{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3PIET34WZWUARET7IBMSECCGLV","short_pith_number":"pith:3PIET34W","schema_version":"1.0","canonical_sha256":"dbd049ef96cda808927f40592208465d4526fdb4e5f5e0d0f8a3f590a92d57a5","source":{"kind":"arxiv","id":"2605.30289","version":1},"attestation_state":"computed","paper":{"title":"Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Merickel, Keith Wilson, M. Ross Kunz","submitted_at":"2026-05-28T17:40:42Z","abstract_excerpt":"Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric datasets in a meaningful way across heterogeneous feature spaces. Existing approaches either target predictive modeling over individual datasets, which requires a shared set of variable definitions, or lack mechanisms for interpretable cross-dataset alignment. The proposed methodology characterizes numeric tabular datasets through structured exploratory data analysis descriptors, embeds those descriptors into a shared vector space using a pretr"},"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":"2605.30289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:40:42Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"2bf818f4c7baf285e039922e7bca456ec81ecfea10b835a2f4b992508e21be15","abstract_canon_sha256":"d91c6398764642eff4bba63ad3369fd793464312dd463d6fd5635c8ebfdb319a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:15.374645Z","signature_b64":"eTj7TwZvTCEBTTS4nD/r/yquVb66XPzTjl2inz8gum2sr3MZOEs2TcomPc3bKjarqhdJ1/vamCGDOTyCX7IgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd049ef96cda808927f40592208465d4526fdb4e5f5e0d0f8a3f590a92d57a5","last_reissued_at":"2026-05-29T02:06:15.374227Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:15.374227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Merickel, Keith Wilson, M. Ross Kunz","submitted_at":"2026-05-28T17:40:42Z","abstract_excerpt":"Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric datasets in a meaningful way across heterogeneous feature spaces. Existing approaches either target predictive modeling over individual datasets, which requires a shared set of variable definitions, or lack mechanisms for interpretable cross-dataset alignment. The proposed methodology characterizes numeric tabular datasets through structured exploratory data analysis descriptors, embeds those descriptors into a shared vector space using a pretr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30289","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/2605.30289/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":"2605.30289","created_at":"2026-05-29T02:06:15.374288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30289v1","created_at":"2026-05-29T02:06:15.374288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30289","created_at":"2026-05-29T02:06:15.374288+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PIET34WZWUA","created_at":"2026-05-29T02:06:15.374288+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PIET34WZWUARET7","created_at":"2026-05-29T02:06:15.374288+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PIET34W","created_at":"2026-05-29T02:06:15.374288+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/3PIET34WZWUARET7IBMSECCGLV","json":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV.json","graph_json":"https://pith.science/api/pith-number/3PIET34WZWUARET7IBMSECCGLV/graph.json","events_json":"https://pith.science/api/pith-number/3PIET34WZWUARET7IBMSECCGLV/events.json","paper":"https://pith.science/paper/3PIET34W"},"agent_actions":{"view_html":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV","download_json":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV.json","view_paper":"https://pith.science/paper/3PIET34W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30289&json=true","fetch_graph":"https://pith.science/api/pith-number/3PIET34WZWUARET7IBMSECCGLV/graph.json","fetch_events":"https://pith.science/api/pith-number/3PIET34WZWUARET7IBMSECCGLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV/action/storage_attestation","attest_author":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV/action/author_attestation","sign_citation":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV/action/citation_signature","submit_replication":"https://pith.science/pith/3PIET34WZWUARET7IBMSECCGLV/action/replication_record"}},"created_at":"2026-05-29T02:06:15.374288+00:00","updated_at":"2026-05-29T02:06:15.374288+00:00"}