{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2F7YXMRGIMCMRMUK42E6CZDHYC","short_pith_number":"pith:2F7YXMRG","canonical_record":{"source":{"id":"2608.00632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:40:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a029a6a1dba9bb824f1e4a17b4489b45bb9af14d7f9c9e535a2dccc82cf2277a","abstract_canon_sha256":"cd32030a058004a14c80e187b959ae2b1a22ee65b7aae422f257b4b537b996bf"},"schema_version":"1.0"},"canonical_sha256":"d17f8bb2264304c8b28ae689e16467c096a7456a83d8bfacb141f84d9dc8a358","source":{"kind":"arxiv","id":"2608.00632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00632","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00632v1","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00632","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"2F7YXMRGIMCM","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"2F7YXMRGIMCMRMUK","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"2F7YXMRG","created_at":"2026-08-04T00:38:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2F7YXMRGIMCMRMUK42E6CZDHYC","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:40:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a029a6a1dba9bb824f1e4a17b4489b45bb9af14d7f9c9e535a2dccc82cf2277a","abstract_canon_sha256":"cd32030a058004a14c80e187b959ae2b1a22ee65b7aae422f257b4b537b996bf"},"schema_version":"1.0"},"canonical_sha256":"d17f8bb2264304c8b28ae689e16467c096a7456a83d8bfacb141f84d9dc8a358","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:38:08.055299Z","signature_b64":"2UHQPSwFpwPBFUm71uj974CS1zjPDiK6oXoufYAfFi3t7I+2ofgBPQXSk+QG1Sq2bj50xFribKchU6hWO3TFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17f8bb2264304c8b28ae689e16467c096a7456a83d8bfacb141f84d9dc8a358","last_reissued_at":"2026-08-04T00:38:08.053968Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:38:08.053968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00632","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":"2026-08-04T00:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEng/x37dvNAnLnJMBfpBoQC4hRFo+ojtcIKYg0Vv/a3HCbzYwhcslVSG3LuDiZZAw/RGx9X//Zw4cAwR5VGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:28:58.450358Z"},"content_sha256":"e27c9f1256afdfc3662335346d08903c2c1bc92d5446384eebd722757fba27bb","schema_version":"1.0","event_id":"sha256:e27c9f1256afdfc3662335346d08903c2c1bc92d5446384eebd722757fba27bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2F7YXMRGIMCMRMUK42E6CZDHYC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning the Pareto Frontier of Predictive Models under Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiwei Zhao, Yang Young Lu, Yiming Dong","submitted_at":"2026-08-01T12:40:52Z","abstract_excerpt":"Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks. These pretrained models can differ not only in performance but also in how they can be used: some only provide black-box predictions, while others may permit white-box access to internal representations that can be probed or fine-tuned. When deployed to the target domain in the presence of distribution shift, no single strategy, including zero-shot application, fine-tuning, or directly training a target-specific model, is uniformly the best.\n  In this work, we propose Fronti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00632","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/2608.00632/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":"2026-08-04T00:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pbTcS6X8cXGgT/2cESYvNXt406Es17ebT/Z9TkTyy3Lf6SMdcQkvZlHYQEsI6DtiFupyywhmBW8w3tf3uMYDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:28:58.450890Z"},"content_sha256":"aad50c6b4a6fde77dde98a87d6471b3428193423e94368ac6a24ec5ff1240019","schema_version":"1.0","event_id":"sha256:aad50c6b4a6fde77dde98a87d6471b3428193423e94368ac6a24ec5ff1240019"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/bundle.json","state_url":"https://pith.science/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/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":"2026-08-07T09:28:58Z","links":{"resolver":"https://pith.science/pith/2F7YXMRGIMCMRMUK42E6CZDHYC","bundle":"https://pith.science/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/bundle.json","state":"https://pith.science/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2F7YXMRGIMCMRMUK42E6CZDHYC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2F7YXMRGIMCMRMUK42E6CZDHYC","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":"cd32030a058004a14c80e187b959ae2b1a22ee65b7aae422f257b4b537b996bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:40:52Z","title_canon_sha256":"a029a6a1dba9bb824f1e4a17b4489b45bb9af14d7f9c9e535a2dccc82cf2277a"},"schema_version":"1.0","source":{"id":"2608.00632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00632","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00632v1","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00632","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"2F7YXMRGIMCM","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"2F7YXMRGIMCMRMUK","created_at":"2026-08-04T00:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"2F7YXMRG","created_at":"2026-08-04T00:38:08Z"}],"graph_snapshots":[{"event_id":"sha256:aad50c6b4a6fde77dde98a87d6471b3428193423e94368ac6a24ec5ff1240019","target":"graph","created_at":"2026-08-04T00:38:08Z","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/2608.00632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks. These pretrained models can differ not only in performance but also in how they can be used: some only provide black-box predictions, while others may permit white-box access to internal representations that can be probed or fine-tuned. When deployed to the target domain in the presence of distribution shift, no single strategy, including zero-shot application, fine-tuning, or directly training a target-specific model, is uniformly the best.\n  In this work, we propose Fronti","authors_text":"Jiwei Zhao, Yang Young Lu, Yiming Dong","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:40:52Z","title":"Learning the Pareto Frontier of Predictive Models under Distribution Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00632","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:e27c9f1256afdfc3662335346d08903c2c1bc92d5446384eebd722757fba27bb","target":"record","created_at":"2026-08-04T00:38:08Z","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":"cd32030a058004a14c80e187b959ae2b1a22ee65b7aae422f257b4b537b996bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:40:52Z","title_canon_sha256":"a029a6a1dba9bb824f1e4a17b4489b45bb9af14d7f9c9e535a2dccc82cf2277a"},"schema_version":"1.0","source":{"id":"2608.00632","kind":"arxiv","version":1}},"canonical_sha256":"d17f8bb2264304c8b28ae689e16467c096a7456a83d8bfacb141f84d9dc8a358","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d17f8bb2264304c8b28ae689e16467c096a7456a83d8bfacb141f84d9dc8a358","first_computed_at":"2026-08-04T00:38:08.053968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:38:08.053968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2UHQPSwFpwPBFUm71uj974CS1zjPDiK6oXoufYAfFi3t7I+2ofgBPQXSk+QG1Sq2bj50xFribKchU6hWO3TFAg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:38:08.055299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e27c9f1256afdfc3662335346d08903c2c1bc92d5446384eebd722757fba27bb","sha256:aad50c6b4a6fde77dde98a87d6471b3428193423e94368ac6a24ec5ff1240019"],"state_sha256":"4e73dae999edfe53ad155d15b1150c731e11721c87ad0b3bb8adfee4f8abef96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F58YUPec1Eal3Dp+xvZ6xhEtKYo+EGVmmuDhNVLDPFKtbWVBa70OIC0vb+lJv1GB055JZQap9I/Jbt4ufuQkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:28:58.455556Z","bundle_sha256":"f81f3343eca2638854646a208f9bbaf723ab25296e5b3d35f109466120110f2a"}}