{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BITMLY2UYOWEWBLXAK3WZAVE2S","short_pith_number":"pith:BITMLY2U","schema_version":"1.0","canonical_sha256":"0a26c5e354c3ac4b057702b76c82a4d4b3e5f503f313fd1faccda8291a4169a9","source":{"kind":"arxiv","id":"2405.10893","version":1},"attestation_state":"computed","paper":{"title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anastasios P. Palamidas, Dimitrios P. Panagoulias, Evridiki Tsoureli-Nikita, George A. Tsihrintzis, Maria Virvou, Mattheos Sanoudos, Persephone Papatheodosiou","submitted_at":"2024-05-17T16:31:56Z","abstract_excerpt":"Large Language Models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence (AI) technology which is rapidly evolving and promises to aid in medical diagnosis either by assisting doctors or by simulating a doctor's workflow in more advanced and complex implementations. In this technical paper, we outline Cognitive Network Evaluation Toolkit for Medical Domains (COGNET-MD), which constitutes a novel benchmark for LLM evaluation in the medical domain. Specifically, we propose a scoring-framework with increased difficulty to assess the ability of LLMs in interpreting medical t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.10893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T16:31:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54468910254a3434e81dfa29447e9a9e25f4961efe7816a6377ed1ee4c3da81b","abstract_canon_sha256":"7c00f3099ea461a1edeeb932530875659b34b1a56529814e77dec9ab29ce63cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:19.063887Z","signature_b64":"xXl/2HmTNy+sdAh4DgcaQxPHmdTRE5L1f5QRyp/LKv4/4qcjIeMupdeRgip9RNYKkOxXWIT88Dn+7CfR9EHbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a26c5e354c3ac4b057702b76c82a4d4b3e5f503f313fd1faccda8291a4169a9","last_reissued_at":"2026-07-05T08:20:19.063419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:19.063419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anastasios P. Palamidas, Dimitrios P. Panagoulias, Evridiki Tsoureli-Nikita, George A. Tsihrintzis, Maria Virvou, Mattheos Sanoudos, Persephone Papatheodosiou","submitted_at":"2024-05-17T16:31:56Z","abstract_excerpt":"Large Language Models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence (AI) technology which is rapidly evolving and promises to aid in medical diagnosis either by assisting doctors or by simulating a doctor's workflow in more advanced and complex implementations. In this technical paper, we outline Cognitive Network Evaluation Toolkit for Medical Domains (COGNET-MD), which constitutes a novel benchmark for LLM evaluation in the medical domain. Specifically, we propose a scoring-framework with increased difficulty to assess the ability of LLMs in interpreting medical t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10893","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/2405.10893/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.10893","created_at":"2026-07-05T08:20:19.063479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10893v1","created_at":"2026-07-05T08:20:19.063479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10893","created_at":"2026-07-05T08:20:19.063479+00:00"},{"alias_kind":"pith_short_12","alias_value":"BITMLY2UYOWE","created_at":"2026-07-05T08:20:19.063479+00:00"},{"alias_kind":"pith_short_16","alias_value":"BITMLY2UYOWEWBLX","created_at":"2026-07-05T08:20:19.063479+00:00"},{"alias_kind":"pith_short_8","alias_value":"BITMLY2U","created_at":"2026-07-05T08:20:19.063479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04325","citing_title":"Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S","json":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S.json","graph_json":"https://pith.science/api/pith-number/BITMLY2UYOWEWBLXAK3WZAVE2S/graph.json","events_json":"https://pith.science/api/pith-number/BITMLY2UYOWEWBLXAK3WZAVE2S/events.json","paper":"https://pith.science/paper/BITMLY2U"},"agent_actions":{"view_html":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S","download_json":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S.json","view_paper":"https://pith.science/paper/BITMLY2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10893&json=true","fetch_graph":"https://pith.science/api/pith-number/BITMLY2UYOWEWBLXAK3WZAVE2S/graph.json","fetch_events":"https://pith.science/api/pith-number/BITMLY2UYOWEWBLXAK3WZAVE2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S/action/storage_attestation","attest_author":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S/action/author_attestation","sign_citation":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S/action/citation_signature","submit_replication":"https://pith.science/pith/BITMLY2UYOWEWBLXAK3WZAVE2S/action/replication_record"}},"created_at":"2026-07-05T08:20:19.063479+00:00","updated_at":"2026-07-05T08:20:19.063479+00:00"}