{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QERLLBZPNL4Y5X7UQW2PP7ZH2F","short_pith_number":"pith:QERLLBZP","schema_version":"1.0","canonical_sha256":"8122b5872f6af98edff485b4f7ff27d17beffa549af2547eb2818c3e5e1ddd81","source":{"kind":"arxiv","id":"2605.12904","version":1},"attestation_state":"computed","paper":{"title":"VIP-COP: Context Optimization for Tabular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VIP-COP estimates importance of training samples and features to build better contexts for tabular foundation models at test time.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leman Akoglu, Xueying Ding, Yilong Chen","submitted_at":"2026-05-13T02:28:31Z","abstract_excerpt":"Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specific training. However, their effectiveness is constrained by context length limits, restricting application to medium-scale data and degrading performance when inference-time data exceed pretraining size distributions. Our work introduces VIP-COP, estimating the Value of Importance for Prediction of training examples and features for hard Context OPtimization for TFMs. Its explicit selection mechanism suppresses noise"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"78dd3fc48e3e262c806d041630e05175112cd989d21048f0e678b54a0376145f","abstract_canon_sha256":"387e2715638bc7e6d2e8171ad89e188b7f7c15dd800279cc3b82e56c006a6f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:10.652307Z","signature_b64":"FQ+kaFXt1+PFDdzR5YRTB3IkFQI0X+8AsWPI50BtqCHtz+HtVe8oCWFQDh+q6SWoirrQ/vA2uwkwY6srSXUmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8122b5872f6af98edff485b4f7ff27d17beffa549af2547eb2818c3e5e1ddd81","last_reissued_at":"2026-05-18T03:09:10.651450Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:10.651450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIP-COP: Context Optimization for Tabular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VIP-COP estimates importance of training samples and features to build better contexts for tabular foundation models at test time.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leman Akoglu, Xueying Ding, Yilong Chen","submitted_at":"2026-05-13T02:28:31Z","abstract_excerpt":"Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specific training. However, their effectiveness is constrained by context length limits, restricting application to medium-scale data and degrading performance when inference-time data exceed pretraining size distributions. Our work introduces VIP-COP, estimating the Value of Importance for Prediction of training examples and features for hard Context OPtimization for TFMs. Its explicit selection mechanism suppresses noise"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VIP-COP consistently outperforms heuristic and optimized baselines across large-scale high-dimensional testbeds, including data augmentation and data-noise settings, establishing a new state of the art in test-time context refinement for TFMs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the online KernelSHAP-based regression accurately identifies influential samples and features for prediction even when the model is treated as a black box and when data distributions differ from pretraining.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VIP-COP is a black-box method that optimizes context for tabular foundation models by ranking and selecting high-value samples and features via online KernelSHAP regression, outperforming baselines on large high-dimensional data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VIP-COP estimates importance of training samples and features to build better contexts for tabular foundation models at test time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"94db3dc9acdb28ac3cfc64ff7b3e44307d1e667aa9fdb7d0615e83339180b4cc"},"source":{"id":"2605.12904","kind":"arxiv","version":1},"verdict":{"id":"4674f5b8-ebf0-4490-a651-fa06a4b68fba","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:04:24.174401Z","strongest_claim":"VIP-COP consistently outperforms heuristic and optimized baselines across large-scale high-dimensional testbeds, including data augmentation and data-noise settings, establishing a new state of the art in test-time context refinement for TFMs.","one_line_summary":"VIP-COP is a black-box method that optimizes context for tabular foundation models by ranking and selecting high-value samples and features via online KernelSHAP regression, outperforming baselines on large high-dimensional data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the online KernelSHAP-based regression accurately identifies influential samples and features for prediction even when the model is treated as a black box and when data distributions differ from pretraining.","pith_extraction_headline":"VIP-COP estimates importance of training samples and features to build better contexts for tabular foundation models at test time."},"references":{"count":42,"sample":[{"doi":"","year":2017,"title":"MIT press Cambridge, MA, USA, 2017","work_id":"727282a3-5f5f-49da-900b-bdc191bb2216","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Unleashing the potential of prompt engineering for large language models.Patterns, 6(6)","work_id":"df3167d9-81bd-4bf3-83cb-c97b9de6eeca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Extending Context Window of Large Language Models via Positional Interpolation","work_id":"c8b6df85-e7da-4bd8-90a4-d309cc2a0f60","ref_index":3,"cited_arxiv_id":"2306.15595","is_internal_anchor":true},{"doi":"","year":2023,"title":"Longlora: Efficient fine-tuning of long-context large language models","work_id":"5649158b-b4f0-42fc-a7ce-1e8e12f1ff6d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Cubuk, Barret Zoph, Dandelion Mané, Vijay Vasudevan, and Quoc V","work_id":"360d57be-26bf-498a-b081-e9c46e0df1ff","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"78df67abba004fc5716376660e5bb5b615e65d8bf77ed2210724e364e495a034","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2e06fdef24a2073c96fffc3ff84a72db2764e980159be9d9e23c5634120ef22d"},"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":"2605.12904","created_at":"2026-05-18T03:09:10.651621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12904v1","created_at":"2026-05-18T03:09:10.651621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12904","created_at":"2026-05-18T03:09:10.651621+00:00"},{"alias_kind":"pith_short_12","alias_value":"QERLLBZPNL4Y","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"QERLLBZPNL4Y5X7U","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"QERLLBZP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F","json":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F.json","graph_json":"https://pith.science/api/pith-number/QERLLBZPNL4Y5X7UQW2PP7ZH2F/graph.json","events_json":"https://pith.science/api/pith-number/QERLLBZPNL4Y5X7UQW2PP7ZH2F/events.json","paper":"https://pith.science/paper/QERLLBZP"},"agent_actions":{"view_html":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F","download_json":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F.json","view_paper":"https://pith.science/paper/QERLLBZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12904&json=true","fetch_graph":"https://pith.science/api/pith-number/QERLLBZPNL4Y5X7UQW2PP7ZH2F/graph.json","fetch_events":"https://pith.science/api/pith-number/QERLLBZPNL4Y5X7UQW2PP7ZH2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F/action/storage_attestation","attest_author":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F/action/author_attestation","sign_citation":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F/action/citation_signature","submit_replication":"https://pith.science/pith/QERLLBZPNL4Y5X7UQW2PP7ZH2F/action/replication_record"}},"created_at":"2026-05-18T03:09:10.651621+00:00","updated_at":"2026-05-18T03:09:10.651621+00:00"}