"2026-07-15T01:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12885","created_at":"2026-07-15T01:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"RDB4AD6LKHPK","created_at":"2026-07-15T01:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"RDB4AD6LKHPKFO7S","created_at":"2026-07-15T01:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"RDB4AD6L","created_at":"2026-07-15T01:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:8179769867b2a1ef35351d69a144dc0541fccb54a8a217003d63d96e87bf8553","target":"graph","created_at":"2026-07-15T01:22:23Z","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/2607.12885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM judges are increasingly being used to evaluate open-ended model responses, often in no-reference settings where a ground-truth answer is unavailable. However, can they reliably assess in such evaluation setups? We explore this question in this paper through a two stage pipeline with a) calibration experiments that assess the judge model's knowledge of the task it is evaluating, and b) sensitivity experiments that assess how the judge model's performance is impacted by the presence and positioning of the reference answer in the prompt. Across experiments covering three languages, we show th","authors_text":"Chalamalasetti Kranti, Sowmya Vajjala","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T15:31:33Z","title":"LLM Judges Can Be Too Generous When There Is No Reference Answer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12885","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:e22745cee5e1d71fa50b726f53751b94be032fcc8b5a6f05448f56ce08ee86e4","target":"record","created_at":"2026-07-15T01:22:23Z","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":"f8d82def872af3e4492cae652544bacc2ce20c8dfec7bc7636212683c6a80559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T15:31:33Z","title_canon_sha256":"b7e87b89db12e4fa0f24c6b3d2093c8e09d2a1c97e3cc730e326af4cb468ced9"},"schema_version":"1.0","source":{"id":"2607.12885","kind":"arxiv","version":1}},"canonical_sha256":"88c3c00fcb51dea2bbf28ba9580e52766380b76db388655da6813b3efcf3cb98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88c3c00fcb51dea2bbf28ba9580e52766380b76db388655da6813b3efcf3cb98","first_computed_at":"2026-07-15T01:22:23.221668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:22:23.221668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pxrVK3ldivArsDLS2qsX+U93uQo4pFyR5+bBh43tCrb1xNxzlCsit8kPuxsbyZ8o0z+Yk9MkawzmOVLlfV72AA==","signature_status":"signed_v1","signed_at":"2026-07-15T01:22:23.222498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e22745cee5e1d71fa50b726f53751b94be032fcc8b5a6f05448f56ce08ee86e4","sha256:8179769867b2a1ef35351d69a144dc0541fccb54a8a217003d63d96e87bf8553"],"state_sha256":"c94c4337680169452a6f121e7a476b82a43a151e917a0b6fb764ab10ef88c220"}