{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XPTLMQAXPJSV6AN7N6KLZSBDB7","short_pith_number":"pith:XPTLMQAX","schema_version":"1.0","canonical_sha256":"bbe6b640177a655f01bf6f94bcc8230ffb97ab106071da3fb7f4b99082f78ba6","source":{"kind":"arxiv","id":"2404.10226","version":1},"attestation_state":"computed","paper":{"title":"Find The Gap: Knowledge Base Reasoning For Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Elham J. Barezi, Parisa Kordjamshidi","submitted_at":"2024-04-16T02:11:46Z","abstract_excerpt":"We analyze knowledge-based visual question answering, for which given a question, the models need to ground it into the visual modality and retrieve the relevant knowledge from a given large knowledge base (KB) to be able to answer. Our analysis has two folds, one based on designing neural architectures and training them from scratch, and another based on large pre-trained language models (LLMs). Our research questions are: 1) Can we effectively augment models by explicit supervised retrieval of the relevant KB information to solve the KB-VQA problem? 2) How do task-specific and LLM-based mode"},"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":"2404.10226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T02:11:46Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"bf8506153fe10f6177bfd26f43c2528651c05751104dd4ed8d41a559dffba530","abstract_canon_sha256":"b0af8916f5eca8c115b1c208e35e4db6b01bb9e1299ae9206a4245d52c08b06d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:27.075651Z","signature_b64":"ZP5gOffe+b6p5K+0VT8GYOPaqRqMoB4EkrWV1vrqcgYd5FNaa5JEoppgE5fX5wr6zihJgPku5uRrXthAEORoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe6b640177a655f01bf6f94bcc8230ffb97ab106071da3fb7f4b99082f78ba6","last_reissued_at":"2026-07-05T08:08:27.075235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:27.075235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Find The Gap: Knowledge Base Reasoning For Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Elham J. Barezi, Parisa Kordjamshidi","submitted_at":"2024-04-16T02:11:46Z","abstract_excerpt":"We analyze knowledge-based visual question answering, for which given a question, the models need to ground it into the visual modality and retrieve the relevant knowledge from a given large knowledge base (KB) to be able to answer. Our analysis has two folds, one based on designing neural architectures and training them from scratch, and another based on large pre-trained language models (LLMs). Our research questions are: 1) Can we effectively augment models by explicit supervised retrieval of the relevant KB information to solve the KB-VQA problem? 2) How do task-specific and LLM-based mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10226","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/2404.10226/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":"2404.10226","created_at":"2026-07-05T08:08:27.075294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10226v1","created_at":"2026-07-05T08:08:27.075294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10226","created_at":"2026-07-05T08:08:27.075294+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPTLMQAXPJSV","created_at":"2026-07-05T08:08:27.075294+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPTLMQAXPJSV6AN7","created_at":"2026-07-05T08:08:27.075294+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPTLMQAX","created_at":"2026-07-05T08:08:27.075294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19354","citing_title":"GC-KBVQA: A New Four-Stage Framework for Enhancing Knowledge Based Visual Question Answering Performance","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7","json":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7.json","graph_json":"https://pith.science/api/pith-number/XPTLMQAXPJSV6AN7N6KLZSBDB7/graph.json","events_json":"https://pith.science/api/pith-number/XPTLMQAXPJSV6AN7N6KLZSBDB7/events.json","paper":"https://pith.science/paper/XPTLMQAX"},"agent_actions":{"view_html":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7","download_json":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7.json","view_paper":"https://pith.science/paper/XPTLMQAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10226&json=true","fetch_graph":"https://pith.science/api/pith-number/XPTLMQAXPJSV6AN7N6KLZSBDB7/graph.json","fetch_events":"https://pith.science/api/pith-number/XPTLMQAXPJSV6AN7N6KLZSBDB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7/action/storage_attestation","attest_author":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7/action/author_attestation","sign_citation":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7/action/citation_signature","submit_replication":"https://pith.science/pith/XPTLMQAXPJSV6AN7N6KLZSBDB7/action/replication_record"}},"created_at":"2026-07-05T08:08:27.075294+00:00","updated_at":"2026-07-05T08:08:27.075294+00:00"}