{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YC4TVNKAZ424DNMT2L55ZLOOCL","short_pith_number":"pith:YC4TVNKA","canonical_record":{"source":{"id":"2102.05082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T19:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"46f27cb829b931ad0d6143a78fb4e416aeabc8b999322243d44ee87daf817709","abstract_canon_sha256":"0f75528c62832ecf242cb3f4814db9cd85e6b1b26048cba4096ca67a9100111e"},"schema_version":"1.0"},"canonical_sha256":"c0b93ab540cf35c1b593d2fbdcadce12ccdb402d70ceb06f45b764906fad2d8c","source":{"kind":"arxiv","id":"2102.05082","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05082","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05082v3","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05082","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_12","alias_value":"YC4TVNKAZ424","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_16","alias_value":"YC4TVNKAZ424DNMT","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_8","alias_value":"YC4TVNKA","created_at":"2026-07-05T03:56:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YC4TVNKAZ424DNMT2L55ZLOOCL","target":"record","payload":{"canonical_record":{"source":{"id":"2102.05082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T19:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"46f27cb829b931ad0d6143a78fb4e416aeabc8b999322243d44ee87daf817709","abstract_canon_sha256":"0f75528c62832ecf242cb3f4814db9cd85e6b1b26048cba4096ca67a9100111e"},"schema_version":"1.0"},"canonical_sha256":"c0b93ab540cf35c1b593d2fbdcadce12ccdb402d70ceb06f45b764906fad2d8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:45.744105Z","signature_b64":"8Oug87aYFOWHvO1gF+pNvgugUuytDN1+9LiN3Q8kOQrqL232gK6OoaaO3qi+GM7V+lWPvsetPQTx5QfOc487Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0b93ab540cf35c1b593d2fbdcadce12ccdb402d70ceb06f45b764906fad2d8c","last_reissued_at":"2026-07-05T03:56:45.743520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:45.743520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.05082","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":"2026-07-05T03:56:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAZCZHILjGRfmIC7Oy4Ke77OasR5jer3hBCa6FrRJMzQlCcAIc/jbA2FpkMpRIao0vtuDyBn+etzOVmmDmJ4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T10:32:28.446872Z"},"content_sha256":"e85d6839bcbd3b3dcae232b75822d2be247eec5c1d837c9b9af3b7848d0f0fbf","schema_version":"1.0","event_id":"sha256:e85d6839bcbd3b3dcae232b75822d2be247eec5c1d837c9b9af3b7848d0f0fbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YC4TVNKAZ424DNMT2L55ZLOOCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain Invariant Representation Learning with Domain Density Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"At{\\i}l{\\i}m G\\\"une\\c{s} Baydin, A. Tuan Nguyen, Toan Tran, Yarin Gal","submitted_at":"2021-02-09T19:25:32Z","abstract_excerpt":"Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, since the information learned by that model might be domain-specific and generalize imperfectly to target domains. To tackle this problem, a predominant approach is to find and learn some domain-invariant information in order to use it for the prediction task. In this paper, we propose a theoretically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05082","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/2102.05082/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":"2026-07-05T03:56:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bY8ZK2IQP1iYfvt99zyFxEleuucIO5jxaH9Eg67sGshn1MOwozAJRpMRyKf+EI5bJaA4+Yj96j86tPbCQ94uBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T10:32:28.447247Z"},"content_sha256":"1f3f522759dc45ce19a8528d990959f60c14f2649643f6830417ff64a0eb2d2d","schema_version":"1.0","event_id":"sha256:1f3f522759dc45ce19a8528d990959f60c14f2649643f6830417ff64a0eb2d2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/bundle.json","state_url":"https://pith.science/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/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":"2026-07-21T10:32:28Z","links":{"resolver":"https://pith.science/pith/YC4TVNKAZ424DNMT2L55ZLOOCL","bundle":"https://pith.science/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/bundle.json","state":"https://pith.science/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YC4TVNKAZ424DNMT2L55ZLOOCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YC4TVNKAZ424DNMT2L55ZLOOCL","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":"0f75528c62832ecf242cb3f4814db9cd85e6b1b26048cba4096ca67a9100111e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T19:25:32Z","title_canon_sha256":"46f27cb829b931ad0d6143a78fb4e416aeabc8b999322243d44ee87daf817709"},"schema_version":"1.0","source":{"id":"2102.05082","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05082","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05082v3","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05082","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_12","alias_value":"YC4TVNKAZ424","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_16","alias_value":"YC4TVNKAZ424DNMT","created_at":"2026-07-05T03:56:45Z"},{"alias_kind":"pith_short_8","alias_value":"YC4TVNKA","created_at":"2026-07-05T03:56:45Z"}],"graph_snapshots":[{"event_id":"sha256:1f3f522759dc45ce19a8528d990959f60c14f2649643f6830417ff64a0eb2d2d","target":"graph","created_at":"2026-07-05T03:56:45Z","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/2102.05082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, since the information learned by that model might be domain-specific and generalize imperfectly to target domains. To tackle this problem, a predominant approach is to find and learn some domain-invariant information in order to use it for the prediction task. In this paper, we propose a theoretically ","authors_text":"At{\\i}l{\\i}m G\\\"une\\c{s} Baydin, A. Tuan Nguyen, Toan Tran, Yarin Gal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T19:25:32Z","title":"Domain Invariant Representation Learning with Domain Density Transformations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05082","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:e85d6839bcbd3b3dcae232b75822d2be247eec5c1d837c9b9af3b7848d0f0fbf","target":"record","created_at":"2026-07-05T03:56:45Z","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":"0f75528c62832ecf242cb3f4814db9cd85e6b1b26048cba4096ca67a9100111e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T19:25:32Z","title_canon_sha256":"46f27cb829b931ad0d6143a78fb4e416aeabc8b999322243d44ee87daf817709"},"schema_version":"1.0","source":{"id":"2102.05082","kind":"arxiv","version":3}},"canonical_sha256":"c0b93ab540cf35c1b593d2fbdcadce12ccdb402d70ceb06f45b764906fad2d8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0b93ab540cf35c1b593d2fbdcadce12ccdb402d70ceb06f45b764906fad2d8c","first_computed_at":"2026-07-05T03:56:45.743520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:45.743520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Oug87aYFOWHvO1gF+pNvgugUuytDN1+9LiN3Q8kOQrqL232gK6OoaaO3qi+GM7V+lWPvsetPQTx5QfOc487Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:45.744105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.05082","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e85d6839bcbd3b3dcae232b75822d2be247eec5c1d837c9b9af3b7848d0f0fbf","sha256:1f3f522759dc45ce19a8528d990959f60c14f2649643f6830417ff64a0eb2d2d"],"state_sha256":"32ca9d8a40c36b013e5000434d2696026e170afdc4b7e477b22e1cd36d16891b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtnf36reVLT6dD3CZk+NrY/ccK9Aa01q2euDgqSFHiKqfRL0j7nZ93/dmzPIhDrZYH0vubEg5AUv7TsKFHP1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T10:32:28.449790Z","bundle_sha256":"3fe7215bbdea9013c4e03a80130f33fc15459985c9d2cf18e3cbd345ac1ad6d7"}}