{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QA6SGMFKWJJA3PNHAPPAMYX3GD","short_pith_number":"pith:QA6SGMFK","canonical_record":{"source":{"id":"2505.20320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T16:13:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"676e86234a225feacfd0e9327f96d52b7036c9c1a1ea0fdaf5b2d5dd4f177bb2","abstract_canon_sha256":"6f110cbed08cade14f3d6c693ef70e66184e2371a3e38cc4aea61aa416696ec7"},"schema_version":"1.0"},"canonical_sha256":"803d2330aab2520dbda703de0662fb30f85178e4681daff8fc0c7e816e5c89a7","source":{"kind":"arxiv","id":"2505.20320","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20320","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20320v1","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20320","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"QA6SGMFKWJJA","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"QA6SGMFKWJJA3PNH","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"QA6SGMFK","created_at":"2026-07-05T11:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QA6SGMFKWJJA3PNHAPPAMYX3GD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T16:13:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"676e86234a225feacfd0e9327f96d52b7036c9c1a1ea0fdaf5b2d5dd4f177bb2","abstract_canon_sha256":"6f110cbed08cade14f3d6c693ef70e66184e2371a3e38cc4aea61aa416696ec7"},"schema_version":"1.0"},"canonical_sha256":"803d2330aab2520dbda703de0662fb30f85178e4681daff8fc0c7e816e5c89a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:11.257761Z","signature_b64":"5YjOMMXaDVYW9pS51afNuRopkQn6+K5EniVOumtp/eGoJIYvlvNZexACQ7f2HWY6y9FepTMGKxAu49+e1p8oCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"803d2330aab2520dbda703de0662fb30f85178e4681daff8fc0c7e816e5c89a7","last_reissued_at":"2026-07-05T11:10:11.257266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:11.257266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20320","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3reGL6zeYGjUmZioTjafeV82DDUqRlB5M+Q8WyLlw+eDCvUqEIgibT9YYrKGjKZHPrTL4SjNqO+jF0eGC2rNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:56.827168Z"},"content_sha256":"319c2f54678127c38e87b7c8410e2003b3ea84a8b1bdc9640365b959128ecd91","schema_version":"1.0","event_id":"sha256:319c2f54678127c38e87b7c8410e2003b3ea84a8b1bdc9640365b959128ecd91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QA6SGMFKWJJA3PNHAPPAMYX3GD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhavalkumar Patel, Eyal Klang, Fabio Sanatana, Ganesh Raut, Girish N. Nadkarni, Matthew A Levin, Omar Dawkins, Prem Timsina, Randolph M. Steinhagen, Reba Miller, Robert Freeman, Satya Narayana Cheetirala","submitted_at":"2025-05-23T16:13:08Z","abstract_excerpt":"Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text segments can match the performance of processing entire clinical notes with large context LLMs. We begin by splitting clinical documents into smaller chunks, converting them into vector embeddings, and storing these in a FAISS index. We then retrieve the top 4,000 words most pertinent to the classification query and feed these consolidated segments into an LLM. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20320","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/2505.20320/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3O9tXOPWalr+ZFJZ/He0jKoY82Ejpq+57OFe/Rr19ZI2YEbN1wiMqIhpVN4duo22yLK4KrStU/P4COEhDRuuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:56.827707Z"},"content_sha256":"ca8280a346e879f8970af27f801735e9dc8940d01c975de39d9f32f40c471851","schema_version":"1.0","event_id":"sha256:ca8280a346e879f8970af27f801735e9dc8940d01c975de39d9f32f40c471851"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/bundle.json","state_url":"https://pith.science/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T07:50:56Z","links":{"resolver":"https://pith.science/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD","bundle":"https://pith.science/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/bundle.json","state":"https://pith.science/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QA6SGMFKWJJA3PNHAPPAMYX3GD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QA6SGMFKWJJA3PNHAPPAMYX3GD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6f110cbed08cade14f3d6c693ef70e66184e2371a3e38cc4aea61aa416696ec7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T16:13:08Z","title_canon_sha256":"676e86234a225feacfd0e9327f96d52b7036c9c1a1ea0fdaf5b2d5dd4f177bb2"},"schema_version":"1.0","source":{"id":"2505.20320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20320","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20320v1","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20320","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"QA6SGMFKWJJA","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"QA6SGMFKWJJA3PNH","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"QA6SGMFK","created_at":"2026-07-05T11:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:ca8280a346e879f8970af27f801735e9dc8940d01c975de39d9f32f40c471851","target":"graph","created_at":"2026-07-05T11:10:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.20320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text segments can match the performance of processing entire clinical notes with large context LLMs. We begin by splitting clinical documents into smaller chunks, converting them into vector embeddings, and storing these in a FAISS index. We then retrieve the top 4,000 words most pertinent to the classification query and feed these consolidated segments into an LLM. We ","authors_text":"Dhavalkumar Patel, Eyal Klang, Fabio Sanatana, Ganesh Raut, Girish N. Nadkarni, Matthew A Levin, Omar Dawkins, Prem Timsina, Randolph M. Steinhagen, Reba Miller, Robert Freeman, Satya Narayana Cheetirala","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T16:13:08Z","title":"Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20320","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:319c2f54678127c38e87b7c8410e2003b3ea84a8b1bdc9640365b959128ecd91","target":"record","created_at":"2026-07-05T11:10:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6f110cbed08cade14f3d6c693ef70e66184e2371a3e38cc4aea61aa416696ec7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T16:13:08Z","title_canon_sha256":"676e86234a225feacfd0e9327f96d52b7036c9c1a1ea0fdaf5b2d5dd4f177bb2"},"schema_version":"1.0","source":{"id":"2505.20320","kind":"arxiv","version":1}},"canonical_sha256":"803d2330aab2520dbda703de0662fb30f85178e4681daff8fc0c7e816e5c89a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"803d2330aab2520dbda703de0662fb30f85178e4681daff8fc0c7e816e5c89a7","first_computed_at":"2026-07-05T11:10:11.257266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:11.257266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5YjOMMXaDVYW9pS51afNuRopkQn6+K5EniVOumtp/eGoJIYvlvNZexACQ7f2HWY6y9FepTMGKxAu49+e1p8oCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:11.257761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:319c2f54678127c38e87b7c8410e2003b3ea84a8b1bdc9640365b959128ecd91","sha256:ca8280a346e879f8970af27f801735e9dc8940d01c975de39d9f32f40c471851"],"state_sha256":"3ce8c4c611d757951c51defd1a6a77bd3497894e50bb1145b1e8049b1bbfbc9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9IpMYOwAtmyW4f2ZYdFzYs5huq4h8Aq4N/Lx8o9bsVn4SNgsCuyR4gcJPwKsGFVaagun/vLg4YGNKgixnquDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:50:56.831956Z","bundle_sha256":"88d805b564cc7fb87abf18b96ac8659808126e66c857bbb5c61c4b98838ac0f1"}}