{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QSPMIAV2PFEOFX7C7L3N4MNKYL","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":"9b3fd152feacb0ff29d96fe568746fe22a603e17ea85c6212866b569b8486734","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T17:59:55Z","title_canon_sha256":"1fa5841651be76533687881151ee3966135e8c7e6b59f05948f29bde46b273e8"},"schema_version":"1.0","source":{"id":"2507.13348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13348","created_at":"2026-07-05T11:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13348v1","created_at":"2026-07-05T11:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13348","created_at":"2026-07-05T11:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"QSPMIAV2PFEO","created_at":"2026-07-05T11:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"QSPMIAV2PFEOFX7C","created_at":"2026-07-05T11:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"QSPMIAV2","created_at":"2026-07-05T11:38:59Z"}],"graph_snapshots":[{"event_id":"sha256:f6d65b9dfa09446b0737d70f5888f3bbd498e3308517df3ff313948cbdfeab60","target":"graph","created_at":"2026-07-05T11:38:59Z","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/2507.13348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the performance drops significantly in a small subset of OCR-related tasks, models still perform accurately in most other general VQA tasks with only 1/4 resolution. Therefore, we propose to dynamically process distinct samples with different resolutions, and present a new paradigm for visual token compress","authors_text":"Bei Yu, Hengshuang Zhao, Jiaya Jia, Junyi Li, Senqiao Yang, Xin Lai","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T17:59:55Z","title":"VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13348","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:bee56a6e9762eead479c3d0bfac00a54fee4c5da5eef3b925a2bb6a47b25f017","target":"record","created_at":"2026-07-05T11:38:59Z","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":"9b3fd152feacb0ff29d96fe568746fe22a603e17ea85c6212866b569b8486734","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T17:59:55Z","title_canon_sha256":"1fa5841651be76533687881151ee3966135e8c7e6b59f05948f29bde46b273e8"},"schema_version":"1.0","source":{"id":"2507.13348","kind":"arxiv","version":1}},"canonical_sha256":"849ec402ba7948e2dfe2faf6de31aac2d29052ccf88dfe7d7778be90804c8f33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"849ec402ba7948e2dfe2faf6de31aac2d29052ccf88dfe7d7778be90804c8f33","first_computed_at":"2026-07-05T11:38:59.604960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:59.604960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YbsNvB+2izvXuLMXB7LZEeK4GViKIXXDC7O/iTILVHCo/BFA0PiBd2sjz92SrSidX5De3lWkYg8Go5UMJ7uzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:59.605424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bee56a6e9762eead479c3d0bfac00a54fee4c5da5eef3b925a2bb6a47b25f017","sha256:f6d65b9dfa09446b0737d70f5888f3bbd498e3308517df3ff313948cbdfeab60"],"state_sha256":"d9ca9566bd555fdb73047e5d118430e35e25853c1d9ac275537bf42c63e0e933"}