{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BU35I7XFTF7YGEEI2VWXCHVCZB","short_pith_number":"pith:BU35I7XF","schema_version":"1.0","canonical_sha256":"0d37d47ee5997f831088d56d711ea2c84a36568233762a2b495033b9613ec679","source":{"kind":"arxiv","id":"2206.08564","version":1},"attestation_state":"computed","paper":{"title":"MET: Masked Encoding for Tabular Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kushal Majmundar, Praneeth Netrapalli, Prateek Jain, Sachin Goyal","submitted_at":"2022-06-17T05:51:10Z","abstract_excerpt":"We consider the task of self-supervised representation learning (SSL) for tabular data: tabular-SSL. Typical contrastive learning based SSL methods require instance-wise data augmentations which are difficult to design for unstructured tabular data. Existing tabular-SSL methods design such augmentations in a relatively ad-hoc fashion and can fail to capture the underlying data manifold. Instead of augmentations based approaches for tabular-SSL, we propose a new reconstruction based method, called Masked Encoding for Tabular Data (MET), that does not require augmentations. MET is based on the p"},"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":"2206.08564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T05:51:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b1f72d9af7a8551bbe20cd5ca0d3ae3fd552ddbb217f48fd00c420d55c16325","abstract_canon_sha256":"827ed48d42505f4f52f0f23d0026e80f378eecb61763c3b723a4fa8d9aee44e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:31.208923Z","signature_b64":"ZzLP69dALQvqr8iztk46LA3H/jo7gRsC93jWzfITg5yv1HyeuJQM4rc8pZ+6I5MKZHB3kc7/AyjlRMWdCUTqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d37d47ee5997f831088d56d711ea2c84a36568233762a2b495033b9613ec679","last_reissued_at":"2026-07-05T04:32:31.208426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:31.208426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MET: Masked Encoding for Tabular Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kushal Majmundar, Praneeth Netrapalli, Prateek Jain, Sachin Goyal","submitted_at":"2022-06-17T05:51:10Z","abstract_excerpt":"We consider the task of self-supervised representation learning (SSL) for tabular data: tabular-SSL. Typical contrastive learning based SSL methods require instance-wise data augmentations which are difficult to design for unstructured tabular data. Existing tabular-SSL methods design such augmentations in a relatively ad-hoc fashion and can fail to capture the underlying data manifold. Instead of augmentations based approaches for tabular-SSL, we propose a new reconstruction based method, called Masked Encoding for Tabular Data (MET), that does not require augmentations. MET is based on the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08564","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/2206.08564/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":"2206.08564","created_at":"2026-07-05T04:32:31.208486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08564v1","created_at":"2026-07-05T04:32:31.208486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08564","created_at":"2026-07-05T04:32:31.208486+00:00"},{"alias_kind":"pith_short_12","alias_value":"BU35I7XFTF7Y","created_at":"2026-07-05T04:32:31.208486+00:00"},{"alias_kind":"pith_short_16","alias_value":"BU35I7XFTF7YGEEI","created_at":"2026-07-05T04:32:31.208486+00:00"},{"alias_kind":"pith_short_8","alias_value":"BU35I7XF","created_at":"2026-07-05T04:32:31.208486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04485","citing_title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB","json":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB.json","graph_json":"https://pith.science/api/pith-number/BU35I7XFTF7YGEEI2VWXCHVCZB/graph.json","events_json":"https://pith.science/api/pith-number/BU35I7XFTF7YGEEI2VWXCHVCZB/events.json","paper":"https://pith.science/paper/BU35I7XF"},"agent_actions":{"view_html":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB","download_json":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB.json","view_paper":"https://pith.science/paper/BU35I7XF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08564&json=true","fetch_graph":"https://pith.science/api/pith-number/BU35I7XFTF7YGEEI2VWXCHVCZB/graph.json","fetch_events":"https://pith.science/api/pith-number/BU35I7XFTF7YGEEI2VWXCHVCZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB/action/storage_attestation","attest_author":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB/action/author_attestation","sign_citation":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB/action/citation_signature","submit_replication":"https://pith.science/pith/BU35I7XFTF7YGEEI2VWXCHVCZB/action/replication_record"}},"created_at":"2026-07-05T04:32:31.208486+00:00","updated_at":"2026-07-05T04:32:31.208486+00:00"}