{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4WM2H6SE56AGRA65DSR655ICVB","short_pith_number":"pith:4WM2H6SE","canonical_record":{"source":{"id":"2412.13662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:39:12Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"420db2412d520e7eabdd046cff50e7ed45b876601d5cf6993c08fddb5e45e127","abstract_canon_sha256":"43569509a01fc33ee9f837d6a15e9923c458c3f4461246e45261ca1781bc03a6"},"schema_version":"1.0"},"canonical_sha256":"e599a3fa44ef806883dd1ca3eef502a85ceb2020a28a58471022183adf27e95d","source":{"kind":"arxiv","id":"2412.13662","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4WM2H6SE56AGRA65DSR655ICVB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T09:39:12Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"420db2412d520e7eabdd046cff50e7ed45b876601d5cf6993c08fddb5e45e127","abstract_canon_sha256":"43569509a01fc33ee9f837d6a15e9923c458c3f4461246e45261ca1781bc03a6"},"schema_version":"1.0"},"canonical_sha256":"e599a3fa44ef806883dd1ca3eef502a85ceb2020a28a58471022183adf27e95d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:06.093549Z","signature_b64":"LEXHdBivY4IAugYven3k6KspWhuU2yT0HgPQNuSI8ZCm5z+F3zbe/TL2ycBuiM8eDlneY7tghFccjnnUajlCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e599a3fa44ef806883dd1ca3eef502a85ceb2020a28a58471022183adf27e95d","last_reissued_at":"2026-07-05T09:51:06.093078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:06.093078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13662","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":"2026-07-05T09:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNpQ+vX8LidR3VONsERPUaUzq1jGqV+Pm8D3ZIEr/AqOR70BGU1hS7hPzjkDmY743dhx5PEIt93/KrYo4FxXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:52:39.164973Z"},"content_sha256":"166906aaba3ff3dbed4a981408e3cb28441023bd747537e5f7ff3697d61698e6","schema_version":"1.0","event_id":"sha256:166906aaba3ff3dbed4a981408e3cb28441023bd747537e5f7ff3697d61698e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4WM2H6SE56AGRA65DSR655ICVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hao Su, Litian Liang, Stanis{\\l}aw Wiktor Strzelecki, Tongzhou Mu, Xiu Yuan, Yunchao Yao, Zhaoyang Li","submitted_at":"2024-12-18T09:39:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13662","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/2412.13662/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":"2026-07-05T09:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8oQmDkFcD1s/J2PHdgJWO2hts4jolWUWrs9soziEmNnQLRqp7q6aO98U23sktxH73qUhiWYFTsZ+jmX47dVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:52:39.165517Z"},"content_sha256":"b6b23c5fded58b36cc2f67ccc968525fc9e33e7869f0e42047671fd9a5c6648f","schema_version":"1.0","event_id":"sha256:b6b23c5fded58b36cc2f67ccc968525fc9e33e7869f0e42047671fd9a5c6648f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WM2H6SE56AGRA65DSR655ICVB/bundle.json","state_url":"https://pith.science/pith/4WM2H6SE56AGRA65DSR655ICVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WM2H6SE56AGRA65DSR655ICVB/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":"2026-08-18T11:52:39Z","links":{"resolver":"https://pith.science/pith/4WM2H6SE56AGRA65DSR655ICVB","bundle":"https://pith.science/pith/4WM2H6SE56AGRA65DSR655ICVB/bundle.json","state":"https://pith.science/pith/4WM2H6SE56AGRA65DSR655ICVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WM2H6SE56AGRA65DSR655ICVB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLi2Hdhzji5gSGT4gH6faGo0yxZRYyM3BpvwBQZazN4yDvt7TLSvQvvlrbJ9yb0vkKuIqgTyY+9gTDdf3bx/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:52:39.169113Z","bundle_sha256":"3048396b41254e49047208f61a1f87fd21b6b740ca1ee4906e2d1a2218833899"}}