{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XOCHYLDH6CVNLFY6YXDB7IBSHR","short_pith_number":"pith:XOCHYLDH","canonical_record":{"source":{"id":"2602.15136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-16T19:29:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"56660222c8dc9482423846d60fba6619cfaf6b19973def41e6974cc70cec2947","abstract_canon_sha256":"2831a08628e878bab0a1ff22940da2beeaa63526899ddd1e650d3703ab868f95"},"schema_version":"1.0"},"canonical_sha256":"bb847c2c67f0aad5971ec5c61fa0323c5219117cf75e13c9ea1fe1ec52d12f0e","source":{"kind":"arxiv","id":"2602.15136","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.15136","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.15136v2","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15136","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"XOCHYLDH6CVN","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"XOCHYLDH6CVNLFY6","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"XOCHYLDH","created_at":"2026-06-23T03:13:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XOCHYLDH6CVNLFY6YXDB7IBSHR","target":"record","payload":{"canonical_record":{"source":{"id":"2602.15136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-16T19:29:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"56660222c8dc9482423846d60fba6619cfaf6b19973def41e6974cc70cec2947","abstract_canon_sha256":"2831a08628e878bab0a1ff22940da2beeaa63526899ddd1e650d3703ab868f95"},"schema_version":"1.0"},"canonical_sha256":"bb847c2c67f0aad5971ec5c61fa0323c5219117cf75e13c9ea1fe1ec52d12f0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.488439Z","signature_b64":"vSEEKXRkhbBflsC/QKh7I12/0hiCLz0IQblM7nA028cIgI7tghoKw64AiqIHT2ZwF4CTBap25bdlD0h38CJMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb847c2c67f0aad5971ec5c61fa0323c5219117cf75e13c9ea1fe1ec52d12f0e","last_reissued_at":"2026-06-23T03:13:54.487947Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.487947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.15136","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":"2026-06-23T03:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25Xn4l0/3PpA1qZiRbUlQyF8M61LBycddTnTO7MHJHtd4yQTPLcedlOKiWWyXswaT4RaMbDmYt3TW1qRRkK0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:47:37.318267Z"},"content_sha256":"b5865348aa9d41019eed99fccabfce9ed5e7914042323c32bfd532fbbf99d936","schema_version":"1.0","event_id":"sha256:b5865348aa9d41019eed99fccabfce9ed5e7914042323c32bfd532fbbf99d936"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XOCHYLDH6CVNLFY6YXDB7IBSHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anzo Teh, Nick Cannella, Yanjun Han, Yury Polyanskiy","submitted_at":"2026-02-16T19:29:27Z","abstract_excerpt":"We theoretically justify the recent empirical finding of [Teh et al., 2025] that a transformer pretrained on synthetically generated data achieves strong performance on empirical Bayes (EB) problems. We take an indirect approach to this question: rather than analyzing the model architecture or training dynamics, we ask why a pretrained Bayes estimator, trained under a prespecified training distribution, can adapt to arbitrary test distributions. Focusing on Poisson EB problems, we identify the existence of universal priors such that training under these priors yields a near-optimal regret boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15136","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/2602.15136/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":"2026-06-23T03:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TEezos1rCqSmxN9FqhAz0N9XdZBatW72fp9szJLQmi/gy65I/plZRc44K4LBMQZZ5aW8W9iTRTmhX3DvIpI1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:47:37.318651Z"},"content_sha256":"d2f735ed87551742519e23e597b2517e33d5ff66d80c3c1ace359a8aebc2aa63","schema_version":"1.0","event_id":"sha256:d2f735ed87551742519e23e597b2517e33d5ff66d80c3c1ace359a8aebc2aa63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/bundle.json","state_url":"https://pith.science/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/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":"2026-07-04T19:47:37Z","links":{"resolver":"https://pith.science/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR","bundle":"https://pith.science/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/bundle.json","state":"https://pith.science/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOCHYLDH6CVNLFY6YXDB7IBSHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XOCHYLDH6CVNLFY6YXDB7IBSHR","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":"2831a08628e878bab0a1ff22940da2beeaa63526899ddd1e650d3703ab868f95","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-16T19:29:27Z","title_canon_sha256":"56660222c8dc9482423846d60fba6619cfaf6b19973def41e6974cc70cec2947"},"schema_version":"1.0","source":{"id":"2602.15136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.15136","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.15136v2","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15136","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"XOCHYLDH6CVN","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"XOCHYLDH6CVNLFY6","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"XOCHYLDH","created_at":"2026-06-23T03:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:d2f735ed87551742519e23e597b2517e33d5ff66d80c3c1ace359a8aebc2aa63","target":"graph","created_at":"2026-06-23T03:13:54Z","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/2602.15136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We theoretically justify the recent empirical finding of [Teh et al., 2025] that a transformer pretrained on synthetically generated data achieves strong performance on empirical Bayes (EB) problems. We take an indirect approach to this question: rather than analyzing the model architecture or training dynamics, we ask why a pretrained Bayes estimator, trained under a prespecified training distribution, can adapt to arbitrary test distributions. Focusing on Poisson EB problems, we identify the existence of universal priors such that training under these priors yields a near-optimal regret boun","authors_text":"Anzo Teh, Nick Cannella, Yanjun Han, Yury Polyanskiy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15136","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:b5865348aa9d41019eed99fccabfce9ed5e7914042323c32bfd532fbbf99d936","target":"record","created_at":"2026-06-23T03:13:54Z","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":"2831a08628e878bab0a1ff22940da2beeaa63526899ddd1e650d3703ab868f95","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-16T19:29:27Z","title_canon_sha256":"56660222c8dc9482423846d60fba6619cfaf6b19973def41e6974cc70cec2947"},"schema_version":"1.0","source":{"id":"2602.15136","kind":"arxiv","version":2}},"canonical_sha256":"bb847c2c67f0aad5971ec5c61fa0323c5219117cf75e13c9ea1fe1ec52d12f0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb847c2c67f0aad5971ec5c61fa0323c5219117cf75e13c9ea1fe1ec52d12f0e","first_computed_at":"2026-06-23T03:13:54.487947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:54.487947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vSEEKXRkhbBflsC/QKh7I12/0hiCLz0IQblM7nA028cIgI7tghoKw64AiqIHT2ZwF4CTBap25bdlD0h38CJMCA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:54.488439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.15136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5865348aa9d41019eed99fccabfce9ed5e7914042323c32bfd532fbbf99d936","sha256:d2f735ed87551742519e23e597b2517e33d5ff66d80c3c1ace359a8aebc2aa63"],"state_sha256":"d76863ac7ef354ddf3c9378dc0a701608bde12d92a4b919e9c45b567bb11a50f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmghjDns0+aHbN6iXA8klVq3QePLubPhKoO7UykmZUYkSI98j6MWLyFnaN5jLYbnxLwfTa3kpyUntyMNK/1GCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T19:47:37.320701Z","bundle_sha256":"e82371b1c77219bf56e53f5ccfdae5ad1869e0c382a1abb51b53b9aa256d31fb"}}