{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YVEIVQUXYO7OOU4ASXWGSL5CFF","short_pith_number":"pith:YVEIVQUX","canonical_record":{"source":{"id":"2402.09816","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T09:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"0bf3ac3482e728e48903f0dad1b719e9a92b7359f6f6e9b2b948850a10c111ca","abstract_canon_sha256":"957e4f275e2af5c1226938a9642b3eae4629951b3925cd1519a646fc7acd87a9"},"schema_version":"1.0"},"canonical_sha256":"c5488ac297c3bee7538095ec692fa2295a6348edd80569e45575a60a94a9af53","source":{"kind":"arxiv","id":"2402.09816","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09816","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09816v2","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09816","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_12","alias_value":"YVEIVQUXYO7O","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_16","alias_value":"YVEIVQUXYO7OOU4A","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_8","alias_value":"YVEIVQUX","created_at":"2026-07-05T11:39:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YVEIVQUXYO7OOU4ASXWGSL5CFF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09816","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T09:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"0bf3ac3482e728e48903f0dad1b719e9a92b7359f6f6e9b2b948850a10c111ca","abstract_canon_sha256":"957e4f275e2af5c1226938a9642b3eae4629951b3925cd1519a646fc7acd87a9"},"schema_version":"1.0"},"canonical_sha256":"c5488ac297c3bee7538095ec692fa2295a6348edd80569e45575a60a94a9af53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:02.096418Z","signature_b64":"nx55+qgFSE0h1Jwj0E7QhzU1rBnvN7nf+fscmCUpvX9eZR8BUP3NF50Uqaq8zYZTBMaRwbwS4i4PdU8hdJ2GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5488ac297c3bee7538095ec692fa2295a6348edd80569e45575a60a94a9af53","last_reissued_at":"2026-07-05T11:39:02.095962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:02.095962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09816","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":"2026-07-05T11:39:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HV6J+Y2ces6TWiN9vuWDfc/8ii+MTrZNIN3nTLEa3/N+3mr6GxQIWgU+e15M7CHiI5OQGG1wfsFhYuUVyI6CAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:06:56.532886Z"},"content_sha256":"bf750b14460e5aa55499bb6a474407e253d6b1f229a4e65ad6ab6c842a549681","schema_version":"1.0","event_id":"sha256:bf750b14460e5aa55499bb6a474407e253d6b1f229a4e65ad6ab6c842a549681"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YVEIVQUXYO7OOU4ASXWGSL5CFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angelos Zavras, Beg\\\"um Demir, Dimitrios Michail, Ioannis Papoutsis","submitted_at":"2024-02-15T09:31:07Z","abstract_excerpt":"Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across various image classification tasks and often rivals fully supervised baselines, despite not being explicitly trained for those tasks. Nevertheless, there are still domains where zero-shot CLIP performance is far from optimal, such as Remote Sensing (RS) and medical imagery. These domains do not only exhibit fundamentally different distributions compared to natura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09816","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/2402.09816/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":"2026-07-05T11:39:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dV/GxISqQijr4aNvT1hGAVxYut9mYyJQPVoYFskJnPZ7MFa4HI+APykUX9kAvJakkRNRcAnkma/BPaiyJ+ooCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:06:56.533252Z"},"content_sha256":"885db3e2796f59fca500917c0a6ebb7c1a2009fc9a2761933cf162786ec94731","schema_version":"1.0","event_id":"sha256:885db3e2796f59fca500917c0a6ebb7c1a2009fc9a2761933cf162786ec94731"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/bundle.json","state_url":"https://pith.science/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/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":"2026-07-12T18:06:56Z","links":{"resolver":"https://pith.science/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF","bundle":"https://pith.science/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/bundle.json","state":"https://pith.science/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVEIVQUXYO7OOU4ASXWGSL5CFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YVEIVQUXYO7OOU4ASXWGSL5CFF","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":"957e4f275e2af5c1226938a9642b3eae4629951b3925cd1519a646fc7acd87a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T09:31:07Z","title_canon_sha256":"0bf3ac3482e728e48903f0dad1b719e9a92b7359f6f6e9b2b948850a10c111ca"},"schema_version":"1.0","source":{"id":"2402.09816","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09816","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09816v2","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09816","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_12","alias_value":"YVEIVQUXYO7O","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_16","alias_value":"YVEIVQUXYO7OOU4A","created_at":"2026-07-05T11:39:02Z"},{"alias_kind":"pith_short_8","alias_value":"YVEIVQUX","created_at":"2026-07-05T11:39:02Z"}],"graph_snapshots":[{"event_id":"sha256:885db3e2796f59fca500917c0a6ebb7c1a2009fc9a2761933cf162786ec94731","target":"graph","created_at":"2026-07-05T11:39:02Z","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/2402.09816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across various image classification tasks and often rivals fully supervised baselines, despite not being explicitly trained for those tasks. Nevertheless, there are still domains where zero-shot CLIP performance is far from optimal, such as Remote Sensing (RS) and medical imagery. These domains do not only exhibit fundamentally different distributions compared to natura","authors_text":"Angelos Zavras, Beg\\\"um Demir, Dimitrios Michail, Ioannis Papoutsis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T09:31:07Z","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09816","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:bf750b14460e5aa55499bb6a474407e253d6b1f229a4e65ad6ab6c842a549681","target":"record","created_at":"2026-07-05T11:39:02Z","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":"957e4f275e2af5c1226938a9642b3eae4629951b3925cd1519a646fc7acd87a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T09:31:07Z","title_canon_sha256":"0bf3ac3482e728e48903f0dad1b719e9a92b7359f6f6e9b2b948850a10c111ca"},"schema_version":"1.0","source":{"id":"2402.09816","kind":"arxiv","version":2}},"canonical_sha256":"c5488ac297c3bee7538095ec692fa2295a6348edd80569e45575a60a94a9af53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5488ac297c3bee7538095ec692fa2295a6348edd80569e45575a60a94a9af53","first_computed_at":"2026-07-05T11:39:02.095962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:02.095962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nx55+qgFSE0h1Jwj0E7QhzU1rBnvN7nf+fscmCUpvX9eZR8BUP3NF50Uqaq8zYZTBMaRwbwS4i4PdU8hdJ2GBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:02.096418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09816","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf750b14460e5aa55499bb6a474407e253d6b1f229a4e65ad6ab6c842a549681","sha256:885db3e2796f59fca500917c0a6ebb7c1a2009fc9a2761933cf162786ec94731"],"state_sha256":"fb117cbca76684951ae6044ad6089cb342039a0ca845258b65ee1c4c9859f178"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6HUKV+oH01PbOXFpYbDB9MBRLLWs6EreqkJZ0G38xJ3o8Z6+myk+0cFMDO+xf/V7wpW4840mJllKedwq/w2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:06:56.535373Z","bundle_sha256":"a75840a82ec06ba4526ffb4ae642cedce4793dc9fd2323a9aeffe56866af9aae"}}