{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EGOL54Y7I3AQGBH7WE4U7P2G4H","short_pith_number":"pith:EGOL54Y7","canonical_record":{"source":{"id":"2503.09837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T20:58:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"535c0d5d20bac56dae2399f119617ee3996d6c14a56a233f076cebc1b35937d9","abstract_canon_sha256":"088ed4af94aea47dd24499eb6575aadae0d37b789c3cf3a8b95f20456b39fced"},"schema_version":"1.0"},"canonical_sha256":"219cbef31f46c10304ffb1394fbf46e1c294d9cfae2173b0d8fd66bbfd7f89a8","source":{"kind":"arxiv","id":"2503.09837","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09837","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09837v2","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09837","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"EGOL54Y7I3AQ","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_16","alias_value":"EGOL54Y7I3AQGBH7","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_8","alias_value":"EGOL54Y7","created_at":"2026-07-05T10:31:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EGOL54Y7I3AQGBH7WE4U7P2G4H","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T20:58:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"535c0d5d20bac56dae2399f119617ee3996d6c14a56a233f076cebc1b35937d9","abstract_canon_sha256":"088ed4af94aea47dd24499eb6575aadae0d37b789c3cf3a8b95f20456b39fced"},"schema_version":"1.0"},"canonical_sha256":"219cbef31f46c10304ffb1394fbf46e1c294d9cfae2173b0d8fd66bbfd7f89a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:02.400512Z","signature_b64":"SOhpq32oSU3pG+uodIUHbu1Bj/IdgQBnkf1BMjon/qdEdbxfTrC9Mcf0IKk6hC2uBxur1hKWbeZF+VRav3LQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"219cbef31f46c10304ffb1394fbf46e1c294d9cfae2173b0d8fd66bbfd7f89a8","last_reissued_at":"2026-07-05T10:31:02.399953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:02.399953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09837","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":"2026-07-05T10:31:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjEbaJffM6muz2IMxNTKxpDGnMi7QlsMEMCx811kcsnwOr6ZYFjuAFpHfb/qIowLButOIr4bIXa472qEVzY4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:40:05.164566Z"},"content_sha256":"a81d3bc51fcd90f15135a44a30ea07fcd1f743e87cfa90b4f0aadb95e9f64bd5","schema_version":"1.0","event_id":"sha256:a81d3bc51fcd90f15135a44a30ea07fcd1f743e87cfa90b4f0aadb95e9f64bd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EGOL54Y7I3AQGBH7WE4U7P2G4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ahmad Mustafa Anis, Hasnain Ali, Saquib Sarfraz","submitted_at":"2025-03-12T20:58:16Z","abstract_excerpt":"Vision Language Models (VLMs) have demonstrated significant potential in various downstream tasks, including Image/Video Generation, Visual Question Answering, Multimodal Chatbots, and Video Understanding. However, these models often struggle with basic image transformations. This paper investigates the image-level understanding of VLMs, specifically CLIP by OpenAI and SigLIP by Google. Our findings reveal that these models lack comprehension of multiple image-level augmentations. To facilitate this study, we created an augmented version of the Flickr8k dataset, pairing each image with a detai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09837","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/2503.09837/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":"2026-07-05T10:31:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0N62MOdLakFVg0dLYkYw66oKB/fm0vCJ6Du4Mw/KhvuApb4DrvICxbLxN6R9A64vkSqsVgVGUDJ++//jkAzGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:40:05.165076Z"},"content_sha256":"3d7d8d813d00b2ff229d6436ed5c23aa820342528bc2f887185205f1195d80c4","schema_version":"1.0","event_id":"sha256:3d7d8d813d00b2ff229d6436ed5c23aa820342528bc2f887185205f1195d80c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/bundle.json","state_url":"https://pith.science/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/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":"2026-08-23T14:40:05Z","links":{"resolver":"https://pith.science/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H","bundle":"https://pith.science/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/bundle.json","state":"https://pith.science/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGOL54Y7I3AQGBH7WE4U7P2G4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EGOL54Y7I3AQGBH7WE4U7P2G4H","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":"088ed4af94aea47dd24499eb6575aadae0d37b789c3cf3a8b95f20456b39fced","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T20:58:16Z","title_canon_sha256":"535c0d5d20bac56dae2399f119617ee3996d6c14a56a233f076cebc1b35937d9"},"schema_version":"1.0","source":{"id":"2503.09837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09837","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09837v2","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09837","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"EGOL54Y7I3AQ","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_16","alias_value":"EGOL54Y7I3AQGBH7","created_at":"2026-07-05T10:31:02Z"},{"alias_kind":"pith_short_8","alias_value":"EGOL54Y7","created_at":"2026-07-05T10:31:02Z"}],"graph_snapshots":[{"event_id":"sha256:3d7d8d813d00b2ff229d6436ed5c23aa820342528bc2f887185205f1195d80c4","target":"graph","created_at":"2026-07-05T10:31:02Z","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/2503.09837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have demonstrated significant potential in various downstream tasks, including Image/Video Generation, Visual Question Answering, Multimodal Chatbots, and Video Understanding. However, these models often struggle with basic image transformations. This paper investigates the image-level understanding of VLMs, specifically CLIP by OpenAI and SigLIP by Google. Our findings reveal that these models lack comprehension of multiple image-level augmentations. To facilitate this study, we created an augmented version of the Flickr8k dataset, pairing each image with a detai","authors_text":"Ahmad Mustafa Anis, Hasnain Ali, Saquib Sarfraz","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T20:58:16Z","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09837","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:a81d3bc51fcd90f15135a44a30ea07fcd1f743e87cfa90b4f0aadb95e9f64bd5","target":"record","created_at":"2026-07-05T10:31:02Z","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":"088ed4af94aea47dd24499eb6575aadae0d37b789c3cf3a8b95f20456b39fced","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T20:58:16Z","title_canon_sha256":"535c0d5d20bac56dae2399f119617ee3996d6c14a56a233f076cebc1b35937d9"},"schema_version":"1.0","source":{"id":"2503.09837","kind":"arxiv","version":2}},"canonical_sha256":"219cbef31f46c10304ffb1394fbf46e1c294d9cfae2173b0d8fd66bbfd7f89a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"219cbef31f46c10304ffb1394fbf46e1c294d9cfae2173b0d8fd66bbfd7f89a8","first_computed_at":"2026-07-05T10:31:02.399953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:02.399953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOhpq32oSU3pG+uodIUHbu1Bj/IdgQBnkf1BMjon/qdEdbxfTrC9Mcf0IKk6hC2uBxur1hKWbeZF+VRav3LQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:02.400512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a81d3bc51fcd90f15135a44a30ea07fcd1f743e87cfa90b4f0aadb95e9f64bd5","sha256:3d7d8d813d00b2ff229d6436ed5c23aa820342528bc2f887185205f1195d80c4"],"state_sha256":"0c9f147ed9edd169f4ef87f2553713530814770efaca9d70e238bfa5d0198265"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUwaKKJ/XzNNfq55hgWN7PUSqPAt0xJfJOB6MSQ1Ag5MOUITWcAk6DLfU/ThPCcAqAJp+ZvwxaR5yL5FE7MEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T14:40:05.169038Z","bundle_sha256":"eb730f95ef6d986edfce65e1752a96829e729fa871485933f77888c8d15c552c"}}