{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZUGNDLP5IFDLLAB3LE6V5ETL4","short_pith_number":"pith:DZUGNDLP","schema_version":"1.0","canonical_sha256":"1e68668d6fea0a35ac01dac9eaf4935f0b01952c80005012f6538c27b7246375","source":{"kind":"arxiv","id":"2408.07989","version":1},"attestation_state":"computed","paper":{"title":"IIU: Independent Inference Units for Knowledge-based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gang Xiong, Jing Yu, Keke Gai, Yili Li","submitted_at":"2024-08-15T07:30:47Z","abstract_excerpt":"Knowledge-based visual question answering requires external knowledge beyond visible content to answer the question correctly. One limitation of existing methods is that they focus more on modeling the inter-modal and intra-modal correlations, which entangles complex multimodal clues by implicit embeddings and lacks interpretability and generalization ability. The key challenge to solve the above problem is to separate the information and process it separately at the functional level. By reusing each processing unit, the generalization ability of the model to deal with different data can be in"},"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":"2408.07989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:30:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2c5853fe7e4b388dc056943eebaa0e7945ea98cddd223a8cba1213c11c4e955","abstract_canon_sha256":"95b7c5a4546df713cf72b493f02894b5a8d2a908e07ca29d7e81454e430b5efa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:42.897154Z","signature_b64":"zPNS/SpiTG620PvsIz4Q63t45Ur/hnekPZKscNPc/k4UTTZWMidIaojkNOVutVsAwwc42oETJeiOyQ0/tFCoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e68668d6fea0a35ac01dac9eaf4935f0b01952c80005012f6538c27b7246375","last_reissued_at":"2026-07-05T08:55:42.896740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:42.896740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IIU: Independent Inference Units for Knowledge-based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gang Xiong, Jing Yu, Keke Gai, Yili Li","submitted_at":"2024-08-15T07:30:47Z","abstract_excerpt":"Knowledge-based visual question answering requires external knowledge beyond visible content to answer the question correctly. One limitation of existing methods is that they focus more on modeling the inter-modal and intra-modal correlations, which entangles complex multimodal clues by implicit embeddings and lacks interpretability and generalization ability. The key challenge to solve the above problem is to separate the information and process it separately at the functional level. By reusing each processing unit, the generalization ability of the model to deal with different data can be in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07989","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/2408.07989/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":"2408.07989","created_at":"2026-07-05T08:55:42.896797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07989v1","created_at":"2026-07-05T08:55:42.896797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07989","created_at":"2026-07-05T08:55:42.896797+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZUGNDLP5IFD","created_at":"2026-07-05T08:55:42.896797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZUGNDLP5IFDLLAB","created_at":"2026-07-05T08:55:42.896797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZUGNDLP","created_at":"2026-07-05T08:55:42.896797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4","json":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4.json","graph_json":"https://pith.science/api/pith-number/DZUGNDLP5IFDLLAB3LE6V5ETL4/graph.json","events_json":"https://pith.science/api/pith-number/DZUGNDLP5IFDLLAB3LE6V5ETL4/events.json","paper":"https://pith.science/paper/DZUGNDLP"},"agent_actions":{"view_html":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4","download_json":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4.json","view_paper":"https://pith.science/paper/DZUGNDLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07989&json=true","fetch_graph":"https://pith.science/api/pith-number/DZUGNDLP5IFDLLAB3LE6V5ETL4/graph.json","fetch_events":"https://pith.science/api/pith-number/DZUGNDLP5IFDLLAB3LE6V5ETL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4/action/storage_attestation","attest_author":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4/action/author_attestation","sign_citation":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4/action/citation_signature","submit_replication":"https://pith.science/pith/DZUGNDLP5IFDLLAB3LE6V5ETL4/action/replication_record"}},"created_at":"2026-07-05T08:55:42.896797+00:00","updated_at":"2026-07-05T08:55:42.896797+00:00"}