{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GK5SYN5HPQRSEKVRHD74OP4CB5","short_pith_number":"pith:GK5SYN5H","schema_version":"1.0","canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","source":{"kind":"arxiv","id":"2606.29532","version":1},"attestation_state":"computed","paper":{"title":"SemJoin: Semantic Join Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya Banerjee, Christopher Gou, Chunwei Liu, Jiaxuan Wang","submitted_at":"2026-06-28T17:57:10Z","abstract_excerpt":"Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeli"},"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":"2606.29532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a4a240ba7172e69018d00731fe2d1a0b0192486acdd93423ca46b36bcc3a655","abstract_canon_sha256":"734f413f7428a5a2986aa2d84838e6e5d0422a19182362c9fe0f4974f22cfcda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:10.647523Z","signature_b64":"2WfbBprl10+vPkp0L2iB9a2sHdw+LqK5OLhHzNisMvbVKwBtEMI/5IS4EBEsXt64KsUSS/P++8Hw2d4wE137CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","last_reissued_at":"2026-06-30T01:18:10.646992Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:10.646992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemJoin: Semantic Join Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya Banerjee, Christopher Gou, Chunwei Liu, Jiaxuan Wang","submitted_at":"2026-06-28T17:57:10Z","abstract_excerpt":"Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29532","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/2606.29532/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":"2606.29532","created_at":"2026-06-30T01:18:10.647071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29532v1","created_at":"2026-06-30T01:18:10.647071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29532","created_at":"2026-06-30T01:18:10.647071+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK5SYN5HPQRS","created_at":"2026-06-30T01:18:10.647071+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK5SYN5HPQRSEKVR","created_at":"2026-06-30T01:18:10.647071+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK5SYN5H","created_at":"2026-06-30T01:18:10.647071+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/GK5SYN5HPQRSEKVRHD74OP4CB5","json":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5.json","graph_json":"https://pith.science/api/pith-number/GK5SYN5HPQRSEKVRHD74OP4CB5/graph.json","events_json":"https://pith.science/api/pith-number/GK5SYN5HPQRSEKVRHD74OP4CB5/events.json","paper":"https://pith.science/paper/GK5SYN5H"},"agent_actions":{"view_html":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5","download_json":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5.json","view_paper":"https://pith.science/paper/GK5SYN5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29532&json=true","fetch_graph":"https://pith.science/api/pith-number/GK5SYN5HPQRSEKVRHD74OP4CB5/graph.json","fetch_events":"https://pith.science/api/pith-number/GK5SYN5HPQRSEKVRHD74OP4CB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/action/storage_attestation","attest_author":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/action/author_attestation","sign_citation":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/action/citation_signature","submit_replication":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/action/replication_record"}},"created_at":"2026-06-30T01:18:10.647071+00:00","updated_at":"2026-06-30T01:18:10.647071+00:00"}