{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3XM7CB6FR6XV52BSDRBPMI57WE","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":"bd649dd4f7baaa804d3b2c658e2f430307b7f451a100d92033b290a6f0bc9712","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T17:49:55Z","title_canon_sha256":"ce1dae3f371c6776216cc0df534245b6e4fe1869ee8a4b991d26b0c96e170d3b"},"schema_version":"1.0","source":{"id":"2406.11896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11896","created_at":"2026-07-05T08:33:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11896v1","created_at":"2026-07-05T08:33:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11896","created_at":"2026-07-05T08:33:52Z"},{"alias_kind":"pith_short_12","alias_value":"3XM7CB6FR6XV","created_at":"2026-07-05T08:33:52Z"},{"alias_kind":"pith_short_16","alias_value":"3XM7CB6FR6XV52BS","created_at":"2026-07-05T08:33:52Z"},{"alias_kind":"pith_short_8","alias_value":"3XM7CB6F","created_at":"2026-07-05T08:33:52Z"}],"graph_snapshots":[{"event_id":"sha256:88cd64743da6b4e256ff68ef2ad1a2f3d16b070496b10a34176f4f9c4b5da10d","target":"graph","created_at":"2026-07-05T08:33:52Z","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/2406.11896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training corpuses for vision language models (VLMs) typically lack sufficient amounts of decision-centric data. This renders off-the-shelf VLMs sub-optimal for decision-making tasks such as in-the-wild device control through graphical user interfaces (GUIs). While training with static demonstrations has shown some promise, we show that such methods fall short for controlling real GUIs due to their failure to deal with real-world stochasticity and non-stationarity not captured in static observational data. This paper introduces a novel autonomous RL approach, called DigiRL, for training in-the-","authors_text":"Alane Suhr, Aviral Kumar, Hao Bai, Jiayi Pan, Mert Cemri, Sergey Levine, Yifei Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T17:49:55Z","title":"DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11896","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":"sha256:74d6210b47c3e22a7fc09500ae384fa2836cd2b1f00d8380bb490301564362ca","target":"record","created_at":"2026-07-05T08:33:52Z","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":"bd649dd4f7baaa804d3b2c658e2f430307b7f451a100d92033b290a6f0bc9712","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T17:49:55Z","title_canon_sha256":"ce1dae3f371c6776216cc0df534245b6e4fe1869ee8a4b991d26b0c96e170d3b"},"schema_version":"1.0","source":{"id":"2406.11896","kind":"arxiv","version":1}},"canonical_sha256":"ddd9f107c58faf5ee8321c42f623bfb10e5957db36b6302e2e2bf044b3c49c24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddd9f107c58faf5ee8321c42f623bfb10e5957db36b6302e2e2bf044b3c49c24","first_computed_at":"2026-07-05T08:33:52.187067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:52.187067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4vkYcztuLtNCDb7x1DA6/ZBwk3Hu29cBv5w8Zv8MAa+BLGiL9cI3gnD4SNsL5HKCMeGaKDIcHB5IR3fXmXseAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:52.187535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74d6210b47c3e22a7fc09500ae384fa2836cd2b1f00d8380bb490301564362ca","sha256:88cd64743da6b4e256ff68ef2ad1a2f3d16b070496b10a34176f4f9c4b5da10d"],"state_sha256":"c2f46b7f8574b6b9e7b0eba500c8a4836667af5d3d517d7fe1a5138bac144358"}