{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXLQHCW36EXKELZDNAA6PMXET2","short_pith_number":"pith:GXLQHCW3","schema_version":"1.0","canonical_sha256":"35d7038adbf12ea22f236801e7b2e49ea6b23ae08f5ee7758aea0c65fc856947","source":{"kind":"arxiv","id":"2404.06680","version":1},"attestation_state":"computed","paper":{"title":"Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Basu, Anai Kothari, Bradley Taylor, Hrituraj Singh, Shashi Kant Gupta","submitted_at":"2024-04-10T02:02:34Z","abstract_excerpt":"Retrieving information from EHR systems is essential for answering specific questions about patient journeys and improving the delivery of clinical care. Despite this fact, most EHR systems still rely on keyword-based searches. With the advent of generative large language models (LLMs), retrieving information can lead to better search and summarization capabilities. Such retrievers can also feed Retrieval-augmented generation (RAG) pipelines to answer any query. However, the task of retrieving information from EHR real-world clinical data contained within EHR systems in order to solve several "},"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":"2404.06680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T02:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"d5a115de8ae190cbaaa53b958c3909cf7c1906fa08cd2f3d6deb79c24bf27ffc","abstract_canon_sha256":"57dd0b60632ca9becba1347f896203f28618395cfa7b106e3b83676963212c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:15.696253Z","signature_b64":"AJ67zMa+hP5uoLJgszPtR4QJDS5ag+JJJMokKTsbAJGeE0zttfPQNbuskI7SbSjgHmIYImQyjK74nSdU/mdKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d7038adbf12ea22f236801e7b2e49ea6b23ae08f5ee7758aea0c65fc856947","last_reissued_at":"2026-07-05T08:06:15.695812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:15.695812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Basu, Anai Kothari, Bradley Taylor, Hrituraj Singh, Shashi Kant Gupta","submitted_at":"2024-04-10T02:02:34Z","abstract_excerpt":"Retrieving information from EHR systems is essential for answering specific questions about patient journeys and improving the delivery of clinical care. Despite this fact, most EHR systems still rely on keyword-based searches. With the advent of generative large language models (LLMs), retrieving information can lead to better search and summarization capabilities. Such retrievers can also feed Retrieval-augmented generation (RAG) pipelines to answer any query. However, the task of retrieving information from EHR real-world clinical data contained within EHR systems in order to solve several "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06680","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/2404.06680/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":"2404.06680","created_at":"2026-07-05T08:06:15.695888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06680v1","created_at":"2026-07-05T08:06:15.695888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06680","created_at":"2026-07-05T08:06:15.695888+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXLQHCW36EXK","created_at":"2026-07-05T08:06:15.695888+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXLQHCW36EXKELZD","created_at":"2026-07-05T08:06:15.695888+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXLQHCW3","created_at":"2026-07-05T08:06:15.695888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06252","citing_title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2","json":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2.json","graph_json":"https://pith.science/api/pith-number/GXLQHCW36EXKELZDNAA6PMXET2/graph.json","events_json":"https://pith.science/api/pith-number/GXLQHCW36EXKELZDNAA6PMXET2/events.json","paper":"https://pith.science/paper/GXLQHCW3"},"agent_actions":{"view_html":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2","download_json":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2.json","view_paper":"https://pith.science/paper/GXLQHCW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06680&json=true","fetch_graph":"https://pith.science/api/pith-number/GXLQHCW36EXKELZDNAA6PMXET2/graph.json","fetch_events":"https://pith.science/api/pith-number/GXLQHCW36EXKELZDNAA6PMXET2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2/action/storage_attestation","attest_author":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2/action/author_attestation","sign_citation":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2/action/citation_signature","submit_replication":"https://pith.science/pith/GXLQHCW36EXKELZDNAA6PMXET2/action/replication_record"}},"created_at":"2026-07-05T08:06:15.695888+00:00","updated_at":"2026-07-05T08:06:15.695888+00:00"}