{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X56ET22POUBSHRRTUT6TRTOGUI","short_pith_number":"pith:X56ET22P","schema_version":"1.0","canonical_sha256":"bf7c49eb4f750323c633a4fd38cdc6a2240cb34bdfd00bede50493e2dbc4aba7","source":{"kind":"arxiv","id":"2509.08596","version":1},"attestation_state":"computed","paper":{"title":"LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Molla-Aliod, Dima Galat","submitted_at":"2025-09-10T13:50:49Z","abstract_excerpt":"Biomedical question answering (QA) poses significant challenges due to the need for precise interpretation of specialized knowledge drawn from a vast, complex, and rapidly evolving corpus. In this work, we explore how large language models (LLMs) can be used for information retrieval (IR), and an ensemble of zero-shot models can accomplish state-of-the-art performance on a domain-specific Yes/No QA task. Evaluating our approach on the BioASQ challenge tasks, we show that ensembles can outperform individual LLMs and in some cases rival or surpass domain-tuned systems - all while preserving gene"},"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":"2509.08596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T13:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"7a077f548c1a0423dd8a98bc95fa67d211cea46e5ebbda69c0d54102d50bfbe2","abstract_canon_sha256":"63c2eb185745fa58a1b970f6519f36c04d03514610f60c248717301b8f9e8e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:32.781986Z","signature_b64":"e9QaTPxI5Q29ud5c26qZHyB6sRikjscDWfoWqOqPDdOd/F9bjlhNro098TB5zloR9IaRX1tT1eLE5PRzToI9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7c49eb4f750323c633a4fd38cdc6a2240cb34bdfd00bede50493e2dbc4aba7","last_reissued_at":"2026-07-05T12:08:32.781478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:32.781478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Molla-Aliod, Dima Galat","submitted_at":"2025-09-10T13:50:49Z","abstract_excerpt":"Biomedical question answering (QA) poses significant challenges due to the need for precise interpretation of specialized knowledge drawn from a vast, complex, and rapidly evolving corpus. In this work, we explore how large language models (LLMs) can be used for information retrieval (IR), and an ensemble of zero-shot models can accomplish state-of-the-art performance on a domain-specific Yes/No QA task. Evaluating our approach on the BioASQ challenge tasks, we show that ensembles can outperform individual LLMs and in some cases rival or surpass domain-tuned systems - all while preserving gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08596","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/2509.08596/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":"2509.08596","created_at":"2026-07-05T12:08:32.781539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08596v1","created_at":"2026-07-05T12:08:32.781539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08596","created_at":"2026-07-05T12:08:32.781539+00:00"},{"alias_kind":"pith_short_12","alias_value":"X56ET22POUBS","created_at":"2026-07-05T12:08:32.781539+00:00"},{"alias_kind":"pith_short_16","alias_value":"X56ET22POUBSHRRT","created_at":"2026-07-05T12:08:32.781539+00:00"},{"alias_kind":"pith_short_8","alias_value":"X56ET22P","created_at":"2026-07-05T12:08:32.781539+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/X56ET22POUBSHRRTUT6TRTOGUI","json":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI.json","graph_json":"https://pith.science/api/pith-number/X56ET22POUBSHRRTUT6TRTOGUI/graph.json","events_json":"https://pith.science/api/pith-number/X56ET22POUBSHRRTUT6TRTOGUI/events.json","paper":"https://pith.science/paper/X56ET22P"},"agent_actions":{"view_html":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI","download_json":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI.json","view_paper":"https://pith.science/paper/X56ET22P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08596&json=true","fetch_graph":"https://pith.science/api/pith-number/X56ET22POUBSHRRTUT6TRTOGUI/graph.json","fetch_events":"https://pith.science/api/pith-number/X56ET22POUBSHRRTUT6TRTOGUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI/action/storage_attestation","attest_author":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI/action/author_attestation","sign_citation":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI/action/citation_signature","submit_replication":"https://pith.science/pith/X56ET22POUBSHRRTUT6TRTOGUI/action/replication_record"}},"created_at":"2026-07-05T12:08:32.781539+00:00","updated_at":"2026-07-05T12:08:32.781539+00:00"}