{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WUMGFHF7GIFE3ULOYHBKVKWMWB","short_pith_number":"pith:WUMGFHF7","canonical_record":{"source":{"id":"2605.14747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:14:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"4de21e821c8b9dcaec4e084b7de3893cffdf6782b32b50f30fabe91765bf2145","abstract_canon_sha256":"6a462e79e0aee246b3ca97a287bce0096693626664a775fe991e3c9c0f6c7e98"},"schema_version":"1.0"},"canonical_sha256":"b518629cbf320a4dd16ec1c2aaaaccb0603fbf6f3f8ba9f1203aafaf3eae50e3","source":{"kind":"arxiv","id":"2605.14747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14747","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14747v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14747","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"WUMGFHF7GIFE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WUMGFHF7GIFE3ULO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WUMGFHF7","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WUMGFHF7GIFE3ULOYHBKVKWMWB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:14:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"4de21e821c8b9dcaec4e084b7de3893cffdf6782b32b50f30fabe91765bf2145","abstract_canon_sha256":"6a462e79e0aee246b3ca97a287bce0096693626664a775fe991e3c9c0f6c7e98"},"schema_version":"1.0"},"canonical_sha256":"b518629cbf320a4dd16ec1c2aaaaccb0603fbf6f3f8ba9f1203aafaf3eae50e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.885020Z","signature_b64":"Ywu3K52kQeumaufx67YWmrUa1PEVYh/fisdwgkuUphqGdNwzyxa7q+/r3vdx3bdYMedQjG23xRq9pZ/LsdAWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b518629cbf320a4dd16ec1c2aaaaccb0603fbf6f3f8ba9f1203aafaf3eae50e3","last_reissued_at":"2026-05-17T23:38:58.884347Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.884347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14747","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":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlZhfT/cyK9zw9wbOYHjJD9z856IZa/E2phXdhkM2Nrjv0KJIe84no0XA2i5e3gh6/UJNrJOf8Jfur0A/nI4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:32:34.362712Z"},"content_sha256":"1c645fa2ad6ee9ba5600f7c0ea479043b4cd8505377191523627b9a59e743c0f","schema_version":"1.0","event_id":"sha256:1c645fa2ad6ee9ba5600f7c0ea479043b4cd8505377191523627b9a59e743c0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WUMGFHF7GIFE3ULOYHBKVKWMWB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Ye, Feifan Song, Hao Tian, Lei Li, Shuhao Gu, Sujian Li, Weimin Xiong, Zihao Yue","submitted_at":"2026-05-14T12:14:24Z","abstract_excerpt":"Recent advances in multimodal large language models have driven growing interest in graphical user interface (GUI) agents, yet their generalization remains constrained by the scarcity of large-scale training data spanning diverse real-world applications. Existing datasets rely heavily on costly manual annotations and are typically confined to narrow domains. To address this challenge, we propose Video2GUI, a fully automated framework that extracts grounded GUI interaction trajectories directly from unlabeled Internet videos. Video2GUI employs a coarse-to-fine filtering strategy to identify hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14747","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":""},"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":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALV1hiUi/5LzPVvXzYiqesIhU9f44cQkCQRj/FTM+qsXnw/J9qLBB9WA3ES284DhatH/gKo4qPrVtpRmowsrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:32:34.363063Z"},"content_sha256":"1e6fd0f96095da66c507acb3a788faabda0f1336ff9b9ef078adfe2cb8812e71","schema_version":"1.0","event_id":"sha256:1e6fd0f96095da66c507acb3a788faabda0f1336ff9b9ef078adfe2cb8812e71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/bundle.json","state_url":"https://pith.science/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/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":"2026-06-02T00:32:34Z","links":{"resolver":"https://pith.science/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB","bundle":"https://pith.science/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/bundle.json","state":"https://pith.science/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUMGFHF7GIFE3ULOYHBKVKWMWB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WUMGFHF7GIFE3ULOYHBKVKWMWB","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":"6a462e79e0aee246b3ca97a287bce0096693626664a775fe991e3c9c0f6c7e98","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:14:24Z","title_canon_sha256":"4de21e821c8b9dcaec4e084b7de3893cffdf6782b32b50f30fabe91765bf2145"},"schema_version":"1.0","source":{"id":"2605.14747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14747","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14747v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14747","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"WUMGFHF7GIFE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WUMGFHF7GIFE3ULO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WUMGFHF7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1e6fd0f96095da66c507acb3a788faabda0f1336ff9b9ef078adfe2cb8812e71","target":"graph","created_at":"2026-05-17T23:38:58Z","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"},"paper":{"abstract_excerpt":"Recent advances in multimodal large language models have driven growing interest in graphical user interface (GUI) agents, yet their generalization remains constrained by the scarcity of large-scale training data spanning diverse real-world applications. Existing datasets rely heavily on costly manual annotations and are typically confined to narrow domains. To address this challenge, we propose Video2GUI, a fully automated framework that extracts grounded GUI interaction trajectories directly from unlabeled Internet videos. Video2GUI employs a coarse-to-fine filtering strategy to identify hig","authors_text":"Bowen Ye, Feifan Song, Hao Tian, Lei Li, Shuhao Gu, Sujian Li, Weimin Xiong, Zihao Yue","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:14:24Z","title":"Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14747","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":"sha256:1c645fa2ad6ee9ba5600f7c0ea479043b4cd8505377191523627b9a59e743c0f","target":"record","created_at":"2026-05-17T23:38:58Z","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":"6a462e79e0aee246b3ca97a287bce0096693626664a775fe991e3c9c0f6c7e98","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T12:14:24Z","title_canon_sha256":"4de21e821c8b9dcaec4e084b7de3893cffdf6782b32b50f30fabe91765bf2145"},"schema_version":"1.0","source":{"id":"2605.14747","kind":"arxiv","version":1}},"canonical_sha256":"b518629cbf320a4dd16ec1c2aaaaccb0603fbf6f3f8ba9f1203aafaf3eae50e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b518629cbf320a4dd16ec1c2aaaaccb0603fbf6f3f8ba9f1203aafaf3eae50e3","first_computed_at":"2026-05-17T23:38:58.884347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:58.884347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ywu3K52kQeumaufx67YWmrUa1PEVYh/fisdwgkuUphqGdNwzyxa7q+/r3vdx3bdYMedQjG23xRq9pZ/LsdAWAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:58.885020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c645fa2ad6ee9ba5600f7c0ea479043b4cd8505377191523627b9a59e743c0f","sha256:1e6fd0f96095da66c507acb3a788faabda0f1336ff9b9ef078adfe2cb8812e71"],"state_sha256":"2fbcc76e69b8b58e1295eeda762d3222b98484a1094ef69e600f69fdd68ae357"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7u+CT5gLW+S6bz2jIU7hDYjiTHawuBgB9bTu0KoYhNHDa1POQcn1F1KLNdhKNIve5Kgew9evH0Bo8wKM8L/6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T00:32:34.365099Z","bundle_sha256":"4c4cc3f92383f6fff06600be2a1d2d5f5707ecbeb0aada5f597106f6a550da36"}}