{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BH3C2JPL7FWOKVXNVASWCD2O4L","short_pith_number":"pith:BH3C2JPL","schema_version":"1.0","canonical_sha256":"09f62d25ebf96ce556eda825610f4ee2da1d3e7c58bd2430dfee118f3c833d7b","source":{"kind":"arxiv","id":"2507.06715","version":1},"attestation_state":"computed","paper":{"title":"CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Garapati Keerthana, Manik Gupta","submitted_at":"2025-07-09T10:13:38Z","abstract_excerpt":"Large language models (LLMs), including zero-shot and few-shot paradigms, have shown promising capabilities in clinical text generation. However, real-world applications face two key challenges: (1) patient data is highly unstructured, heterogeneous, and scattered across multiple note types and (2) clinical notes are often long and semantically dense, making naive prompting infeasible due to context length constraints and the risk of omitting clinically relevant information.\n  We introduce CLI-RAG (Clinically Informed Retrieval-Augmented Generation), a domain-specific framework for structured "},"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":"2507.06715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T10:13:38Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"35325676fa404b7c50e42c4b9c02290fcf6d33b998d7b8134504084f11d274ef","abstract_canon_sha256":"3779dd6ff87b6aad452cf48b3f022d33d80cfabb1997eed5cc363d881ab43a67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:21.855054Z","signature_b64":"Q15maLUAmOQKnNlwzpXSSi4aPva86jrsWmk6j0SgSzBdvczUZCDjwKcJqPBbx4wOsRGIcEgfvvrSJXCEDcZKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f62d25ebf96ce556eda825610f4ee2da1d3e7c58bd2430dfee118f3c833d7b","last_reissued_at":"2026-07-05T11:34:21.854420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:21.854420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Garapati Keerthana, Manik Gupta","submitted_at":"2025-07-09T10:13:38Z","abstract_excerpt":"Large language models (LLMs), including zero-shot and few-shot paradigms, have shown promising capabilities in clinical text generation. However, real-world applications face two key challenges: (1) patient data is highly unstructured, heterogeneous, and scattered across multiple note types and (2) clinical notes are often long and semantically dense, making naive prompting infeasible due to context length constraints and the risk of omitting clinically relevant information.\n  We introduce CLI-RAG (Clinically Informed Retrieval-Augmented Generation), a domain-specific framework for structured "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06715","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/2507.06715/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":"2507.06715","created_at":"2026-07-05T11:34:21.854531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06715v1","created_at":"2026-07-05T11:34:21.854531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06715","created_at":"2026-07-05T11:34:21.854531+00:00"},{"alias_kind":"pith_short_12","alias_value":"BH3C2JPL7FWO","created_at":"2026-07-05T11:34:21.854531+00:00"},{"alias_kind":"pith_short_16","alias_value":"BH3C2JPL7FWOKVXN","created_at":"2026-07-05T11:34:21.854531+00:00"},{"alias_kind":"pith_short_8","alias_value":"BH3C2JPL","created_at":"2026-07-05T11:34:21.854531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24902","citing_title":"When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L","json":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L.json","graph_json":"https://pith.science/api/pith-number/BH3C2JPL7FWOKVXNVASWCD2O4L/graph.json","events_json":"https://pith.science/api/pith-number/BH3C2JPL7FWOKVXNVASWCD2O4L/events.json","paper":"https://pith.science/paper/BH3C2JPL"},"agent_actions":{"view_html":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L","download_json":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L.json","view_paper":"https://pith.science/paper/BH3C2JPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06715&json=true","fetch_graph":"https://pith.science/api/pith-number/BH3C2JPL7FWOKVXNVASWCD2O4L/graph.json","fetch_events":"https://pith.science/api/pith-number/BH3C2JPL7FWOKVXNVASWCD2O4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L/action/storage_attestation","attest_author":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L/action/author_attestation","sign_citation":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L/action/citation_signature","submit_replication":"https://pith.science/pith/BH3C2JPL7FWOKVXNVASWCD2O4L/action/replication_record"}},"created_at":"2026-07-05T11:34:21.854531+00:00","updated_at":"2026-07-05T11:34:21.854531+00:00"}