{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:54UC34BRUXTXE3XDRHA2DZUWSG","short_pith_number":"pith:54UC34BR","schema_version":"1.0","canonical_sha256":"ef282df031a5e7726ee389c1a1e69691aea3fbd4d107798fb58a0c7dab580636","source":{"kind":"arxiv","id":"2505.19288","version":2},"attestation_state":"computed","paper":{"title":"Hypercube-Based Retrieval-Augmented Generation for Scientific Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Jin, Giri Narasimhan, Jiawei Han, Jimeng Shi, Runchu Tian, Shaowen Wang, Sizhe Zhou, Wei Hu","submitted_at":"2025-05-25T19:42:06Z","abstract_excerpt":"Large language models (LLMs) often need to incorporate external knowledge to solve theme-specific problems. Retrieval-augmented generation (RAG) has shown its high promise, empowering LLMs to generate more qualified responses with retrieved external data and knowledge. However, most RAG methods retrieve relevant documents based on either sparse or dense retrieval methods or their combinations, which overlooks the essential, multi-dimensional, and structured semantic information present in documents. This structured information plays a critical role in finding concise yet highly relevant inform"},"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":"2505.19288","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T19:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"ba10422a1af81f4782373ada70ea0eb4587ac0edb2c0b144f0cebb7777e583d0","abstract_canon_sha256":"f4405b5fbe083b42914b6d8aeca27b1afaa39a4d3aef38de92ebca2ee9751826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:23.455651Z","signature_b64":"Se5Y5KkartgAtFbXoZMnzPET90T8uiJwc9tGdKDN6GTH46V7YKRtXUqGkOaN6su5t5VN9QSrl8Oq7qdQrtByAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef282df031a5e7726ee389c1a1e69691aea3fbd4d107798fb58a0c7dab580636","last_reissued_at":"2026-07-05T11:47:23.455013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:23.455013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypercube-Based Retrieval-Augmented Generation for Scientific Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Jin, Giri Narasimhan, Jiawei Han, Jimeng Shi, Runchu Tian, Shaowen Wang, Sizhe Zhou, Wei Hu","submitted_at":"2025-05-25T19:42:06Z","abstract_excerpt":"Large language models (LLMs) often need to incorporate external knowledge to solve theme-specific problems. Retrieval-augmented generation (RAG) has shown its high promise, empowering LLMs to generate more qualified responses with retrieved external data and knowledge. However, most RAG methods retrieve relevant documents based on either sparse or dense retrieval methods or their combinations, which overlooks the essential, multi-dimensional, and structured semantic information present in documents. This structured information plays a critical role in finding concise yet highly relevant inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19288","kind":"arxiv","version":2},"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/2505.19288/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":"2505.19288","created_at":"2026-07-05T11:47:23.455086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19288v2","created_at":"2026-07-05T11:47:23.455086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19288","created_at":"2026-07-05T11:47:23.455086+00:00"},{"alias_kind":"pith_short_12","alias_value":"54UC34BRUXTX","created_at":"2026-07-05T11:47:23.455086+00:00"},{"alias_kind":"pith_short_16","alias_value":"54UC34BRUXTXE3XD","created_at":"2026-07-05T11:47:23.455086+00:00"},{"alias_kind":"pith_short_8","alias_value":"54UC34BR","created_at":"2026-07-05T11:47:23.455086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12975","citing_title":"Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG","json":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG.json","graph_json":"https://pith.science/api/pith-number/54UC34BRUXTXE3XDRHA2DZUWSG/graph.json","events_json":"https://pith.science/api/pith-number/54UC34BRUXTXE3XDRHA2DZUWSG/events.json","paper":"https://pith.science/paper/54UC34BR"},"agent_actions":{"view_html":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG","download_json":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG.json","view_paper":"https://pith.science/paper/54UC34BR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19288&json=true","fetch_graph":"https://pith.science/api/pith-number/54UC34BRUXTXE3XDRHA2DZUWSG/graph.json","fetch_events":"https://pith.science/api/pith-number/54UC34BRUXTXE3XDRHA2DZUWSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG/action/storage_attestation","attest_author":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG/action/author_attestation","sign_citation":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG/action/citation_signature","submit_replication":"https://pith.science/pith/54UC34BRUXTXE3XDRHA2DZUWSG/action/replication_record"}},"created_at":"2026-07-05T11:47:23.455086+00:00","updated_at":"2026-07-05T11:47:23.455086+00:00"}