{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GDQ2JXMVY26IWMMNS43D363VMV","short_pith_number":"pith:GDQ2JXMV","canonical_record":{"source":{"id":"2605.26713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T08:54:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b66e44b50538d89d756ae88a14622ee580feaeda2d5827bc0b3805c9ad09104","abstract_canon_sha256":"f3d5342977b8b0c752a5c14e630162f13acc969da993153ec932d4950ba34c33"},"schema_version":"1.0"},"canonical_sha256":"30e1a4dd95c6bc8b318d97363dfb75656d4223936a21cc06e1d1aba209873902","source":{"kind":"arxiv","id":"2605.26713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26713","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26713v1","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26713","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"GDQ2JXMVY26I","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"GDQ2JXMVY26IWMMN","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"GDQ2JXMV","created_at":"2026-05-27T01:06:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GDQ2JXMVY26IWMMNS43D363VMV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T08:54:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b66e44b50538d89d756ae88a14622ee580feaeda2d5827bc0b3805c9ad09104","abstract_canon_sha256":"f3d5342977b8b0c752a5c14e630162f13acc969da993153ec932d4950ba34c33"},"schema_version":"1.0"},"canonical_sha256":"30e1a4dd95c6bc8b318d97363dfb75656d4223936a21cc06e1d1aba209873902","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:08.851969Z","signature_b64":"ZqHMvscp9KawUoNzWR3k7NTF5joNylwO1JnomfC0PsYxfZXxFDODhQQXG8LRs8PThi3qunegxckC8Mfaj4KgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e1a4dd95c6bc8b318d97363dfb75656d4223936a21cc06e1d1aba209873902","last_reissued_at":"2026-05-27T01:06:08.851054Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:08.851054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26713","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKaqJ5iDlgtvg095YVbLysepESHhthDXKY1kTPgLdzZ4Wuqrap8Uou9YAR5xRR8FwkiMH3QgrBtMlzzV72TbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:02:29.675685Z"},"content_sha256":"3a27f1610c16306af445ada5926122b14b94292a2d651cb4afadcfd6b7cae75f","schema_version":"1.0","event_id":"sha256:3a27f1610c16306af445ada5926122b14b94292a2d651cb4afadcfd6b7cae75f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GDQ2JXMVY26IWMMNS43D363VMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers Can Learn Posterior Predictive Distributions In-Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changwoo J. Lee, Gyeonghun Kang, Xiang Cheng","submitted_at":"2026-05-26T08:54:02Z","abstract_excerpt":"Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance and ability to go beyond point predictions, theoretical understandings of the algorithmic capability of transformers to learn distributions in context are still lacking. Focusing on Gaussian process regression problems, we show by construction that transformers can implement a gradient descent algorithm targeting the posterior predictive mean and variance, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26713","kind":"arxiv","version":1},"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/2605.26713/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":"2026-05-27T01:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmRDDLr8sKuoR1gxZgQa5RsoNbua9aQpM/D0WWGCGMZW9usiCxkFdOgsuRC9kGJxu13ReTGw3bcRoc+So7D3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:02:29.676437Z"},"content_sha256":"0c395f8ac24283814c5c649925c6fb6ba439212b0540939517f5c43706fe1e2d","schema_version":"1.0","event_id":"sha256:0c395f8ac24283814c5c649925c6fb6ba439212b0540939517f5c43706fe1e2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDQ2JXMVY26IWMMNS43D363VMV/bundle.json","state_url":"https://pith.science/pith/GDQ2JXMVY26IWMMNS43D363VMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDQ2JXMVY26IWMMNS43D363VMV/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":"2026-06-10T01:02:29Z","links":{"resolver":"https://pith.science/pith/GDQ2JXMVY26IWMMNS43D363VMV","bundle":"https://pith.science/pith/GDQ2JXMVY26IWMMNS43D363VMV/bundle.json","state":"https://pith.science/pith/GDQ2JXMVY26IWMMNS43D363VMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDQ2JXMVY26IWMMNS43D363VMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDQ2JXMVY26IWMMNS43D363VMV","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":"f3d5342977b8b0c752a5c14e630162f13acc969da993153ec932d4950ba34c33","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T08:54:02Z","title_canon_sha256":"7b66e44b50538d89d756ae88a14622ee580feaeda2d5827bc0b3805c9ad09104"},"schema_version":"1.0","source":{"id":"2605.26713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26713","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26713v1","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26713","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"GDQ2JXMVY26I","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"GDQ2JXMVY26IWMMN","created_at":"2026-05-27T01:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"GDQ2JXMV","created_at":"2026-05-27T01:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:0c395f8ac24283814c5c649925c6fb6ba439212b0540939517f5c43706fe1e2d","target":"graph","created_at":"2026-05-27T01:06:08Z","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/2605.26713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance and ability to go beyond point predictions, theoretical understandings of the algorithmic capability of transformers to learn distributions in context are still lacking. Focusing on Gaussian process regression problems, we show by construction that transformers can implement a gradient descent algorithm targeting the posterior predictive mean and variance, f","authors_text":"Changwoo J. Lee, Gyeonghun Kang, Xiang Cheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T08:54:02Z","title":"Transformers Can Learn Posterior Predictive Distributions In-Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26713","kind":"arxiv","version":1},"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":"sha256:3a27f1610c16306af445ada5926122b14b94292a2d651cb4afadcfd6b7cae75f","target":"record","created_at":"2026-05-27T01:06:08Z","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":"f3d5342977b8b0c752a5c14e630162f13acc969da993153ec932d4950ba34c33","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T08:54:02Z","title_canon_sha256":"7b66e44b50538d89d756ae88a14622ee580feaeda2d5827bc0b3805c9ad09104"},"schema_version":"1.0","source":{"id":"2605.26713","kind":"arxiv","version":1}},"canonical_sha256":"30e1a4dd95c6bc8b318d97363dfb75656d4223936a21cc06e1d1aba209873902","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30e1a4dd95c6bc8b318d97363dfb75656d4223936a21cc06e1d1aba209873902","first_computed_at":"2026-05-27T01:06:08.851054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:08.851054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZqHMvscp9KawUoNzWR3k7NTF5joNylwO1JnomfC0PsYxfZXxFDODhQQXG8LRs8PThi3qunegxckC8Mfaj4KgBQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:08.851969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a27f1610c16306af445ada5926122b14b94292a2d651cb4afadcfd6b7cae75f","sha256:0c395f8ac24283814c5c649925c6fb6ba439212b0540939517f5c43706fe1e2d"],"state_sha256":"54dbf7aca0800a2b37480e1dc8139cabded7b2fbcbe8cc538833f46b034803e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJI4KhtIrtFmFGXVX0zDv9gmZK9wjVi9g9Ig36f0WhSUnPmt8J2nIzbKvurL3pgpl4Rf96/zZDV/a4H4TikYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T01:02:29.680385Z","bundle_sha256":"bb16d4dff430f40d1b26eead307102efe3f62c209c49e05ce3904479ad4a0969"}}