{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XXJ3444BN3G2FDB22ZKBMSW5KH","short_pith_number":"pith:XXJ3444B","canonical_record":{"source":{"id":"2410.04235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T17:26:03Z","cross_cats_sorted":[],"title_canon_sha256":"078d24637db429761baff3eaa7f82d48632e3d6fa9847f09e793b6c3f213d49a","abstract_canon_sha256":"a9109b0a29001035510fdb639dc071e976ad21337f5995482314ae08e431bcc8"},"schema_version":"1.0"},"canonical_sha256":"bdd3be73816ecda28c3ad654164add51e2fa92b3afa9e58fe132a84ce6a65c9f","source":{"kind":"arxiv","id":"2410.04235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04235","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04235v1","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04235","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"XXJ3444BN3G2","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"XXJ3444BN3G2FDB2","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"XXJ3444B","created_at":"2026-07-05T09:16:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XXJ3444BN3G2FDB22ZKBMSW5KH","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T17:26:03Z","cross_cats_sorted":[],"title_canon_sha256":"078d24637db429761baff3eaa7f82d48632e3d6fa9847f09e793b6c3f213d49a","abstract_canon_sha256":"a9109b0a29001035510fdb639dc071e976ad21337f5995482314ae08e431bcc8"},"schema_version":"1.0"},"canonical_sha256":"bdd3be73816ecda28c3ad654164add51e2fa92b3afa9e58fe132a84ce6a65c9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:31.609430Z","signature_b64":"qA6TN/QWCes0+t1atMXB6Ofyr8AT3hQhc9YLxiWzVCYErdIauJt4Ek9u/YcMhNFWx2c6bkfrDPNFRPIRsmg+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd3be73816ecda28c3ad654164add51e2fa92b3afa9e58fe132a84ce6a65c9f","last_reissued_at":"2026-07-05T09:16:31.608904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:31.608904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04235","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":"2026-07-05T09:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHRadO8Jd+2dFahYxPBfMoFwD5Yw8veLXTN7KDHvC98hHQrEvb+WhuWvpuwkYuF6u3tj2S2CZ8FCFuXcJEzZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:48:10.306523Z"},"content_sha256":"8160ad8228afa8492f02807282847e8ae68e7c04c84473f64814a716991535e9","schema_version":"1.0","event_id":"sha256:8160ad8228afa8492f02807282847e8ae68e7c04c84473f64814a716991535e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XXJ3444BN3G2FDB22ZKBMSW5KH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Distribution Alignment with Diversity-based Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Napoli, Paul White","submitted_at":"2024-10-05T17:26:03Z","abstract_excerpt":"Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant across domains, by minimising the discrepancy between the distributions. However, the discrepancy estimates can be extremely noisy when training via stochastic gradient descent (SGD), and shifts in the relative proportions of different subgroups can lead to domain misalignments; these can both stifle the benefits of the method. This paper proposes to improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04235","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/2410.04235/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":"2026-07-05T09:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+lBbfi7xHzv3vtP2KZnB5SVuJc4zYrU94jt65zENwuQrVu8pMKpS2sN2G5PPUTSacWVau2GGN1F9WPSBBpuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:48:10.307432Z"},"content_sha256":"d291e5004e47ba212705bf8f91eece7bc69bf2c2208952b5f05846d775f75c5b","schema_version":"1.0","event_id":"sha256:d291e5004e47ba212705bf8f91eece7bc69bf2c2208952b5f05846d775f75c5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/bundle.json","state_url":"https://pith.science/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/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":"2026-08-09T05:48:10Z","links":{"resolver":"https://pith.science/pith/XXJ3444BN3G2FDB22ZKBMSW5KH","bundle":"https://pith.science/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/bundle.json","state":"https://pith.science/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXJ3444BN3G2FDB22ZKBMSW5KH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XXJ3444BN3G2FDB22ZKBMSW5KH","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":"a9109b0a29001035510fdb639dc071e976ad21337f5995482314ae08e431bcc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T17:26:03Z","title_canon_sha256":"078d24637db429761baff3eaa7f82d48632e3d6fa9847f09e793b6c3f213d49a"},"schema_version":"1.0","source":{"id":"2410.04235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04235","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04235v1","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04235","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"XXJ3444BN3G2","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"XXJ3444BN3G2FDB2","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"XXJ3444B","created_at":"2026-07-05T09:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:d291e5004e47ba212705bf8f91eece7bc69bf2c2208952b5f05846d775f75c5b","target":"graph","created_at":"2026-07-05T09:16:31Z","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/2410.04235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant across domains, by minimising the discrepancy between the distributions. However, the discrepancy estimates can be extremely noisy when training via stochastic gradient descent (SGD), and shifts in the relative proportions of different subgroups can lead to domain misalignments; these can both stifle the benefits of the method. This paper proposes to improv","authors_text":"Andrea Napoli, Paul White","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T17:26:03Z","title":"Improving Distribution Alignment with Diversity-based Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04235","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":"sha256:8160ad8228afa8492f02807282847e8ae68e7c04c84473f64814a716991535e9","target":"record","created_at":"2026-07-05T09:16:31Z","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":"a9109b0a29001035510fdb639dc071e976ad21337f5995482314ae08e431bcc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T17:26:03Z","title_canon_sha256":"078d24637db429761baff3eaa7f82d48632e3d6fa9847f09e793b6c3f213d49a"},"schema_version":"1.0","source":{"id":"2410.04235","kind":"arxiv","version":1}},"canonical_sha256":"bdd3be73816ecda28c3ad654164add51e2fa92b3afa9e58fe132a84ce6a65c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdd3be73816ecda28c3ad654164add51e2fa92b3afa9e58fe132a84ce6a65c9f","first_computed_at":"2026-07-05T09:16:31.608904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:31.608904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qA6TN/QWCes0+t1atMXB6Ofyr8AT3hQhc9YLxiWzVCYErdIauJt4Ek9u/YcMhNFWx2c6bkfrDPNFRPIRsmg+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:31.609430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8160ad8228afa8492f02807282847e8ae68e7c04c84473f64814a716991535e9","sha256:d291e5004e47ba212705bf8f91eece7bc69bf2c2208952b5f05846d775f75c5b"],"state_sha256":"087d19fe60e3f44ad867518edc0b763a5888fd52f1ca594d552727c9ddddb4ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SD/ke66e+kMWH4+Cy/dlqUT5ZuEClkAuWbvySjVkL2qcoQUqR8kjipAFTcqeixMguMTuK175/SQbtXcYlIHEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:48:10.318083Z","bundle_sha256":"fd5de82ed7f92caea24303ca917cdb0864f5dc037eba49b1319dc55b01f0d452"}}