{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2SZTSMHKUWHTUJ4UJJC6K2RLAI","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":"8502d7847a56e4710fa398d521b6866bfeb783e641cebc303ba160f524fdefb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T12:47:30Z","title_canon_sha256":"b9cf2857acd71adf9902eebada5ba4ad494c0558fb1925896806f293fe4b68c5"},"schema_version":"1.0","source":{"id":"2606.31599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31599","created_at":"2026-07-01T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31599v1","created_at":"2026-07-01T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31599","created_at":"2026-07-01T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"2SZTSMHKUWHT","created_at":"2026-07-01T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"2SZTSMHKUWHTUJ4U","created_at":"2026-07-01T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"2SZTSMHK","created_at":"2026-07-01T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:ee193fd7fe68ba1d7a645093389c116e92fcdba7985b468e46ea438e05320030","target":"graph","created_at":"2026-07-01T01:18:08Z","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/2606.31599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making. We recognize that pruning visual tokens outside the grounding region greatly enhances medical reasoning. However, a united RL framework for active visual token pruning (VTP) and medical multimodal reasoning remains unestablished. Here, we propose a dual-stream RL framework, ViToS, to fulfill token pruning and question answering. ViToS trains one","authors_text":"Chunfeng Song, Jiamin Wu, Kaitao Chen, Mianxin Liu, Mu Zhou, Qihao Zheng, Shangquan Sun, Weiqian Zhao, Xiaosong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T12:47:30Z","title":"Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31599","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:eff4f4ecfbf96038736bb1c84aae4471f4f639440a2732ecdb37f8551e728730","target":"record","created_at":"2026-07-01T01:18:08Z","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":"8502d7847a56e4710fa398d521b6866bfeb783e641cebc303ba160f524fdefb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T12:47:30Z","title_canon_sha256":"b9cf2857acd71adf9902eebada5ba4ad494c0558fb1925896806f293fe4b68c5"},"schema_version":"1.0","source":{"id":"2606.31599","kind":"arxiv","version":1}},"canonical_sha256":"d4b33930eaa58f3a27944a45e56a2b0230d286353435923d7fa18df56e80065d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4b33930eaa58f3a27944a45e56a2b0230d286353435923d7fa18df56e80065d","first_computed_at":"2026-07-01T01:18:08.739021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:08.739021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ThRjSiToQsYFv/PFPPVnO/f3A14PO9FwCo7Ie3BxPgDAXiTblztzDfWGVsPZbktO994Za0QUQuAzBZ/hNdCmCg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:08.739456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eff4f4ecfbf96038736bb1c84aae4471f4f639440a2732ecdb37f8551e728730","sha256:ee193fd7fe68ba1d7a645093389c116e92fcdba7985b468e46ea438e05320030"],"state_sha256":"5091934e5a319c81a9099661bbb19ada1d5a07e4a1c6700ed88f22cfd2937b5f"}