{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RKVLTAGRNON6NNHU5LV76JH4HR","short_pith_number":"pith:RKVLTAGR","canonical_record":{"source":{"id":"2311.00055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T18:03:54Z","cross_cats_sorted":[],"title_canon_sha256":"60106bedee7b4925822ce50fb01c81ab1dcaa25195e7bf273b77c6f15de2f91d","abstract_canon_sha256":"edb24b2f7d4f713574e7fe2636ca3aad9fea98d3b1c9252c1ceb793c7e891464"},"schema_version":"1.0"},"canonical_sha256":"8aaab980d16b9be6b4f4eaebff24fc3c76da117cf9e04e2f29e0ac2469452d2e","source":{"kind":"arxiv","id":"2311.00055","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00055","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00055v2","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00055","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"RKVLTAGRNON6","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"RKVLTAGRNON6NNHU","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"RKVLTAGR","created_at":"2026-07-05T10:12:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RKVLTAGRNON6NNHU5LV76JH4HR","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T18:03:54Z","cross_cats_sorted":[],"title_canon_sha256":"60106bedee7b4925822ce50fb01c81ab1dcaa25195e7bf273b77c6f15de2f91d","abstract_canon_sha256":"edb24b2f7d4f713574e7fe2636ca3aad9fea98d3b1c9252c1ceb793c7e891464"},"schema_version":"1.0"},"canonical_sha256":"8aaab980d16b9be6b4f4eaebff24fc3c76da117cf9e04e2f29e0ac2469452d2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:57.130182Z","signature_b64":"0jPS3PO4Ws/59b9lQCStsvUdqV9YrCBwHtMz2Ch5cCSfp6CJPc5Q239s5/L84nju6vgjaFRGrlLrAtMip1mcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aaab980d16b9be6b4f4eaebff24fc3c76da117cf9e04e2f29e0ac2469452d2e","last_reissued_at":"2026-07-05T10:12:57.129683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:57.129683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00055","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":"2026-07-05T10:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1hWyh3ZhC+6zAu4SV5iCtE+tPA8nUa9zcbuWbO1eJ+XwQlYUBUgL4+B315oyIxJBcRnXgp9RP0rkzm1NLuPyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:00:05.253538Z"},"content_sha256":"4c97e8a3282e781605731e0ea38d6ad414c72848739ae9f448b37ee1def9978f","schema_version":"1.0","event_id":"sha256:4c97e8a3282e781605731e0ea38d6ad414c72848739ae9f448b37ee1def9978f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RKVLTAGRNON6NNHU5LV76JH4HR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Huai-Hong Yin, Qi-Le Zhou, Wei-Lun Chao","submitted_at":"2023-10-31T18:03:54Z","abstract_excerpt":"Pre-training is prevalent in deep learning for vision and text data, leveraging knowledge from other datasets to enhance downstream tasks. However, for tabular data, the inherent heterogeneity in attribute and label spaces across datasets complicates the learning of shareable knowledge. We propose Tabular data Pre-Training via Meta-representation (TabPTM), aiming to pre-train a general tabular model over diverse datasets. The core idea is to embed data instances into a shared feature space, where each instance is represented by its distance to a fixed number of nearest neighbors and their labe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00055","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/2311.00055/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":"2026-07-05T10:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfHRKx2JVQVaoYlRpQvBDSGMud/YUaWKDVyfKl5iporz7pInmPvee/H3z4+s0tUhRYqQnyIxQUYN9BALnSCMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:00:05.254047Z"},"content_sha256":"4f7608e6790bf9971b0c541445158b9a8471d6e490b91b849b9f097a50ac6ca4","schema_version":"1.0","event_id":"sha256:4f7608e6790bf9971b0c541445158b9a8471d6e490b91b849b9f097a50ac6ca4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKVLTAGRNON6NNHU5LV76JH4HR/bundle.json","state_url":"https://pith.science/pith/RKVLTAGRNON6NNHU5LV76JH4HR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKVLTAGRNON6NNHU5LV76JH4HR/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":"2026-08-15T12:00:05Z","links":{"resolver":"https://pith.science/pith/RKVLTAGRNON6NNHU5LV76JH4HR","bundle":"https://pith.science/pith/RKVLTAGRNON6NNHU5LV76JH4HR/bundle.json","state":"https://pith.science/pith/RKVLTAGRNON6NNHU5LV76JH4HR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKVLTAGRNON6NNHU5LV76JH4HR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RKVLTAGRNON6NNHU5LV76JH4HR","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":"edb24b2f7d4f713574e7fe2636ca3aad9fea98d3b1c9252c1ceb793c7e891464","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T18:03:54Z","title_canon_sha256":"60106bedee7b4925822ce50fb01c81ab1dcaa25195e7bf273b77c6f15de2f91d"},"schema_version":"1.0","source":{"id":"2311.00055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00055","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00055v2","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00055","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"RKVLTAGRNON6","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"RKVLTAGRNON6NNHU","created_at":"2026-07-05T10:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"RKVLTAGR","created_at":"2026-07-05T10:12:57Z"}],"graph_snapshots":[{"event_id":"sha256:4f7608e6790bf9971b0c541445158b9a8471d6e490b91b849b9f097a50ac6ca4","target":"graph","created_at":"2026-07-05T10:12:57Z","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/2311.00055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training is prevalent in deep learning for vision and text data, leveraging knowledge from other datasets to enhance downstream tasks. However, for tabular data, the inherent heterogeneity in attribute and label spaces across datasets complicates the learning of shareable knowledge. We propose Tabular data Pre-Training via Meta-representation (TabPTM), aiming to pre-train a general tabular model over diverse datasets. The core idea is to embed data instances into a shared feature space, where each instance is represented by its distance to a fixed number of nearest neighbors and their labe","authors_text":"De-Chuan Zhan, Han-Jia Ye, Huai-Hong Yin, Qi-Le Zhou, Wei-Lun Chao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T18:03:54Z","title":"Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00055","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":"sha256:4c97e8a3282e781605731e0ea38d6ad414c72848739ae9f448b37ee1def9978f","target":"record","created_at":"2026-07-05T10:12:57Z","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":"edb24b2f7d4f713574e7fe2636ca3aad9fea98d3b1c9252c1ceb793c7e891464","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T18:03:54Z","title_canon_sha256":"60106bedee7b4925822ce50fb01c81ab1dcaa25195e7bf273b77c6f15de2f91d"},"schema_version":"1.0","source":{"id":"2311.00055","kind":"arxiv","version":2}},"canonical_sha256":"8aaab980d16b9be6b4f4eaebff24fc3c76da117cf9e04e2f29e0ac2469452d2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aaab980d16b9be6b4f4eaebff24fc3c76da117cf9e04e2f29e0ac2469452d2e","first_computed_at":"2026-07-05T10:12:57.129683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:57.129683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0jPS3PO4Ws/59b9lQCStsvUdqV9YrCBwHtMz2Ch5cCSfp6CJPc5Q239s5/L84nju6vgjaFRGrlLrAtMip1mcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:57.130182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c97e8a3282e781605731e0ea38d6ad414c72848739ae9f448b37ee1def9978f","sha256:4f7608e6790bf9971b0c541445158b9a8471d6e490b91b849b9f097a50ac6ca4"],"state_sha256":"68c1821a2c105f5fbbecfcc546455f70f282a83eaad09608a434fed734748011"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKWK7Xs14IdFT35RmX3k5/uv81gaYLBNVTG5lUHoWy0nq61Q+amMNNtivMYoHMZCg4+U3HIN3JaFLGJr9zumAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T12:00:05.257736Z","bundle_sha256":"7183d9d19ed8dd726b55447cba892ca3c781b5448ce05a60975f1a6cc96a4ee8"}}