{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQ5O53GIYUVCEY7BW3KFBMPN5M","short_pith_number":"pith:EQ5O53GI","schema_version":"1.0","canonical_sha256":"243aeeecc8c52a2263e1b6d450b1edeb3661e60fcd200f8870eab3e7df297cb7","source":{"kind":"arxiv","id":"2605.16973","version":1},"attestation_state":"computed","paper":{"title":"SHED: Style-Homogenized Embedding Alignment for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Removing style centroids from CLIP embeddings improves generalization to unseen domains.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kai Gan, Tong Wei","submitted_at":"2026-05-16T12:51:38Z","abstract_excerpt":"Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios. To address this, we propose Style-Homogenized Embedding alignment for Domain-generalization (SHED), a novel CLIP-base"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.16973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T12:51:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"054b2418eeed5ecf003dfadd0d76550fd9ae74ce3c2e4edffc4ea292c5035de0","abstract_canon_sha256":"4379277a712a32c1960ce1ff2efba60aa6d11cf75d9df19c6c8d978818c6edba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:33.792795Z","signature_b64":"cU3suqmHk+hUWt+PloLKND89GptPJ+Gq/pxcavX2dMOqgSRR2jhNc+Le5/5x1m1Pk6h0JVu/ISmggqe2OhiuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"243aeeecc8c52a2263e1b6d450b1edeb3661e60fcd200f8870eab3e7df297cb7","last_reissued_at":"2026-05-20T00:03:33.791989Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:33.791989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHED: Style-Homogenized Embedding Alignment for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Removing style centroids from CLIP embeddings improves generalization to unseen domains.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kai Gan, Tong Wei","submitted_at":"2026-05-16T12:51:38Z","abstract_excerpt":"Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios. To address this, we propose Style-Homogenized Embedding alignment for Domain-generalization (SHED), a novel CLIP-base"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SHED achieves state-of-the-art performance, outperforming prior methods significantly (e.g., +4.0% on DomainNet vs. standard fine-tuning).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That subtracting estimated style centroids from embeddings preserves class semantics while removing only domain-specific information, and that projecting textual domain centroids into visual space enables effective membership-weighted inference without any target domain data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SHED improves domain generalization in CLIP by aligning style-homogenized embeddings instead of raw ones, achieving state-of-the-art results on five benchmarks including a 4% gain on DomainNet.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Removing style centroids from CLIP embeddings improves generalization to unseen domains.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"97acd1be920168a93a565869c2cb48acccbf26a8206d2d170f150871707f6d06"},"source":{"id":"2605.16973","kind":"arxiv","version":1},"verdict":{"id":"38c0bc99-024c-421e-bf55-91dfe7df1b4d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:20:02.015623Z","strongest_claim":"SHED achieves state-of-the-art performance, outperforming prior methods significantly (e.g., +4.0% on DomainNet vs. standard fine-tuning).","one_line_summary":"SHED improves domain generalization in CLIP by aligning style-homogenized embeddings instead of raw ones, achieving state-of-the-art results on five benchmarks including a 4% gain on DomainNet.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That subtracting estimated style centroids from embeddings preserves class semantics while removing only domain-specific information, and that projecting textual domain centroids into visual space enables effective membership-weighted inference without any target domain data.","pith_extraction_headline":"Removing style centroids from CLIP embeddings improves generalization to unseen domains."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16973/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T20:31:33.579607Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:19.052947Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T19:51:56.906160Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T19:50:07.816280Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.221152Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.307823Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ea1dea97c46bedc16014f49cd9520e47dae89572ea7bd80ba02670a33c2f349d"},"references":{"count":55,"sample":[{"doi":"","year":1985,"title":"Structure and Interpretation of Computer Programs","work_id":"01a14db6-7d1d-4607-868a-f7393285bd98","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2001,"title":"Visual Information Extraction with Lixto","work_id":"70a0bb1e-35f7-444f-b12d-bd6dcd37cc57","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1985,"title":"Brachman and James G","work_id":"0dc6cf5e-34e0-4f51-b711-0498f8e618ec","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1992,"title":"Complexity results for nonmonotonic logics","work_id":"d0459553-e996-400d-b3ca-0618c3da598c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"Hypertree Decompositions and Tractable Queries","work_id":"97611438-476f-473e-b229-ee75292c4fac","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":55,"snapshot_sha256":"fc8fff5149a06699b8a2bf8c6361063ea54efc2a6190a74d2b0594b88c91d78b","internal_anchors":2},"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":"2605.16973","created_at":"2026-05-20T00:03:33.792156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16973v1","created_at":"2026-05-20T00:03:33.792156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16973","created_at":"2026-05-20T00:03:33.792156+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQ5O53GIYUVC","created_at":"2026-05-20T00:03:33.792156+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQ5O53GIYUVCEY7B","created_at":"2026-05-20T00:03:33.792156+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQ5O53GI","created_at":"2026-05-20T00:03:33.792156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M","json":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M.json","graph_json":"https://pith.science/api/pith-number/EQ5O53GIYUVCEY7BW3KFBMPN5M/graph.json","events_json":"https://pith.science/api/pith-number/EQ5O53GIYUVCEY7BW3KFBMPN5M/events.json","paper":"https://pith.science/paper/EQ5O53GI"},"agent_actions":{"view_html":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M","download_json":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M.json","view_paper":"https://pith.science/paper/EQ5O53GI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16973&json=true","fetch_graph":"https://pith.science/api/pith-number/EQ5O53GIYUVCEY7BW3KFBMPN5M/graph.json","fetch_events":"https://pith.science/api/pith-number/EQ5O53GIYUVCEY7BW3KFBMPN5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M/action/storage_attestation","attest_author":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M/action/author_attestation","sign_citation":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M/action/citation_signature","submit_replication":"https://pith.science/pith/EQ5O53GIYUVCEY7BW3KFBMPN5M/action/replication_record"}},"created_at":"2026-05-20T00:03:33.792156+00:00","updated_at":"2026-05-20T00:03:33.792156+00:00"}