{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:37NZJMFM6X4YRKZRPLCE25L6NJ","short_pith_number":"pith:37NZJMFM","schema_version":"1.0","canonical_sha256":"dfdb94b0acf5f988ab317ac44d757e6a556dae032ceb57927dd5a2c575e9d7ae","source":{"kind":"arxiv","id":"2411.17207","version":1},"attestation_state":"computed","paper":{"title":"On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton Frederik Thielmann, Soheila Samiee","submitted_at":"2024-11-26T08:23:29Z","abstract_excerpt":"Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language model-based approaches, DL models for tabular data have also grown in complexity and size. Although tabular datasets do not typically pose scalability issues, the escalating size of these models has raised efficiency concerns. Despite its importance, efficiency has been relatively underexplored in tabular DL research. This paper critically examines the lates"},"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":"2411.17207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T08:23:29Z","cross_cats_sorted":[],"title_canon_sha256":"5b691d2884b9c48b80c27c35f4ce57bacc79e2c1bfefbd269f36382a48e598e7","abstract_canon_sha256":"155aa94a0cbf309c929e688dac31b0e39ff12b840cd5606d1762f492dc1b02a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:29.064304Z","signature_b64":"6vt9LlgLohG6Yus6kWLMJbOuJaKy22+fo/L/l9to+GDZx3HblpxvWv2PWUFAKtGnCabgNW1+xCy9JJZguZWCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfdb94b0acf5f988ab317ac44d757e6a556dae032ceb57927dd5a2c575e9d7ae","last_reissued_at":"2026-07-05T09:40:29.063893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:29.063893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton Frederik Thielmann, Soheila Samiee","submitted_at":"2024-11-26T08:23:29Z","abstract_excerpt":"Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language model-based approaches, DL models for tabular data have also grown in complexity and size. Although tabular datasets do not typically pose scalability issues, the escalating size of these models has raised efficiency concerns. Despite its importance, efficiency has been relatively underexplored in tabular DL research. This paper critically examines the lates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17207","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/2411.17207/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":"2411.17207","created_at":"2026-07-05T09:40:29.063948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17207v1","created_at":"2026-07-05T09:40:29.063948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17207","created_at":"2026-07-05T09:40:29.063948+00:00"},{"alias_kind":"pith_short_12","alias_value":"37NZJMFM6X4Y","created_at":"2026-07-05T09:40:29.063948+00:00"},{"alias_kind":"pith_short_16","alias_value":"37NZJMFM6X4YRKZR","created_at":"2026-07-05T09:40:29.063948+00:00"},{"alias_kind":"pith_short_8","alias_value":"37NZJMFM","created_at":"2026-07-05T09:40:29.063948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20738","citing_title":"An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02384","citing_title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04363","citing_title":"Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04363","citing_title":"Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ","json":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ.json","graph_json":"https://pith.science/api/pith-number/37NZJMFM6X4YRKZRPLCE25L6NJ/graph.json","events_json":"https://pith.science/api/pith-number/37NZJMFM6X4YRKZRPLCE25L6NJ/events.json","paper":"https://pith.science/paper/37NZJMFM"},"agent_actions":{"view_html":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ","download_json":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ.json","view_paper":"https://pith.science/paper/37NZJMFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17207&json=true","fetch_graph":"https://pith.science/api/pith-number/37NZJMFM6X4YRKZRPLCE25L6NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/37NZJMFM6X4YRKZRPLCE25L6NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ/action/storage_attestation","attest_author":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ/action/author_attestation","sign_citation":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ/action/citation_signature","submit_replication":"https://pith.science/pith/37NZJMFM6X4YRKZRPLCE25L6NJ/action/replication_record"}},"created_at":"2026-07-05T09:40:29.063948+00:00","updated_at":"2026-07-05T09:40:29.063948+00:00"}