{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SLQEXECV7QEOY6KYT2JCRK75TW","short_pith_number":"pith:SLQEXECV","canonical_record":{"source":{"id":"2408.09831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-19T09:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"d6ceb39dedc63e390e18da7d2734a4eee56566fd933f20480fd4f70d7439d0dd","abstract_canon_sha256":"60cb27afe471af24207c1ae4eb4e67bd5726c0bc659eba0a2c95fd99942f7bac"},"schema_version":"1.0"},"canonical_sha256":"92e04b9055fc08ec79589e9228abfd9da39f3a1c7d5e552c13fa2467da7438f9","source":{"kind":"arxiv","id":"2408.09831","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09831","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09831v2","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09831","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"SLQEXECV7QEO","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"SLQEXECV7QEOY6KY","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"SLQEXECV","created_at":"2026-07-05T10:02:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SLQEXECV7QEOY6KYT2JCRK75TW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-19T09:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"d6ceb39dedc63e390e18da7d2734a4eee56566fd933f20480fd4f70d7439d0dd","abstract_canon_sha256":"60cb27afe471af24207c1ae4eb4e67bd5726c0bc659eba0a2c95fd99942f7bac"},"schema_version":"1.0"},"canonical_sha256":"92e04b9055fc08ec79589e9228abfd9da39f3a1c7d5e552c13fa2467da7438f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:05.672035Z","signature_b64":"IIAR2TujuPn06P+0JyVDbNqwx8y4kZ6uTShbV19rlOMWeXsKOAtAKJ/uoLgRtVrLjDk07U7Zl6FuqaxCR04sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e04b9055fc08ec79589e9228abfd9da39f3a1c7d5e552c13fa2467da7438f9","last_reissued_at":"2026-07-05T10:02:05.671586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:05.671586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09831","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yuJKotvyolx6ztAgadDxl5hot6NTC4BYlkkuQtGIzyahDorRzOSR8RYJUry9qVS0eAAok3TkuIFqg7/wR52DBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:13:13.055960Z"},"content_sha256":"dc700976aa0d20ae06d942ae294ae0344497bf190e28c602cd7dcbe821dc13cd","schema_version":"1.0","event_id":"sha256:dc700976aa0d20ae06d942ae294ae0344497bf190e28c602cd7dcbe821dc13cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SLQEXECV7QEOY6KYT2JCRK75TW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ranking Generated Answers: On the Agreement of Retrieval Models with Humans on Consumer Health Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daniel Steinbach, Harrisen Scells, Jonas Probst, Martin Potthast, Sebastian Heineking","submitted_at":"2024-08-19T09:27:45Z","abstract_excerpt":"Evaluating the output of generative large language models (LLMs) is challenging and difficult to scale. Many evaluations of LLMs focus on tasks such as single-choice question-answering or text classification. These tasks are not suitable for assessing open-ended question-answering capabilities, which are critical in domains where expertise is required. One such domain is health, where misleading or incorrect answers can have a negative impact on a user's well-being. Using human experts to evaluate the quality of LLM answers is generally considered the gold standard, but expert annotation is co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09831","kind":"arxiv","version":2},"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/2408.09831/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":"2026-07-05T10:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4E/pO8tI9Tx1RuwbcBNF04hO9JK8zObvufBt3T+7+IW7wsfBydUB67C/Ca85gW75qIVXEY0e0+D0CTd0RHrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:13:13.056508Z"},"content_sha256":"b262e7f8698e34f42c0f91807362834c57c6e56a35fd60864bddb685e8516300","schema_version":"1.0","event_id":"sha256:b262e7f8698e34f42c0f91807362834c57c6e56a35fd60864bddb685e8516300"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLQEXECV7QEOY6KYT2JCRK75TW/bundle.json","state_url":"https://pith.science/pith/SLQEXECV7QEOY6KYT2JCRK75TW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLQEXECV7QEOY6KYT2JCRK75TW/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":"2026-08-17T23:13:13Z","links":{"resolver":"https://pith.science/pith/SLQEXECV7QEOY6KYT2JCRK75TW","bundle":"https://pith.science/pith/SLQEXECV7QEOY6KYT2JCRK75TW/bundle.json","state":"https://pith.science/pith/SLQEXECV7QEOY6KYT2JCRK75TW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLQEXECV7QEOY6KYT2JCRK75TW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SLQEXECV7QEOY6KYT2JCRK75TW","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":"60cb27afe471af24207c1ae4eb4e67bd5726c0bc659eba0a2c95fd99942f7bac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-19T09:27:45Z","title_canon_sha256":"d6ceb39dedc63e390e18da7d2734a4eee56566fd933f20480fd4f70d7439d0dd"},"schema_version":"1.0","source":{"id":"2408.09831","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09831","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09831v2","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09831","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"SLQEXECV7QEO","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"SLQEXECV7QEOY6KY","created_at":"2026-07-05T10:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"SLQEXECV","created_at":"2026-07-05T10:02:05Z"}],"graph_snapshots":[{"event_id":"sha256:b262e7f8698e34f42c0f91807362834c57c6e56a35fd60864bddb685e8516300","target":"graph","created_at":"2026-07-05T10:02:05Z","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/2408.09831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the output of generative large language models (LLMs) is challenging and difficult to scale. Many evaluations of LLMs focus on tasks such as single-choice question-answering or text classification. These tasks are not suitable for assessing open-ended question-answering capabilities, which are critical in domains where expertise is required. One such domain is health, where misleading or incorrect answers can have a negative impact on a user's well-being. Using human experts to evaluate the quality of LLM answers is generally considered the gold standard, but expert annotation is co","authors_text":"Daniel Steinbach, Harrisen Scells, Jonas Probst, Martin Potthast, Sebastian Heineking","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-19T09:27:45Z","title":"Ranking Generated Answers: On the Agreement of Retrieval Models with Humans on Consumer Health Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09831","kind":"arxiv","version":2},"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:dc700976aa0d20ae06d942ae294ae0344497bf190e28c602cd7dcbe821dc13cd","target":"record","created_at":"2026-07-05T10:02:05Z","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":"60cb27afe471af24207c1ae4eb4e67bd5726c0bc659eba0a2c95fd99942f7bac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-19T09:27:45Z","title_canon_sha256":"d6ceb39dedc63e390e18da7d2734a4eee56566fd933f20480fd4f70d7439d0dd"},"schema_version":"1.0","source":{"id":"2408.09831","kind":"arxiv","version":2}},"canonical_sha256":"92e04b9055fc08ec79589e9228abfd9da39f3a1c7d5e552c13fa2467da7438f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92e04b9055fc08ec79589e9228abfd9da39f3a1c7d5e552c13fa2467da7438f9","first_computed_at":"2026-07-05T10:02:05.671586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:05.671586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIAR2TujuPn06P+0JyVDbNqwx8y4kZ6uTShbV19rlOMWeXsKOAtAKJ/uoLgRtVrLjDk07U7Zl6FuqaxCR04sAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:05.672035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09831","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc700976aa0d20ae06d942ae294ae0344497bf190e28c602cd7dcbe821dc13cd","sha256:b262e7f8698e34f42c0f91807362834c57c6e56a35fd60864bddb685e8516300"],"state_sha256":"7585b401e1de3e73c1c457ab7a332529a20f10e44b332ed01c10c08f4aeeb862"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQ9Q8vE3Cc/m0tumwF/8p9NvzQf0BtC1Znxt+nKs1Wk4WPazTqaLP89W2tei3sgo1vpd9B9axVtmVgq/poGPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:13:13.061510Z","bundle_sha256":"aa8096d90d520731f9c087e0b3a69a405d329440648a67fe3a2a4b77574d5ae0"}}