{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C4URSUFAUE6YNN5ACHCRPVFRHZ","short_pith_number":"pith:C4URSUFA","canonical_record":{"source":{"id":"2506.23663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:39:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1642a4952c0515c5665f57fc15338f7e3343edabcab2a6aa9dbb1eabec86e8b1","abstract_canon_sha256":"0e34cae109562e99b5d1e0c13d9f91489f84dd3d560151ebd943c8720f0f5097"},"schema_version":"1.0"},"canonical_sha256":"17291950a0a13d86b7a011c517d4b13e565378c82a42e93378891369f414dc49","source":{"kind":"arxiv","id":"2506.23663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23663","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23663v1","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23663","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"C4URSUFAUE6Y","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"C4URSUFAUE6YNN5A","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"C4URSUFA","created_at":"2026-07-05T11:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C4URSUFAUE6YNN5ACHCRPVFRHZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:39:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1642a4952c0515c5665f57fc15338f7e3343edabcab2a6aa9dbb1eabec86e8b1","abstract_canon_sha256":"0e34cae109562e99b5d1e0c13d9f91489f84dd3d560151ebd943c8720f0f5097"},"schema_version":"1.0"},"canonical_sha256":"17291950a0a13d86b7a011c517d4b13e565378c82a42e93378891369f414dc49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:25.955929Z","signature_b64":"03MNGolEc6M+Yz0IUMq8zUa3bGOAj9ZsnmWuGApc20d0XS23ZVSdRn0fqv0QH6exApY1maD/3smsAgVwSOTGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17291950a0a13d86b7a011c517d4b13e565378c82a42e93378891369f414dc49","last_reissued_at":"2026-07-05T11:29:25.955515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:25.955515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23663","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7axLNOoSGq31FDn3IrhmsuQybAK/aWIPVcH6JFC1wtdt0OtalceCK6iHOhOlWA5JL1QJ0+1El9BduL541rWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:23:44.077851Z"},"content_sha256":"e67c3cd411a5764f711053b217fc6ca12673616ab7c32de8f4b08cd60fc07adf","schema_version":"1.0","event_id":"sha256:e67c3cd411a5764f711053b217fc6ca12673616ab7c32de8f4b08cd60fc07adf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C4URSUFAUE6YNN5ACHCRPVFRHZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Domain Robustness of Contrastive Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Brodmann, Erik Rodner, Mario Koddenbrock, Rudolf Hoffmann","submitted_at":"2025-06-30T09:39:33Z","abstract_excerpt":"In real-world vision-language applications, practitioners increasingly rely on large, pretrained foundation models rather than custom-built solutions, despite limited transparency regarding their training data and processes. While these models achieve impressive performance on general benchmarks, their effectiveness can decline notably under specialized domain shifts, such as unique imaging conditions or environmental variations. In this work, we introduce Deepbench, a framework designed to assess domain-specific robustness of vision-language models (VLMs). Deepbench leverages a large language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23663","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/2506.23663/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":"2026-07-05T11:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6ViSZMAe8q70X1s4DpnrI0TeuXnEGDGeATAogCYobfgAWnx53CtZ9BpBY0BvaRV+7jog9eCrlBHI6SlNp0vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:23:44.078436Z"},"content_sha256":"a756de9ff3b5a82993b0f38c6014cd99ef991d858aa4a1012e4790245b563436","schema_version":"1.0","event_id":"sha256:a756de9ff3b5a82993b0f38c6014cd99ef991d858aa4a1012e4790245b563436"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/bundle.json","state_url":"https://pith.science/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/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":"2026-08-09T21:23:44Z","links":{"resolver":"https://pith.science/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ","bundle":"https://pith.science/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/bundle.json","state":"https://pith.science/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4URSUFAUE6YNN5ACHCRPVFRHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C4URSUFAUE6YNN5ACHCRPVFRHZ","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":"0e34cae109562e99b5d1e0c13d9f91489f84dd3d560151ebd943c8720f0f5097","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:39:33Z","title_canon_sha256":"1642a4952c0515c5665f57fc15338f7e3343edabcab2a6aa9dbb1eabec86e8b1"},"schema_version":"1.0","source":{"id":"2506.23663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23663","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23663v1","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23663","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"C4URSUFAUE6Y","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"C4URSUFAUE6YNN5A","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"C4URSUFA","created_at":"2026-07-05T11:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:a756de9ff3b5a82993b0f38c6014cd99ef991d858aa4a1012e4790245b563436","target":"graph","created_at":"2026-07-05T11:29:25Z","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/2506.23663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world vision-language applications, practitioners increasingly rely on large, pretrained foundation models rather than custom-built solutions, despite limited transparency regarding their training data and processes. While these models achieve impressive performance on general benchmarks, their effectiveness can decline notably under specialized domain shifts, such as unique imaging conditions or environmental variations. In this work, we introduce Deepbench, a framework designed to assess domain-specific robustness of vision-language models (VLMs). Deepbench leverages a large language","authors_text":"David Brodmann, Erik Rodner, Mario Koddenbrock, Rudolf Hoffmann","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:39:33Z","title":"On the Domain Robustness of Contrastive Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23663","kind":"arxiv","version":1},"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:e67c3cd411a5764f711053b217fc6ca12673616ab7c32de8f4b08cd60fc07adf","target":"record","created_at":"2026-07-05T11:29:25Z","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":"0e34cae109562e99b5d1e0c13d9f91489f84dd3d560151ebd943c8720f0f5097","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:39:33Z","title_canon_sha256":"1642a4952c0515c5665f57fc15338f7e3343edabcab2a6aa9dbb1eabec86e8b1"},"schema_version":"1.0","source":{"id":"2506.23663","kind":"arxiv","version":1}},"canonical_sha256":"17291950a0a13d86b7a011c517d4b13e565378c82a42e93378891369f414dc49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17291950a0a13d86b7a011c517d4b13e565378c82a42e93378891369f414dc49","first_computed_at":"2026-07-05T11:29:25.955515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:25.955515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03MNGolEc6M+Yz0IUMq8zUa3bGOAj9ZsnmWuGApc20d0XS23ZVSdRn0fqv0QH6exApY1maD/3smsAgVwSOTGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:25.955929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e67c3cd411a5764f711053b217fc6ca12673616ab7c32de8f4b08cd60fc07adf","sha256:a756de9ff3b5a82993b0f38c6014cd99ef991d858aa4a1012e4790245b563436"],"state_sha256":"91bd0d20cabfe167833072a5d7ad9f798014486f2d5b27e87d1bbf732a6cd462"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAyir9VK2cl617mQjpVqHDcwBqyyqb3sULyiwQ8saXxr+7kn+lUt1DBgXEveSt7ti0geS4+VKFtDSHH0wFJ7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:23:44.083611Z","bundle_sha256":"7f02031efd02de59b2e867487e10f8b698507e8917885730d11c05b716a6f439"}}