{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UN5IUIUMYQDSP4CKJJ4NQBG5N7","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":"9f0e4738740b1cccf6a18f4aa2101aa32eb879f15adebd972c0911e1bf49fdde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T13:33:11Z","title_canon_sha256":"a057c9bcff11d65b7d46ecbe7e0c7332d138c77a710450c8a50af00ccb8cb59e"},"schema_version":"1.0","source":{"id":"2608.03649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03649","created_at":"2026-08-05T01:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03649v1","created_at":"2026-08-05T01:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03649","created_at":"2026-08-05T01:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"UN5IUIUMYQDS","created_at":"2026-08-05T01:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"UN5IUIUMYQDSP4CK","created_at":"2026-08-05T01:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"UN5IUIUM","created_at":"2026-08-05T01:36:49Z"}],"graph_snapshots":[{"event_id":"sha256:02df440336a062838b988391e29abf892751972748a87fa6032bd8eb235aa739","target":"graph","created_at":"2026-08-05T01:36:49Z","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/2608.03649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead, shared work, and the operators each policy can avoid. A stage-level decomposition reconciles these components with measured end-to-end latency. In a 30-example pilot, the two tested autoregressive probes remain slower than Full despite state reuse. A lightweight post-vision predictor yields paired confidence intervals below zero on RTX 3090 and A100 and remains significant after a conservative all-pairs Holm correction. A pre-vision image-size ","authors_text":"Hao Dou, Ruiwen Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T13:33:11Z","title":"When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03649","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":"sha256:9d22c884202cce96f47d634113505907edebd0d3dc5df1d65c2eeee8e529e865","target":"record","created_at":"2026-08-05T01:36:49Z","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":"9f0e4738740b1cccf6a18f4aa2101aa32eb879f15adebd972c0911e1bf49fdde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T13:33:11Z","title_canon_sha256":"a057c9bcff11d65b7d46ecbe7e0c7332d138c77a710450c8a50af00ccb8cb59e"},"schema_version":"1.0","source":{"id":"2608.03649","kind":"arxiv","version":1}},"canonical_sha256":"a37a8a228cc40727f04a4a78d804dd6fcf3f0cd81d5cbd4d382e2176389ef668","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37a8a228cc40727f04a4a78d804dd6fcf3f0cd81d5cbd4d382e2176389ef668","first_computed_at":"2026-08-05T01:36:49.206328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:49.206328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r5i+ic1PJdzNAwLs/bW9dHVIvFEmwY7lLWYQ9YeQoP91fk+HQ3CwxSC3ye0zMt7XApnc9fj2AogKUPwqQ5vNDg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:49.207940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d22c884202cce96f47d634113505907edebd0d3dc5df1d65c2eeee8e529e865","sha256:02df440336a062838b988391e29abf892751972748a87fa6032bd8eb235aa739"],"state_sha256":"97e964257a886faf1bf5cfa7d46ab1f74b1e8d5dd3c027e3289df1cb73b21f7c"}