{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GIFEFHFDM22O4DH2GLGH7PTS5G","short_pith_number":"pith:GIFEFHFD","schema_version":"1.0","canonical_sha256":"320a429ca366b4ee0cfa32cc7fbe72e99436fb05e9f5a40eed8ce61c2a4f9266","source":{"kind":"arxiv","id":"2412.20331","version":1},"attestation_state":"computed","paper":{"title":"Mind the Data Gap: Bridging LLMs to Enterprise Data Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"\\c{C}a\\u{g}atay Demiralp, Fabian Wenz, Moe Kayali, Nesime Tatbul","submitted_at":"2024-12-29T03:07:20Z","abstract_excerpt":"Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to "},"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":"2412.20331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-12-29T03:07:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3d3450c685cb17f54a8529520b49b99c31211c91055bfdd87dd7b10a97325944","abstract_canon_sha256":"519b22f1c6626b036afa3a57e904cf81ee3183e462d618de5adb61d18eee08be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:57.666238Z","signature_b64":"C7AOz0JhwRwzBnTo5OWG7ibrxD8kuKWdWj+5NYtrs/7hpNRBuSDZrJLUeLzbfXBvhmdzVU1IUlgKFPfK07UBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320a429ca366b4ee0cfa32cc7fbe72e99436fb05e9f5a40eed8ce61c2a4f9266","last_reissued_at":"2026-07-05T09:54:57.665734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:57.665734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Data Gap: Bridging LLMs to Enterprise Data Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"\\c{C}a\\u{g}atay Demiralp, Fabian Wenz, Moe Kayali, Nesime Tatbul","submitted_at":"2024-12-29T03:07:20Z","abstract_excerpt":"Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20331","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/2412.20331/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":"2412.20331","created_at":"2026-07-05T09:54:57.665804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20331v1","created_at":"2026-07-05T09:54:57.665804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20331","created_at":"2026-07-05T09:54:57.665804+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIFEFHFDM22O","created_at":"2026-07-05T09:54:57.665804+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIFEFHFDM22O4DH2","created_at":"2026-07-05T09:54:57.665804+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIFEFHFD","created_at":"2026-07-05T09:54:57.665804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30452","citing_title":"Exploring Differences Between Tabular Enterprise Data and Public Benchmarks","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G","json":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G.json","graph_json":"https://pith.science/api/pith-number/GIFEFHFDM22O4DH2GLGH7PTS5G/graph.json","events_json":"https://pith.science/api/pith-number/GIFEFHFDM22O4DH2GLGH7PTS5G/events.json","paper":"https://pith.science/paper/GIFEFHFD"},"agent_actions":{"view_html":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G","download_json":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G.json","view_paper":"https://pith.science/paper/GIFEFHFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20331&json=true","fetch_graph":"https://pith.science/api/pith-number/GIFEFHFDM22O4DH2GLGH7PTS5G/graph.json","fetch_events":"https://pith.science/api/pith-number/GIFEFHFDM22O4DH2GLGH7PTS5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G/action/storage_attestation","attest_author":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G/action/author_attestation","sign_citation":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G/action/citation_signature","submit_replication":"https://pith.science/pith/GIFEFHFDM22O4DH2GLGH7PTS5G/action/replication_record"}},"created_at":"2026-07-05T09:54:57.665804+00:00","updated_at":"2026-07-05T09:54:57.665804+00:00"}