{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7D6UCQRCAW5NHWKV2GPQ7PB6MD","short_pith_number":"pith:7D6UCQRC","canonical_record":{"source":{"id":"2506.08008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9060cd254f77d0d761d1d857b86003cdc834d66579c2b1a6b61c0f51e1a4253","abstract_canon_sha256":"79b38f8fffb8eca7d934b6bada7881ba908b44998079df374ce2edee39da57d4"},"schema_version":"1.0"},"canonical_sha256":"f8fd41422205bad3d955d19f0fbc3e60d23852d4b0154b35bb8ddbf147837a65","source":{"kind":"arxiv","id":"2506.08008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08008","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08008v1","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08008","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"7D6UCQRCAW5N","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"7D6UCQRCAW5NHWKV","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"7D6UCQRC","created_at":"2026-07-05T11:18:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7D6UCQRCAW5NHWKV2GPQ7PB6MD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c9060cd254f77d0d761d1d857b86003cdc834d66579c2b1a6b61c0f51e1a4253","abstract_canon_sha256":"79b38f8fffb8eca7d934b6bada7881ba908b44998079df374ce2edee39da57d4"},"schema_version":"1.0"},"canonical_sha256":"f8fd41422205bad3d955d19f0fbc3e60d23852d4b0154b35bb8ddbf147837a65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:37.185261Z","signature_b64":"P7kqk1DcPD1J4tW3llv+WMN0DU2AcQMwzOIdIXzMYq5+Qx3j1Bm6xuFrApPBQMGoX//FZiysPTz7zi+msr07BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8fd41422205bad3d955d19f0fbc3e60d23852d4b0154b35bb8ddbf147837a65","last_reissued_at":"2026-07-05T11:18:37.184781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:37.184781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08008","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":"2026-07-05T11:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vi/xSJY/Wu5BiQdi0W14aCPErf0OPIGxZ8f3GeIL4JJTi4CpW7Duuv2Ytpq6IOhuqTXXzC6FTM6HfPiJmDepCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:31:24.922130Z"},"content_sha256":"5637cd6a950a449343f9a7a03fc0883306f9586080da6aa93a5c754e010d5ab8","schema_version":"1.0","event_id":"sha256:5637cd6a950a449343f9a7a03fc0883306f9586080da6aa93a5c754e010d5ab8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7D6UCQRCAW5NHWKV2GPQ7PB6MD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hidden in plain sight: VLMs overlook their visual representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Devin Guillory, Stephanie Fu, Trevor Darrell, Tyler Bonnen","submitted_at":"2025-06-09T17:59:54Z","abstract_excerpt":"Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a direct readout of their visual encoders to understand their ability to integrate across these modalities. Across a series of vision-centric benchmarks (e.g., depth estimation, correspondence), we find that VLMs perform substantially worse than their visual encoders, dropping to near-chance performance. We investigate these results through a series of analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08008","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/2506.08008/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":"2026-07-05T11:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oINobpVZdwKStHkyg6Yrm24+Qn1XYMPSklOvCmbmcrRolCHerBRGHypNe1L7XtZy+GY9Al606YgbOKobV9KqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:31:24.922534Z"},"content_sha256":"0fc889ace1b57842daef259a3c926fa1d3bd8554f80a3561c8ebdab4c0551eaf","schema_version":"1.0","event_id":"sha256:0fc889ace1b57842daef259a3c926fa1d3bd8554f80a3561c8ebdab4c0551eaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/bundle.json","state_url":"https://pith.science/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/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":"2026-07-20T10:31:24Z","links":{"resolver":"https://pith.science/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD","bundle":"https://pith.science/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/bundle.json","state":"https://pith.science/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7D6UCQRCAW5NHWKV2GPQ7PB6MD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7D6UCQRCAW5NHWKV2GPQ7PB6MD","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":"79b38f8fffb8eca7d934b6bada7881ba908b44998079df374ce2edee39da57d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:54Z","title_canon_sha256":"c9060cd254f77d0d761d1d857b86003cdc834d66579c2b1a6b61c0f51e1a4253"},"schema_version":"1.0","source":{"id":"2506.08008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08008","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08008v1","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08008","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"7D6UCQRCAW5N","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"7D6UCQRCAW5NHWKV","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"7D6UCQRC","created_at":"2026-07-05T11:18:37Z"}],"graph_snapshots":[{"event_id":"sha256:0fc889ace1b57842daef259a3c926fa1d3bd8554f80a3561c8ebdab4c0551eaf","target":"graph","created_at":"2026-07-05T11:18:37Z","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/2506.08008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a direct readout of their visual encoders to understand their ability to integrate across these modalities. Across a series of vision-centric benchmarks (e.g., depth estimation, correspondence), we find that VLMs perform substantially worse than their visual encoders, dropping to near-chance performance. We investigate these results through a series of analys","authors_text":"Devin Guillory, Stephanie Fu, Trevor Darrell, Tyler Bonnen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:54Z","title":"Hidden in plain sight: VLMs overlook their visual representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08008","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":"sha256:5637cd6a950a449343f9a7a03fc0883306f9586080da6aa93a5c754e010d5ab8","target":"record","created_at":"2026-07-05T11:18:37Z","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":"79b38f8fffb8eca7d934b6bada7881ba908b44998079df374ce2edee39da57d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:54Z","title_canon_sha256":"c9060cd254f77d0d761d1d857b86003cdc834d66579c2b1a6b61c0f51e1a4253"},"schema_version":"1.0","source":{"id":"2506.08008","kind":"arxiv","version":1}},"canonical_sha256":"f8fd41422205bad3d955d19f0fbc3e60d23852d4b0154b35bb8ddbf147837a65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8fd41422205bad3d955d19f0fbc3e60d23852d4b0154b35bb8ddbf147837a65","first_computed_at":"2026-07-05T11:18:37.184781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:37.184781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P7kqk1DcPD1J4tW3llv+WMN0DU2AcQMwzOIdIXzMYq5+Qx3j1Bm6xuFrApPBQMGoX//FZiysPTz7zi+msr07BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:37.185261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5637cd6a950a449343f9a7a03fc0883306f9586080da6aa93a5c754e010d5ab8","sha256:0fc889ace1b57842daef259a3c926fa1d3bd8554f80a3561c8ebdab4c0551eaf"],"state_sha256":"122a5b4af57bf653624d87861fea128623e77fc1786a9454627bd398bb9258af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z3z3WehHDxW/9D6nv9mmsHJpcLuPG4Xp94KuXZXQ7jgD9IUANp7u5TF+zczdtG88RiWPtyU3yi2fy0dimOVRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T10:31:24.925220Z","bundle_sha256":"e2326210cb333200c78f62b6786d645864b2f73e403d01816ad7f3cf94919118"}}