{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PB6J2J2DITER36HF3FJ4ODUGA","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":"ed927c4c152f0aee748d14ba314cd8832cb4b0871e71488a636e84ae0f5ca66c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T11:07:19Z","title_canon_sha256":"a6f1e831b5f7c0cba4e35848ede3d1c0192ad6eee8fdff52b3c82baeefe2026a"},"schema_version":"1.0","source":{"id":"2504.00654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00654","created_at":"2026-07-05T10:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00654v1","created_at":"2026-07-05T10:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00654","created_at":"2026-07-05T10:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"6PB6J2J2DITE","created_at":"2026-07-05T10:42:48Z"},{"alias_kind":"pith_short_16","alias_value":"6PB6J2J2DITER36H","created_at":"2026-07-05T10:42:48Z"},{"alias_kind":"pith_short_8","alias_value":"6PB6J2J2","created_at":"2026-07-05T10:42:48Z"}],"graph_snapshots":[{"event_id":"sha256:19513cc5cb5cafeb3f438c2cbd02bf634f6f4271d4d43ad4494561c5fc15aa67","target":"graph","created_at":"2026-07-05T10:42:48Z","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/2504.00654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher GPU memory usage and computational overhead. Images often contain more redundant information than text, and not all visual details are pertinent to specific questions. To address these challenges, we propose QG-VTC, a novel question-guided visual token compression method for MLLM-based VQA tasks. QG-VTC employs a pretrained text encoder and a learnable feed-","authors_text":"Chao Deng, Jian Xu, Lin-Lin Huang, Shuai Li, Xiao-Hui Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T11:07:19Z","title":"QG-VTC: Question-Guided Visual Token Compression in MLLMs for Efficient VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00654","kind":"arxiv","version":1},"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:ae6768693f6ebc3386db3ca8ceca8b3118fb3055db39f37986672442e99a3cc4","target":"record","created_at":"2026-07-05T10:42:48Z","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":"ed927c4c152f0aee748d14ba314cd8832cb4b0871e71488a636e84ae0f5ca66c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T11:07:19Z","title_canon_sha256":"a6f1e831b5f7c0cba4e35848ede3d1c0192ad6eee8fdff52b3c82baeefe2026a"},"schema_version":"1.0","source":{"id":"2504.00654","kind":"arxiv","version":1}},"canonical_sha256":"f3c3e4e93a1a2648efc72eca9e3874300c737c7e1793704bf386b3065a898a31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c3e4e93a1a2648efc72eca9e3874300c737c7e1793704bf386b3065a898a31","first_computed_at":"2026-07-05T10:42:48.301544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:48.301544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CXcpw0bZDoudGa6C92KmnHoRer9Ay6IL/UudsbS1TZeTjrolnzeyo6TBZyEkKlBrz6z2mHJjGXC7zcwBfnxMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:48.302064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae6768693f6ebc3386db3ca8ceca8b3118fb3055db39f37986672442e99a3cc4","sha256:19513cc5cb5cafeb3f438c2cbd02bf634f6f4271d4d43ad4494561c5fc15aa67"],"state_sha256":"4c1a83574fc2789ae247dac8390e4ad9b66821a78a4e4244b8c1d919733d9255"}