{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PB6J2J2DITER36HF3FJ4ODUGA","short_pith_number":"pith:6PB6J2J2","canonical_record":{"source":{"id":"2504.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T11:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"a6f1e831b5f7c0cba4e35848ede3d1c0192ad6eee8fdff52b3c82baeefe2026a","abstract_canon_sha256":"ed927c4c152f0aee748d14ba314cd8832cb4b0871e71488a636e84ae0f5ca66c"},"schema_version":"1.0"},"canonical_sha256":"f3c3e4e93a1a2648efc72eca9e3874300c737c7e1793704bf386b3065a898a31","source":{"kind":"arxiv","id":"2504.00654","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PB6J2J2DITER36HF3FJ4ODUGA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T11:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"a6f1e831b5f7c0cba4e35848ede3d1c0192ad6eee8fdff52b3c82baeefe2026a","abstract_canon_sha256":"ed927c4c152f0aee748d14ba314cd8832cb4b0871e71488a636e84ae0f5ca66c"},"schema_version":"1.0"},"canonical_sha256":"f3c3e4e93a1a2648efc72eca9e3874300c737c7e1793704bf386b3065a898a31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:48.302064Z","signature_b64":"CXcpw0bZDoudGa6C92KmnHoRer9Ay6IL/UudsbS1TZeTjrolnzeyo6TBZyEkKlBrz6z2mHJjGXC7zcwBfnxMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c3e4e93a1a2648efc72eca9e3874300c737c7e1793704bf386b3065a898a31","last_reissued_at":"2026-07-05T10:42:48.301544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:48.301544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00654","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0CcPp2p2YDwG04FeWZGfIzTXX8U4Kwj/FuQ0SC79QE8hJzuGM2Jx0guHgIHaHV8cRmRx+WsU4lkwWh0L0IZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:55:07.848595Z"},"content_sha256":"ae6768693f6ebc3386db3ca8ceca8b3118fb3055db39f37986672442e99a3cc4","schema_version":"1.0","event_id":"sha256:ae6768693f6ebc3386db3ca8ceca8b3118fb3055db39f37986672442e99a3cc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PB6J2J2DITER36HF3FJ4ODUGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QG-VTC: Question-Guided Visual Token Compression in MLLMs for Efficient VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Deng, Jian Xu, Lin-Lin Huang, Shuai Li, Xiao-Hui Li","submitted_at":"2025-04-01T11:07:19Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00654","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/2504.00654/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9lTB9oxm85Fptg63cOIIxvHEMa+u0qXoTdHOflPFW5UYc6/5ePfMzCsUl7Dqt9RUE7GCBGrtj6xwZkjxQ+I9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:55:07.849409Z"},"content_sha256":"19513cc5cb5cafeb3f438c2cbd02bf634f6f4271d4d43ad4494561c5fc15aa67","schema_version":"1.0","event_id":"sha256:19513cc5cb5cafeb3f438c2cbd02bf634f6f4271d4d43ad4494561c5fc15aa67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PB6J2J2DITER36HF3FJ4ODUGA/bundle.json","state_url":"https://pith.science/pith/6PB6J2J2DITER36HF3FJ4ODUGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PB6J2J2DITER36HF3FJ4ODUGA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T03:55:07Z","links":{"resolver":"https://pith.science/pith/6PB6J2J2DITER36HF3FJ4ODUGA","bundle":"https://pith.science/pith/6PB6J2J2DITER36HF3FJ4ODUGA/bundle.json","state":"https://pith.science/pith/6PB6J2J2DITER36HF3FJ4ODUGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PB6J2J2DITER36HF3FJ4ODUGA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cLIk9tI4Yg/rXKuVReuz8T5SWrf6kanbtPCBX1/G3TaY9RDNx7bib84QopMreTrS0ps/uwpBBXdwfalL71KNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:55:07.855126Z","bundle_sha256":"84748c6e5c53f5e8fc0ece496d8a69dd288aa1cf9c8fb1850f07d537a5d3cf79"}}