{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YOBB4CP4QCHADHB6MEOGO3XIPP","short_pith_number":"pith:YOBB4CP4","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"},"canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","source":{"kind":"arxiv","id":"2410.15981","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15981","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15981v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15981","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"YOBB4CP4QCHA","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOBB4CP4QCHADHB6","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOBB4CP4","created_at":"2026-07-05T10:13:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YOBB4CP4QCHADHB6MEOGO3XIPP","target":"record","payload":{"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"},"canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","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"},"source_kind":"arxiv","source_id":"2410.15981","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EfWRAHr+q3urAoK1gZ75veEOUpvYE/0CREuh6ji+hwXPsucMVqOImPic5jqYtM8KFItCazWhdynSlDuSu7x2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:26:00.125712Z"},"content_sha256":"77cc8a3192486178e6dd8d268a9e61d293e29a0b7b632ebdb469312550876ee9","schema_version":"1.0","event_id":"sha256:77cc8a3192486178e6dd8d268a9e61d293e29a0b7b632ebdb469312550876ee9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YOBB4CP4QCHADHB6MEOGO3XIPP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+tVYMnG2xb7Nhk9RaU5hvAGCaCHzU9HrUwv/0uVm6JANyBl0MAzsTOuSah1U9aQhw2si/v8HZNkgOCQDPo7LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:26:00.126263Z"},"content_sha256":"c511f650b9aae4c0dfec36b584862fac71261e206119c75a4111c1c84d5652d0","schema_version":"1.0","event_id":"sha256:c511f650b9aae4c0dfec36b584862fac71261e206119c75a4111c1c84d5652d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/bundle.json","state_url":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/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":"2026-08-09T16:26:00Z","links":{"resolver":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP","bundle":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/bundle.json","state":"https://pith.science/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOBB4CP4QCHADHB6MEOGO3XIPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YOBB4CP4QCHADHB6MEOGO3XIPP","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":"4c83e1b2d7271e199d7303bce64d50d707b53d8684ecd6389546f5769cb09bde","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T13:06:38Z","title_canon_sha256":"53e56080df2ced77f33d0965aed7a2d6f45cb18d4b151ac5188c4b7959617b54"},"schema_version":"1.0","source":{"id":"2410.15981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15981","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15981v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15981","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"YOBB4CP4QCHA","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOBB4CP4QCHADHB6","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOBB4CP4","created_at":"2026-07-05T10:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:c511f650b9aae4c0dfec36b584862fac71261e206119c75a4111c1c84d5652d0","target":"graph","created_at":"2026-07-05T10:13:04Z","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/2410.15981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Xiong, Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka, Stefan Schmid, Steffen Staab, Yuqicheng Zhu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T13:06:38Z","title":"Robust Visual Representation Learning with Multi-modal Prior Knowledge for Image Classification Under Distribution Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15981","kind":"arxiv","version":2},"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":"sha256:77cc8a3192486178e6dd8d268a9e61d293e29a0b7b632ebdb469312550876ee9","target":"record","created_at":"2026-07-05T10:13:04Z","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":"4c83e1b2d7271e199d7303bce64d50d707b53d8684ecd6389546f5769cb09bde","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T13:06:38Z","title_canon_sha256":"53e56080df2ced77f33d0965aed7a2d6f45cb18d4b151ac5188c4b7959617b54"},"schema_version":"1.0","source":{"id":"2410.15981","kind":"arxiv","version":2}},"canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3821e09fc808e019c3e611c676ee87be6332740809e8a4b1c5f7187c4bedbfe","first_computed_at":"2026-07-05T10:13:04.681109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:04.681109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IyRIzU9Px/PV2cc3kls3ElRZAy0e01Ijae2UhTgdGED1zszp9T7sfzvmOht9AzEAml1pkYO7u5nzcMVTfjK0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:04.681573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77cc8a3192486178e6dd8d268a9e61d293e29a0b7b632ebdb469312550876ee9","sha256:c511f650b9aae4c0dfec36b584862fac71261e206119c75a4111c1c84d5652d0"],"state_sha256":"728955fcadf1f4e62ccd13bc6de72054a435ac184bb606c63c98e68c3ae16490"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OnqNkOhuVZ056IXvNjPxoEMs7K2hpkdDz3G25APwNDKP7ssNhXvAoqN5S8P6AGVdoRaeQJNtxKttERXdLNRzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:26:00.129693Z","bundle_sha256":"12f7be62f2b8633aa561f1c2b2f2fed4bca2b30a16f9cdf7da8f3bf66dc563af"}}