{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4ZA2TEKB5CUHCVZLUTP3P6NNKD","short_pith_number":"pith:4ZA2TEKB","canonical_record":{"source":{"id":"2303.05506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T18:57:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"462fd28ad7a53ae5b519d9eab2bf7a7d252a933efa60b772027df12dc13c4d20","abstract_canon_sha256":"5eb525fe0f1fc06fd2cb31424a1424f25e3ac76aa5e48d6a3933798a991306b5"},"schema_version":"1.0"},"canonical_sha256":"e641a99141e8a871572ba4dfb7f9ad50ea9e288eaa9bff11456b3ac583a6b2f9","source":{"kind":"arxiv","id":"2303.05506","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05506","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05506v1","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05506","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"4ZA2TEKB5CUH","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"4ZA2TEKB5CUHCVZL","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"4ZA2TEKB","created_at":"2026-07-05T05:49:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4ZA2TEKB5CUHCVZLUTP3P6NNKD","target":"record","payload":{"canonical_record":{"source":{"id":"2303.05506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T18:57:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"462fd28ad7a53ae5b519d9eab2bf7a7d252a933efa60b772027df12dc13c4d20","abstract_canon_sha256":"5eb525fe0f1fc06fd2cb31424a1424f25e3ac76aa5e48d6a3933798a991306b5"},"schema_version":"1.0"},"canonical_sha256":"e641a99141e8a871572ba4dfb7f9ad50ea9e288eaa9bff11456b3ac583a6b2f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:41.850382Z","signature_b64":"a19z2EsPmsoEjB+y1SfZmaEsR8pvg0fCigfSBBu4/VdHhHnLjqM6TlbbJ/FFD6L0P79wymhB0IAhjGVUHMV9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e641a99141e8a871572ba4dfb7f9ad50ea9e288eaa9bff11456b3ac583a6b2f9","last_reissued_at":"2026-07-05T05:49:41.849923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:41.849923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.05506","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B4sn6INWb8tHmM1CZuXMiW+y4DP4/H+FCKp1odHSKWAFVKJiXAXMmJE8Pngt3cbfdHhg+5CVRy3v4RPGM6ycBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:14:14.753794Z"},"content_sha256":"c6da687d72df5300ae9f2fe621436ebb23d5a2ed9809ce7c289a5a4dc2b91a10","schema_version":"1.0","event_id":"sha256:c6da687d72df5300ae9f2fe621436ebb23d5a2ed9809ce7c289a5a4dc2b91a10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4ZA2TEKB5CUHCVZLUTP3P6NNKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Jeffares, Fergus Imrie, Jonathan Crabb\\'e, Mihaela van der Schaar, Tennison Liu","submitted_at":"2023-03-09T18:57:13Z","abstract_excerpt":"Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on various forms of regularization to prevent overfitting and provide strong generalization performance. Existing regularization techniques include broad modelling decisions such as choice of architecture, loss functions, and optimization methods. In this work, we introduce Tabular Neural Gradient Orthogonalization and Specialization (TANGOS), a novel framework for regularization in the tabular setting built on latent uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05506","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/2303.05506/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FoxL4im6CP3IrK6btJQK30kPlq8PibjutAv5YOVN6R6xhsumVQowgCXiY37YbMyrJiff1AFgXBBBMSUr6tD8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:14:14.754174Z"},"content_sha256":"02caf480804fc46b3155d8884b74f2b944ec7ce68d1a7e66e03cf0206619bceb","schema_version":"1.0","event_id":"sha256:02caf480804fc46b3155d8884b74f2b944ec7ce68d1a7e66e03cf0206619bceb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/bundle.json","state_url":"https://pith.science/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T06:14:14Z","links":{"resolver":"https://pith.science/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD","bundle":"https://pith.science/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/bundle.json","state":"https://pith.science/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZA2TEKB5CUHCVZLUTP3P6NNKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4ZA2TEKB5CUHCVZLUTP3P6NNKD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5eb525fe0f1fc06fd2cb31424a1424f25e3ac76aa5e48d6a3933798a991306b5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T18:57:13Z","title_canon_sha256":"462fd28ad7a53ae5b519d9eab2bf7a7d252a933efa60b772027df12dc13c4d20"},"schema_version":"1.0","source":{"id":"2303.05506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05506","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05506v1","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05506","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"4ZA2TEKB5CUH","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"4ZA2TEKB5CUHCVZL","created_at":"2026-07-05T05:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"4ZA2TEKB","created_at":"2026-07-05T05:49:41Z"}],"graph_snapshots":[{"event_id":"sha256:02caf480804fc46b3155d8884b74f2b944ec7ce68d1a7e66e03cf0206619bceb","target":"graph","created_at":"2026-07-05T05:49:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.05506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on various forms of regularization to prevent overfitting and provide strong generalization performance. Existing regularization techniques include broad modelling decisions such as choice of architecture, loss functions, and optimization methods. In this work, we introduce Tabular Neural Gradient Orthogonalization and Specialization (TANGOS), a novel framework for regularization in the tabular setting built on latent uni","authors_text":"Alan Jeffares, Fergus Imrie, Jonathan Crabb\\'e, Mihaela van der Schaar, Tennison Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T18:57:13Z","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05506","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c6da687d72df5300ae9f2fe621436ebb23d5a2ed9809ce7c289a5a4dc2b91a10","target":"record","created_at":"2026-07-05T05:49:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5eb525fe0f1fc06fd2cb31424a1424f25e3ac76aa5e48d6a3933798a991306b5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T18:57:13Z","title_canon_sha256":"462fd28ad7a53ae5b519d9eab2bf7a7d252a933efa60b772027df12dc13c4d20"},"schema_version":"1.0","source":{"id":"2303.05506","kind":"arxiv","version":1}},"canonical_sha256":"e641a99141e8a871572ba4dfb7f9ad50ea9e288eaa9bff11456b3ac583a6b2f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e641a99141e8a871572ba4dfb7f9ad50ea9e288eaa9bff11456b3ac583a6b2f9","first_computed_at":"2026-07-05T05:49:41.849923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:41.849923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a19z2EsPmsoEjB+y1SfZmaEsR8pvg0fCigfSBBu4/VdHhHnLjqM6TlbbJ/FFD6L0P79wymhB0IAhjGVUHMV9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:41.850382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6da687d72df5300ae9f2fe621436ebb23d5a2ed9809ce7c289a5a4dc2b91a10","sha256:02caf480804fc46b3155d8884b74f2b944ec7ce68d1a7e66e03cf0206619bceb"],"state_sha256":"5b95549253ef9347a8e7c7b44b5b98520a164fb2684936a9903fb30d0016e902"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYsCAmkPOw24nHxElfcP26fbqcSvSlOJPt4wn3nVztQUCPSFeuHK5DEhA0SqsaPJm1ITj3DjI0vu++zb5JhvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:14:14.756248Z","bundle_sha256":"9b790e2fe9dacfb07c1e726dec9dbbad0b7d4273005b7d81ffa879d64c37f5b6"}}