{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L44WVAOPAGGWSUH7JSVJN2D2WI","short_pith_number":"pith:L44WVAOP","schema_version":"1.0","canonical_sha256":"5f396a81cf018d6950ff4caa96e87ab2380d72f3c45ffd34c7dba655ffc521aa","source":{"kind":"arxiv","id":"2406.14981","version":1},"attestation_state":"computed","paper":{"title":"Human-AI collectives produce the most accurate differential diagnoses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"B. Harack, E. A. Chu, G. Barabucci, I. Lin, J. Berger, J. Komarneni, K. Laskowski, N. Fu, N. Z\\\"oller, R. H.J.M. Kurvers, S. M. Herzog, V. Shia, V. Trianni","submitted_at":"2024-06-21T08:46:30Z","abstract_excerpt":"Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate, lack common sense, and are biased - shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here we present a hybrid collective intelli"},"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":"2406.14981","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T08:46:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ab38fd8353ec7f47e64a5e48a25abb725ace8547c5f86f7e61655c1d6f7b5d0d","abstract_canon_sha256":"f284d01700df3dbb0f496edd3edbd79ea331bac1babb4aff151688c90c0beebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:11.571858Z","signature_b64":"ITwYvR9ds+P0w2ZMarAJWFQksem9WO6jR5HSH5htyl5Vt6/ulyo8r/96rv956QezeU2J0Pmi1fSsoh/4jCpmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f396a81cf018d6950ff4caa96e87ab2380d72f3c45ffd34c7dba655ffc521aa","last_reissued_at":"2026-07-05T08:35:11.571377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:11.571377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-AI collectives produce the most accurate differential diagnoses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"B. Harack, E. A. Chu, G. Barabucci, I. Lin, J. Berger, J. Komarneni, K. Laskowski, N. Fu, N. Z\\\"oller, R. H.J.M. Kurvers, S. M. Herzog, V. Shia, V. Trianni","submitted_at":"2024-06-21T08:46:30Z","abstract_excerpt":"Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate, lack common sense, and are biased - shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here we present a hybrid collective intelli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14981","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/2406.14981/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":"2406.14981","created_at":"2026-07-05T08:35:11.571436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14981v1","created_at":"2026-07-05T08:35:11.571436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14981","created_at":"2026-07-05T08:35:11.571436+00:00"},{"alias_kind":"pith_short_12","alias_value":"L44WVAOPAGGW","created_at":"2026-07-05T08:35:11.571436+00:00"},{"alias_kind":"pith_short_16","alias_value":"L44WVAOPAGGWSUH7","created_at":"2026-07-05T08:35:11.571436+00:00"},{"alias_kind":"pith_short_8","alias_value":"L44WVAOP","created_at":"2026-07-05T08:35:11.571436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09584","citing_title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI","json":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI.json","graph_json":"https://pith.science/api/pith-number/L44WVAOPAGGWSUH7JSVJN2D2WI/graph.json","events_json":"https://pith.science/api/pith-number/L44WVAOPAGGWSUH7JSVJN2D2WI/events.json","paper":"https://pith.science/paper/L44WVAOP"},"agent_actions":{"view_html":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI","download_json":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI.json","view_paper":"https://pith.science/paper/L44WVAOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14981&json=true","fetch_graph":"https://pith.science/api/pith-number/L44WVAOPAGGWSUH7JSVJN2D2WI/graph.json","fetch_events":"https://pith.science/api/pith-number/L44WVAOPAGGWSUH7JSVJN2D2WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI/action/storage_attestation","attest_author":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI/action/author_attestation","sign_citation":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI/action/citation_signature","submit_replication":"https://pith.science/pith/L44WVAOPAGGWSUH7JSVJN2D2WI/action/replication_record"}},"created_at":"2026-07-05T08:35:11.571436+00:00","updated_at":"2026-07-05T08:35:11.571436+00:00"}