{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CAALD36E23BM2D5JNOET2ZZIRY","short_pith_number":"pith:CAALD36E","canonical_record":{"source":{"id":"2401.14846","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T13:27:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"209b3628e3656477e139cc66cb3a1b3af648a9c93f29193fd22f297d0e4c311e","abstract_canon_sha256":"7830729b2fa75cadd6e0ad33852b706b12852e2f32563dbf04b372c9433c5945"},"schema_version":"1.0"},"canonical_sha256":"1000b1efc4d6c2cd0fa96b893d67288e167f237d5ef0b1ad6cbd1e6e88e4082c","source":{"kind":"arxiv","id":"2401.14846","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14846","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14846v2","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14846","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"CAALD36E23BM","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"CAALD36E23BM2D5J","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"CAALD36E","created_at":"2026-07-05T07:56:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CAALD36E23BM2D5JNOET2ZZIRY","target":"record","payload":{"canonical_record":{"source":{"id":"2401.14846","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T13:27:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"209b3628e3656477e139cc66cb3a1b3af648a9c93f29193fd22f297d0e4c311e","abstract_canon_sha256":"7830729b2fa75cadd6e0ad33852b706b12852e2f32563dbf04b372c9433c5945"},"schema_version":"1.0"},"canonical_sha256":"1000b1efc4d6c2cd0fa96b893d67288e167f237d5ef0b1ad6cbd1e6e88e4082c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:58.960249Z","signature_b64":"Xb9lQyheSArw0g74Ivfjuoso3XDngKMPin61q3xc8RwxmyqVZQFZ8qLr/PIsLnwoyLH1HCs0WFqX0QZiPjGCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1000b1efc4d6c2cd0fa96b893d67288e167f237d5ef0b1ad6cbd1e6e88e4082c","last_reissued_at":"2026-07-05T07:56:58.959824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:58.959824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.14846","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":"2026-07-05T07:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNkqFS3a/A/Cw7ijgx+fLA+jETWCwWfzQY6nFPKam6ZyiFq0o7LP4+9CTdrqMbu5zTD+X8HMAmkG1Jqfyo7pBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:06:47.295576Z"},"content_sha256":"0a5381137988391cc1b02093344c4c7efed0adc4eb600f8da258696884bef713","schema_version":"1.0","event_id":"sha256:0a5381137988391cc1b02093344c4c7efed0adc4eb600f8da258696884bef713"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CAALD36E23BM2D5JNOET2ZZIRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Domain Generalization: A Noise Robustness Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Rui Qiao","submitted_at":"2024-01-26T13:27:15Z","abstract_excerpt":"Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks. To better understand this phenomenon, we investigate whether there are benefits of DG algorithms over ERM through the lens of label noise. Specifically, our finite-sample analysis reveals that label noise exacerbates the effect of spurious correlations for ERM, undermining generalization. Conversely, we illustrate that DG algorithms exhibit implicit l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14846","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/2401.14846/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":"2026-07-05T07:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wx+ZsMt40T0oAVb0bdKxovnJGW0uo/BKCSE1LQrJrj/376RzY+7cPeBHW+3oD+UENkEq+7sKbdIIQPtb5NbeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:06:47.296080Z"},"content_sha256":"da22936adeec392737de7e8c4587c59b37246f2d8d0a70f7683337fdbeeaedac","schema_version":"1.0","event_id":"sha256:da22936adeec392737de7e8c4587c59b37246f2d8d0a70f7683337fdbeeaedac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CAALD36E23BM2D5JNOET2ZZIRY/bundle.json","state_url":"https://pith.science/pith/CAALD36E23BM2D5JNOET2ZZIRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CAALD36E23BM2D5JNOET2ZZIRY/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":"2026-08-10T11:06:47Z","links":{"resolver":"https://pith.science/pith/CAALD36E23BM2D5JNOET2ZZIRY","bundle":"https://pith.science/pith/CAALD36E23BM2D5JNOET2ZZIRY/bundle.json","state":"https://pith.science/pith/CAALD36E23BM2D5JNOET2ZZIRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CAALD36E23BM2D5JNOET2ZZIRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CAALD36E23BM2D5JNOET2ZZIRY","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":"7830729b2fa75cadd6e0ad33852b706b12852e2f32563dbf04b372c9433c5945","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T13:27:15Z","title_canon_sha256":"209b3628e3656477e139cc66cb3a1b3af648a9c93f29193fd22f297d0e4c311e"},"schema_version":"1.0","source":{"id":"2401.14846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14846","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14846v2","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14846","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"CAALD36E23BM","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"CAALD36E23BM2D5J","created_at":"2026-07-05T07:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"CAALD36E","created_at":"2026-07-05T07:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:da22936adeec392737de7e8c4587c59b37246f2d8d0a70f7683337fdbeeaedac","target":"graph","created_at":"2026-07-05T07:56:58Z","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/2401.14846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks. To better understand this phenomenon, we investigate whether there are benefits of DG algorithms over ERM through the lens of label noise. Specifically, our finite-sample analysis reveals that label noise exacerbates the effect of spurious correlations for ERM, undermining generalization. Conversely, we illustrate that DG algorithms exhibit implicit l","authors_text":"Bryan Kian Hsiang Low, Rui Qiao","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T13:27:15Z","title":"Understanding Domain Generalization: A Noise Robustness Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14846","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":"sha256:0a5381137988391cc1b02093344c4c7efed0adc4eb600f8da258696884bef713","target":"record","created_at":"2026-07-05T07:56:58Z","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":"7830729b2fa75cadd6e0ad33852b706b12852e2f32563dbf04b372c9433c5945","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T13:27:15Z","title_canon_sha256":"209b3628e3656477e139cc66cb3a1b3af648a9c93f29193fd22f297d0e4c311e"},"schema_version":"1.0","source":{"id":"2401.14846","kind":"arxiv","version":2}},"canonical_sha256":"1000b1efc4d6c2cd0fa96b893d67288e167f237d5ef0b1ad6cbd1e6e88e4082c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1000b1efc4d6c2cd0fa96b893d67288e167f237d5ef0b1ad6cbd1e6e88e4082c","first_computed_at":"2026-07-05T07:56:58.959824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:58.959824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xb9lQyheSArw0g74Ivfjuoso3XDngKMPin61q3xc8RwxmyqVZQFZ8qLr/PIsLnwoyLH1HCs0WFqX0QZiPjGCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:58.960249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5381137988391cc1b02093344c4c7efed0adc4eb600f8da258696884bef713","sha256:da22936adeec392737de7e8c4587c59b37246f2d8d0a70f7683337fdbeeaedac"],"state_sha256":"ab213bcf578576ebc7fabd2f2053d0fd9419cf1f8a230c3f17da24a93d3790ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtFOJk0e1PeL58R7Uqq4AsD5D2NKZSPn8BFbwLzw51p4eVtjTJO2buDAORme80v9lK1bttkfY9/hOR6VvzV2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:06:47.300654Z","bundle_sha256":"48cde7311a622e438d137f2fae0724288b944eae8f1d4a4da530348a547ccb8f"}}