{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K22FT5T2B3WTFQF36UQUFAHKFE","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":"99ad11b6ed6df93337877a291500e49a228e39907880ec74b5a1f36eea53b936","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T13:11:26Z","title_canon_sha256":"26c2eb1fc64b3ed31d38ae5f12c0cddb11749478ffe2b3a1cc06bb0d4478ed29"},"schema_version":"1.0","source":{"id":"2607.16326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16326","created_at":"2026-07-21T00:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16326v1","created_at":"2026-07-21T00:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16326","created_at":"2026-07-21T00:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"K22FT5T2B3WT","created_at":"2026-07-21T00:20:12Z"},{"alias_kind":"pith_short_16","alias_value":"K22FT5T2B3WTFQF3","created_at":"2026-07-21T00:20:12Z"},{"alias_kind":"pith_short_8","alias_value":"K22FT5T2","created_at":"2026-07-21T00:20:12Z"}],"graph_snapshots":[{"event_id":"sha256:ad2571e5f40f373089fc9b08c234e84ba4128fed4ffa9e9e6596af6b2e1f8cb7","target":"graph","created_at":"2026-07-21T00:20:12Z","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/2607.16326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning methods either operate before the LLM using text-agnostic heuristics or prune inside the LLM at the cost of efficiency and noisy cross-modal attention. To address these limitations, we propose CRISP, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context. CRISP works in a two-stage pipeline: Stage 1 first identifies text-aligned visual tok","authors_text":"Baoquan Zhao, Juncen Guo, Mengyang Zhao, Rui Zhu, Wei Zhou, Xiaolei Chen, Xu Li, Yi Zheng, Yuxuan Liang, Zhe Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T13:11:26Z","title":"CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16326","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":"sha256:76999b89524c6d99c82408b50022fd790722b3a7e94ddccb22bc7cbc4d105a23","target":"record","created_at":"2026-07-21T00:20:12Z","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":"99ad11b6ed6df93337877a291500e49a228e39907880ec74b5a1f36eea53b936","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T13:11:26Z","title_canon_sha256":"26c2eb1fc64b3ed31d38ae5f12c0cddb11749478ffe2b3a1cc06bb0d4478ed29"},"schema_version":"1.0","source":{"id":"2607.16326","kind":"arxiv","version":1}},"canonical_sha256":"56b459f67a0eed32c0bbf5214280ea292b94c8a9a964b157e84119230a7381c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56b459f67a0eed32c0bbf5214280ea292b94c8a9a964b157e84119230a7381c1","first_computed_at":"2026-07-21T00:20:12.537561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:12.537561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYICHbJ6MREjfQbw+jczbgn+dhK9DWEnBp4v9Jwkef3edsIY8Li3xb3WyJyG1QAWHRuwNxA2mnFeAmsOluEkBw==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:12.538477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76999b89524c6d99c82408b50022fd790722b3a7e94ddccb22bc7cbc4d105a23","sha256:ad2571e5f40f373089fc9b08c234e84ba4128fed4ffa9e9e6596af6b2e1f8cb7"],"state_sha256":"370d3cfb52ad778fdabb009e68e78f971a31801beefd3bb610f36267f0226b8b"}