{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VVLZBRQVZKD3XUDFR4VYSIN2YD","short_pith_number":"pith:VVLZBRQV","canonical_record":{"source":{"id":"2504.16727","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T14:01:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c5bb20cff0afdb7efac00bdcd1ebca5029addaff13fd21535492ac3bf98a335","abstract_canon_sha256":"2fb024331d541f9d1760f7fa99332d80092fe97e5cf19f4183fe6dce22e6fbf3"},"schema_version":"1.0"},"canonical_sha256":"ad5790c615ca87bbd0658f2b8921bac0f9150119f105a732c19ce315901695fb","source":{"kind":"arxiv","id":"2504.16727","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16727","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16727v3","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16727","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"VVLZBRQVZKD3","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"VVLZBRQVZKD3XUDF","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"VVLZBRQV","created_at":"2026-07-05T11:14:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VVLZBRQVZKD3XUDFR4VYSIN2YD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16727","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T14:01:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c5bb20cff0afdb7efac00bdcd1ebca5029addaff13fd21535492ac3bf98a335","abstract_canon_sha256":"2fb024331d541f9d1760f7fa99332d80092fe97e5cf19f4183fe6dce22e6fbf3"},"schema_version":"1.0"},"canonical_sha256":"ad5790c615ca87bbd0658f2b8921bac0f9150119f105a732c19ce315901695fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:06.544380Z","signature_b64":"QkTDZKgHNHTkF5JxGOenUqEVy+td7kiPmov5VroTwQj8r4AqzXH84NwtbJ5gZiQBi1R3Uwz+i4thunYdmgzkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad5790c615ca87bbd0658f2b8921bac0f9150119f105a732c19ce315901695fb","last_reissued_at":"2026-07-05T11:14:06.543889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:06.543889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16727","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDC0/56+iAoQdTApuf9QHRi06ZazEAi6Axlfq9G5yQxhsT76kWu9VVy1Hl/XrPRmCKDjkIk9SYbvmJRfA3/rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:42:23.603559Z"},"content_sha256":"314591f5049ac5ed1debf9793d0f34fcaf6aff20ab10256d9738f479ec7f4584","schema_version":"1.0","event_id":"sha256:314591f5049ac5ed1debf9793d0f34fcaf6aff20ab10256d9738f479ec7f4584"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VVLZBRQVZKD3XUDFR4VYSIN2YD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Sandeep Polisetty, Yi R. Fung, Yumeng Wang, Zhiyuan Fan","submitted_at":"2025-04-23T14:01:32Z","abstract_excerpt":"Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a sur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16727","kind":"arxiv","version":3},"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/2504.16727/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":"2026-07-05T11:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCD5oTjynUQMf8BJKYuEQIlSks9wrcvorGSoC/bl0u+qwL5J16M45IhDy9qEyLd2VuDZKuynKlylNC+q2EI2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:42:23.604142Z"},"content_sha256":"63079275c84556fb6acc330674825e069217cba4b0e8fb3ce2789e9bec895729","schema_version":"1.0","event_id":"sha256:63079275c84556fb6acc330674825e069217cba4b0e8fb3ce2789e9bec895729"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/bundle.json","state_url":"https://pith.science/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/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":"2026-08-18T00:42:23Z","links":{"resolver":"https://pith.science/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD","bundle":"https://pith.science/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/bundle.json","state":"https://pith.science/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVLZBRQVZKD3XUDFR4VYSIN2YD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VVLZBRQVZKD3XUDFR4VYSIN2YD","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":"2fb024331d541f9d1760f7fa99332d80092fe97e5cf19f4183fe6dce22e6fbf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T14:01:32Z","title_canon_sha256":"3c5bb20cff0afdb7efac00bdcd1ebca5029addaff13fd21535492ac3bf98a335"},"schema_version":"1.0","source":{"id":"2504.16727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16727","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16727v3","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16727","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"VVLZBRQVZKD3","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"VVLZBRQVZKD3XUDF","created_at":"2026-07-05T11:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"VVLZBRQV","created_at":"2026-07-05T11:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:63079275c84556fb6acc330674825e069217cba4b0e8fb3ce2789e9bec895729","target":"graph","created_at":"2026-07-05T11:14:06Z","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/2504.16727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a sur","authors_text":"Sandeep Polisetty, Yi R. Fung, Yumeng Wang, Zhiyuan Fan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T14:01:32Z","title":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16727","kind":"arxiv","version":3},"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":"sha256:314591f5049ac5ed1debf9793d0f34fcaf6aff20ab10256d9738f479ec7f4584","target":"record","created_at":"2026-07-05T11:14:06Z","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":"2fb024331d541f9d1760f7fa99332d80092fe97e5cf19f4183fe6dce22e6fbf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T14:01:32Z","title_canon_sha256":"3c5bb20cff0afdb7efac00bdcd1ebca5029addaff13fd21535492ac3bf98a335"},"schema_version":"1.0","source":{"id":"2504.16727","kind":"arxiv","version":3}},"canonical_sha256":"ad5790c615ca87bbd0658f2b8921bac0f9150119f105a732c19ce315901695fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad5790c615ca87bbd0658f2b8921bac0f9150119f105a732c19ce315901695fb","first_computed_at":"2026-07-05T11:14:06.543889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:06.543889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkTDZKgHNHTkF5JxGOenUqEVy+td7kiPmov5VroTwQj8r4AqzXH84NwtbJ5gZiQBi1R3Uwz+i4thunYdmgzkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:06.544380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:314591f5049ac5ed1debf9793d0f34fcaf6aff20ab10256d9738f479ec7f4584","sha256:63079275c84556fb6acc330674825e069217cba4b0e8fb3ce2789e9bec895729"],"state_sha256":"c81212f22d9c92f69439bd353394d7386adb1da5f6242d86d0e26b9009f4d1b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljdpcIYBSNF/IyEcVxiqiLhCYeT/hwHAtwPh3eKr3P0cJ6okBbum6DQ/TEm+MfnSS42MhybZFKPJkTIoUZRoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:42:23.615082Z","bundle_sha256":"ae85236912658bf2e3bf70c11d42609aee725daf24b4db27a4c75bfffdb59f0e"}}