{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4DUNWW53GZFZILGGNYGG4HFUBQ","short_pith_number":"pith:4DUNWW53","canonical_record":{"source":{"id":"2409.01941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T14:38:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5d2713816b20de0b2816860899bd56bf2d4d09baa298ed1f7b40484a6782ed5","abstract_canon_sha256":"456bfb2aa5926d1c502a3b47d6891103570f1b3d21cbcccbfbd0fd875a939237"},"schema_version":"1.0"},"canonical_sha256":"e0e8db5bbb364b942cc66e0c6e1cb40c254b25f2f3299a9c2e4e65b2c73c7e8d","source":{"kind":"arxiv","id":"2409.01941","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01941","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01941v1","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01941","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_12","alias_value":"4DUNWW53GZFZ","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_16","alias_value":"4DUNWW53GZFZILGG","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_8","alias_value":"4DUNWW53","created_at":"2026-07-05T09:02:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4DUNWW53GZFZILGGNYGG4HFUBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.01941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T14:38:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5d2713816b20de0b2816860899bd56bf2d4d09baa298ed1f7b40484a6782ed5","abstract_canon_sha256":"456bfb2aa5926d1c502a3b47d6891103570f1b3d21cbcccbfbd0fd875a939237"},"schema_version":"1.0"},"canonical_sha256":"e0e8db5bbb364b942cc66e0c6e1cb40c254b25f2f3299a9c2e4e65b2c73c7e8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:36.302803Z","signature_b64":"4Ru6pKAhnrgx7KtG+2zib6g+01IduzxnhhEtlpfl8kgK8x66PMo6EyZXWXE5wZ66oBM8fLqZjvxTmT2ulRZ1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0e8db5bbb364b942cc66e0c6e1cb40c254b25f2f3299a9c2e4e65b2c73c7e8d","last_reissued_at":"2026-07-05T09:02:36.302351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:36.302351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.01941","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":"2026-07-05T09:02:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Dd3YD/mt68JJi8NXI7yvNkCGBpPAy52IWHQAUEp7/5Fs/t4TQp/PSEa/DpJV9POm8way45BL8fG/sqsl+NUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:08.162057Z"},"content_sha256":"5157cb782fe728ef5dec7667804a37c1d9b7672874346fbad33bf853ab51f6ee","schema_version":"1.0","event_id":"sha256:5157cb782fe728ef5dec7667804a37c1d9b7672874346fbad33bf853ab51f6ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4DUNWW53GZFZILGGNYGG4HFUBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Leveraging Large Language Models for Automated Medical Q&A Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bahador Saket, Feroz Ahmad, Gaurav Trivedi, Herprit Mahal, Jack Krolik","submitted_at":"2024-09-03T14:38:29Z","abstract_excerpt":"This paper explores the potential of using Large Language Models (LLMs) to automate the evaluation of responses in medical Question and Answer (Q\\&A) systems, a crucial form of Natural Language Processing. Traditionally, human evaluation has been indispensable for assessing the quality of these responses. However, manual evaluation by medical professionals is time-consuming and costly. Our study examines whether LLMs can reliably replicate human evaluations by using questions derived from patient data, thereby saving valuable time for medical experts. While the findings suggest promising resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01941","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/2409.01941/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":"2026-07-05T09:02:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aoptcF7KvxoeKfgJVPXU/3KeWWvcCQWffKuvF1YSOHkN6DzPVeQQfEQLY7Oj6oaVT4e/H4vW6aa7xM1Lesl+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:08.162725Z"},"content_sha256":"f60a4a379cc16c8bd0f5f089f8bbe136f54e7c53a24f48c0b103beb9dcb9d1ef","schema_version":"1.0","event_id":"sha256:f60a4a379cc16c8bd0f5f089f8bbe136f54e7c53a24f48c0b103beb9dcb9d1ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/bundle.json","state_url":"https://pith.science/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/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":"2026-08-09T08:48:08Z","links":{"resolver":"https://pith.science/pith/4DUNWW53GZFZILGGNYGG4HFUBQ","bundle":"https://pith.science/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/bundle.json","state":"https://pith.science/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DUNWW53GZFZILGGNYGG4HFUBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4DUNWW53GZFZILGGNYGG4HFUBQ","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":"456bfb2aa5926d1c502a3b47d6891103570f1b3d21cbcccbfbd0fd875a939237","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T14:38:29Z","title_canon_sha256":"b5d2713816b20de0b2816860899bd56bf2d4d09baa298ed1f7b40484a6782ed5"},"schema_version":"1.0","source":{"id":"2409.01941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01941","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01941v1","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01941","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_12","alias_value":"4DUNWW53GZFZ","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_16","alias_value":"4DUNWW53GZFZILGG","created_at":"2026-07-05T09:02:36Z"},{"alias_kind":"pith_short_8","alias_value":"4DUNWW53","created_at":"2026-07-05T09:02:36Z"}],"graph_snapshots":[{"event_id":"sha256:f60a4a379cc16c8bd0f5f089f8bbe136f54e7c53a24f48c0b103beb9dcb9d1ef","target":"graph","created_at":"2026-07-05T09:02:36Z","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/2409.01941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the potential of using Large Language Models (LLMs) to automate the evaluation of responses in medical Question and Answer (Q\\&A) systems, a crucial form of Natural Language Processing. Traditionally, human evaluation has been indispensable for assessing the quality of these responses. However, manual evaluation by medical professionals is time-consuming and costly. Our study examines whether LLMs can reliably replicate human evaluations by using questions derived from patient data, thereby saving valuable time for medical experts. While the findings suggest promising resul","authors_text":"Bahador Saket, Feroz Ahmad, Gaurav Trivedi, Herprit Mahal, Jack Krolik","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T14:38:29Z","title":"Towards Leveraging Large Language Models for Automated Medical Q&A Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01941","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":"sha256:5157cb782fe728ef5dec7667804a37c1d9b7672874346fbad33bf853ab51f6ee","target":"record","created_at":"2026-07-05T09:02:36Z","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":"456bfb2aa5926d1c502a3b47d6891103570f1b3d21cbcccbfbd0fd875a939237","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T14:38:29Z","title_canon_sha256":"b5d2713816b20de0b2816860899bd56bf2d4d09baa298ed1f7b40484a6782ed5"},"schema_version":"1.0","source":{"id":"2409.01941","kind":"arxiv","version":1}},"canonical_sha256":"e0e8db5bbb364b942cc66e0c6e1cb40c254b25f2f3299a9c2e4e65b2c73c7e8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0e8db5bbb364b942cc66e0c6e1cb40c254b25f2f3299a9c2e4e65b2c73c7e8d","first_computed_at":"2026-07-05T09:02:36.302351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:36.302351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Ru6pKAhnrgx7KtG+2zib6g+01IduzxnhhEtlpfl8kgK8x66PMo6EyZXWXE5wZ66oBM8fLqZjvxTmT2ulRZ1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:36.302803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5157cb782fe728ef5dec7667804a37c1d9b7672874346fbad33bf853ab51f6ee","sha256:f60a4a379cc16c8bd0f5f089f8bbe136f54e7c53a24f48c0b103beb9dcb9d1ef"],"state_sha256":"b50a500b805fa7c499b5ca44bbacebe749e401ce5e4e8cb36b790d9720f32b1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcZhZMo1+i8b9x5/vz3whxTAV3oeQnweSGCDBDgAujWWBn+Y7M5YQbvfXNLDCSC8IteSeQWDyNgNq0UEEK6QAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:48:08.168667Z","bundle_sha256":"f7afd0aa291d858f57ab814ab78e9712e10579e8fd3d6ee857750a70fe63862e"}}