{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WKD3OVPKYI3KN5QAG2TOYCLTLI","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":"9a33d222920c4d7dbc2c73608fb782409216e1ceb75941c96c7f18c4e0ab0100","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:30:46Z","title_canon_sha256":"efb3b0d93362ef21e89c58efd8c128b04ced3dc5a18e8de7bfa59173add5d72a"},"schema_version":"1.0","source":{"id":"2505.14279","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14279","created_at":"2026-07-05T11:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14279v2","created_at":"2026-07-05T11:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14279","created_at":"2026-07-05T11:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"WKD3OVPKYI3K","created_at":"2026-07-05T11:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"WKD3OVPKYI3KN5QA","created_at":"2026-07-05T11:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"WKD3OVPK","created_at":"2026-07-05T11:11:45Z"}],"graph_snapshots":[{"event_id":"sha256:0d1f3312c7264c2959d89c07f886fd0a6de04e4b08eb3060fb0c79eb2857e185","target":"graph","created_at":"2026-07-05T11:11:45Z","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/2505.14279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) drive scientific question-answering on modern search engines, yet their evaluation robustness remains underexplored. We introduce YESciEval, an open-source framework that combines fine-grained rubric-based assessment with reinforcement learning to mitigate optimism bias in LLM evaluators. We release multidisciplinary scienceQ&A datasets, including adversarial variants, with evaluation scores from multiple LLMs. Independent of proprietary models and human feedback, our approach enables scalable, cost-free evaluation. By advancing reliable LLM-as-a-judge models, this","authors_text":"Hamed Babaei Giglou, Jennifer D'Souza, Quentin M\\\"unch","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:30:46Z","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14279","kind":"arxiv","version":2},"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":"sha256:9235199517522d8d93238b4f000f93102703c389e0fb96fd411e4a4704cad842","target":"record","created_at":"2026-07-05T11:11:45Z","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":"9a33d222920c4d7dbc2c73608fb782409216e1ceb75941c96c7f18c4e0ab0100","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:30:46Z","title_canon_sha256":"efb3b0d93362ef21e89c58efd8c128b04ced3dc5a18e8de7bfa59173add5d72a"},"schema_version":"1.0","source":{"id":"2505.14279","kind":"arxiv","version":2}},"canonical_sha256":"b287b755eac236a6f60036a6ec09735a31639d64c319c45de22b268f1872c63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b287b755eac236a6f60036a6ec09735a31639d64c319c45de22b268f1872c63b","first_computed_at":"2026-07-05T11:11:45.798904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:45.798904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"69rGrI/TUGssDjFAlrBfMMWzhLqFGGvQAi3pwpL5HqVga/X6XBmf/U5P1+XCs4l48n/mSfEJ6p4BTph+cDYLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:45.799382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14279","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9235199517522d8d93238b4f000f93102703c389e0fb96fd411e4a4704cad842","sha256:0d1f3312c7264c2959d89c07f886fd0a6de04e4b08eb3060fb0c79eb2857e185"],"state_sha256":"5c3ae58eea9431f15364096741a392192575221e1b4fe8553a744af30f9cd733"}