{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KH3XCHCJCT4QGO3P4NS5HBSNNF","short_pith_number":"pith:KH3XCHCJ","schema_version":"1.0","canonical_sha256":"51f7711c4914f9033b6fe365d3864d696a51ba3e9e15b5a718a82e5d6c8b73cd","source":{"kind":"arxiv","id":"2302.06375","version":4},"attestation_state":"computed","paper":{"title":"One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enver Sangineto, Fabrizio Garuti, Lorenzo Forni, Rita Cucchiara, Simone Luetto","submitted_at":"2023-02-13T14:08:40Z","abstract_excerpt":"There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features a"},"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":"2302.06375","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T14:08:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1cd0dcd414cd29f8804f54e7f63536d0e7bfdbaaf58649524c9326d4aa25932","abstract_canon_sha256":"d0f892db89ef0fe33730ea818e80ba29d5463326a8f69670a89a998190ed4a4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:12.233106Z","signature_b64":"njMyHeI1boyv1CTlHNCz3A8UftX6/vbw/2jEQfexAg21jbQKLLmqSRQwUAQVvXSeBvshMAyzLplXbGrFom97DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51f7711c4914f9033b6fe365d3864d696a51ba3e9e15b5a718a82e5d6c8b73cd","last_reissued_at":"2026-07-05T10:58:12.232609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:12.232609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enver Sangineto, Fabrizio Garuti, Lorenzo Forni, Rita Cucchiara, Simone Luetto","submitted_at":"2023-02-13T14:08:40Z","abstract_excerpt":"There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06375","kind":"arxiv","version":4},"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/2302.06375/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":"2302.06375","created_at":"2026-07-05T10:58:12.232667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06375v4","created_at":"2026-07-05T10:58:12.232667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06375","created_at":"2026-07-05T10:58:12.232667+00:00"},{"alias_kind":"pith_short_12","alias_value":"KH3XCHCJCT4Q","created_at":"2026-07-05T10:58:12.232667+00:00"},{"alias_kind":"pith_short_16","alias_value":"KH3XCHCJCT4QGO3P","created_at":"2026-07-05T10:58:12.232667+00:00"},{"alias_kind":"pith_short_8","alias_value":"KH3XCHCJ","created_at":"2026-07-05T10:58:12.232667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03717","citing_title":"Universal Time-Series Representation Learning: A Survey","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF","json":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF.json","graph_json":"https://pith.science/api/pith-number/KH3XCHCJCT4QGO3P4NS5HBSNNF/graph.json","events_json":"https://pith.science/api/pith-number/KH3XCHCJCT4QGO3P4NS5HBSNNF/events.json","paper":"https://pith.science/paper/KH3XCHCJ"},"agent_actions":{"view_html":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF","download_json":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF.json","view_paper":"https://pith.science/paper/KH3XCHCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06375&json=true","fetch_graph":"https://pith.science/api/pith-number/KH3XCHCJCT4QGO3P4NS5HBSNNF/graph.json","fetch_events":"https://pith.science/api/pith-number/KH3XCHCJCT4QGO3P4NS5HBSNNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF/action/storage_attestation","attest_author":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF/action/author_attestation","sign_citation":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF/action/citation_signature","submit_replication":"https://pith.science/pith/KH3XCHCJCT4QGO3P4NS5HBSNNF/action/replication_record"}},"created_at":"2026-07-05T10:58:12.232667+00:00","updated_at":"2026-07-05T10:58:12.232667+00:00"}