{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3PIET34WZWUARET7IBMSECCGLV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d91c6398764642eff4bba63ad3369fd793464312dd463d6fd5635c8ebfdb319a","cross_cats_sorted":["stat.AP","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:40:42Z","title_canon_sha256":"2bf818f4c7baf285e039922e7bca456ec81ecfea10b835a2f4b992508e21be15"},"schema_version":"1.0","source":{"id":"2605.30289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30289","created_at":"2026-05-29T02:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30289v1","created_at":"2026-05-29T02:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30289","created_at":"2026-05-29T02:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"3PIET34WZWUA","created_at":"2026-05-29T02:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"3PIET34WZWUARET7","created_at":"2026-05-29T02:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"3PIET34W","created_at":"2026-05-29T02:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:860eb3520069634f7f7667597f2d5fc9436548af6a4d1185b8f367d9cb0c70a7","target":"graph","created_at":"2026-05-29T02:06:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.30289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"John Merickel, Keith Wilson, M. Ross Kunz","cross_cats":["stat.AP","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:40:42Z","title":"Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30289","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:114f8a32d8b625c268fc537858c00e983d5d422abb7658a3d4af1535b101383f","target":"record","created_at":"2026-05-29T02:06:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d91c6398764642eff4bba63ad3369fd793464312dd463d6fd5635c8ebfdb319a","cross_cats_sorted":["stat.AP","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:40:42Z","title_canon_sha256":"2bf818f4c7baf285e039922e7bca456ec81ecfea10b835a2f4b992508e21be15"},"schema_version":"1.0","source":{"id":"2605.30289","kind":"arxiv","version":1}},"canonical_sha256":"dbd049ef96cda808927f40592208465d4526fdb4e5f5e0d0f8a3f590a92d57a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd049ef96cda808927f40592208465d4526fdb4e5f5e0d0f8a3f590a92d57a5","first_computed_at":"2026-05-29T02:06:15.374227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:15.374227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTj7TwZvTCEBTTS4nD/r/yquVb66XPzTjl2inz8gum2sr3MZOEs2TcomPc3bKjarqhdJ1/vamCGDOTyCX7IgCw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:15.374645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:114f8a32d8b625c268fc537858c00e983d5d422abb7658a3d4af1535b101383f","sha256:860eb3520069634f7f7667597f2d5fc9436548af6a4d1185b8f367d9cb0c70a7"],"state_sha256":"3b4ffe1b8473a49a5636f757ee642ae00a09ff57f15607cafce4e7b21c38e850"}