{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IRFT7PVWVTD7G2CENVCSP635S6","short_pith_number":"pith:IRFT7PVW","canonical_record":{"source":{"id":"2408.06721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","cross_cats_sorted":[],"title_canon_sha256":"c99ad9c607da345b3c64bf1e081c043631c416bbdbefbdb8c36eb674e79f0182","abstract_canon_sha256":"1d3996242a7b7d6e787371fdd75022908ebcdd0d9943959b63048ee829c91332"},"schema_version":"1.0"},"canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","source":{"kind":"arxiv","id":"2408.06721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06721","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06721v1","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06721","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"IRFT7PVWVTD7","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"IRFT7PVWVTD7G2CE","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"IRFT7PVW","created_at":"2026-07-05T08:55:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IRFT7PVWVTD7G2CENVCSP635S6","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","cross_cats_sorted":[],"title_canon_sha256":"c99ad9c607da345b3c64bf1e081c043631c416bbdbefbdb8c36eb674e79f0182","abstract_canon_sha256":"1d3996242a7b7d6e787371fdd75022908ebcdd0d9943959b63048ee829c91332"},"schema_version":"1.0"},"canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:01.081162Z","signature_b64":"XEis3aBsK20+3y40GusHC7aA2qifPOYNHpdV/c9cdMNwgeEuyBtL+j6bScXmRu/2BcghWDPh8hB6NY5uLoCmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","last_reissued_at":"2026-07-05T08:55:01.080743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:01.080743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06721","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":"2026-07-05T08:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSK8NAaAMFzn6069VU8I+BdVmzqYP7NYz2sCdNxm1uuN/oIfsWVe5IlQ9Ca3KpEQ/JUDOTz/VEGCgx1RNjlxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:09.982948Z"},"content_sha256":"5617f05267bb4027150ed1f5f86809a50f7bc5044fd78ba4acc0f47dc56fac3a","schema_version":"1.0","event_id":"sha256:5617f05267bb4027150ed1f5f86809a50f7bc5044fd78ba4acc0f47dc56fac3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IRFT7PVWVTD7G2CENVCSP635S6","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":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Shivam Chandhok, Wan-Cyuan Fan","submitted_at":"2024-08-13T08:26:32Z","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, also lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks: object classification, understanding spatial arrangement, and ability to delineate individual object instances (through counting), by constructing a series of tests that probe which components of design, specifically, maybe lacking. Importantly, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06721","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/2408.06721/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":"2026-07-05T08:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5itMFUX1U4ifpnsnf5/GG6PkhI098+Ul6ODEHm3E1/FwsRg4OujGNDdp4x10bzgtxhisf83P6AA/CZ2THS5TDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:09.983847Z"},"content_sha256":"f0e5ca9b4a470480b30286147e4cf811c91896b1407f8dcc52c7ab880ea7ef32","schema_version":"1.0","event_id":"sha256:f0e5ca9b4a470480b30286147e4cf811c91896b1407f8dcc52c7ab880ea7ef32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/bundle.json","state_url":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRFT7PVWVTD7G2CENVCSP635S6/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":"2026-07-09T06:40:09Z","links":{"resolver":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6","bundle":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/bundle.json","state":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRFT7PVWVTD7G2CENVCSP635S6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IRFT7PVWVTD7G2CENVCSP635S6","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":"1d3996242a7b7d6e787371fdd75022908ebcdd0d9943959b63048ee829c91332","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","title_canon_sha256":"c99ad9c607da345b3c64bf1e081c043631c416bbdbefbdb8c36eb674e79f0182"},"schema_version":"1.0","source":{"id":"2408.06721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06721","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06721v1","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06721","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"IRFT7PVWVTD7","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"IRFT7PVWVTD7G2CE","created_at":"2026-07-05T08:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"IRFT7PVW","created_at":"2026-07-05T08:55:01Z"}],"graph_snapshots":[{"event_id":"sha256:f0e5ca9b4a470480b30286147e4cf811c91896b1407f8dcc52c7ab880ea7ef32","target":"graph","created_at":"2026-07-05T08:55:01Z","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/2408.06721/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, also lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks: object classification, understanding spatial arrangement, and ability to delineate individual object instances (through counting), by constructing a series of tests that probe which components of design, specifically, maybe lacking. Importantly, ","authors_text":"Leonid Sigal, Shivam Chandhok, Wan-Cyuan Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","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":"2408.06721","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":"sha256:5617f05267bb4027150ed1f5f86809a50f7bc5044fd78ba4acc0f47dc56fac3a","target":"record","created_at":"2026-07-05T08:55:01Z","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":"1d3996242a7b7d6e787371fdd75022908ebcdd0d9943959b63048ee829c91332","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","title_canon_sha256":"c99ad9c607da345b3c64bf1e081c043631c416bbdbefbdb8c36eb674e79f0182"},"schema_version":"1.0","source":{"id":"2408.06721","kind":"arxiv","version":1}},"canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","first_computed_at":"2026-07-05T08:55:01.080743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:01.080743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XEis3aBsK20+3y40GusHC7aA2qifPOYNHpdV/c9cdMNwgeEuyBtL+j6bScXmRu/2BcghWDPh8hB6NY5uLoCmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:01.081162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5617f05267bb4027150ed1f5f86809a50f7bc5044fd78ba4acc0f47dc56fac3a","sha256:f0e5ca9b4a470480b30286147e4cf811c91896b1407f8dcc52c7ab880ea7ef32"],"state_sha256":"5bfcce6a446705fef5fd1d24a506c3a380ed893dd6b061eb14b0853112fc0e32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PiAmv34rbPCbXEN0Dkv6uxx59iByFfXZb9Nvxzi/IAZ4u3/4pQvCo3LXDgQchnLbCIDmmtkb9JBGghd659WGBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:40:09.988296Z","bundle_sha256":"9543b45183ed3096b0f08508bb648c5f0da0f34029f7d692bbfa47ad947d8b7e"}}