{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SUQDVCFMA5CGIBORXDVFZ6B2EV","short_pith_number":"pith:SUQDVCFM","schema_version":"1.0","canonical_sha256":"95203a88ac07446405d1b8ea5cf83a2544aac202c4296505705066d6b4f7e646","source":{"kind":"arxiv","id":"2506.13778","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Alexander Gelbukh, Anvi Alex Eponon, Christian E. Maldonado-Sifuentes, Grigori Sidorov, Ildar Batyrshin, Moein Shahiki-Tash","submitted_at":"2025-06-09T16:15:11Z","abstract_excerpt":"This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method.\n  In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent. We also introduce \"paper-cards\", concise paper summaries under 300 characters, which enha"},"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":"2506.13778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-09T16:15:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a5ff4c9c6fa54915de71ed53b4925ea8a56a934e9c9a011e6bcd2a380ebc687e","abstract_canon_sha256":"ca07a01a93fc636bedae927c4749fb996e041672612a8ef9718a289176fb0b19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:43.205754Z","signature_b64":"R/LohkX3o8pW4QWkkxtYZrVhYpkcWjlkCAjjoMQyUJ3di0C12fT7BsEuWVYHAtTZRNKlt4nnOXpDhbGtFPJ4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95203a88ac07446405d1b8ea5cf83a2544aac202c4296505705066d6b4f7e646","last_reissued_at":"2026-07-05T11:22:43.205278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:43.205278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Alexander Gelbukh, Anvi Alex Eponon, Christian E. Maldonado-Sifuentes, Grigori Sidorov, Ildar Batyrshin, Moein Shahiki-Tash","submitted_at":"2025-06-09T16:15:11Z","abstract_excerpt":"This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method.\n  In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent. We also introduce \"paper-cards\", concise paper summaries under 300 characters, which enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13778","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/2506.13778/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":"2506.13778","created_at":"2026-07-05T11:22:43.205343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13778v1","created_at":"2026-07-05T11:22:43.205343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13778","created_at":"2026-07-05T11:22:43.205343+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUQDVCFMA5CG","created_at":"2026-07-05T11:22:43.205343+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUQDVCFMA5CGIBOR","created_at":"2026-07-05T11:22:43.205343+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUQDVCFM","created_at":"2026-07-05T11:22:43.205343+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/SUQDVCFMA5CGIBORXDVFZ6B2EV","json":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV.json","graph_json":"https://pith.science/api/pith-number/SUQDVCFMA5CGIBORXDVFZ6B2EV/graph.json","events_json":"https://pith.science/api/pith-number/SUQDVCFMA5CGIBORXDVFZ6B2EV/events.json","paper":"https://pith.science/paper/SUQDVCFM"},"agent_actions":{"view_html":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV","download_json":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV.json","view_paper":"https://pith.science/paper/SUQDVCFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13778&json=true","fetch_graph":"https://pith.science/api/pith-number/SUQDVCFMA5CGIBORXDVFZ6B2EV/graph.json","fetch_events":"https://pith.science/api/pith-number/SUQDVCFMA5CGIBORXDVFZ6B2EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV/action/storage_attestation","attest_author":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV/action/author_attestation","sign_citation":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV/action/citation_signature","submit_replication":"https://pith.science/pith/SUQDVCFMA5CGIBORXDVFZ6B2EV/action/replication_record"}},"created_at":"2026-07-05T11:22:43.205343+00:00","updated_at":"2026-07-05T11:22:43.205343+00:00"}