{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZEOLA2IPGZO7UGK6HF3X332GKU","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":"930e35fd582285942dceb5fa9562a07bc9caf05e21990b8d68956745b8b882d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T09:36:02Z","title_canon_sha256":"505cdc1d366c3663027ddd7e20ad9befc6434368132fc1542bbc02f0f5102eb6"},"schema_version":"1.0","source":{"id":"2411.17773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17773","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17773v2","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17773","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZEOLA2IPGZO7","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZEOLA2IPGZO7UGK6","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZEOLA2IP","created_at":"2026-07-05T09:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:6b3ed9dbf646233427fec48bb21844b19cfe74e00bd3ced1a49190e6a68eceaf","target":"graph","created_at":"2026-07-05T09:43:12Z","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/2411.17773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a range of downstream applications, such as visual question answering and image captioning. However, the substantial computational costs associated with processing high-resolution images and videos pose a barrier to their broader adoption. To address this challenge, compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs. While existing methods conduct token reduction in the fea","authors_text":"Chuanyang Zheng, Han Shi, Hong Cheng, Minbin Huang, Runhui Huang, Xiangguo Sun, Xin Jiang, Yimeng Chen, Zhenguo Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T09:36:02Z","title":"Efficient Multi-modal Large Language Models via Visual Token Grouping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17773","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":"sha256:04e7fb0ca9c33ce38622820f2c8eff57da1f415710024eef03933048e4d3b80e","target":"record","created_at":"2026-07-05T09:43:12Z","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":"930e35fd582285942dceb5fa9562a07bc9caf05e21990b8d68956745b8b882d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T09:36:02Z","title_canon_sha256":"505cdc1d366c3663027ddd7e20ad9befc6434368132fc1542bbc02f0f5102eb6"},"schema_version":"1.0","source":{"id":"2411.17773","kind":"arxiv","version":2}},"canonical_sha256":"c91cb0690f365dfa195e39777def46551390b73a57036729fd1273efc0114618","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c91cb0690f365dfa195e39777def46551390b73a57036729fd1273efc0114618","first_computed_at":"2026-07-05T09:43:12.086060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:12.086060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tf3qsUov8LCWdvc0XbVR/FNw+OlSjYaPqauHrVORQ6OSSGXXP1jZjAEfNgQ/RuqDAe/sM6/TBpMclcUxqZiVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:12.086578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04e7fb0ca9c33ce38622820f2c8eff57da1f415710024eef03933048e4d3b80e","sha256:6b3ed9dbf646233427fec48bb21844b19cfe74e00bd3ced1a49190e6a68eceaf"],"state_sha256":"5f8df5c2463811ca054459ddf3443ac87269eb5e2c2bbf3dd5fbe77990cd37dd"}