{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F5NYIVJAJPWDJ2BS7W4AU6CQFN","short_pith_number":"pith:F5NYIVJA","canonical_record":{"source":{"id":"2411.00238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T22:24:47Z","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"title_canon_sha256":"44f0e6dc47ffab5cf2ae0d3091856dc7c8122a7f78cbc226c092a85f668aa313","abstract_canon_sha256":"9c31a46f9faa8124e0ec23d9e42693e88088ee99fc5cbb90f8e6c21dac3edeb0"},"schema_version":"1.0"},"canonical_sha256":"2f5b8455204bec34e832fdb80a78502b69d0a2b7b02517f2b671858c4fcbe526","source":{"kind":"arxiv","id":"2411.00238","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00238","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00238v2","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00238","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"F5NYIVJAJPWD","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"F5NYIVJAJPWDJ2BS","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"F5NYIVJA","created_at":"2026-07-05T10:50:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F5NYIVJAJPWDJ2BS7W4AU6CQFN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T22:24:47Z","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"title_canon_sha256":"44f0e6dc47ffab5cf2ae0d3091856dc7c8122a7f78cbc226c092a85f668aa313","abstract_canon_sha256":"9c31a46f9faa8124e0ec23d9e42693e88088ee99fc5cbb90f8e6c21dac3edeb0"},"schema_version":"1.0"},"canonical_sha256":"2f5b8455204bec34e832fdb80a78502b69d0a2b7b02517f2b671858c4fcbe526","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:10.049606Z","signature_b64":"K/FjOmcq9IJVfsmZ9VAKdsNvwBocThr7bSbf7yDvNoTkkB2MfoHeIknhcHgXO6JJT7D7kZ1qd9qcNHkghOjTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5b8455204bec34e832fdb80a78502b69d0a2b7b02517f2b671858c4fcbe526","last_reissued_at":"2026-07-05T10:50:10.049114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:10.049114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00238","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":"2026-07-05T10:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CiVcnucj7jiZVODgv6/C43hu8HG9Iln4HS62Rek18K8ge82auyPDVyGoyMQ1TgyGXQWGG2N2oynpcf1mRSrcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:25:32.397655Z"},"content_sha256":"0c6ff14fc07d19808c5b70be30e83b3675abdd53fc21d61cc11d41c8ed07aef0","schema_version":"1.0","event_id":"sha256:0c6ff14fc07d19808c5b70be30e83b3675abdd53fc21d61cc11d41c8ed07aef0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F5NYIVJAJPWDJ2BS7W4AU6CQFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Alexander Ku, Amogh Joshi, Declan Campbell, Jonathan D. Cohen, Kia Ghods, Nicol\\`o De Sabbata, Steven M. Frankland, Sunayana Rane, Taylor W. Webb, Thomas L. Griffiths, Tyler Giallanza","submitted_at":"2024-10-31T22:24:47Z","abstract_excerpt":"Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array of complex, naturalistic images, yet they exhibit surprising failures on basic multi-object reasoning tasks -- such as counting, localization, and simple forms of visual analogy -- that humans perform with near perfect accuracy. To better understand this puzzling pattern of successes and failures, we turn to theoretical accounts of the binding pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00238","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/2411.00238/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":"2026-07-05T10:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CGa+DuCKkllkZ06PCfdaAqh6dwrv68kCnJncDPukVHVW+Bm7LDbC6x9rU77hXzu/eh+rcgSeMhCVP8OGZIOXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:25:32.398300Z"},"content_sha256":"411d5e2a590d654edeb8814d8bcbec63c105f8948c780b283acc30079eb51cdc","schema_version":"1.0","event_id":"sha256:411d5e2a590d654edeb8814d8bcbec63c105f8948c780b283acc30079eb51cdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/bundle.json","state_url":"https://pith.science/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/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":"2026-07-07T07:25:32Z","links":{"resolver":"https://pith.science/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN","bundle":"https://pith.science/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/bundle.json","state":"https://pith.science/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5NYIVJAJPWDJ2BS7W4AU6CQFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5NYIVJAJPWDJ2BS7W4AU6CQFN","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":"9c31a46f9faa8124e0ec23d9e42693e88088ee99fc5cbb90f8e6c21dac3edeb0","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T22:24:47Z","title_canon_sha256":"44f0e6dc47ffab5cf2ae0d3091856dc7c8122a7f78cbc226c092a85f668aa313"},"schema_version":"1.0","source":{"id":"2411.00238","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00238","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00238v2","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00238","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"F5NYIVJAJPWD","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"F5NYIVJAJPWDJ2BS","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"F5NYIVJA","created_at":"2026-07-05T10:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:411d5e2a590d654edeb8814d8bcbec63c105f8948c780b283acc30079eb51cdc","target":"graph","created_at":"2026-07-05T10:50:10Z","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/2411.00238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array of complex, naturalistic images, yet they exhibit surprising failures on basic multi-object reasoning tasks -- such as counting, localization, and simple forms of visual analogy -- that humans perform with near perfect accuracy. To better understand this puzzling pattern of successes and failures, we turn to theoretical accounts of the binding pro","authors_text":"Alexander Ku, Amogh Joshi, Declan Campbell, Jonathan D. Cohen, Kia Ghods, Nicol\\`o De Sabbata, Steven M. Frankland, Sunayana Rane, Taylor W. Webb, Thomas L. Griffiths, Tyler Giallanza","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T22:24:47Z","title":"Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00238","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":"sha256:0c6ff14fc07d19808c5b70be30e83b3675abdd53fc21d61cc11d41c8ed07aef0","target":"record","created_at":"2026-07-05T10:50:10Z","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":"9c31a46f9faa8124e0ec23d9e42693e88088ee99fc5cbb90f8e6c21dac3edeb0","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T22:24:47Z","title_canon_sha256":"44f0e6dc47ffab5cf2ae0d3091856dc7c8122a7f78cbc226c092a85f668aa313"},"schema_version":"1.0","source":{"id":"2411.00238","kind":"arxiv","version":2}},"canonical_sha256":"2f5b8455204bec34e832fdb80a78502b69d0a2b7b02517f2b671858c4fcbe526","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5b8455204bec34e832fdb80a78502b69d0a2b7b02517f2b671858c4fcbe526","first_computed_at":"2026-07-05T10:50:10.049114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:10.049114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/FjOmcq9IJVfsmZ9VAKdsNvwBocThr7bSbf7yDvNoTkkB2MfoHeIknhcHgXO6JJT7D7kZ1qd9qcNHkghOjTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:10.049606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00238","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c6ff14fc07d19808c5b70be30e83b3675abdd53fc21d61cc11d41c8ed07aef0","sha256:411d5e2a590d654edeb8814d8bcbec63c105f8948c780b283acc30079eb51cdc"],"state_sha256":"fa80cdad542e2c818ba89dff53296701760e42fc5d8dd2f27ccf2a6832b56a35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gawlbk+9Hhh1OYh41MgHyKJdaJ6WP1E0uyWBHVl4nt5siKDf0Brv3qqkIdXcQ9y4dZF0NUC/+IjPFqM/bdHLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:25:32.401885Z","bundle_sha256":"1d311656d0bd68e7df1ee0f6a5eeff5cff22dc0c0cc643bbd3a12a7b615cb4c1"}}