{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NIBOZM3SM2AJC4FR5OR6LITS6P","short_pith_number":"pith:NIBOZM3S","schema_version":"1.0","canonical_sha256":"6a02ecb37266809170b1eba3e5a272f3e45456e0fce86eadb8db505b2286fad9","source":{"kind":"arxiv","id":"2508.07955","version":3},"attestation_state":"computed","paper":{"title":"Expert Preference-based Evaluation of Automated Related Work Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furkan \\c{S}ahinu\\c{c}, Iryna Gurevych, Subhabrata Dutta","submitted_at":"2025-08-11T13:08:07Z","abstract_excerpt":"Expert domain writing, such as scientific writing, typically demands extensive domain knowledge. Although large language models (LLMs) show promising potential in this task, evaluating the quality of automatically generated scientific writing is a crucial open issue, as it requires knowledge of domain-specific criteria and the ability to discern expert preferences. Conventional automatic evaluation metrics and LLM-as-a-judge systems, primarily designed for mainstream NLP tasks, are insufficient to grasp expert preferences and domain-specific quality standards. To address this gap and support r"},"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":"2508.07955","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T13:08:07Z","cross_cats_sorted":[],"title_canon_sha256":"4d900119ec7966a576e97dca9b52a397303a254df378a55f7a36f362373e9f97","abstract_canon_sha256":"5f8257a95d6ccdf5ef3a20f62abb93159b551cfbd6610faf244be2020ca6517e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:46.716811Z","signature_b64":"Jqvu4cj/MounQKcE/DIUYJaKYSpLAzkhMDQiCPBJq23BNj0lROttfn2bNdZB7SsXT9SYyA8pdPYmEfuaDsLrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a02ecb37266809170b1eba3e5a272f3e45456e0fce86eadb8db505b2286fad9","last_reissued_at":"2026-06-23T03:13:46.716300Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:46.716300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expert Preference-based Evaluation of Automated Related Work Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furkan \\c{S}ahinu\\c{c}, Iryna Gurevych, Subhabrata Dutta","submitted_at":"2025-08-11T13:08:07Z","abstract_excerpt":"Expert domain writing, such as scientific writing, typically demands extensive domain knowledge. Although large language models (LLMs) show promising potential in this task, evaluating the quality of automatically generated scientific writing is a crucial open issue, as it requires knowledge of domain-specific criteria and the ability to discern expert preferences. Conventional automatic evaluation metrics and LLM-as-a-judge systems, primarily designed for mainstream NLP tasks, are insufficient to grasp expert preferences and domain-specific quality standards. To address this gap and support r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07955","kind":"arxiv","version":3},"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/2508.07955/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":"2508.07955","created_at":"2026-06-23T03:13:46.716371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07955v3","created_at":"2026-06-23T03:13:46.716371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07955","created_at":"2026-06-23T03:13:46.716371+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIBOZM3SM2AJ","created_at":"2026-06-23T03:13:46.716371+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIBOZM3SM2AJC4FR","created_at":"2026-06-23T03:13:46.716371+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIBOZM3S","created_at":"2026-06-23T03:13:46.716371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.24894","citing_title":"RWGBench: Evaluating Scholarly Positioning in Related Work Generation","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P","json":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P.json","graph_json":"https://pith.science/api/pith-number/NIBOZM3SM2AJC4FR5OR6LITS6P/graph.json","events_json":"https://pith.science/api/pith-number/NIBOZM3SM2AJC4FR5OR6LITS6P/events.json","paper":"https://pith.science/paper/NIBOZM3S"},"agent_actions":{"view_html":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P","download_json":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P.json","view_paper":"https://pith.science/paper/NIBOZM3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07955&json=true","fetch_graph":"https://pith.science/api/pith-number/NIBOZM3SM2AJC4FR5OR6LITS6P/graph.json","fetch_events":"https://pith.science/api/pith-number/NIBOZM3SM2AJC4FR5OR6LITS6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P/action/storage_attestation","attest_author":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P/action/author_attestation","sign_citation":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P/action/citation_signature","submit_replication":"https://pith.science/pith/NIBOZM3SM2AJC4FR5OR6LITS6P/action/replication_record"}},"created_at":"2026-06-23T03:13:46.716371+00:00","updated_at":"2026-06-23T03:13:46.716371+00:00"}