{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CYQ3QSIZFEUPQUVDVOJHFN3DQQ","short_pith_number":"pith:CYQ3QSIZ","canonical_record":{"source":{"id":"2405.13396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T07:13:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c80b49dd5945de93a21f33f94bc9610d2cf0d4afe6a05e0047d3fba943b46f3f","abstract_canon_sha256":"cc2c60dc21e92e8d670fb5a7fba18be8339a08d4fa3989cf0a2246bd5c793344"},"schema_version":"1.0"},"canonical_sha256":"1621b849192928f852a3ab9272b7638422074d35962b0b4885f7c5ee275864fe","source":{"kind":"arxiv","id":"2405.13396","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13396","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13396v2","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13396","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"CYQ3QSIZFEUP","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"CYQ3QSIZFEUPQUVD","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"CYQ3QSIZ","created_at":"2026-07-05T10:04:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CYQ3QSIZFEUPQUVDVOJHFN3DQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.13396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T07:13:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c80b49dd5945de93a21f33f94bc9610d2cf0d4afe6a05e0047d3fba943b46f3f","abstract_canon_sha256":"cc2c60dc21e92e8d670fb5a7fba18be8339a08d4fa3989cf0a2246bd5c793344"},"schema_version":"1.0"},"canonical_sha256":"1621b849192928f852a3ab9272b7638422074d35962b0b4885f7c5ee275864fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:13.299403Z","signature_b64":"zcpr4HuV2vD5VmQG9/GeFSzyLsl/MlfBqQLwmz6KqYYCb5JOOI20INapif89Uc7hLtG/kuwxnicCvomHIAEFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1621b849192928f852a3ab9272b7638422074d35962b0b4885f7c5ee275864fe","last_reissued_at":"2026-07-05T10:04:13.298879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:13.298879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.13396","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":"2026-07-05T10:04:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FFD3kheMxxJ3KnmcdZkzfOXi7EXWXTUrR8wAa+rmi5MC7hgg/4GpUAvbpA1zKm/3usUNkBE4euyzP+G/axKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:24:51.650904Z"},"content_sha256":"190aa5c52adb3ce091574dae0c97a342582cbb098d70b342ddd593e8961a0f65","schema_version":"1.0","event_id":"sha256:190aa5c52adb3ce091574dae0c97a342582cbb098d70b342ddd593e8961a0f65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CYQ3QSIZFEUPQUVDVOJHFN3DQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix den Breejen, Sangmin Bae, Se-Young Yun, Stephen Cha","submitted_at":"2024-05-22T07:13:55Z","abstract_excerpt":"The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fine-tuning setting, resulting in a significant performance boost. We also discover that fine-tuning enables ICL-transformers to create complex decision boundaries, a property regular neural networks do not have. Based on this observation, we propose to pretrain ICL-transformers on a new forest dataset generator which creates datasets that are unrealistic, but have complex decision boundaries. TabForest, the ICL-transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13396","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/2405.13396/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":"2026-07-05T10:04:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzDDdJDx90A6E44RxdKXL9XJos9txSaLDlAkPGVHtz24mHC3D+8SXjX1tMQgX1f31p+szaIpuIJGaLVDaSRuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:24:51.651391Z"},"content_sha256":"1c4ddedfbd148e18ec53e010d64c348a3e1e4e3c36cfcd72de3554daa26acdbe","schema_version":"1.0","event_id":"sha256:1c4ddedfbd148e18ec53e010d64c348a3e1e4e3c36cfcd72de3554daa26acdbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/bundle.json","state_url":"https://pith.science/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/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":"2026-08-15T10:24:51Z","links":{"resolver":"https://pith.science/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ","bundle":"https://pith.science/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/bundle.json","state":"https://pith.science/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYQ3QSIZFEUPQUVDVOJHFN3DQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CYQ3QSIZFEUPQUVDVOJHFN3DQQ","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":"cc2c60dc21e92e8d670fb5a7fba18be8339a08d4fa3989cf0a2246bd5c793344","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T07:13:55Z","title_canon_sha256":"c80b49dd5945de93a21f33f94bc9610d2cf0d4afe6a05e0047d3fba943b46f3f"},"schema_version":"1.0","source":{"id":"2405.13396","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13396","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13396v2","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13396","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"CYQ3QSIZFEUP","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"CYQ3QSIZFEUPQUVD","created_at":"2026-07-05T10:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"CYQ3QSIZ","created_at":"2026-07-05T10:04:13Z"}],"graph_snapshots":[{"event_id":"sha256:1c4ddedfbd148e18ec53e010d64c348a3e1e4e3c36cfcd72de3554daa26acdbe","target":"graph","created_at":"2026-07-05T10:04:13Z","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/2405.13396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fine-tuning setting, resulting in a significant performance boost. We also discover that fine-tuning enables ICL-transformers to create complex decision boundaries, a property regular neural networks do not have. Based on this observation, we propose to pretrain ICL-transformers on a new forest dataset generator which creates datasets that are unrealistic, but have complex decision boundaries. TabForest, the ICL-transf","authors_text":"Felix den Breejen, Sangmin Bae, Se-Young Yun, Stephen Cha","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T07:13:55Z","title":"Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13396","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":"sha256:190aa5c52adb3ce091574dae0c97a342582cbb098d70b342ddd593e8961a0f65","target":"record","created_at":"2026-07-05T10:04:13Z","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":"cc2c60dc21e92e8d670fb5a7fba18be8339a08d4fa3989cf0a2246bd5c793344","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T07:13:55Z","title_canon_sha256":"c80b49dd5945de93a21f33f94bc9610d2cf0d4afe6a05e0047d3fba943b46f3f"},"schema_version":"1.0","source":{"id":"2405.13396","kind":"arxiv","version":2}},"canonical_sha256":"1621b849192928f852a3ab9272b7638422074d35962b0b4885f7c5ee275864fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1621b849192928f852a3ab9272b7638422074d35962b0b4885f7c5ee275864fe","first_computed_at":"2026-07-05T10:04:13.298879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:13.298879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zcpr4HuV2vD5VmQG9/GeFSzyLsl/MlfBqQLwmz6KqYYCb5JOOI20INapif89Uc7hLtG/kuwxnicCvomHIAEFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:13.299403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13396","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:190aa5c52adb3ce091574dae0c97a342582cbb098d70b342ddd593e8961a0f65","sha256:1c4ddedfbd148e18ec53e010d64c348a3e1e4e3c36cfcd72de3554daa26acdbe"],"state_sha256":"6c310ae906fc458f1c2d5942b84fdd719bc3e0931f4da86fa4d4181f45c819ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IkackrZKby33lnxP5tekr6YwCYnfZyYRvCV84oCUMTXob8ReNMc99nxO8hAc4wwZcMaSpvXERnDjWjpuUO1oCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:24:51.655622Z","bundle_sha256":"2559b35bba277ccfe5c00f0bfca02c5c06a01c3004beeb924e4cb15fbaa98bd6"}}