{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VUH5ITOARGG2EXLIUGLJ6ECYKG","short_pith_number":"pith:VUH5ITOA","canonical_record":{"source":{"id":"2606.18448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T19:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"e9c9b1be37c85f2ea43f5266909d8e07f21599b88179b41204be3d40591a74c8","abstract_canon_sha256":"73cefb561e47a4c223af405eeba170b7d60e142cbe4ea3fa2c4c9282df0d7c16"},"schema_version":"1.0"},"canonical_sha256":"ad0fd44dc0898da25d68a1969f105851884e0eea8e14a9af7ac849d3f0c186f0","source":{"kind":"arxiv","id":"2606.18448","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18448","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18448v1","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18448","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"VUH5ITOARGG2","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"VUH5ITOARGG2EXLI","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"VUH5ITOA","created_at":"2026-06-19T16:11:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VUH5ITOARGG2EXLIUGLJ6ECYKG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.18448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T19:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"e9c9b1be37c85f2ea43f5266909d8e07f21599b88179b41204be3d40591a74c8","abstract_canon_sha256":"73cefb561e47a4c223af405eeba170b7d60e142cbe4ea3fa2c4c9282df0d7c16"},"schema_version":"1.0"},"canonical_sha256":"ad0fd44dc0898da25d68a1969f105851884e0eea8e14a9af7ac849d3f0c186f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:01.501076Z","signature_b64":"0I6U7z4lXqTGx8jHt4euC81DzpUgeqCw7WCdDd0xLaNdnpzaQ/0ExDBE7sCKj4Q3cOPEBtwdnSIhnOgVjPfTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad0fd44dc0898da25d68a1969f105851884e0eea8e14a9af7ac849d3f0c186f0","last_reissued_at":"2026-06-19T16:11:01.500653Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:01.500653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.18448","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0rm61XUW0TUIeUC7+dIDeQRL07G0zPlmYUS9Ks3mUGA5byaJvf20Mf+yFZBq36pY/qlgfXtyuRolhPfGF5bDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T09:48:36.220723Z"},"content_sha256":"8537af342e74fee88d3ef9ed5b1761b5f65e239a17edd64198783ab893aec34a","schema_version":"1.0","event_id":"sha256:8537af342e74fee88d3ef9ed5b1761b5f65e239a17edd64198783ab893aec34a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VUH5ITOARGG2EXLIUGLJ6ECYKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VISUALSKILL: Multimodal Skills for Computer-Use Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Andreas, Jiabao Ji, Li An, Qiucheng Wu, Shiyu Chang, Yang Zhang, Yujian Liu, Ziyan Jiang","submitted_at":"2026-06-16T19:57:07Z","abstract_excerpt":"Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks and unseen software. Existing skill libraries address this with reusable skills, but represent the skill artifact as text only, despite the visual nature of GUI interaction. We propose VISUALSKILL: a hierarchical multimodal skill, tailored to each target application and organised as a central index over per-topic files, which the agent consumes through a load_topic MCP tool that fetches the relevant topic's text and figures on demand. We construct each skill with a tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18448","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.18448/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5F3R3Xp5YeBN0zfyvWj4KgM99FE89pZ9cMj7qfASdkuOEO4AMMwZASBEq2iM2j+xj6WtEjdUdr28TeR6VoswBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T09:48:36.221090Z"},"content_sha256":"c805490feaeb4879416f40452fd7f3bc86edfe0a19fadc1ab7774660fe33fc23","schema_version":"1.0","event_id":"sha256:c805490feaeb4879416f40452fd7f3bc86edfe0a19fadc1ab7774660fe33fc23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/bundle.json","state_url":"https://pith.science/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T09:48:36Z","links":{"resolver":"https://pith.science/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG","bundle":"https://pith.science/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/bundle.json","state":"https://pith.science/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUH5ITOARGG2EXLIUGLJ6ECYKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VUH5ITOARGG2EXLIUGLJ6ECYKG","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":"73cefb561e47a4c223af405eeba170b7d60e142cbe4ea3fa2c4c9282df0d7c16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T19:57:07Z","title_canon_sha256":"e9c9b1be37c85f2ea43f5266909d8e07f21599b88179b41204be3d40591a74c8"},"schema_version":"1.0","source":{"id":"2606.18448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18448","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18448v1","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18448","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"VUH5ITOARGG2","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"VUH5ITOARGG2EXLI","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"VUH5ITOA","created_at":"2026-06-19T16:11:01Z"}],"graph_snapshots":[{"event_id":"sha256:c805490feaeb4879416f40452fd7f3bc86edfe0a19fadc1ab7774660fe33fc23","target":"graph","created_at":"2026-06-19T16:11:01Z","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/2606.18448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks and unseen software. Existing skill libraries address this with reusable skills, but represent the skill artifact as text only, despite the visual nature of GUI interaction. We propose VISUALSKILL: a hierarchical multimodal skill, tailored to each target application and organised as a central index over per-topic files, which the agent consumes through a load_topic MCP tool that fetches the relevant topic's text and figures on demand. We construct each skill with a tw","authors_text":"Jacob Andreas, Jiabao Ji, Li An, Qiucheng Wu, Shiyu Chang, Yang Zhang, Yujian Liu, Ziyan Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T19:57:07Z","title":"VISUALSKILL: Multimodal Skills for Computer-Use Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18448","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":"sha256:8537af342e74fee88d3ef9ed5b1761b5f65e239a17edd64198783ab893aec34a","target":"record","created_at":"2026-06-19T16:11:01Z","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":"73cefb561e47a4c223af405eeba170b7d60e142cbe4ea3fa2c4c9282df0d7c16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T19:57:07Z","title_canon_sha256":"e9c9b1be37c85f2ea43f5266909d8e07f21599b88179b41204be3d40591a74c8"},"schema_version":"1.0","source":{"id":"2606.18448","kind":"arxiv","version":1}},"canonical_sha256":"ad0fd44dc0898da25d68a1969f105851884e0eea8e14a9af7ac849d3f0c186f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad0fd44dc0898da25d68a1969f105851884e0eea8e14a9af7ac849d3f0c186f0","first_computed_at":"2026-06-19T16:11:01.500653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:01.500653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0I6U7z4lXqTGx8jHt4euC81DzpUgeqCw7WCdDd0xLaNdnpzaQ/0ExDBE7sCKj4Q3cOPEBtwdnSIhnOgVjPfTBA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:01.501076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8537af342e74fee88d3ef9ed5b1761b5f65e239a17edd64198783ab893aec34a","sha256:c805490feaeb4879416f40452fd7f3bc86edfe0a19fadc1ab7774660fe33fc23"],"state_sha256":"d3f3a0727ab10073677c36bc6eccbb1c7575545e759d59f09515c406194cabb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJY9RenXpxIDLZwXJAgRbBWQykrUOG1HvnQ974KI0tKjD+BCWwvd9bFQvgA5xtqX9MnDFyiDls7s9swGMfxPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T09:48:36.223056Z","bundle_sha256":"13e570423e9c38ef74794e0cfc111a5f10a18539c42cb36ff77e5af0ec6e4e41"}}