{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WGZU5ZZRFNWOMBS7SUDALDO5DG","short_pith_number":"pith:WGZU5ZZR","schema_version":"1.0","canonical_sha256":"b1b34ee7312b6ce6065f9506058ddd19b3b17aa61195af91233eea6394f6027b","source":{"kind":"arxiv","id":"2607.12835","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Hanhua Hong, Jiaoyan Chen, Jung-jae Kim, Luu Gia Huy, Sophia Ananiadou, Yizhi Li","submitted_at":"2026-07-14T14:52:42Z","abstract_excerpt":"Rubric-based evaluation is a promising approach for assessing open-ended outputs from LLM-based research agents, particularly in paper reproduction, where direct paper-to-repository comparison is prone to hallucination. However, constructing paper-specific rubrics requires substantial expert effort, limiting the scalability of benchmarks such as PaperBench. In this work, we present, to our knowledge, the first systematic meta-evaluation of LLM-generated rubrics for paper reproduction. We reformulate rubrics into a checklist-style format and evaluate four generation settings across two backbone"},"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":"2607.12835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T14:52:42Z","cross_cats_sorted":[],"title_canon_sha256":"23a75f73fe909aec46515f85458b42ee8ba2d56e9f3eb371f09fdafc389d9111","abstract_canon_sha256":"b083ad7040951d2947e1a5eba1ab92aa06dd37c9ec904fab03f834776cac2447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:20.923826Z","signature_b64":"DEVi1NuyhU6xo8J4nPzTFLDzS898eOu6ABDpgUe71Nmpn2Llw/Coe4X+gMDhYjC0XL4OoFotxhnNfTmg5NIoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b34ee7312b6ce6065f9506058ddd19b3b17aa61195af91233eea6394f6027b","last_reissued_at":"2026-07-15T01:22:20.922754Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:20.922754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Hanhua Hong, Jiaoyan Chen, Jung-jae Kim, Luu Gia Huy, Sophia Ananiadou, Yizhi Li","submitted_at":"2026-07-14T14:52:42Z","abstract_excerpt":"Rubric-based evaluation is a promising approach for assessing open-ended outputs from LLM-based research agents, particularly in paper reproduction, where direct paper-to-repository comparison is prone to hallucination. However, constructing paper-specific rubrics requires substantial expert effort, limiting the scalability of benchmarks such as PaperBench. In this work, we present, to our knowledge, the first systematic meta-evaluation of LLM-generated rubrics for paper reproduction. We reformulate rubrics into a checklist-style format and evaluate four generation settings across two backbone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12835","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/2607.12835/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":"2607.12835","created_at":"2026-07-15T01:22:20.923339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12835v1","created_at":"2026-07-15T01:22:20.923339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12835","created_at":"2026-07-15T01:22:20.923339+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGZU5ZZRFNWO","created_at":"2026-07-15T01:22:20.923339+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGZU5ZZRFNWOMBS7","created_at":"2026-07-15T01:22:20.923339+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGZU5ZZR","created_at":"2026-07-15T01:22:20.923339+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/WGZU5ZZRFNWOMBS7SUDALDO5DG","json":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG.json","graph_json":"https://pith.science/api/pith-number/WGZU5ZZRFNWOMBS7SUDALDO5DG/graph.json","events_json":"https://pith.science/api/pith-number/WGZU5ZZRFNWOMBS7SUDALDO5DG/events.json","paper":"https://pith.science/paper/WGZU5ZZR"},"agent_actions":{"view_html":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG","download_json":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG.json","view_paper":"https://pith.science/paper/WGZU5ZZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12835&json=true","fetch_graph":"https://pith.science/api/pith-number/WGZU5ZZRFNWOMBS7SUDALDO5DG/graph.json","fetch_events":"https://pith.science/api/pith-number/WGZU5ZZRFNWOMBS7SUDALDO5DG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG/action/storage_attestation","attest_author":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG/action/author_attestation","sign_citation":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG/action/citation_signature","submit_replication":"https://pith.science/pith/WGZU5ZZRFNWOMBS7SUDALDO5DG/action/replication_record"}},"created_at":"2026-07-15T01:22:20.923339+00:00","updated_at":"2026-07-15T01:22:20.923339+00:00"}