{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ECKOID2B22ZGXZRAOIQODKOQCO","short_pith_number":"pith:ECKOID2B","canonical_record":{"source":{"id":"2110.04361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:11:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5acdcb271c9228d2303b3863f555cebb4c09ba5e5b55dc48639e85f38be51e23","abstract_canon_sha256":"dde054ad1557f2a6662362aa219a01e08e967d177b8fd2bf4bd4c758449048de"},"schema_version":"1.0"},"canonical_sha256":"2094e40f41d6b26be6207220e1a9d013974ef5b5e11958adaadc086d5da3b7bd","source":{"kind":"arxiv","id":"2110.04361","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04361","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04361v2","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04361","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"ECKOID2B22ZG","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"ECKOID2B22ZGXZRA","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"ECKOID2B","created_at":"2026-07-05T03:26:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ECKOID2B22ZGXZRAOIQODKOQCO","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:11:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5acdcb271c9228d2303b3863f555cebb4c09ba5e5b55dc48639e85f38be51e23","abstract_canon_sha256":"dde054ad1557f2a6662362aa219a01e08e967d177b8fd2bf4bd4c758449048de"},"schema_version":"1.0"},"canonical_sha256":"2094e40f41d6b26be6207220e1a9d013974ef5b5e11958adaadc086d5da3b7bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:21.017180Z","signature_b64":"SGdmGZ9uZEw79N1cuzUha0Tl5aTYIcX+iqsH7zhNrQFWZSuOU5FUDnVgM8UQa6oxEC4pAx8zea37nMM/fw6IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2094e40f41d6b26be6207220e1a9d013974ef5b5e11958adaadc086d5da3b7bd","last_reissued_at":"2026-07-05T03:26:21.016724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:21.016724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04361","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tc42LH6kRMVhl/ai+ov3+hbShiXHRqXEjntz7gSLhq48nF76jrp5AsWqz8GSlyZm+T7+n0MyTPZ6W4qK2l0vCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:09:41.084663Z"},"content_sha256":"7211655335415b36392b6fdba338c280a26050502181cdf6cb43cb083ec3ab98","schema_version":"1.0","event_id":"sha256:7211655335415b36392b6fdba338c280a26050502181cdf6cb43cb083ec3ab98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ECKOID2B22ZGXZRAOIQODKOQCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ehsan Hajiramezanali, Lindsay Edwards, Talip Ucar","submitted_at":"2021-10-08T20:11:09Z","abstract_excerpt":"Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of spatial, temporal, or semantic structure in the data through augmentation. However, such structure may not exist in tabular datasets commonly used in fields such as healthcare, making it difficult to design an effective augmentation method, and hindering a similar progress in tabular data setting. In this paper, we introduce a new framework, Subsetting features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04361","kind":"arxiv","version":2},"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/2110.04361/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":"2026-07-05T03:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++P6Ln7Jee/gb14fmny801ACYy4/nMjVtoJzw02Z9OqjeTo9E24WG7RZGh9eIu0xV7DQCUUgpp0P2Ye0Ynw+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:09:41.085257Z"},"content_sha256":"1c52e56bd9f0d1ccf9a651f327a8c9429d4c491a8d0d75d4069fe96aca88f472","schema_version":"1.0","event_id":"sha256:1c52e56bd9f0d1ccf9a651f327a8c9429d4c491a8d0d75d4069fe96aca88f472"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECKOID2B22ZGXZRAOIQODKOQCO/bundle.json","state_url":"https://pith.science/pith/ECKOID2B22ZGXZRAOIQODKOQCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECKOID2B22ZGXZRAOIQODKOQCO/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":"2026-08-21T23:09:41Z","links":{"resolver":"https://pith.science/pith/ECKOID2B22ZGXZRAOIQODKOQCO","bundle":"https://pith.science/pith/ECKOID2B22ZGXZRAOIQODKOQCO/bundle.json","state":"https://pith.science/pith/ECKOID2B22ZGXZRAOIQODKOQCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECKOID2B22ZGXZRAOIQODKOQCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ECKOID2B22ZGXZRAOIQODKOQCO","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":"dde054ad1557f2a6662362aa219a01e08e967d177b8fd2bf4bd4c758449048de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:11:09Z","title_canon_sha256":"5acdcb271c9228d2303b3863f555cebb4c09ba5e5b55dc48639e85f38be51e23"},"schema_version":"1.0","source":{"id":"2110.04361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04361","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04361v2","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04361","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"ECKOID2B22ZG","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"ECKOID2B22ZGXZRA","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"ECKOID2B","created_at":"2026-07-05T03:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:1c52e56bd9f0d1ccf9a651f327a8c9429d4c491a8d0d75d4069fe96aca88f472","target":"graph","created_at":"2026-07-05T03:26:21Z","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/2110.04361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of spatial, temporal, or semantic structure in the data through augmentation. However, such structure may not exist in tabular datasets commonly used in fields such as healthcare, making it difficult to design an effective augmentation method, and hindering a similar progress in tabular data setting. In this paper, we introduce a new framework, Subsetting features","authors_text":"Ehsan Hajiramezanali, Lindsay Edwards, Talip Ucar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:11:09Z","title":"SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04361","kind":"arxiv","version":2},"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":"sha256:7211655335415b36392b6fdba338c280a26050502181cdf6cb43cb083ec3ab98","target":"record","created_at":"2026-07-05T03:26:21Z","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":"dde054ad1557f2a6662362aa219a01e08e967d177b8fd2bf4bd4c758449048de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:11:09Z","title_canon_sha256":"5acdcb271c9228d2303b3863f555cebb4c09ba5e5b55dc48639e85f38be51e23"},"schema_version":"1.0","source":{"id":"2110.04361","kind":"arxiv","version":2}},"canonical_sha256":"2094e40f41d6b26be6207220e1a9d013974ef5b5e11958adaadc086d5da3b7bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2094e40f41d6b26be6207220e1a9d013974ef5b5e11958adaadc086d5da3b7bd","first_computed_at":"2026-07-05T03:26:21.016724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:21.016724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGdmGZ9uZEw79N1cuzUha0Tl5aTYIcX+iqsH7zhNrQFWZSuOU5FUDnVgM8UQa6oxEC4pAx8zea37nMM/fw6IBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:21.017180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7211655335415b36392b6fdba338c280a26050502181cdf6cb43cb083ec3ab98","sha256:1c52e56bd9f0d1ccf9a651f327a8c9429d4c491a8d0d75d4069fe96aca88f472"],"state_sha256":"c0fdf6ee0b1ed9e8abe966c7db61b51dab9c988660e65b48452daf8db2ac9de2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jhg/SFhQAeCM4dua6hDB5skfd68MJMGjrc8OhVVJSHn5LTZuYQSFkhJUTDhzI6Atm485ng7jtwQkO1FfrvjFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T23:09:41.088864Z","bundle_sha256":"afb34c8f18fc8cd65ed1e914dca989dd47dca4c4f020fd571cf56313a2f28efa"}}