{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6OGYIGJ35F5ZOCQ42PJRUH7PKH","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":"667959f78736fee0cff85b2f26119f89473f4ae8d7a1c08f0986554a899dedb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T12:42:09Z","title_canon_sha256":"06f537d9742a7c587460202be0123d23854b17d5fbdeab6189165e3c9485ccc3"},"schema_version":"1.0","source":{"id":"2606.17871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17871","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17871v1","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17871","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"6OGYIGJ35F5Z","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"6OGYIGJ35F5ZOCQ4","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"6OGYIGJ3","created_at":"2026-06-19T16:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:5a25fcd668c1d0bf96241d3939e4ec6d581c1d61a816dda8a73ccf1afbd2beb9","target":"graph","created_at":"2026-06-19T16:10:42Z","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/2606.17871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confid","authors_text":"Jinpeng Hu, Liu Liu, Li Zhu, Mengjia Li, Xiyang Sun, Yaxiong Wang, Yuchen Zhang, Yujiao Wu, Zhihao Cui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T12:42:09Z","title":"StepGuard: Guarding Web Navigation via Single-Step Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17871","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":"sha256:40dd9f39db2a4accb7a7c4d6c2c196b1d531a7873545855d00e2d4662cfe73d2","target":"record","created_at":"2026-06-19T16:10:42Z","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":"667959f78736fee0cff85b2f26119f89473f4ae8d7a1c08f0986554a899dedb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T12:42:09Z","title_canon_sha256":"06f537d9742a7c587460202be0123d23854b17d5fbdeab6189165e3c9485ccc3"},"schema_version":"1.0","source":{"id":"2606.17871","kind":"arxiv","version":1}},"canonical_sha256":"f38d84193be97b970a1cd3d31a1fef51eabb49fdd6b6aa1ab3dfa52fb601c815","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f38d84193be97b970a1cd3d31a1fef51eabb49fdd6b6aa1ab3dfa52fb601c815","first_computed_at":"2026-06-19T16:10:42.365376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:42.365376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+V732VW1RftcU0RPip+emUDw1pKdchOpx/IvIYF952yF17MEuR2xpdxRClAonp/5RE7WCO6uwl4pNUXJ9X8qAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:42.365785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40dd9f39db2a4accb7a7c4d6c2c196b1d531a7873545855d00e2d4662cfe73d2","sha256:5a25fcd668c1d0bf96241d3939e4ec6d581c1d61a816dda8a73ccf1afbd2beb9"],"state_sha256":"7fbd32ae36a9e29806a45ba7b534de4987b8ff67e094b8e4959d5ba480663e27"}