{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YOBB4CP4QCHADHB6MEOGO3XIPP","short_pith_number":"pith:YOBB4CP4","schema_version":"1.0","canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","source":{"kind":"arxiv","id":"2410.15981","version":2},"attestation_state":"computed","paper":{"title":"Robust Visual Representation Learning with Multi-modal Prior Knowledge for Image Classification Under Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Xiong, Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka, Stefan Schmid, Steffen Staab, Yuqicheng Zhu","submitted_at":"2024-10-21T13:06:38Z","abstract_excerpt":"Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing data. In this paper, we propose Knowledge-Guided Visual representation learning (KGV) - a distribution-based learning approach leveraging multi-modal prior knowledge - to improve generalization under distribution shift. It integrates knowledge from two distinct modalities: 1) a knowledge graph (KG) with hierarchical and association relationships; and 2) generated synthetic images of visual elements semantically repres"},"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":"2410.15981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T13:06:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53e56080df2ced77f33d0965aed7a2d6f45cb18d4b151ac5188c4b7959617b54","abstract_canon_sha256":"4c83e1b2d7271e199d7303bce64d50d707b53d8684ecd6389546f5769cb09bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:04.681573Z","signature_b64":"IyRIzU9Px/PV2cc3kls3ElRZAy0e01Ijae2UhTgdGED1zszp9T7sfzvmOht9AzEAml1pkYO7u5nzcMVTfjK0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","last_reissued_at":"2026-07-05T10:13:04.681109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:04.681109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Visual Representation Learning with Multi-modal Prior Knowledge for Image Classification Under Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Xiong, Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka, Stefan Schmid, Steffen Staab, Yuqicheng Zhu","submitted_at":"2024-10-21T13:06:38Z","abstract_excerpt":"Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing data. In this paper, we propose Knowledge-Guided Visual representation learning (KGV) - a distribution-based learning approach leveraging multi-modal prior knowledge - to improve generalization under distribution shift. It integrates knowledge from two distinct modalities: 1) a knowledge graph (KG) with hierarchical and association relationships; and 2) generated synthetic images of visual elements semantically repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15981","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/2410.15981/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":"2410.15981","created_at":"2026-07-05T10:13:04.681166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15981v2","created_at":"2026-07-05T10:13:04.681166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15981","created_at":"2026-07-05T10:13:04.681166+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOBB4CP4QCHA","created_at":"2026-07-05T10:13:04.681166+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOBB4CP4QCHADHB6","created_at":"2026-07-05T10:13:04.681166+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOBB4CP4","created_at":"2026-07-05T10:13:04.681166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01049","citing_title":"GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP","json":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP.json","graph_json":"https://pith.science/api/pith-number/YOBB4CP4QCHADHB6MEOGO3XIPP/graph.json","events_json":"https://pith.science/api/pith-number/YOBB4CP4QCHADHB6MEOGO3XIPP/events.json","paper":"https://pith.science/paper/YOBB4CP4"},"agent_actions":{"view_html":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP","download_json":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP.json","view_paper":"https://pith.science/paper/YOBB4CP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15981&json=true","fetch_graph":"https://pith.science/api/pith-number/YOBB4CP4QCHADHB6MEOGO3XIPP/graph.json","fetch_events":"https://pith.science/api/pith-number/YOBB4CP4QCHADHB6MEOGO3XIPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/action/storage_attestation","attest_author":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/action/author_attestation","sign_citation":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/action/citation_signature","submit_replication":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/action/replication_record"}},"created_at":"2026-07-05T10:13:04.681166+00:00","updated_at":"2026-07-05T10:13:04.681166+00:00"}