{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DSTEQN7YQMKTZFTX2GGUM6ASQD","short_pith_number":"pith:DSTEQN7Y","canonical_record":{"source":{"id":"2507.10442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:26:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7dcbb2201d1d48cd4dd92c6b1d5f0483908558685a9ef45d3acbd8d026397993","abstract_canon_sha256":"9e73402ba114d6c84c47809e2a191a937f7df8ae15722a238abde46826d80ee0"},"schema_version":"1.0"},"canonical_sha256":"1ca64837f883153c9677d18d46781280dbc285e09ade26c4b829b81fea87813c","source":{"kind":"arxiv","id":"2507.10442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10442","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10442v1","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10442","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"DSTEQN7YQMKT","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"DSTEQN7YQMKTZFTX","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"DSTEQN7Y","created_at":"2026-07-05T11:36:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DSTEQN7YQMKTZFTX2GGUM6ASQD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:26:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7dcbb2201d1d48cd4dd92c6b1d5f0483908558685a9ef45d3acbd8d026397993","abstract_canon_sha256":"9e73402ba114d6c84c47809e2a191a937f7df8ae15722a238abde46826d80ee0"},"schema_version":"1.0"},"canonical_sha256":"1ca64837f883153c9677d18d46781280dbc285e09ade26c4b829b81fea87813c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:51.329700Z","signature_b64":"SJeq7szUQmMgF4CwcoZGvc+epyh6g9CbzdT/MGlmYP/fHYNyM6j8vMoSH+F06b5M1ifTx2xAierN6U7Grp47Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca64837f883153c9677d18d46781280dbc285e09ade26c4b829b81fea87813c","last_reissued_at":"2026-07-05T11:36:51.329155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:51.329155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10442","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":"2026-07-05T11:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wfbj8lbwTsqKRXa1cemL7yUaxHlLB6XuGEMBTNDETSifCuzJgEfKLwF3Q4Fq3coAnFZRDk0jfKh6bP96B/r/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:47:14.941593Z"},"content_sha256":"4359bf275e8688c194243cfaf9e9587ad278d7bbc3426087fef754d6f8a126c3","schema_version":"1.0","event_id":"sha256:4359bf275e8688c194243cfaf9e9587ad278d7bbc3426087fef754d6f8a126c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DSTEQN7YQMKTZFTX2GGUM6ASQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leonid Sigal, Shivam Chandhok, Vered Shwartz, Vineeth N Balasubramanian, Wan-Cyuan Fan","submitted_at":"2025-07-10T15:26:41Z","abstract_excerpt":"Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10442","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/2507.10442/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":"2026-07-05T11:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcqTgo1CokZxafCQdY6k8k9HifweeWFVc6IbY4rllD9uAkB6m8iDSZZVOw9cDpfbiUafBLOMOXILxSlji9FMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:47:14.942355Z"},"content_sha256":"2b892134e479f26a07f14908682e7167d6de6951351e2ca51bf2424e3f045e01","schema_version":"1.0","event_id":"sha256:2b892134e479f26a07f14908682e7167d6de6951351e2ca51bf2424e3f045e01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/bundle.json","state_url":"https://pith.science/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/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":"2026-08-01T05:47:14Z","links":{"resolver":"https://pith.science/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD","bundle":"https://pith.science/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/bundle.json","state":"https://pith.science/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSTEQN7YQMKTZFTX2GGUM6ASQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DSTEQN7YQMKTZFTX2GGUM6ASQD","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":"9e73402ba114d6c84c47809e2a191a937f7df8ae15722a238abde46826d80ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:26:41Z","title_canon_sha256":"7dcbb2201d1d48cd4dd92c6b1d5f0483908558685a9ef45d3acbd8d026397993"},"schema_version":"1.0","source":{"id":"2507.10442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10442","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10442v1","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10442","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"DSTEQN7YQMKT","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"DSTEQN7YQMKTZFTX","created_at":"2026-07-05T11:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"DSTEQN7Y","created_at":"2026-07-05T11:36:51Z"}],"graph_snapshots":[{"event_id":"sha256:2b892134e479f26a07f14908682e7167d6de6951351e2ca51bf2424e3f045e01","target":"graph","created_at":"2026-07-05T11:36:51Z","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/2507.10442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and con","authors_text":"Leonid Sigal, Shivam Chandhok, Vered Shwartz, Vineeth N Balasubramanian, Wan-Cyuan Fan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:26:41Z","title":"Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10442","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":"sha256:4359bf275e8688c194243cfaf9e9587ad278d7bbc3426087fef754d6f8a126c3","target":"record","created_at":"2026-07-05T11:36:51Z","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":"9e73402ba114d6c84c47809e2a191a937f7df8ae15722a238abde46826d80ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:26:41Z","title_canon_sha256":"7dcbb2201d1d48cd4dd92c6b1d5f0483908558685a9ef45d3acbd8d026397993"},"schema_version":"1.0","source":{"id":"2507.10442","kind":"arxiv","version":1}},"canonical_sha256":"1ca64837f883153c9677d18d46781280dbc285e09ade26c4b829b81fea87813c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca64837f883153c9677d18d46781280dbc285e09ade26c4b829b81fea87813c","first_computed_at":"2026-07-05T11:36:51.329155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:51.329155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SJeq7szUQmMgF4CwcoZGvc+epyh6g9CbzdT/MGlmYP/fHYNyM6j8vMoSH+F06b5M1ifTx2xAierN6U7Grp47Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:51.329700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4359bf275e8688c194243cfaf9e9587ad278d7bbc3426087fef754d6f8a126c3","sha256:2b892134e479f26a07f14908682e7167d6de6951351e2ca51bf2424e3f045e01"],"state_sha256":"09b18c09172e4504f8269a6d9efb969ceaaaf2d2fa21d44fa6c9ea7ce7ee8bb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pR5OIbo0ZKLWPPNoISMtYzSU0JS/SVa96dWBiHCEJmUTGbxEVmDgEU503P9pUlKrTtxvEkxjpJib2uek991JBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:47:14.949862Z","bundle_sha256":"904e95ab29870c83cb8fe8437c331d91f72d0502517f7d9b11042bcb8fba3d82"}}