{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:STES65VEH3WJFNJNDSCWC2D55Z","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":"fd33e5b9aef2b2d782897829063f35e8999188508d7e1390fbcff7b329755e16","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T05:44:07Z","title_canon_sha256":"c28f2c3ed83bdbb43bf3c1f30ceefcbc7b951e74f1937dac260a306f56862785"},"schema_version":"1.0","source":{"id":"2608.06411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06411","created_at":"2026-08-10T01:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06411v1","created_at":"2026-08-10T01:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06411","created_at":"2026-08-10T01:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"STES65VEH3WJ","created_at":"2026-08-10T01:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"STES65VEH3WJFNJN","created_at":"2026-08-10T01:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"STES65VE","created_at":"2026-08-10T01:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:77eb76bb968c7136191e93d8743c4ed1f17f8b286cc2308bbde488efb61cb69c","target":"graph","created_at":"2026-08-10T01:10:36Z","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/2608.06411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens. Visual token pruning can reduce this cost, but requires accurate token importance estimates. Recent studies have demonstrated that text-to-vision attention from middle language model layers can effectively guide visual token pruning, typically using attention from a predefined middle layer to select the visual tokens to retain. Two problems therefore remain. First, our analysis shows that the layer whose atte","authors_text":"Deqing Wang, Hao Geng, Minjun Yu, Shuang Li, Tao Deng, Yuyao Sun","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T05:44:07Z","title":"Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06411","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":"sha256:80e22e0f1fd586cbec61c2e044c86f2ba7cd0f59d9bb05fb7f74bf01bf4faf75","target":"record","created_at":"2026-08-10T01:10:36Z","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":"fd33e5b9aef2b2d782897829063f35e8999188508d7e1390fbcff7b329755e16","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T05:44:07Z","title_canon_sha256":"c28f2c3ed83bdbb43bf3c1f30ceefcbc7b951e74f1937dac260a306f56862785"},"schema_version":"1.0","source":{"id":"2608.06411","kind":"arxiv","version":1}},"canonical_sha256":"94c92f76a43eec92b52d1c8561687dee5b519d15dd54ead8b1014c172eb52df7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94c92f76a43eec92b52d1c8561687dee5b519d15dd54ead8b1014c172eb52df7","first_computed_at":"2026-08-10T01:10:36.207495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:10:36.207495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i0mcozBgFmR2VAmJiXavzu4Hz+zfkgQmWJTfwuLIMrD5//T12+nHNjI3oPcC7vTQwWcXtlhb+m1VwK/Pee72Bg==","signature_status":"signed_v1","signed_at":"2026-08-10T01:10:36.209790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80e22e0f1fd586cbec61c2e044c86f2ba7cd0f59d9bb05fb7f74bf01bf4faf75","sha256:77eb76bb968c7136191e93d8743c4ed1f17f8b286cc2308bbde488efb61cb69c"],"state_sha256":"5eaf8a5fb3ab2afabebc25e29546b5b7a8b9b5054338c9b145cf7832db49bb20"}