{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FUMMT2QM2UKOSED2NTKIY2NJRP","short_pith_number":"pith:FUMMT2QM","canonical_record":{"source":{"id":"2411.17491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:59:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01b9781937dd91ad4c1f98f189a5524f8fc785669e7b0deb57a149bfb7a9b458","abstract_canon_sha256":"73a5ec84aed8f855fece6980367512fbfe33e5a70432a839adce0640156522ec"},"schema_version":"1.0"},"canonical_sha256":"2d18c9ea0cd514e9107a6cd48c69a98be8f76028573c172e96033ce4671e14b0","source":{"kind":"arxiv","id":"2411.17491","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17491","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17491v1","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17491","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"FUMMT2QM2UKO","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"FUMMT2QM2UKOSED2","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"FUMMT2QM","created_at":"2026-07-05T09:40:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FUMMT2QM2UKOSED2NTKIY2NJRP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:59:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01b9781937dd91ad4c1f98f189a5524f8fc785669e7b0deb57a149bfb7a9b458","abstract_canon_sha256":"73a5ec84aed8f855fece6980367512fbfe33e5a70432a839adce0640156522ec"},"schema_version":"1.0"},"canonical_sha256":"2d18c9ea0cd514e9107a6cd48c69a98be8f76028573c172e96033ce4671e14b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:47.970372Z","signature_b64":"fJpDbWK36kdwH1m6FCW1li5iBm9zfsWMHRNiYKHTPwoanm2ti1wfbWr3FoYiCF8fwDC9Y9kSvcKAOIWZ+av7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d18c9ea0cd514e9107a6cd48c69a98be8f76028573c172e96033ce4671e14b0","last_reissued_at":"2026-07-05T09:40:47.969859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:47.969859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17491","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":"2026-07-05T09:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtum3fu3hN3zaJr+hwkANbKT4Jx7zkO+S003ab0mR83aYX81QgmaN14Q7x2Rt1cPzkYQ+X72BtiJ0RoUi7YcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:27:48.930227Z"},"content_sha256":"2a0a7045c56966e2f62d81c8b76d44f53b322bd084f493e185f28c6f2a593194","schema_version":"1.0","event_id":"sha256:2a0a7045c56966e2f62d81c8b76d44f53b322bd084f493e185f28c6f2a593194"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FUMMT2QM2UKOSED2NTKIY2NJRP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Omri Kaduri, Shai Bagon, Tali Dekel","submitted_at":"2024-11-26T14:59:06Z","abstract_excerpt":"Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we conduct a thorough empirical analysis, focusing on attention modules across layers. We reveal several key insights about how these models process visual data: (i) the internal representation of the query tokens (e.g., representations of \"describe the image\"), is utilized by VLMs to store global image information; we demonstrate that these models generate surpr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17491","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/2411.17491/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":"2026-07-05T09:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBbkDzGW/28duLPBoBjeCWY88sv88vKVz8r7Jsj/aXppTLBpg3XVydk0GD7YeT+yoi/O3EcvHlyTxJpYNG1jCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:27:48.930624Z"},"content_sha256":"ad0b56d9fc32e4dcec8787d873d203345ecb721652c8ab6d9a70e136099b3c56","schema_version":"1.0","event_id":"sha256:ad0b56d9fc32e4dcec8787d873d203345ecb721652c8ab6d9a70e136099b3c56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/bundle.json","state_url":"https://pith.science/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/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":"2026-07-13T17:27:48Z","links":{"resolver":"https://pith.science/pith/FUMMT2QM2UKOSED2NTKIY2NJRP","bundle":"https://pith.science/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/bundle.json","state":"https://pith.science/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FUMMT2QM2UKOSED2NTKIY2NJRP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FUMMT2QM2UKOSED2NTKIY2NJRP","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":"73a5ec84aed8f855fece6980367512fbfe33e5a70432a839adce0640156522ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:59:06Z","title_canon_sha256":"01b9781937dd91ad4c1f98f189a5524f8fc785669e7b0deb57a149bfb7a9b458"},"schema_version":"1.0","source":{"id":"2411.17491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17491","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17491v1","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17491","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"FUMMT2QM2UKO","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"FUMMT2QM2UKOSED2","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"FUMMT2QM","created_at":"2026-07-05T09:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:ad0b56d9fc32e4dcec8787d873d203345ecb721652c8ab6d9a70e136099b3c56","target":"graph","created_at":"2026-07-05T09:40:47Z","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/2411.17491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we conduct a thorough empirical analysis, focusing on attention modules across layers. We reveal several key insights about how these models process visual data: (i) the internal representation of the query tokens (e.g., representations of \"describe the image\"), is utilized by VLMs to store global image information; we demonstrate that these models generate surpr","authors_text":"Omri Kaduri, Shai Bagon, Tali Dekel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:59:06Z","title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17491","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":"sha256:2a0a7045c56966e2f62d81c8b76d44f53b322bd084f493e185f28c6f2a593194","target":"record","created_at":"2026-07-05T09:40:47Z","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":"73a5ec84aed8f855fece6980367512fbfe33e5a70432a839adce0640156522ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:59:06Z","title_canon_sha256":"01b9781937dd91ad4c1f98f189a5524f8fc785669e7b0deb57a149bfb7a9b458"},"schema_version":"1.0","source":{"id":"2411.17491","kind":"arxiv","version":1}},"canonical_sha256":"2d18c9ea0cd514e9107a6cd48c69a98be8f76028573c172e96033ce4671e14b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d18c9ea0cd514e9107a6cd48c69a98be8f76028573c172e96033ce4671e14b0","first_computed_at":"2026-07-05T09:40:47.969859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:47.969859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJpDbWK36kdwH1m6FCW1li5iBm9zfsWMHRNiYKHTPwoanm2ti1wfbWr3FoYiCF8fwDC9Y9kSvcKAOIWZ+av7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:47.970372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a0a7045c56966e2f62d81c8b76d44f53b322bd084f493e185f28c6f2a593194","sha256:ad0b56d9fc32e4dcec8787d873d203345ecb721652c8ab6d9a70e136099b3c56"],"state_sha256":"94c022efb7c71b37bebbb904f210a788ac305715087eb4223fb119ee20c17b95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jHU+Q+9QBXZd8mJqU1ZAo5IF0bBrVa4KN3QGnlCvlN0RmCqjjCK2dpVjJglV3KOuutZJOpjm3gDsbJsmamZTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T17:27:48.932633Z","bundle_sha256":"d39354de0314814cbfc001354b16a5b18bfe4ac9eb13e8bc9202033b2af3c33e"}}