{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QTWK7M5EILECIDJ6DG5ADQ4BWN","short_pith_number":"pith:QTWK7M5E","schema_version":"1.0","canonical_sha256":"84ecafb3a442c8240d3e19ba01c381b3403c2a41856742679b94a189962e09d8","source":{"kind":"arxiv","id":"2605.14365","version":1},"attestation_state":"computed","paper":{"title":"LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LoMETab generalizes rank-1 multiplicative ensembles to rank-r adapters for tabular models, strictly enlarging the hypothesis class and exposing tunable diversity controls.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changryeol Choi, Gowun Jeong, Hyewon Park, Yujin Kwon","submitted_at":"2026-05-14T04:47:16Z","abstract_excerpt":"Recent tabular learning benchmarks increasingly show a tight performance cluster rather than a clear hierarchy among leading methods, spanning gradient boosted decision trees, attention-based architectures, and implicit ensembles such as TabM. As benchmark gains plateau, a complementary goal is to understand and control the mechanisms that make simple neural tabular models competitive. We propose LoMETab, a rank-$r$ generalization of multiplicative implicit ensembles. LoMETab lifts the rank-1 BatchEnsemble/TabM modulation to a rank-$r$ identity-residual Hadamard family by parameterizing each m"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:47:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c114c7238e8a5777a35d40442699e25cdaed58bccc3ff77b75800c8d1e103f12","abstract_canon_sha256":"981b5145510893e2148daef694e1c6fd5367bd108580836d118654d675db943e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.898523Z","signature_b64":"bWFq2VaQQPpeGlu/4u/XqIcBXZPRza4/ZpU7pqhLv9dHE4aS5WylAPZPlf/GigpcaFu/ANq69ji6dAtsqgywDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ecafb3a442c8240d3e19ba01c381b3403c2a41856742679b94a189962e09d8","last_reissued_at":"2026-05-17T23:39:07.897817Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.897817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LoMETab generalizes rank-1 multiplicative ensembles to rank-r adapters for tabular models, strictly enlarging the hypothesis class and exposing tunable diversity controls.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changryeol Choi, Gowun Jeong, Hyewon Park, Yujin Kwon","submitted_at":"2026-05-14T04:47:16Z","abstract_excerpt":"Recent tabular learning benchmarks increasingly show a tight performance cluster rather than a clear hierarchy among leading methods, spanning gradient boosted decision trees, attention-based architectures, and implicit ensembles such as TabM. As benchmark gains plateau, a complementary goal is to understand and control the mechanisms that make simple neural tabular models competitive. We propose LoMETab, a rank-$r$ generalization of multiplicative implicit ensembles. LoMETab lifts the rank-1 BatchEnsemble/TabM modulation to a rank-$r$ identity-residual Hadamard family by parameterizing each m"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We prove that for r >= 2 this generalization strictly enlarges BatchEnsemble's hypothesis class. Empirically, LoMETab sustains higher pairwise KL than an additive low-rank ablation, and (r, sigma_init) provides broad control over pairwise KL, varying by up to several orders of magnitude.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the added representational capacity and induced diversity will translate into practically useful predictive behavior rather than merely dataset-dependent variation; the abstract reports that performance over the (r, sigma_init) grid is dataset-dependent.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LoMETab generalizes rank-1 multiplicative ensembles to rank-r adapters for tabular models, strictly enlarging the hypothesis class and exposing tunable diversity controls.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5d5426ace85027eeaa4289c21f1c5e1837e669502f77a42df925d3fe7a222bb0"},"source":{"id":"2605.14365","kind":"arxiv","version":1},"verdict":{"id":"fb9c7d3c-d33a-4766-8274-0424ae153871","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:49:04.351626Z","strongest_claim":"We prove that for r >= 2 this generalization strictly enlarges BatchEnsemble's hypothesis class. Empirically, LoMETab sustains higher pairwise KL than an additive low-rank ablation, and (r, sigma_init) provides broad control over pairwise KL, varying by up to several orders of magnitude.","one_line_summary":"LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the added representational capacity and induced diversity will translate into practically useful predictive behavior rather than merely dataset-dependent variation; the abstract reports that performance over the (r, sigma_init) grid is dataset-dependent.","pith_extraction_headline":"LoMETab generalizes rank-1 multiplicative ensembles to rank-r adapters for tabular models, strictly enlarging the hypothesis class and exposing tunable diversity controls."},"references":{"count":23,"sample":[{"doi":"","year":2019,"title":"Optuna: A next-generation hyperparameter optimization framework","work_id":"f11f4cd0-9ce5-4174-a976-f401f5e9ce28","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"XGBoost: A scalable tree boosting system","work_id":"bea565cd-2b99-41c7-8085-02eba78c6f8f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Masksembles for uncertainty estimation","work_id":"c8d2a3d6-20d5-47ec-955a-24064d06b6d3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"On embeddings for numerical features in tabular deep learning","work_id":"aaa16ab9-7e1e-4cca-903a-566c4b099f74","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"TabR: Tabular deep learning meets nearest neighbors","work_id":"063c1227-1e8a-4626-9d08-87eb984116d0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"1cb42c6ab57edb06565febc01d19bb8e642782881483b3ce025f6df37199a497","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ebde908e23afe8710f643e2ac4f28152414efdc0a3796f700efb496812ff706b"},"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":"2605.14365","created_at":"2026-05-17T23:39:07.897914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14365v1","created_at":"2026-05-17T23:39:07.897914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14365","created_at":"2026-05-17T23:39:07.897914+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTWK7M5EILEC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTWK7M5EILECIDJ6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTWK7M5E","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN","json":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN.json","graph_json":"https://pith.science/api/pith-number/QTWK7M5EILECIDJ6DG5ADQ4BWN/graph.json","events_json":"https://pith.science/api/pith-number/QTWK7M5EILECIDJ6DG5ADQ4BWN/events.json","paper":"https://pith.science/paper/QTWK7M5E"},"agent_actions":{"view_html":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN","download_json":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN.json","view_paper":"https://pith.science/paper/QTWK7M5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14365&json=true","fetch_graph":"https://pith.science/api/pith-number/QTWK7M5EILECIDJ6DG5ADQ4BWN/graph.json","fetch_events":"https://pith.science/api/pith-number/QTWK7M5EILECIDJ6DG5ADQ4BWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN/action/storage_attestation","attest_author":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN/action/author_attestation","sign_citation":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN/action/citation_signature","submit_replication":"https://pith.science/pith/QTWK7M5EILECIDJ6DG5ADQ4BWN/action/replication_record"}},"created_at":"2026-05-17T23:39:07.897914+00:00","updated_at":"2026-05-17T23:39:07.897914+00:00"}