{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MZWPOXNMRF4XNIIMQYHNFQ5GGV","short_pith_number":"pith:MZWPOXNM","schema_version":"1.0","canonical_sha256":"666cf75dac897976a10c860ed2c3a635789229158a3f36df7706b3f4bb0079a4","source":{"kind":"arxiv","id":"2402.06971","version":1},"attestation_state":"computed","paper":{"title":"In-Context Data Distillation with TabPFN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Caterini, Guangwei Yu, Junwei Ma, Valentin Thomas","submitted_at":"2024-02-10T15:23:45Z","abstract_excerpt":"Foundation models have revolutionized tasks in computer vision and natural language processing. However, in the realm of tabular data, tree-based models like XGBoost continue to dominate. TabPFN, a transformer model tailored for tabular data, mirrors recent foundation models in its exceptional in-context learning capability, being competitive with XGBoost's performance without the need for task-specific training or hyperparameter tuning. Despite its promise, TabPFN's applicability is hindered by its data size constraint, limiting its use in real-world scenarios. To address this, we present in-"},"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":"2402.06971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T15:23:45Z","cross_cats_sorted":[],"title_canon_sha256":"708d32b569062cde766c177e17e7b9855a163c81b2cab9ee4bd0773a48b971da","abstract_canon_sha256":"b5d6e3ae2372850799db17a8c81306e91d9545c88638b15a24355a1b54c5aab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:41.257139Z","signature_b64":"a/NVdqAaa6nwDSeO8g/zdT1UhNd30BlalmZqffXiMTcT9h2S/oeBm5gvVQfKXZVZsWoCTwTWr++Ynhf7Oe2ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"666cf75dac897976a10c860ed2c3a635789229158a3f36df7706b3f4bb0079a4","last_reissued_at":"2026-07-05T07:43:41.256644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:41.256644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Data Distillation with TabPFN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Caterini, Guangwei Yu, Junwei Ma, Valentin Thomas","submitted_at":"2024-02-10T15:23:45Z","abstract_excerpt":"Foundation models have revolutionized tasks in computer vision and natural language processing. However, in the realm of tabular data, tree-based models like XGBoost continue to dominate. TabPFN, a transformer model tailored for tabular data, mirrors recent foundation models in its exceptional in-context learning capability, being competitive with XGBoost's performance without the need for task-specific training or hyperparameter tuning. Despite its promise, TabPFN's applicability is hindered by its data size constraint, limiting its use in real-world scenarios. To address this, we present in-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06971","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/2402.06971/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":"2402.06971","created_at":"2026-07-05T07:43:41.256705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06971v1","created_at":"2026-07-05T07:43:41.256705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06971","created_at":"2026-07-05T07:43:41.256705+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZWPOXNMRF4X","created_at":"2026-07-05T07:43:41.256705+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZWPOXNMRF4XNIIM","created_at":"2026-07-05T07:43:41.256705+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZWPOXNM","created_at":"2026-07-05T07:43:41.256705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01990","citing_title":"Testing for Single-Population Ancestry in the Admixture Model","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12904","citing_title":"VIP-COP: Context Optimization for Tabular Foundation Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV","json":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV.json","graph_json":"https://pith.science/api/pith-number/MZWPOXNMRF4XNIIMQYHNFQ5GGV/graph.json","events_json":"https://pith.science/api/pith-number/MZWPOXNMRF4XNIIMQYHNFQ5GGV/events.json","paper":"https://pith.science/paper/MZWPOXNM"},"agent_actions":{"view_html":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV","download_json":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV.json","view_paper":"https://pith.science/paper/MZWPOXNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06971&json=true","fetch_graph":"https://pith.science/api/pith-number/MZWPOXNMRF4XNIIMQYHNFQ5GGV/graph.json","fetch_events":"https://pith.science/api/pith-number/MZWPOXNMRF4XNIIMQYHNFQ5GGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV/action/storage_attestation","attest_author":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV/action/author_attestation","sign_citation":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV/action/citation_signature","submit_replication":"https://pith.science/pith/MZWPOXNMRF4XNIIMQYHNFQ5GGV/action/replication_record"}},"created_at":"2026-07-05T07:43:41.256705+00:00","updated_at":"2026-07-05T07:43:41.256705+00:00"}