{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BCC2U5KAPOIXA3U5MXUUBK35XY","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":"3386ecce2da3abed05cf7aaf390f1651e6a25519798a2da764d461d278687570","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:13:04Z","title_canon_sha256":"64ba929f0ec968f7f5859866f9603a088e8c0c261c74c9ced60b8f22f6a422d2"},"schema_version":"1.0","source":{"id":"2605.16359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16359","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16359v1","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16359","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_12","alias_value":"BCC2U5KAPOIX","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_16","alias_value":"BCC2U5KAPOIXA3U5","created_at":"2026-05-20T00:02:18Z"},{"alias_kind":"pith_short_8","alias_value":"BCC2U5KA","created_at":"2026-05-20T00:02:18Z"}],"graph_snapshots":[{"event_id":"sha256:c48ac0f1ad0b50ac99c8a9919a2eb72b7c2c089e4db17fc19b25eb1bc07023de","target":"graph","created_at":"2026-05-20T00:02:18Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T20:40:55.520349Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16359/integrity.json","findings":[],"snapshot_sha256":"5af3bb9a32bf23724a76d334d56a4f4329175dd90c9d67a64bddfa49b1c616d1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling question: as multimodal models grow, how many visual tokens are actually needed, and how should they be allocated under a fixed visual token budget? Existing training-free pruning methods typically answer this with one-shot proxies such as decoder attention, visual similarity, or conditional diversity. We argue that visual token pruning is better viewed as task-conditioned evidence search, especially under aggressive comp","authors_text":"Daling Wang, Junzhao Huang, Shi Feng, Xiaocui Yang, Yifei Zhang, Yijie Huang, Yiqun Zhang, Yongkang Liu, Zhuoyue Jia, Zihan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:13:04Z","title":"How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16359","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":"sha256:972b7ddcb26b96f248907e65a5fa0a1244bfcbfe42750491967b07b7e3cdb419","target":"record","created_at":"2026-05-20T00:02:18Z","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":"3386ecce2da3abed05cf7aaf390f1651e6a25519798a2da764d461d278687570","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:13:04Z","title_canon_sha256":"64ba929f0ec968f7f5859866f9603a088e8c0c261c74c9ced60b8f22f6a422d2"},"schema_version":"1.0","source":{"id":"2605.16359","kind":"arxiv","version":1}},"canonical_sha256":"0885aa75407b91706e9d65e940ab7dbe3a259334ed215f812f1fa3c08b8663ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0885aa75407b91706e9d65e940ab7dbe3a259334ed215f812f1fa3c08b8663ff","first_computed_at":"2026-05-20T00:02:18.289362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:18.289362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MIy/AzPDTS74yTOiWCTyW62BosFg50HBtf36pe0+0Xbxl9KZTcZqguBf9yw32BXyvZa6qA6msif3x6U1xqvBAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:18.289904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:972b7ddcb26b96f248907e65a5fa0a1244bfcbfe42750491967b07b7e3cdb419","sha256:c48ac0f1ad0b50ac99c8a9919a2eb72b7c2c089e4db17fc19b25eb1bc07023de"],"state_sha256":"961cbca38d0f5ca4458b519ecdc6c3b306598bfd7aab2707bed415bc8aa5c6fd"}