{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PBZ6R74JWSMHJ6S7BV2KTJUQMV","short_pith_number":"pith:PBZ6R74J","canonical_record":{"source":{"id":"2607.24112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:54:08Z","cross_cats_sorted":[],"title_canon_sha256":"df2cbb1dc139564b74ba335d298dad8533fa300d926cf016316e7248ae71e63b","abstract_canon_sha256":"87d1ce8a42bfa182f6732cb0f6e14dec6b8465fc3c4009532a6d6f45843dbafe"},"schema_version":"1.0"},"canonical_sha256":"7873e8ff89b49874fa5f0d74a9a690655e198cfe57d582a92f86d6724635ce78","source":{"kind":"arxiv","id":"2607.24112","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24112","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24112v1","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24112","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"PBZ6R74JWSMH","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"PBZ6R74JWSMHJ6S7","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"PBZ6R74J","created_at":"2026-07-28T01:23:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PBZ6R74JWSMHJ6S7BV2KTJUQMV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:54:08Z","cross_cats_sorted":[],"title_canon_sha256":"df2cbb1dc139564b74ba335d298dad8533fa300d926cf016316e7248ae71e63b","abstract_canon_sha256":"87d1ce8a42bfa182f6732cb0f6e14dec6b8465fc3c4009532a6d6f45843dbafe"},"schema_version":"1.0"},"canonical_sha256":"7873e8ff89b49874fa5f0d74a9a690655e198cfe57d582a92f86d6724635ce78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:45.805737Z","signature_b64":"8JNnnRWq3k9rttkoVVt2sq+RLh2a3EH7nsoxqLI83UsPQxu8s4Zvtnl/Z3utMugPZwNkOhbHtmCv811eQu9fAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7873e8ff89b49874fa5f0d74a9a690655e198cfe57d582a92f86d6724635ce78","last_reissued_at":"2026-07-28T01:23:45.804840Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:45.804840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24112","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":"2026-07-28T01:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SKonxksUXvmDX/KjrtMJ9Tz4Yc2lLhmVo2jTdnNHwustcX/ZDXpFvqccbd0GAJAxqqhbo47lwbD11LElG8vOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:42:39.927126Z"},"content_sha256":"3ca040b9e5798d3459074d6be52f25602357f99ead1c4d35965694c31210f160","schema_version":"1.0","event_id":"sha256:3ca040b9e5798d3459074d6be52f25602357f99ead1c4d35965694c31210f160"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PBZ6R74JWSMHJ6S7BV2KTJUQMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling GUI Agents with Visual State Transitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Wu, Chao Du, Haonan Wang, Kaixin Li, Longxu Dou, Meng Fang, Michael Qizhe Shieh, Tianyu Pang, Xiangyan Liu","submitted_at":"2026-07-27T07:54:08Z","abstract_excerpt":"We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state transitions by jointly optimizing inverse dynamics (predicting actions from state changes) and forward dynamics (predicting next states from current states and actions). This optimization equips the model with better action-grounded visual representations and an internal world model of GUI dynamics. When subsequently fine-tuned on trajectories with task instructions, our STP-trained models consistently outperform baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24112","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/2607.24112/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":"2026-07-28T01:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jZP2GkV1QlIweHGevIYBijCYILjVtD/PuDkpWdd98PDXmNoUnwm7Fw6L68qorB++H3J87sOrIgvhu2tubUiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:42:39.928028Z"},"content_sha256":"0e49404ee9ad3421a03dba3796ebe82fe0b819dab057083ca0a240712707ba89","schema_version":"1.0","event_id":"sha256:0e49404ee9ad3421a03dba3796ebe82fe0b819dab057083ca0a240712707ba89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/bundle.json","state_url":"https://pith.science/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/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":"2026-08-04T12:42:39Z","links":{"resolver":"https://pith.science/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV","bundle":"https://pith.science/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/bundle.json","state":"https://pith.science/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBZ6R74JWSMHJ6S7BV2KTJUQMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PBZ6R74JWSMHJ6S7BV2KTJUQMV","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":"87d1ce8a42bfa182f6732cb0f6e14dec6b8465fc3c4009532a6d6f45843dbafe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:54:08Z","title_canon_sha256":"df2cbb1dc139564b74ba335d298dad8533fa300d926cf016316e7248ae71e63b"},"schema_version":"1.0","source":{"id":"2607.24112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24112","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24112v1","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24112","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"PBZ6R74JWSMH","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"PBZ6R74JWSMHJ6S7","created_at":"2026-07-28T01:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"PBZ6R74J","created_at":"2026-07-28T01:23:45Z"}],"graph_snapshots":[{"event_id":"sha256:0e49404ee9ad3421a03dba3796ebe82fe0b819dab057083ca0a240712707ba89","target":"graph","created_at":"2026-07-28T01:23:45Z","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/2607.24112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state transitions by jointly optimizing inverse dynamics (predicting actions from state changes) and forward dynamics (predicting next states from current states and actions). This optimization equips the model with better action-grounded visual representations and an internal world model of GUI dynamics. When subsequently fine-tuned on trajectories with task instructions, our STP-trained models consistently outperform baseline","authors_text":"Biao Wu, Chao Du, Haonan Wang, Kaixin Li, Longxu Dou, Meng Fang, Michael Qizhe Shieh, Tianyu Pang, Xiangyan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:54:08Z","title":"Scaling GUI Agents with Visual State Transitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24112","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":"sha256:3ca040b9e5798d3459074d6be52f25602357f99ead1c4d35965694c31210f160","target":"record","created_at":"2026-07-28T01:23:45Z","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":"87d1ce8a42bfa182f6732cb0f6e14dec6b8465fc3c4009532a6d6f45843dbafe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:54:08Z","title_canon_sha256":"df2cbb1dc139564b74ba335d298dad8533fa300d926cf016316e7248ae71e63b"},"schema_version":"1.0","source":{"id":"2607.24112","kind":"arxiv","version":1}},"canonical_sha256":"7873e8ff89b49874fa5f0d74a9a690655e198cfe57d582a92f86d6724635ce78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7873e8ff89b49874fa5f0d74a9a690655e198cfe57d582a92f86d6724635ce78","first_computed_at":"2026-07-28T01:23:45.804840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:45.804840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8JNnnRWq3k9rttkoVVt2sq+RLh2a3EH7nsoxqLI83UsPQxu8s4Zvtnl/Z3utMugPZwNkOhbHtmCv811eQu9fAg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:45.805737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ca040b9e5798d3459074d6be52f25602357f99ead1c4d35965694c31210f160","sha256:0e49404ee9ad3421a03dba3796ebe82fe0b819dab057083ca0a240712707ba89"],"state_sha256":"cdebffa997bc25ea51a081ef876ac662c91b32cb2eb23cc5adebd177c3af4cee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJJh6XkrfntMlPb7pMRLRX6uvlJNViIZaFjlrn0rphz1oWQ46sVZf5/GG4cBRjIEEd2lGG5Z9/wIUNzqa9jEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:42:39.934696Z","bundle_sha256":"2d6fda05d48ab7ad342270b038364fc2280a3148db0f960fc95f51ec5fa33dfe"}}