{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CB5EVLIPWM5YPP7UQ4XKKZBX5E","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":"be04ba50d5032824705f93cc2b5deea2ba5cad221c27f0db9996a70b78703d85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T19:22:43Z","title_canon_sha256":"096d66cdab65bead6f1b93768adedf3e60a917094b643129707d111e062660d3"},"schema_version":"1.0","source":{"id":"2606.01414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01414","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01414v1","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01414","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"CB5EVLIPWM5Y","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"CB5EVLIPWM5YPP7U","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"CB5EVLIP","created_at":"2026-06-02T02:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:12b74007bce89378baec97bd16b99056ec50dd901f478c6071ecd50c7c8f94eb","target":"graph","created_at":"2026-06-02T02:04:32Z","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/2606.01414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reusable skills are a key mechanism for extending agent capabilities, allowing agents to accumulate experience and solve increasingly complex tasks. Yet most existing skill-learning methods store reusable experience as text-only assets, such as instructions, reasoning traces, or summarized trajectories. We argue that this text-only paradigm creates a fundamental bottleneck for visual-centric tasks, where reusable knowledge often depends on spatial layout, visual grounding, fine-grained appearance, and localized state changes. To address this limitation, we propose \\textbf{\\NAME}, a multimodal ","authors_text":"Binxiao Xu, Bocheng Zou, Hang Hua, Ruichuan An","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T19:22:43Z","title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01414","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":"sha256:78b2527859619899a967adad1340dffd9728ed4fa0c6123f0bc7a1fcbae71cc7","target":"record","created_at":"2026-06-02T02:04:32Z","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":"be04ba50d5032824705f93cc2b5deea2ba5cad221c27f0db9996a70b78703d85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T19:22:43Z","title_canon_sha256":"096d66cdab65bead6f1b93768adedf3e60a917094b643129707d111e062660d3"},"schema_version":"1.0","source":{"id":"2606.01414","kind":"arxiv","version":1}},"canonical_sha256":"107a4aad0fb33b87bff4872ea56437e91f048fc92cc451792ac24e0e54d4514a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"107a4aad0fb33b87bff4872ea56437e91f048fc92cc451792ac24e0e54d4514a","first_computed_at":"2026-06-02T02:04:32.679125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:32.679125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cA1t2K9m9BCjhT6zN/uFq0mAQMtBsBWytUA94bX1VXCPMc6YaHkDHAd3g9DgjgjuV2j2mGgVH7lV7HhgnCHjBg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:32.679484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78b2527859619899a967adad1340dffd9728ed4fa0c6123f0bc7a1fcbae71cc7","sha256:12b74007bce89378baec97bd16b99056ec50dd901f478c6071ecd50c7c8f94eb"],"state_sha256":"57358c32b69687e6f841fe3ba23ebb42ffb9f12102dd72f60c12a4044c0d7249"}