{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2OWODLLIWWCHW7VATZUXOIBYED","short_pith_number":"pith:2OWODLLI","canonical_record":{"source":{"id":"2109.04320","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T14:52:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bea3262c5a811f9dbd1a3716ce415ada2204542e420b3e10bbacb1115189c928","abstract_canon_sha256":"66acfdd8e47dbe01b7857d0b70f0484cf92204ef877ec67052ed75a2b1695c7a"},"schema_version":"1.0"},"canonical_sha256":"d3ace1ad68b5847b7ea09e6977203820d1753fcd26f68b8821bdf556d6fa807a","source":{"kind":"arxiv","id":"2109.04320","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04320","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04320v3","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04320","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"2OWODLLIWWCH","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"2OWODLLIWWCHW7VA","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"2OWODLLI","created_at":"2026-07-05T05:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2OWODLLIWWCHW7VATZUXOIBYED","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04320","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T14:52:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bea3262c5a811f9dbd1a3716ce415ada2204542e420b3e10bbacb1115189c928","abstract_canon_sha256":"66acfdd8e47dbe01b7857d0b70f0484cf92204ef877ec67052ed75a2b1695c7a"},"schema_version":"1.0"},"canonical_sha256":"d3ace1ad68b5847b7ea09e6977203820d1753fcd26f68b8821bdf556d6fa807a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:39.522438Z","signature_b64":"FKv8h65oPokmYqLNh6kGCjGLnLDWXbLyLoPbgQtKs+1gflpGfsvYv8oKgBVzCXvorOg2CW+3aAvaN2oA9TMZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ace1ad68b5847b7ea09e6977203820d1753fcd26f68b8821bdf556d6fa807a","last_reissued_at":"2026-07-05T05:02:39.522041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:39.522041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04320","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UhdrHk2dihLUYK8dxLgrWLD/iAnKymYDlkiYWz9rolfzvBmt2LpYj6XNupzdMLZ0Rly2Bkr1JWbLnnG62fh9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:19:40.303357Z"},"content_sha256":"b2f66d481bdc24b8bf31fdcda7c67fa78aff5da1440b39d4ca69bbd84a25545c","schema_version":"1.0","event_id":"sha256:b2f66d481bdc24b8bf31fdcda7c67fa78aff5da1440b39d4ca69bbd84a25545c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2OWODLLIWWCHW7VATZUXOIBYED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Frikha, Denis Krompa{\\ss}, Volker Tresp","submitted_at":"2021-09-09T14:52:05Z","abstract_excerpt":"Machine learning models that can generalize to unseen domains are essential when applied in real-world scenarios involving strong domain shifts. We address the challenging domain generalization (DG) problem, where a model trained on a set of source domains is expected to generalize well in unseen domains without any exposure to their data. The main challenge of DG is that the features learned from the source domains are not necessarily present in the unseen target domains, leading to performance deterioration. We assume that learning a richer set of features is crucial to improve the transfer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04320","kind":"arxiv","version":3},"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/2109.04320/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":"2026-07-05T05:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QReofjVesqdIJLtNaLe76VA2FWRdjz5jirg2wUdRUnMyDzDEBy8CUULB22lgqXRpLBp20yXVF4sMC3QW6MS6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:19:40.303739Z"},"content_sha256":"20dbe6f5108395d54388431d6e8a85a2be51d40b7855870956614a59daee7f3a","schema_version":"1.0","event_id":"sha256:20dbe6f5108395d54388431d6e8a85a2be51d40b7855870956614a59daee7f3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2OWODLLIWWCHW7VATZUXOIBYED/bundle.json","state_url":"https://pith.science/pith/2OWODLLIWWCHW7VATZUXOIBYED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2OWODLLIWWCHW7VATZUXOIBYED/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":"2026-07-06T17:19:40Z","links":{"resolver":"https://pith.science/pith/2OWODLLIWWCHW7VATZUXOIBYED","bundle":"https://pith.science/pith/2OWODLLIWWCHW7VATZUXOIBYED/bundle.json","state":"https://pith.science/pith/2OWODLLIWWCHW7VATZUXOIBYED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2OWODLLIWWCHW7VATZUXOIBYED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2OWODLLIWWCHW7VATZUXOIBYED","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":"66acfdd8e47dbe01b7857d0b70f0484cf92204ef877ec67052ed75a2b1695c7a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T14:52:05Z","title_canon_sha256":"bea3262c5a811f9dbd1a3716ce415ada2204542e420b3e10bbacb1115189c928"},"schema_version":"1.0","source":{"id":"2109.04320","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04320","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04320v3","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04320","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"2OWODLLIWWCH","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"2OWODLLIWWCHW7VA","created_at":"2026-07-05T05:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"2OWODLLI","created_at":"2026-07-05T05:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:20dbe6f5108395d54388431d6e8a85a2be51d40b7855870956614a59daee7f3a","target":"graph","created_at":"2026-07-05T05:02:39Z","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/2109.04320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models that can generalize to unseen domains are essential when applied in real-world scenarios involving strong domain shifts. We address the challenging domain generalization (DG) problem, where a model trained on a set of source domains is expected to generalize well in unseen domains without any exposure to their data. The main challenge of DG is that the features learned from the source domains are not necessarily present in the unseen target domains, leading to performance deterioration. We assume that learning a richer set of features is crucial to improve the transfer ","authors_text":"Ahmed Frikha, Denis Krompa{\\ss}, Volker Tresp","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T14:52:05Z","title":"Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04320","kind":"arxiv","version":3},"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:b2f66d481bdc24b8bf31fdcda7c67fa78aff5da1440b39d4ca69bbd84a25545c","target":"record","created_at":"2026-07-05T05:02:39Z","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":"66acfdd8e47dbe01b7857d0b70f0484cf92204ef877ec67052ed75a2b1695c7a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T14:52:05Z","title_canon_sha256":"bea3262c5a811f9dbd1a3716ce415ada2204542e420b3e10bbacb1115189c928"},"schema_version":"1.0","source":{"id":"2109.04320","kind":"arxiv","version":3}},"canonical_sha256":"d3ace1ad68b5847b7ea09e6977203820d1753fcd26f68b8821bdf556d6fa807a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3ace1ad68b5847b7ea09e6977203820d1753fcd26f68b8821bdf556d6fa807a","first_computed_at":"2026-07-05T05:02:39.522041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:39.522041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FKv8h65oPokmYqLNh6kGCjGLnLDWXbLyLoPbgQtKs+1gflpGfsvYv8oKgBVzCXvorOg2CW+3aAvaN2oA9TMZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:39.522438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04320","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2f66d481bdc24b8bf31fdcda7c67fa78aff5da1440b39d4ca69bbd84a25545c","sha256:20dbe6f5108395d54388431d6e8a85a2be51d40b7855870956614a59daee7f3a"],"state_sha256":"2d44e0b4a121b8d057387242bebde4549f2c8996385c5e3f9bedc717f936b895"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5oFkp4X5ampVMVB0QAuZ+6TF131SUf5VgIiZc6u1VkV2UyTIHAAULQM7Pom4XQ+PrkFPTTmb+8tgKVjbbkbRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:19:40.305655Z","bundle_sha256":"5274f850eada05602a791f23302eba1684f37b522fd446fb0d420705564a4ca2"}}