{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5IJMCA4X2JT2ZECEA44Y2RG2F","short_pith_number":"pith:Y5IJMCA4","schema_version":"1.0","canonical_sha256":"c75096081cbe933d64822039cc6a26d15dfcf4a959b2d828617451c15f2c6b93","source":{"kind":"arxiv","id":"2608.01468","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Balaji Anandganesh, Lee Mai, Xueying Zhao","submitted_at":"2026-08-02T20:02:44Z","abstract_excerpt":"This work presents DS@GT ARC BioASQ team's work for a biomedical question answering pipeline, integrating multi-source query expansion, neural reranking, retrieval refinement, and OpenBioLLM-assisted answer generation. The system combines PubMed retrieval with fine-tuned MiniLM-based semantic reranking, Reciprocal Rank Fusion (RRF), and feature-based relevance scoring to improve document ranking quality. To address challenging queries with weak retrieval performance, we introduce a conditional weak-question recovery strategy that applies semantic expansion, relationship-aware augmentation, and"},"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":"2608.01468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T20:02:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21ee28941e8b93a4596953d607bdd172fae977e0ccff922e0700b22b9545f70a","abstract_canon_sha256":"e4bc7d4b26d99eecc11d6b67f08cb99f1a983b81a07bdaa3166c7c3b38cf0f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:21.648342Z","signature_b64":"0kjyvLsBuPPhbv1SdIsNhZjcOPQfAsRgSP6ne0XIwHT78VJpMoESQAzYn+Acp3QNKuBg6WwvmLVL0u7cQNPOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c75096081cbe933d64822039cc6a26d15dfcf4a959b2d828617451c15f2c6b93","last_reissued_at":"2026-08-04T02:05:21.646806Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:21.646806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Balaji Anandganesh, Lee Mai, Xueying Zhao","submitted_at":"2026-08-02T20:02:44Z","abstract_excerpt":"This work presents DS@GT ARC BioASQ team's work for a biomedical question answering pipeline, integrating multi-source query expansion, neural reranking, retrieval refinement, and OpenBioLLM-assisted answer generation. The system combines PubMed retrieval with fine-tuned MiniLM-based semantic reranking, Reciprocal Rank Fusion (RRF), and feature-based relevance scoring to improve document ranking quality. To address challenging queries with weak retrieval performance, we introduce a conditional weak-question recovery strategy that applies semantic expansion, relationship-aware augmentation, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01468","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/2608.01468/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":"2608.01468","created_at":"2026-08-04T02:05:21.648315+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01468v1","created_at":"2026-08-04T02:05:21.648315+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01468","created_at":"2026-08-04T02:05:21.648315+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5IJMCA4X2JT","created_at":"2026-08-04T02:05:21.648315+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5IJMCA4X2JT2ZEC","created_at":"2026-08-04T02:05:21.648315+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5IJMCA4","created_at":"2026-08-04T02:05:21.648315+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/Y5IJMCA4X2JT2ZECEA44Y2RG2F","json":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F.json","graph_json":"https://pith.science/api/pith-number/Y5IJMCA4X2JT2ZECEA44Y2RG2F/graph.json","events_json":"https://pith.science/api/pith-number/Y5IJMCA4X2JT2ZECEA44Y2RG2F/events.json","paper":"https://pith.science/paper/Y5IJMCA4"},"agent_actions":{"view_html":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F","download_json":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F.json","view_paper":"https://pith.science/paper/Y5IJMCA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01468&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5IJMCA4X2JT2ZECEA44Y2RG2F/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5IJMCA4X2JT2ZECEA44Y2RG2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F/action/storage_attestation","attest_author":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F/action/author_attestation","sign_citation":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F/action/citation_signature","submit_replication":"https://pith.science/pith/Y5IJMCA4X2JT2ZECEA44Y2RG2F/action/replication_record"}},"created_at":"2026-08-04T02:05:21.648315+00:00","updated_at":"2026-08-04T02:05:21.648315+00:00"}