{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WM2H6SE56AGRA65DSR655ICVB","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":"43569509a01fc33ee9f837d6a15e9923c458c3f4461246e45261ca1781bc03a6","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:39:12Z","title_canon_sha256":"420db2412d520e7eabdd046cff50e7ed45b876601d5cf6993c08fddb5e45e127"},"schema_version":"1.0","source":{"id":"2412.13662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13662","created_at":"2026-07-05T09:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13662v1","created_at":"2026-07-05T09:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13662","created_at":"2026-07-05T09:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"4WM2H6SE56AG","created_at":"2026-07-05T09:51:06Z"},{"alias_kind":"pith_short_16","alias_value":"4WM2H6SE56AGRA65","created_at":"2026-07-05T09:51:06Z"},{"alias_kind":"pith_short_8","alias_value":"4WM2H6SE","created_at":"2026-07-05T09:51:06Z"}],"graph_snapshots":[{"event_id":"sha256:b6b23c5fded58b36cc2f67ccc968525fc9e33e7869f0e42047671fd9a5c6648f","target":"graph","created_at":"2026-07-05T09:51:06Z","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/2412.13662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning policies from high-dimensional visual inputs, such as pixels and point clouds, is crucial in various applications. Visual reinforcement learning is a promising approach that directly trains policies from visual observations, although it faces challenges in sample efficiency and computational costs. This study conducts an empirical comparison of State-to-Visual DAgger, a two-stage framework that initially trains a state policy before adopting online imitation to learn a visual policy, and Visual RL across a diverse set of tasks. We evaluate both methods across 16 tasks from three bench","authors_text":"Hao Su, Litian Liang, Stanis{\\l}aw Wiktor Strzelecki, Tongzhou Mu, Xiu Yuan, Yunchao Yao, Zhaoyang Li","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:39:12Z","title":"When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13662","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":"sha256:166906aaba3ff3dbed4a981408e3cb28441023bd747537e5f7ff3697d61698e6","target":"record","created_at":"2026-07-05T09:51:06Z","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":"43569509a01fc33ee9f837d6a15e9923c458c3f4461246e45261ca1781bc03a6","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:39:12Z","title_canon_sha256":"420db2412d520e7eabdd046cff50e7ed45b876601d5cf6993c08fddb5e45e127"},"schema_version":"1.0","source":{"id":"2412.13662","kind":"arxiv","version":1}},"canonical_sha256":"e599a3fa44ef806883dd1ca3eef502a85ceb2020a28a58471022183adf27e95d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e599a3fa44ef806883dd1ca3eef502a85ceb2020a28a58471022183adf27e95d","first_computed_at":"2026-07-05T09:51:06.093078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:06.093078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LEXHdBivY4IAugYven3k6KspWhuU2yT0HgPQNuSI8ZCm5z+F3zbe/TL2ycBuiM8eDlneY7tghFccjnnUajlCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:06.093549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:166906aaba3ff3dbed4a981408e3cb28441023bd747537e5f7ff3697d61698e6","sha256:b6b23c5fded58b36cc2f67ccc968525fc9e33e7869f0e42047671fd9a5c6648f"],"state_sha256":"9df2c417c8166f63089f8e4e33dcde8646d5541a8a68435e3b97a8010a977f6c"}