{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ID67LVCXRBB52RNNTYSRR3ZWCB","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":"84fa500758c105670ef69ffc7eed09a75393f549d9cfc9d4b5c0596fe0e33930","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:55:02Z","title_canon_sha256":"b0891b1cd4a67f7ee725829ad7b87ebe64785a7d328dbe4af76d3e713ae84f67"},"schema_version":"1.0","source":{"id":"2410.07149","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07149","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07149v2","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07149","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"ID67LVCXRBB5","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"ID67LVCXRBB52RNN","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"ID67LVCX","created_at":"2026-07-05T10:54:13Z"}],"graph_snapshots":[{"event_id":"sha256:e64e1c0788301ea0be5e4dc3dfb3510c1b60309f43412f551e6fc3516306a082","target":"graph","created_at":"2026-07-05T10:54:13Z","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/2410.07149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the localization of object information, the evolution of visual token representations across layers, and the mechanism of integrating visual information for predictions. Through ablation studies, we demonstrated that object identification accuracy drops by over 70\\% when object-specific tokens are removed. We observed that visual token representations become increa","authors_text":"Clement Neo, David Krueger, Fazl Barez, Luke Ong, Mor Geva, Philip Torr","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:55:02Z","title":"Towards Interpreting Visual Information Processing in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07149","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":"sha256:574d33435f1746ee7596b9de608016386d99ee7eb512fe09aff5e0bb79b08906","target":"record","created_at":"2026-07-05T10:54:13Z","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":"84fa500758c105670ef69ffc7eed09a75393f549d9cfc9d4b5c0596fe0e33930","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:55:02Z","title_canon_sha256":"b0891b1cd4a67f7ee725829ad7b87ebe64785a7d328dbe4af76d3e713ae84f67"},"schema_version":"1.0","source":{"id":"2410.07149","kind":"arxiv","version":2}},"canonical_sha256":"40fdf5d4578843dd45ad9e2518ef361056bd3a56db60824b52ad8edbfa691137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40fdf5d4578843dd45ad9e2518ef361056bd3a56db60824b52ad8edbfa691137","first_computed_at":"2026-07-05T10:54:13.374800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:13.374800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53yReb7pC7tqFtOo1fXux70P4NZKuUPoxTeLM+jdF53MmJ/IQLVuAwjN7YBYJIunJNcpPC9Pv00LNN9x6OSEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:13.375304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07149","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:574d33435f1746ee7596b9de608016386d99ee7eb512fe09aff5e0bb79b08906","sha256:e64e1c0788301ea0be5e4dc3dfb3510c1b60309f43412f551e6fc3516306a082"],"state_sha256":"0cf18fce69c5b16820f79fc876a0492c19f4e1f46d376fafa84217905965d961"}