{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7G2OAF3IBVN4BNW64S4DTRIGMV","short_pith_number":"pith:7G2OAF3I","schema_version":"1.0","canonical_sha256":"f9b4e017680d5bc0b6dee4b839c506655cc04ed9bf3aca9de08b69684713bc1f","source":{"kind":"arxiv","id":"2605.19196","version":1},"attestation_state":"computed","paper":{"title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Asaf Yehudai, Leyao Wang, Michal Shmueli-Scheuer, Peng Chen, Rex Ying, Yanan He, Yixin Liu","submitted_at":"2026-05-18T23:55:08Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.19196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T23:55:08Z","cross_cats_sorted":[],"title_canon_sha256":"8b6713a5aa05135e1552164a715ca989152edbf1c4f6305c4d3b0eb366d102ff","abstract_canon_sha256":"96d5bc119bea352777849d4953fe5f716d1233f8deafba486242355a9c749114"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:33.046152Z","signature_b64":"U7a2R3/IATDw9im9EEuNwhwPGql5kcTCzg3qqvVcyB5u+TNoTsS+0MOowLP/wHrn3CxqphBfOVyeSVM2iZ+NDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b4e017680d5bc0b6dee4b839c506655cc04ed9bf3aca9de08b69684713bc1f","last_reissued_at":"2026-05-20T01:05:33.045381Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:33.045381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Asaf Yehudai, Leyao Wang, Michal Shmueli-Scheuer, Peng Chen, Rex Ying, Yanan He, Yixin Liu","submitted_at":"2026-05-18T23:55:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19196","kind":"arxiv","version":1},"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/2605.19196/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.19196","created_at":"2026-05-20T01:05:33.045514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19196v1","created_at":"2026-05-20T01:05:33.045514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19196","created_at":"2026-05-20T01:05:33.045514+00:00"},{"alias_kind":"pith_short_12","alias_value":"7G2OAF3IBVN4","created_at":"2026-05-20T01:05:33.045514+00:00"},{"alias_kind":"pith_short_16","alias_value":"7G2OAF3IBVN4BNW6","created_at":"2026-05-20T01:05:33.045514+00:00"},{"alias_kind":"pith_short_8","alias_value":"7G2OAF3I","created_at":"2026-05-20T01:05:33.045514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV","json":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV.json","graph_json":"https://pith.science/api/pith-number/7G2OAF3IBVN4BNW64S4DTRIGMV/graph.json","events_json":"https://pith.science/api/pith-number/7G2OAF3IBVN4BNW64S4DTRIGMV/events.json","paper":"https://pith.science/paper/7G2OAF3I"},"agent_actions":{"view_html":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV","download_json":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV.json","view_paper":"https://pith.science/paper/7G2OAF3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19196&json=true","fetch_graph":"https://pith.science/api/pith-number/7G2OAF3IBVN4BNW64S4DTRIGMV/graph.json","fetch_events":"https://pith.science/api/pith-number/7G2OAF3IBVN4BNW64S4DTRIGMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV/action/storage_attestation","attest_author":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV/action/author_attestation","sign_citation":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV/action/citation_signature","submit_replication":"https://pith.science/pith/7G2OAF3IBVN4BNW64S4DTRIGMV/action/replication_record"}},"created_at":"2026-05-20T01:05:33.045514+00:00","updated_at":"2026-05-20T01:05:33.045514+00:00"}