{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RVZNIQ4SRP5X4OKMMZVDUUFTZY","short_pith_number":"pith:RVZNIQ4S","canonical_record":{"source":{"id":"2207.09944","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-07-20T14:41:09Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"0a81cfaa7970ceb8992849643e94df45785ed347da4ccb69f6fcda2b7a4402d6","abstract_canon_sha256":"d909d0d0c79d0741fb5e404c8c40119507711991ba492611e0c2b819c09887f8"},"schema_version":"1.0"},"canonical_sha256":"8d72d443928bfb7e394c666a3a50b3ce1b6c23cd613a745ae924563292c9a22a","source":{"kind":"arxiv","id":"2207.09944","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09944","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09944v4","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09944","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_12","alias_value":"RVZNIQ4SRP5X","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_16","alias_value":"RVZNIQ4SRP5X4OKM","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_8","alias_value":"RVZNIQ4S","created_at":"2026-07-05T06:43:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RVZNIQ4SRP5X4OKMMZVDUUFTZY","target":"record","payload":{"canonical_record":{"source":{"id":"2207.09944","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-07-20T14:41:09Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"0a81cfaa7970ceb8992849643e94df45785ed347da4ccb69f6fcda2b7a4402d6","abstract_canon_sha256":"d909d0d0c79d0741fb5e404c8c40119507711991ba492611e0c2b819c09887f8"},"schema_version":"1.0"},"canonical_sha256":"8d72d443928bfb7e394c666a3a50b3ce1b6c23cd613a745ae924563292c9a22a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:18.945019Z","signature_b64":"zfk/wrFWz8P3u6SJPNGC7oW92blYUEQVVcPzY645aYGxknKioEtLmb1dubnJS9Ve9Pfl4S9kUXx5TO4hJ4eIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d72d443928bfb7e394c666a3a50b3ce1b6c23cd613a745ae924563292c9a22a","last_reissued_at":"2026-07-05T06:43:18.944537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:18.944537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.09944","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qERes+ByFpstbxP8BrmXJ/uyVwmBWu8wgaNdk7f5Z3qlf4o+KlKtdiIWKv+0mLuV95KL8S5ZIs8Jkv/kHC+kDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:39:55.218178Z"},"content_sha256":"53dcdec3c0443367806ad93c854ee268bf1fda852e515cc8070980f7f069a8ad","schema_version":"1.0","event_id":"sha256:53dcdec3c0443367806ad93c854ee268bf1fda852e515cc8070980f7f069a8ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RVZNIQ4SRP5X4OKMMZVDUUFTZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probable Domain Generalization via Quantile Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Robey, Bernhard Sch\\\"olkopf, Cian Eastwood, George J. Pappas, Hamed Hassani, Julius von K\\\"ugelgen, Shashank Singh","submitted_at":"2022-07-20T14:41:09Z","abstract_excerpt":"Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To achieve this, DG is commonly formulated as an average- or worst-case problem over the set of possible domains. However, predictors that perform well on average lack robustness while predictors that perform well in the worst case tend to be overly-conservative. To address this, we propose a new probabilistic framework for DG where the goal is to learn predictors that perform well with high probability. Our key idea is th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09944","kind":"arxiv","version":4},"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/2207.09944/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":"2026-07-05T06:43:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l8BtxWc1tO1lhm5MixDm/R7FjDNKZzMCSsNqTGQOhMl/DGyRyJ1qfwXz0SDlckey2ztSFYxdq8633vwFWpx+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:39:55.218570Z"},"content_sha256":"35d9b535d6b774416873ef4835f02d8c4681dcd4bd0ff86b1f7b779fc7a775a2","schema_version":"1.0","event_id":"sha256:35d9b535d6b774416873ef4835f02d8c4681dcd4bd0ff86b1f7b779fc7a775a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/bundle.json","state_url":"https://pith.science/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/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":"2026-07-07T11:39:55Z","links":{"resolver":"https://pith.science/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY","bundle":"https://pith.science/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/bundle.json","state":"https://pith.science/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVZNIQ4SRP5X4OKMMZVDUUFTZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RVZNIQ4SRP5X4OKMMZVDUUFTZY","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":"d909d0d0c79d0741fb5e404c8c40119507711991ba492611e0c2b819c09887f8","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-07-20T14:41:09Z","title_canon_sha256":"0a81cfaa7970ceb8992849643e94df45785ed347da4ccb69f6fcda2b7a4402d6"},"schema_version":"1.0","source":{"id":"2207.09944","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09944","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09944v4","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09944","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_12","alias_value":"RVZNIQ4SRP5X","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_16","alias_value":"RVZNIQ4SRP5X4OKM","created_at":"2026-07-05T06:43:18Z"},{"alias_kind":"pith_short_8","alias_value":"RVZNIQ4S","created_at":"2026-07-05T06:43:18Z"}],"graph_snapshots":[{"event_id":"sha256:35d9b535d6b774416873ef4835f02d8c4681dcd4bd0ff86b1f7b779fc7a775a2","target":"graph","created_at":"2026-07-05T06:43:18Z","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/2207.09944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To achieve this, DG is commonly formulated as an average- or worst-case problem over the set of possible domains. However, predictors that perform well on average lack robustness while predictors that perform well in the worst case tend to be overly-conservative. To address this, we propose a new probabilistic framework for DG where the goal is to learn predictors that perform well with high probability. Our key idea is th","authors_text":"Alexander Robey, Bernhard Sch\\\"olkopf, Cian Eastwood, George J. Pappas, Hamed Hassani, Julius von K\\\"ugelgen, Shashank Singh","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-07-20T14:41:09Z","title":"Probable Domain Generalization via Quantile Risk Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09944","kind":"arxiv","version":4},"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":"sha256:53dcdec3c0443367806ad93c854ee268bf1fda852e515cc8070980f7f069a8ad","target":"record","created_at":"2026-07-05T06:43:18Z","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":"d909d0d0c79d0741fb5e404c8c40119507711991ba492611e0c2b819c09887f8","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-07-20T14:41:09Z","title_canon_sha256":"0a81cfaa7970ceb8992849643e94df45785ed347da4ccb69f6fcda2b7a4402d6"},"schema_version":"1.0","source":{"id":"2207.09944","kind":"arxiv","version":4}},"canonical_sha256":"8d72d443928bfb7e394c666a3a50b3ce1b6c23cd613a745ae924563292c9a22a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d72d443928bfb7e394c666a3a50b3ce1b6c23cd613a745ae924563292c9a22a","first_computed_at":"2026-07-05T06:43:18.944537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:18.944537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfk/wrFWz8P3u6SJPNGC7oW92blYUEQVVcPzY645aYGxknKioEtLmb1dubnJS9Ve9Pfl4S9kUXx5TO4hJ4eIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:18.945019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.09944","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53dcdec3c0443367806ad93c854ee268bf1fda852e515cc8070980f7f069a8ad","sha256:35d9b535d6b774416873ef4835f02d8c4681dcd4bd0ff86b1f7b779fc7a775a2"],"state_sha256":"b50c1e6ee524cd8d15b0313b3f0d61b0b61bdb70964be849790f0b8c67f9f8cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mP4k0msXK95t/B8QkH1QhU7kUjsUBLp2gxqZ7aI5GofncSsHuWlLxozn4YcGz0lGdb6y/+iHT29m2Q6tblYgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:39:55.220491Z","bundle_sha256":"abc71a80ab9756e0c1379007999c17c6d7a27d35b0789158953712e7e9607b10"}}