{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A7M6PB2CMS5J53NQXSLDLZPZ5L","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":"f6bd92c596b2c487848371ac9664be7c08b10cb8edc2fc0c0863e9df52dc5c67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T08:03:39Z","title_canon_sha256":"6ec68299982b539d71a57320c458065a4796234e97319bd9f21ecc58ae4f6198"},"schema_version":"1.0","source":{"id":"2402.05472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05472","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05472v1","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05472","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"A7M6PB2CMS5J","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"A7M6PB2CMS5J53NQ","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"A7M6PB2C","created_at":"2026-07-05T07:42:50Z"}],"graph_snapshots":[{"event_id":"sha256:d28d8a7f2be17f4dbd4dc4c7f676620e3391cbf136458566715899ccb1ad7db4","target":"graph","created_at":"2026-07-05T07:42:50Z","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/2402.05472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that aligns visual features with the LLM's representation space. Despite their success, a critical limitation persists: the vision encoding process remains decoupled from user queries, often in the form of image-related questions. Consequently, the resulting visual features may not be optimally attuned to the query-specific elements of the image. To address this, w","authors_text":"Aviad Aberdam, Elad Ben Avraham, Oren Nuriel, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T08:03:39Z","title":"Question Aware Vision Transformer for Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05472","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":"sha256:8528e46121d2de90aa7b6d91b5f29c8060fa437d89731c09a03f5ec355d7af3c","target":"record","created_at":"2026-07-05T07:42:50Z","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":"f6bd92c596b2c487848371ac9664be7c08b10cb8edc2fc0c0863e9df52dc5c67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T08:03:39Z","title_canon_sha256":"6ec68299982b539d71a57320c458065a4796234e97319bd9f21ecc58ae4f6198"},"schema_version":"1.0","source":{"id":"2402.05472","kind":"arxiv","version":1}},"canonical_sha256":"07d9e7874264ba9eedb0bc9635e5f9eaf7ab739247ff39ce069bc8d5898d6bd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07d9e7874264ba9eedb0bc9635e5f9eaf7ab739247ff39ce069bc8d5898d6bd1","first_computed_at":"2026-07-05T07:42:50.850807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:50.850807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tgyri3WffrKb9zXo3hKlGwKrWYm09963YevmFUPGHlkskhUTTfPnDEAhXUA4Zl1nPwm7I3LWGpSC1+11m7tTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:50.851286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8528e46121d2de90aa7b6d91b5f29c8060fa437d89731c09a03f5ec355d7af3c","sha256:d28d8a7f2be17f4dbd4dc4c7f676620e3391cbf136458566715899ccb1ad7db4"],"state_sha256":"088c9163881a03194bc6072c4ea0532d375ac26a40cb902d5159d4c33e23da62"}