{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MXU4TJDVDXUJ4VVZPWVVIWOFKG","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":"bff821ebe7c91c46aaeb3db3c738772db43ef08b4b620c59dd52d42a23279617","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:19:21Z","title_canon_sha256":"1afd3698d80939840986ba0d2da09ad274577312195338a9164742e50c97bfff"},"schema_version":"1.0","source":{"id":"2506.18387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18387","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18387v1","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18387","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_12","alias_value":"MXU4TJDVDXUJ","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_16","alias_value":"MXU4TJDVDXUJ4VVZ","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_8","alias_value":"MXU4TJDV","created_at":"2026-07-05T11:25:49Z"}],"graph_snapshots":[{"event_id":"sha256:4d05e2257ea57b7f88662055554c18719042ebd20f9f2207b9352403d39acc20","target":"graph","created_at":"2026-07-05T11:25:49Z","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/2506.18387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates how accurately different evaluation metrics capture the quality of causal explanations in automatically generated diagnostic reports. We compare six metrics: BERTScore, Cosine Similarity, BioSentVec, GPT-White, GPT-Black, and expert qualitative assessment across two input types: observation-based and multiple-choice-based report generation. Two weighting strategies are applied: one reflecting task-specific priorities, and the other assigning equal weights to all metrics. Our results show that GPT-Black demonstrates the strongest discriminative power in identifying logic","authors_text":"Key-Sun Choi, Yousang Cho","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:19:21Z","title":"Evaluating Causal Explanation in Medical Reports with LLM-Based and Human-Aligned Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18387","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:bc0994578ac9c344bcaca8b683176f752c37444fe6d81e3108b334c0e81bb963","target":"record","created_at":"2026-07-05T11:25:49Z","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":"bff821ebe7c91c46aaeb3db3c738772db43ef08b4b620c59dd52d42a23279617","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:19:21Z","title_canon_sha256":"1afd3698d80939840986ba0d2da09ad274577312195338a9164742e50c97bfff"},"schema_version":"1.0","source":{"id":"2506.18387","kind":"arxiv","version":1}},"canonical_sha256":"65e9c9a4751de89e56b97dab5459c551b9c8a28bdcada4d586e72bf593c3cb6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65e9c9a4751de89e56b97dab5459c551b9c8a28bdcada4d586e72bf593c3cb6d","first_computed_at":"2026-07-05T11:25:49.591896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:49.591896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"infS6UrkT2Z4GnNWEYLJ+/pd3xTfYECSImEUqaAl2fWoZlZmOvRhEq2n9qnD/HeL7SFbDpg3pD27PKe8OGleCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:49.592324Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc0994578ac9c344bcaca8b683176f752c37444fe6d81e3108b334c0e81bb963","sha256:4d05e2257ea57b7f88662055554c18719042ebd20f9f2207b9352403d39acc20"],"state_sha256":"a8cb2cf72a3f50841fcd81b115f9d4f495f88310d33ea3943f08d445df7b66f5"}