{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:264EE335XVUDQ5H4GFUDPHWWWS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dd3705a7afc0ad6f5df5a93fed757162b1a14e9d33539863ab4c756ef99a3783","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T02:01:52Z","title_canon_sha256":"bbaa44b485f5e13252800c992effc0b3988500c51d91ee6b0fd9e90c21c3f307"},"schema_version":"1.0","source":{"id":"2506.00777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00777","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00777v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00777","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"264EE335XVUD","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"264EE335XVUDQ5H4","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"264EE335","created_at":"2026-07-05T11:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:b424709e44e7c720b7b8149dbcec5df1ed2d3f82dea61664e1cf2c452ffad1a9","target":"graph","created_at":"2026-07-05T11:13:40Z","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/2506.00777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive performance in biomedical relation extraction, even in zero-shot scenarios. However, evaluating LLMs in this task remains challenging due to their ability to generate human-like text, often producing synonyms or abbreviations of gold-standard answers, making traditional automatic evaluation metrics unreliable. On the other hand, while human evaluation is more reliable, it is costly and time-consuming, making it impractical for real-world applications. This paper investigates the use of LLMs-as-the-Judge as an alternative evaluation meth","authors_text":"Chun Peng, Elham Dolatabadi, Enamul Hoque, Israt Jahan, Jimmy Huang, Md Tahmid Rahman Laskar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T02:01:52Z","title":"Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00777","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":"sha256:2727314cc889b856357217214be278ec9934e94328a4ab5e957ee775caa556c7","target":"record","created_at":"2026-07-05T11:13:40Z","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":"dd3705a7afc0ad6f5df5a93fed757162b1a14e9d33539863ab4c756ef99a3783","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T02:01:52Z","title_canon_sha256":"bbaa44b485f5e13252800c992effc0b3988500c51d91ee6b0fd9e90c21c3f307"},"schema_version":"1.0","source":{"id":"2506.00777","kind":"arxiv","version":1}},"canonical_sha256":"d7b8426f7dbd683874fc3168379ed6b483dd9fb1d5f1bec44aa37e5ec198a757","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7b8426f7dbd683874fc3168379ed6b483dd9fb1d5f1bec44aa37e5ec198a757","first_computed_at":"2026-07-05T11:13:40.279768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:40.279768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q3mL8yLaxCx2yFbnsxrNiKB0V5cSNx81kTPmwvm2TAsHrLHF6bwMPwaJDSzybtC76IgdiyuabOt2czG/dkABDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:40.280285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2727314cc889b856357217214be278ec9934e94328a4ab5e957ee775caa556c7","sha256:b424709e44e7c720b7b8149dbcec5df1ed2d3f82dea61664e1cf2c452ffad1a9"],"state_sha256":"93ef60af0dffd92c6b023737ee94d75b4571fd4471c42d575390ba80b2c2caf4"}