{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TOM25LCZDZDTXYBIDSIR2CFBVB","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":"31c90f88e511f5ff091206db2851dce0170282acf30a18a4fe1f32ff2ccf5614","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T02:24:19Z","title_canon_sha256":"405ab2c5307fd85e86d88f139408e4b600b801b37ba7af37e98c75974b65010f"},"schema_version":"1.0","source":{"id":"2508.08277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08277","created_at":"2026-07-05T11:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08277v1","created_at":"2026-07-05T11:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08277","created_at":"2026-07-05T11:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"TOM25LCZDZDT","created_at":"2026-07-05T11:52:25Z"},{"alias_kind":"pith_short_16","alias_value":"TOM25LCZDZDTXYBI","created_at":"2026-07-05T11:52:25Z"},{"alias_kind":"pith_short_8","alias_value":"TOM25LCZ","created_at":"2026-07-05T11:52:25Z"}],"graph_snapshots":[{"event_id":"sha256:cb7d0076b446003fc58072dbece83cb4d7b998fce01d27e7d7d74d48855ed59f","target":"graph","created_at":"2026-07-05T11:52:25Z","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/2508.08277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the performance of Large Language Models (LLMs) is a critical yet challenging task, particularly when aiming to avoid subjective assessments. This paper proposes a framework for leveraging subjective metrics derived from the class textual materials across different semesters to assess LLM outputs across various tasks. By utilizing well-defined benchmarks, factual datasets, and structured evaluation pipelines, the approach ensures consistent, reproducible, and bias-minimized measurements. The framework emphasizes automation and transparency in scoring, reducing reliance on human inte","authors_text":"Edward Gehringer, Haoze Du, Richard Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T02:24:19Z","title":"Objective Metrics for Evaluating Large Language Models Using External Data Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08277","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":"sha256:20932a5671aafd056bfa53868eddef2fbfab28d2cb11526665e289c73d5d0b4e","target":"record","created_at":"2026-07-05T11:52:25Z","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":"31c90f88e511f5ff091206db2851dce0170282acf30a18a4fe1f32ff2ccf5614","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T02:24:19Z","title_canon_sha256":"405ab2c5307fd85e86d88f139408e4b600b801b37ba7af37e98c75974b65010f"},"schema_version":"1.0","source":{"id":"2508.08277","kind":"arxiv","version":1}},"canonical_sha256":"9b99aeac591e473be0281c911d08a1a86f3d86342de0a3c6403f3b20bfde222d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b99aeac591e473be0281c911d08a1a86f3d86342de0a3c6403f3b20bfde222d","first_computed_at":"2026-07-05T11:52:25.189785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:25.189785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tngeDx1yyULtnUtXfwR7SCUkiqH7hCe54bTDSjY1zEOhCJ8fq1EbVIdzuGb0Jb/lBzvQcqOnlVTVykOR332BDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:25.190332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20932a5671aafd056bfa53868eddef2fbfab28d2cb11526665e289c73d5d0b4e","sha256:cb7d0076b446003fc58072dbece83cb4d7b998fce01d27e7d7d74d48855ed59f"],"state_sha256":"637c246ce8c855c913f489cc24adf4ad870c392c5845050d8b6eb79789898e8c"}