{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EHEK4JLTTED3YHOXXTXFCX2ETD","short_pith_number":"pith:EHEK4JLT","schema_version":"1.0","canonical_sha256":"21c8ae25739907bc1dd7bcee515f4498d770107138531c26fd027ffed7ed6b12","source":{"kind":"arxiv","id":"2508.18048","version":1},"attestation_state":"computed","paper":{"title":"HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jihyeon Park, Jiyoon Myung, Joohyung Han","submitted_at":"2025-08-25T14:06:27Z","abstract_excerpt":"User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over Semi-structured Tabular data), a hybrid retrieval framework that combines LLM-powered structured filtering with semantic embedding search to support complex information needs over semi-structured tabular data. HyST extracts attribute-level constraints from natural language using large language models (LLMs) and applies them as metadata filters, while processing the rema"},"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":"2508.18048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-25T14:06:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4003699a86e9103ff5c217a1a339e8838e138a1fb006f00bc572e4664fb8e81","abstract_canon_sha256":"0ab1cbe00dee7a3ebcbfbbea4c67b16c594640e94dc4f978dd46311711e0425b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:52.690268Z","signature_b64":"SybnnPfCZydkcOLQBd0vQRPL+50X89c1G85BWifEZXqETMVrhHIofIaxskIf4+f+vR0Gzm44drxMLhELg3lnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21c8ae25739907bc1dd7bcee515f4498d770107138531c26fd027ffed7ed6b12","last_reissued_at":"2026-07-05T11:58:52.689749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:52.689749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jihyeon Park, Jiyoon Myung, Joohyung Han","submitted_at":"2025-08-25T14:06:27Z","abstract_excerpt":"User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over Semi-structured Tabular data), a hybrid retrieval framework that combines LLM-powered structured filtering with semantic embedding search to support complex information needs over semi-structured tabular data. HyST extracts attribute-level constraints from natural language using large language models (LLMs) and applies them as metadata filters, while processing the rema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18048","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/2508.18048/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":"2508.18048","created_at":"2026-07-05T11:58:52.689807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18048v1","created_at":"2026-07-05T11:58:52.689807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18048","created_at":"2026-07-05T11:58:52.689807+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHEK4JLTTED3","created_at":"2026-07-05T11:58:52.689807+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHEK4JLTTED3YHOX","created_at":"2026-07-05T11:58:52.689807+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHEK4JLT","created_at":"2026-07-05T11:58:52.689807+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/EHEK4JLTTED3YHOXXTXFCX2ETD","json":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD.json","graph_json":"https://pith.science/api/pith-number/EHEK4JLTTED3YHOXXTXFCX2ETD/graph.json","events_json":"https://pith.science/api/pith-number/EHEK4JLTTED3YHOXXTXFCX2ETD/events.json","paper":"https://pith.science/paper/EHEK4JLT"},"agent_actions":{"view_html":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD","download_json":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD.json","view_paper":"https://pith.science/paper/EHEK4JLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18048&json=true","fetch_graph":"https://pith.science/api/pith-number/EHEK4JLTTED3YHOXXTXFCX2ETD/graph.json","fetch_events":"https://pith.science/api/pith-number/EHEK4JLTTED3YHOXXTXFCX2ETD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD/action/storage_attestation","attest_author":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD/action/author_attestation","sign_citation":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD/action/citation_signature","submit_replication":"https://pith.science/pith/EHEK4JLTTED3YHOXXTXFCX2ETD/action/replication_record"}},"created_at":"2026-07-05T11:58:52.689807+00:00","updated_at":"2026-07-05T11:58:52.689807+00:00"}