{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YFUEQ4EEDCV3GB26WJ7X5EXQLE","short_pith_number":"pith:YFUEQ4EE","schema_version":"1.0","canonical_sha256":"c16848708418abb3075eb27f7e92f059241393d9df80e2cdd27ff6fc340e6e10","source":{"kind":"arxiv","id":"2311.14335","version":1},"attestation_state":"computed","paper":{"title":"Comparative Analysis of Transformers for Modeling Tabular Data: A Casestudy using Industry Scale Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mohit Kumar, Piyush Arora, Salil R. Joshi, Shamika Ganesan, Siddhant Kulkarni, Usneek Singh","submitted_at":"2023-11-24T08:16:39Z","abstract_excerpt":"We perform a comparative analysis of transformer-based models designed for modeling tabular data, specifically on an industry-scale dataset. While earlier studies demonstrated promising outcomes on smaller public or synthetic datasets, the effectiveness did not extend to larger industry-scale datasets. The challenges identified include handling high-dimensional data, the necessity for efficient pre-processing of categorical and numerical features, and addressing substantial computational requirements.\n  To overcome the identified challenges, the study conducts an extensive examination of vario"},"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":"2311.14335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T08:16:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d55686cbb66da9a9b6620fd236049839cf68fa1ae69055afc05d5f268f2e4ab","abstract_canon_sha256":"5522a2cbf3c985ac599101dbb2e8df4b62e5fc880b19e118ebec13cfe496e569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:16.592700Z","signature_b64":"4AU+hYJzV9JpCGvax8kkWGeW2EOvFGME6bXeoSTo8OI7VnZ02bveKItG3uXG0AlLVoAnUQnuu3Rd5iI9p4fwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c16848708418abb3075eb27f7e92f059241393d9df80e2cdd27ff6fc340e6e10","last_reissued_at":"2026-07-05T07:16:16.592120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:16.592120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative Analysis of Transformers for Modeling Tabular Data: A Casestudy using Industry Scale Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mohit Kumar, Piyush Arora, Salil R. Joshi, Shamika Ganesan, Siddhant Kulkarni, Usneek Singh","submitted_at":"2023-11-24T08:16:39Z","abstract_excerpt":"We perform a comparative analysis of transformer-based models designed for modeling tabular data, specifically on an industry-scale dataset. While earlier studies demonstrated promising outcomes on smaller public or synthetic datasets, the effectiveness did not extend to larger industry-scale datasets. The challenges identified include handling high-dimensional data, the necessity for efficient pre-processing of categorical and numerical features, and addressing substantial computational requirements.\n  To overcome the identified challenges, the study conducts an extensive examination of vario"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14335","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/2311.14335/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":"2311.14335","created_at":"2026-07-05T07:16:16.592186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14335v1","created_at":"2026-07-05T07:16:16.592186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14335","created_at":"2026-07-05T07:16:16.592186+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFUEQ4EEDCV3","created_at":"2026-07-05T07:16:16.592186+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFUEQ4EEDCV3GB26","created_at":"2026-07-05T07:16:16.592186+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFUEQ4EE","created_at":"2026-07-05T07:16:16.592186+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/YFUEQ4EEDCV3GB26WJ7X5EXQLE","json":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE.json","graph_json":"https://pith.science/api/pith-number/YFUEQ4EEDCV3GB26WJ7X5EXQLE/graph.json","events_json":"https://pith.science/api/pith-number/YFUEQ4EEDCV3GB26WJ7X5EXQLE/events.json","paper":"https://pith.science/paper/YFUEQ4EE"},"agent_actions":{"view_html":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE","download_json":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE.json","view_paper":"https://pith.science/paper/YFUEQ4EE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14335&json=true","fetch_graph":"https://pith.science/api/pith-number/YFUEQ4EEDCV3GB26WJ7X5EXQLE/graph.json","fetch_events":"https://pith.science/api/pith-number/YFUEQ4EEDCV3GB26WJ7X5EXQLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE/action/storage_attestation","attest_author":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE/action/author_attestation","sign_citation":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE/action/citation_signature","submit_replication":"https://pith.science/pith/YFUEQ4EEDCV3GB26WJ7X5EXQLE/action/replication_record"}},"created_at":"2026-07-05T07:16:16.592186+00:00","updated_at":"2026-07-05T07:16:16.592186+00:00"}