{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U7ESEVSA37RJ7VAW3BASRIGWEG","short_pith_number":"pith:U7ESEVSA","schema_version":"1.0","canonical_sha256":"a7c9225640dfe29fd416d84128a0d6219666727bf38496f688d835344cb93a7a","source":{"kind":"arxiv","id":"1908.07442","version":5},"attestation_state":"computed","paper":{"title":"TabNet: Attentive Interpretable Tabular Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sercan O. Arik, Tomas Pfister","submitted_at":"2019-08-20T15:46:53Z","abstract_excerpt":"We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient features. We demonstrate that TabNet outperforms other neural network and decision tree variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into the global model behavior. Finally, for the first time to o"},"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":"1908.07442","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-20T15:46:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b1a05a24073cc07a5212db80c404c04a7f1e4b5b4c335714f8b2dbcb4719e98d","abstract_canon_sha256":"c1808d3d68c8ede24547c4b21f948a97bd989f63ab461221a2e2ef7c32de95fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:07.123499Z","signature_b64":"WfDK+6+QeP/nwhYa39Vm8oCUdvbimy9jVqQXuvIw8rz9C2VimPWy2E14PKhCX24Px+1LZOO4Te2g3Z80YMUFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c9225640dfe29fd416d84128a0d6219666727bf38496f688d835344cb93a7a","last_reissued_at":"2026-07-05T01:58:07.122953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:07.122953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabNet: Attentive Interpretable Tabular Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sercan O. Arik, Tomas Pfister","submitted_at":"2019-08-20T15:46:53Z","abstract_excerpt":"We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient features. We demonstrate that TabNet outperforms other neural network and decision tree variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into the global model behavior. Finally, for the first time to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07442","kind":"arxiv","version":5},"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/1908.07442/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":"1908.07442","created_at":"2026-07-05T01:58:07.123020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07442v5","created_at":"2026-07-05T01:58:07.123020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07442","created_at":"2026-07-05T01:58:07.123020+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7ESEVSA37RJ","created_at":"2026-07-05T01:58:07.123020+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7ESEVSA37RJ7VAW","created_at":"2026-07-05T01:58:07.123020+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7ESEVSA","created_at":"2026-07-05T01:58:07.123020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07756","citing_title":"The Importance of Encoder Choice:A Tabular-Image Study","ref_index":199,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19329","citing_title":"The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2012.06678","citing_title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05635","citing_title":"From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG","json":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG.json","graph_json":"https://pith.science/api/pith-number/U7ESEVSA37RJ7VAW3BASRIGWEG/graph.json","events_json":"https://pith.science/api/pith-number/U7ESEVSA37RJ7VAW3BASRIGWEG/events.json","paper":"https://pith.science/paper/U7ESEVSA"},"agent_actions":{"view_html":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG","download_json":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG.json","view_paper":"https://pith.science/paper/U7ESEVSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07442&json=true","fetch_graph":"https://pith.science/api/pith-number/U7ESEVSA37RJ7VAW3BASRIGWEG/graph.json","fetch_events":"https://pith.science/api/pith-number/U7ESEVSA37RJ7VAW3BASRIGWEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG/action/storage_attestation","attest_author":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG/action/author_attestation","sign_citation":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG/action/citation_signature","submit_replication":"https://pith.science/pith/U7ESEVSA37RJ7VAW3BASRIGWEG/action/replication_record"}},"created_at":"2026-07-05T01:58:07.123020+00:00","updated_at":"2026-07-05T01:58:07.123020+00:00"}