{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HWUMNPZ6WMDH4J4ESPBNJX2JA3","short_pith_number":"pith:HWUMNPZ6","schema_version":"1.0","canonical_sha256":"3da8c6bf3eb3067e278493c2d4df4906fb9f2615989b607ad9dac3002ffb13c7","source":{"kind":"arxiv","id":"2504.06572","version":1},"attestation_state":"computed","paper":{"title":"Domain Generalization via Discrete Codebook Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhao Ying, Lizhuang Ma, Qianyu Zhou, Shaocong Long, Xikun Jiang, Yuan Luo","submitted_at":"2025-04-09T04:19:35Z","abstract_excerpt":"Domain generalization (DG) strives to address distribution shifts across diverse environments to enhance model's generalizability. Current DG approaches are confined to acquiring robust representations with continuous features, specifically training at the pixel level. However, this DG paradigm may struggle to mitigate distribution gaps in dealing with a large space of continuous features, rendering it susceptible to pixel details that exhibit spurious correlations or noise. In this paper, we first theoretically demonstrate that the domain gaps in continuous representation learning can be redu"},"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":"2504.06572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T04:19:35Z","cross_cats_sorted":[],"title_canon_sha256":"4dcb02cfb427844d8d30898c8ff0827f16c62f48a24529264c51abd90c9fb156","abstract_canon_sha256":"0a0e1003e5551eafc65ee8c94e7e840ef919fab4bb04c705599730d997c4c38b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:29.128221Z","signature_b64":"FbtKghpKx7IrTgBy0eawavgRgxyawbT1ajdMedi/oIS/CFFnvA4TD+3ipe8zRtE7KDdLfcJ3U0yxm/0dEtXEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3da8c6bf3eb3067e278493c2d4df4906fb9f2615989b607ad9dac3002ffb13c7","last_reissued_at":"2026-07-05T10:46:29.127857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:29.127857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization via Discrete Codebook Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhao Ying, Lizhuang Ma, Qianyu Zhou, Shaocong Long, Xikun Jiang, Yuan Luo","submitted_at":"2025-04-09T04:19:35Z","abstract_excerpt":"Domain generalization (DG) strives to address distribution shifts across diverse environments to enhance model's generalizability. Current DG approaches are confined to acquiring robust representations with continuous features, specifically training at the pixel level. However, this DG paradigm may struggle to mitigate distribution gaps in dealing with a large space of continuous features, rendering it susceptible to pixel details that exhibit spurious correlations or noise. In this paper, we first theoretically demonstrate that the domain gaps in continuous representation learning can be redu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06572","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/2504.06572/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":"2504.06572","created_at":"2026-07-05T10:46:29.127914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06572v1","created_at":"2026-07-05T10:46:29.127914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06572","created_at":"2026-07-05T10:46:29.127914+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWUMNPZ6WMDH","created_at":"2026-07-05T10:46:29.127914+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWUMNPZ6WMDH4J4E","created_at":"2026-07-05T10:46:29.127914+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWUMNPZ6","created_at":"2026-07-05T10:46:29.127914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20835","citing_title":"PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3","json":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3.json","graph_json":"https://pith.science/api/pith-number/HWUMNPZ6WMDH4J4ESPBNJX2JA3/graph.json","events_json":"https://pith.science/api/pith-number/HWUMNPZ6WMDH4J4ESPBNJX2JA3/events.json","paper":"https://pith.science/paper/HWUMNPZ6"},"agent_actions":{"view_html":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3","download_json":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3.json","view_paper":"https://pith.science/paper/HWUMNPZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06572&json=true","fetch_graph":"https://pith.science/api/pith-number/HWUMNPZ6WMDH4J4ESPBNJX2JA3/graph.json","fetch_events":"https://pith.science/api/pith-number/HWUMNPZ6WMDH4J4ESPBNJX2JA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3/action/storage_attestation","attest_author":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3/action/author_attestation","sign_citation":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3/action/citation_signature","submit_replication":"https://pith.science/pith/HWUMNPZ6WMDH4J4ESPBNJX2JA3/action/replication_record"}},"created_at":"2026-07-05T10:46:29.127914+00:00","updated_at":"2026-07-05T10:46:29.127914+00:00"}