{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S73DKDWNVNXD3DAJOGCFV2MCRZ","short_pith_number":"pith:S73DKDWN","schema_version":"1.0","canonical_sha256":"97f6350ecdab6e3d8c0971845ae9828e63d9b6a33e86fb8e17c06ee506a4ea51","source":{"kind":"arxiv","id":"2310.09147","version":1},"attestation_state":"computed","paper":{"title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Dan Guo, Jia Li, Meng Wang, Sheng Zhou, Xun Yang","submitted_at":"2023-10-13T14:39:34Z","abstract_excerpt":"Text-based visual question answering (TextVQA) faces the significant challenge of avoiding redundant relational inference. To be specific, a large number of detected objects and optical character recognition (OCR) tokens result in rich visual relationships. Existing works take all visual relationships into account for answer prediction. However, there are three observations: (1) a single subject in the images can be easily detected as multiple objects with distinct bounding boxes (considered repetitive objects). The associations between these repetitive objects are superfluous for answer reaso"},"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":"2310.09147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-10-13T14:39:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"424ddca1c320a8f3b3740419a211000eee54ab3189af89c2648e4d4bd47cf58d","abstract_canon_sha256":"916430aba65bffb40965d7e50a9a0160ecf5dfe23f675c5caa32a08926fd7797"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:40.508927Z","signature_b64":"RRAp3ekeWmEE6Z+wBNw8j/IA9OfFaG7MfV5gjTuodJdRwlNauAfdVfUXBcXW4rv7OeBIaMtnzJ5Bgk/0qdcKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97f6350ecdab6e3d8c0971845ae9828e63d9b6a33e86fb8e17c06ee506a4ea51","last_reissued_at":"2026-07-05T07:00:40.508407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:40.508407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Dan Guo, Jia Li, Meng Wang, Sheng Zhou, Xun Yang","submitted_at":"2023-10-13T14:39:34Z","abstract_excerpt":"Text-based visual question answering (TextVQA) faces the significant challenge of avoiding redundant relational inference. To be specific, a large number of detected objects and optical character recognition (OCR) tokens result in rich visual relationships. Existing works take all visual relationships into account for answer prediction. However, there are three observations: (1) a single subject in the images can be easily detected as multiple objects with distinct bounding boxes (considered repetitive objects). The associations between these repetitive objects are superfluous for answer reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09147","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/2310.09147/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":"2310.09147","created_at":"2026-07-05T07:00:40.508471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09147v1","created_at":"2026-07-05T07:00:40.508471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09147","created_at":"2026-07-05T07:00:40.508471+00:00"},{"alias_kind":"pith_short_12","alias_value":"S73DKDWNVNXD","created_at":"2026-07-05T07:00:40.508471+00:00"},{"alias_kind":"pith_short_16","alias_value":"S73DKDWNVNXD3DAJ","created_at":"2026-07-05T07:00:40.508471+00:00"},{"alias_kind":"pith_short_8","alias_value":"S73DKDWN","created_at":"2026-07-05T07:00:40.508471+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/S73DKDWNVNXD3DAJOGCFV2MCRZ","json":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ.json","graph_json":"https://pith.science/api/pith-number/S73DKDWNVNXD3DAJOGCFV2MCRZ/graph.json","events_json":"https://pith.science/api/pith-number/S73DKDWNVNXD3DAJOGCFV2MCRZ/events.json","paper":"https://pith.science/paper/S73DKDWN"},"agent_actions":{"view_html":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ","download_json":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ.json","view_paper":"https://pith.science/paper/S73DKDWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09147&json=true","fetch_graph":"https://pith.science/api/pith-number/S73DKDWNVNXD3DAJOGCFV2MCRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/S73DKDWNVNXD3DAJOGCFV2MCRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ/action/storage_attestation","attest_author":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ/action/author_attestation","sign_citation":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ/action/citation_signature","submit_replication":"https://pith.science/pith/S73DKDWNVNXD3DAJOGCFV2MCRZ/action/replication_record"}},"created_at":"2026-07-05T07:00:40.508471+00:00","updated_at":"2026-07-05T07:00:40.508471+00:00"}