{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MD5M3LKCNEBG4AZCHKZX2DKFTX","short_pith_number":"pith:MD5M3LKC","schema_version":"1.0","canonical_sha256":"60facdad4269026e03223ab37d0d459de450733eef869b7c74a7b30e65f0b831","source":{"kind":"arxiv","id":"2608.07641","version":1},"attestation_state":"computed","paper":{"title":"SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fanjin Zhang, Jie Tang, Jing Zhang, Juanzi Li, Ruyu Zhao, Yuanchun Wang, Yuheng Zhang","submitted_at":"2026-08-07T16:11:46Z","abstract_excerpt":"The rapid advancement of large language models has transformed survey writing from a months-long manual effort into an automated process. As generation scales, reliable evaluation becomes the bottleneck, and LLMs are increasingly used as survey evaluators. However, existing approaches largely rely on off-the-shelf LLM-as-a-judge methods without systematic alignment to human reviewers, and there remains a lack of systematic frameworks for quantifying alignment with human reviewers. To address this gap, we propose SurveyReview, a reviewer-aligned, multi-dimensional benchmark and dataset for surv"},"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":"2608.07641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T16:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"cb671f47845b1623507bf15ed28e4b4994d1b157296717c175704e0cf04e6e94","abstract_canon_sha256":"ea01b17f71a9425ec8266487a378e6373475080994705e58daa88c10cb35a6be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T00:15:33.503613Z","signature_b64":"IJ+UU0qwRagGOlKtL/MeysTcY10B/uqWqMKvF3fhBFpxD/V28jCoiliJ7plMkiFIWCCU/ymVAv5Bn7aN1RQLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60facdad4269026e03223ab37d0d459de450733eef869b7c74a7b30e65f0b831","last_reissued_at":"2026-08-11T00:15:33.501189Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T00:15:33.501189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fanjin Zhang, Jie Tang, Jing Zhang, Juanzi Li, Ruyu Zhao, Yuanchun Wang, Yuheng Zhang","submitted_at":"2026-08-07T16:11:46Z","abstract_excerpt":"The rapid advancement of large language models has transformed survey writing from a months-long manual effort into an automated process. As generation scales, reliable evaluation becomes the bottleneck, and LLMs are increasingly used as survey evaluators. However, existing approaches largely rely on off-the-shelf LLM-as-a-judge methods without systematic alignment to human reviewers, and there remains a lack of systematic frameworks for quantifying alignment with human reviewers. To address this gap, we propose SurveyReview, a reviewer-aligned, multi-dimensional benchmark and dataset for surv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07641","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/2608.07641/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":"2608.07641","created_at":"2026-08-11T00:15:33.501753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07641v1","created_at":"2026-08-11T00:15:33.501753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07641","created_at":"2026-08-11T00:15:33.501753+00:00"},{"alias_kind":"pith_short_12","alias_value":"MD5M3LKCNEBG","created_at":"2026-08-11T00:15:33.501753+00:00"},{"alias_kind":"pith_short_16","alias_value":"MD5M3LKCNEBG4AZC","created_at":"2026-08-11T00:15:33.501753+00:00"},{"alias_kind":"pith_short_8","alias_value":"MD5M3LKC","created_at":"2026-08-11T00:15:33.501753+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/MD5M3LKCNEBG4AZCHKZX2DKFTX","json":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX.json","graph_json":"https://pith.science/api/pith-number/MD5M3LKCNEBG4AZCHKZX2DKFTX/graph.json","events_json":"https://pith.science/api/pith-number/MD5M3LKCNEBG4AZCHKZX2DKFTX/events.json","paper":"https://pith.science/paper/MD5M3LKC"},"agent_actions":{"view_html":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX","download_json":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX.json","view_paper":"https://pith.science/paper/MD5M3LKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07641&json=true","fetch_graph":"https://pith.science/api/pith-number/MD5M3LKCNEBG4AZCHKZX2DKFTX/graph.json","fetch_events":"https://pith.science/api/pith-number/MD5M3LKCNEBG4AZCHKZX2DKFTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX/action/storage_attestation","attest_author":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX/action/author_attestation","sign_citation":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX/action/citation_signature","submit_replication":"https://pith.science/pith/MD5M3LKCNEBG4AZCHKZX2DKFTX/action/replication_record"}},"created_at":"2026-08-11T00:15:33.501753+00:00","updated_at":"2026-08-11T00:15:33.501753+00:00"}