{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJ3MKMRUKIAZBU5I2EGRM36TCM","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":"9697fb11454f2c789ee1b493d5c206cbde675b6174f424092442a3e75dec18ce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T02:39:03Z","title_canon_sha256":"679b9b27b6acf74dd25daf3499b20f91d15ec61ef19ddb15a70f5f158140ad88"},"schema_version":"1.0","source":{"id":"2505.12632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12632","created_at":"2026-07-05T11:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12632v1","created_at":"2026-07-05T11:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12632","created_at":"2026-07-05T11:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"GJ3MKMRUKIAZ","created_at":"2026-07-05T11:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"GJ3MKMRUKIAZBU5I","created_at":"2026-07-05T11:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"GJ3MKMRU","created_at":"2026-07-05T11:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:c42ace3bd0827d42743e770b4ce2a783352f7de00fde7b73e9a6a7ba6cfc4963","target":"graph","created_at":"2026-07-05T11:05:07Z","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/2505.12632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have sparked significant interest in developing GUI visual agents. We introduce MONDAY (Mobile OS Navigation Task Dataset for Agents from YouTube), a large-scale dataset of 313K annotated frames from 20K instructional videos capturing diverse real-world mobile OS navigation across multiple platforms. Models that include MONDAY in their pre-training phases demonstrate robust cross-platform generalization capabilities, consistently outperforming models trained on existing single OS datasets while achieving an a","authors_text":"Dong-Ki Kim, Honglak Lee, Kyunghoon Bae, Lajanugen Logeswaran, Sungryull Sohn, Tiange Luo, Yeda Song, Yunseok Jang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T02:39:03Z","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12632","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":"sha256:65c3c9e2f584703b864b76b76ed54b66fc8a739fe7efc06acff88ab12ce6e8f3","target":"record","created_at":"2026-07-05T11:05:07Z","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":"9697fb11454f2c789ee1b493d5c206cbde675b6174f424092442a3e75dec18ce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T02:39:03Z","title_canon_sha256":"679b9b27b6acf74dd25daf3499b20f91d15ec61ef19ddb15a70f5f158140ad88"},"schema_version":"1.0","source":{"id":"2505.12632","kind":"arxiv","version":1}},"canonical_sha256":"3276c53234520190d3a8d10d166fd3131a8d96f2741a8c1d063b8030908cced0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3276c53234520190d3a8d10d166fd3131a8d96f2741a8c1d063b8030908cced0","first_computed_at":"2026-07-05T11:05:07.371194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:07.371194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lIg8ZroyidO8WY+TCXZn2iQ15pQJVZ7+CT9bHfbEXNVxsm75UsUxR1X8nuqdtg/1TVNTtMLEGcCYQRk/gDZMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:07.371749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65c3c9e2f584703b864b76b76ed54b66fc8a739fe7efc06acff88ab12ce6e8f3","sha256:c42ace3bd0827d42743e770b4ce2a783352f7de00fde7b73e9a6a7ba6cfc4963"],"state_sha256":"d30b906a582324bb829a1a3c63f55bb059067ac528c7eddaa7211eafac3a374e"}