{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FYDOSZ3GT73BBNPJHI64TKLYEK","short_pith_number":"pith:FYDOSZ3G","schema_version":"1.0","canonical_sha256":"2e06e967669ff610b5e93a3dc9a97822acc812d979a15050dc7f3cef4f4cf0f5","source":{"kind":"arxiv","id":"2107.02053","version":2},"attestation_state":"computed","paper":{"title":"MixStyle Neural Networks for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiyang Zhou, Tao Xiang, Yongxin Yang, Yu Qiao","submitted_at":"2021-07-05T14:29:19Z","abstract_excerpt":"Neural networks do not generalize well to unseen data with domain shifts -- a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simple plug-and-play, parameter-free module that can improve domain generalization performance without the need to collect more data or increase model capacity. The design of MixStyle is simple: it mixes the feature statistics of two random instances in a single forward pass during training. The idea is grounded by the finding from recent style transfer research that feature statistics capture image style information, whi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.02053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-05T14:29:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9d7af345bf38feda62e5e555521b381f9332a80ca1ff703afb95796ba3bde206","abstract_canon_sha256":"d2be04792dff9258c27a5890323a8d7b1c74d5e4def6d0ae8ed5b3bef6572ec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:50.607947Z","signature_b64":"LpaQlekU05RP2VZjlV81FF57LvAEBBwToljJPsopSaUzjk4ztfCYuz4RTG5Bx/DqYck+y51aRJyhZ5xAxrjUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e06e967669ff610b5e93a3dc9a97822acc812d979a15050dc7f3cef4f4cf0f5","last_reissued_at":"2026-07-05T06:50:50.607473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:50.607473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixStyle Neural Networks for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiyang Zhou, Tao Xiang, Yongxin Yang, Yu Qiao","submitted_at":"2021-07-05T14:29:19Z","abstract_excerpt":"Neural networks do not generalize well to unseen data with domain shifts -- a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simple plug-and-play, parameter-free module that can improve domain generalization performance without the need to collect more data or increase model capacity. The design of MixStyle is simple: it mixes the feature statistics of two random instances in a single forward pass during training. The idea is grounded by the finding from recent style transfer research that feature statistics capture image style information, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02053","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/2107.02053/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.02053","created_at":"2026-07-05T06:50:50.607531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02053v2","created_at":"2026-07-05T06:50:50.607531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02053","created_at":"2026-07-05T06:50:50.607531+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYDOSZ3GT73B","created_at":"2026-07-05T06:50:50.607531+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYDOSZ3GT73BBNPJ","created_at":"2026-07-05T06:50:50.607531+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYDOSZ3G","created_at":"2026-07-05T06:50:50.607531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.19203","citing_title":"Improving Generalization in MRI-Based Deep Learning Models for Total Knee Replacement Prediction","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK","json":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK.json","graph_json":"https://pith.science/api/pith-number/FYDOSZ3GT73BBNPJHI64TKLYEK/graph.json","events_json":"https://pith.science/api/pith-number/FYDOSZ3GT73BBNPJHI64TKLYEK/events.json","paper":"https://pith.science/paper/FYDOSZ3G"},"agent_actions":{"view_html":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK","download_json":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK.json","view_paper":"https://pith.science/paper/FYDOSZ3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02053&json=true","fetch_graph":"https://pith.science/api/pith-number/FYDOSZ3GT73BBNPJHI64TKLYEK/graph.json","fetch_events":"https://pith.science/api/pith-number/FYDOSZ3GT73BBNPJHI64TKLYEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK/action/storage_attestation","attest_author":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK/action/author_attestation","sign_citation":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK/action/citation_signature","submit_replication":"https://pith.science/pith/FYDOSZ3GT73BBNPJHI64TKLYEK/action/replication_record"}},"created_at":"2026-07-05T06:50:50.607531+00:00","updated_at":"2026-07-05T06:50:50.607531+00:00"}