{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A27EJCMMAERBAV6U6B6E4OKQ7H","short_pith_number":"pith:A27EJCMM","schema_version":"1.0","canonical_sha256":"06be44898c01221057d4f07c4e3950f9f5e9df71d539538eaba2b990087bd90f","source":{"kind":"arxiv","id":"2406.05207","version":1},"attestation_state":"computed","paper":{"title":"Retrieval & Fine-Tuning for In-Context Tabular Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Caterini, Guangwei Yu, Junwei Ma, Keyvan Golestan, Maksims Volkovs, Rasa Hosseinzadeh, Valentin Thomas","submitted_at":"2024-06-07T18:43:33Z","abstract_excerpt":"Tabular data is a pervasive modality spanning a wide range of domains, and the inherent diversity poses a considerable challenge for deep learning. Recent advancements using transformer-based in-context learning have shown promise on smaller and less complex datasets, but have struggled to scale to larger and more complex ones. To address this limitation, we propose a combination of retrieval and fine-tuning: we can adapt the transformer to a local subset of the data by collecting nearest neighbours, and then perform task-specific fine-tuning with this retrieved set of neighbours in context. U"},"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":"2406.05207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T18:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"1f3680c08aa6eaa2b40a46aae6ef616ebc876984c8f0cdafbaa7f87536d3553f","abstract_canon_sha256":"8a00966d75d29f1b3f0d5cd3ac522cb4994d1a6651aefc0b12d4e6834fe79ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:02.341077Z","signature_b64":"6PVKreb2wqSQjt1UNJY+2byDlzbCRqjyHLEDswOTDXnMA7yFKMbU7TS5HMW+wdGIEpYLdgExsNbdNVqKuzIvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06be44898c01221057d4f07c4e3950f9f5e9df71d539538eaba2b990087bd90f","last_reissued_at":"2026-07-05T08:29:02.340520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:02.340520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval & Fine-Tuning for In-Context Tabular Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Caterini, Guangwei Yu, Junwei Ma, Keyvan Golestan, Maksims Volkovs, Rasa Hosseinzadeh, Valentin Thomas","submitted_at":"2024-06-07T18:43:33Z","abstract_excerpt":"Tabular data is a pervasive modality spanning a wide range of domains, and the inherent diversity poses a considerable challenge for deep learning. Recent advancements using transformer-based in-context learning have shown promise on smaller and less complex datasets, but have struggled to scale to larger and more complex ones. To address this limitation, we propose a combination of retrieval and fine-tuning: we can adapt the transformer to a local subset of the data by collecting nearest neighbours, and then perform task-specific fine-tuning with this retrieved set of neighbours in context. U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05207","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/2406.05207/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":"2406.05207","created_at":"2026-07-05T08:29:02.340576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05207v1","created_at":"2026-07-05T08:29:02.340576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05207","created_at":"2026-07-05T08:29:02.340576+00:00"},{"alias_kind":"pith_short_12","alias_value":"A27EJCMMAERB","created_at":"2026-07-05T08:29:02.340576+00:00"},{"alias_kind":"pith_short_16","alias_value":"A27EJCMMAERBAV6U","created_at":"2026-07-05T08:29:02.340576+00:00"},{"alias_kind":"pith_short_8","alias_value":"A27EJCMM","created_at":"2026-07-05T08:29:02.340576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11473","citing_title":"CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H","json":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H.json","graph_json":"https://pith.science/api/pith-number/A27EJCMMAERBAV6U6B6E4OKQ7H/graph.json","events_json":"https://pith.science/api/pith-number/A27EJCMMAERBAV6U6B6E4OKQ7H/events.json","paper":"https://pith.science/paper/A27EJCMM"},"agent_actions":{"view_html":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H","download_json":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H.json","view_paper":"https://pith.science/paper/A27EJCMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05207&json=true","fetch_graph":"https://pith.science/api/pith-number/A27EJCMMAERBAV6U6B6E4OKQ7H/graph.json","fetch_events":"https://pith.science/api/pith-number/A27EJCMMAERBAV6U6B6E4OKQ7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H/action/storage_attestation","attest_author":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H/action/author_attestation","sign_citation":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H/action/citation_signature","submit_replication":"https://pith.science/pith/A27EJCMMAERBAV6U6B6E4OKQ7H/action/replication_record"}},"created_at":"2026-07-05T08:29:02.340576+00:00","updated_at":"2026-07-05T08:29:02.340576+00:00"}