{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOM25LCZDZDTXYBIDSIR2CFBVB","short_pith_number":"pith:TOM25LCZ","schema_version":"1.0","canonical_sha256":"9b99aeac591e473be0281c911d08a1a86f3d86342de0a3c6403f3b20bfde222d","source":{"kind":"arxiv","id":"2508.08277","version":1},"attestation_state":"computed","paper":{"title":"Objective Metrics for Evaluating Large Language Models Using External Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Gehringer, Haoze Du, Richard Li","submitted_at":"2025-08-01T02:24:19Z","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"},"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":"2508.08277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T02:24:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"405ab2c5307fd85e86d88f139408e4b600b801b37ba7af37e98c75974b65010f","abstract_canon_sha256":"31c90f88e511f5ff091206db2851dce0170282acf30a18a4fe1f32ff2ccf5614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:25.190332Z","signature_b64":"tngeDx1yyULtnUtXfwR7SCUkiqH7hCe54bTDSjY1zEOhCJ8fq1EbVIdzuGb0Jb/lBzvQcqOnlVTVykOR332BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b99aeac591e473be0281c911d08a1a86f3d86342de0a3c6403f3b20bfde222d","last_reissued_at":"2026-07-05T11:52:25.189785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:25.189785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Objective Metrics for Evaluating Large Language Models Using External Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Gehringer, Haoze Du, Richard Li","submitted_at":"2025-08-01T02:24:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08277","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/2508.08277/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":"2508.08277","created_at":"2026-07-05T11:52:25.189864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08277v1","created_at":"2026-07-05T11:52:25.189864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08277","created_at":"2026-07-05T11:52:25.189864+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOM25LCZDZDT","created_at":"2026-07-05T11:52:25.189864+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOM25LCZDZDTXYBI","created_at":"2026-07-05T11:52:25.189864+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOM25LCZ","created_at":"2026-07-05T11:52:25.189864+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/TOM25LCZDZDTXYBIDSIR2CFBVB","json":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB.json","graph_json":"https://pith.science/api/pith-number/TOM25LCZDZDTXYBIDSIR2CFBVB/graph.json","events_json":"https://pith.science/api/pith-number/TOM25LCZDZDTXYBIDSIR2CFBVB/events.json","paper":"https://pith.science/paper/TOM25LCZ"},"agent_actions":{"view_html":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB","download_json":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB.json","view_paper":"https://pith.science/paper/TOM25LCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08277&json=true","fetch_graph":"https://pith.science/api/pith-number/TOM25LCZDZDTXYBIDSIR2CFBVB/graph.json","fetch_events":"https://pith.science/api/pith-number/TOM25LCZDZDTXYBIDSIR2CFBVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB/action/storage_attestation","attest_author":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB/action/author_attestation","sign_citation":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB/action/citation_signature","submit_replication":"https://pith.science/pith/TOM25LCZDZDTXYBIDSIR2CFBVB/action/replication_record"}},"created_at":"2026-07-05T11:52:25.189864+00:00","updated_at":"2026-07-05T11:52:25.189864+00:00"}