{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7G2OAF3IBVN4BNW64S4DTRIGMV","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"96d5bc119bea352777849d4953fe5f716d1233f8deafba486242355a9c749114","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T23:55:08Z","title_canon_sha256":"8b6713a5aa05135e1552164a715ca989152edbf1c4f6305c4d3b0eb366d102ff"},"schema_version":"1.0","source":{"id":"2605.19196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19196","created_at":"2026-05-20T01:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19196v1","created_at":"2026-05-20T01:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19196","created_at":"2026-05-20T01:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"7G2OAF3IBVN4","created_at":"2026-05-20T01:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"7G2OAF3IBVN4BNW6","created_at":"2026-05-20T01:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"7G2OAF3I","created_at":"2026-05-20T01:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:273e6da473ffd4a28d88d3a95b53024b414d3473374e4b063d2b0172ed0bcb38","target":"graph","created_at":"2026-05-20T01:05:33Z","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/2605.19196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluati","authors_text":"Arman Cohan, Asaf Yehudai, Leyao Wang, Michal Shmueli-Scheuer, Peng Chen, Rex Ying, Yanan He, Yixin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T23:55:08Z","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19196","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":"sha256:7e59f933c8fd99f8f2b748694996627437f92167adc32e57a72531526124b328","target":"record","created_at":"2026-05-20T01:05:33Z","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":"96d5bc119bea352777849d4953fe5f716d1233f8deafba486242355a9c749114","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T23:55:08Z","title_canon_sha256":"8b6713a5aa05135e1552164a715ca989152edbf1c4f6305c4d3b0eb366d102ff"},"schema_version":"1.0","source":{"id":"2605.19196","kind":"arxiv","version":1}},"canonical_sha256":"f9b4e017680d5bc0b6dee4b839c506655cc04ed9bf3aca9de08b69684713bc1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9b4e017680d5bc0b6dee4b839c506655cc04ed9bf3aca9de08b69684713bc1f","first_computed_at":"2026-05-20T01:05:33.045381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:33.045381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7a2R3/IATDw9im9EEuNwhwPGql5kcTCzg3qqvVcyB5u+TNoTsS+0MOowLP/wHrn3CxqphBfOVyeSVM2iZ+NDA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:33.046152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e59f933c8fd99f8f2b748694996627437f92167adc32e57a72531526124b328","sha256:273e6da473ffd4a28d88d3a95b53024b414d3473374e4b063d2b0172ed0bcb38","sha256:4769a2e274729399edebeb06977f758162307ba86c8c78ab5dff84e37dab0bbc"],"state_sha256":"1a085129688bdd88bc19835a8749289597e4ca4057496fcf38eb2ef04f61a68b"}