{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NZGR564B53G45E4K3L5EC4F35","short_pith_number":"pith:6NZGR564","schema_version":"1.0","canonical_sha256":"f37268f7dc0f766e749c56d7d20b85df413288d469f965ab88feeacfbe15afb1","source":{"kind":"arxiv","id":"2403.15790","version":1},"attestation_state":"computed","paper":{"title":"Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2024-03-23T10:37:22Z","abstract_excerpt":"The field of imbalanced self-supervised learning, especially in the context of tabular data, has not been extensively studied. Existing research has predominantly focused on image datasets. This paper aims to fill this gap by examining the specific challenges posed by data imbalance in self-supervised learning in the domain of tabular data, with a primary focus on autoencoders. Autoencoders are widely employed for learning and constructing a new representation of a dataset, particularly for dimensionality reduction. They are also often used for generative model learning, as seen in variational"},"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":"2403.15790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-23T10:37:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ba0d0d464addd17974f3d1fb16addb1928d5438c66cbb2137b926212b0c2b64","abstract_canon_sha256":"a362fdc874981aa7f885e90df595b0814caaf69dddcc11f4397205174ebe7700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:06.355391Z","signature_b64":"QGtSgvsfY+mwNjKHevUYKWL1wCxqopq0X3pWrRt9RQQlS5R5lsZKr/yLv5Rkn1bI6v91jGtExloprsWNQIP7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f37268f7dc0f766e749c56d7d20b85df413288d469f965ab88feeacfbe15afb1","last_reissued_at":"2026-07-05T08:00:06.354828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:06.354828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2024-03-23T10:37:22Z","abstract_excerpt":"The field of imbalanced self-supervised learning, especially in the context of tabular data, has not been extensively studied. Existing research has predominantly focused on image datasets. This paper aims to fill this gap by examining the specific challenges posed by data imbalance in self-supervised learning in the domain of tabular data, with a primary focus on autoencoders. Autoencoders are widely employed for learning and constructing a new representation of a dataset, particularly for dimensionality reduction. They are also often used for generative model learning, as seen in variational"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15790","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/2403.15790/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":"2403.15790","created_at":"2026-07-05T08:00:06.354895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15790v1","created_at":"2026-07-05T08:00:06.354895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15790","created_at":"2026-07-05T08:00:06.354895+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NZGR564B53G","created_at":"2026-07-05T08:00:06.354895+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NZGR564B53G45E4","created_at":"2026-07-05T08:00:06.354895+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NZGR564","created_at":"2026-07-05T08:00:06.354895+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/6NZGR564B53G45E4K3L5EC4F35","json":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35.json","graph_json":"https://pith.science/api/pith-number/6NZGR564B53G45E4K3L5EC4F35/graph.json","events_json":"https://pith.science/api/pith-number/6NZGR564B53G45E4K3L5EC4F35/events.json","paper":"https://pith.science/paper/6NZGR564"},"agent_actions":{"view_html":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35","download_json":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35.json","view_paper":"https://pith.science/paper/6NZGR564","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15790&json=true","fetch_graph":"https://pith.science/api/pith-number/6NZGR564B53G45E4K3L5EC4F35/graph.json","fetch_events":"https://pith.science/api/pith-number/6NZGR564B53G45E4K3L5EC4F35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35/action/storage_attestation","attest_author":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35/action/author_attestation","sign_citation":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35/action/citation_signature","submit_replication":"https://pith.science/pith/6NZGR564B53G45E4K3L5EC4F35/action/replication_record"}},"created_at":"2026-07-05T08:00:06.354895+00:00","updated_at":"2026-07-05T08:00:06.354895+00:00"}