{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O6FML2FCUFMCPXYUUJXAJJMRIJ","short_pith_number":"pith:O6FML2FC","schema_version":"1.0","canonical_sha256":"778ac5e8a2a15827df14a26e04a5914279ab63a8201dfee09bd9fd9fd1ae455d","source":{"kind":"arxiv","id":"2606.11473","version":1},"attestation_state":"computed","paper":{"title":"CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Seshadri, Jamie Heredge, Mattia J. Villani, Niraj Kumar, Pranav Deshpande","submitted_at":"2026-06-09T22:07:04Z","abstract_excerpt":"Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset f"},"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":"2606.11473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T22:07:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b64582a08f1782c6c7ea7cb32d7717ef80b5c8620d919b79a96c8e0ab994217c","abstract_canon_sha256":"ba22ce3a46590e680f1fd0318809ed405d5c8d24af07400a87f0359bd00a2700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:50.999888Z","signature_b64":"+ou1So2IKJMOyo9giVTFILVqoLZzfsHgY9jJfSRrG7oySG27emhL2fwGuBBk0jMfJA3lAqjklKMKh4op6MMQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778ac5e8a2a15827df14a26e04a5914279ab63a8201dfee09bd9fd9fd1ae455d","last_reissued_at":"2026-06-11T01:09:50.999232Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:50.999232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Seshadri, Jamie Heredge, Mattia J. Villani, Niraj Kumar, Pranav Deshpande","submitted_at":"2026-06-09T22:07:04Z","abstract_excerpt":"Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11473","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/2606.11473/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":"2606.11473","created_at":"2026-06-11T01:09:50.999349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11473v1","created_at":"2026-06-11T01:09:50.999349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11473","created_at":"2026-06-11T01:09:50.999349+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6FML2FCUFMC","created_at":"2026-06-11T01:09:50.999349+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6FML2FCUFMCPXYU","created_at":"2026-06-11T01:09:50.999349+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6FML2FC","created_at":"2026-06-11T01:09:50.999349+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/O6FML2FCUFMCPXYUUJXAJJMRIJ","json":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ.json","graph_json":"https://pith.science/api/pith-number/O6FML2FCUFMCPXYUUJXAJJMRIJ/graph.json","events_json":"https://pith.science/api/pith-number/O6FML2FCUFMCPXYUUJXAJJMRIJ/events.json","paper":"https://pith.science/paper/O6FML2FC"},"agent_actions":{"view_html":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ","download_json":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ.json","view_paper":"https://pith.science/paper/O6FML2FC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11473&json=true","fetch_graph":"https://pith.science/api/pith-number/O6FML2FCUFMCPXYUUJXAJJMRIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/O6FML2FCUFMCPXYUUJXAJJMRIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ/action/storage_attestation","attest_author":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ/action/author_attestation","sign_citation":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ/action/citation_signature","submit_replication":"https://pith.science/pith/O6FML2FCUFMCPXYUUJXAJJMRIJ/action/replication_record"}},"created_at":"2026-06-11T01:09:50.999349+00:00","updated_at":"2026-06-11T01:09:50.999349+00:00"}