{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYXH2YLO22543DEBW2ZBCVDDHS","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":"9427d8afa03fe9ca7e57402556e3b2650024c497e6b34164107982e53d7b5038","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T09:31:35Z","title_canon_sha256":"def3ba2855a3f99513fe8c4c08dfe22c3be2d4975a456aa9d9a7d36b8280ff15"},"schema_version":"1.0","source":{"id":"2503.21307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21307","created_at":"2026-07-05T10:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21307v1","created_at":"2026-07-05T10:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21307","created_at":"2026-07-05T10:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"TYXH2YLO2254","created_at":"2026-07-05T10:40:22Z"},{"alias_kind":"pith_short_16","alias_value":"TYXH2YLO22543DEB","created_at":"2026-07-05T10:40:22Z"},{"alias_kind":"pith_short_8","alias_value":"TYXH2YLO","created_at":"2026-07-05T10:40:22Z"}],"graph_snapshots":[{"event_id":"sha256:31eb71aa34f15cdd2a033d1bb5ec0afabec555d90894c3dde994260269b63837","target":"graph","created_at":"2026-07-05T10:40:22Z","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/2503.21307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most multimodal large language models (MLLMs) treat visual tokens as \"a sequence of text\", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand for computational resources and time. In this paper, we propose InternVL-X, which outperforms the InternVL model in both performance and efficiency by incorporating three visual token compression methods. First, we propose a novel vision-language projector, PVTC. This component integrates adjacent visual embeddings to form a local query and utilizes the transf","authors_text":"Dongchen Lu, Huo Cao, Jianliang Zeng, Leping Huang, Mao Shu, Yuyao Sun, Zilu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T09:31:35Z","title":"InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21307","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":"sha256:2b518dce47abc014fcc283ac4a28cab71dd4dc87b65d06d3caa3242df9331687","target":"record","created_at":"2026-07-05T10:40:22Z","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":"9427d8afa03fe9ca7e57402556e3b2650024c497e6b34164107982e53d7b5038","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T09:31:35Z","title_canon_sha256":"def3ba2855a3f99513fe8c4c08dfe22c3be2d4975a456aa9d9a7d36b8280ff15"},"schema_version":"1.0","source":{"id":"2503.21307","kind":"arxiv","version":1}},"canonical_sha256":"9e2e7d616ed6bbcd8c81b6b21154633c8aad241d180744578a8d2247d66e7d1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e2e7d616ed6bbcd8c81b6b21154633c8aad241d180744578a8d2247d66e7d1d","first_computed_at":"2026-07-05T10:40:22.930707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:22.930707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9VrXNLykfgTsenyUx6SiLy0gYrEyzUYyhBdx0DimeU2ZYZO+4cLrgKJ/1SW1hR2VzDR7nKz66aiLzNKw1rXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:22.931181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b518dce47abc014fcc283ac4a28cab71dd4dc87b65d06d3caa3242df9331687","sha256:31eb71aa34f15cdd2a033d1bb5ec0afabec555d90894c3dde994260269b63837"],"state_sha256":"5b94745e0de12a7ea80d9c50a2068a87d9160b7cd9b5bdbdce346e1a222c9ebc"}