{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E7ENM3SXJAOU4CZJ7L2FC52IBE","short_pith_number":"pith:E7ENM3SX","canonical_record":{"source":{"id":"2401.01943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T19:03:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b6071ed2f8041dc3311c748a599fe09092e8116d0594ceab7423aca2573bd46","abstract_canon_sha256":"ffbb14cdc80913aca7a23e21efc39d60f5c7be26cc4c6d99f48fd8c8a32674df"},"schema_version":"1.0"},"canonical_sha256":"27c8d66e57481d4e0b29faf4517748091229eb9fab56fccee838fac2ec78884a","source":{"kind":"arxiv","id":"2401.01943","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01943","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01943v2","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01943","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"E7ENM3SXJAOU","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"E7ENM3SXJAOU4CZJ","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"E7ENM3SX","created_at":"2026-07-05T07:30:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E7ENM3SXJAOU4CZJ7L2FC52IBE","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T19:03:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b6071ed2f8041dc3311c748a599fe09092e8116d0594ceab7423aca2573bd46","abstract_canon_sha256":"ffbb14cdc80913aca7a23e21efc39d60f5c7be26cc4c6d99f48fd8c8a32674df"},"schema_version":"1.0"},"canonical_sha256":"27c8d66e57481d4e0b29faf4517748091229eb9fab56fccee838fac2ec78884a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:59.519088Z","signature_b64":"ww1p0v9tTYoL52/bIR5acQpz6Qht81yF0dLOSCE0YKxCdUjrm0rwFRoe6LcVgd1HupxMY3CRnyv1owzW2aiNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27c8d66e57481d4e0b29faf4517748091229eb9fab56fccee838fac2ec78884a","last_reissued_at":"2026-07-05T07:30:59.518638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:59.518638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01943","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":"2026-07-05T07:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khha1kNFKjFitpgu27RXSSR3ZW7BPnZV2jBQUKod5VHjiz135t2mXrIK0xIPY/R6SKpZEoRwkTvJ6l7W8ZwlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:39.905193Z"},"content_sha256":"965d18e8e32ac11a200f559d38ef306d141a085801ad431cfbaa1a3e71ddfd64","schema_version":"1.0","event_id":"sha256:965d18e8e32ac11a200f559d38ef306d141a085801ad431cfbaa1a3e71ddfd64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E7ENM3SXJAOU4CZJ7L2FC52IBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalist embedding models are better at short-context clinical semantic search than specialized embedding models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexei Figueroa, Jean-Baptiste Excoffier, Jens-Michalis Papaioannou, Keno Bressem, Matthieu Ortala, Tom Roehr","submitted_at":"2024-01-03T19:03:32Z","abstract_excerpt":"The increasing use of tools and solutions based on Large Language Models (LLMs) for various tasks in the medical domain has become a prominent trend. Their use in this highly critical and sensitive domain has thus raised important questions about their robustness, especially in response to variations in input, and the reliability of the generated outputs. This study addresses these questions by constructing a textual dataset based on the ICD-10-CM code descriptions, widely used in US hospitals and containing many clinical terms, and their easily reproducible rephrasing. We then benchmarked exi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01943","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/2401.01943/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":"2026-07-05T07:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7VkUVvy0TMdBzGMXrExJauFGeoqCyqpj0A52SAlze/Xy3wPn4HjMtvfFYwqczHe1408pQis+1ztffWgmUy2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:39.905611Z"},"content_sha256":"7cd672915a35618e17742b7e0c6f184bfb1fdfd063f89b039f587df16f4713a9","schema_version":"1.0","event_id":"sha256:7cd672915a35618e17742b7e0c6f184bfb1fdfd063f89b039f587df16f4713a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/bundle.json","state_url":"https://pith.science/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/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":"2026-08-07T22:41:39Z","links":{"resolver":"https://pith.science/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE","bundle":"https://pith.science/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/bundle.json","state":"https://pith.science/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7ENM3SXJAOU4CZJ7L2FC52IBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E7ENM3SXJAOU4CZJ7L2FC52IBE","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":"ffbb14cdc80913aca7a23e21efc39d60f5c7be26cc4c6d99f48fd8c8a32674df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T19:03:32Z","title_canon_sha256":"3b6071ed2f8041dc3311c748a599fe09092e8116d0594ceab7423aca2573bd46"},"schema_version":"1.0","source":{"id":"2401.01943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01943","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01943v2","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01943","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"E7ENM3SXJAOU","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"E7ENM3SXJAOU4CZJ","created_at":"2026-07-05T07:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"E7ENM3SX","created_at":"2026-07-05T07:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:7cd672915a35618e17742b7e0c6f184bfb1fdfd063f89b039f587df16f4713a9","target":"graph","created_at":"2026-07-05T07:30:59Z","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/2401.01943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing use of tools and solutions based on Large Language Models (LLMs) for various tasks in the medical domain has become a prominent trend. Their use in this highly critical and sensitive domain has thus raised important questions about their robustness, especially in response to variations in input, and the reliability of the generated outputs. This study addresses these questions by constructing a textual dataset based on the ICD-10-CM code descriptions, widely used in US hospitals and containing many clinical terms, and their easily reproducible rephrasing. We then benchmarked exi","authors_text":"Alexei Figueroa, Jean-Baptiste Excoffier, Jens-Michalis Papaioannou, Keno Bressem, Matthieu Ortala, Tom Roehr","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T19:03:32Z","title":"Generalist embedding models are better at short-context clinical semantic search than specialized embedding models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01943","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":"sha256:965d18e8e32ac11a200f559d38ef306d141a085801ad431cfbaa1a3e71ddfd64","target":"record","created_at":"2026-07-05T07:30:59Z","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":"ffbb14cdc80913aca7a23e21efc39d60f5c7be26cc4c6d99f48fd8c8a32674df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-03T19:03:32Z","title_canon_sha256":"3b6071ed2f8041dc3311c748a599fe09092e8116d0594ceab7423aca2573bd46"},"schema_version":"1.0","source":{"id":"2401.01943","kind":"arxiv","version":2}},"canonical_sha256":"27c8d66e57481d4e0b29faf4517748091229eb9fab56fccee838fac2ec78884a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27c8d66e57481d4e0b29faf4517748091229eb9fab56fccee838fac2ec78884a","first_computed_at":"2026-07-05T07:30:59.518638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:59.518638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ww1p0v9tTYoL52/bIR5acQpz6Qht81yF0dLOSCE0YKxCdUjrm0rwFRoe6LcVgd1HupxMY3CRnyv1owzW2aiNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:59.519088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:965d18e8e32ac11a200f559d38ef306d141a085801ad431cfbaa1a3e71ddfd64","sha256:7cd672915a35618e17742b7e0c6f184bfb1fdfd063f89b039f587df16f4713a9"],"state_sha256":"07a952f48bc8f21f92c67a33e41b0f1d3e428e7cde11ae47a655897b9b5378c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Llw88n2YbRH8ACuCvnTkRsQGgcXRR1uVcQWLZb1tByUH8r2ScA1mb7gHwtBQ+BhRamIqHPdl0g7Xq0ntsW4LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:41:39.908365Z","bundle_sha256":"4b5c6dab2d9f6357aead68c516677ecccf82c98bacf058861ee176987bd09071"}}