{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XPBFZN456WGVU2JIHYDDFJ3W5Q","short_pith_number":"pith:XPBFZN45","canonical_record":{"source":{"id":"2207.03208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T10:29:31Z","cross_cats_sorted":[],"title_canon_sha256":"ba2fd0451d8c772af29e293511385fd17f639fbf643ec9cc682c4ba4c38a2cfa","abstract_canon_sha256":"92d6635b4dfb4cff8de40085e02f3e3a26ebd2bab83d1b415446d0dedcc996c2"},"schema_version":"1.0"},"canonical_sha256":"bbc25cb79df58d5a69283e0632a776ec0738373fbb66c3c633afc2fce0a5a3e8","source":{"kind":"arxiv","id":"2207.03208","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.03208","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2207.03208v2","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03208","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"XPBFZN456WGV","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"XPBFZN456WGVU2JI","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"XPBFZN45","created_at":"2026-07-05T04:39:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XPBFZN456WGVU2JIHYDDFJ3W5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2207.03208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T10:29:31Z","cross_cats_sorted":[],"title_canon_sha256":"ba2fd0451d8c772af29e293511385fd17f639fbf643ec9cc682c4ba4c38a2cfa","abstract_canon_sha256":"92d6635b4dfb4cff8de40085e02f3e3a26ebd2bab83d1b415446d0dedcc996c2"},"schema_version":"1.0"},"canonical_sha256":"bbc25cb79df58d5a69283e0632a776ec0738373fbb66c3c633afc2fce0a5a3e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:40.227872Z","signature_b64":"/XG8CO9XPLusYdTmUI5AAQyM5pcAYWzDY3k8isXXuU7h1rAcXl/gv/PtDUY2hpyC9lRMTLrp58TWO/Iy6uv6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc25cb79df58d5a69283e0632a776ec0738373fbb66c3c633afc2fce0a5a3e8","last_reissued_at":"2026-07-05T04:39:40.227471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:40.227471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.03208","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":"2026-07-05T04:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KbuT8+7bQ+BhIdhIqQkpZh4fQrvXYlaM367+0SE+jdi2YkScds+LHY+HaR6hpX/wyr4HyIeLd3VMCkTKFyNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:04.691698Z"},"content_sha256":"031099e2b0b395c8ca63e3bf90b93fded3bb7cee53c3cbff348a42f245f035c9","schema_version":"1.0","event_id":"sha256:031099e2b0b395c8ca63e3bf90b93fded3bb7cee53c3cbff348a42f245f035c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XPBFZN456WGVU2JIHYDDFJ3W5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Pretraining Objectives for Tabular Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Alekberov, Artem Babenko, Ivan Rubachev, Yury Gorishniy","submitted_at":"2022-07-07T10:29:31Z","abstract_excerpt":"Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from pretraining, which is a workhorse of DL for vision and NLP. For tabular problems, several pretraining methods were proposed, but it is not entirely clear if pretraining provides consistent noticeable improvements and what method should be used, since the methods are often not compared to each other or comparison is limited to the simplest MLP architectures.\n  In this work, we aim to identify the best practices to pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03208","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/2207.03208/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":"2026-07-05T04:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjAiypywU9Mf7eLwB/ve69kRgMkMOomOwrichod9C1dHteYu/5Ov9O/Nrrq4oK30WEbv6x/+Q8F/I2XHp1mtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:04.692074Z"},"content_sha256":"434db277ec31f9a2da9eecf58f0946e0c6da2f468be9053bb87e5b646d6b3298","schema_version":"1.0","event_id":"sha256:434db277ec31f9a2da9eecf58f0946e0c6da2f468be9053bb87e5b646d6b3298"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/bundle.json","state_url":"https://pith.science/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/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":"2026-07-08T19:12:04Z","links":{"resolver":"https://pith.science/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q","bundle":"https://pith.science/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/bundle.json","state":"https://pith.science/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPBFZN456WGVU2JIHYDDFJ3W5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XPBFZN456WGVU2JIHYDDFJ3W5Q","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":"92d6635b4dfb4cff8de40085e02f3e3a26ebd2bab83d1b415446d0dedcc996c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T10:29:31Z","title_canon_sha256":"ba2fd0451d8c772af29e293511385fd17f639fbf643ec9cc682c4ba4c38a2cfa"},"schema_version":"1.0","source":{"id":"2207.03208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.03208","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2207.03208v2","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03208","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"XPBFZN456WGV","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"XPBFZN456WGVU2JI","created_at":"2026-07-05T04:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"XPBFZN45","created_at":"2026-07-05T04:39:40Z"}],"graph_snapshots":[{"event_id":"sha256:434db277ec31f9a2da9eecf58f0946e0c6da2f468be9053bb87e5b646d6b3298","target":"graph","created_at":"2026-07-05T04:39:40Z","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/2207.03208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from pretraining, which is a workhorse of DL for vision and NLP. For tabular problems, several pretraining methods were proposed, but it is not entirely clear if pretraining provides consistent noticeable improvements and what method should be used, since the methods are often not compared to each other or comparison is limited to the simplest MLP architectures.\n  In this work, we aim to identify the best practices to pr","authors_text":"Artem Alekberov, Artem Babenko, Ivan Rubachev, Yury Gorishniy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T10:29:31Z","title":"Revisiting Pretraining Objectives for Tabular Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03208","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":"sha256:031099e2b0b395c8ca63e3bf90b93fded3bb7cee53c3cbff348a42f245f035c9","target":"record","created_at":"2026-07-05T04:39:40Z","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":"92d6635b4dfb4cff8de40085e02f3e3a26ebd2bab83d1b415446d0dedcc996c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T10:29:31Z","title_canon_sha256":"ba2fd0451d8c772af29e293511385fd17f639fbf643ec9cc682c4ba4c38a2cfa"},"schema_version":"1.0","source":{"id":"2207.03208","kind":"arxiv","version":2}},"canonical_sha256":"bbc25cb79df58d5a69283e0632a776ec0738373fbb66c3c633afc2fce0a5a3e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbc25cb79df58d5a69283e0632a776ec0738373fbb66c3c633afc2fce0a5a3e8","first_computed_at":"2026-07-05T04:39:40.227471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:40.227471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/XG8CO9XPLusYdTmUI5AAQyM5pcAYWzDY3k8isXXuU7h1rAcXl/gv/PtDUY2hpyC9lRMTLrp58TWO/Iy6uv6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:40.227872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.03208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:031099e2b0b395c8ca63e3bf90b93fded3bb7cee53c3cbff348a42f245f035c9","sha256:434db277ec31f9a2da9eecf58f0946e0c6da2f468be9053bb87e5b646d6b3298"],"state_sha256":"bee3e66a274625189b3a919aa81c54994130e6bf82d083fd8457c7edbad2fffb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pk7BGkVp4UirHC2zFtfgEEy178BrSuxDUMXuIW9a+bGLHPWG58/7nwnw3q/dy+9eIlAwKOdPbRjzpXJYGWK+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:12:04.694282Z","bundle_sha256":"2da3b75e85879f858a0ded5b91386dbfe070685cb1b037c0eb5a586003add646"}}