{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UDTYJBMCLQGMUG7JVYMREG24DZ","short_pith_number":"pith:UDTYJBMC","schema_version":"1.0","canonical_sha256":"a0e78485825c0cca1be9ae19121b5c1e5b665bc2b0a309cbc96fef40e58baf8d","source":{"kind":"arxiv","id":"2606.31808","version":1},"attestation_state":"computed","paper":{"title":"Large Databases Need Small, Open-Weight Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Alfy Samuel, Parker Glenn","submitted_at":"2026-06-30T15:25:10Z","abstract_excerpt":"Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of large databases, where LM-enhanced relational operators can incur costs exceeding $10,000 for a single set of experiments, hindering thorough research and practical deployment. In this paper, we demonstrate that quantized, open-weight models running locally on just 16GB of VRAM can match or exceed the accuracy of closed-source counterparts at lower latency and a fraction of the price, challenging the prevailing assumption that closed-source LM A"},"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":"2606.31808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T15:25:10Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"8b679afa7032c3a95aab1fddb211012cd69e4b18ca5be3d14c54ea9f304a1075","abstract_canon_sha256":"c0c085693d1445560b26abd3ae76ce54f9f2456080ba85638c2300b6dc044c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:16.249676Z","signature_b64":"cKmPbmkl04H1Kn9ZkacuAFvtICZN1E1JWcX+z3jscBrAjZrFwo/0+/Z+6qMvZXBA3SbavD3bYDAetXJQ+gTAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e78485825c0cca1be9ae19121b5c1e5b665bc2b0a309cbc96fef40e58baf8d","last_reissued_at":"2026-07-01T01:18:16.249252Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:16.249252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Databases Need Small, Open-Weight Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Alfy Samuel, Parker Glenn","submitted_at":"2026-06-30T15:25:10Z","abstract_excerpt":"Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of large databases, where LM-enhanced relational operators can incur costs exceeding $10,000 for a single set of experiments, hindering thorough research and practical deployment. In this paper, we demonstrate that quantized, open-weight models running locally on just 16GB of VRAM can match or exceed the accuracy of closed-source counterparts at lower latency and a fraction of the price, challenging the prevailing assumption that closed-source LM A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31808","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/2606.31808/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":"2606.31808","created_at":"2026-07-01T01:18:16.249311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31808v1","created_at":"2026-07-01T01:18:16.249311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31808","created_at":"2026-07-01T01:18:16.249311+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDTYJBMCLQGM","created_at":"2026-07-01T01:18:16.249311+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDTYJBMCLQGMUG7J","created_at":"2026-07-01T01:18:16.249311+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDTYJBMC","created_at":"2026-07-01T01:18:16.249311+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/UDTYJBMCLQGMUG7JVYMREG24DZ","json":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ.json","graph_json":"https://pith.science/api/pith-number/UDTYJBMCLQGMUG7JVYMREG24DZ/graph.json","events_json":"https://pith.science/api/pith-number/UDTYJBMCLQGMUG7JVYMREG24DZ/events.json","paper":"https://pith.science/paper/UDTYJBMC"},"agent_actions":{"view_html":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ","download_json":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ.json","view_paper":"https://pith.science/paper/UDTYJBMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31808&json=true","fetch_graph":"https://pith.science/api/pith-number/UDTYJBMCLQGMUG7JVYMREG24DZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UDTYJBMCLQGMUG7JVYMREG24DZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ/action/storage_attestation","attest_author":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ/action/author_attestation","sign_citation":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ/action/citation_signature","submit_replication":"https://pith.science/pith/UDTYJBMCLQGMUG7JVYMREG24DZ/action/replication_record"}},"created_at":"2026-07-01T01:18:16.249311+00:00","updated_at":"2026-07-01T01:18:16.249311+00:00"}