{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WWOVGXVNNUPYK2IB56KEMINNLK","short_pith_number":"pith:WWOVGXVN","canonical_record":{"source":{"id":"2502.06666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:52:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed95aef1a29051c47aefc36efa40e64235410c28457c82cace0d2ef7fe8820a2","abstract_canon_sha256":"2e91a601ed0f01805a23f2f81d3c9bc03f5ef01c398150a57f73cd8b555d953a"},"schema_version":"1.0"},"canonical_sha256":"b59d535ead6d1f856901ef944621ad5abec77d68f21ef6649c616f22b88650fa","source":{"kind":"arxiv","id":"2502.06666","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06666","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06666v1","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06666","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"WWOVGXVNNUPY","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"WWOVGXVNNUPYK2IB","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"WWOVGXVN","created_at":"2026-07-05T10:17:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WWOVGXVNNUPYK2IB56KEMINNLK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:52:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed95aef1a29051c47aefc36efa40e64235410c28457c82cace0d2ef7fe8820a2","abstract_canon_sha256":"2e91a601ed0f01805a23f2f81d3c9bc03f5ef01c398150a57f73cd8b555d953a"},"schema_version":"1.0"},"canonical_sha256":"b59d535ead6d1f856901ef944621ad5abec77d68f21ef6649c616f22b88650fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:16.341400Z","signature_b64":"TSp826V1eybO2jUFRstizu1P1zTX7b7Toub7QQfHh3cBjOdkJYy11Q7qT6BLoRw5vpDTf83sVJb+zQo+B8FqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b59d535ead6d1f856901ef944621ad5abec77d68f21ef6649c616f22b88650fa","last_reissued_at":"2026-07-05T10:17:16.340850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:16.340850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06666","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tU1C7kDRD5k/+Qn1Y+WsrOsdiq/LDDb1SZ6IZRuTXKP80wxKkJkZ+u3xMG0UVZy0ZjnNskzMHdZSQ3Mc617SAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:51:58.960921Z"},"content_sha256":"dbc76135ed5d91cf963ad603496e7c873b1c8712f7ff030b455bf18a352e79b9","schema_version":"1.0","event_id":"sha256:dbc76135ed5d91cf963ad603496e7c873b1c8712f7ff030b455bf18a352e79b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WWOVGXVNNUPYK2IB56KEMINNLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anna Arias-Duart, Ashwin Kumar Gururajan, Daniel Hinjos, Dario Garcia-Gasulla, Enrique Lopez-Cuena, Lucia Urcelay Ganzabal, Marta Gonzalez Mallo, Pablo Agustin Martin-Torres, Pablo Bernabeu-Perez, Sergio Alvarez-Napagao","submitted_at":"2025-02-10T16:52:39Z","abstract_excerpt":"Current Large Language Models (LLMs) benchmarks are often based on open-ended or close-ended QA evaluations, avoiding the requirement of human labor. Close-ended measurements evaluate the factuality of responses but lack expressiveness. Open-ended capture the model's capacity to produce discourse responses but are harder to assess for correctness. These two approaches are commonly used, either independently or together, though their relationship remains poorly understood. This work is focused on the healthcare domain, where both factuality and discourse matter greatly. It introduces a comprehe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06666","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/2502.06666/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":"2026-07-05T10:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fIld72X92/UCXf6GA113Ad8C1tvuRKwSjU8zbaBTeMHZXHzksI6zUTa6PFleM6GyFZcubd8YlMu8O692f3JBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:51:58.961535Z"},"content_sha256":"5304c0257f2339bfef59436e3a4b87cd5b5473c28575ba2452b7f592d352f270","schema_version":"1.0","event_id":"sha256:5304c0257f2339bfef59436e3a4b87cd5b5473c28575ba2452b7f592d352f270"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWOVGXVNNUPYK2IB56KEMINNLK/bundle.json","state_url":"https://pith.science/pith/WWOVGXVNNUPYK2IB56KEMINNLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWOVGXVNNUPYK2IB56KEMINNLK/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":"2026-08-09T06:51:58Z","links":{"resolver":"https://pith.science/pith/WWOVGXVNNUPYK2IB56KEMINNLK","bundle":"https://pith.science/pith/WWOVGXVNNUPYK2IB56KEMINNLK/bundle.json","state":"https://pith.science/pith/WWOVGXVNNUPYK2IB56KEMINNLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWOVGXVNNUPYK2IB56KEMINNLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WWOVGXVNNUPYK2IB56KEMINNLK","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":"2e91a601ed0f01805a23f2f81d3c9bc03f5ef01c398150a57f73cd8b555d953a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:52:39Z","title_canon_sha256":"ed95aef1a29051c47aefc36efa40e64235410c28457c82cace0d2ef7fe8820a2"},"schema_version":"1.0","source":{"id":"2502.06666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06666","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06666v1","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06666","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"WWOVGXVNNUPY","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"WWOVGXVNNUPYK2IB","created_at":"2026-07-05T10:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"WWOVGXVN","created_at":"2026-07-05T10:17:16Z"}],"graph_snapshots":[{"event_id":"sha256:5304c0257f2339bfef59436e3a4b87cd5b5473c28575ba2452b7f592d352f270","target":"graph","created_at":"2026-07-05T10:17:16Z","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/2502.06666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Large Language Models (LLMs) benchmarks are often based on open-ended or close-ended QA evaluations, avoiding the requirement of human labor. Close-ended measurements evaluate the factuality of responses but lack expressiveness. Open-ended capture the model's capacity to produce discourse responses but are harder to assess for correctness. These two approaches are commonly used, either independently or together, though their relationship remains poorly understood. This work is focused on the healthcare domain, where both factuality and discourse matter greatly. It introduces a comprehe","authors_text":"Anna Arias-Duart, Ashwin Kumar Gururajan, Daniel Hinjos, Dario Garcia-Gasulla, Enrique Lopez-Cuena, Lucia Urcelay Ganzabal, Marta Gonzalez Mallo, Pablo Agustin Martin-Torres, Pablo Bernabeu-Perez, Sergio Alvarez-Napagao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:52:39Z","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06666","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:dbc76135ed5d91cf963ad603496e7c873b1c8712f7ff030b455bf18a352e79b9","target":"record","created_at":"2026-07-05T10:17:16Z","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":"2e91a601ed0f01805a23f2f81d3c9bc03f5ef01c398150a57f73cd8b555d953a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:52:39Z","title_canon_sha256":"ed95aef1a29051c47aefc36efa40e64235410c28457c82cace0d2ef7fe8820a2"},"schema_version":"1.0","source":{"id":"2502.06666","kind":"arxiv","version":1}},"canonical_sha256":"b59d535ead6d1f856901ef944621ad5abec77d68f21ef6649c616f22b88650fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b59d535ead6d1f856901ef944621ad5abec77d68f21ef6649c616f22b88650fa","first_computed_at":"2026-07-05T10:17:16.340850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:16.340850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TSp826V1eybO2jUFRstizu1P1zTX7b7Toub7QQfHh3cBjOdkJYy11Q7qT6BLoRw5vpDTf83sVJb+zQo+B8FqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:16.341400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc76135ed5d91cf963ad603496e7c873b1c8712f7ff030b455bf18a352e79b9","sha256:5304c0257f2339bfef59436e3a4b87cd5b5473c28575ba2452b7f592d352f270"],"state_sha256":"39ecc264fffbd34914354bcb97aca44bc5875334b8b1dd5d960ee96028b43468"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLydh2WZ64xKjsWQVAxaw/hCPwsTV1gejuQmJnQYsUQcYIGkKRLdmoYVOkV04mkFlVD6kYtjAsjVFMrKW+5wBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:51:58.965441Z","bundle_sha256":"091e50edbdccc0d4ff2f5922a5d72006e92348b99c5ffb6a89ffe4e3be329f65"}}