{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RIDDJEKRVBTA4FXEOESHXQ36WD","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":"65ca66a5fe4e213689330460f9d4c9445c387386a200bcc7fe6df3005249c6f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T15:11:39Z","title_canon_sha256":"666d0a1f7cf2c7bb5cb18b77f3d6c697f9004d38a133c74675a769b08cd2ab12"},"schema_version":"1.0","source":{"id":"2409.07331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07331","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07331v2","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07331","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"RIDDJEKRVBTA","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"RIDDJEKRVBTA4FXE","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"RIDDJEKR","created_at":"2026-07-05T10:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:1546584cafdcd280ca3377771c1de97e4440a72531d1bf73305cabc69a019043","target":"graph","created_at":"2026-07-05T10:08:21Z","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/2409.07331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated great performance on visual question answering (VQA). When it comes to knowledge-based Visual Question Answering (KB-VQA), MLLMs may lack the specialized domain knowledge needed to answer questions, necessitating the retrieval of necessary information from external knowledge sources. Previous works like Retrival-Augmented VQA-v2 (RAVQA-v2) focus on utilizing as much input information, such as image-based textual descriptions and retrieved knowledge, as possible to improve performance, but they all overlook the issue that with the numbe","authors_text":"Chun Yuan, Hao Zhang, Jieming Zhu, Rui Zhang, Weixi Weng, Xiaojun Meng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T15:11:39Z","title":"Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07331","kind":"arxiv","version":2},"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:f86cb085dca2945e8c038239d0e21163fe192b843cd9d8afc94a706a709d2638","target":"record","created_at":"2026-07-05T10:08:21Z","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":"65ca66a5fe4e213689330460f9d4c9445c387386a200bcc7fe6df3005249c6f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T15:11:39Z","title_canon_sha256":"666d0a1f7cf2c7bb5cb18b77f3d6c697f9004d38a133c74675a769b08cd2ab12"},"schema_version":"1.0","source":{"id":"2409.07331","kind":"arxiv","version":2}},"canonical_sha256":"8a06349151a8660e16e471247bc37eb0f05610e3426e299623d55b909f27a917","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a06349151a8660e16e471247bc37eb0f05610e3426e299623d55b909f27a917","first_computed_at":"2026-07-05T10:08:21.001444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:21.001444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5y1GnhEUypQVni2UdZwehq/2x9EAT9CbrqBqhNX91vnwd/rbmxeggp/jqVGbTiTr3bsPvX6J5d28RsMfeDCpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:21.002005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f86cb085dca2945e8c038239d0e21163fe192b843cd9d8afc94a706a709d2638","sha256:1546584cafdcd280ca3377771c1de97e4440a72531d1bf73305cabc69a019043"],"state_sha256":"3b2e87fbd771e0eec411b09bf3f67f6296bf3dae3feef1f5393c1941c9cc2ad3"}