{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2DI52UWCA2IZ2PZVFARPFYGUBC","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":"291fa37a2175ed64bc48384f65eaed6b1765a7349f91d59402517b96e69e2517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:36:39Z","title_canon_sha256":"c3b6fb0d9606c83f3274d84276dad068b836abdcd9d662b6bf694e12093ee968"},"schema_version":"1.0","source":{"id":"2605.28774","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28774","created_at":"2026-05-28T02:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28774v1","created_at":"2026-05-28T02:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28774","created_at":"2026-05-28T02:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"2DI52UWCA2IZ","created_at":"2026-05-28T02:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"2DI52UWCA2IZ2PZV","created_at":"2026-05-28T02:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"2DI52UWC","created_at":"2026-05-28T02:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:8d5a133aa7b495c1eb5ac196142659bff48916aa1bb341a7eae6c331e2aee674","target":"graph","created_at":"2026-05-28T02:05:02Z","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/2605.28774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting Gap. Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training: tool use is attempted on only ~30% of rollouts, and when attempted, the tool-using rollouts with","authors_text":"Byung-Kwan Lee, Minki Kang, Pavlo Molchanov, Ryo Hachiuma, Shizhe Diao, Sung Ju Hwang, Yu-Chiang Frank Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:36:39Z","title":"Agent Explorative Policy Optimization for Multimodal Agentic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28774","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:d094f92050f1149f0d852a67a172407580a57a9a1191a93ba0a0f4250c379100","target":"record","created_at":"2026-05-28T02:05:02Z","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":"291fa37a2175ed64bc48384f65eaed6b1765a7349f91d59402517b96e69e2517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:36:39Z","title_canon_sha256":"c3b6fb0d9606c83f3274d84276dad068b836abdcd9d662b6bf694e12093ee968"},"schema_version":"1.0","source":{"id":"2605.28774","kind":"arxiv","version":1}},"canonical_sha256":"d0d1dd52c206919d3f352822f2e0d408b3d74bf0ff62c39e63f595929c50533c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0d1dd52c206919d3f352822f2e0d408b3d74bf0ff62c39e63f595929c50533c","first_computed_at":"2026-05-28T02:05:02.712770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:02.712770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SAXdCJHaeRO7VRT8Eg1g9ZFlqdWR7YMidlEoXGB77BLFHVKUmXHJjlhV5rw2247NprCHDJRtzkcNg63yiOqVDw==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:02.713209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28774","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d094f92050f1149f0d852a67a172407580a57a9a1191a93ba0a0f4250c379100","sha256:8d5a133aa7b495c1eb5ac196142659bff48916aa1bb341a7eae6c331e2aee674"],"state_sha256":"ea69120b91a74c35f6b99d4989150f49af350406fab4808ee56b5790f6114e82"}