{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3YOMG66B6BXHV6WTDH7NEVU2NC","short_pith_number":"pith:3YOMG66B","canonical_record":{"source":{"id":"2402.16785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:00:29Z","cross_cats_sorted":[],"title_canon_sha256":"b08d2e66b6812e29a47f144f30bb5a11ae736d90e705dfed40a36ee93e790eb2","abstract_canon_sha256":"13dc5422192cb6a2c88eae3da7802f2a74767a84e9d94c271f36d69b1e8fc917"},"schema_version":"1.0"},"canonical_sha256":"de1cc37bc1f06e7afad319fed2569a688dc0f4f52267143065906b9cb424c660","source":{"kind":"arxiv","id":"2402.16785","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16785","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16785v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16785","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"3YOMG66B6BXH","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"3YOMG66B6BXHV6WT","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"3YOMG66B","created_at":"2026-07-05T08:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3YOMG66B6BXHV6WTDH7NEVU2NC","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:00:29Z","cross_cats_sorted":[],"title_canon_sha256":"b08d2e66b6812e29a47f144f30bb5a11ae736d90e705dfed40a36ee93e790eb2","abstract_canon_sha256":"13dc5422192cb6a2c88eae3da7802f2a74767a84e9d94c271f36d69b1e8fc917"},"schema_version":"1.0"},"canonical_sha256":"de1cc37bc1f06e7afad319fed2569a688dc0f4f52267143065906b9cb424c660","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:32.443514Z","signature_b64":"agQtUMJmmbh6cYH+gp7Eq61vY5eJpiieEOt1qRAWhChpj8ZIdK6QIOB6kF94sOqe5xpPEatWgbJuEkIA2LVLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de1cc37bc1f06e7afad319fed2569a688dc0f4f52267143065906b9cb424c660","last_reissued_at":"2026-07-05T08:25:32.443079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:32.443079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16785","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":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XomrYbV3wXrE9d5gJYHcdUXLpJEM5pjVOMNu5gQeFIh3SmDyg1arA1QoafiKGMsqKkSDRof/LeNLiy7NYkwdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:01:58.474150Z"},"content_sha256":"b4c4bb0462b4fb93c752d0a57671938814d338d62438dbcf064503cc35731908","schema_version":"1.0","event_id":"sha256:b4c4bb0462b4fb93c752d0a57671938814d338d62438dbcf064503cc35731908"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3YOMG66B6BXHV6WTDH7NEVU2NC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CARTE: Pretraining and Transfer for Tabular Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ga\\\"el Varoquaux, L\\'eo Grinsztajn, Myung Jun Kim","submitted_at":"2024-02-26T18:00:29Z","abstract_excerpt":"Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding correspondences, correspondences in the entries (entity matching) where different words may denote the same entity, correspondences across columns (schema matching), which may come in different orders, names... We propose a neural architecture that does not need such correspondences. As a result, we can pretrain it on background data that has not been matched. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16785","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/2402.16785/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":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mu80RV4zyaSpLgIx05QRgjJ/WT0G7XBIePVty/8NtyA6Fkve1/+MEzrmySzL+XvVxyYTK4BGOfaD68U8FDO3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:01:58.474672Z"},"content_sha256":"d790e47ef769a9a185a6cdb9ba7f7da513dec513fa383a0598ec0a58d08f491d","schema_version":"1.0","event_id":"sha256:d790e47ef769a9a185a6cdb9ba7f7da513dec513fa383a0598ec0a58d08f491d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/bundle.json","state_url":"https://pith.science/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/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":"2026-08-21T12:01:58Z","links":{"resolver":"https://pith.science/pith/3YOMG66B6BXHV6WTDH7NEVU2NC","bundle":"https://pith.science/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/bundle.json","state":"https://pith.science/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YOMG66B6BXHV6WTDH7NEVU2NC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YOMG66B6BXHV6WTDH7NEVU2NC","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":"13dc5422192cb6a2c88eae3da7802f2a74767a84e9d94c271f36d69b1e8fc917","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:00:29Z","title_canon_sha256":"b08d2e66b6812e29a47f144f30bb5a11ae736d90e705dfed40a36ee93e790eb2"},"schema_version":"1.0","source":{"id":"2402.16785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16785","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16785v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16785","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"3YOMG66B6BXH","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"3YOMG66B6BXHV6WT","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"3YOMG66B","created_at":"2026-07-05T08:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:d790e47ef769a9a185a6cdb9ba7f7da513dec513fa383a0598ec0a58d08f491d","target":"graph","created_at":"2026-07-05T08:25:32Z","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/2402.16785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding correspondences, correspondences in the entries (entity matching) where different words may denote the same entity, correspondences across columns (schema matching), which may come in different orders, names... We propose a neural architecture that does not need such correspondences. As a result, we can pretrain it on background data that has not been matched. Th","authors_text":"Ga\\\"el Varoquaux, L\\'eo Grinsztajn, Myung Jun Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:00:29Z","title":"CARTE: Pretraining and Transfer for Tabular Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16785","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:b4c4bb0462b4fb93c752d0a57671938814d338d62438dbcf064503cc35731908","target":"record","created_at":"2026-07-05T08:25:32Z","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":"13dc5422192cb6a2c88eae3da7802f2a74767a84e9d94c271f36d69b1e8fc917","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:00:29Z","title_canon_sha256":"b08d2e66b6812e29a47f144f30bb5a11ae736d90e705dfed40a36ee93e790eb2"},"schema_version":"1.0","source":{"id":"2402.16785","kind":"arxiv","version":2}},"canonical_sha256":"de1cc37bc1f06e7afad319fed2569a688dc0f4f52267143065906b9cb424c660","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de1cc37bc1f06e7afad319fed2569a688dc0f4f52267143065906b9cb424c660","first_computed_at":"2026-07-05T08:25:32.443079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:32.443079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"agQtUMJmmbh6cYH+gp7Eq61vY5eJpiieEOt1qRAWhChpj8ZIdK6QIOB6kF94sOqe5xpPEatWgbJuEkIA2LVLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:32.443514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4c4bb0462b4fb93c752d0a57671938814d338d62438dbcf064503cc35731908","sha256:d790e47ef769a9a185a6cdb9ba7f7da513dec513fa383a0598ec0a58d08f491d"],"state_sha256":"3f91824858f28b21ec8bdb9a0f7226ac586b2e52d0f86d6e6a9665d117b5f257"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dUeMGZYS8bMxJS7Oh7gJophGS0fpExeesLkgwN2oGknfyfQVEnbKxzQRqDJJcQiFvQCantxkfawNv95415aCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T12:01:58.483132Z","bundle_sha256":"7d278d5dbf8fa917eb343401972b2a859bb1413fbfc724485409c54deac0a0b7"}}