{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J3QAKL4FYQEYDLBVHEQSMEDLZK","short_pith_number":"pith:J3QAKL4F","schema_version":"1.0","canonical_sha256":"4ee0052f85c40981ac35392126106bca92ee8ddecd613bc6848129cfbb0a7aa0","source":{"kind":"arxiv","id":"2608.12138","version":1},"attestation_state":"computed","paper":{"title":"A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Charuta Mandke, Praveen Reddy, Sarah Khan, Shitij Arora, Siddharth Reddy Anthireddy, Suvrankar Datta, Vishal Singh","submitted_at":"2026-08-12T14:55:46Z","abstract_excerpt":"General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but such comparisons draw on a narrow set of systems and on benchmarks developed largely in high-income settings. We evaluate VITA, a retrieval-augmented generation (RAG) system purpose-built for contextual knowledge retrieval in India and other low- and middle-income (LMIC) settings. VITA retrieves from a curated corpus of disease-specific guidelines, India-specific antimicrobial resistance data, national formulary constraints, and resource-limited c"},"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":"2608.12138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T14:55:46Z","cross_cats_sorted":["cs.AI","cs.HC","cs.IR","cs.LG"],"title_canon_sha256":"e8394293c9c0b77a8cd158bd982ee90d2a8e996ec197bd375c5417a3bdae0cca","abstract_canon_sha256":"ed1c0fdb8bc7bb6a34b43d2623212338fcc4937c917db4c1fee1889a3558c78d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:30:12.270669Z","signature_b64":"1wZDb5MTwGxxUdZlHpIC1JFHnmTWWQNTQwUtnqKW64Mu3dkxrbdaC6Lq0OlIWLX3OS/5cPdoIwo82+84L9DHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ee0052f85c40981ac35392126106bca92ee8ddecd613bc6848129cfbb0a7aa0","last_reissued_at":"2026-08-13T01:30:12.268314Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:30:12.268314Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Charuta Mandke, Praveen Reddy, Sarah Khan, Shitij Arora, Siddharth Reddy Anthireddy, Suvrankar Datta, Vishal Singh","submitted_at":"2026-08-12T14:55:46Z","abstract_excerpt":"General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but such comparisons draw on a narrow set of systems and on benchmarks developed largely in high-income settings. We evaluate VITA, a retrieval-augmented generation (RAG) system purpose-built for contextual knowledge retrieval in India and other low- and middle-income (LMIC) settings. VITA retrieves from a curated corpus of disease-specific guidelines, India-specific antimicrobial resistance data, national formulary constraints, and resource-limited c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12138","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/2608.12138/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":"2608.12138","created_at":"2026-08-13T01:30:12.269552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12138v1","created_at":"2026-08-13T01:30:12.269552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12138","created_at":"2026-08-13T01:30:12.269552+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3QAKL4FYQEY","created_at":"2026-08-13T01:30:12.269552+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3QAKL4FYQEYDLBV","created_at":"2026-08-13T01:30:12.269552+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3QAKL4F","created_at":"2026-08-13T01:30:12.269552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK","json":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK.json","graph_json":"https://pith.science/api/pith-number/J3QAKL4FYQEYDLBVHEQSMEDLZK/graph.json","events_json":"https://pith.science/api/pith-number/J3QAKL4FYQEYDLBVHEQSMEDLZK/events.json","paper":"https://pith.science/paper/J3QAKL4F"},"agent_actions":{"view_html":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK","download_json":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK.json","view_paper":"https://pith.science/paper/J3QAKL4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12138&json=true","fetch_graph":"https://pith.science/api/pith-number/J3QAKL4FYQEYDLBVHEQSMEDLZK/graph.json","fetch_events":"https://pith.science/api/pith-number/J3QAKL4FYQEYDLBVHEQSMEDLZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK/action/storage_attestation","attest_author":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK/action/author_attestation","sign_citation":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK/action/citation_signature","submit_replication":"https://pith.science/pith/J3QAKL4FYQEYDLBVHEQSMEDLZK/action/replication_record"}},"created_at":"2026-08-13T01:30:12.269552+00:00","updated_at":"2026-08-13T01:30:12.269552+00:00"}