{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A7M6PB2CMS5J53NQXSLDLZPZ5L","short_pith_number":"pith:A7M6PB2C","schema_version":"1.0","canonical_sha256":"07d9e7874264ba9eedb0bc9635e5f9eaf7ab739247ff39ce069bc8d5898d6bd1","source":{"kind":"arxiv","id":"2402.05472","version":1},"attestation_state":"computed","paper":{"title":"Question Aware Vision Transformer for Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aviad Aberdam, Elad Ben Avraham, Oren Nuriel, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","submitted_at":"2024-02-08T08:03:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.05472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T08:03:39Z","cross_cats_sorted":[],"title_canon_sha256":"6ec68299982b539d71a57320c458065a4796234e97319bd9f21ecc58ae4f6198","abstract_canon_sha256":"f6bd92c596b2c487848371ac9664be7c08b10cb8edc2fc0c0863e9df52dc5c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:50.851286Z","signature_b64":"tgyri3WffrKb9zXo3hKlGwKrWYm09963YevmFUPGHlkskhUTTfPnDEAhXUA4Zl1nPwm7I3LWGpSC1+11m7tTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07d9e7874264ba9eedb0bc9635e5f9eaf7ab739247ff39ce069bc8d5898d6bd1","last_reissued_at":"2026-07-05T07:42:50.850807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:50.850807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Question Aware Vision Transformer for Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aviad Aberdam, Elad Ben Avraham, Oren Nuriel, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","submitted_at":"2024-02-08T08:03:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05472","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/2402.05472/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.05472","created_at":"2026-07-05T07:42:50.850866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05472v1","created_at":"2026-07-05T07:42:50.850866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05472","created_at":"2026-07-05T07:42:50.850866+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7M6PB2CMS5J","created_at":"2026-07-05T07:42:50.850866+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7M6PB2CMS5J53NQ","created_at":"2026-07-05T07:42:50.850866+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7M6PB2C","created_at":"2026-07-05T07:42:50.850866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L","json":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L.json","graph_json":"https://pith.science/api/pith-number/A7M6PB2CMS5J53NQXSLDLZPZ5L/graph.json","events_json":"https://pith.science/api/pith-number/A7M6PB2CMS5J53NQXSLDLZPZ5L/events.json","paper":"https://pith.science/paper/A7M6PB2C"},"agent_actions":{"view_html":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L","download_json":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L.json","view_paper":"https://pith.science/paper/A7M6PB2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05472&json=true","fetch_graph":"https://pith.science/api/pith-number/A7M6PB2CMS5J53NQXSLDLZPZ5L/graph.json","fetch_events":"https://pith.science/api/pith-number/A7M6PB2CMS5J53NQXSLDLZPZ5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L/action/storage_attestation","attest_author":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L/action/author_attestation","sign_citation":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L/action/citation_signature","submit_replication":"https://pith.science/pith/A7M6PB2CMS5J53NQXSLDLZPZ5L/action/replication_record"}},"created_at":"2026-07-05T07:42:50.850866+00:00","updated_at":"2026-07-05T07:42:50.850866+00:00"}