{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E55OYR2KK6NRLFTTVYU6OJEGOS","short_pith_number":"pith:E55OYR2K","schema_version":"1.0","canonical_sha256":"277aec474a579b159673ae29e72486748daf1b14976b3813a9dc61d1cb7f4f7b","source":{"kind":"arxiv","id":"2605.29411","version":1},"attestation_state":"computed","paper":{"title":"The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gorantla, Huan Liu, K. Sel\\c{c}uk Candan, Shu Wan","submitted_at":"2026-05-28T06:01:04Z","abstract_excerpt":"Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the boundary is observed, the target is conditionally independent of the rest of the table. This is a tempting object for tabular prediction, since it names exactly the columns a model should need. Yet modern regressors are still trained on the full feature set. We ask whether the Markov boundary is genuinely useful for prediction on SCM3K, a 3,450-task synthetic SCM benchmark with feature counts from 40 to 1000 and six SCM families, ev"},"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":"2605.29411","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T06:01:04Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"3e025f534cd155e190fefe3a2e321b73e2996797bf020d9364d1b7aa08215795","abstract_canon_sha256":"8159480f2b06c269b808b3253b8b1af0ca5bd2d4b035d541c43bef382d998b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:37.571665Z","signature_b64":"caowTVDD2Nc4dzsvhI/pZzqoT7yqts3qx86ouxVrrOZ9y+hUeqjomTg6RC6YsjAEcFBnGo3Uf/hkBsEUhpKmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"277aec474a579b159673ae29e72486748daf1b14976b3813a9dc61d1cb7f4f7b","last_reissued_at":"2026-05-29T01:05:37.571073Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:37.571073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gorantla, Huan Liu, K. Sel\\c{c}uk Candan, Shu Wan","submitted_at":"2026-05-28T06:01:04Z","abstract_excerpt":"Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the boundary is observed, the target is conditionally independent of the rest of the table. This is a tempting object for tabular prediction, since it names exactly the columns a model should need. Yet modern regressors are still trained on the full feature set. We ask whether the Markov boundary is genuinely useful for prediction on SCM3K, a 3,450-task synthetic SCM benchmark with feature counts from 40 to 1000 and six SCM families, ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29411","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/2605.29411/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":"2605.29411","created_at":"2026-05-29T01:05:37.571176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29411v1","created_at":"2026-05-29T01:05:37.571176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29411","created_at":"2026-05-29T01:05:37.571176+00:00"},{"alias_kind":"pith_short_12","alias_value":"E55OYR2KK6NR","created_at":"2026-05-29T01:05:37.571176+00:00"},{"alias_kind":"pith_short_16","alias_value":"E55OYR2KK6NRLFTT","created_at":"2026-05-29T01:05:37.571176+00:00"},{"alias_kind":"pith_short_8","alias_value":"E55OYR2K","created_at":"2026-05-29T01:05:37.571176+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/E55OYR2KK6NRLFTTVYU6OJEGOS","json":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS.json","graph_json":"https://pith.science/api/pith-number/E55OYR2KK6NRLFTTVYU6OJEGOS/graph.json","events_json":"https://pith.science/api/pith-number/E55OYR2KK6NRLFTTVYU6OJEGOS/events.json","paper":"https://pith.science/paper/E55OYR2K"},"agent_actions":{"view_html":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS","download_json":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS.json","view_paper":"https://pith.science/paper/E55OYR2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29411&json=true","fetch_graph":"https://pith.science/api/pith-number/E55OYR2KK6NRLFTTVYU6OJEGOS/graph.json","fetch_events":"https://pith.science/api/pith-number/E55OYR2KK6NRLFTTVYU6OJEGOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS/action/storage_attestation","attest_author":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS/action/author_attestation","sign_citation":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS/action/citation_signature","submit_replication":"https://pith.science/pith/E55OYR2KK6NRLFTTVYU6OJEGOS/action/replication_record"}},"created_at":"2026-05-29T01:05:37.571176+00:00","updated_at":"2026-05-29T01:05:37.571176+00:00"}