{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BKXAGLBTWHSTTVHUZLBR6VW5J6","short_pith_number":"pith:BKXAGLBT","canonical_record":{"source":{"id":"2506.05429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T08:09:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"49b9bb405e34dfd7140e9508b583b93bce13895464a33de831c08802c5dd4159","abstract_canon_sha256":"4022dab88c7c7f83207b42c97b638d4fbb65d70286e58a02780b3b2e97641f88"},"schema_version":"1.0"},"canonical_sha256":"0aae032c33b1e539d4f4cac31f56dd4faccad56c4ebc1a5832e17ba302f35b63","source":{"kind":"arxiv","id":"2506.05429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05429","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05429v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05429","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"BKXAGLBTWHST","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"BKXAGLBTWHSTTVHU","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"BKXAGLBT","created_at":"2026-07-05T11:17:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BKXAGLBTWHSTTVHUZLBR6VW5J6","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T08:09:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"49b9bb405e34dfd7140e9508b583b93bce13895464a33de831c08802c5dd4159","abstract_canon_sha256":"4022dab88c7c7f83207b42c97b638d4fbb65d70286e58a02780b3b2e97641f88"},"schema_version":"1.0"},"canonical_sha256":"0aae032c33b1e539d4f4cac31f56dd4faccad56c4ebc1a5832e17ba302f35b63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:02.481481Z","signature_b64":"1Uiawmt2OcZmyXHiYSpP1K/4vfkkkJZywWFqs2wWZ4RNpxtVLAAGFJSAzAhgo8hLwSKaM3VYL0AYv5gLdOWWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aae032c33b1e539d4f4cac31f56dd4faccad56c4ebc1a5832e17ba302f35b63","last_reissued_at":"2026-07-05T11:17:02.481015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:02.481015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05429","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":"2026-07-05T11:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zr+PbY3p4yxiim6+kJ2ORjnKjQGe0NtTrto94BCYW57HTbv4HlK3+esLyt4zegUgp8nWkHaoXgaESBGB28GbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:49.466124Z"},"content_sha256":"01bfe27095d2fddf5c9b7915f23cc8c33cbc830f54e9fc2e1004fca2e999c5c1","schema_version":"1.0","event_id":"sha256:01bfe27095d2fddf5c9b7915f23cc8c33cbc830f54e9fc2e1004fca2e999c5c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BKXAGLBTWHSTTVHUZLBR6VW5J6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coordinated Robustness Evaluation Framework for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Guillen, Ashwin Ramesh Babu, Avisek Naug, Ricardo Luna Gutierrez, Sahand Ghorbanpour, Sajad Mousavi, Soumyendu Sarkar, Vineet Gundecha","submitted_at":"2025-06-05T08:09:05Z","abstract_excerpt":"Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning and visual question and answering. However, similar to traditional models, they are susceptible to small perturbations, posing a challenge to their robustness, particularly in deployment scenarios. Evaluating the robustness of these models requires perturbations in both the vision and language modalities to learn their inter-modal dependencies. In this work, we train a generic surrogate model that can take both image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05429","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/2506.05429/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":"2026-07-05T11:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TsymyEfgLMLe/MmGL9PZogJBs6kc1ZnEoh4tbyrXbcmwQB6GKsP1msWUYaHz8z2a/LhaVBc30cp5h3Wzv4yjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:49.466649Z"},"content_sha256":"bd9f1414d430b0b0abb0074d98856bdb2e88a7c17e5405d1923eb9ab3fe897ed","schema_version":"1.0","event_id":"sha256:bd9f1414d430b0b0abb0074d98856bdb2e88a7c17e5405d1923eb9ab3fe897ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/bundle.json","state_url":"https://pith.science/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/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":"2026-08-07T19:54:49Z","links":{"resolver":"https://pith.science/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6","bundle":"https://pith.science/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/bundle.json","state":"https://pith.science/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKXAGLBTWHSTTVHUZLBR6VW5J6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BKXAGLBTWHSTTVHUZLBR6VW5J6","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":"4022dab88c7c7f83207b42c97b638d4fbb65d70286e58a02780b3b2e97641f88","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T08:09:05Z","title_canon_sha256":"49b9bb405e34dfd7140e9508b583b93bce13895464a33de831c08802c5dd4159"},"schema_version":"1.0","source":{"id":"2506.05429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05429","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05429v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05429","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"BKXAGLBTWHST","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"BKXAGLBTWHSTTVHU","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"BKXAGLBT","created_at":"2026-07-05T11:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:bd9f1414d430b0b0abb0074d98856bdb2e88a7c17e5405d1923eb9ab3fe897ed","target":"graph","created_at":"2026-07-05T11:17:02Z","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/2506.05429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning and visual question and answering. However, similar to traditional models, they are susceptible to small perturbations, posing a challenge to their robustness, particularly in deployment scenarios. Evaluating the robustness of these models requires perturbations in both the vision and language modalities to learn their inter-modal dependencies. In this work, we train a generic surrogate model that can take both image ","authors_text":"Antonio Guillen, Ashwin Ramesh Babu, Avisek Naug, Ricardo Luna Gutierrez, Sahand Ghorbanpour, Sajad Mousavi, Soumyendu Sarkar, Vineet Gundecha","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T08:09:05Z","title":"Coordinated Robustness Evaluation Framework for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05429","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":"sha256:01bfe27095d2fddf5c9b7915f23cc8c33cbc830f54e9fc2e1004fca2e999c5c1","target":"record","created_at":"2026-07-05T11:17:02Z","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":"4022dab88c7c7f83207b42c97b638d4fbb65d70286e58a02780b3b2e97641f88","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T08:09:05Z","title_canon_sha256":"49b9bb405e34dfd7140e9508b583b93bce13895464a33de831c08802c5dd4159"},"schema_version":"1.0","source":{"id":"2506.05429","kind":"arxiv","version":1}},"canonical_sha256":"0aae032c33b1e539d4f4cac31f56dd4faccad56c4ebc1a5832e17ba302f35b63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aae032c33b1e539d4f4cac31f56dd4faccad56c4ebc1a5832e17ba302f35b63","first_computed_at":"2026-07-05T11:17:02.481015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:02.481015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Uiawmt2OcZmyXHiYSpP1K/4vfkkkJZywWFqs2wWZ4RNpxtVLAAGFJSAzAhgo8hLwSKaM3VYL0AYv5gLdOWWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:02.481481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01bfe27095d2fddf5c9b7915f23cc8c33cbc830f54e9fc2e1004fca2e999c5c1","sha256:bd9f1414d430b0b0abb0074d98856bdb2e88a7c17e5405d1923eb9ab3fe897ed"],"state_sha256":"f7cf14387126af3f052ddd04b0cb956ee6e33932290c78e81feee3525527edf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIlaQ781D0n6U+BrkltLvcbKoXPFAk3GlVamlky4YQb1MNODMGNCR9+1/1H9bo0aZrTa6fZ8oMppeJfSYs4VCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:54:49.470925Z","bundle_sha256":"285d7e4a7373b598c14fa0caf3b1ae7de8e9ce14bff09ae5d0faca45d8a92213"}}