{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BEWMTYWDGZFLABUDGJW2U5Z44I","short_pith_number":"pith:BEWMTYWD","canonical_record":{"source":{"id":"2509.00326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"eabddd9340cdb3a8a1f3a7a414f1cab5af486dfc8b4b1909b343f3c1fbb010e7","abstract_canon_sha256":"854f60d5a1daf4d6a85cbedc49ef670eaa8c224a46fa699539b257eb00a640dc"},"schema_version":"1.0"},"canonical_sha256":"092cc9e2c3364ab00683326daa773ce22df3e46686dec2219eada645ada72406","source":{"kind":"arxiv","id":"2509.00326","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00326","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00326v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00326","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"BEWMTYWDGZFL","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"BEWMTYWDGZFLABUD","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"BEWMTYWD","created_at":"2026-06-02T02:04:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BEWMTYWDGZFLABUDGJW2U5Z44I","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"eabddd9340cdb3a8a1f3a7a414f1cab5af486dfc8b4b1909b343f3c1fbb010e7","abstract_canon_sha256":"854f60d5a1daf4d6a85cbedc49ef670eaa8c224a46fa699539b257eb00a640dc"},"schema_version":"1.0"},"canonical_sha256":"092cc9e2c3364ab00683326daa773ce22df3e46686dec2219eada645ada72406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:08.442244Z","signature_b64":"ZUmwvyeFe1zEJhC2Mn3x2zgiQQPI05tGvMUpwVTKpZdiCSm8gFq/G+JBOxrYzgWPbhGCCcOvihhz9KJLJTNTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092cc9e2c3364ab00683326daa773ce22df3e46686dec2219eada645ada72406","last_reissued_at":"2026-06-02T02:04:08.441468Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:08.441468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00326","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":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ol+Qvxpz35v4Toq2FdTAu5lflBmGt7AoapEYt+iNuW7Vwa21dUU+iMKX+MHyBr0gxl2SoAgv8oy+jljYvVNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:40:11.276985Z"},"content_sha256":"67d9af61ce0c3bbb6a3c2fd6dd4414ba269a3e0c6dcd53c13654fca47e3585a3","schema_version":"1.0","event_id":"sha256:67d9af61ce0c3bbb6a3c2fd6dd4414ba269a3e0c6dcd53c13654fca47e3585a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BEWMTYWDGZFLABUDGJW2U5Z44I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Renat Sergazinov, Shao-An Yin","submitted_at":"2025-08-30T02:57:01Z","abstract_excerpt":"TabPFN v2 achieves better results than tree-based models on several tabular benchmarks, which is notable since tree-based models are usually the strongest choice for tabular data. However, it cannot handle more than 10K context tokens because transformers have quadratic computation and memory costs.\n  Unlike existing approaches that rely on context compression, such as selecting representative samples via K-nearest neighbors (KNN), we introduce a tiled-block strategy to compute attention within the TabPFN framework. This design is compatible with standard GPU setups and, to the best of our kno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00326","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/2509.00326/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":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZTabcb88Q9WlKT35qzibz3h/re58vbNgUIoYSGPsIKx5ejjrn/BVSTBcRTQ1pF7C527HGhfZOZ/qqPI0IxPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:40:11.277719Z"},"content_sha256":"506d82bf64170e0a5f2eb74bfbc41d74991bd980fc1324230d4377c6c8fac0ff","schema_version":"1.0","event_id":"sha256:506d82bf64170e0a5f2eb74bfbc41d74991bd980fc1324230d4377c6c8fac0ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/bundle.json","state_url":"https://pith.science/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/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":"2026-06-08T16:40:11Z","links":{"resolver":"https://pith.science/pith/BEWMTYWDGZFLABUDGJW2U5Z44I","bundle":"https://pith.science/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/bundle.json","state":"https://pith.science/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BEWMTYWDGZFLABUDGJW2U5Z44I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BEWMTYWDGZFLABUDGJW2U5Z44I","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":"854f60d5a1daf4d6a85cbedc49ef670eaa8c224a46fa699539b257eb00a640dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:57:01Z","title_canon_sha256":"eabddd9340cdb3a8a1f3a7a414f1cab5af486dfc8b4b1909b343f3c1fbb010e7"},"schema_version":"1.0","source":{"id":"2509.00326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00326","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00326v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00326","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"BEWMTYWDGZFL","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"BEWMTYWDGZFLABUD","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"BEWMTYWD","created_at":"2026-06-02T02:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:506d82bf64170e0a5f2eb74bfbc41d74991bd980fc1324230d4377c6c8fac0ff","target":"graph","created_at":"2026-06-02T02:04:08Z","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/2509.00326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"TabPFN v2 achieves better results than tree-based models on several tabular benchmarks, which is notable since tree-based models are usually the strongest choice for tabular data. However, it cannot handle more than 10K context tokens because transformers have quadratic computation and memory costs.\n  Unlike existing approaches that rely on context compression, such as selecting representative samples via K-nearest neighbors (KNN), we introduce a tiled-block strategy to compute attention within the TabPFN framework. This design is compatible with standard GPU setups and, to the best of our kno","authors_text":"Renat Sergazinov, Shao-An Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:57:01Z","title":"Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00326","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":"sha256:67d9af61ce0c3bbb6a3c2fd6dd4414ba269a3e0c6dcd53c13654fca47e3585a3","target":"record","created_at":"2026-06-02T02:04:08Z","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":"854f60d5a1daf4d6a85cbedc49ef670eaa8c224a46fa699539b257eb00a640dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:57:01Z","title_canon_sha256":"eabddd9340cdb3a8a1f3a7a414f1cab5af486dfc8b4b1909b343f3c1fbb010e7"},"schema_version":"1.0","source":{"id":"2509.00326","kind":"arxiv","version":2}},"canonical_sha256":"092cc9e2c3364ab00683326daa773ce22df3e46686dec2219eada645ada72406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"092cc9e2c3364ab00683326daa773ce22df3e46686dec2219eada645ada72406","first_computed_at":"2026-06-02T02:04:08.441468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:08.441468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZUmwvyeFe1zEJhC2Mn3x2zgiQQPI05tGvMUpwVTKpZdiCSm8gFq/G+JBOxrYzgWPbhGCCcOvihhz9KJLJTNTBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:08.442244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67d9af61ce0c3bbb6a3c2fd6dd4414ba269a3e0c6dcd53c13654fca47e3585a3","sha256:506d82bf64170e0a5f2eb74bfbc41d74991bd980fc1324230d4377c6c8fac0ff"],"state_sha256":"048a1997462a9fed99fc9a0f4559c4891d16e0c2e3259a45004a13aa1ff661d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1O54mDeeg9ZEVrWXpNyIbxJ5lJCrmAenYRb3uW9wPXQ0W9l3Rxb0nDeShLTMHGSYiiv9RlIOWQBcOcmvT11CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T16:40:11.281058Z","bundle_sha256":"844e2b9d10c8ebdc3eb22e3b82d7ac9292041de75a1f7cb8db2ceafe1ec2672f"}}