{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKLIFI237CO7WI65O5JQ2NRQUA","short_pith_number":"pith:MKLIFI23","schema_version":"1.0","canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","source":{"kind":"arxiv","id":"2508.20810","version":3},"attestation_state":"computed","paper":{"title":"From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Guillaume Chabot-Couture, Jessica M. Lundin, Usman Nasir Nakakana","submitted_at":"2025-08-28T14:10:59Z","abstract_excerpt":"Rigorous evaluation of domain-specific language models requires benchmarks that are comprehensive, contamination-resistant, and maintainable. Static, manually curated datasets do not satisfy these properties. We present a graph-based evaluation harness that transforms structured clinical guidelines into a queryable knowledge graph and dynamically instantiates evaluation queries via graph traversal. The framework provides three guarantees: (1) complete coverage of guideline relationships; (2) surface-form contamination resistance through combinatorial variation; and (3) validity inherited from "},"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":"2508.20810","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-28T14:10:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e4db8f4b1e548f0dfc2b675e85bf20175d8e149f9af971c9fac7edcc0e137d2","abstract_canon_sha256":"56a2d87ebeeb2506505caf256bffe8a35c6add182ba5fd1d456975cf50e8e570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:23.015144Z","signature_b64":"HnEiFDKCKAjvyZzTHABWTAbiwjbBELY9IeLRXKgjpkzcf2CSt+D7fJehz1om8ft8GF3jl/sjG/yfKt6erdDSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","last_reissued_at":"2026-05-20T00:00:23.014334Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:23.014334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Guillaume Chabot-Couture, Jessica M. Lundin, Usman Nasir Nakakana","submitted_at":"2025-08-28T14:10:59Z","abstract_excerpt":"Rigorous evaluation of domain-specific language models requires benchmarks that are comprehensive, contamination-resistant, and maintainable. Static, manually curated datasets do not satisfy these properties. We present a graph-based evaluation harness that transforms structured clinical guidelines into a queryable knowledge graph and dynamically instantiates evaluation queries via graph traversal. The framework provides three guarantees: (1) complete coverage of guideline relationships; (2) surface-form contamination resistance through combinatorial variation; and (3) validity inherited from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20810","kind":"arxiv","version":3},"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/2508.20810/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":"2508.20810","created_at":"2026-05-20T00:00:23.014455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20810v3","created_at":"2026-05-20T00:00:23.014455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20810","created_at":"2026-05-20T00:00:23.014455+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKLIFI237CO7","created_at":"2026-05-20T00:00:23.014455+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKLIFI237CO7WI65","created_at":"2026-05-20T00:00:23.014455+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKLIFI23","created_at":"2026-05-20T00:00:23.014455+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/MKLIFI237CO7WI65O5JQ2NRQUA","json":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA.json","graph_json":"https://pith.science/api/pith-number/MKLIFI237CO7WI65O5JQ2NRQUA/graph.json","events_json":"https://pith.science/api/pith-number/MKLIFI237CO7WI65O5JQ2NRQUA/events.json","paper":"https://pith.science/paper/MKLIFI23"},"agent_actions":{"view_html":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA","download_json":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA.json","view_paper":"https://pith.science/paper/MKLIFI23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20810&json=true","fetch_graph":"https://pith.science/api/pith-number/MKLIFI237CO7WI65O5JQ2NRQUA/graph.json","fetch_events":"https://pith.science/api/pith-number/MKLIFI237CO7WI65O5JQ2NRQUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/action/storage_attestation","attest_author":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/action/author_attestation","sign_citation":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/action/citation_signature","submit_replication":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/action/replication_record"}},"created_at":"2026-05-20T00:00:23.014455+00:00","updated_at":"2026-05-20T00:00:23.014455+00:00"}