{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JCKB33MEAIUKPUKKFBCEMGAXOO","short_pith_number":"pith:JCKB33ME","schema_version":"1.0","canonical_sha256":"48941ded840228a7d14a2844461817739461f923713c317433c0ac7c4de75591","source":{"kind":"arxiv","id":"2608.03860","version":1},"attestation_state":"computed","paper":{"title":"SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.PF"],"primary_cat":"cs.CL","authors_text":"Asab Azad, Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab","submitted_at":"2026-08-04T16:04:07Z","abstract_excerpt":"We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in "},"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":"2608.03860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T16:04:07Z","cross_cats_sorted":["cs.AI","cs.IR","cs.PF"],"title_canon_sha256":"db08cf27bcdfbec8f0309eeeae403f776f9745fd01332b8b5d632e76defe3538","abstract_canon_sha256":"dc082ce351577052351b5d95adbafeaba5f11d240c20573c59ee167a580fb42b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:16.221326Z","signature_b64":"PbVst34ZqR2oPT5D34awZvCGo5BSCdftlStO+8xCHRK9t0+0yTvzW511XniFohdG+DETCenF8E1HeEGIImrQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48941ded840228a7d14a2844461817739461f923713c317433c0ac7c4de75591","last_reissued_at":"2026-08-05T01:37:16.219841Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:16.219841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.PF"],"primary_cat":"cs.CL","authors_text":"Asab Azad, Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab","submitted_at":"2026-08-04T16:04:07Z","abstract_excerpt":"We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03860","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/2608.03860/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":"2608.03860","created_at":"2026-08-05T01:37:16.220285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03860v1","created_at":"2026-08-05T01:37:16.220285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03860","created_at":"2026-08-05T01:37:16.220285+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCKB33MEAIUK","created_at":"2026-08-05T01:37:16.220285+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCKB33MEAIUKPUKK","created_at":"2026-08-05T01:37:16.220285+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCKB33ME","created_at":"2026-08-05T01:37:16.220285+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/JCKB33MEAIUKPUKKFBCEMGAXOO","json":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO.json","graph_json":"https://pith.science/api/pith-number/JCKB33MEAIUKPUKKFBCEMGAXOO/graph.json","events_json":"https://pith.science/api/pith-number/JCKB33MEAIUKPUKKFBCEMGAXOO/events.json","paper":"https://pith.science/paper/JCKB33ME"},"agent_actions":{"view_html":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO","download_json":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO.json","view_paper":"https://pith.science/paper/JCKB33ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03860&json=true","fetch_graph":"https://pith.science/api/pith-number/JCKB33MEAIUKPUKKFBCEMGAXOO/graph.json","fetch_events":"https://pith.science/api/pith-number/JCKB33MEAIUKPUKKFBCEMGAXOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO/action/storage_attestation","attest_author":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO/action/author_attestation","sign_citation":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO/action/citation_signature","submit_replication":"https://pith.science/pith/JCKB33MEAIUKPUKKFBCEMGAXOO/action/replication_record"}},"created_at":"2026-08-05T01:37:16.220285+00:00","updated_at":"2026-08-05T01:37:16.220285+00:00"}