{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MKLIFI237CO7WI65O5JQ2NRQUA","short_pith_number":"pith:MKLIFI23","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"},"canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","source":{"kind":"arxiv","id":"2508.20810","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20810","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20810v3","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20810","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"MKLIFI237CO7","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"MKLIFI237CO7WI65","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"MKLIFI23","created_at":"2026-05-20T00:00:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MKLIFI237CO7WI65O5JQ2NRQUA","target":"record","payload":{"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"},"canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","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"},"source_kind":"arxiv","source_id":"2508.20810","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyG7e46mSkC8r5murbjvyYg3WsHmv4RGmfVIucbHP/lNbzegHybPPFjmeqqtrloMiOqiQJFuhEfuON5FtM8WAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:33:48.360854Z"},"content_sha256":"115bf9c7ea3a8c7f8aa174d38f8a983cb116459c18694e6f07f21059124f18ab","schema_version":"1.0","event_id":"sha256:115bf9c7ea3a8c7f8aa174d38f8a983cb116459c18694e6f07f21059124f18ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MKLIFI237CO7WI65O5JQ2NRQUA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ARh49dl3RaNal6yQm+ZaiL+Cmrk3JyZPaofIOVpg65ehe6fB3UexfP0ePRp+zMc0v8Ah6+kCAGEVpJXcJT72BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:33:48.361219Z"},"content_sha256":"6fbbb69789f79d9fa371d16a60527ee3f94bdc21e6239e994cd6e61f7b1aeff0","schema_version":"1.0","event_id":"sha256:6fbbb69789f79d9fa371d16a60527ee3f94bdc21e6239e994cd6e61f7b1aeff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/bundle.json","state_url":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKLIFI237CO7WI65O5JQ2NRQUA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T18:33:48Z","links":{"resolver":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA","bundle":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/bundle.json","state":"https://pith.science/pith/MKLIFI237CO7WI65O5JQ2NRQUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKLIFI237CO7WI65O5JQ2NRQUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKLIFI237CO7WI65O5JQ2NRQUA","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":"56a2d87ebeeb2506505caf256bffe8a35c6add182ba5fd1d456975cf50e8e570","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-28T14:10:59Z","title_canon_sha256":"5e4db8f4b1e548f0dfc2b675e85bf20175d8e149f9af971c9fac7edcc0e137d2"},"schema_version":"1.0","source":{"id":"2508.20810","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20810","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20810v3","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20810","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"MKLIFI237CO7","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"MKLIFI237CO7WI65","created_at":"2026-05-20T00:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"MKLIFI23","created_at":"2026-05-20T00:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:6fbbb69789f79d9fa371d16a60527ee3f94bdc21e6239e994cd6e61f7b1aeff0","target":"graph","created_at":"2026-05-20T00:00:23Z","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/2508.20810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Guillaume Chabot-Couture, Jessica M. Lundin, Usman Nasir Nakakana","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-28T14:10:59Z","title":"From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20810","kind":"arxiv","version":3},"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":"sha256:115bf9c7ea3a8c7f8aa174d38f8a983cb116459c18694e6f07f21059124f18ab","target":"record","created_at":"2026-05-20T00:00:23Z","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":"56a2d87ebeeb2506505caf256bffe8a35c6add182ba5fd1d456975cf50e8e570","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-28T14:10:59Z","title_canon_sha256":"5e4db8f4b1e548f0dfc2b675e85bf20175d8e149f9af971c9fac7edcc0e137d2"},"schema_version":"1.0","source":{"id":"2508.20810","kind":"arxiv","version":3}},"canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"629682a35bf89dfb23dd77530d3630a0232faab0543b72ddfa915f54b2cf5022","first_computed_at":"2026-05-20T00:00:23.014334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:23.014334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HnEiFDKCKAjvyZzTHABWTAbiwjbBELY9IeLRXKgjpkzcf2CSt+D7fJehz1om8ft8GF3jl/sjG/yfKt6erdDSCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:23.015144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20810","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115bf9c7ea3a8c7f8aa174d38f8a983cb116459c18694e6f07f21059124f18ab","sha256:6fbbb69789f79d9fa371d16a60527ee3f94bdc21e6239e994cd6e61f7b1aeff0"],"state_sha256":"d5f5d7aa6d606db82762a7cf437890c1285d5e7f2308045451841d48acdf0ca4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSZRB1ddAimfJsj8JeXB5MP98gfs4G2qejHLZzX3Uj11rA5WG9DHGhAodEYWf9EZJb+hZatKAhjRXz3rmrjyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:33:48.363344Z","bundle_sha256":"d93d5ed6e5658bc5bef2a3b67c6f45339f111eaa8f89901eb3ecad51a655e466"}}